summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.mailmap2
-rw-r--r--Documentation/block/inline-encryption.rst451
-rw-r--r--Documentation/core-api/cachetlb.rst6
-rw-r--r--Documentation/core-api/mm-api.rst5
-rw-r--r--Documentation/devicetree/bindings/mfd/brcm,cru.yaml11
-rw-r--r--Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml33
-rw-r--r--Documentation/filesystems/index.rst1
-rw-r--r--Documentation/filesystems/locks.rst17
-rw-r--r--Documentation/filesystems/netfs_library.rst2
-rw-r--r--Documentation/networking/devlink/ice.rst9
-rw-r--r--Documentation/networking/mctp.rst10
-rw-r--r--Documentation/userspace-api/ioctl/ioctl-number.rst1
-rw-r--r--MAINTAINERS18
-rw-r--r--Makefile4
-rw-r--r--arch/arc/include/asm/cacheflush.h1
-rw-r--r--arch/arm/Kconfig1
-rw-r--r--arch/arm/boot/compressed/decompress.c3
-rw-r--r--arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts2
-rw-r--r--arch/arm/include/asm/cacheflush.h1
-rw-r--r--arch/arm/include/asm/uaccess.h4
-rw-r--r--arch/arm/kernel/head.S4
-rw-r--r--arch/arm/kernel/traps.c2
-rw-r--r--arch/arm/kernel/vmlinux-xip.lds.S6
-rw-r--r--arch/arm/mm/proc-macros.S1
-rw-r--r--arch/arm/probes/kprobes/core.c2
-rw-r--r--arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts2
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts8
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi8
-rw-r--r--arch/arm64/boot/dts/qcom/sm8250.dtsi3
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/gfp.h1
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c13
-rw-r--r--arch/arm64/kvm/hyp/nvhe/page_alloc.c15
-rw-r--r--arch/arm64/kvm/mmu.c6
-rw-r--r--arch/arm64/net/bpf_jit_comp.c5
-rw-r--r--arch/m68k/emu/nfblock.c9
-rw-r--r--arch/m68k/include/asm/cacheflush_mm.h1
-rw-r--r--arch/mips/include/asm/cacheflush.h2
-rw-r--r--arch/nds32/include/asm/cacheflush.h1
-rw-r--r--arch/nds32/kernel/ftrace.c2
-rw-r--r--arch/nios2/include/asm/cacheflush.h3
-rw-r--r--arch/nios2/include/asm/irqflags.h4
-rw-r--r--arch/nios2/include/asm/registers.h2
-rw-r--r--arch/nios2/platform/Kconfig.platform1
-rw-r--r--arch/parisc/include/asm/cacheflush.h3
-rw-r--r--arch/powerpc/kernel/idle_book3s.S10
-rw-r--r--arch/powerpc/kernel/smp.c2
-rw-r--r--arch/powerpc/platforms/pseries/iommu.c27
-rw-r--r--arch/riscv/Kconfig6
-rw-r--r--arch/riscv/include/asm/kasan.h3
-rw-r--r--arch/riscv/kernel/head.S1
-rw-r--r--arch/riscv/mm/kasan_init.c14
-rw-r--r--arch/riscv/net/bpf_jit_core.c8
-rw-r--r--arch/s390/kvm/gaccess.c12
-rw-r--r--arch/s390/kvm/intercept.c4
-rw-r--r--arch/s390/kvm/interrupt.c5
-rw-r--r--arch/s390/kvm/kvm-s390.c1
-rw-r--r--arch/sh/include/asm/cacheflush.h3
-rw-r--r--arch/um/drivers/ubd_kern.c13
-rw-r--r--arch/x86/crypto/sm4-aesni-avx-asm_64.S6
-rw-r--r--arch/x86/crypto/sm4-aesni-avx2-asm_64.S6
-rw-r--r--arch/x86/include/asm/kvm_host.h5
-rw-r--r--arch/x86/kvm/lapic.c20
-rw-r--r--arch/x86/kvm/mmu/mmu.c6
-rw-r--r--arch/x86/kvm/svm/sev.c29
-rw-r--r--arch/x86/kvm/svm/svm.h2
-rw-r--r--arch/x86/kvm/vmx/vmx.c32
-rw-r--r--arch/x86/kvm/x86.c189
-rw-r--r--arch/x86/kvm/xen.c27
-rw-r--r--arch/xtensa/include/asm/cacheflush.h5
-rw-r--r--arch/xtensa/platforms/iss/simdisk.c13
-rw-r--r--block/Makefile4
-rw-r--r--block/bdev.c8
-rw-r--r--block/bfq-cgroup.c12
-rw-r--r--block/bio.c44
-rw-r--r--block/blk-cgroup.c10
-rw-r--r--block/blk-core.c28
-rw-r--r--block/blk-crypto-fallback.c118
-rw-r--r--block/blk-crypto-profile.c565
-rw-r--r--block/blk-crypto.c29
-rw-r--r--block/blk-flush.c12
-rw-r--r--block/blk-ia-ranges.c348
-rw-r--r--block/blk-integrity.c4
-rw-r--r--block/blk-merge.c17
-rw-r--r--block/blk-mq-debugfs.c2
-rw-r--r--block/blk-mq-sched.c4
-rw-r--r--block/blk-mq-sched.h12
-rw-r--r--block/blk-mq-tag.c7
-rw-r--r--block/blk-mq-tag.h23
-rw-r--r--block/blk-mq.c337
-rw-r--r--block/blk-mq.h24
-rw-r--r--block/blk-settings.c20
-rw-r--r--block/blk-sysfs.c26
-rw-r--r--block/blk-wbt.c3
-rw-r--r--block/blk.h8
-rw-r--r--block/fops.c188
-rw-r--r--block/genhd.c48
-rw-r--r--block/keyslot-manager.c579
-rw-r--r--block/partitions/core.c1
-rw-r--r--drivers/acpi/power.c7
-rw-r--r--drivers/acpi/tables.c3
-rw-r--r--drivers/ata/sata_mv.c4
-rw-r--r--drivers/base/regmap/regcache-rbtree.c7
-rw-r--r--drivers/block/Kconfig23
-rw-r--r--drivers/block/Makefile1
-rw-r--r--drivers/block/amiflop.c7
-rw-r--r--drivers/block/aoe/aoeblk.c19
-rw-r--r--drivers/block/ataflop.c109
-rw-r--r--drivers/block/cryptoloop.c206
-rw-r--r--drivers/block/drbd/drbd_main.c6
-rw-r--r--drivers/block/floppy.c34
-rw-r--r--drivers/block/loop.c416
-rw-r--r--drivers/block/loop.h30
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c6
-rw-r--r--drivers/block/n64cart.c12
-rw-r--r--drivers/block/nbd.c176
-rw-r--r--drivers/block/null_blk/main.c192
-rw-r--r--drivers/block/null_blk/null_blk.h6
-rw-r--r--drivers/block/paride/pcd.c312
-rw-r--r--drivers/block/paride/pd.c144
-rw-r--r--drivers/block/paride/pf.c236
-rw-r--r--drivers/block/pktcdvd.c4
-rw-r--r--drivers/block/rbd.c6
-rw-r--r--drivers/block/rnbd/rnbd-clt.c13
-rw-r--r--drivers/block/rsxx/core.c4
-rw-r--r--drivers/block/rsxx/dev.c12
-rw-r--r--drivers/block/swim.c35
-rw-r--r--drivers/block/swim3.c5
-rw-r--r--drivers/block/sx8.c15
-rw-r--r--drivers/block/virtio_blk.c12
-rw-r--r--drivers/block/xen-blkfront.c8
-rw-r--r--drivers/cdrom/gdrom.c7
-rw-r--r--drivers/char/tpm/Kconfig2
-rw-r--r--drivers/char/tpm/tpm2-space.c3
-rw-r--r--drivers/char/tpm/tpm_tis_core.c26
-rw-r--r--drivers/char/tpm/tpm_tis_core.h4
-rw-r--r--drivers/char/tpm/tpm_tis_spi_main.c1
-rw-r--r--drivers/clk/clk-composite.c10
-rw-r--r--drivers/gpio/gpio-mlxbf2.c5
-rw-r--r--drivers/gpio/gpio-xgs-iproc.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nv.c2
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c20
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c29
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c13
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c6
-rw-r--r--drivers/gpu/drm/amd/display/include/dal_asic_id.h2
-rw-r--r--drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c6
-rw-r--r--drivers/gpu/drm/ast/ast_mode.c18
-rw-r--r--drivers/gpu/drm/drm_panel_orientation_quirks.c12
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c3
-rw-r--r--drivers/gpu/drm/i915/gt/intel_timeline.c4
-rw-r--r--drivers/gpu/drm/i915/i915_reg.h8
-rw-r--r--drivers/gpu/drm/i915/i915_trace.h7
-rw-r--r--drivers/gpu/drm/i915/intel_dram.c30
-rw-r--r--drivers/gpu/drm/kmb/kmb_crtc.c41
-rw-r--r--drivers/gpu/drm/kmb/kmb_drv.c2
-rw-r--r--drivers/gpu/drm/kmb/kmb_drv.h10
-rw-r--r--drivers/gpu/drm/kmb/kmb_dsi.c25
-rw-r--r--drivers/gpu/drm/kmb/kmb_dsi.h2
-rw-r--r--drivers/gpu/drm/kmb/kmb_plane.c43
-rw-r--r--drivers/gpu/drm/kmb/kmb_plane.h6
-rw-r--r--drivers/gpu/drm/msm/adreno/a6xx_gpu.c7
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.h4
-rw-r--r--drivers/gpu/drm/msm/msm_gpu_devfreq.c3
-rw-r--r--drivers/gpu/drm/mxsfb/mxsfb_drv.c6
-rw-r--r--drivers/gpu/drm/panel/panel-ilitek-ili9881c.c12
-rw-r--r--drivers/gpu/drm/selftests/test-drm_damage_helper.c1
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_util.c1
-rw-r--r--drivers/hv/hyperv_vmbus.h1
-rw-r--r--drivers/infiniband/core/sa_query.c5
-rw-r--r--drivers/infiniband/hw/hfi1/pio.c9
-rw-r--r--drivers/infiniband/hw/irdma/uk.c4
-rw-r--r--drivers/infiniband/hw/irdma/verbs.c8
-rw-r--r--drivers/infiniband/hw/irdma/ws.c13
-rw-r--r--drivers/infiniband/hw/mlx5/mr.c2
-rw-r--r--drivers/infiniband/hw/mlx5/qp.c2
-rw-r--r--drivers/infiniband/hw/qedr/qedr.h1
-rw-r--r--drivers/infiniband/hw/qedr/qedr_iw_cm.c2
-rw-r--r--drivers/infiniband/hw/qedr/verbs.c5
-rw-r--r--drivers/infiniband/hw/qib/qib_user_sdma.c33
-rw-r--r--drivers/infiniband/sw/rdmavt/qp.c2
-rw-r--r--drivers/isdn/hardware/mISDN/hfcpci.c8
-rw-r--r--drivers/md/bcache/bcache.h6
-rw-r--r--drivers/md/bcache/bcache_ondisk.h (renamed from include/uapi/linux/bcache.h)4
-rw-r--r--drivers/md/bcache/bset.h2
-rw-r--r--drivers/md/bcache/btree.c2
-rw-r--r--drivers/md/bcache/debug.c15
-rw-r--r--drivers/md/bcache/features.c2
-rw-r--r--drivers/md/bcache/features.h3
-rw-r--r--drivers/md/bcache/io.c16
-rw-r--r--drivers/md/bcache/request.c6
-rw-r--r--drivers/md/bcache/super.c89
-rw-r--r--drivers/md/bcache/sysfs.c2
-rw-r--r--drivers/md/bcache/sysfs.h18
-rw-r--r--drivers/md/bcache/util.h25
-rw-r--r--drivers/md/dm-core.h4
-rw-r--r--drivers/md/dm-table.c168
-rw-r--r--drivers/md/dm.c14
-rw-r--r--drivers/md/md.c92
-rw-r--r--drivers/md/md.h2
-rw-r--r--drivers/md/raid1.c13
-rw-r--r--drivers/md/raid10.c2
-rw-r--r--drivers/md/raid5.c7
-rw-r--r--drivers/mmc/core/crypto.c11
-rw-r--r--drivers/mmc/host/Kconfig2
-rw-r--r--drivers/mmc/host/cqhci-core.c3
-rw-r--r--drivers/mmc/host/cqhci-crypto.c33
-rw-r--r--drivers/mmc/host/dw_mmc-exynos.c14
-rw-r--r--drivers/mmc/host/mtk-sd.c38
-rw-r--r--drivers/mmc/host/sdhci-esdhc-imx.c16
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c29
-rw-r--r--drivers/mmc/host/sdhci.c6
-rw-r--r--drivers/mmc/host/tmio_mmc_core.c17
-rw-r--r--drivers/mmc/host/vub300.c18
-rw-r--r--drivers/mtd/mtd_blkdevs.c6
-rw-r--r--drivers/net/can/m_can/m_can_platform.c14
-rw-r--r--drivers/net/can/rcar/rcar_can.c20
-rw-r--r--drivers/net/can/sja1000/peak_pci.c9
-rw-r--r--drivers/net/can/usb/peak_usb/pcan_usb_fd.c8
-rw-r--r--drivers/net/dsa/lantiq_gswip.c2
-rw-r--r--drivers/net/dsa/mt7530.c8
-rw-r--r--drivers/net/ethernet/cavium/thunder/nic_main.c2
-rw-r--r--drivers/net/ethernet/cavium/thunder/nicvf_main.c4
-rw-r--r--drivers/net/ethernet/freescale/enetc/enetc_ethtool.c2
-rw-r--r--drivers/net/ethernet/freescale/enetc/enetc_pf.c5
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hnae3.c21
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hnae3.h1
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c16
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3_enet.c37
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3_enet.h7
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c9
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c30
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c5
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h2
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c36
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h1
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c2
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c11
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h1
-rw-r--r--drivers/net/ethernet/intel/e1000e/e1000.h4
-rw-r--r--drivers/net/ethernet/intel/e1000e/ich8lan.c31
-rw-r--r--drivers/net/ethernet/intel/e1000e/ich8lan.h3
-rw-r--r--drivers/net/ethernet/intel/e1000e/netdev.c45
-rw-r--r--drivers/net/ethernet/intel/ice/ice_common.c2
-rw-r--r--drivers/net/ethernet/intel/ice/ice_devids.h4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_devlink.c3
-rw-r--r--drivers/net/ethernet/intel/ice/ice_flex_pipe.c4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lag.c18
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lib.c9
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c8
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ptp.c3
-rw-r--r--drivers/net/ethernet/intel/ice/ice_sched.c13
-rw-r--r--drivers/net/ethernet/intel/ice/ice_sched.h1
-rw-r--r--drivers/net/ethernet/intel/igc/igc_hw.h2
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c148
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/fs.h3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c51
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_fs.c28
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c20
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lag.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlxsw/pci.c25
-rw-r--r--drivers/net/ethernet/microchip/lan743x_main.c35
-rw-r--r--drivers/net/ethernet/microchip/sparx5/sparx5_main.c1
-rw-r--r--drivers/net/ethernet/mscc/ocelot_vsc7514.c1
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/main.c16
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/main.h2
-rw-r--r--drivers/net/ethernet/netronome/nfp/bpf/offload.c17
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_asm.c4
-rw-r--r--drivers/net/ethernet/nxp/lpc_eth.c5
-rw-r--r--drivers/net/ethernet/realtek/r8169_main.c1
-rw-r--r--drivers/net/ethernet/sfc/mcdi_port_common.c37
-rw-r--r--drivers/net/ethernet/sfc/ptp.c4
-rw-r--r--drivers/net/ethernet/sfc/siena_sriov.c2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_main.c2
-rw-r--r--drivers/net/hamradio/baycom_epp.c6
-rw-r--r--drivers/net/phy/phy.c140
-rw-r--r--drivers/net/usb/Kconfig1
-rw-r--r--drivers/net/usb/lan78xx.c6
-rw-r--r--drivers/net/usb/usbnet.c5
-rw-r--r--drivers/net/vmxnet3/vmxnet3_drv.c1
-rw-r--r--drivers/net/vrf.c4
-rw-r--r--drivers/net/xen-netfront.c8
-rw-r--r--drivers/nfc/port100.c4
-rw-r--r--drivers/nfc/st95hf/core.c6
-rw-r--r--drivers/nvdimm/pmem.c33
-rw-r--r--drivers/nvme/host/core.c120
-rw-r--r--drivers/nvme/host/fabrics.c6
-rw-r--r--drivers/nvme/host/fabrics.h8
-rw-r--r--drivers/nvme/host/fc.c34
-rw-r--r--drivers/nvme/host/multipath.c32
-rw-r--r--drivers/nvme/host/nvme.h5
-rw-r--r--drivers/nvme/host/pci.c17
-rw-r--r--drivers/nvme/host/rdma.c25
-rw-r--r--drivers/nvme/host/tcp.c27
-rw-r--r--drivers/nvme/host/zns.c2
-rw-r--r--drivers/nvme/target/admin-cmd.c18
-rw-r--r--drivers/nvme/target/configfs.c41
-rw-r--r--drivers/nvme/target/core.c18
-rw-r--r--drivers/nvme/target/discovery.c19
-rw-r--r--drivers/nvme/target/fabrics-cmd.c3
-rw-r--r--drivers/nvme/target/loop.c6
-rw-r--r--drivers/nvme/target/nvmet.h6
-rw-r--r--drivers/nvme/target/rdma.c30
-rw-r--r--drivers/nvme/target/tcp.c23
-rw-r--r--drivers/of/of_reserved_mem.c2
-rw-r--r--drivers/pinctrl/bcm/pinctrl-ns.c29
-rw-r--r--drivers/pinctrl/pinctrl-amd.c31
-rw-r--r--drivers/pinctrl/stm32/pinctrl-stm32.c4
-rw-r--r--drivers/ptp/ptp_clock.c16
-rw-r--r--drivers/ptp/ptp_kvm_x86.c4
-rw-r--r--drivers/reset/Kconfig4
-rw-r--r--drivers/reset/reset-brcmstb-rescal.c2
-rw-r--r--drivers/reset/reset-socfpga.c26
-rw-r--r--drivers/reset/tegra/reset-bpmp.c9
-rw-r--r--drivers/s390/block/dasd.c9
-rw-r--r--drivers/s390/block/dasd_3990_erp.c6
-rw-r--r--drivers/s390/block/dasd_eckd.c294
-rw-r--r--drivers/s390/block/dasd_eckd.h13
-rw-r--r--drivers/s390/block/dasd_erp.c8
-rw-r--r--drivers/s390/block/dasd_int.h11
-rw-r--r--drivers/s390/block/dasd_ioctl.c4
-rw-r--r--drivers/scsi/hosts.c3
-rw-r--r--drivers/scsi/ibmvscsi/ibmvfc.c3
-rw-r--r--drivers/scsi/mpi3mr/mpi3mr_os.c2
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_scsih.c9
-rw-r--r--drivers/scsi/qla2xxx/qla_bsg.c2
-rw-r--r--drivers/scsi/qla2xxx/qla_nvme.c15
-rw-r--r--drivers/scsi/qla2xxx/qla_os.c2
-rw-r--r--drivers/scsi/qla2xxx/qla_target.c14
-rw-r--r--drivers/scsi/scsi.c4
-rw-r--r--drivers/scsi/scsi_sysfs.c9
-rw-r--r--drivers/scsi/scsi_transport_iscsi.c2
-rw-r--r--drivers/scsi/sd.c7
-rw-r--r--drivers/scsi/storvsc_drv.c32
-rw-r--r--drivers/scsi/ufs/ufs-exynos.c6
-rw-r--r--drivers/scsi/ufs/ufshcd-crypto.c32
-rw-r--r--drivers/scsi/ufs/ufshcd-crypto.h9
-rw-r--r--drivers/scsi/ufs/ufshcd-pci.c33
-rw-r--r--drivers/scsi/ufs/ufshcd.c9
-rw-r--r--drivers/scsi/ufs/ufshcd.h6
-rw-r--r--drivers/scsi/ufs/ufshpb.c283
-rw-r--r--drivers/scsi/ufs/ufshpb.h2
-rw-r--r--drivers/spi/spi-altera-dfl.c2
-rw-r--r--drivers/spi/spi-altera-platform.c2
-rw-r--r--drivers/spi/spi-pl022.c5
-rw-r--r--drivers/spi/spi-tegra20-slink.c2
-rw-r--r--drivers/vdpa/vdpa_user/vduse_dev.c29
-rw-r--r--drivers/virtio/virtio_ring.c2
-rw-r--r--drivers/watchdog/iTCO_wdt.c12
-rw-r--r--drivers/watchdog/ixp4xx_wdt.c2
-rw-r--r--drivers/watchdog/omap_wdt.c6
-rw-r--r--drivers/watchdog/sbsa_gwdt.c5
-rw-r--r--fs/afs/write.c9
-rw-r--r--fs/autofs/waitq.c2
-rw-r--r--fs/btrfs/compression.c3
-rw-r--r--fs/btrfs/inode.c3
-rw-r--r--fs/btrfs/lzo.c36
-rw-r--r--fs/btrfs/zlib.c36
-rw-r--r--fs/btrfs/zstd.c27
-rw-r--r--fs/cachefiles/rdwr.c16
-rw-r--r--fs/ceph/caps.c12
-rw-r--r--fs/ceph/file.c1
-rw-r--r--fs/ceph/inode.c2
-rw-r--r--fs/ceph/locks.c3
-rw-r--r--fs/ceph/mds_client.c17
-rw-r--r--fs/ceph/super.c17
-rw-r--r--fs/ceph/super.h3
-rw-r--r--fs/fs-writeback.c5
-rw-r--r--fs/fuse/fuse_i.h3
-rw-r--r--fs/fuse/inode.c87
-rw-r--r--fs/fuse/virtio_fs.c12
-rw-r--r--fs/gfs2/file.c2
-rw-r--r--fs/io-wq.c65
-rw-r--r--fs/io-wq.h59
-rw-r--r--fs/io_uring.c1768
-rw-r--r--fs/jfs/jfs_metapage.c1
-rw-r--r--fs/kernel_read_file.c2
-rw-r--r--fs/ksmbd/auth.c16
-rw-r--r--fs/ksmbd/connection.c2
-rw-r--r--fs/ksmbd/ksmbd_netlink.h2
-rw-r--r--fs/ksmbd/mgmt/user_config.c2
-rw-r--r--fs/ksmbd/mgmt/user_config.h1
-rw-r--r--fs/ksmbd/smb2misc.c55
-rw-r--r--fs/ksmbd/smb2ops.c3
-rw-r--r--fs/ksmbd/smb2pdu.c346
-rw-r--r--fs/ksmbd/smb2pdu.h2
-rw-r--r--fs/ksmbd/transport_ipc.c3
-rw-r--r--fs/ksmbd/transport_ipc.h2
-rw-r--r--fs/ksmbd/transport_rdma.c21
-rw-r--r--fs/ksmbd/vfs.c2
-rw-r--r--fs/ksmbd/vfs.h2
-rw-r--r--fs/locks.c161
-rw-r--r--fs/namei.c4
-rw-r--r--fs/nfs/file.c9
-rw-r--r--fs/ocfs2/alloc.c46
-rw-r--r--fs/ocfs2/suballoc.c22
-rw-r--r--fs/ocfs2/super.c14
-rw-r--r--fs/read_write.c4
-rw-r--r--fs/userfaultfd.c12
-rw-r--r--include/acpi/platform/acgcc.h9
-rw-r--r--include/asm-generic/cacheflush.h6
-rw-r--r--include/linux/backing-dev.h6
-rw-r--r--include/linux/bio.h41
-rw-r--r--include/linux/blk-crypto-profile.h166
-rw-r--r--include/linux/blk-mq.h40
-rw-r--r--include/linux/blkdev.h100
-rw-r--r--include/linux/bpf.h7
-rw-r--r--include/linux/bpf_types.h8
-rw-r--r--include/linux/cpuhotplug.h4
-rw-r--r--include/linux/device-mapper.h4
-rw-r--r--include/linux/elfcore.h2
-rw-r--r--include/linux/filter.h1
-rw-r--r--include/linux/flex_proportions.h9
-rw-r--r--include/linux/genhd.h7
-rw-r--r--include/linux/gfp.h22
-rw-r--r--include/linux/highmem-internal.h11
-rw-r--r--include/linux/highmem.h37
-rw-r--r--include/linux/huge_mm.h15
-rw-r--r--include/linux/keyslot-manager.h120
-rw-r--r--include/linux/ksm.h4
-rw-r--r--include/linux/memcontrol.h264
-rw-r--r--include/linux/memory.h5
-rw-r--r--include/linux/migrate.h4
-rw-r--r--include/linux/mlx5/driver.h1
-rw-r--r--include/linux/mm.h239
-rw-r--r--include/linux/mm_inline.h103
-rw-r--r--include/linux/mm_types.h77
-rw-r--r--include/linux/mmc/host.h4
-rw-r--r--include/linux/mmdebug.h20
-rw-r--r--include/linux/netfs.h77
-rw-r--r--include/linux/nvme-fc-driver.h7
-rw-r--r--include/linux/nvme-rdma.h2
-rw-r--r--include/linux/nvme.h30
-rw-r--r--include/linux/page-flags.h290
-rw-r--r--include/linux/page_idle.h99
-rw-r--r--include/linux/page_owner.h8
-rw-r--r--include/linux/page_ref.h158
-rw-r--r--include/linux/pagemap.h585
-rw-r--r--include/linux/percpu-refcount.h33
-rw-r--r--include/linux/rmap.h10
-rw-r--r--include/linux/sched.h2
-rw-r--r--include/linux/secretmem.h2
-rw-r--r--include/linux/skmsg.h1
-rw-r--r--include/linux/swap.h17
-rw-r--r--include/linux/tpm.h1
-rw-r--r--include/linux/trace_recursion.h49
-rw-r--r--include/linux/user_namespace.h2
-rw-r--r--include/linux/vmstat.h113
-rw-r--r--include/linux/writeback.h9
-rw-r--r--include/net/cfg80211.h2
-rw-r--r--include/net/mctp.h2
-rw-r--r--include/net/mptcp.h4
-rw-r--r--include/net/sctp/sm.h6
-rw-r--r--include/net/sock.h8
-rw-r--r--include/net/tcp.h5
-rw-r--r--include/net/tls.h11
-rw-r--r--include/net/udp.h5
-rw-r--r--include/trace/events/block.h6
-rw-r--r--include/trace/events/io_uring.h61
-rw-r--r--include/trace/events/pagemap.h46
-rw-r--r--include/trace/events/writeback.h28
-rw-r--r--include/uapi/asm-generic/fcntl.h4
-rw-r--r--include/uapi/linux/io_uring.h1
-rw-r--r--include/uapi/linux/mctp.h7
-rw-r--r--kernel/auditsc.c2
-rw-r--r--kernel/bpf/arraymap.c1
-rw-r--r--kernel/bpf/core.c24
-rw-r--r--kernel/bpf/syscall.c11
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/cgroup/cgroup.c4
-rw-r--r--kernel/cred.c9
-rw-r--r--kernel/dma/debug.c36
-rw-r--r--kernel/dma/debug.h24
-rw-r--r--kernel/dma/mapping.c24
-rw-r--r--kernel/events/uprobes.c3
-rw-r--r--kernel/sched/core.c6
-rw-r--r--kernel/signal.c25
-rw-r--r--kernel/trace/blktrace.c7
-rw-r--r--kernel/trace/ftrace.c22
-rw-r--r--kernel/trace/trace_eprobe.c4
-rw-r--r--kernel/ucount.c49
-rw-r--r--lib/flex_proportions.c28
-rw-r--r--lib/sbitmap.c2
-rw-r--r--mm/Makefile2
-rw-r--r--mm/compaction.c4
-rw-r--r--mm/damon/core-test.h4
-rw-r--r--mm/filemap.c567
-rw-r--r--mm/folio-compat.c142
-rw-r--r--mm/huge_memory.c15
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/internal.h36
-rw-r--r--mm/khugepaged.c34
-rw-r--r--mm/ksm.c34
-rw-r--r--mm/memblock.c12
-rw-r--r--mm/memcontrol.c356
-rw-r--r--mm/memory-failure.c30
-rw-r--r--mm/memory.c29
-rw-r--r--mm/mempolicy.c26
-rw-r--r--mm/memremap.c2
-rw-r--r--mm/migrate.c251
-rw-r--r--mm/mlock.c3
-rw-r--r--mm/oom_kill.c23
-rw-r--r--mm/page-writeback.c476
-rw-r--r--mm/page_alloc.c22
-rw-r--r--mm/page_ext.c4
-rw-r--r--mm/page_io.c4
-rw-r--r--mm/page_owner.c10
-rw-r--r--mm/rmap.c14
-rw-r--r--mm/secretmem.c11
-rw-r--r--mm/shmem.c7
-rw-r--r--mm/slab.c4
-rw-r--r--mm/slub.c31
-rw-r--r--mm/swap.c197
-rw-r--r--mm/swap_state.c2
-rw-r--r--mm/swapfile.c8
-rw-r--r--mm/userfaultfd.c2
-rw-r--r--mm/util.c111
-rw-r--r--mm/vmalloc.c15
-rw-r--r--mm/vmscan.c8
-rw-r--r--mm/workingset.c52
-rw-r--r--net/batman-adv/bridge_loop_avoidance.c8
-rw-r--r--net/batman-adv/main.c56
-rw-r--r--net/batman-adv/network-coding.c4
-rw-r--r--net/batman-adv/translation-table.c4
-rw-r--r--net/bridge/br_private.h4
-rw-r--r--net/bridge/netfilter/ebtables.c4
-rw-r--r--net/can/isotp.c51
-rw-r--r--net/can/j1939/j1939-priv.h1
-rw-r--r--net/can/j1939/main.c7
-rw-r--r--net/can/j1939/transport.c14
-rw-r--r--net/core/dev.c9
-rw-r--r--net/core/net-sysfs.c4
-rw-r--r--net/core/skbuff.c36
-rw-r--r--net/core/skmsg.c14
-rw-r--r--net/core/sock_destructor.h12
-rw-r--r--net/core/sysctl_net_core.c2
-rw-r--r--net/dsa/dsa2.c9
-rw-r--r--net/ipv4/tcp.c5
-rw-r--r--net/ipv4/tcp_bpf.c27
-rw-r--r--net/ipv4/tcp_ipv4.c45
-rw-r--r--net/ipv4/udp.c3
-rw-r--r--net/ipv4/udp_bpf.c1
-rw-r--r--net/ipv6/ip6_output.c3
-rw-r--r--net/ipv6/netfilter/ip6t_rt.c48
-rw-r--r--net/ipv6/tcp_ipv6.c15
-rw-r--r--net/mac80211/mesh.c9
-rw-r--r--net/mptcp/options.c39
-rw-r--r--net/netfilter/Kconfig2
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c5
-rw-r--r--net/netfilter/nft_chain_filter.c9
-rw-r--r--net/netfilter/xt_IDLETIMER.c2
-rw-r--r--net/sched/act_ct.c2
-rw-r--r--net/sctp/sm_statefuns.c139
-rw-r--r--net/smc/af_smc.c2
-rw-r--r--net/smc/smc_llc.c2
-rw-r--r--net/tipc/crypto.c32
-rw-r--r--net/tls/tls_main.c4
-rw-r--r--net/tls/tls_sw.c21
-rw-r--r--net/unix/af_unix.c4
-rw-r--r--net/unix/unix_bpf.c2
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/wireless/core.h2
-rw-r--r--net/wireless/mlme.c26
-rw-r--r--net/wireless/scan.c7
-rw-r--r--net/wireless/util.c14
-rw-r--r--security/keys/process_keys.c8
-rw-r--r--sound/pci/hda/patch_realtek.c47
-rw-r--r--sound/soc/codecs/Kconfig1
-rw-r--r--sound/soc/codecs/cs42l42.c16
-rw-r--r--sound/soc/codecs/cs4341.c7
-rw-r--r--sound/soc/codecs/nau8824.c4
-rw-r--r--sound/soc/codecs/pcm179x-spi.c1
-rw-r--r--sound/soc/codecs/pcm512x.c2
-rw-r--r--sound/soc/codecs/wcd938x.c6
-rw-r--r--sound/soc/codecs/wm8960.c13
-rw-r--r--sound/soc/fsl/fsl_xcvr.c17
-rw-r--r--sound/soc/intel/boards/bytcht_es8316.c37
-rw-r--r--sound/soc/soc-core.c1
-rw-r--r--sound/soc/soc-dapm.c13
-rw-r--r--sound/usb/mixer.c7
-rw-r--r--sound/usb/quirks-table.h32
-rw-r--r--sound/usb/quirks.c9
-rwxr-xr-xtools/kvm/kvm_stat/kvm_stat2
-rw-r--r--tools/perf/Makefile.perf2
-rw-r--r--tools/perf/arch/powerpc/util/skip-callchain-idx.c2
-rw-r--r--tools/perf/builtin-script.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c75
-rw-r--r--tools/testing/selftests/net/config1
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh63
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile1
-rw-r--r--tools/testing/selftests/net/forwarding/forwarding.config.sample2
-rwxr-xr-xtools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh172
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh8
-rw-r--r--tools/testing/selftests/net/nettest.c28
-rwxr-xr-xtools/testing/selftests/netfilter/nft_flowtable.sh1
-rwxr-xr-xtools/testing/selftests/netfilter/nft_nat.sh145
-rw-r--r--tools/testing/selftests/vm/split_huge_page_test.c2
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c23
-rw-r--r--tools/testing/vsock/vsock_diag_test.c2
606 files changed, 11563 insertions, 8072 deletions
diff --git a/.mailmap b/.mailmap
index 6e849110cb4e..90e614d2bf7e 100644
--- a/.mailmap
+++ b/.mailmap
@@ -33,6 +33,8 @@ Al Viro <viro@zenIV.linux.org.uk>
Andi Kleen <ak@linux.intel.com> <ak@suse.de>
Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
Andreas Herrmann <aherrman@de.ibm.com>
+Andrej Shadura <andrew.shadura@collabora.co.uk>
+Andrej Shadura <andrew@shadura.me> <andrew@beldisplaytech.com>
Andrew Morton <akpm@linux-foundation.org>
Andrew Murray <amurray@thegoodpenguin.co.uk> <amurray@embedded-bits.co.uk>
Andrew Murray <amurray@thegoodpenguin.co.uk> <andrew.murray@arm.com>
diff --git a/Documentation/block/inline-encryption.rst b/Documentation/block/inline-encryption.rst
index 7f9b40d6b416..71d1044617a9 100644
--- a/Documentation/block/inline-encryption.rst
+++ b/Documentation/block/inline-encryption.rst
@@ -7,230 +7,269 @@ Inline Encryption
Background
==========
-Inline encryption hardware sits logically between memory and the disk, and can
-en/decrypt data as it goes in/out of the disk. Inline encryption hardware has a
-fixed number of "keyslots" - slots into which encryption contexts (i.e. the
-encryption key, encryption algorithm, data unit size) can be programmed by the
-kernel at any time. Each request sent to the disk can be tagged with the index
-of a keyslot (and also a data unit number to act as an encryption tweak), and
-the inline encryption hardware will en/decrypt the data in the request with the
-encryption context programmed into that keyslot. This is very different from
-full disk encryption solutions like self encrypting drives/TCG OPAL/ATA
-Security standards, since with inline encryption, any block on disk could be
-encrypted with any encryption context the kernel chooses.
-
+Inline encryption hardware sits logically between memory and disk, and can
+en/decrypt data as it goes in/out of the disk. For each I/O request, software
+can control exactly how the inline encryption hardware will en/decrypt the data
+in terms of key, algorithm, data unit size (the granularity of en/decryption),
+and data unit number (a value that determines the initialization vector(s)).
+
+Some inline encryption hardware accepts all encryption parameters including raw
+keys directly in low-level I/O requests. However, most inline encryption
+hardware instead has a fixed number of "keyslots" and requires that the key,
+algorithm, and data unit size first be programmed into a keyslot. Each
+low-level I/O request then just contains a keyslot index and data unit number.
+
+Note that inline encryption hardware is very different from traditional crypto
+accelerators, which are supported through the kernel crypto API. Traditional
+crypto accelerators operate on memory regions, whereas inline encryption
+hardware operates on I/O requests. Thus, inline encryption hardware needs to be
+managed by the block layer, not the kernel crypto API.
+
+Inline encryption hardware is also very different from "self-encrypting drives",
+such as those based on the TCG Opal or ATA Security standards. Self-encrypting
+drives don't provide fine-grained control of encryption and provide no way to
+verify the correctness of the resulting ciphertext. Inline encryption hardware
+provides fine-grained control of encryption, including the choice of key and
+initialization vector for each sector, and can be tested for correctness.
Objective
=========
-We want to support inline encryption (IE) in the kernel.
-To allow for testing, we also want a crypto API fallback when actual
-IE hardware is absent. We also want IE to work with layered devices
-like dm and loopback (i.e. we want to be able to use the IE hardware
-of the underlying devices if present, or else fall back to crypto API
-en/decryption).
-
+We want to support inline encryption in the kernel. To make testing easier, we
+also want support for falling back to the kernel crypto API when actual inline
+encryption hardware is absent. We also want inline encryption to work with
+layered devices like device-mapper and loopback (i.e. we want to be able to use
+the inline encryption hardware of the underlying devices if present, or else
+fall back to crypto API en/decryption).
Constraints and notes
=====================
-- IE hardware has a limited number of "keyslots" that can be programmed
- with an encryption context (key, algorithm, data unit size, etc.) at any time.
- One can specify a keyslot in a data request made to the device, and the
- device will en/decrypt the data using the encryption context programmed into
- that specified keyslot. When possible, we want to make multiple requests with
- the same encryption context share the same keyslot.
-
-- We need a way for upper layers like filesystems to specify an encryption
- context to use for en/decrypting a struct bio, and a device driver (like UFS)
- needs to be able to use that encryption context when it processes the bio.
-
-- We need a way for device drivers to expose their inline encryption
- capabilities in a unified way to the upper layers.
-
-
-Design
-======
-
-We add a struct bio_crypt_ctx to struct bio that can
-represent an encryption context, because we need to be able to pass this
-encryption context from the upper layers (like the fs layer) to the
-device driver to act upon.
-
-While IE hardware works on the notion of keyslots, the FS layer has no
-knowledge of keyslots - it simply wants to specify an encryption context to
-use while en/decrypting a bio.
-
-We introduce a keyslot manager (KSM) that handles the translation from
-encryption contexts specified by the FS to keyslots on the IE hardware.
-This KSM also serves as the way IE hardware can expose its capabilities to
-upper layers. The generic mode of operation is: each device driver that wants
-to support IE will construct a KSM and set it up in its struct request_queue.
-Upper layers that want to use IE on this device can then use this KSM in
-the device's struct request_queue to translate an encryption context into
-a keyslot. The presence of the KSM in the request queue shall be used to mean
-that the device supports IE.
-
-The KSM uses refcounts to track which keyslots are idle (either they have no
-encryption context programmed, or there are no in-flight struct bios
-referencing that keyslot). When a new encryption context needs a keyslot, it
-tries to find a keyslot that has already been programmed with the same
-encryption context, and if there is no such keyslot, it evicts the least
-recently used idle keyslot and programs the new encryption context into that
-one. If no idle keyslots are available, then the caller will sleep until there
-is at least one.
-
-
-blk-mq changes, other block layer changes and blk-crypto-fallback
-=================================================================
-
-We add a pointer to a ``bi_crypt_context`` and ``keyslot`` to
-struct request. These will be referred to as the ``crypto fields``
-for the request. This ``keyslot`` is the keyslot into which the
-``bi_crypt_context`` has been programmed in the KSM of the ``request_queue``
-that this request is being sent to.
-
-We introduce ``block/blk-crypto-fallback.c``, which allows upper layers to remain
-blissfully unaware of whether or not real inline encryption hardware is present
-underneath. When a bio is submitted with a target ``request_queue`` that doesn't
-support the encryption context specified with the bio, the block layer will
-en/decrypt the bio with the blk-crypto-fallback.
-
-If the bio is a ``WRITE`` bio, a bounce bio is allocated, and the data in the bio
-is encrypted stored in the bounce bio - blk-mq will then proceed to process the
-bounce bio as if it were not encrypted at all (except when blk-integrity is
-concerned). ``blk-crypto-fallback`` sets the bounce bio's ``bi_end_io`` to an
-internal function that cleans up the bounce bio and ends the original bio.
-
-If the bio is a ``READ`` bio, the bio's ``bi_end_io`` (and also ``bi_private``)
-is saved and overwritten by ``blk-crypto-fallback`` to
-``bio_crypto_fallback_decrypt_bio``. The bio's ``bi_crypt_context`` is also
-overwritten with ``NULL``, so that to the rest of the stack, the bio looks
-as if it was a regular bio that never had an encryption context specified.
-``bio_crypto_fallback_decrypt_bio`` will decrypt the bio, restore the original
-``bi_end_io`` (and also ``bi_private``) and end the bio again.
-
-Regardless of whether real inline encryption hardware is used or the
+- We need a way for upper layers (e.g. filesystems) to specify an encryption
+ context to use for en/decrypting a bio, and device drivers (e.g. UFSHCD) need
+ to be able to use that encryption context when they process the request.
+ Encryption contexts also introduce constraints on bio merging; the block layer
+ needs to be aware of these constraints.
+
+- Different inline encryption hardware has different supported algorithms,
+ supported data unit sizes, maximum data unit numbers, etc. We call these
+ properties the "crypto capabilities". We need a way for device drivers to
+ advertise crypto capabilities to upper layers in a generic way.
+
+- Inline encryption hardware usually (but not always) requires that keys be
+ programmed into keyslots before being used. Since programming keyslots may be
+ slow and there may not be very many keyslots, we shouldn't just program the
+ key for every I/O request, but rather keep track of which keys are in the
+ keyslots and reuse an already-programmed keyslot when possible.
+
+- Upper layers typically define a specific end-of-life for crypto keys, e.g.
+ when an encrypted directory is locked or when a crypto mapping is torn down.
+ At these times, keys are wiped from memory. We must provide a way for upper
+ layers to also evict keys from any keyslots they are present in.
+
+- When possible, device-mapper devices must be able to pass through the inline
+ encryption support of their underlying devices. However, it doesn't make
+ sense for device-mapper devices to have keyslots themselves.
+
+Basic design
+============
+
+We introduce ``struct blk_crypto_key`` to represent an inline encryption key and
+how it will be used. This includes the actual bytes of the key; the size of the
+key; the algorithm and data unit size the key will be used with; and the number
+of bytes needed to represent the maximum data unit number the key will be used
+with.
+
+We introduce ``struct bio_crypt_ctx`` to represent an encryption context. It
+contains a data unit number and a pointer to a blk_crypto_key. We add pointers
+to a bio_crypt_ctx to ``struct bio`` and ``struct request``; this allows users
+of the block layer (e.g. filesystems) to provide an encryption context when
+creating a bio and have it be passed down the stack for processing by the block
+layer and device drivers. Note that the encryption context doesn't explicitly
+say whether to encrypt or decrypt, as that is implicit from the direction of the
+bio; WRITE means encrypt, and READ means decrypt.
+
+We also introduce ``struct blk_crypto_profile`` to contain all generic inline
+encryption-related state for a particular inline encryption device. The
+blk_crypto_profile serves as the way that drivers for inline encryption hardware
+advertise their crypto capabilities and provide certain functions (e.g.,
+functions to program and evict keys) to upper layers. Each device driver that
+wants to support inline encryption will construct a blk_crypto_profile, then
+associate it with the disk's request_queue.
+
+The blk_crypto_profile also manages the hardware's keyslots, when applicable.
+This happens in the block layer, so that users of the block layer can just
+specify encryption contexts and don't need to know about keyslots at all, nor do
+device drivers need to care about most details of keyslot management.
+
+Specifically, for each keyslot, the block layer (via the blk_crypto_profile)
+keeps track of which blk_crypto_key that keyslot contains (if any), and how many
+in-flight I/O requests are using it. When the block layer creates a
+``struct request`` for a bio that has an encryption context, it grabs a keyslot
+that already contains the key if possible. Otherwise it waits for an idle
+keyslot (a keyslot that isn't in-use by any I/O), then programs the key into the
+least-recently-used idle keyslot using the function the device driver provided.
+In both cases, the resulting keyslot is stored in the ``crypt_keyslot`` field of
+the request, where it is then accessible to device drivers and is released after
+the request completes.
+
+``struct request`` also contains a pointer to the original bio_crypt_ctx.
+Requests can be built from multiple bios, and the block layer must take the
+encryption context into account when trying to merge bios and requests. For two
+bios/requests to be merged, they must have compatible encryption contexts: both
+unencrypted, or both encrypted with the same key and contiguous data unit
+numbers. Only the encryption context for the first bio in a request is
+retained, since the remaining bios have been verified to be merge-compatible
+with the first bio.
+
+To make it possible for inline encryption to work with request_queue based
+layered devices, when a request is cloned, its encryption context is cloned as
+well. When the cloned request is submitted, it is then processed as usual; this
+includes getting a keyslot from the clone's target device if needed.
+
+blk-crypto-fallback
+===================
+
+It is desirable for the inline encryption support of upper layers (e.g.
+filesystems) to be testable without real inline encryption hardware, and
+likewise for the block layer's keyslot management logic. It is also desirable
+to allow upper layers to just always use inline encryption rather than have to
+implement encryption in multiple ways.
+
+Therefore, we also introduce *blk-crypto-fallback*, which is an implementation
+of inline encryption using the kernel crypto API. blk-crypto-fallback is built
+into the block layer, so it works on any block device without any special setup.
+Essentially, when a bio with an encryption context is submitted to a
+request_queue that doesn't support that encryption context, the block layer will
+handle en/decryption of the bio using blk-crypto-fallback.
+
+For encryption, the data cannot be encrypted in-place, as callers usually rely
+on it being unmodified. Instead, blk-crypto-fallback allocates bounce pages,
+fills a new bio with those bounce pages, encrypts the data into those bounce
+pages, and submits that "bounce" bio. When the bounce bio completes,
+blk-crypto-fallback completes the original bio. If the original bio is too
+large, multiple bounce bios may be required; see the code for details.
+
+For decryption, blk-crypto-fallback "wraps" the bio's completion callback
+(``bi_complete``) and private data (``bi_private``) with its own, unsets the
+bio's encryption context, then submits the bio. If the read completes
+successfully, blk-crypto-fallback restores the bio's original completion
+callback and private data, then decrypts the bio's data in-place using the
+kernel crypto API. Decryption happens from a workqueue, as it may sleep.
+Afterwards, blk-crypto-fallback completes the bio.
+
+In both cases, the bios that blk-crypto-fallback submits no longer have an
+encryption context. Therefore, lower layers only see standard unencrypted I/O.
+
+blk-crypto-fallback also defines its own blk_crypto_profile and has its own
+"keyslots"; its keyslots contain ``struct crypto_skcipher`` objects. The reason
+for this is twofold. First, it allows the keyslot management logic to be tested
+without actual inline encryption hardware. Second, similar to actual inline
+encryption hardware, the crypto API doesn't accept keys directly in requests but
+rather requires that keys be set ahead of time, and setting keys can be
+expensive; moreover, allocating a crypto_skcipher can't happen on the I/O path
+at all due to the locks it takes. Therefore, the concept of keyslots still
+makes sense for blk-crypto-fallback.
+
+Note that regardless of whether real inline encryption hardware or
blk-crypto-fallback is used, the ciphertext written to disk (and hence the
-on-disk format of data) will be the same (assuming the hardware's implementation
-of the algorithm being used adheres to spec and functions correctly).
-
-If a ``request queue``'s inline encryption hardware claimed to support the
-encryption context specified with a bio, then it will not be handled by the
-``blk-crypto-fallback``. We will eventually reach a point in blk-mq when a
-struct request needs to be allocated for that bio. At that point,
-blk-mq tries to program the encryption context into the ``request_queue``'s
-keyslot_manager, and obtain a keyslot, which it stores in its newly added
-``keyslot`` field. This keyslot is released when the request is completed.
-
-When the first bio is added to a request, ``blk_crypto_rq_bio_prep`` is called,
-which sets the request's ``crypt_ctx`` to a copy of the bio's
-``bi_crypt_context``. bio_crypt_do_front_merge is called whenever a subsequent
-bio is merged to the front of the request, which updates the ``crypt_ctx`` of
-the request so that it matches the newly merged bio's ``bi_crypt_context``. In particular, the request keeps a copy of the ``bi_crypt_context`` of the first
-bio in its bio-list (blk-mq needs to be careful to maintain this invariant
-during bio and request merges).
-
-To make it possible for inline encryption to work with request queue based
-layered devices, when a request is cloned, its ``crypto fields`` are cloned as
-well. When the cloned request is submitted, blk-mq programs the
-``bi_crypt_context`` of the request into the clone's request_queue's keyslot
-manager, and stores the returned keyslot in the clone's ``keyslot``.
+on-disk format of data) will be the same (assuming that both the inline
+encryption hardware's implementation and the kernel crypto API's implementation
+of the algorithm being used adhere to spec and function correctly).
+blk-crypto-fallback is optional and is controlled by the
+``CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK`` kernel configuration option.
API presented to users of the block layer
=========================================
-``struct blk_crypto_key`` represents a crypto key (the raw key, size of the
-key, the crypto algorithm to use, the data unit size to use, and the number of
-bytes required to represent data unit numbers that will be specified with the
-``bi_crypt_context``).
-
-``blk_crypto_init_key`` allows upper layers to initialize such a
-``blk_crypto_key``.
-
-``bio_crypt_set_ctx`` should be called on any bio that a user of
-the block layer wants en/decrypted via inline encryption (or the
-blk-crypto-fallback, if hardware support isn't available for the desired
-crypto configuration). This function takes the ``blk_crypto_key`` and the
-data unit number (DUN) to use when en/decrypting the bio.
-
-``blk_crypto_config_supported`` allows upper layers to query whether or not the
-an encryption context passed to request queue can be handled by blk-crypto
-(either by real inline encryption hardware, or by the blk-crypto-fallback).
-This is useful e.g. when blk-crypto-fallback is disabled, and the upper layer
-wants to use an algorithm that may not supported by hardware - this function
-lets the upper layer know ahead of time that the algorithm isn't supported,
-and the upper layer can fallback to something else if appropriate.
-
-``blk_crypto_start_using_key`` - Upper layers must call this function on
-``blk_crypto_key`` and a ``request_queue`` before using the key with any bio
-headed for that ``request_queue``. This function ensures that either the
-hardware supports the key's crypto settings, or the crypto API fallback has
-transforms for the needed mode allocated and ready to go. Note that this
-function may allocate an ``skcipher``, and must not be called from the data
-path, since allocating ``skciphers`` from the data path can deadlock.
-
-``blk_crypto_evict_key`` *must* be called by upper layers before a
-``blk_crypto_key`` is freed. Further, it *must* only be called only once
-there are no more in-flight requests that use that ``blk_crypto_key``.
-``blk_crypto_evict_key`` will ensure that a key is removed from any keyslots in
-inline encryption hardware that the key might have been programmed into (or the blk-crypto-fallback).
+``blk_crypto_config_supported()`` allows users to check ahead of time whether
+inline encryption with particular crypto settings will work on a particular
+request_queue -- either via hardware or via blk-crypto-fallback. This function
+takes in a ``struct blk_crypto_config`` which is like blk_crypto_key, but omits
+the actual bytes of the key and instead just contains the algorithm, data unit
+size, etc. This function can be useful if blk-crypto-fallback is disabled.
+
+``blk_crypto_init_key()`` allows users to initialize a blk_crypto_key.
+
+Users must call ``blk_crypto_start_using_key()`` before actually starting to use
+a blk_crypto_key on a request_queue (even if ``blk_crypto_config_supported()``
+was called earlier). This is needed to initialize blk-crypto-fallback if it
+will be needed. This must not be called from the data path, as this may have to
+allocate resources, which may deadlock in that case.
+
+Next, to attach an encryption context to a bio, users should call
+``bio_crypt_set_ctx()``. This function allocates a bio_crypt_ctx and attaches
+it to a bio, given the blk_crypto_key and the data unit number that will be used
+for en/decryption. Users don't need to worry about freeing the bio_crypt_ctx
+later, as that happens automatically when the bio is freed or reset.
+
+Finally, when done using inline encryption with a blk_crypto_key on a
+request_queue, users must call ``blk_crypto_evict_key()``. This ensures that
+the key is evicted from all keyslots it may be programmed into and unlinked from
+any kernel data structures it may be linked into.
+
+In summary, for users of the block layer, the lifecycle of a blk_crypto_key is
+as follows:
+
+1. ``blk_crypto_config_supported()`` (optional)
+2. ``blk_crypto_init_key()``
+3. ``blk_crypto_start_using_key()``
+4. ``bio_crypt_set_ctx()`` (potentially many times)
+5. ``blk_crypto_evict_key()`` (after all I/O has completed)
+6. Zeroize the blk_crypto_key (this has no dedicated function)
+
+If a blk_crypto_key is being used on multiple request_queues, then
+``blk_crypto_config_supported()`` (if used), ``blk_crypto_start_using_key()``,
+and ``blk_crypto_evict_key()`` must be called on each request_queue.
API presented to device drivers
===============================
-A :c:type:``struct blk_keyslot_manager`` should be set up by device drivers in
-the ``request_queue`` of the device. The device driver needs to call
-``blk_ksm_init`` (or its resource-managed variant ``devm_blk_ksm_init``) on the
-``blk_keyslot_manager``, while specifying the number of keyslots supported by
-the hardware.
-
-The device driver also needs to tell the KSM how to actually manipulate the
-IE hardware in the device to do things like programming the crypto key into
-the IE hardware into a particular keyslot. All this is achieved through the
-struct blk_ksm_ll_ops field in the KSM that the device driver
-must fill up after initing the ``blk_keyslot_manager``.
-
-The KSM also handles runtime power management for the device when applicable
-(e.g. when it wants to program a crypto key into the IE hardware, the device
-must be runtime powered on) - so the device driver must also set the ``dev``
-field in the ksm to point to the `struct device` for the KSM to use for runtime
-power management.
-
-``blk_ksm_reprogram_all_keys`` can be called by device drivers if the device
-needs each and every of its keyslots to be reprogrammed with the key it
-"should have" at the point in time when the function is called. This is useful
-e.g. if a device loses all its keys on runtime power down/up.
-
-If the driver used ``blk_ksm_init`` instead of ``devm_blk_ksm_init``, then
-``blk_ksm_destroy`` should be called to free up all resources used by a
-``blk_keyslot_manager`` once it is no longer needed.
+A device driver that wants to support inline encryption must set up a
+blk_crypto_profile in the request_queue of its device. To do this, it first
+must call ``blk_crypto_profile_init()`` (or its resource-managed variant
+``devm_blk_crypto_profile_init()``), providing the number of keyslots.
+
+Next, it must advertise its crypto capabilities by setting fields in the
+blk_crypto_profile, e.g. ``modes_supported`` and ``max_dun_bytes_supported``.
+
+It then must set function pointers in the ``ll_ops`` field of the
+blk_crypto_profile to tell upper layers how to control the inline encryption
+hardware, e.g. how to program and evict keyslots. Most drivers will need to
+implement ``keyslot_program`` and ``keyslot_evict``. For details, see the
+comments for ``struct blk_crypto_ll_ops``.
+
+Once the driver registers a blk_crypto_profile with a request_queue, I/O
+requests the driver receives via that queue may have an encryption context. All
+encryption contexts will be compatible with the crypto capabilities declared in
+the blk_crypto_profile, so drivers don't need to worry about handling
+unsupported requests. Also, if a nonzero number of keyslots was declared in the
+blk_crypto_profile, then all I/O requests that have an encryption context will
+also have a keyslot which was already programmed with the appropriate key.
+
+If the driver implements runtime suspend and its blk_crypto_ll_ops don't work
+while the device is runtime-suspended, then the driver must also set the ``dev``
+field of the blk_crypto_profile to point to the ``struct device`` that will be
+resumed before any of the low-level operations are called.
+
+If there are situations where the inline encryption hardware loses the contents
+of its keyslots, e.g. device resets, the driver must handle reprogramming the
+keyslots. To do this, the driver may call ``blk_crypto_reprogram_all_keys()``.
+
+Finally, if the driver used ``blk_crypto_profile_init()`` instead of
+``devm_blk_crypto_profile_init()``, then it is responsible for calling
+``blk_crypto_profile_destroy()`` when the crypto profile is no longer needed.
Layered Devices
===============
-Request queue based layered devices like dm-rq that wish to support IE need to
-create their own keyslot manager for their request queue, and expose whatever
-functionality they choose. When a layered device wants to pass a clone of that
-request to another ``request_queue``, blk-crypto will initialize and prepare the
-clone as necessary - see ``blk_crypto_insert_cloned_request`` in
-``blk-crypto.c``.
-
-
-Future Optimizations for layered devices
-========================================
-
-Creating a keyslot manager for a layered device uses up memory for each
-keyslot, and in general, a layered device merely passes the request on to a
-"child" device, so the keyslots in the layered device itself are completely
-unused, and don't need any refcounting or keyslot programming. We can instead
-define a new type of KSM; the "passthrough KSM", that layered devices can use
-to advertise an unlimited number of keyslots, and support for any encryption
-algorithms they choose, while not actually using any memory for each keyslot.
-Another use case for the "passthrough KSM" is for IE devices that do not have a
-limited number of keyslots.
-
+Request queue based layered devices like dm-rq that wish to support inline
+encryption need to create their own blk_crypto_profile for their request_queue,
+and expose whatever functionality they choose. When a layered device wants to
+pass a clone of that request to another request_queue, blk-crypto will
+initialize and prepare the clone as necessary; see
+``blk_crypto_insert_cloned_request()``.
Interaction between inline encryption and blk integrity
=======================================================
@@ -257,7 +296,7 @@ Because there isn't any real hardware yet, it seems prudent to assume that
hardware implementations might not implement both features together correctly,
and disallow the combination for now. Whenever a device supports integrity, the
kernel will pretend that the device does not support hardware inline encryption
-(by essentially setting the keyslot manager in the request_queue of the device
-to NULL). When the crypto API fallback is enabled, this means that all bios with
-and encryption context will use the fallback, and IO will complete as usual.
-When the fallback is disabled, a bio with an encryption context will be failed.
+(by setting the blk_crypto_profile in the request_queue of the device to NULL).
+When the crypto API fallback is enabled, this means that all bios with and
+encryption context will use the fallback, and IO will complete as usual. When
+the fallback is disabled, a bio with an encryption context will be failed.
diff --git a/Documentation/core-api/cachetlb.rst b/Documentation/core-api/cachetlb.rst
index 8aed9103e48a..5c0552e78c58 100644
--- a/Documentation/core-api/cachetlb.rst
+++ b/Documentation/core-api/cachetlb.rst
@@ -326,6 +326,12 @@ maps this page at its virtual address.
dirty. Again, see sparc64 for examples of how
to deal with this.
+ ``void flush_dcache_folio(struct folio *folio)``
+ This function is called under the same circumstances as
+ flush_dcache_page(). It allows the architecture to
+ optimise for flushing the entire folio of pages instead
+ of flushing one page at a time.
+
``void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long user_vaddr, void *dst, void *src, int len)``
``void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index a42f9baddfbf..395835f9289f 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -95,6 +95,11 @@ More Memory Management Functions
.. kernel-doc:: mm/mempolicy.c
.. kernel-doc:: include/linux/mm_types.h
:internal:
+.. kernel-doc:: include/linux/mm_inline.h
+.. kernel-doc:: include/linux/page-flags.h
.. kernel-doc:: include/linux/mm.h
:internal:
+.. kernel-doc:: include/linux/page_ref.h
.. kernel-doc:: include/linux/mmzone.h
+.. kernel-doc:: mm/util.c
+ :functions: folio_mapping
diff --git a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml
index fc1317ab3226..28ac60acf4ac 100644
--- a/Documentation/devicetree/bindings/mfd/brcm,cru.yaml
+++ b/Documentation/devicetree/bindings/mfd/brcm,cru.yaml
@@ -32,13 +32,13 @@ properties:
"#size-cells":
const: 1
- pinctrl:
- $ref: ../pinctrl/brcm,ns-pinmux.yaml
-
patternProperties:
'^clock-controller@[a-f0-9]+$':
$ref: ../clock/brcm,iproc-clocks.yaml
+ '^pin-controller@[a-f0-9]+$':
+ $ref: ../pinctrl/brcm,ns-pinmux.yaml
+
'^thermal@[a-f0-9]+$':
$ref: ../thermal/brcm,ns-thermal.yaml
@@ -73,9 +73,10 @@ examples:
"iprocfast", "sata1", "sata2";
};
- pinctrl {
+ pin-controller@1c0 {
compatible = "brcm,bcm4708-pinmux";
- offset = <0x1c0>;
+ reg = <0x1c0 0x24>;
+ reg-names = "cru_gpio_control";
};
thermal@2c0 {
diff --git a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml
index 470aff599c27..fc39e3e9f71c 100644
--- a/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/brcm,ns-pinmux.yaml
@@ -17,9 +17,6 @@ description:
A list of pins varies across chipsets so few bindings are available.
- Node of the pinmux must be nested in the CRU (Central Resource Unit) "syscon"
- node.
-
properties:
compatible:
enum:
@@ -27,10 +24,11 @@ properties:
- brcm,bcm4709-pinmux
- brcm,bcm53012-pinmux
- offset:
- description: offset of pin registers in the CRU block
+ reg:
maxItems: 1
- $ref: /schemas/types.yaml#/definitions/uint32-array
+
+ reg-names:
+ const: cru_gpio_control
patternProperties:
'-pins$':
@@ -72,23 +70,20 @@ allOf:
uart1_grp ]
required:
- - offset
+ - reg
+ - reg-names
additionalProperties: false
examples:
- |
- cru@1800c100 {
- compatible = "syscon", "simple-mfd";
- reg = <0x1800c100 0x1a4>;
-
- pinctrl {
- compatible = "brcm,bcm4708-pinmux";
- offset = <0xc0>;
-
- spi-pins {
- function = "spi";
- groups = "spi_grp";
- };
+ pin-controller@1800c1c0 {
+ compatible = "brcm,bcm4708-pinmux";
+ reg = <0x1800c1c0 0x24>;
+ reg-names = "cru_gpio_control";
+
+ spi-pins {
+ function = "spi";
+ groups = "spi_grp";
};
};
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index c0ad233963ae..bee63d42e5ec 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -29,7 +29,6 @@ algorithms work.
fiemap
files
locks
- mandatory-locking
mount_api
quota
seq_file
diff --git a/Documentation/filesystems/locks.rst b/Documentation/filesystems/locks.rst
index c5ae858b1aac..26429317dbbc 100644
--- a/Documentation/filesystems/locks.rst
+++ b/Documentation/filesystems/locks.rst
@@ -57,16 +57,9 @@ fcntl(), with all the problems that implies.
1.3 Mandatory Locking As A Mount Option
---------------------------------------
-Mandatory locking, as described in
-'Documentation/filesystems/mandatory-locking.rst' was prior to this release a
-general configuration option that was valid for all mounted filesystems. This
-had a number of inherent dangers, not the least of which was the ability to
-freeze an NFS server by asking it to read a file for which a mandatory lock
-existed.
-
-From this release of the kernel, mandatory locking can be turned on and off
-on a per-filesystem basis, using the mount options 'mand' and 'nomand'.
-The default is to disallow mandatory locking. The intention is that
-mandatory locking only be enabled on a local filesystem as the specific need
-arises.
+Mandatory locking was prior to this release a general configuration option
+that was valid for all mounted filesystems. This had a number of inherent
+dangers, not the least of which was the ability to freeze an NFS server by
+asking it to read a file for which a mandatory lock existed.
+Such option was dropped in Kernel v5.14.
diff --git a/Documentation/filesystems/netfs_library.rst b/Documentation/filesystems/netfs_library.rst
index 57a641847818..bb68d39f03b7 100644
--- a/Documentation/filesystems/netfs_library.rst
+++ b/Documentation/filesystems/netfs_library.rst
@@ -524,3 +524,5 @@ Note that these methods are passed a pointer to the cache resource structure,
not the read request structure as they could be used in other situations where
there isn't a read request structure as well, such as writing dirty data to the
cache.
+
+.. kernel-doc:: include/linux/netfs.h
diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index a432dc419fa4..5d97cee9457b 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -30,10 +30,11 @@ The ``ice`` driver reports the following versions
PHY, link, etc.
* - ``fw.mgmt.api``
- running
- - 1.5
- - 2-digit version number of the API exported over the AdminQ by the
- management firmware. Used by the driver to identify what commands
- are supported.
+ - 1.5.1
+ - 3-digit version number (major.minor.patch) of the API exported over
+ the AdminQ by the management firmware. Used by the driver to
+ identify what commands are supported. Historical versions of the
+ kernel only displayed a 2-digit version number (major.minor).
* - ``fw.mgmt.build``
- running
- 0x305d955f
diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst
index 6100cdc220f6..fa7730dbf7b9 100644
--- a/Documentation/networking/mctp.rst
+++ b/Documentation/networking/mctp.rst
@@ -59,11 +59,11 @@ specified with a ``sockaddr`` type, with a single-byte endpoint address:
};
struct sockaddr_mctp {
- unsigned short int smctp_family;
- int smctp_network;
- struct mctp_addr smctp_addr;
- __u8 smctp_type;
- __u8 smctp_tag;
+ __kernel_sa_family_t smctp_family;
+ unsigned int smctp_network;
+ struct mctp_addr smctp_addr;
+ __u8 smctp_type;
+ __u8 smctp_tag;
};
#define MCTP_NET_ANY 0x0
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index 2e8134059c87..6655d929a351 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -104,6 +104,7 @@ Code Seq# Include File Comments
'8' all SNP8023 advanced NIC card
<mailto:mcr@solidum.com>
';' 64-7F linux/vfio.h
+'=' 00-3f uapi/linux/ptp_clock.h <mailto:richardcochran@gmail.com>
'@' 00-0F linux/radeonfb.h conflict!
'@' 00-0F drivers/video/aty/aty128fb.c conflict!
'A' 00-1F linux/apm_bios.h conflict!
diff --git a/MAINTAINERS b/MAINTAINERS
index 8d118d7957d2..3b79fd441dde 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5458,6 +5458,19 @@ F: include/net/devlink.h
F: include/uapi/linux/devlink.h
F: net/core/devlink.c
+DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT
+M: Christoph Niedermaier <cniedermaier@dh-electronics.com>
+L: kernel@dh-electronics.com
+S: Maintained
+F: arch/arm/boot/dts/imx6*-dhcom-*
+
+DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT
+M: Marek Vasut <marex@denx.de>
+L: kernel@dh-electronics.com
+S: Maintained
+F: arch/arm/boot/dts/stm32mp1*-dhcom-*
+F: arch/arm/boot/dts/stm32mp1*-dhcor-*
+
DIALOG SEMICONDUCTOR DRIVERS
M: Support Opensource <support.opensource@diasemi.com>
S: Supported
@@ -6147,8 +6160,7 @@ T: git git://anongit.freedesktop.org/drm/drm
F: Documentation/devicetree/bindings/display/
F: Documentation/devicetree/bindings/gpu/
F: Documentation/gpu/
-F: drivers/gpu/drm/
-F: drivers/gpu/vga/
+F: drivers/gpu/
F: include/drm/
F: include/linux/vga*
F: include/uapi/drm/
@@ -11278,7 +11290,6 @@ F: Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
F: drivers/net/ethernet/marvell/octeontx2/af/
MARVELL PRESTERA ETHERNET SWITCH DRIVER
-M: Vadym Kochan <vkochan@marvell.com>
M: Taras Chornyi <tchornyi@marvell.com>
S: Supported
W: https://github.com/Marvell-switching/switchdev-prestera
@@ -20336,6 +20347,7 @@ X86 ARCHITECTURE (32-BIT AND 64-BIT)
M: Thomas Gleixner <tglx@linutronix.de>
M: Ingo Molnar <mingo@redhat.com>
M: Borislav Petkov <bp@alien8.de>
+M: Dave Hansen <dave.hansen@linux.intel.com>
M: x86@kernel.org
R: "H. Peter Anvin" <hpa@zytor.com>
L: linux-kernel@vger.kernel.org
diff --git a/Makefile b/Makefile
index 95ba2c34dc33..a5231635ed43 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
VERSION = 5
PATCHLEVEL = 15
SUBLEVEL = 0
-EXTRAVERSION = -rc6
-NAME = Opossums on Parade
+EXTRAVERSION =
+NAME = Trick or Treat
# *DOCUMENTATION*
# To see a list of typical targets execute "make help"
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h
index e201b4b1655a..e8c2c7469e10 100644
--- a/arch/arc/include/asm/cacheflush.h
+++ b/arch/arc/include/asm/cacheflush.h
@@ -36,6 +36,7 @@ void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void dma_cache_wback_inv(phys_addr_t start, unsigned long sz);
void dma_cache_inv(phys_addr_t start, unsigned long sz);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 59baf6c132a7..dcf2df6da98f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -92,6 +92,7 @@ config ARM
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/arm/boot/compressed/decompress.c b/arch/arm/boot/compressed/decompress.c
index aa075d8372ea..74255e819831 100644
--- a/arch/arm/boot/compressed/decompress.c
+++ b/arch/arm/boot/compressed/decompress.c
@@ -47,7 +47,10 @@ extern char * strchrnul(const char *, int);
#endif
#ifdef CONFIG_KERNEL_XZ
+/* Prevent KASAN override of string helpers in decompressor */
+#undef memmove
#define memmove memmove
+#undef memcpy
#define memcpy memcpy
#include "../../../../lib/decompress_unxz.c"
#endif
diff --git a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
index 8077f1716fbc..ecb91fb899ff 100644
--- a/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
+++ b/arch/arm/boot/dts/sun7i-a20-olinuxino-lime2.dts
@@ -112,7 +112,7 @@
pinctrl-names = "default";
pinctrl-0 = <&gmac_rgmii_pins>;
phy-handle = <&phy1>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 5e56288e343b..e68fb879e4f9 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -290,6 +290,7 @@ extern void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr
*/
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
extern void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *folio);
#define ARCH_IMPLEMENTS_FLUSH_KERNEL_VMAP_RANGE 1
static inline void flush_kernel_vmap_range(void *addr, int size)
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 084d1c07c2d0..36fbc3329252 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -176,6 +176,7 @@ extern int __get_user_64t_4(void *);
register unsigned long __l asm("r1") = __limit; \
register int __e asm("r0"); \
unsigned int __ua_flags = uaccess_save_and_enable(); \
+ int __tmp_e; \
switch (sizeof(*(__p))) { \
case 1: \
if (sizeof((x)) >= 8) \
@@ -203,9 +204,10 @@ extern int __get_user_64t_4(void *);
break; \
default: __e = __get_user_bad(); break; \
} \
+ __tmp_e = __e; \
uaccess_restore(__ua_flags); \
x = (typeof(*(p))) __r2; \
- __e; \
+ __tmp_e; \
})
#define get_user(x, p) \
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 29070eb8df7d..3fc7f9750ce4 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -253,7 +253,7 @@ __create_page_tables:
add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
ldr r6, =(_end - 1)
adr_l r5, kernel_sec_start @ _pa(kernel_sec_start)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
str r8, [r5, #4] @ Save physical start of kernel (BE)
#else
str r8, [r5] @ Save physical start of kernel (LE)
@@ -266,7 +266,7 @@ __create_page_tables:
bls 1b
eor r3, r3, r7 @ Remove the MMU flags
adr_l r5, kernel_sec_end @ _pa(kernel_sec_end)
-#ifdef CONFIG_CPU_ENDIAN_BE8
+#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32
str r3, [r5, #4] @ Save physical end of kernel (BE)
#else
str r3, [r5] @ Save physical end of kernel (LE)
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 4a7edc6e848f..195dff58bafc 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -136,7 +136,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
for (p = first, i = 0; i < 8 && p < top; i++, p += 4) {
if (p >= bottom && p < top) {
unsigned long val;
- if (get_kernel_nofault(val, (unsigned long *)p))
+ if (!get_kernel_nofault(val, (unsigned long *)p))
sprintf(str + i * 9, " %08lx", val);
else
sprintf(str + i * 9, " ????????");
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 50136828f5b5..f14c2360ea0b 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -40,6 +40,10 @@ SECTIONS
ARM_DISCARD
*(.alt.smp.init)
*(.pv_table)
+#ifndef CONFIG_ARM_UNWIND
+ *(.ARM.exidx) *(.ARM.exidx.*)
+ *(.ARM.extab) *(.ARM.extab.*)
+#endif
}
. = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR);
@@ -172,7 +176,7 @@ ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA")
#endif
-#ifdef CONFIG_ARM_MPU
+#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST)
/*
* Due to PMSAv7 restriction on base address and size we have to
* enforce minimal alignment restrictions. It was seen that weaker
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e2c743aa2eb2..d9f7dfe2a7ed 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -340,6 +340,7 @@ ENTRY(\name\()_cache_fns)
.macro define_tlb_functions name:req, flags_up:req, flags_smp
.type \name\()_tlb_fns, #object
+ .align 2
ENTRY(\name\()_tlb_fns)
.long \name\()_flush_user_tlb_range
.long \name\()_flush_kern_tlb_range
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 27e0af78e88b..9d8634e2f12f 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -439,7 +439,7 @@ static struct undef_hook kprobes_arm_break_hook = {
#endif /* !CONFIG_THUMB2_KERNEL */
-int __init arch_init_kprobes()
+int __init arch_init_kprobes(void)
{
arm_probes_decode_init();
#ifdef CONFIG_THUMB2_KERNEL
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
index 02f8e72f0cad..05486cccee1c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-h5-nanopi-neo2.dts
@@ -75,7 +75,7 @@
pinctrl-0 = <&emac_rgmii_pins>;
phy-supply = <&reg_gmac_3v3>;
phy-handle = <&ext_rgmii_phy>;
- phy-mode = "rgmii";
+ phy-mode = "rgmii-id";
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
index d17abb515835..e99e7644ff39 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-s.dts
@@ -70,7 +70,9 @@
regulator-name = "rst-usb-eth2";
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_usb_eth2>;
- gpio = <&gpio3 2 GPIO_ACTIVE_LOW>;
+ gpio = <&gpio3 2 GPIO_ACTIVE_HIGH>;
+ enable-active-high;
+ regulator-always-on;
};
reg_vdd_5v: regulator-5v {
@@ -95,7 +97,7 @@
clocks = <&osc_can>;
interrupt-parent = <&gpio4>;
interrupts = <28 IRQ_TYPE_EDGE_FALLING>;
- spi-max-frequency = <100000>;
+ spi-max-frequency = <10000000>;
vdd-supply = <&reg_vdd_3v3>;
xceiver-supply = <&reg_vdd_5v>;
};
@@ -111,7 +113,7 @@
&fec1 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_enet>;
- phy-connection-type = "rgmii";
+ phy-connection-type = "rgmii-rxid";
phy-handle = <&ethphy>;
status = "okay";
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
index 9db9b90bf2bc..42bbbb3f532b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-kontron-n801x-som.dtsi
@@ -91,10 +91,12 @@
reg_vdd_soc: BUCK1 {
regulator-name = "buck1";
regulator-min-microvolt = <800000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <850000>;
regulator-boot-on;
regulator-always-on;
regulator-ramp-delay = <3125>;
+ nxp,dvs-run-voltage = <850000>;
+ nxp,dvs-standby-voltage = <800000>;
};
reg_vdd_arm: BUCK2 {
@@ -111,7 +113,7 @@
reg_vdd_dram: BUCK3 {
regulator-name = "buck3";
regulator-min-microvolt = <850000>;
- regulator-max-microvolt = <900000>;
+ regulator-max-microvolt = <950000>;
regulator-boot-on;
regulator-always-on;
};
@@ -150,7 +152,7 @@
reg_vdd_snvs: LDO2 {
regulator-name = "ldo2";
- regulator-min-microvolt = <850000>;
+ regulator-min-microvolt = <800000>;
regulator-max-microvolt = <900000>;
regulator-boot-on;
regulator-always-on;
diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
index 8c15d9fed08f..d12e4cbfc852 100644
--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
@@ -2590,9 +2590,10 @@
power-domains = <&dispcc MDSS_GDSC>;
clocks = <&dispcc DISP_CC_MDSS_AHB_CLK>,
+ <&gcc GCC_DISP_HF_AXI_CLK>,
<&gcc GCC_DISP_SF_AXI_CLK>,
<&dispcc DISP_CC_MDSS_MDP_CLK>;
- clock-names = "iface", "nrt_bus", "core";
+ clock-names = "iface", "bus", "nrt_bus", "core";
assigned-clocks = <&dispcc DISP_CC_MDSS_MDP_CLK>;
assigned-clock-rates = <460000000>;
diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
index fb0f523d1492..0a048dc06a7d 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/gfp.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h
@@ -24,6 +24,7 @@ struct hyp_pool {
/* Allocation */
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order);
+void hyp_split_page(struct hyp_page *page);
void hyp_get_page(struct hyp_pool *pool, void *addr);
void hyp_put_page(struct hyp_pool *pool, void *addr);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..34eeb524b686 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -35,7 +35,18 @@ const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
- return hyp_alloc_pages(&host_s2_pool, get_order(size));
+ void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size));
+
+ hyp_split_page(hyp_virt_to_page(addr));
+
+ /*
+ * The size of concatenated PGDs is always a power of two of PAGE_SIZE,
+ * so there should be no need to free any of the tail pages to make the
+ * allocation exact.
+ */
+ WARN_ON(size != (PAGE_SIZE << get_order(size)));
+
+ return addr;
}
static void *host_s2_zalloc_page(void *pool)
diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
index 41fc25bdfb34..0bd7701ad1df 100644
--- a/arch/arm64/kvm/hyp/nvhe/page_alloc.c
+++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c
@@ -152,6 +152,7 @@ static inline void hyp_page_ref_inc(struct hyp_page *p)
static inline int hyp_page_ref_dec_and_test(struct hyp_page *p)
{
+ BUG_ON(!p->refcount);
p->refcount--;
return (p->refcount == 0);
}
@@ -193,6 +194,20 @@ void hyp_get_page(struct hyp_pool *pool, void *addr)
hyp_spin_unlock(&pool->lock);
}
+void hyp_split_page(struct hyp_page *p)
+{
+ unsigned short order = p->order;
+ unsigned int i;
+
+ p->order = 0;
+ for (i = 1; i < (1 << order); i++) {
+ struct hyp_page *tail = p + i;
+
+ tail->order = 0;
+ hyp_set_page_refcounted(tail);
+ }
+}
+
void *hyp_alloc_pages(struct hyp_pool *pool, unsigned short order)
{
unsigned short i = order;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1a94a7ca48f2..69bd1732a299 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1529,8 +1529,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
* when updating the PG_mte_tagged page flag, see
* sanitise_mte_tags for more details.
*/
- if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED)
- return -EINVAL;
+ if (kvm_has_mte(kvm) && vma->vm_flags & VM_SHARED) {
+ ret = -EINVAL;
+ break;
+ }
if (vma->vm_flags & VM_PFNMAP) {
/* IO region dirty page logging not allowed */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 41c23f474ea6..803e7773fa86 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1136,6 +1136,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c
index 4ef457ba5220..9c57b245dc12 100644
--- a/arch/m68k/emu/nfblock.c
+++ b/arch/m68k/emu/nfblock.c
@@ -99,6 +99,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
{
struct nfhd_device *dev;
int dev_id = id - NFHD_DEV_OFFSET;
+ int err = -ENOMEM;
pr_info("nfhd%u: found device with %u blocks (%u bytes)\n", dev_id,
blocks, bsize);
@@ -129,16 +130,20 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize)
sprintf(dev->disk->disk_name, "nfhd%u", dev_id);
set_capacity(dev->disk, (sector_t)blocks * (bsize / 512));
blk_queue_logical_block_size(dev->disk->queue, bsize);
- add_disk(dev->disk);
+ err = add_disk(dev->disk);
+ if (err)
+ goto out_cleanup_disk;
list_add_tail(&dev->list, &nfhd_list);
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(dev->disk);
free_dev:
kfree(dev);
out:
- return -ENOMEM;
+ return err;
}
static int __init nfhd_init(void)
diff --git a/arch/m68k/include/asm/cacheflush_mm.h b/arch/m68k/include/asm/cacheflush_mm.h
index 1ac55e7b47f0..8ab46625ddd3 100644
--- a/arch/m68k/include/asm/cacheflush_mm.h
+++ b/arch/m68k/include/asm/cacheflush_mm.h
@@ -250,6 +250,7 @@ static inline void __flush_page_to_ram(void *vaddr)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
#define flush_dcache_page(page) __flush_page_to_ram(page_address(page))
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
#define flush_icache_page(vma, page) __flush_page_to_ram(page_address(page))
diff --git a/arch/mips/include/asm/cacheflush.h b/arch/mips/include/asm/cacheflush.h
index b3dc9c589442..f207388541d5 100644
--- a/arch/mips/include/asm/cacheflush.h
+++ b/arch/mips/include/asm/cacheflush.h
@@ -61,6 +61,8 @@ static inline void flush_dcache_page(struct page *page)
SetPageDcacheDirty(page);
}
+void flush_dcache_folio(struct folio *folio);
+
#define flush_dcache_mmap_lock(mapping) do { } while (0)
#define flush_dcache_mmap_unlock(mapping) do { } while (0)
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index c2a222ebfa2a..3fc0bb7d6487 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -27,6 +27,7 @@ void flush_cache_vunmap(unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
unsigned long vaddr, void *dst, void *src, int len);
void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c
index 0e23e3a8df6b..d55b73b18149 100644
--- a/arch/nds32/kernel/ftrace.c
+++ b/arch/nds32/kernel/ftrace.c
@@ -6,7 +6,7 @@
#ifndef CONFIG_DYNAMIC_FTRACE
extern void (*ftrace_trace_function)(unsigned long, unsigned long,
- struct ftrace_ops*, struct pt_regs*);
+ struct ftrace_ops*, struct ftrace_regs*);
extern void ftrace_graph_caller(void);
noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip,
diff --git a/arch/nios2/include/asm/cacheflush.h b/arch/nios2/include/asm/cacheflush.h
index 18eb9f69f806..1999561b22aa 100644
--- a/arch/nios2/include/asm/cacheflush.h
+++ b/arch/nios2/include/asm/cacheflush.h
@@ -28,7 +28,8 @@ extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
extern void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
unsigned long pfn);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
extern void flush_icache_page(struct vm_area_struct *vma, struct page *page);
diff --git a/arch/nios2/include/asm/irqflags.h b/arch/nios2/include/asm/irqflags.h
index b3ec3e510706..25acf27862f9 100644
--- a/arch/nios2/include/asm/irqflags.h
+++ b/arch/nios2/include/asm/irqflags.h
@@ -9,7 +9,7 @@
static inline unsigned long arch_local_save_flags(void)
{
- return RDCTL(CTL_STATUS);
+ return RDCTL(CTL_FSTATUS);
}
/*
@@ -18,7 +18,7 @@ static inline unsigned long arch_local_save_flags(void)
*/
static inline void arch_local_irq_restore(unsigned long flags)
{
- WRCTL(CTL_STATUS, flags);
+ WRCTL(CTL_FSTATUS, flags);
}
static inline void arch_local_irq_disable(void)
diff --git a/arch/nios2/include/asm/registers.h b/arch/nios2/include/asm/registers.h
index 183c720e454d..95b67dd16f81 100644
--- a/arch/nios2/include/asm/registers.h
+++ b/arch/nios2/include/asm/registers.h
@@ -11,7 +11,7 @@
#endif
/* control register numbers */
-#define CTL_STATUS 0
+#define CTL_FSTATUS 0
#define CTL_ESTATUS 1
#define CTL_BSTATUS 2
#define CTL_IENABLE 3
diff --git a/arch/nios2/platform/Kconfig.platform b/arch/nios2/platform/Kconfig.platform
index 9e32fb7f3d4c..e849daff6fd1 100644
--- a/arch/nios2/platform/Kconfig.platform
+++ b/arch/nios2/platform/Kconfig.platform
@@ -37,6 +37,7 @@ config NIOS2_DTB_PHYS_ADDR
config NIOS2_DTB_SOURCE_BOOL
bool "Compile and link device tree into kernel image"
+ depends on !COMPILE_TEST
help
This allows you to specify a dts (device tree source) file
which will be compiled and linked into the kernel image.
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index eef0096db5f8..da0cd4b3a28f 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -49,7 +49,8 @@ void invalidate_kernel_vmap_range(void *vaddr, int size);
#define flush_cache_vunmap(start, end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
#define flush_dcache_mmap_lock(mapping) xa_lock_irq(&mapping->i_pages)
#define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&mapping->i_pages)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index abb719b21cae..3d97fb833834 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -126,14 +126,16 @@ _GLOBAL(idle_return_gpr_loss)
/*
* This is the sequence required to execute idle instructions, as
* specified in ISA v2.07 (and earlier). MSR[IR] and MSR[DR] must be 0.
- *
- * The 0(r1) slot is used to save r2 in isa206, so use that here.
+ * We have to store a GPR somewhere, ptesync, then reload it, and create
+ * a false dependency on the result of the load. It doesn't matter which
+ * GPR we store, or where we store it. We have already stored r2 to the
+ * stack at -8(r1) in isa206_idle_insn_mayloss, so use that.
*/
#define IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST) \
/* Magic NAP/SLEEP/WINKLE mode enter sequence */ \
- std r2,0(r1); \
+ std r2,-8(r1); \
ptesync; \
- ld r2,0(r1); \
+ ld r2,-8(r1); \
236: cmpd cr0,r2,r2; \
bne 236b; \
IDLE_INST; \
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 9cc7d3dbf439..605bab448f84 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1730,8 +1730,6 @@ void __cpu_die(unsigned int cpu)
void arch_cpu_idle_dead(void)
{
- sched_preempt_enable_no_resched();
-
/*
* Disable on the down path. This will be re-enabled by
* start_secondary() via start_secondary_resume() below
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index dab5c56ffd0e..a52af8fbf571 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -1302,6 +1302,12 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
struct property *default_win;
int reset_win_ext;
+ /* DDW + IOMMU on single window may fail if there is any allocation */
+ if (iommu_table_in_use(tbl)) {
+ dev_warn(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
+ goto out_failed;
+ }
+
default_win = of_find_property(pdn, "ibm,dma-window", NULL);
if (!default_win)
goto out_failed;
@@ -1356,12 +1362,6 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
query.largest_available_block,
1ULL << page_shift);
- /* DDW + IOMMU on single window may fail if there is any allocation */
- if (default_win_removed && iommu_table_in_use(tbl)) {
- dev_dbg(&dev->dev, "current IOMMU table in use, can't be replaced.\n");
- goto out_failed;
- }
-
len = order_base_2(query.largest_available_block << page_shift);
win_name = DMA64_PROPNAME;
} else {
@@ -1411,18 +1411,19 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
} else {
struct iommu_table *newtbl;
int i;
+ unsigned long start = 0, end = 0;
for (i = 0; i < ARRAY_SIZE(pci->phb->mem_resources); i++) {
const unsigned long mask = IORESOURCE_MEM_64 | IORESOURCE_MEM;
/* Look for MMIO32 */
- if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM)
+ if ((pci->phb->mem_resources[i].flags & mask) == IORESOURCE_MEM) {
+ start = pci->phb->mem_resources[i].start;
+ end = pci->phb->mem_resources[i].end;
break;
+ }
}
- if (i == ARRAY_SIZE(pci->phb->mem_resources))
- goto out_del_list;
-
/* New table for using DDW instead of the default DMA window */
newtbl = iommu_pseries_alloc_table(pci->phb->node);
if (!newtbl) {
@@ -1432,15 +1433,15 @@ static bool enable_ddw(struct pci_dev *dev, struct device_node *pdn)
iommu_table_setparms_common(newtbl, pci->phb->bus->number, create.liobn, win_addr,
1UL << len, page_shift, NULL, &iommu_table_lpar_multi_ops);
- iommu_init_table(newtbl, pci->phb->node, pci->phb->mem_resources[i].start,
- pci->phb->mem_resources[i].end);
+ iommu_init_table(newtbl, pci->phb->node, start, end);
pci->table_group->tables[1] = newtbl;
/* Keep default DMA window stuct if removed */
if (default_win_removed) {
tbl->it_size = 0;
- kfree(tbl->it_map);
+ vfree(tbl->it_map);
+ tbl->it_map = NULL;
}
set_iommu_table_base(&dev->dev, newtbl);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 6a6fa9e976d5..f076cee11af6 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -163,6 +163,12 @@ config PAGE_OFFSET
default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
+config KASAN_SHADOW_OFFSET
+ hex
+ depends on KASAN_GENERIC
+ default 0xdfffffc800000000 if 64BIT
+ default 0xffffffff if 32BIT
+
config ARCH_FLATMEM_ENABLE
def_bool !NUMA
diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h
index a2b3d9cdbc86..b00f503ec124 100644
--- a/arch/riscv/include/asm/kasan.h
+++ b/arch/riscv/include/asm/kasan.h
@@ -30,8 +30,7 @@
#define KASAN_SHADOW_SIZE (UL(1) << ((CONFIG_VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT))
#define KASAN_SHADOW_START KERN_VIRT_START
#define KASAN_SHADOW_END (KASAN_SHADOW_START + KASAN_SHADOW_SIZE)
-#define KASAN_SHADOW_OFFSET (KASAN_SHADOW_END - (1ULL << \
- (64 - KASAN_SHADOW_SCALE_SHIFT)))
+#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
void kasan_init(void);
asmlinkage void kasan_early_init(void);
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index fce5184b22c3..52c5ff9804c5 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -193,6 +193,7 @@ setup_trap_vector:
csrw CSR_SCRATCH, zero
ret
+.align 2
.Lsecondary_park:
/* We lack SMP support or have too many harts, so park this hart */
wfi
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index d7189c8714a9..54294f83513d 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -17,6 +17,9 @@ asmlinkage void __init kasan_early_init(void)
uintptr_t i;
pgd_t *pgd = early_pg_dir + pgd_index(KASAN_SHADOW_START);
+ BUILD_BUG_ON(KASAN_SHADOW_OFFSET !=
+ KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT)));
+
for (i = 0; i < PTRS_PER_PTE; ++i)
set_pte(kasan_early_shadow_pte + i,
mk_pte(virt_to_page(kasan_early_shadow_page),
@@ -172,21 +175,10 @@ void __init kasan_init(void)
phys_addr_t p_start, p_end;
u64 i;
- /*
- * Populate all kernel virtual address space with kasan_early_shadow_page
- * except for the linear mapping and the modules/kernel/BPF mapping.
- */
- kasan_populate_early_shadow((void *)KASAN_SHADOW_START,
- (void *)kasan_mem_to_shadow((void *)
- VMEMMAP_END));
if (IS_ENABLED(CONFIG_KASAN_VMALLOC))
kasan_shallow_populate(
(void *)kasan_mem_to_shadow((void *)VMALLOC_START),
(void *)kasan_mem_to_shadow((void *)VMALLOC_END));
- else
- kasan_populate_early_shadow(
- (void *)kasan_mem_to_shadow((void *)VMALLOC_START),
- (void *)kasan_mem_to_shadow((void *)VMALLOC_END));
/* Populate the linear mapping */
for_each_mem_range(i, &p_start, &p_end) {
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index fed86f42dfbe..753d85bdfad0 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
if (i == NR_JIT_ITERATIONS) {
pr_err("bpf-jit: image did not converge in <%d passes!\n", i);
- bpf_jit_binary_free(jit_data->header);
+ if (jit_data->header)
+ bpf_jit_binary_free(jit_data->header);
prog = orig_prog;
goto out_offset;
}
@@ -166,6 +167,11 @@ out:
return prog;
}
+u64 bpf_jit_alloc_exec_limit(void)
+{
+ return BPF_JIT_REGION_SIZE;
+}
+
void *bpf_jit_alloc_exec(unsigned long size)
{
return __vmalloc_node_range(size, PAGE_SIZE, BPF_JIT_REGION_START,
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index b9f85b2dc053..6af59c59cc1b 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -894,6 +894,11 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra,
/**
* guest_translate_address - translate guest logical into guest absolute address
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @gpa: Guest physical address
+ * @mode: Translation access mode
*
* Parameter semantics are the same as the ones from guest_translate.
* The memory contents at the guest address are not changed.
@@ -934,6 +939,11 @@ int guest_translate_address(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
/**
* check_gva_range - test a range of guest virtual addresses for accessibility
+ * @vcpu: virtual cpu
+ * @gva: Guest virtual address
+ * @ar: Access register
+ * @length: Length of test range
+ * @mode: Translation access mode
*/
int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
unsigned long length, enum gacc_mode mode)
@@ -956,6 +966,7 @@ int check_gva_range(struct kvm_vcpu *vcpu, unsigned long gva, u8 ar,
/**
* kvm_s390_check_low_addr_prot_real - check for low-address protection
+ * @vcpu: virtual cpu
* @gra: Guest real address
*
* Checks whether an address is subject to low-address protection and set
@@ -979,6 +990,7 @@ int kvm_s390_check_low_addr_prot_real(struct kvm_vcpu *vcpu, unsigned long gra)
* @pgt: pointer to the beginning of the page table for the given address if
* successful (return value 0), or to the first invalid DAT entry in
* case of exceptions (return value > 0)
+ * @dat_protection: referenced memory is write protected
* @fake: pgt references contiguous guest memory block, not a pgtable
*/
static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 72b25b7cc6ae..2bd8f854f1b4 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -269,6 +269,7 @@ static int handle_prog(struct kvm_vcpu *vcpu)
/**
* handle_external_interrupt - used for external interruption interceptions
+ * @vcpu: virtual cpu
*
* This interception only occurs if the CPUSTAT_EXT_INT bit was set, or if
* the new PSW does not have external interrupts disabled. In the first case,
@@ -315,7 +316,8 @@ static int handle_external_interrupt(struct kvm_vcpu *vcpu)
}
/**
- * Handle MOVE PAGE partial execution interception.
+ * handle_mvpg_pei - Handle MOVE PAGE partial execution interception.
+ * @vcpu: virtual cpu
*
* This interception can only happen for guests with DAT disabled and
* addresses that are currently not mapped in the host. Thus we try to
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 10722455fd02..2245f4b8d362 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -3053,13 +3053,14 @@ static void __airqs_kick_single_vcpu(struct kvm *kvm, u8 deliverable_mask)
int vcpu_idx, online_vcpus = atomic_read(&kvm->online_vcpus);
struct kvm_s390_gisa_interrupt *gi = &kvm->arch.gisa_int;
struct kvm_vcpu *vcpu;
+ u8 vcpu_isc_mask;
for_each_set_bit(vcpu_idx, kvm->arch.idle_mask, online_vcpus) {
vcpu = kvm_get_vcpu(kvm, vcpu_idx);
if (psw_ioint_disabled(vcpu))
continue;
- deliverable_mask &= (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
- if (deliverable_mask) {
+ vcpu_isc_mask = (u8)(vcpu->arch.sie_block->gcr[6] >> 24);
+ if (deliverable_mask & vcpu_isc_mask) {
/* lately kicked but not yet running */
if (test_and_set_bit(vcpu_idx, gi->kicked_mask))
return;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 6a6dd5e1daf6..1c97493d21e1 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -3363,6 +3363,7 @@ out_free_sie_block:
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
+ clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
return kvm_s390_vcpu_has_irq(vcpu, 0);
}
diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index 372afa82fee6..c7a97f32432f 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -42,7 +42,8 @@ extern void flush_cache_page(struct vm_area_struct *vma,
extern void flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page *page);
+void flush_dcache_page(struct page *page);
+void flush_dcache_folio(struct folio *folio);
extern void flush_icache_range(unsigned long start, unsigned long end);
#define flush_icache_user_range flush_icache_range
extern void flush_icache_page(struct vm_area_struct *vma,
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index fefd343412c7..69d2d0049a61 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -855,8 +855,8 @@ static const struct attribute_group *ubd_attr_groups[] = {
NULL,
};
-static void ubd_disk_register(int major, u64 size, int unit,
- struct gendisk *disk)
+static int ubd_disk_register(int major, u64 size, int unit,
+ struct gendisk *disk)
{
disk->major = major;
disk->first_minor = unit << UBD_SHIFT;
@@ -873,7 +873,7 @@ static void ubd_disk_register(int major, u64 size, int unit,
disk->private_data = &ubd_devs[unit];
disk->queue = ubd_devs[unit].queue;
- device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
+ return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups);
}
#define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE))
@@ -920,10 +920,15 @@ static int ubd_add(int n, char **error_out)
blk_queue_write_cache(ubd_dev->queue, true, false);
blk_queue_max_segments(ubd_dev->queue, MAX_SG);
blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1);
- ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk);
+ if (err)
+ goto out_cleanup_disk;
+
ubd_gendisk[n] = disk;
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&ubd_dev->tag_set);
out:
diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
index 18d2f5199194..1cc72b4804fa 100644
--- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S
@@ -78,7 +78,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -133,6 +133,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
index d2ffd7f76ee2..9c5d3f3ad45a 100644
--- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
+++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S
@@ -93,7 +93,7 @@
vpxor tmp0, x, x;
-.section .rodata.cst164, "aM", @progbits, 164
+.section .rodata.cst16, "aM", @progbits, 16
.align 16
/*
@@ -148,6 +148,10 @@
.L0f0f0f0f:
.long 0x0f0f0f0f
+/* 12 bytes, only for padding */
+.Lpadding_deadbeef:
+ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef
+
.text
.align 16
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f8f48a7ec577..13f64654dfff 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -702,7 +702,8 @@ struct kvm_vcpu_arch {
struct kvm_pio_request pio;
void *pio_data;
- void *guest_ins_data;
+ void *sev_pio_data;
+ unsigned sev_pio_count;
u8 event_exit_inst_len;
@@ -1097,7 +1098,7 @@ struct kvm_arch {
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
- spinlock_t pvclock_gtod_sync_lock;
+ raw_spinlock_t pvclock_gtod_sync_lock;
bool use_master_clock;
u64 master_kernel_ns;
u64 master_cycle_now;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 76fb00921203..d6ac32f3f650 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2321,13 +2321,14 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_apicv);
void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
{
struct kvm_lapic *apic = vcpu->arch.apic;
+ u64 msr_val;
int i;
if (!init_event) {
- vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE |
- MSR_IA32_APICBASE_ENABLE;
+ msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE;
if (kvm_vcpu_is_reset_bsp(vcpu))
- vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+ msr_val |= MSR_IA32_APICBASE_BSP;
+ kvm_lapic_set_base(vcpu, msr_val);
}
if (!apic)
@@ -2336,11 +2337,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event)
/* Stop the timer in case it's a reset to an active apic */
hrtimer_cancel(&apic->lapic_timer.timer);
- if (!init_event) {
- apic->base_address = APIC_DEFAULT_PHYS_BASE;
-
+ /* The xAPIC ID is set at RESET even if the APIC was already enabled. */
+ if (!init_event)
kvm_apic_set_xapic_id(apic, vcpu->vcpu_id);
- }
kvm_apic_set_version(apic->vcpu);
for (i = 0; i < KVM_APIC_LVT_NUM; i++)
@@ -2481,6 +2480,11 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
lapic_timer_advance_dynamic = false;
}
+ /*
+ * Stuff the APIC ENABLE bit in lieu of temporarily incrementing
+ * apic_hw_disabled; the full RESET value is set by kvm_lapic_reset().
+ */
+ vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */
kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
@@ -2942,5 +2946,7 @@ int kvm_apic_accept_events(struct kvm_vcpu *vcpu)
void kvm_lapic_exit(void)
{
static_key_deferred_flush(&apic_hw_disabled);
+ WARN_ON(static_branch_unlikely(&apic_hw_disabled.key));
static_key_deferred_flush(&apic_sw_disabled);
+ WARN_ON(static_branch_unlikely(&apic_sw_disabled.key));
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1a64ba5b9437..0cc58901bf7a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4596,10 +4596,10 @@ static void update_pkru_bitmask(struct kvm_mmu *mmu)
unsigned bit;
bool wp;
- if (!is_cr4_pke(mmu)) {
- mmu->pkru_mask = 0;
+ mmu->pkru_mask = 0;
+
+ if (!is_cr4_pke(mmu))
return;
- }
wp = is_cr0_wp(mmu);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c36b5fe4c27c..7e34d7163ada 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -618,7 +618,12 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu,
vmsa.handle = to_kvm_svm(kvm)->sev_info.handle;
vmsa.address = __sme_pa(svm->vmsa);
vmsa.len = PAGE_SIZE;
- return sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ ret = sev_issue_cmd(kvm, SEV_CMD_LAUNCH_UPDATE_VMSA, &vmsa, error);
+ if (ret)
+ return ret;
+
+ vcpu->arch.guest_state_protected = true;
+ return 0;
}
static int sev_launch_update_vmsa(struct kvm *kvm, struct kvm_sev_cmd *argp)
@@ -1479,6 +1484,13 @@ static int sev_receive_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
goto e_free_trans;
}
+ /*
+ * Flush (on non-coherent CPUs) before RECEIVE_UPDATE_DATA, the PSP
+ * encrypts the written data with the guest's key, and the cache may
+ * contain dirty, unencrypted data.
+ */
+ sev_clflush_pages(guest_page, n);
+
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
data.guest_address |= sev_me_mask;
@@ -2579,11 +2591,20 @@ int sev_handle_vmgexit(struct kvm_vcpu *vcpu)
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
{
- if (!setup_vmgexit_scratch(svm, in, svm->vmcb->control.exit_info_2))
+ int count;
+ int bytes;
+
+ if (svm->vmcb->control.exit_info_2 > INT_MAX)
+ return -EINVAL;
+
+ count = svm->vmcb->control.exit_info_2;
+ if (unlikely(check_mul_overflow(count, size, &bytes)))
+ return -EINVAL;
+
+ if (!setup_vmgexit_scratch(svm, in, bytes))
return -EINVAL;
- return kvm_sev_es_string_io(&svm->vcpu, size, port,
- svm->ghcb_sa, svm->ghcb_sa_len, in);
+ return kvm_sev_es_string_io(&svm->vcpu, size, port, svm->ghcb_sa, count, in);
}
void sev_es_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 128a54b1fbf1..5d30db599e10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -191,7 +191,7 @@ struct vcpu_svm {
/* SEV-ES scratch area support */
void *ghcb_sa;
- u64 ghcb_sa_len;
+ u32 ghcb_sa_len;
bool ghcb_sa_sync;
bool ghcb_sa_free;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 116b08904ac3..7d595effb66f 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5562,9 +5562,13 @@ static int handle_encls(struct kvm_vcpu *vcpu)
static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
{
- vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
- vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
- return 0;
+ /*
+ * Hardware may or may not set the BUS_LOCK_DETECTED flag on BUS_LOCK
+ * VM-Exits. Unconditionally set the flag here and leave the handling to
+ * vmx_handle_exit().
+ */
+ to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+ return 1;
}
/*
@@ -6051,9 +6055,8 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
int ret = __vmx_handle_exit(vcpu, exit_fastpath);
/*
- * Even when current exit reason is handled by KVM internally, we
- * still need to exit to user space when bus lock detected to inform
- * that there is a bus lock in guest.
+ * Exit to user space when bus lock detected to inform that there is
+ * a bus lock in guest.
*/
if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
if (ret > 0)
@@ -6302,18 +6305,13 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
/*
* If we are running L2 and L1 has a new pending interrupt
- * which can be injected, we should re-evaluate
- * what should be done with this new L1 interrupt.
- * If L1 intercepts external-interrupts, we should
- * exit from L2 to L1. Otherwise, interrupt should be
- * delivered directly to L2.
+ * which can be injected, this may cause a vmexit or it may
+ * be injected into L2. Either way, this interrupt will be
+ * processed via KVM_REQ_EVENT, not RVI, because we do not use
+ * virtual interrupt delivery to inject L1 interrupts into L2.
*/
- if (is_guest_mode(vcpu) && max_irr_updated) {
- if (nested_exit_on_intr(vcpu))
- kvm_vcpu_exiting_guest_mode(vcpu);
- else
- kvm_make_request(KVM_REQ_EVENT, vcpu);
- }
+ if (is_guest_mode(vcpu) && max_irr_updated)
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
} else {
max_irr = kvm_lapic_find_highest_irr(vcpu);
}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index aabd3a2ec1bc..bfe0de3008a6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2542,7 +2542,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
@@ -2550,7 +2550,7 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
}
kvm_track_tsc_matching(vcpu);
- spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2780,9 +2780,9 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
kvm_make_mclock_inprogress_request(kvm);
/* no guest entries from this point */
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2800,15 +2800,15 @@ u64 get_kvmclock_ns(struct kvm *kvm)
unsigned long flags;
u64 ret;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
@@ -2902,13 +2902,13 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -6100,13 +6100,13 @@ set_pit2_out:
* is slightly ahead) here we risk going negative on unsigned
* 'system_time' when 'user_ns.clock' is very small.
*/
- spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
if (kvm->arch.use_master_clock)
now_ns = ka->master_kernel_ns;
else
now_ns = get_kvmclock_base_ns();
ka->kvmclock_offset = user_ns.clock - now_ns;
- spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
@@ -6906,7 +6906,7 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
}
static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val,
+ unsigned short port,
unsigned int count, bool in)
{
vcpu->arch.pio.port = port;
@@ -6914,10 +6914,8 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
vcpu->arch.pio.count = count;
vcpu->arch.pio.size = size;
- if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
- vcpu->arch.pio.count = 0;
+ if (!kernel_pio(vcpu, vcpu->arch.pio_data))
return 1;
- }
vcpu->run->exit_reason = KVM_EXIT_IO;
vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
@@ -6929,26 +6927,39 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
return 0;
}
-static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
- unsigned short port, void *val, unsigned int count)
+static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, unsigned int count)
{
- int ret;
+ WARN_ON(vcpu->arch.pio.count);
+ memset(vcpu->arch.pio_data, 0, size * count);
+ return emulator_pio_in_out(vcpu, size, port, count, true);
+}
- if (vcpu->arch.pio.count)
- goto data_avail;
+static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
+{
+ int size = vcpu->arch.pio.size;
+ unsigned count = vcpu->arch.pio.count;
+ memcpy(val, vcpu->arch.pio_data, size * count);
+ trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
+ vcpu->arch.pio.count = 0;
+}
- memset(vcpu->arch.pio_data, 0, size * count);
+static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, void *val, unsigned int count)
+{
+ if (vcpu->arch.pio.count) {
+ /* Complete previous iteration. */
+ } else {
+ int r = __emulator_pio_in(vcpu, size, port, count);
+ if (!r)
+ return r;
- ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
- if (ret) {
-data_avail:
- memcpy(val, vcpu->arch.pio_data, size * count);
- trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data);
- vcpu->arch.pio.count = 0;
- return 1;
+ /* Results already available, fall through. */
}
- return 0;
+ WARN_ON(count != vcpu->arch.pio.count);
+ complete_emulator_pio_in(vcpu, val);
+ return 1;
}
static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
@@ -6963,9 +6974,15 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size,
unsigned short port, const void *val,
unsigned int count)
{
+ int ret;
+
memcpy(vcpu->arch.pio_data, val, size * count);
trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data);
- return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+ ret = emulator_pio_in_out(vcpu, size, port, count, false);
+ if (ret)
+ vcpu->arch.pio.count = 0;
+
+ return ret;
}
static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
@@ -8139,9 +8156,9 @@ static void kvm_hyperv_tsc_notifier(void)
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -8783,9 +8800,17 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
kvm_run->cr8 = kvm_get_cr8(vcpu);
kvm_run->apic_base = kvm_get_apic_base(vcpu);
+
+ /*
+ * The call to kvm_ready_for_interrupt_injection() may end up in
+ * kvm_xen_has_interrupt() which may require the srcu lock to be
+ * held, to protect against changes in the vcpu_info address.
+ */
+ vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
kvm_run->ready_for_interrupt_injection =
pic_in_kernel(vcpu->kvm) ||
kvm_vcpu_ready_for_interrupt_injection(vcpu);
+ srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (is_smm(vcpu))
kvm_run->flags |= KVM_RUN_X86_SMM;
@@ -9643,14 +9668,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
- if (unlikely(kvm_vcpu_exit_request(vcpu))) {
+ if (vcpu->arch.apicv_active)
+ static_call(kvm_x86_sync_pir_to_irr)(vcpu);
+
+ if (unlikely(kvm_vcpu_exit_request(vcpu))) {
exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED;
break;
}
-
- if (vcpu->arch.apicv_active)
- static_call(kvm_x86_sync_pir_to_irr)(vcpu);
- }
+ }
/*
* Do this here before restoring debug registers on the host. And
@@ -11182,7 +11207,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
- spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
pvclock_update_vm_gtod_copy(kvm);
@@ -11392,7 +11417,8 @@ static int memslot_rmap_alloc(struct kvm_memory_slot *slot,
int level = i + 1;
int lpages = __kvm_mmu_slot_lpages(slot, npages, level);
- WARN_ON(slot->arch.rmap[i]);
+ if (slot->arch.rmap[i])
+ continue;
slot->arch.rmap[i] = kvcalloc(lpages, sz, GFP_KERNEL_ACCOUNT);
if (!slot->arch.rmap[i]) {
@@ -12367,44 +12393,81 @@ int kvm_sev_es_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned int bytes,
}
EXPORT_SYMBOL_GPL(kvm_sev_es_mmio_read);
-static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port);
+
+static int complete_sev_es_emulated_outs(struct kvm_vcpu *vcpu)
{
- memcpy(vcpu->arch.guest_ins_data, vcpu->arch.pio_data,
- vcpu->arch.pio.count * vcpu->arch.pio.size);
- vcpu->arch.pio.count = 0;
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+ vcpu->arch.pio.count = 0;
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_outs(vcpu, size, port);
return 1;
}
static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port)
{
- int ret;
-
- ret = emulator_pio_out_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret)
- return ret;
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ int ret = emulator_pio_out(vcpu, size, port, vcpu->arch.sev_pio_data, count);
+
+ /* memcpy done already by emulator_pio_out. */
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+ if (!ret)
+ break;
- vcpu->arch.pio.count = 0;
+ /* Emulation done by the kernel. */
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
+ }
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_outs;
return 0;
}
static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
- unsigned int port, void *data, unsigned int count)
+ unsigned int port);
+
+static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
{
- int ret;
+ unsigned count = vcpu->arch.pio.count;
+ complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
+ vcpu->arch.sev_pio_count -= count;
+ vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+}
- ret = emulator_pio_in_emulated(vcpu->arch.emulate_ctxt, size, port,
- data, count);
- if (ret) {
- vcpu->arch.pio.count = 0;
- } else {
- vcpu->arch.guest_ins_data = data;
- vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
+static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+{
+ int size = vcpu->arch.pio.size;
+ int port = vcpu->arch.pio.port;
+
+ advance_sev_es_emulated_ins(vcpu);
+ if (vcpu->arch.sev_pio_count)
+ return kvm_sev_es_ins(vcpu, size, port);
+ return 1;
+}
+
+static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
+ unsigned int port)
+{
+ for (;;) {
+ unsigned int count =
+ min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
+ if (!__emulator_pio_in(vcpu, size, port, count))
+ break;
+
+ /* Emulation done by the kernel. */
+ advance_sev_es_emulated_ins(vcpu);
+ if (!vcpu->arch.sev_pio_count)
+ return 1;
}
+ vcpu->arch.complete_userspace_io = complete_sev_es_emulated_ins;
return 0;
}
@@ -12412,8 +12475,10 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
unsigned int port, void *data, unsigned int count,
int in)
{
- return in ? kvm_sev_es_ins(vcpu, size, port, data, count)
- : kvm_sev_es_outs(vcpu, size, port, data, count);
+ vcpu->arch.sev_pio_data = data;
+ vcpu->arch.sev_pio_count = count;
+ return in ? kvm_sev_es_ins(vcpu, size, port)
+ : kvm_sev_es_outs(vcpu, size, port);
}
EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 9ea9c3dabe37..8f62baebd028 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -190,6 +190,7 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state)
int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
{
+ int err;
u8 rc = 0;
/*
@@ -216,13 +217,29 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v)
if (likely(slots->generation == ghc->generation &&
!kvm_is_error_hva(ghc->hva) && ghc->memslot)) {
/* Fast path */
- __get_user(rc, (u8 __user *)ghc->hva + offset);
- } else {
- /* Slow path */
- kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
- sizeof(rc));
+ pagefault_disable();
+ err = __get_user(rc, (u8 __user *)ghc->hva + offset);
+ pagefault_enable();
+ if (!err)
+ return rc;
}
+ /* Slow path */
+
+ /*
+ * This function gets called from kvm_vcpu_block() after setting the
+ * task to TASK_INTERRUPTIBLE, to see if it needs to wake immediately
+ * from a HLT. So we really mustn't sleep. If the page ended up absent
+ * at that point, just return 1 in order to trigger an immediate wake,
+ * and we'll end up getting called again from a context where we *can*
+ * fault in the page and wait for it.
+ */
+ if (in_atomic() || !task_is_running(current))
+ return 1;
+
+ kvm_read_guest_offset_cached(v->kvm, ghc, &rc, offset,
+ sizeof(rc));
+
return rc;
}
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index cf907e5bf2f2..a8a041609c5d 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -120,7 +120,8 @@ void flush_cache_page(struct vm_area_struct*,
#define flush_cache_vunmap(start,end) flush_cache_all()
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
-extern void flush_dcache_page(struct page*);
+void flush_dcache_page(struct page *);
+void flush_dcache_folio(struct folio *);
void local_flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
@@ -137,7 +138,9 @@ void local_flush_cache_page(struct vm_area_struct *vma,
#define flush_cache_vunmap(start,end) do { } while (0)
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
#define flush_dcache_page(page) do { } while (0)
+static inline void flush_dcache_folio(struct folio *folio) { }
#define flush_icache_range local_flush_icache_range
#define flush_cache_page(vma, addr, pfn) do { } while (0)
diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c
index ddd1fe3db474..07b642c1916a 100644
--- a/arch/xtensa/platforms/iss/simdisk.c
+++ b/arch/xtensa/platforms/iss/simdisk.c
@@ -258,6 +258,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
struct proc_dir_entry *procdir)
{
char tmp[2] = { '0' + which, 0 };
+ int err = -ENOMEM;
dev->fd = -1;
dev->filename = NULL;
@@ -266,7 +267,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd = blk_alloc_disk(NUMA_NO_NODE);
if (!dev->gd)
- return -ENOMEM;
+ goto out;
dev->gd->major = simdisk_major;
dev->gd->first_minor = which;
dev->gd->minors = SIMDISK_MINORS;
@@ -274,10 +275,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which,
dev->gd->private_data = dev;
snprintf(dev->gd->disk_name, 32, "simdisk%d", which);
set_capacity(dev->gd, 0);
- add_disk(dev->gd);
+ err = add_disk(dev->gd);
+ if (err)
+ goto out_cleanup_disk;
dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev);
+
return 0;
+
+out_cleanup_disk:
+ blk_cleanup_disk(dev->gd);
+out:
+ return err;
}
static int __init simdisk_init(void)
diff --git a/block/Makefile b/block/Makefile
index 74df168729ec..44df57e562bf 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-y := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
genhd.o ioprio.o badblocks.o partitions/ blk-rq-qos.o \
- disk-events.o
+ disk-events.o blk-ia-ranges.o
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_BLK_DEV_BSG_COMMON) += bsg.o
@@ -36,6 +36,6 @@ obj-$(CONFIG_BLK_DEBUG_FS) += blk-mq-debugfs.o
obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
obj-$(CONFIG_BLK_SED_OPAL) += sed-opal.o
obj-$(CONFIG_BLK_PM) += blk-pm.o
-obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += keyslot-manager.o blk-crypto.o
+obj-$(CONFIG_BLK_INLINE_ENCRYPTION) += blk-crypto.o blk-crypto-profile.o
obj-$(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) += blk-crypto-fallback.o
obj-$(CONFIG_BLOCK_HOLDER_DEPRECATED) += holder.o
diff --git a/block/bdev.c b/block/bdev.c
index cff0bb3a4578..7e6156203a71 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -964,9 +964,11 @@ EXPORT_SYMBOL(blkdev_put);
* @pathname: special file representing the block device
* @dev: return value of the block device's dev_t
*
- * Get a reference to the blockdevice at @pathname in the current
- * namespace if possible and return it. Return ERR_PTR(error)
- * otherwise.
+ * Lookup the block device's dev_t at @pathname in the current
+ * namespace if possible and return it by @dev.
+ *
+ * RETURNS:
+ * 0 if succeeded, errno otherwise.
*/
int lookup_bdev(const char *pathname, dev_t *dev)
{
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index 882ec4bc51ad..24a5c5329bcd 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -463,7 +463,7 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
{
if (blkg_rwstat_init(&stats->bytes, gfp) ||
blkg_rwstat_init(&stats->ios, gfp))
- return -ENOMEM;
+ goto error;
#ifdef CONFIG_BFQ_CGROUP_DEBUG
if (blkg_rwstat_init(&stats->merged, gfp) ||
@@ -476,13 +476,15 @@ static int bfqg_stats_init(struct bfqg_stats *stats, gfp_t gfp)
bfq_stat_init(&stats->dequeue, gfp) ||
bfq_stat_init(&stats->group_wait_time, gfp) ||
bfq_stat_init(&stats->idle_time, gfp) ||
- bfq_stat_init(&stats->empty_time, gfp)) {
- bfqg_stats_exit(stats);
- return -ENOMEM;
- }
+ bfq_stat_init(&stats->empty_time, gfp))
+ goto error;
#endif
return 0;
+
+error:
+ bfqg_stats_exit(stats);
+ return -ENOMEM;
}
static struct bfq_group_data *cpd_to_bfqgd(struct blkcg_policy_data *cpd)
diff --git a/block/bio.c b/block/bio.c
index 4f397ba47db5..15ab0d6d1c06 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1033,52 +1033,40 @@ int bio_add_page(struct bio *bio, struct page *page,
}
EXPORT_SYMBOL(bio_add_page);
-void bio_release_pages(struct bio *bio, bool mark_dirty)
+void __bio_release_pages(struct bio *bio, bool mark_dirty)
{
struct bvec_iter_all iter_all;
struct bio_vec *bvec;
- if (bio_flagged(bio, BIO_NO_PAGE_REF))
- return;
-
bio_for_each_segment_all(bvec, bio, iter_all) {
if (mark_dirty && !PageCompound(bvec->bv_page))
set_page_dirty_lock(bvec->bv_page);
put_page(bvec->bv_page);
}
}
-EXPORT_SYMBOL_GPL(bio_release_pages);
+EXPORT_SYMBOL_GPL(__bio_release_pages);
-static void __bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
{
+ size_t size = iov_iter_count(iter);
+
WARN_ON_ONCE(bio->bi_max_vecs);
+ if (bio_op(bio) == REQ_OP_ZONE_APPEND) {
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
+ size_t max_sectors = queue_max_zone_append_sectors(q);
+
+ size = min(size, max_sectors << SECTOR_SHIFT);
+ }
+
bio->bi_vcnt = iter->nr_segs;
bio->bi_io_vec = (struct bio_vec *)iter->bvec;
bio->bi_iter.bi_bvec_done = iter->iov_offset;
- bio->bi_iter.bi_size = iter->count;
+ bio->bi_iter.bi_size = size;
bio_set_flag(bio, BIO_NO_PAGE_REF);
bio_set_flag(bio, BIO_CLONED);
}
-static int bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter)
-{
- __bio_iov_bvec_set(bio, iter);
- iov_iter_advance(iter, iter->count);
- return 0;
-}
-
-static int bio_iov_bvec_set_append(struct bio *bio, struct iov_iter *iter)
-{
- struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- struct iov_iter i = *iter;
-
- iov_iter_truncate(&i, queue_max_zone_append_sectors(q) << 9);
- __bio_iov_bvec_set(bio, &i);
- iov_iter_advance(iter, i.count);
- return 0;
-}
-
static void bio_put_pages(struct page **pages, size_t size, size_t off)
{
size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE);
@@ -1220,9 +1208,9 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
int ret = 0;
if (iov_iter_is_bvec(iter)) {
- if (bio_op(bio) == REQ_OP_ZONE_APPEND)
- return bio_iov_bvec_set_append(bio, iter);
- return bio_iov_bvec_set(bio, iter);
+ bio_iov_bvec_set(bio, iter);
+ iov_iter_advance(iter, bio->bi_iter.bi_size);
+ return 0;
}
do {
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 8908298d6ad3..88b1fce90520 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -634,6 +634,14 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
q = bdev_get_queue(bdev);
+ /*
+ * blkcg_deactivate_policy() requires queue to be frozen, we can grab
+ * q_usage_counter to prevent concurrent with blkcg_deactivate_policy().
+ */
+ ret = blk_queue_enter(q, 0);
+ if (ret)
+ return ret;
+
rcu_read_lock();
spin_lock_irq(&q->queue_lock);
@@ -703,6 +711,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol,
goto success;
}
success:
+ blk_queue_exit(q);
ctx->bdev = bdev;
ctx->blkg = blkg;
ctx->body = input;
@@ -715,6 +724,7 @@ fail_unlock:
rcu_read_unlock();
fail:
blkdev_put_no_open(bdev);
+ blk_queue_exit(q);
/*
* If queue was bypassing, we should retry. Do so after a
* short msleep(). It isn't strictly necessary but queue
diff --git a/block/blk-core.c b/block/blk-core.c
index d0c2e11411d0..fd389a16013c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -389,7 +389,7 @@ EXPORT_SYMBOL(blk_cleanup_queue);
static bool blk_try_enter_queue(struct request_queue *q, bool pm)
{
rcu_read_lock();
- if (!percpu_ref_tryget_live(&q->q_usage_counter))
+ if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter))
goto fail;
/*
@@ -404,7 +404,7 @@ static bool blk_try_enter_queue(struct request_queue *q, bool pm)
return true;
fail_put:
- percpu_ref_put(&q->q_usage_counter);
+ blk_queue_exit(q);
fail:
rcu_read_unlock();
return false;
@@ -1080,7 +1080,7 @@ EXPORT_SYMBOL(submit_bio);
*/
int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
{
- struct request_queue *q = bio->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue(bio->bi_bdev);
blk_qc_t cookie = READ_ONCE(bio->bi_cookie);
int ret;
@@ -1089,7 +1089,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
return 0;
if (current->plug)
- blk_flush_plug_list(current->plug, false);
+ blk_flush_plug(current->plug, false);
if (blk_queue_enter(q, BLK_MQ_REQ_NOWAIT))
return 0;
@@ -1550,11 +1550,12 @@ void blk_start_plug_nr_ios(struct blk_plug *plug, unsigned short nr_ios)
if (tsk->plug)
return;
- INIT_LIST_HEAD(&plug->mq_list);
+ plug->mq_list = NULL;
plug->cached_rq = NULL;
plug->nr_ios = min_t(unsigned short, nr_ios, BLK_MAX_REQUEST_COUNT);
plug->rq_count = 0;
plug->multiple_queues = false;
+ plug->has_elevator = false;
plug->nowait = false;
INIT_LIST_HEAD(&plug->cb_list);
@@ -1636,11 +1637,11 @@ struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data,
}
EXPORT_SYMBOL(blk_check_plugged);
-void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule)
{
- flush_plug_callbacks(plug, from_schedule);
-
- if (!list_empty(&plug->mq_list))
+ if (!list_empty(&plug->cb_list))
+ flush_plug_callbacks(plug, from_schedule);
+ if (!rq_list_empty(plug->mq_list))
blk_mq_flush_plug_list(plug, from_schedule);
if (unlikely(!from_schedule && plug->cached_rq))
blk_mq_free_plug_rqs(plug);
@@ -1658,11 +1659,10 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
*/
void blk_finish_plug(struct blk_plug *plug)
{
- if (plug != current->plug)
- return;
- blk_flush_plug_list(plug, false);
-
- current->plug = NULL;
+ if (plug == current->plug) {
+ blk_flush_plug(plug, false);
+ current->plug = NULL;
+ }
}
EXPORT_SYMBOL(blk_finish_plug);
diff --git a/block/blk-crypto-fallback.c b/block/blk-crypto-fallback.c
index ec4c7823541c..c87aba8584c6 100644
--- a/block/blk-crypto-fallback.c
+++ b/block/blk-crypto-fallback.c
@@ -12,9 +12,9 @@
#include <crypto/skcipher.h>
#include <linux/blk-cgroup.h>
#include <linux/blk-crypto.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/blkdev.h>
#include <linux/crypto.h>
-#include <linux/keyslot-manager.h>
#include <linux/mempool.h>
#include <linux/module.h>
#include <linux/random.h>
@@ -73,12 +73,12 @@ static mempool_t *bio_fallback_crypt_ctx_pool;
static DEFINE_MUTEX(tfms_init_lock);
static bool tfms_inited[BLK_ENCRYPTION_MODE_MAX];
-static struct blk_crypto_keyslot {
+static struct blk_crypto_fallback_keyslot {
enum blk_crypto_mode_num crypto_mode;
struct crypto_skcipher *tfms[BLK_ENCRYPTION_MODE_MAX];
} *blk_crypto_keyslots;
-static struct blk_keyslot_manager blk_crypto_ksm;
+static struct blk_crypto_profile blk_crypto_fallback_profile;
static struct workqueue_struct *blk_crypto_wq;
static mempool_t *blk_crypto_bounce_page_pool;
static struct bio_set crypto_bio_split;
@@ -89,9 +89,9 @@ static struct bio_set crypto_bio_split;
*/
static u8 blank_key[BLK_CRYPTO_MAX_KEY_SIZE];
-static void blk_crypto_evict_keyslot(unsigned int slot)
+static void blk_crypto_fallback_evict_keyslot(unsigned int slot)
{
- struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ struct blk_crypto_fallback_keyslot *slotp = &blk_crypto_keyslots[slot];
enum blk_crypto_mode_num crypto_mode = slotp->crypto_mode;
int err;
@@ -104,45 +104,41 @@ static void blk_crypto_evict_keyslot(unsigned int slot)
slotp->crypto_mode = BLK_ENCRYPTION_MODE_INVALID;
}
-static int blk_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot)
+static int
+blk_crypto_fallback_keyslot_program(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
{
- struct blk_crypto_keyslot *slotp = &blk_crypto_keyslots[slot];
+ struct blk_crypto_fallback_keyslot *slotp = &blk_crypto_keyslots[slot];
const enum blk_crypto_mode_num crypto_mode =
key->crypto_cfg.crypto_mode;
int err;
if (crypto_mode != slotp->crypto_mode &&
slotp->crypto_mode != BLK_ENCRYPTION_MODE_INVALID)
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
slotp->crypto_mode = crypto_mode;
err = crypto_skcipher_setkey(slotp->tfms[crypto_mode], key->raw,
key->size);
if (err) {
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
return err;
}
return 0;
}
-static int blk_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot)
+static int blk_crypto_fallback_keyslot_evict(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot)
{
- blk_crypto_evict_keyslot(slot);
+ blk_crypto_fallback_evict_keyslot(slot);
return 0;
}
-/*
- * The crypto API fallback KSM ops - only used for a bio when it specifies a
- * blk_crypto_key that was not supported by the device's inline encryption
- * hardware.
- */
-static const struct blk_ksm_ll_ops blk_crypto_ksm_ll_ops = {
- .keyslot_program = blk_crypto_keyslot_program,
- .keyslot_evict = blk_crypto_keyslot_evict,
+static const struct blk_crypto_ll_ops blk_crypto_fallback_ll_ops = {
+ .keyslot_program = blk_crypto_fallback_keyslot_program,
+ .keyslot_evict = blk_crypto_fallback_keyslot_evict,
};
static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio)
@@ -160,7 +156,7 @@ static void blk_crypto_fallback_encrypt_endio(struct bio *enc_bio)
bio_endio(src_bio);
}
-static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
+static struct bio *blk_crypto_fallback_clone_bio(struct bio *bio_src)
{
struct bvec_iter iter;
struct bio_vec bv;
@@ -187,13 +183,14 @@ static struct bio *blk_crypto_clone_bio(struct bio *bio_src)
return bio;
}
-static bool blk_crypto_alloc_cipher_req(struct blk_ksm_keyslot *slot,
- struct skcipher_request **ciph_req_ret,
- struct crypto_wait *wait)
+static bool
+blk_crypto_fallback_alloc_cipher_req(struct blk_crypto_keyslot *slot,
+ struct skcipher_request **ciph_req_ret,
+ struct crypto_wait *wait)
{
struct skcipher_request *ciph_req;
- const struct blk_crypto_keyslot *slotp;
- int keyslot_idx = blk_ksm_get_slot_idx(slot);
+ const struct blk_crypto_fallback_keyslot *slotp;
+ int keyslot_idx = blk_crypto_keyslot_index(slot);
slotp = &blk_crypto_keyslots[keyslot_idx];
ciph_req = skcipher_request_alloc(slotp->tfms[slotp->crypto_mode],
@@ -210,7 +207,7 @@ static bool blk_crypto_alloc_cipher_req(struct blk_ksm_keyslot *slot,
return true;
}
-static bool blk_crypto_split_bio_if_needed(struct bio **bio_ptr)
+static bool blk_crypto_fallback_split_bio_if_needed(struct bio **bio_ptr)
{
struct bio *bio = *bio_ptr;
unsigned int i = 0;
@@ -265,7 +262,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
{
struct bio *src_bio, *enc_bio;
struct bio_crypt_ctx *bc;
- struct blk_ksm_keyslot *slot;
+ struct blk_crypto_keyslot *slot;
int data_unit_size;
struct skcipher_request *ciph_req = NULL;
DECLARE_CRYPTO_WAIT(wait);
@@ -277,7 +274,7 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
blk_status_t blk_st;
/* Split the bio if it's too big for single page bvec */
- if (!blk_crypto_split_bio_if_needed(bio_ptr))
+ if (!blk_crypto_fallback_split_bio_if_needed(bio_ptr))
return false;
src_bio = *bio_ptr;
@@ -285,24 +282,25 @@ static bool blk_crypto_fallback_encrypt_bio(struct bio **bio_ptr)
data_unit_size = bc->bc_key->crypto_cfg.data_unit_size;
/* Allocate bounce bio for encryption */
- enc_bio = blk_crypto_clone_bio(src_bio);
+ enc_bio = blk_crypto_fallback_clone_bio(src_bio);
if (!enc_bio) {
src_bio->bi_status = BLK_STS_RESOURCE;
return false;
}
/*
- * Use the crypto API fallback keyslot manager to get a crypto_skcipher
- * for the algorithm and key specified for this bio.
+ * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for
+ * this bio's algorithm and key.
*/
- blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot);
+ blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile,
+ bc->bc_key, &slot);
if (blk_st != BLK_STS_OK) {
src_bio->bi_status = blk_st;
goto out_put_enc_bio;
}
/* and then allocate an skcipher_request for it */
- if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) {
+ if (!blk_crypto_fallback_alloc_cipher_req(slot, &ciph_req, &wait)) {
src_bio->bi_status = BLK_STS_RESOURCE;
goto out_release_keyslot;
}
@@ -363,7 +361,7 @@ out_free_bounce_pages:
out_free_ciph_req:
skcipher_request_free(ciph_req);
out_release_keyslot:
- blk_ksm_put_slot(slot);
+ blk_crypto_put_keyslot(slot);
out_put_enc_bio:
if (enc_bio)
bio_put(enc_bio);
@@ -381,7 +379,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
container_of(work, struct bio_fallback_crypt_ctx, work);
struct bio *bio = f_ctx->bio;
struct bio_crypt_ctx *bc = &f_ctx->crypt_ctx;
- struct blk_ksm_keyslot *slot;
+ struct blk_crypto_keyslot *slot;
struct skcipher_request *ciph_req = NULL;
DECLARE_CRYPTO_WAIT(wait);
u64 curr_dun[BLK_CRYPTO_DUN_ARRAY_SIZE];
@@ -394,17 +392,18 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
blk_status_t blk_st;
/*
- * Use the crypto API fallback keyslot manager to get a crypto_skcipher
- * for the algorithm and key specified for this bio.
+ * Get a blk-crypto-fallback keyslot that contains a crypto_skcipher for
+ * this bio's algorithm and key.
*/
- blk_st = blk_ksm_get_slot_for_key(&blk_crypto_ksm, bc->bc_key, &slot);
+ blk_st = blk_crypto_get_keyslot(&blk_crypto_fallback_profile,
+ bc->bc_key, &slot);
if (blk_st != BLK_STS_OK) {
bio->bi_status = blk_st;
goto out_no_keyslot;
}
/* and then allocate an skcipher_request for it */
- if (!blk_crypto_alloc_cipher_req(slot, &ciph_req, &wait)) {
+ if (!blk_crypto_fallback_alloc_cipher_req(slot, &ciph_req, &wait)) {
bio->bi_status = BLK_STS_RESOURCE;
goto out;
}
@@ -435,7 +434,7 @@ static void blk_crypto_fallback_decrypt_bio(struct work_struct *work)
out:
skcipher_request_free(ciph_req);
- blk_ksm_put_slot(slot);
+ blk_crypto_put_keyslot(slot);
out_no_keyslot:
mempool_free(f_ctx, bio_fallback_crypt_ctx_pool);
bio_endio(bio);
@@ -474,9 +473,9 @@ static void blk_crypto_fallback_decrypt_endio(struct bio *bio)
* @bio_ptr: pointer to the bio to prepare
*
* If bio is doing a WRITE operation, this splits the bio into two parts if it's
- * too big (see blk_crypto_split_bio_if_needed). It then allocates a bounce bio
- * for the first part, encrypts it, and update bio_ptr to point to the bounce
- * bio.
+ * too big (see blk_crypto_fallback_split_bio_if_needed()). It then allocates a
+ * bounce bio for the first part, encrypts it, and updates bio_ptr to point to
+ * the bounce bio.
*
* For a READ operation, we mark the bio for decryption by using bi_private and
* bi_end_io.
@@ -500,8 +499,8 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr)
return false;
}
- if (!blk_ksm_crypto_cfg_supported(&blk_crypto_ksm,
- &bc->bc_key->crypto_cfg)) {
+ if (!__blk_crypto_cfg_supported(&blk_crypto_fallback_profile,
+ &bc->bc_key->crypto_cfg)) {
bio->bi_status = BLK_STS_NOTSUPP;
return false;
}
@@ -527,7 +526,7 @@ bool blk_crypto_fallback_bio_prep(struct bio **bio_ptr)
int blk_crypto_fallback_evict_key(const struct blk_crypto_key *key)
{
- return blk_ksm_evict_key(&blk_crypto_ksm, key);
+ return __blk_crypto_evict_key(&blk_crypto_fallback_profile, key);
}
static bool blk_crypto_fallback_inited;
@@ -535,6 +534,7 @@ static int blk_crypto_fallback_init(void)
{
int i;
int err;
+ struct blk_crypto_profile *profile = &blk_crypto_fallback_profile;
if (blk_crypto_fallback_inited)
return 0;
@@ -545,24 +545,24 @@ static int blk_crypto_fallback_init(void)
if (err)
goto out;
- err = blk_ksm_init(&blk_crypto_ksm, blk_crypto_num_keyslots);
+ err = blk_crypto_profile_init(profile, blk_crypto_num_keyslots);
if (err)
goto fail_free_bioset;
err = -ENOMEM;
- blk_crypto_ksm.ksm_ll_ops = blk_crypto_ksm_ll_ops;
- blk_crypto_ksm.max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
+ profile->ll_ops = blk_crypto_fallback_ll_ops;
+ profile->max_dun_bytes_supported = BLK_CRYPTO_MAX_IV_SIZE;
/* All blk-crypto modes have a crypto API fallback. */
for (i = 0; i < BLK_ENCRYPTION_MODE_MAX; i++)
- blk_crypto_ksm.crypto_modes_supported[i] = 0xFFFFFFFF;
- blk_crypto_ksm.crypto_modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0;
+ profile->modes_supported[i] = 0xFFFFFFFF;
+ profile->modes_supported[BLK_ENCRYPTION_MODE_INVALID] = 0;
blk_crypto_wq = alloc_workqueue("blk_crypto_wq",
WQ_UNBOUND | WQ_HIGHPRI |
WQ_MEM_RECLAIM, num_online_cpus());
if (!blk_crypto_wq)
- goto fail_free_ksm;
+ goto fail_destroy_profile;
blk_crypto_keyslots = kcalloc(blk_crypto_num_keyslots,
sizeof(blk_crypto_keyslots[0]),
@@ -596,8 +596,8 @@ fail_free_keyslots:
kfree(blk_crypto_keyslots);
fail_free_wq:
destroy_workqueue(blk_crypto_wq);
-fail_free_ksm:
- blk_ksm_destroy(&blk_crypto_ksm);
+fail_destroy_profile:
+ blk_crypto_profile_destroy(profile);
fail_free_bioset:
bioset_exit(&crypto_bio_split);
out:
@@ -611,7 +611,7 @@ out:
int blk_crypto_fallback_start_using_mode(enum blk_crypto_mode_num mode_num)
{
const char *cipher_str = blk_crypto_modes[mode_num].cipher_str;
- struct blk_crypto_keyslot *slotp;
+ struct blk_crypto_fallback_keyslot *slotp;
unsigned int i;
int err = 0;
diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c
new file mode 100644
index 000000000000..605ba0626a5c
--- /dev/null
+++ b/block/blk-crypto-profile.c
@@ -0,0 +1,565 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2019 Google LLC
+ */
+
+/**
+ * DOC: blk-crypto profiles
+ *
+ * 'struct blk_crypto_profile' contains all generic inline encryption-related
+ * state for a particular inline encryption device. blk_crypto_profile serves
+ * as the way that drivers for inline encryption hardware expose their crypto
+ * capabilities and certain functions (e.g., functions to program and evict
+ * keys) to upper layers. Device drivers that want to support inline encryption
+ * construct a crypto profile, then associate it with the disk's request_queue.
+ *
+ * If the device has keyslots, then its blk_crypto_profile also handles managing
+ * these keyslots in a device-independent way, using the driver-provided
+ * functions to program and evict keys as needed. This includes keeping track
+ * of which key and how many I/O requests are using each keyslot, getting
+ * keyslots for I/O requests, and handling key eviction requests.
+ *
+ * For more information, see Documentation/block/inline-encryption.rst.
+ */
+
+#define pr_fmt(fmt) "blk-crypto: " fmt
+
+#include <linux/blk-crypto-profile.h>
+#include <linux/device.h>
+#include <linux/atomic.h>
+#include <linux/mutex.h>
+#include <linux/pm_runtime.h>
+#include <linux/wait.h>
+#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
+
+struct blk_crypto_keyslot {
+ atomic_t slot_refs;
+ struct list_head idle_slot_node;
+ struct hlist_node hash_node;
+ const struct blk_crypto_key *key;
+ struct blk_crypto_profile *profile;
+};
+
+static inline void blk_crypto_hw_enter(struct blk_crypto_profile *profile)
+{
+ /*
+ * Calling into the driver requires profile->lock held and the device
+ * resumed. But we must resume the device first, since that can acquire
+ * and release profile->lock via blk_crypto_reprogram_all_keys().
+ */
+ if (profile->dev)
+ pm_runtime_get_sync(profile->dev);
+ down_write(&profile->lock);
+}
+
+static inline void blk_crypto_hw_exit(struct blk_crypto_profile *profile)
+{
+ up_write(&profile->lock);
+ if (profile->dev)
+ pm_runtime_put_sync(profile->dev);
+}
+
+/**
+ * blk_crypto_profile_init() - Initialize a blk_crypto_profile
+ * @profile: the blk_crypto_profile to initialize
+ * @num_slots: the number of keyslots
+ *
+ * Storage drivers must call this when starting to set up a blk_crypto_profile,
+ * before filling in additional fields.
+ *
+ * Return: 0 on success, or else a negative error code.
+ */
+int blk_crypto_profile_init(struct blk_crypto_profile *profile,
+ unsigned int num_slots)
+{
+ unsigned int slot;
+ unsigned int i;
+ unsigned int slot_hashtable_size;
+
+ memset(profile, 0, sizeof(*profile));
+ init_rwsem(&profile->lock);
+
+ if (num_slots == 0)
+ return 0;
+
+ /* Initialize keyslot management data. */
+
+ profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]),
+ GFP_KERNEL);
+ if (!profile->slots)
+ return -ENOMEM;
+
+ profile->num_slots = num_slots;
+
+ init_waitqueue_head(&profile->idle_slots_wait_queue);
+ INIT_LIST_HEAD(&profile->idle_slots);
+
+ for (slot = 0; slot < num_slots; slot++) {
+ profile->slots[slot].profile = profile;
+ list_add_tail(&profile->slots[slot].idle_slot_node,
+ &profile->idle_slots);
+ }
+
+ spin_lock_init(&profile->idle_slots_lock);
+
+ slot_hashtable_size = roundup_pow_of_two(num_slots);
+ /*
+ * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2
+ * buckets. This only makes a difference when there is only 1 keyslot.
+ */
+ if (slot_hashtable_size < 2)
+ slot_hashtable_size = 2;
+
+ profile->log_slot_ht_size = ilog2(slot_hashtable_size);
+ profile->slot_hashtable =
+ kvmalloc_array(slot_hashtable_size,
+ sizeof(profile->slot_hashtable[0]), GFP_KERNEL);
+ if (!profile->slot_hashtable)
+ goto err_destroy;
+ for (i = 0; i < slot_hashtable_size; i++)
+ INIT_HLIST_HEAD(&profile->slot_hashtable[i]);
+
+ return 0;
+
+err_destroy:
+ blk_crypto_profile_destroy(profile);
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_profile_init);
+
+static void blk_crypto_profile_destroy_callback(void *profile)
+{
+ blk_crypto_profile_destroy(profile);
+}
+
+/**
+ * devm_blk_crypto_profile_init() - Resource-managed blk_crypto_profile_init()
+ * @dev: the device which owns the blk_crypto_profile
+ * @profile: the blk_crypto_profile to initialize
+ * @num_slots: the number of keyslots
+ *
+ * Like blk_crypto_profile_init(), but causes blk_crypto_profile_destroy() to be
+ * called automatically on driver detach.
+ *
+ * Return: 0 on success, or else a negative error code.
+ */
+int devm_blk_crypto_profile_init(struct device *dev,
+ struct blk_crypto_profile *profile,
+ unsigned int num_slots)
+{
+ int err = blk_crypto_profile_init(profile, num_slots);
+
+ if (err)
+ return err;
+
+ return devm_add_action_or_reset(dev,
+ blk_crypto_profile_destroy_callback,
+ profile);
+}
+EXPORT_SYMBOL_GPL(devm_blk_crypto_profile_init);
+
+static inline struct hlist_head *
+blk_crypto_hash_bucket_for_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ return &profile->slot_hashtable[
+ hash_ptr(key, profile->log_slot_ht_size)];
+}
+
+static void
+blk_crypto_remove_slot_from_lru_list(struct blk_crypto_keyslot *slot)
+{
+ struct blk_crypto_profile *profile = slot->profile;
+ unsigned long flags;
+
+ spin_lock_irqsave(&profile->idle_slots_lock, flags);
+ list_del(&slot->idle_slot_node);
+ spin_unlock_irqrestore(&profile->idle_slots_lock, flags);
+}
+
+static struct blk_crypto_keyslot *
+blk_crypto_find_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ const struct hlist_head *head =
+ blk_crypto_hash_bucket_for_key(profile, key);
+ struct blk_crypto_keyslot *slotp;
+
+ hlist_for_each_entry(slotp, head, hash_node) {
+ if (slotp->key == key)
+ return slotp;
+ }
+ return NULL;
+}
+
+static struct blk_crypto_keyslot *
+blk_crypto_find_and_grab_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ struct blk_crypto_keyslot *slot;
+
+ slot = blk_crypto_find_keyslot(profile, key);
+ if (!slot)
+ return NULL;
+ if (atomic_inc_return(&slot->slot_refs) == 1) {
+ /* Took first reference to this slot; remove it from LRU list */
+ blk_crypto_remove_slot_from_lru_list(slot);
+ }
+ return slot;
+}
+
+/**
+ * blk_crypto_keyslot_index() - Get the index of a keyslot
+ * @slot: a keyslot that blk_crypto_get_keyslot() returned
+ *
+ * Return: the 0-based index of the keyslot within the device's keyslots.
+ */
+unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot)
+{
+ return slot - slot->profile->slots;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_keyslot_index);
+
+/**
+ * blk_crypto_get_keyslot() - Get a keyslot for a key, if needed.
+ * @profile: the crypto profile of the device the key will be used on
+ * @key: the key that will be used
+ * @slot_ptr: If a keyslot is allocated, an opaque pointer to the keyslot struct
+ * will be stored here; otherwise NULL will be stored here.
+ *
+ * If the device has keyslots, this gets a keyslot that's been programmed with
+ * the specified key. If the key is already in a slot, this reuses it;
+ * otherwise this waits for a slot to become idle and programs the key into it.
+ *
+ * This must be paired with a call to blk_crypto_put_keyslot().
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ * Return: BLK_STS_OK on success, meaning that either a keyslot was allocated or
+ * one wasn't needed; or a blk_status_t error on failure.
+ */
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ struct blk_crypto_keyslot **slot_ptr)
+{
+ struct blk_crypto_keyslot *slot;
+ int slot_idx;
+ int err;
+
+ *slot_ptr = NULL;
+
+ /*
+ * If the device has no concept of "keyslots", then there is no need to
+ * get one.
+ */
+ if (profile->num_slots == 0)
+ return BLK_STS_OK;
+
+ down_read(&profile->lock);
+ slot = blk_crypto_find_and_grab_keyslot(profile, key);
+ up_read(&profile->lock);
+ if (slot)
+ goto success;
+
+ for (;;) {
+ blk_crypto_hw_enter(profile);
+ slot = blk_crypto_find_and_grab_keyslot(profile, key);
+ if (slot) {
+ blk_crypto_hw_exit(profile);
+ goto success;
+ }
+
+ /*
+ * If we're here, that means there wasn't a slot that was
+ * already programmed with the key. So try to program it.
+ */
+ if (!list_empty(&profile->idle_slots))
+ break;
+
+ blk_crypto_hw_exit(profile);
+ wait_event(profile->idle_slots_wait_queue,
+ !list_empty(&profile->idle_slots));
+ }
+
+ slot = list_first_entry(&profile->idle_slots, struct blk_crypto_keyslot,
+ idle_slot_node);
+ slot_idx = blk_crypto_keyslot_index(slot);
+
+ err = profile->ll_ops.keyslot_program(profile, key, slot_idx);
+ if (err) {
+ wake_up(&profile->idle_slots_wait_queue);
+ blk_crypto_hw_exit(profile);
+ return errno_to_blk_status(err);
+ }
+
+ /* Move this slot to the hash list for the new key. */
+ if (slot->key)
+ hlist_del(&slot->hash_node);
+ slot->key = key;
+ hlist_add_head(&slot->hash_node,
+ blk_crypto_hash_bucket_for_key(profile, key));
+
+ atomic_set(&slot->slot_refs, 1);
+
+ blk_crypto_remove_slot_from_lru_list(slot);
+
+ blk_crypto_hw_exit(profile);
+success:
+ *slot_ptr = slot;
+ return BLK_STS_OK;
+}
+
+/**
+ * blk_crypto_put_keyslot() - Release a reference to a keyslot
+ * @slot: The keyslot to release the reference of (may be NULL).
+ *
+ * Context: Any context.
+ */
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot)
+{
+ struct blk_crypto_profile *profile;
+ unsigned long flags;
+
+ if (!slot)
+ return;
+
+ profile = slot->profile;
+
+ if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
+ &profile->idle_slots_lock, flags)) {
+ list_add_tail(&slot->idle_slot_node, &profile->idle_slots);
+ spin_unlock_irqrestore(&profile->idle_slots_lock, flags);
+ wake_up(&profile->idle_slots_wait_queue);
+ }
+}
+
+/**
+ * __blk_crypto_cfg_supported() - Check whether the given crypto profile
+ * supports the given crypto configuration.
+ * @profile: the crypto profile to check
+ * @cfg: the crypto configuration to check for
+ *
+ * Return: %true if @profile supports the given @cfg.
+ */
+bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
+ const struct blk_crypto_config *cfg)
+{
+ if (!profile)
+ return false;
+ if (!(profile->modes_supported[cfg->crypto_mode] & cfg->data_unit_size))
+ return false;
+ if (profile->max_dun_bytes_supported < cfg->dun_bytes)
+ return false;
+ return true;
+}
+
+/**
+ * __blk_crypto_evict_key() - Evict a key from a device.
+ * @profile: the crypto profile of the device
+ * @key: the key to evict. It must not still be used in any I/O.
+ *
+ * If the device has keyslots, this finds the keyslot (if any) that contains the
+ * specified key and calls the driver's keyslot_evict function to evict it.
+ *
+ * Otherwise, this just calls the driver's keyslot_evict function if it is
+ * implemented, passing just the key (without any particular keyslot). This
+ * allows layered devices to evict the key from their underlying devices.
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
+ * if the keyslot is still in use, or another -errno value on other
+ * error.
+ */
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key)
+{
+ struct blk_crypto_keyslot *slot;
+ int err = 0;
+
+ if (profile->num_slots == 0) {
+ if (profile->ll_ops.keyslot_evict) {
+ blk_crypto_hw_enter(profile);
+ err = profile->ll_ops.keyslot_evict(profile, key, -1);
+ blk_crypto_hw_exit(profile);
+ return err;
+ }
+ return 0;
+ }
+
+ blk_crypto_hw_enter(profile);
+ slot = blk_crypto_find_keyslot(profile, key);
+ if (!slot)
+ goto out_unlock;
+
+ if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
+ err = -EBUSY;
+ goto out_unlock;
+ }
+ err = profile->ll_ops.keyslot_evict(profile, key,
+ blk_crypto_keyslot_index(slot));
+ if (err)
+ goto out_unlock;
+
+ hlist_del(&slot->hash_node);
+ slot->key = NULL;
+ err = 0;
+out_unlock:
+ blk_crypto_hw_exit(profile);
+ return err;
+}
+
+/**
+ * blk_crypto_reprogram_all_keys() - Re-program all keyslots.
+ * @profile: The crypto profile
+ *
+ * Re-program all keyslots that are supposed to have a key programmed. This is
+ * intended only for use by drivers for hardware that loses its keys on reset.
+ *
+ * Context: Process context. Takes and releases profile->lock.
+ */
+void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile)
+{
+ unsigned int slot;
+
+ if (profile->num_slots == 0)
+ return;
+
+ /* This is for device initialization, so don't resume the device */
+ down_write(&profile->lock);
+ for (slot = 0; slot < profile->num_slots; slot++) {
+ const struct blk_crypto_key *key = profile->slots[slot].key;
+ int err;
+
+ if (!key)
+ continue;
+
+ err = profile->ll_ops.keyslot_program(profile, key, slot);
+ WARN_ON(err);
+ }
+ up_write(&profile->lock);
+}
+EXPORT_SYMBOL_GPL(blk_crypto_reprogram_all_keys);
+
+void blk_crypto_profile_destroy(struct blk_crypto_profile *profile)
+{
+ if (!profile)
+ return;
+ kvfree(profile->slot_hashtable);
+ kvfree_sensitive(profile->slots,
+ sizeof(profile->slots[0]) * profile->num_slots);
+ memzero_explicit(profile, sizeof(*profile));
+}
+EXPORT_SYMBOL_GPL(blk_crypto_profile_destroy);
+
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q)
+{
+ if (blk_integrity_queue_supports_integrity(q)) {
+ pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
+ return false;
+ }
+ q->crypto_profile = profile;
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_register);
+
+void blk_crypto_unregister(struct request_queue *q)
+{
+ q->crypto_profile = NULL;
+}
+
+/**
+ * blk_crypto_intersect_capabilities() - restrict supported crypto capabilities
+ * by child device
+ * @parent: the crypto profile for the parent device
+ * @child: the crypto profile for the child device, or NULL
+ *
+ * This clears all crypto capabilities in @parent that aren't set in @child. If
+ * @child is NULL, then this clears all parent capabilities.
+ *
+ * Only use this when setting up the crypto profile for a layered device, before
+ * it's been exposed yet.
+ */
+void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
+ const struct blk_crypto_profile *child)
+{
+ if (child) {
+ unsigned int i;
+
+ parent->max_dun_bytes_supported =
+ min(parent->max_dun_bytes_supported,
+ child->max_dun_bytes_supported);
+ for (i = 0; i < ARRAY_SIZE(child->modes_supported); i++)
+ parent->modes_supported[i] &= child->modes_supported[i];
+ } else {
+ parent->max_dun_bytes_supported = 0;
+ memset(parent->modes_supported, 0,
+ sizeof(parent->modes_supported));
+ }
+}
+EXPORT_SYMBOL_GPL(blk_crypto_intersect_capabilities);
+
+/**
+ * blk_crypto_has_capabilities() - Check whether @target supports at least all
+ * the crypto capabilities that @reference does.
+ * @target: the target profile
+ * @reference: the reference profile
+ *
+ * Return: %true if @target supports all the crypto capabilities of @reference.
+ */
+bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target,
+ const struct blk_crypto_profile *reference)
+{
+ int i;
+
+ if (!reference)
+ return true;
+
+ if (!target)
+ return false;
+
+ for (i = 0; i < ARRAY_SIZE(target->modes_supported); i++) {
+ if (reference->modes_supported[i] & ~target->modes_supported[i])
+ return false;
+ }
+
+ if (reference->max_dun_bytes_supported >
+ target->max_dun_bytes_supported)
+ return false;
+
+ return true;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_has_capabilities);
+
+/**
+ * blk_crypto_update_capabilities() - Update the capabilities of a crypto
+ * profile to match those of another crypto
+ * profile.
+ * @dst: The crypto profile whose capabilities to update.
+ * @src: The crypto profile whose capabilities this function will update @dst's
+ * capabilities to.
+ *
+ * Blk-crypto requires that crypto capabilities that were
+ * advertised when a bio was created continue to be supported by the
+ * device until that bio is ended. This is turn means that a device cannot
+ * shrink its advertised crypto capabilities without any explicit
+ * synchronization with upper layers. So if there's no such explicit
+ * synchronization, @src must support all the crypto capabilities that
+ * @dst does (i.e. we need blk_crypto_has_capabilities(@src, @dst)).
+ *
+ * Note also that as long as the crypto capabilities are being expanded, the
+ * order of updates becoming visible is not important because it's alright
+ * for blk-crypto to see stale values - they only cause blk-crypto to
+ * believe that a crypto capability isn't supported when it actually is (which
+ * might result in blk-crypto-fallback being used if available, or the bio being
+ * failed).
+ */
+void blk_crypto_update_capabilities(struct blk_crypto_profile *dst,
+ const struct blk_crypto_profile *src)
+{
+ memcpy(dst->modes_supported, src->modes_supported,
+ sizeof(dst->modes_supported));
+
+ dst->max_dun_bytes_supported = src->max_dun_bytes_supported;
+}
+EXPORT_SYMBOL_GPL(blk_crypto_update_capabilities);
diff --git a/block/blk-crypto.c b/block/blk-crypto.c
index 8f53f4a1f9e2..ec9efeeeca91 100644
--- a/block/blk-crypto.c
+++ b/block/blk-crypto.c
@@ -11,7 +11,7 @@
#include <linux/bio.h>
#include <linux/blkdev.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/module.h>
#include <linux/slab.h>
@@ -218,8 +218,9 @@ static bool bio_crypt_check_alignment(struct bio *bio)
blk_status_t __blk_crypto_init_request(struct request *rq)
{
- return blk_ksm_get_slot_for_key(rq->q->ksm, rq->crypt_ctx->bc_key,
- &rq->crypt_keyslot);
+ return blk_crypto_get_keyslot(rq->q->crypto_profile,
+ rq->crypt_ctx->bc_key,
+ &rq->crypt_keyslot);
}
/**
@@ -233,7 +234,7 @@ blk_status_t __blk_crypto_init_request(struct request *rq)
*/
void __blk_crypto_free_request(struct request *rq)
{
- blk_ksm_put_slot(rq->crypt_keyslot);
+ blk_crypto_put_keyslot(rq->crypt_keyslot);
mempool_free(rq->crypt_ctx, bio_crypt_ctx_pool);
blk_crypto_rq_set_defaults(rq);
}
@@ -264,6 +265,7 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr)
{
struct bio *bio = *bio_ptr;
const struct blk_crypto_key *bc_key = bio->bi_crypt_context->bc_key;
+ struct blk_crypto_profile *profile;
/* Error if bio has no data. */
if (WARN_ON_ONCE(!bio_has_data(bio))) {
@@ -280,8 +282,8 @@ bool __blk_crypto_bio_prep(struct bio **bio_ptr)
* Success if device supports the encryption context, or if we succeeded
* in falling back to the crypto API.
*/
- if (blk_ksm_crypto_cfg_supported(bdev_get_queue(bio->bi_bdev)->ksm,
- &bc_key->crypto_cfg))
+ profile = bdev_get_queue(bio->bi_bdev)->crypto_profile;
+ if (__blk_crypto_cfg_supported(profile, &bc_key->crypto_cfg))
return true;
if (blk_crypto_fallback_bio_prep(bio_ptr))
@@ -357,7 +359,7 @@ bool blk_crypto_config_supported(struct request_queue *q,
const struct blk_crypto_config *cfg)
{
return IS_ENABLED(CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK) ||
- blk_ksm_crypto_cfg_supported(q->ksm, cfg);
+ __blk_crypto_cfg_supported(q->crypto_profile, cfg);
}
/**
@@ -378,7 +380,7 @@ bool blk_crypto_config_supported(struct request_queue *q,
int blk_crypto_start_using_key(const struct blk_crypto_key *key,
struct request_queue *q)
{
- if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg))
+ if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg))
return 0;
return blk_crypto_fallback_start_using_mode(key->crypto_cfg.crypto_mode);
}
@@ -394,18 +396,17 @@ int blk_crypto_start_using_key(const struct blk_crypto_key *key,
* evicted from any hardware that it might have been programmed into. The key
* must not be in use by any in-flight IO when this function is called.
*
- * Return: 0 on success or if key is not present in the q's ksm, -err on error.
+ * Return: 0 on success or if the key wasn't in any keyslot; -errno on error.
*/
int blk_crypto_evict_key(struct request_queue *q,
const struct blk_crypto_key *key)
{
- if (blk_ksm_crypto_cfg_supported(q->ksm, &key->crypto_cfg))
- return blk_ksm_evict_key(q->ksm, key);
+ if (__blk_crypto_cfg_supported(q->crypto_profile, &key->crypto_cfg))
+ return __blk_crypto_evict_key(q->crypto_profile, key);
/*
- * If the request queue's associated inline encryption hardware didn't
- * have support for the key, then the key might have been programmed
- * into the fallback keyslot manager, so try to evict from there.
+ * If the request_queue didn't support the key, then blk-crypto-fallback
+ * may have been used, so try to evict the key from blk-crypto-fallback.
*/
return blk_crypto_fallback_evict_key(key);
}
diff --git a/block/blk-flush.c b/block/blk-flush.c
index 4201728bf3a5..8e364bda5166 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -379,7 +379,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error)
* @rq is being submitted. Analyze what needs to be done and put it on the
* right queue.
*/
-void blk_insert_flush(struct request *rq)
+bool blk_insert_flush(struct request *rq)
{
struct request_queue *q = rq->q;
unsigned long fflags = q->queue_flags; /* may change, cache */
@@ -409,7 +409,7 @@ void blk_insert_flush(struct request *rq)
*/
if (!policy) {
blk_mq_end_request(rq, 0);
- return;
+ return true;
}
BUG_ON(rq->bio != rq->biotail); /*assumes zero or single bio rq */
@@ -420,10 +420,8 @@ void blk_insert_flush(struct request *rq)
* for normal execution.
*/
if ((policy & REQ_FSEQ_DATA) &&
- !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) {
- blk_mq_request_bypass_insert(rq, false, false);
- return;
- }
+ !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH)))
+ return false;
/*
* @rq should go through flush machinery. Mark it part of flush
@@ -439,6 +437,8 @@ void blk_insert_flush(struct request *rq)
spin_lock_irq(&fq->mq_flush_lock);
blk_flush_complete_seq(rq, fq, REQ_FSEQ_ACTIONS & ~policy, 0);
spin_unlock_irq(&fq->mq_flush_lock);
+
+ return true;
}
/**
diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c
new file mode 100644
index 000000000000..c246c425d0d7
--- /dev/null
+++ b/block/blk-ia-ranges.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Block device concurrent positioning ranges.
+ *
+ * Copyright (C) 2021 Western Digital Corporation or its Affiliates.
+ */
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+
+#include "blk.h"
+
+static ssize_t
+blk_ia_range_sector_show(struct blk_independent_access_range *iar,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n", iar->sector);
+}
+
+static ssize_t
+blk_ia_range_nr_sectors_show(struct blk_independent_access_range *iar,
+ char *buf)
+{
+ return sprintf(buf, "%llu\n", iar->nr_sectors);
+}
+
+struct blk_ia_range_sysfs_entry {
+ struct attribute attr;
+ ssize_t (*show)(struct blk_independent_access_range *iar, char *buf);
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_sector_entry = {
+ .attr = { .name = "sector", .mode = 0444 },
+ .show = blk_ia_range_sector_show,
+};
+
+static struct blk_ia_range_sysfs_entry blk_ia_range_nr_sectors_entry = {
+ .attr = { .name = "nr_sectors", .mode = 0444 },
+ .show = blk_ia_range_nr_sectors_show,
+};
+
+static struct attribute *blk_ia_range_attrs[] = {
+ &blk_ia_range_sector_entry.attr,
+ &blk_ia_range_nr_sectors_entry.attr,
+ NULL,
+};
+ATTRIBUTE_GROUPS(blk_ia_range);
+
+static ssize_t blk_ia_range_sysfs_show(struct kobject *kobj,
+ struct attribute *attr, char *buf)
+{
+ struct blk_ia_range_sysfs_entry *entry =
+ container_of(attr, struct blk_ia_range_sysfs_entry, attr);
+ struct blk_independent_access_range *iar =
+ container_of(kobj, struct blk_independent_access_range, kobj);
+ ssize_t ret;
+
+ mutex_lock(&iar->queue->sysfs_lock);
+ ret = entry->show(iar, buf);
+ mutex_unlock(&iar->queue->sysfs_lock);
+
+ return ret;
+}
+
+static const struct sysfs_ops blk_ia_range_sysfs_ops = {
+ .show = blk_ia_range_sysfs_show,
+};
+
+/*
+ * Independent access range entries are not freed individually, but alltogether
+ * with struct blk_independent_access_ranges and its array of ranges. Since
+ * kobject_add() takes a reference on the parent kobject contained in
+ * struct blk_independent_access_ranges, the array of independent access range
+ * entries cannot be freed until kobject_del() is called for all entries.
+ * So we do not need to do anything here, but still need this no-op release
+ * operation to avoid complaints from the kobject code.
+ */
+static void blk_ia_range_sysfs_nop_release(struct kobject *kobj)
+{
+}
+
+static struct kobj_type blk_ia_range_ktype = {
+ .sysfs_ops = &blk_ia_range_sysfs_ops,
+ .default_groups = blk_ia_range_groups,
+ .release = blk_ia_range_sysfs_nop_release,
+};
+
+/*
+ * This will be executed only after all independent access range entries are
+ * removed with kobject_del(), at which point, it is safe to free everything,
+ * including the array of ranges.
+ */
+static void blk_ia_ranges_sysfs_release(struct kobject *kobj)
+{
+ struct blk_independent_access_ranges *iars =
+ container_of(kobj, struct blk_independent_access_ranges, kobj);
+
+ kfree(iars);
+}
+
+static struct kobj_type blk_ia_ranges_ktype = {
+ .release = blk_ia_ranges_sysfs_release,
+};
+
+/**
+ * disk_register_ia_ranges - register with sysfs a set of independent
+ * access ranges
+ * @disk: Target disk
+ * @new_iars: New set of independent access ranges
+ *
+ * Register with sysfs a set of independent access ranges for @disk.
+ * If @new_iars is not NULL, this set of ranges is registered and the old set
+ * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is
+ * registered if it is not already.
+ */
+int disk_register_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *new_iars)
+{
+ struct request_queue *q = disk->queue;
+ struct blk_independent_access_ranges *iars;
+ int i, ret;
+
+ lockdep_assert_held(&q->sysfs_dir_lock);
+ lockdep_assert_held(&q->sysfs_lock);
+
+ /* If a new range set is specified, unregister the old one */
+ if (new_iars) {
+ if (q->ia_ranges)
+ disk_unregister_independent_access_ranges(disk);
+ q->ia_ranges = new_iars;
+ }
+
+ iars = q->ia_ranges;
+ if (!iars)
+ return 0;
+
+ /*
+ * At this point, iars is the new set of sector access ranges that needs
+ * to be registered with sysfs.
+ */
+ WARN_ON(iars->sysfs_registered);
+ ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype,
+ &q->kobj, "%s", "independent_access_ranges");
+ if (ret) {
+ q->ia_ranges = NULL;
+ kfree(iars);
+ return ret;
+ }
+
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ iars->ia_range[i].queue = q;
+ ret = kobject_init_and_add(&iars->ia_range[i].kobj,
+ &blk_ia_range_ktype, &iars->kobj,
+ "%d", i);
+ if (ret) {
+ while (--i >= 0)
+ kobject_del(&iars->ia_range[i].kobj);
+ kobject_del(&iars->kobj);
+ kobject_put(&iars->kobj);
+ return ret;
+ }
+ }
+
+ iars->sysfs_registered = true;
+
+ return 0;
+}
+
+void disk_unregister_independent_access_ranges(struct gendisk *disk)
+{
+ struct request_queue *q = disk->queue;
+ struct blk_independent_access_ranges *iars = q->ia_ranges;
+ int i;
+
+ lockdep_assert_held(&q->sysfs_dir_lock);
+ lockdep_assert_held(&q->sysfs_lock);
+
+ if (!iars)
+ return;
+
+ if (iars->sysfs_registered) {
+ for (i = 0; i < iars->nr_ia_ranges; i++)
+ kobject_del(&iars->ia_range[i].kobj);
+ kobject_del(&iars->kobj);
+ kobject_put(&iars->kobj);
+ } else {
+ kfree(iars);
+ }
+
+ q->ia_ranges = NULL;
+}
+
+static struct blk_independent_access_range *
+disk_find_ia_range(struct blk_independent_access_ranges *iars,
+ sector_t sector)
+{
+ struct blk_independent_access_range *iar;
+ int i;
+
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ iar = &iars->ia_range[i];
+ if (sector >= iar->sector &&
+ sector < iar->sector + iar->nr_sectors)
+ return iar;
+ }
+
+ return NULL;
+}
+
+static bool disk_check_ia_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars)
+{
+ struct blk_independent_access_range *iar, *tmp;
+ sector_t capacity = get_capacity(disk);
+ sector_t sector = 0;
+ int i;
+
+ /*
+ * While sorting the ranges in increasing LBA order, check that the
+ * ranges do not overlap, that there are no sector holes and that all
+ * sectors belong to one range.
+ */
+ for (i = 0; i < iars->nr_ia_ranges; i++) {
+ tmp = disk_find_ia_range(iars, sector);
+ if (!tmp || tmp->sector != sector) {
+ pr_warn("Invalid non-contiguous independent access ranges\n");
+ return false;
+ }
+
+ iar = &iars->ia_range[i];
+ if (tmp != iar) {
+ swap(iar->sector, tmp->sector);
+ swap(iar->nr_sectors, tmp->nr_sectors);
+ }
+
+ sector += iar->nr_sectors;
+ }
+
+ if (sector != capacity) {
+ pr_warn("Independent access ranges do not match disk capacity\n");
+ return false;
+ }
+
+ return true;
+}
+
+static bool disk_ia_ranges_changed(struct gendisk *disk,
+ struct blk_independent_access_ranges *new)
+{
+ struct blk_independent_access_ranges *old = disk->queue->ia_ranges;
+ int i;
+
+ if (!old)
+ return true;
+
+ if (old->nr_ia_ranges != new->nr_ia_ranges)
+ return true;
+
+ for (i = 0; i < old->nr_ia_ranges; i++) {
+ if (new->ia_range[i].sector != old->ia_range[i].sector ||
+ new->ia_range[i].nr_sectors != old->ia_range[i].nr_sectors)
+ return true;
+ }
+
+ return false;
+}
+
+/**
+ * disk_alloc_independent_access_ranges - Allocate an independent access ranges
+ * data structure
+ * @disk: target disk
+ * @nr_ia_ranges: Number of independent access ranges
+ *
+ * Allocate a struct blk_independent_access_ranges structure with @nr_ia_ranges
+ * access range descriptors.
+ */
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges)
+{
+ struct blk_independent_access_ranges *iars;
+
+ iars = kzalloc_node(struct_size(iars, ia_range, nr_ia_ranges),
+ GFP_KERNEL, disk->queue->node);
+ if (iars)
+ iars->nr_ia_ranges = nr_ia_ranges;
+ return iars;
+}
+EXPORT_SYMBOL_GPL(disk_alloc_independent_access_ranges);
+
+/**
+ * disk_set_independent_access_ranges - Set a disk independent access ranges
+ * @disk: target disk
+ * @iars: independent access ranges structure
+ *
+ * Set the independent access ranges information of the request queue
+ * of @disk to @iars. If @iars is NULL and the independent access ranges
+ * structure already set is cleared. If there are no differences between
+ * @iars and the independent access ranges structure already set, @iars
+ * is freed.
+ */
+void disk_set_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars)
+{
+ struct request_queue *q = disk->queue;
+
+ if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) {
+ kfree(iars);
+ iars = NULL;
+ }
+
+ mutex_lock(&q->sysfs_dir_lock);
+ mutex_lock(&q->sysfs_lock);
+
+ if (iars) {
+ if (!disk_check_ia_ranges(disk, iars)) {
+ kfree(iars);
+ iars = NULL;
+ goto reg;
+ }
+
+ if (!disk_ia_ranges_changed(disk, iars)) {
+ kfree(iars);
+ goto unlock;
+ }
+ }
+
+ /*
+ * This may be called for a registered queue. E.g. during a device
+ * revalidation. If that is the case, we need to unregister the old
+ * set of independent access ranges and register the new set. If the
+ * queue is not registered, registration of the device request queue
+ * will register the independent access ranges, so only swap in the
+ * new set and free the old one.
+ */
+reg:
+ if (blk_queue_registered(q)) {
+ disk_register_independent_access_ranges(disk, iars);
+ } else {
+ swap(q->ia_ranges, iars);
+ kfree(iars);
+ }
+
+unlock:
+ mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
+}
+EXPORT_SYMBOL_GPL(disk_set_independent_access_ranges);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index cef534a7cbc9..d670d54e5f7a 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -409,9 +409,9 @@ void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template
blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- if (disk->queue->ksm) {
+ if (disk->queue->crypto_profile) {
pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
- blk_ksm_unregister(disk->queue);
+ blk_crypto_unregister(disk->queue);
}
#endif
}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index ec727234ac48..df69f4bb7717 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -383,7 +383,7 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
*/
void blk_queue_split(struct bio **bio)
{
- struct request_queue *q = (*bio)->bi_bdev->bd_disk->queue;
+ struct request_queue *q = bdev_get_queue((*bio)->bi_bdev);
unsigned int nr_segs;
if (blk_may_split(q, *bio))
@@ -1067,9 +1067,8 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
* @q: request_queue new bio is being queued at
* @bio: new bio being queued
* @nr_segs: number of segments in @bio
- * @same_queue_rq: pointer to &struct request that gets filled in when
- * another request associated with @q is found on the plug list
- * (optional, may be %NULL)
+ * @same_queue_rq: output value, will be true if there's an existing request
+ * from the passed in @q already in the plug list
*
* Determine whether @bio being queued on @q can be merged with the previous
* request on %current's plugged list. Returns %true if merge was successful,
@@ -1085,23 +1084,23 @@ static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q,
* Caller must ensure !blk_queue_nomerges(q) beforehand.
*/
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs, struct request **same_queue_rq)
+ unsigned int nr_segs, bool *same_queue_rq)
{
struct blk_plug *plug;
struct request *rq;
plug = blk_mq_plug(q, bio);
- if (!plug || list_empty(&plug->mq_list))
+ if (!plug || rq_list_empty(plug->mq_list))
return false;
/* check the previously added entry for a quick merge attempt */
- rq = list_last_entry(&plug->mq_list, struct request, queuelist);
- if (rq->q == q && same_queue_rq) {
+ rq = rq_list_peek(&plug->mq_list);
+ if (rq->q == q) {
/*
* Only blk-mq multiple hardware queues case checks the rq in
* the same queue, there should be only one such rq in a queue
*/
- *same_queue_rq = rq;
+ *same_queue_rq = true;
}
if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == BIO_MERGE_OK)
return true;
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 68ca5d21cda7..0f8c60e9c719 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -550,7 +550,7 @@ static int hctx_active_show(void *data, struct seq_file *m)
{
struct blk_mq_hw_ctx *hctx = data;
- seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
+ seq_printf(m, "%d\n", __blk_mq_active_requests(hctx));
return 0;
}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index e85b7556b096..c62b966dfaba 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -361,7 +361,7 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
}
}
-bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
+bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs)
{
struct elevator_queue *e = q->elevator;
@@ -541,7 +541,7 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q, unsigned int fla
queue_for_each_hw_ctx(q, hctx, i) {
if (hctx->sched_tags) {
- if (!blk_mq_is_shared_tags(q->tag_set->flags))
+ if (!blk_mq_is_shared_tags(flags))
blk_mq_free_rq_map(hctx->sched_tags);
hctx->sched_tags = NULL;
}
diff --git a/block/blk-mq-sched.h b/block/blk-mq-sched.h
index 98836106b25f..25d1034952b6 100644
--- a/block/blk-mq-sched.h
+++ b/block/blk-mq-sched.h
@@ -12,7 +12,7 @@ void blk_mq_sched_assign_ioc(struct request *rq);
bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs, struct request **merged_request);
-bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
+bool blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
unsigned int nr_segs);
bool blk_mq_sched_try_insert_merge(struct request_queue *q, struct request *rq,
struct list_head *free);
@@ -43,16 +43,6 @@ static inline bool bio_mergeable(struct bio *bio)
}
static inline bool
-blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs)
-{
- if (blk_queue_nomerges(q) || !bio_mergeable(bio))
- return false;
-
- return __blk_mq_sched_bio_merge(q, bio, nr_segs);
-}
-
-static inline bool
blk_mq_sched_allow_merge(struct request_queue *q, struct request *rq,
struct bio *bio)
{
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index b94c3e8ef392..995336abee33 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -399,9 +399,12 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn,
void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
busy_tag_iter_fn *fn, void *priv)
{
- int i;
+ unsigned int flags = tagset->flags;
+ int i, nr_tags;
+
+ nr_tags = blk_mq_is_shared_tags(flags) ? 1 : tagset->nr_hw_queues;
- for (i = 0; i < tagset->nr_hw_queues; i++) {
+ for (i = 0; i < nr_tags; i++) {
if (tagset->tags && tagset->tags[i])
__blk_mq_all_tag_iter(tagset->tags[i], fn, priv,
BT_TAG_ITER_STARTED);
diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h
index 78ae2fb8e2a4..df787b5a23bd 100644
--- a/block/blk-mq-tag.h
+++ b/block/blk-mq-tag.h
@@ -4,29 +4,6 @@
struct blk_mq_alloc_data;
-/*
- * Tag address space map.
- */
-struct blk_mq_tags {
- unsigned int nr_tags;
- unsigned int nr_reserved_tags;
-
- atomic_t active_queues;
-
- struct sbitmap_queue bitmap_tags;
- struct sbitmap_queue breserved_tags;
-
- struct request **rqs;
- struct request **static_rqs;
- struct list_head page_list;
-
- /*
- * used to clear request reference in rqs[] before freeing one
- * request pool
- */
- spinlock_t lock;
-};
-
extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags,
unsigned int reserved_tags,
int node, int alloc_policy);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9248edd8a7d3..07eb1412760b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -19,7 +19,6 @@
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/llist.h>
-#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
@@ -242,7 +241,12 @@ EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
*/
void blk_mq_quiesce_queue_nowait(struct request_queue *q)
{
- blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ unsigned long flags;
+
+ spin_lock_irqsave(&q->queue_lock, flags);
+ if (!q->quiesce_depth++)
+ blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+ spin_unlock_irqrestore(&q->queue_lock, flags);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
@@ -283,10 +287,21 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
*/
void blk_mq_unquiesce_queue(struct request_queue *q)
{
- blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ unsigned long flags;
+ bool run_queue = false;
+
+ spin_lock_irqsave(&q->queue_lock, flags);
+ if (WARN_ON_ONCE(q->quiesce_depth <= 0)) {
+ ;
+ } else if (!--q->quiesce_depth) {
+ blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ run_queue = true;
+ }
+ spin_unlock_irqrestore(&q->queue_lock, flags);
/* dispatch requests which are inserted during quiescing */
- blk_mq_run_hw_queues(q, true);
+ if (run_queue)
+ blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
@@ -301,40 +316,37 @@ void blk_mq_wake_waiters(struct request_queue *q)
}
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
- unsigned int tag, u64 alloc_time_ns)
+ struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns)
{
struct blk_mq_ctx *ctx = data->ctx;
struct blk_mq_hw_ctx *hctx = data->hctx;
struct request_queue *q = data->q;
- struct elevator_queue *e = q->elevator;
- struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct request *rq = tags->static_rqs[tag];
- unsigned int rq_flags = 0;
- if (e) {
- rq_flags = RQF_ELV;
- rq->tag = BLK_MQ_NO_TAG;
- rq->internal_tag = tag;
- } else {
- rq->tag = tag;
- rq->internal_tag = BLK_MQ_NO_TAG;
- }
+ rq->q = q;
+ rq->mq_ctx = ctx;
+ rq->mq_hctx = hctx;
+ rq->cmd_flags = data->cmd_flags;
if (data->flags & BLK_MQ_REQ_PM)
- rq_flags |= RQF_PM;
+ data->rq_flags |= RQF_PM;
if (blk_queue_io_stat(q))
- rq_flags |= RQF_IO_STAT;
- rq->rq_flags = rq_flags;
+ data->rq_flags |= RQF_IO_STAT;
+ rq->rq_flags = data->rq_flags;
+
+ if (!(data->rq_flags & RQF_ELV)) {
+ rq->tag = tag;
+ rq->internal_tag = BLK_MQ_NO_TAG;
+ } else {
+ rq->tag = BLK_MQ_NO_TAG;
+ rq->internal_tag = tag;
+ }
+ rq->timeout = 0;
if (blk_mq_need_time_stamp(rq))
rq->start_time_ns = ktime_get_ns();
else
rq->start_time_ns = 0;
- /* csd/requeue_work/fifo_time is initialized before use */
- rq->q = q;
- rq->mq_ctx = ctx;
- rq->mq_hctx = hctx;
- rq->cmd_flags = data->cmd_flags;
rq->rq_disk = NULL;
rq->part = NULL;
#ifdef CONFIG_BLK_RQ_ALLOC_TIME
@@ -346,7 +358,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
#endif
- rq->timeout = 0;
rq->end_io = NULL;
rq->end_io_data = NULL;
@@ -381,20 +392,23 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data,
u64 alloc_time_ns)
{
unsigned int tag, tag_offset;
+ struct blk_mq_tags *tags;
struct request *rq;
- unsigned long tags;
+ unsigned long tag_mask;
int i, nr = 0;
- tags = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
- if (unlikely(!tags))
+ tag_mask = blk_mq_get_tags(data, data->nr_tags, &tag_offset);
+ if (unlikely(!tag_mask))
return NULL;
- for (i = 0; tags; i++) {
- if (!(tags & (1UL << i)))
+ tags = blk_mq_tags_from_data(data);
+ for (i = 0; tag_mask; i++) {
+ if (!(tag_mask & (1UL << i)))
continue;
+ prefetch(tags->static_rqs[tag]);
tag = tag_offset + i;
- tags &= ~(1UL << i);
- rq = blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
+ tag_mask &= ~(1UL << i);
+ rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns);
rq_list_add(data->cached_rq, rq);
}
data->nr_tags -= nr;
@@ -465,7 +479,8 @@ retry:
goto retry;
}
- return blk_mq_rq_ctx_init(data, tag, alloc_time_ns);
+ return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag,
+ alloc_time_ns);
}
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
@@ -475,6 +490,7 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
.q = q,
.flags = flags,
.cmd_flags = op,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
.nr_tags = 1,
};
struct request *rq;
@@ -504,6 +520,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
.q = q,
.flags = flags,
.cmd_flags = op,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
.nr_tags = 1,
};
u64 alloc_time_ns = 0;
@@ -549,7 +566,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
tag = blk_mq_get_tag(&data);
if (tag == BLK_MQ_NO_TAG)
goto out_queue_exit;
- return blk_mq_rq_ctx_init(&data, tag, alloc_time_ns);
+ return blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
+ alloc_time_ns);
out_queue_exit:
blk_queue_exit(q);
@@ -580,7 +598,7 @@ void blk_mq_free_request(struct request *rq)
struct request_queue *q = rq->q;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
- if (rq->rq_flags & (RQF_ELVPRIV | RQF_ELV)) {
+ if (rq->rq_flags & RQF_ELVPRIV) {
struct elevator_queue *e = q->elevator;
if (e->type->ops.finish_request)
@@ -618,25 +636,23 @@ void blk_mq_free_plug_rqs(struct blk_plug *plug)
static void req_bio_endio(struct request *rq, struct bio *bio,
unsigned int nbytes, blk_status_t error)
{
- if (error)
+ if (unlikely(error)) {
bio->bi_status = error;
-
- if (unlikely(rq->rq_flags & RQF_QUIET))
- bio_set_flag(bio, BIO_QUIET);
-
- bio_advance(bio, nbytes);
-
- if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) {
+ } else if (req_op(rq) == REQ_OP_ZONE_APPEND) {
/*
* Partial zone append completions cannot be supported as the
* BIO fragments may end up not being written sequentially.
*/
- if (bio->bi_iter.bi_size)
+ if (bio->bi_iter.bi_size != nbytes)
bio->bi_status = BLK_STS_IOERR;
else
bio->bi_iter.bi_sector = rq->__sector;
}
+ bio_advance(bio, nbytes);
+
+ if (unlikely(rq->rq_flags & RQF_QUIET))
+ bio_set_flag(bio, BIO_QUIET);
/* don't actually finish bio if it's part of flush sequence */
if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ))
bio_endio(bio);
@@ -680,7 +696,7 @@ bool blk_update_request(struct request *req, blk_status_t error,
{
int total_bytes;
- trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes);
+ trace_block_rq_complete(req, error, nr_bytes);
if (!req->bio)
return false;
@@ -806,7 +822,7 @@ static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
void blk_mq_end_request_batch(struct io_comp_batch *iob)
{
int tags[TAG_COMP_BATCH], nr_tags = 0;
- struct blk_mq_hw_ctx *last_hctx = NULL;
+ struct blk_mq_hw_ctx *cur_hctx = NULL;
struct request *rq;
u64 now = 0;
@@ -829,17 +845,17 @@ void blk_mq_end_request_batch(struct io_comp_batch *iob)
blk_pm_mark_last_busy(rq);
rq_qos_done(rq->q, rq);
- if (nr_tags == TAG_COMP_BATCH ||
- (last_hctx && last_hctx != rq->mq_hctx)) {
- blk_mq_flush_tag_batch(last_hctx, tags, nr_tags);
+ if (nr_tags == TAG_COMP_BATCH || cur_hctx != rq->mq_hctx) {
+ if (cur_hctx)
+ blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
nr_tags = 0;
+ cur_hctx = rq->mq_hctx;
}
tags[nr_tags++] = rq->tag;
- last_hctx = rq->mq_hctx;
}
if (nr_tags)
- blk_mq_flush_tag_batch(last_hctx, tags, nr_tags);
+ blk_mq_flush_tag_batch(cur_hctx, tags, nr_tags);
}
EXPORT_SYMBOL_GPL(blk_mq_end_request_batch);
@@ -1040,7 +1056,6 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
/* this request will be re-inserted to io scheduler queue */
blk_mq_sched_requeue_request(rq);
- BUG_ON(!list_empty(&rq->queuelist));
blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);
@@ -1121,17 +1136,6 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q,
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
-struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
-{
- if (tag < tags->nr_tags) {
- prefetch(tags->rqs[tag]);
- return tags->rqs[tag];
- }
-
- return NULL;
-}
-EXPORT_SYMBOL(blk_mq_tag_to_rq);
-
static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
void *priv, bool reserved)
{
@@ -1336,7 +1340,7 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
return data.rq;
}
-static bool __blk_mq_get_driver_tag(struct request *rq)
+static bool __blk_mq_alloc_driver_tag(struct request *rq)
{
struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
@@ -1360,11 +1364,9 @@ static bool __blk_mq_get_driver_tag(struct request *rq)
return true;
}
-bool blk_mq_get_driver_tag(struct request *rq)
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq)
{
- struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
-
- if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq))
+ if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
return false;
if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
@@ -1594,6 +1596,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
int errors, queued;
blk_status_t ret = BLK_STS_OK;
LIST_HEAD(zone_list);
+ bool needs_resource = false;
if (list_empty(list))
return false;
@@ -1639,6 +1642,8 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
queued++;
break;
case BLK_STS_RESOURCE:
+ needs_resource = true;
+ fallthrough;
case BLK_STS_DEV_RESOURCE:
blk_mq_handle_dev_resource(rq, list);
goto out;
@@ -1649,6 +1654,7 @@ bool blk_mq_dispatch_rq_list(struct blk_mq_hw_ctx *hctx, struct list_head *list,
* accept.
*/
blk_mq_handle_zone_resource(rq, &zone_list);
+ needs_resource = true;
break;
default:
errors++;
@@ -1673,7 +1679,6 @@ out:
/* For non-shared tags, the RESTART check will suffice */
bool no_tag = prep == PREP_DISPATCH_NO_TAG &&
(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED);
- bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET;
if (nr_budgets)
blk_mq_release_budgets(q, list);
@@ -1714,14 +1719,16 @@ out:
* If driver returns BLK_STS_RESOURCE and SCHED_RESTART
* bit is set, run queue after a delay to avoid IO stalls
* that could otherwise occur if the queue is idle. We'll do
- * similar if we couldn't get budget and SCHED_RESTART is set.
+ * similar if we couldn't get budget or couldn't lock a zone
+ * and SCHED_RESTART is set.
*/
needs_restart = blk_mq_sched_needs_restart(hctx);
+ if (prep == PREP_DISPATCH_NO_BUDGET)
+ needs_resource = true;
if (!needs_restart ||
(no_tag && list_empty_careful(&hctx->dispatch_wait.entry)))
blk_mq_run_hw_queue(hctx, true);
- else if (needs_restart && (ret == BLK_STS_RESOURCE ||
- no_budget_avail))
+ else if (needs_restart && needs_resource)
blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
blk_mq_update_dispatch_busy(hctx, true);
@@ -2161,54 +2168,106 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
spin_unlock(&ctx->lock);
}
-static int plug_rq_cmp(void *priv, const struct list_head *a,
- const struct list_head *b)
+static void blk_mq_commit_rqs(struct blk_mq_hw_ctx *hctx, int *queued,
+ bool from_schedule)
{
- struct request *rqa = container_of(a, struct request, queuelist);
- struct request *rqb = container_of(b, struct request, queuelist);
+ if (hctx->queue->mq_ops->commit_rqs) {
+ trace_block_unplug(hctx->queue, *queued, !from_schedule);
+ hctx->queue->mq_ops->commit_rqs(hctx);
+ }
+ *queued = 0;
+}
- if (rqa->mq_ctx != rqb->mq_ctx)
- return rqa->mq_ctx > rqb->mq_ctx;
- if (rqa->mq_hctx != rqb->mq_hctx)
- return rqa->mq_hctx > rqb->mq_hctx;
+static void blk_mq_plug_issue_direct(struct blk_plug *plug, bool from_schedule)
+{
+ struct blk_mq_hw_ctx *hctx = NULL;
+ struct request *rq;
+ int queued = 0;
+ int errors = 0;
+
+ while ((rq = rq_list_pop(&plug->mq_list))) {
+ bool last = rq_list_empty(plug->mq_list);
+ blk_status_t ret;
- return blk_rq_pos(rqa) > blk_rq_pos(rqb);
+ if (hctx != rq->mq_hctx) {
+ if (hctx)
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
+ hctx = rq->mq_hctx;
+ }
+
+ ret = blk_mq_request_issue_directly(rq, last);
+ switch (ret) {
+ case BLK_STS_OK:
+ queued++;
+ break;
+ case BLK_STS_RESOURCE:
+ case BLK_STS_DEV_RESOURCE:
+ blk_mq_request_bypass_insert(rq, false, last);
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
+ return;
+ default:
+ blk_mq_end_request(rq, ret);
+ errors++;
+ break;
+ }
+ }
+
+ /*
+ * If we didn't flush the entire list, we could have told the driver
+ * there was more coming, but that turned out to be a lie.
+ */
+ if (errors)
+ blk_mq_commit_rqs(hctx, &queued, from_schedule);
}
void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
+ struct blk_mq_hw_ctx *this_hctx;
+ struct blk_mq_ctx *this_ctx;
+ unsigned int depth;
LIST_HEAD(list);
- if (list_empty(&plug->mq_list))
+ if (rq_list_empty(plug->mq_list))
return;
- list_splice_init(&plug->mq_list, &list);
-
- if (plug->rq_count > 2 && plug->multiple_queues)
- list_sort(NULL, &list, plug_rq_cmp);
-
plug->rq_count = 0;
+ if (!plug->multiple_queues && !plug->has_elevator && !from_schedule) {
+ blk_mq_plug_issue_direct(plug, from_schedule);
+ if (rq_list_empty(plug->mq_list))
+ return;
+ }
+
+ this_hctx = NULL;
+ this_ctx = NULL;
+ depth = 0;
do {
- struct list_head rq_list;
- struct request *rq, *head_rq = list_entry_rq(list.next);
- struct list_head *pos = &head_rq->queuelist; /* skip first */
- struct blk_mq_hw_ctx *this_hctx = head_rq->mq_hctx;
- struct blk_mq_ctx *this_ctx = head_rq->mq_ctx;
- unsigned int depth = 1;
-
- list_for_each_continue(pos, &list) {
- rq = list_entry_rq(pos);
- BUG_ON(!rq->q);
- if (rq->mq_hctx != this_hctx || rq->mq_ctx != this_ctx)
- break;
- depth++;
+ struct request *rq;
+
+ rq = rq_list_pop(&plug->mq_list);
+
+ if (!this_hctx) {
+ this_hctx = rq->mq_hctx;
+ this_ctx = rq->mq_ctx;
+ } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) {
+ trace_block_unplug(this_hctx->queue, depth,
+ !from_schedule);
+ blk_mq_sched_insert_requests(this_hctx, this_ctx,
+ &list, from_schedule);
+ depth = 0;
+ this_hctx = rq->mq_hctx;
+ this_ctx = rq->mq_ctx;
+
}
- list_cut_before(&rq_list, &list, pos);
- trace_block_unplug(head_rq->q, depth, !from_schedule);
- blk_mq_sched_insert_requests(this_hctx, this_ctx, &rq_list,
+ list_add(&rq->queuelist, &list);
+ depth++;
+ } while (!rq_list_empty(plug->mq_list));
+
+ if (!list_empty(&list)) {
+ trace_block_unplug(this_hctx->queue, depth, !from_schedule);
+ blk_mq_sched_insert_requests(this_hctx, this_ctx, &list,
from_schedule);
- } while(!list_empty(&list));
+ }
}
static void blk_mq_bio_to_request(struct request *rq, struct bio *bio,
@@ -2388,16 +2447,17 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
{
- list_add_tail(&rq->queuelist, &plug->mq_list);
- plug->rq_count++;
- if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) {
- struct request *tmp;
+ if (!plug->multiple_queues) {
+ struct request *nxt = rq_list_peek(&plug->mq_list);
- tmp = list_first_entry(&plug->mq_list, struct request,
- queuelist);
- if (tmp->q != rq->q)
+ if (nxt && nxt->q != rq->q)
plug->multiple_queues = true;
}
+ if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
+ plug->has_elevator = true;
+ rq->rq_next = NULL;
+ rq_list_add(&plug->mq_list, rq);
+ plug->rq_count++;
}
/*
@@ -2429,10 +2489,9 @@ void blk_mq_submit_bio(struct bio *bio)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
const int is_sync = op_is_sync(bio->bi_opf);
- const int is_flush_fua = op_is_flush(bio->bi_opf);
struct request *rq;
struct blk_plug *plug;
- struct request *same_queue_rq = NULL;
+ bool same_queue_rq = false;
unsigned int nr_segs = 1;
blk_status_t ret;
@@ -2443,12 +2502,12 @@ void blk_mq_submit_bio(struct bio *bio)
if (!bio_integrity_prep(bio))
goto queue_exit;
- if (!is_flush_fua && !blk_queue_nomerges(q) &&
- blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
- goto queue_exit;
-
- if (blk_mq_sched_bio_merge(q, bio, nr_segs))
- goto queue_exit;
+ if (!blk_queue_nomerges(q) && bio_mergeable(bio)) {
+ if (blk_attempt_plug_merge(q, bio, nr_segs, &same_queue_rq))
+ goto queue_exit;
+ if (blk_mq_sched_bio_merge(q, bio, nr_segs))
+ goto queue_exit;
+ }
rq_qos_throttle(q, bio);
@@ -2461,6 +2520,7 @@ void blk_mq_submit_bio(struct bio *bio)
.q = q,
.nr_tags = 1,
.cmd_flags = bio->bi_opf,
+ .rq_flags = q->elevator ? RQF_ELV : 0,
};
if (plug) {
@@ -2491,14 +2551,12 @@ void blk_mq_submit_bio(struct bio *bio)
return;
}
- if (unlikely(is_flush_fua)) {
- struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
- /* Bypass scheduler for flush requests */
- blk_insert_flush(rq);
- blk_mq_run_hw_queue(hctx, true);
- } else if (plug && (q->nr_hw_queues == 1 ||
- blk_mq_is_shared_tags(rq->mq_hctx->flags) ||
- q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
+ if (op_is_flush(bio->bi_opf) && blk_insert_flush(rq))
+ return;
+
+ if (plug && (q->nr_hw_queues == 1 ||
+ blk_mq_is_shared_tags(rq->mq_hctx->flags) ||
+ q->mq_ops->commit_rqs || !blk_queue_nonrot(q))) {
/*
* Use plugging if we have a ->commit_rqs() hook as well, as
* we know the driver uses bd->last in a smart fashion.
@@ -2509,14 +2567,16 @@ void blk_mq_submit_bio(struct bio *bio)
unsigned int request_count = plug->rq_count;
struct request *last = NULL;
- if (!request_count)
+ if (!request_count) {
trace_block_plug(q);
- else
- last = list_entry_rq(plug->mq_list.prev);
+ } else if (!blk_queue_nomerges(q)) {
+ last = rq_list_peek(&plug->mq_list);
+ if (blk_rq_bytes(last) < BLK_PLUG_FLUSH_SIZE)
+ last = NULL;
+ }
- if (request_count >= blk_plug_max_rq_count(plug) || (last &&
- blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
- blk_flush_plug_list(plug, false);
+ if (request_count >= blk_plug_max_rq_count(plug) || last) {
+ blk_mq_flush_plug_list(plug, false);
trace_block_plug(q);
}
@@ -2525,6 +2585,8 @@ void blk_mq_submit_bio(struct bio *bio)
/* Insert the request at the IO scheduler queue */
blk_mq_sched_insert_request(rq, false, true, true);
} else if (plug && !blk_queue_nomerges(q)) {
+ struct request *next_rq = NULL;
+
/*
* We do limited plugging. If the bio can be merged, do that.
* Otherwise the existing request in the plug list will be
@@ -2532,19 +2594,16 @@ void blk_mq_submit_bio(struct bio *bio)
* The plug list might get flushed before this. If that happens,
* the plug list is empty, and same_queue_rq is invalid.
*/
- if (list_empty(&plug->mq_list))
- same_queue_rq = NULL;
if (same_queue_rq) {
- list_del_init(&same_queue_rq->queuelist);
+ next_rq = rq_list_pop(&plug->mq_list);
plug->rq_count--;
}
blk_add_rq_to_plug(plug, rq);
trace_block_plug(q);
- if (same_queue_rq) {
+ if (next_rq) {
trace_block_unplug(q, 1, true);
- blk_mq_try_issue_directly(same_queue_rq->mq_hctx,
- same_queue_rq);
+ blk_mq_try_issue_directly(next_rq->mq_hctx, next_rq);
}
} else if ((q->nr_hw_queues > 1 && is_sync) ||
!rq->mq_hctx->dispatch_busy) {
diff --git a/block/blk-mq.h b/block/blk-mq.h
index ebf67f4d4f2e..28859fc5faee 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -122,6 +122,7 @@ extern int blk_mq_sysfs_register(struct request_queue *q);
extern void blk_mq_sysfs_unregister(struct request_queue *q);
extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx);
void blk_mq_free_plug_rqs(struct blk_plug *plug);
+void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
void blk_mq_release(struct request_queue *q);
@@ -148,6 +149,7 @@ struct blk_mq_alloc_data {
blk_mq_req_flags_t flags;
unsigned int shallow_depth;
unsigned int cmd_flags;
+ unsigned int rq_flags;
/* allocate multiple requests/tags in one go */
unsigned int nr_tags;
@@ -165,10 +167,9 @@ static inline bool blk_mq_is_shared_tags(unsigned int flags)
static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data)
{
- if (data->q->elevator)
- return data->hctx->sched_tags;
-
- return data->hctx->tags;
+ if (!(data->rq_flags & RQF_ELV))
+ return data->hctx->tags;
+ return data->hctx->sched_tags;
}
static inline bool blk_mq_hctx_stopped(struct blk_mq_hw_ctx *hctx)
@@ -258,7 +259,20 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
__blk_mq_put_driver_tag(rq->mq_hctx, rq);
}
-bool blk_mq_get_driver_tag(struct request *rq);
+bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq);
+
+static inline bool blk_mq_get_driver_tag(struct request *rq)
+{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
+
+ if (rq->tag != BLK_MQ_NO_TAG &&
+ !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+ hctx->tags->rqs[rq->tag] = rq;
+ return true;
+ }
+
+ return __blk_mq_get_driver_tag(hctx, rq);
+}
static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)
{
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a7c857ad7d10..b880c70e22e4 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -842,6 +842,24 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
+static bool disk_has_partitions(struct gendisk *disk)
+{
+ unsigned long idx;
+ struct block_device *part;
+ bool ret = false;
+
+ rcu_read_lock();
+ xa_for_each(&disk->part_tbl, idx, part) {
+ if (bdev_is_partition(part)) {
+ ret = true;
+ break;
+ }
+ }
+ rcu_read_unlock();
+
+ return ret;
+}
+
/**
* blk_queue_set_zoned - configure a disk queue zoned model.
* @disk: the gendisk of the queue to configure
@@ -876,7 +894,7 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
* we do nothing special as far as the block layer is concerned.
*/
if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
- !xa_empty(&disk->part_tbl))
+ disk_has_partitions(disk))
model = BLK_ZONED_NONE;
break;
case BLK_ZONED_NONE:
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 36f14d658e81..cef1f713370b 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -873,16 +873,15 @@ int blk_register_queue(struct gendisk *disk)
}
mutex_lock(&q->sysfs_lock);
+
+ ret = disk_register_independent_access_ranges(disk, NULL);
+ if (ret)
+ goto put_dev;
+
if (q->elevator) {
ret = elv_register_queue(q, false);
- if (ret) {
- mutex_unlock(&q->sysfs_lock);
- mutex_unlock(&q->sysfs_dir_lock);
- kobject_del(&q->kobj);
- blk_trace_remove_sysfs(dev);
- kobject_put(&dev->kobj);
- return ret;
- }
+ if (ret)
+ goto put_dev;
}
blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
@@ -914,6 +913,16 @@ unlock:
}
return ret;
+
+put_dev:
+ disk_unregister_independent_access_ranges(disk);
+ mutex_unlock(&q->sysfs_lock);
+ mutex_unlock(&q->sysfs_dir_lock);
+ kobject_del(&q->kobj);
+ blk_trace_remove_sysfs(dev);
+ kobject_put(&dev->kobj);
+
+ return ret;
}
/**
@@ -958,6 +967,7 @@ void blk_unregister_queue(struct gendisk *disk)
mutex_lock(&q->sysfs_lock);
if (q->elevator)
elv_unregister_queue(q);
+ disk_unregister_independent_access_ranges(disk);
mutex_unlock(&q->sysfs_lock);
mutex_unlock(&q->sysfs_dir_lock);
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 874c1c37bf0c..0c119be0e813 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -357,6 +357,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
unsigned int inflight = wbt_inflight(rwb);
int status;
+ if (!rwb->rqos.q->disk)
+ return;
+
status = latency_exceeded(rwb, cb->stat);
trace_wbt_timer(rwb->rqos.q->disk->bdi, status, rqd->scale_step,
diff --git a/block/blk.h b/block/blk.h
index e80350327e6d..7afffd548daf 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -218,7 +218,7 @@ void blk_add_timer(struct request *req);
void blk_print_req_error(struct request *req, blk_status_t status);
bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
- unsigned int nr_segs, struct request **same_queue_rq);
+ unsigned int nr_segs, bool *same_queue_rq);
bool blk_bio_list_merge(struct request_queue *q, struct list_head *list,
struct bio *bio, unsigned int nr_segs);
@@ -236,7 +236,7 @@ void __blk_account_io_done(struct request *req, u64 now);
*/
#define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED)
-void blk_insert_flush(struct request *rq);
+bool blk_insert_flush(struct request *rq);
int elevator_switch_mq(struct request_queue *q,
struct elevator_type *new_e);
@@ -454,4 +454,8 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg);
extern const struct address_space_operations def_blk_aops;
+int disk_register_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *new_iars);
+void disk_unregister_independent_access_ranges(struct gendisk *disk);
+
#endif /* BLK_INTERNAL_H */
diff --git a/block/fops.c b/block/fops.c
index 2ae8a7bd2b84..3777c7b76eae 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -76,7 +76,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
bio_init(&bio, vecs, nr_pages);
bio_set_dev(&bio, bdev);
- bio.bi_iter.bi_sector = pos >> 9;
+ bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio.bi_write_hint = iocb->ki_hint;
bio.bi_private = current;
bio.bi_end_io = blkdev_bio_end_io_simple;
@@ -124,9 +124,8 @@ out:
}
enum {
- DIO_MULTI_BIO = 1,
- DIO_SHOULD_DIRTY = 2,
- DIO_IS_SYNC = 4,
+ DIO_SHOULD_DIRTY = 1,
+ DIO_IS_SYNC = 2,
};
struct blkdev_dio {
@@ -137,7 +136,7 @@ struct blkdev_dio {
size_t size;
atomic_t ref;
unsigned int flags;
- struct bio bio;
+ struct bio bio ____cacheline_aligned_in_smp;
};
static struct bio_set blkdev_dio_pool;
@@ -150,7 +149,7 @@ static void blkdev_bio_end_io(struct bio *bio)
if (bio->bi_status && !dio->bio.bi_status)
dio->bio.bi_status = bio->bi_status;
- if (!(dio->flags & DIO_MULTI_BIO) || atomic_dec_and_test(&dio->ref)) {
+ if (atomic_dec_and_test(&dio->ref)) {
if (!(dio->flags & DIO_IS_SYNC)) {
struct kiocb *iocb = dio->iocb;
ssize_t ret;
@@ -165,8 +164,7 @@ static void blkdev_bio_end_io(struct bio *bio)
}
dio->iocb->ki_complete(iocb, ret, 0);
- if (dio->flags & DIO_MULTI_BIO)
- bio_put(&dio->bio);
+ bio_put(&dio->bio);
} else {
struct task_struct *waiter = dio->waiter;
@@ -190,7 +188,6 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
struct blk_plug plug;
struct blkdev_dio *dio;
struct bio *bio;
- bool do_poll = (iocb->ki_flags & IOCB_HIPRI);
bool is_read = (iov_iter_rw(iter) == READ), is_sync;
loff_t pos = iocb->ki_pos;
int ret = 0;
@@ -202,11 +199,17 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
dio = container_of(bio, struct blkdev_dio, bio);
+ atomic_set(&dio->ref, 1);
+ /*
+ * Grab an extra reference to ensure the dio structure which is embedded
+ * into the first bio stays around.
+ */
+ bio_get(bio);
+
is_sync = is_sync_kiocb(iocb);
if (is_sync) {
dio->flags = DIO_IS_SYNC;
dio->waiter = current;
- bio_get(bio);
} else {
dio->flags = 0;
dio->iocb = iocb;
@@ -216,16 +219,11 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
if (is_read && iter_is_iovec(iter))
dio->flags |= DIO_SHOULD_DIRTY;
- /*
- * Don't plug for HIPRI/polled IO, as those should go straight
- * to issue
- */
- if (!(iocb->ki_flags & IOCB_HIPRI))
- blk_start_plug(&plug);
+ blk_start_plug(&plug);
for (;;) {
bio_set_dev(bio, bdev);
- bio->bi_iter.bi_sector = pos >> 9;
+ bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
bio->bi_write_hint = iocb->ki_hint;
bio->bi_private = dio;
bio->bi_end_io = blkdev_bio_end_io;
@@ -254,34 +252,15 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
if (!nr_pages) {
- if (do_poll)
- bio_set_polled(bio, iocb);
submit_bio(bio);
- if (do_poll)
- WRITE_ONCE(iocb->private, bio);
break;
}
- if (!(dio->flags & DIO_MULTI_BIO)) {
- /*
- * AIO needs an extra reference to ensure the dio
- * structure which is embedded into the first bio
- * stays around.
- */
- if (!is_sync)
- bio_get(bio);
- dio->flags |= DIO_MULTI_BIO;
- atomic_set(&dio->ref, 2);
- do_poll = false;
- } else {
- atomic_inc(&dio->ref);
- }
-
+ atomic_inc(&dio->ref);
submit_bio(bio);
bio = bio_alloc(GFP_KERNEL, nr_pages);
}
- if (!(iocb->ki_flags & IOCB_HIPRI))
- blk_finish_plug(&plug);
+ blk_finish_plug(&plug);
if (!is_sync)
return -EIOCBQUEUED;
@@ -290,9 +269,7 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
set_current_state(TASK_UNINTERRUPTIBLE);
if (!READ_ONCE(dio->waiter))
break;
-
- if (!do_poll || !bio_poll(bio, NULL, 0))
- blk_io_schedule();
+ blk_io_schedule();
}
__set_current_state(TASK_RUNNING);
@@ -305,6 +282,94 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
return ret;
}
+static void blkdev_bio_end_io_async(struct bio *bio)
+{
+ struct blkdev_dio *dio = container_of(bio, struct blkdev_dio, bio);
+ struct kiocb *iocb = dio->iocb;
+ ssize_t ret;
+
+ if (likely(!bio->bi_status)) {
+ ret = dio->size;
+ iocb->ki_pos += ret;
+ } else {
+ ret = blk_status_to_errno(bio->bi_status);
+ }
+
+ iocb->ki_complete(iocb, ret, 0);
+
+ if (dio->flags & DIO_SHOULD_DIRTY) {
+ bio_check_pages_dirty(bio);
+ } else {
+ bio_release_pages(bio, false);
+ bio_put(bio);
+ }
+}
+
+static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
+ struct iov_iter *iter,
+ unsigned int nr_pages)
+{
+ struct block_device *bdev = iocb->ki_filp->private_data;
+ struct blkdev_dio *dio;
+ struct bio *bio;
+ loff_t pos = iocb->ki_pos;
+ int ret = 0;
+
+ if ((pos | iov_iter_alignment(iter)) &
+ (bdev_logical_block_size(bdev) - 1))
+ return -EINVAL;
+
+ bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+ dio = container_of(bio, struct blkdev_dio, bio);
+ dio->flags = 0;
+ dio->iocb = iocb;
+ bio_set_dev(bio, bdev);
+ bio->bi_iter.bi_sector = pos >> SECTOR_SHIFT;
+ bio->bi_write_hint = iocb->ki_hint;
+ bio->bi_end_io = blkdev_bio_end_io_async;
+ bio->bi_ioprio = iocb->ki_ioprio;
+
+ if (iov_iter_is_bvec(iter)) {
+ /*
+ * Users don't rely on the iterator being in any particular
+ * state for async I/O returning -EIOCBQUEUED, hence we can
+ * avoid expensive iov_iter_advance(). Bypass
+ * bio_iov_iter_get_pages() and set the bvec directly.
+ */
+ bio_iov_bvec_set(bio, iter);
+ } else {
+ ret = bio_iov_iter_get_pages(bio, iter);
+ if (unlikely(ret)) {
+ bio->bi_status = BLK_STS_IOERR;
+ bio_endio(bio);
+ return ret;
+ }
+ }
+ dio->size = bio->bi_iter.bi_size;
+
+ if (iov_iter_rw(iter) == READ) {
+ bio->bi_opf = REQ_OP_READ;
+ if (iter_is_iovec(iter)) {
+ dio->flags |= DIO_SHOULD_DIRTY;
+ bio_set_pages_dirty(bio);
+ }
+ } else {
+ bio->bi_opf = dio_bio_write_op(iocb);
+ task_io_account_write(bio->bi_iter.bi_size);
+ }
+
+ if (iocb->ki_flags & IOCB_HIPRI) {
+ bio->bi_opf |= REQ_POLLED | REQ_NOWAIT;
+ submit_bio(bio);
+ WRITE_ONCE(iocb->private, bio);
+ } else {
+ if (iocb->ki_flags & IOCB_NOWAIT)
+ bio->bi_opf |= REQ_NOWAIT;
+ submit_bio(bio);
+ }
+ return -EIOCBQUEUED;
+}
+
static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
unsigned int nr_pages;
@@ -313,9 +378,11 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
return 0;
nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
- if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
- return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
-
+ if (likely(nr_pages <= BIO_MAX_VECS)) {
+ if (is_sync_kiocb(iocb))
+ return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+ return __blkdev_direct_IO_async(iocb, iter, nr_pages);
+ }
return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
}
@@ -503,17 +570,20 @@ static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
size_t shorted = 0;
ssize_t ret;
- if (pos >= size)
- return 0;
-
- size -= pos;
- if (iov_iter_count(to) > size) {
- shorted = iov_iter_count(to) - size;
- iov_iter_truncate(to, size);
+ if (unlikely(pos + iov_iter_count(to) > size)) {
+ if (pos >= size)
+ return 0;
+ size -= pos;
+ if (iov_iter_count(to) > size) {
+ shorted = iov_iter_count(to) - size;
+ iov_iter_truncate(to, size);
+ }
}
ret = generic_file_read_iter(iocb, to);
- iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+
+ if (unlikely(shorted))
+ iov_iter_reexpand(to, iov_iter_count(to) + shorted);
return ret;
}
@@ -562,16 +632,18 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
switch (mode) {
case FALLOC_FL_ZERO_RANGE:
case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
- error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
+ error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL,
+ BLKDEV_ZERO_NOUNMAP);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
- error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
- GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
+ error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL,
+ BLKDEV_ZERO_NOFALLBACK);
break;
case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
- error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
- GFP_KERNEL, 0);
+ error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT,
+ len >> SECTOR_SHIFT, GFP_KERNEL, 0);
break;
default:
error = -EOPNOTSUPP;
diff --git a/block/genhd.c b/block/genhd.c
index 53495e3391e3..febaaa55125a 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -590,16 +590,6 @@ void del_gendisk(struct gendisk *disk)
* Prevent new I/O from crossing bio_queue_enter().
*/
blk_queue_start_drain(q);
- blk_mq_freeze_queue_wait(q);
-
- rq_qos_exit(q);
- blk_sync_queue(q);
- blk_flush_integrity();
- /*
- * Allow using passthrough request again after the queue is torn down.
- */
- blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
- __blk_mq_unfreeze_queue(q, true);
if (!(disk->flags & GENHD_FL_HIDDEN)) {
sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");
@@ -622,9 +612,41 @@ void del_gendisk(struct gendisk *disk)
sysfs_remove_link(block_depr, dev_name(disk_to_dev(disk)));
pm_runtime_set_memalloc_noio(disk_to_dev(disk), false);
device_del(disk_to_dev(disk));
+
+ blk_mq_freeze_queue_wait(q);
+
+ rq_qos_exit(q);
+ blk_sync_queue(q);
+ blk_flush_integrity();
+ /*
+ * Allow using passthrough request again after the queue is torn down.
+ */
+ blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q);
+ __blk_mq_unfreeze_queue(q, true);
+
}
EXPORT_SYMBOL(del_gendisk);
+/**
+ * invalidate_disk - invalidate the disk
+ * @disk: the struct gendisk to invalidate
+ *
+ * A helper to invalidates the disk. It will clean the disk's associated
+ * buffer/page caches and reset its internal states so that the disk
+ * can be reused by the drivers.
+ *
+ * Context: can sleep
+ */
+void invalidate_disk(struct gendisk *disk)
+{
+ struct block_device *bdev = disk->part0;
+
+ invalidate_bdev(bdev);
+ bdev->bd_inode->i_mapping->wb_err = 0;
+ set_capacity(disk, 0);
+}
+EXPORT_SYMBOL(invalidate_disk);
+
/* sysfs access to bad-blocks list. */
static ssize_t disk_badblocks_show(struct device *dev,
struct device_attribute *attr,
@@ -1390,12 +1412,6 @@ void set_disk_ro(struct gendisk *disk, bool read_only)
}
EXPORT_SYMBOL(set_disk_ro);
-int bdev_read_only(struct block_device *bdev)
-{
- return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
-}
-EXPORT_SYMBOL(bdev_read_only);
-
void inc_diskseq(struct gendisk *disk)
{
disk->diskseq = atomic64_inc_return(&diskseq);
diff --git a/block/keyslot-manager.c b/block/keyslot-manager.c
deleted file mode 100644
index 1792159d12d1..000000000000
--- a/block/keyslot-manager.c
+++ /dev/null
@@ -1,579 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright 2019 Google LLC
- */
-
-/**
- * DOC: The Keyslot Manager
- *
- * Many devices with inline encryption support have a limited number of "slots"
- * into which encryption contexts may be programmed, and requests can be tagged
- * with a slot number to specify the key to use for en/decryption.
- *
- * As the number of slots is limited, and programming keys is expensive on
- * many inline encryption hardware, we don't want to program the same key into
- * multiple slots - if multiple requests are using the same key, we want to
- * program just one slot with that key and use that slot for all requests.
- *
- * The keyslot manager manages these keyslots appropriately, and also acts as
- * an abstraction between the inline encryption hardware and the upper layers.
- *
- * Lower layer devices will set up a keyslot manager in their request queue
- * and tell it how to perform device specific operations like programming/
- * evicting keys from keyslots.
- *
- * Upper layers will call blk_ksm_get_slot_for_key() to program a
- * key into some slot in the inline encryption hardware.
- */
-
-#define pr_fmt(fmt) "blk-crypto: " fmt
-
-#include <linux/keyslot-manager.h>
-#include <linux/device.h>
-#include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/pm_runtime.h>
-#include <linux/wait.h>
-#include <linux/blkdev.h>
-#include <linux/blk-integrity.h>
-
-struct blk_ksm_keyslot {
- atomic_t slot_refs;
- struct list_head idle_slot_node;
- struct hlist_node hash_node;
- const struct blk_crypto_key *key;
- struct blk_keyslot_manager *ksm;
-};
-
-static inline void blk_ksm_hw_enter(struct blk_keyslot_manager *ksm)
-{
- /*
- * Calling into the driver requires ksm->lock held and the device
- * resumed. But we must resume the device first, since that can acquire
- * and release ksm->lock via blk_ksm_reprogram_all_keys().
- */
- if (ksm->dev)
- pm_runtime_get_sync(ksm->dev);
- down_write(&ksm->lock);
-}
-
-static inline void blk_ksm_hw_exit(struct blk_keyslot_manager *ksm)
-{
- up_write(&ksm->lock);
- if (ksm->dev)
- pm_runtime_put_sync(ksm->dev);
-}
-
-static inline bool blk_ksm_is_passthrough(struct blk_keyslot_manager *ksm)
-{
- return ksm->num_slots == 0;
-}
-
-/**
- * blk_ksm_init() - Initialize a keyslot manager
- * @ksm: The keyslot_manager to initialize.
- * @num_slots: The number of key slots to manage.
- *
- * Allocate memory for keyslots and initialize a keyslot manager. Called by
- * e.g. storage drivers to set up a keyslot manager in their request_queue.
- *
- * Return: 0 on success, or else a negative error code.
- */
-int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots)
-{
- unsigned int slot;
- unsigned int i;
- unsigned int slot_hashtable_size;
-
- memset(ksm, 0, sizeof(*ksm));
-
- if (num_slots == 0)
- return -EINVAL;
-
- ksm->slots = kvcalloc(num_slots, sizeof(ksm->slots[0]), GFP_KERNEL);
- if (!ksm->slots)
- return -ENOMEM;
-
- ksm->num_slots = num_slots;
-
- init_rwsem(&ksm->lock);
-
- init_waitqueue_head(&ksm->idle_slots_wait_queue);
- INIT_LIST_HEAD(&ksm->idle_slots);
-
- for (slot = 0; slot < num_slots; slot++) {
- ksm->slots[slot].ksm = ksm;
- list_add_tail(&ksm->slots[slot].idle_slot_node,
- &ksm->idle_slots);
- }
-
- spin_lock_init(&ksm->idle_slots_lock);
-
- slot_hashtable_size = roundup_pow_of_two(num_slots);
- /*
- * hash_ptr() assumes bits != 0, so ensure the hash table has at least 2
- * buckets. This only makes a difference when there is only 1 keyslot.
- */
- if (slot_hashtable_size < 2)
- slot_hashtable_size = 2;
-
- ksm->log_slot_ht_size = ilog2(slot_hashtable_size);
- ksm->slot_hashtable = kvmalloc_array(slot_hashtable_size,
- sizeof(ksm->slot_hashtable[0]),
- GFP_KERNEL);
- if (!ksm->slot_hashtable)
- goto err_destroy_ksm;
- for (i = 0; i < slot_hashtable_size; i++)
- INIT_HLIST_HEAD(&ksm->slot_hashtable[i]);
-
- return 0;
-
-err_destroy_ksm:
- blk_ksm_destroy(ksm);
- return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_init);
-
-static void blk_ksm_destroy_callback(void *ksm)
-{
- blk_ksm_destroy(ksm);
-}
-
-/**
- * devm_blk_ksm_init() - Resource-managed blk_ksm_init()
- * @dev: The device which owns the blk_keyslot_manager.
- * @ksm: The blk_keyslot_manager to initialize.
- * @num_slots: The number of key slots to manage.
- *
- * Like blk_ksm_init(), but causes blk_ksm_destroy() to be called automatically
- * on driver detach.
- *
- * Return: 0 on success, or else a negative error code.
- */
-int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm,
- unsigned int num_slots)
-{
- int err = blk_ksm_init(ksm, num_slots);
-
- if (err)
- return err;
-
- return devm_add_action_or_reset(dev, blk_ksm_destroy_callback, ksm);
-}
-EXPORT_SYMBOL_GPL(devm_blk_ksm_init);
-
-static inline struct hlist_head *
-blk_ksm_hash_bucket_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- return &ksm->slot_hashtable[hash_ptr(key, ksm->log_slot_ht_size)];
-}
-
-static void blk_ksm_remove_slot_from_lru_list(struct blk_ksm_keyslot *slot)
-{
- struct blk_keyslot_manager *ksm = slot->ksm;
- unsigned long flags;
-
- spin_lock_irqsave(&ksm->idle_slots_lock, flags);
- list_del(&slot->idle_slot_node);
- spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
-}
-
-static struct blk_ksm_keyslot *blk_ksm_find_keyslot(
- struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- const struct hlist_head *head = blk_ksm_hash_bucket_for_key(ksm, key);
- struct blk_ksm_keyslot *slotp;
-
- hlist_for_each_entry(slotp, head, hash_node) {
- if (slotp->key == key)
- return slotp;
- }
- return NULL;
-}
-
-static struct blk_ksm_keyslot *blk_ksm_find_and_grab_keyslot(
- struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- struct blk_ksm_keyslot *slot;
-
- slot = blk_ksm_find_keyslot(ksm, key);
- if (!slot)
- return NULL;
- if (atomic_inc_return(&slot->slot_refs) == 1) {
- /* Took first reference to this slot; remove it from LRU list */
- blk_ksm_remove_slot_from_lru_list(slot);
- }
- return slot;
-}
-
-unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot)
-{
- return slot - slot->ksm->slots;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_get_slot_idx);
-
-/**
- * blk_ksm_get_slot_for_key() - Program a key into a keyslot.
- * @ksm: The keyslot manager to program the key into.
- * @key: Pointer to the key object to program, including the raw key, crypto
- * mode, and data unit size.
- * @slot_ptr: A pointer to return the pointer of the allocated keyslot.
- *
- * Get a keyslot that's been programmed with the specified key. If one already
- * exists, return it with incremented refcount. Otherwise, wait for a keyslot
- * to become idle and program it.
- *
- * Context: Process context. Takes and releases ksm->lock.
- * Return: BLK_STS_OK on success (and keyslot is set to the pointer of the
- * allocated keyslot), or some other blk_status_t otherwise (and
- * keyslot is set to NULL).
- */
-blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- struct blk_ksm_keyslot **slot_ptr)
-{
- struct blk_ksm_keyslot *slot;
- int slot_idx;
- int err;
-
- *slot_ptr = NULL;
-
- if (blk_ksm_is_passthrough(ksm))
- return BLK_STS_OK;
-
- down_read(&ksm->lock);
- slot = blk_ksm_find_and_grab_keyslot(ksm, key);
- up_read(&ksm->lock);
- if (slot)
- goto success;
-
- for (;;) {
- blk_ksm_hw_enter(ksm);
- slot = blk_ksm_find_and_grab_keyslot(ksm, key);
- if (slot) {
- blk_ksm_hw_exit(ksm);
- goto success;
- }
-
- /*
- * If we're here, that means there wasn't a slot that was
- * already programmed with the key. So try to program it.
- */
- if (!list_empty(&ksm->idle_slots))
- break;
-
- blk_ksm_hw_exit(ksm);
- wait_event(ksm->idle_slots_wait_queue,
- !list_empty(&ksm->idle_slots));
- }
-
- slot = list_first_entry(&ksm->idle_slots, struct blk_ksm_keyslot,
- idle_slot_node);
- slot_idx = blk_ksm_get_slot_idx(slot);
-
- err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot_idx);
- if (err) {
- wake_up(&ksm->idle_slots_wait_queue);
- blk_ksm_hw_exit(ksm);
- return errno_to_blk_status(err);
- }
-
- /* Move this slot to the hash list for the new key. */
- if (slot->key)
- hlist_del(&slot->hash_node);
- slot->key = key;
- hlist_add_head(&slot->hash_node, blk_ksm_hash_bucket_for_key(ksm, key));
-
- atomic_set(&slot->slot_refs, 1);
-
- blk_ksm_remove_slot_from_lru_list(slot);
-
- blk_ksm_hw_exit(ksm);
-success:
- *slot_ptr = slot;
- return BLK_STS_OK;
-}
-
-/**
- * blk_ksm_put_slot() - Release a reference to a slot
- * @slot: The keyslot to release the reference of.
- *
- * Context: Any context.
- */
-void blk_ksm_put_slot(struct blk_ksm_keyslot *slot)
-{
- struct blk_keyslot_manager *ksm;
- unsigned long flags;
-
- if (!slot)
- return;
-
- ksm = slot->ksm;
-
- if (atomic_dec_and_lock_irqsave(&slot->slot_refs,
- &ksm->idle_slots_lock, flags)) {
- list_add_tail(&slot->idle_slot_node, &ksm->idle_slots);
- spin_unlock_irqrestore(&ksm->idle_slots_lock, flags);
- wake_up(&ksm->idle_slots_wait_queue);
- }
-}
-
-/**
- * blk_ksm_crypto_cfg_supported() - Find out if a crypto configuration is
- * supported by a ksm.
- * @ksm: The keyslot manager to check
- * @cfg: The crypto configuration to check for.
- *
- * Checks for crypto_mode/data unit size/dun bytes support.
- *
- * Return: Whether or not this ksm supports the specified crypto config.
- */
-bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_config *cfg)
-{
- if (!ksm)
- return false;
- if (!(ksm->crypto_modes_supported[cfg->crypto_mode] &
- cfg->data_unit_size))
- return false;
- if (ksm->max_dun_bytes_supported < cfg->dun_bytes)
- return false;
- return true;
-}
-
-/**
- * blk_ksm_evict_key() - Evict a key from the lower layer device.
- * @ksm: The keyslot manager to evict from
- * @key: The key to evict
- *
- * Find the keyslot that the specified key was programmed into, and evict that
- * slot from the lower layer device. The slot must not be in use by any
- * in-flight IO when this function is called.
- *
- * Context: Process context. Takes and releases ksm->lock.
- * Return: 0 on success or if there's no keyslot with the specified key, -EBUSY
- * if the keyslot is still in use, or another -errno value on other
- * error.
- */
-int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key)
-{
- struct blk_ksm_keyslot *slot;
- int err = 0;
-
- if (blk_ksm_is_passthrough(ksm)) {
- if (ksm->ksm_ll_ops.keyslot_evict) {
- blk_ksm_hw_enter(ksm);
- err = ksm->ksm_ll_ops.keyslot_evict(ksm, key, -1);
- blk_ksm_hw_exit(ksm);
- return err;
- }
- return 0;
- }
-
- blk_ksm_hw_enter(ksm);
- slot = blk_ksm_find_keyslot(ksm, key);
- if (!slot)
- goto out_unlock;
-
- if (WARN_ON_ONCE(atomic_read(&slot->slot_refs) != 0)) {
- err = -EBUSY;
- goto out_unlock;
- }
- err = ksm->ksm_ll_ops.keyslot_evict(ksm, key,
- blk_ksm_get_slot_idx(slot));
- if (err)
- goto out_unlock;
-
- hlist_del(&slot->hash_node);
- slot->key = NULL;
- err = 0;
-out_unlock:
- blk_ksm_hw_exit(ksm);
- return err;
-}
-
-/**
- * blk_ksm_reprogram_all_keys() - Re-program all keyslots.
- * @ksm: The keyslot manager
- *
- * Re-program all keyslots that are supposed to have a key programmed. This is
- * intended only for use by drivers for hardware that loses its keys on reset.
- *
- * Context: Process context. Takes and releases ksm->lock.
- */
-void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm)
-{
- unsigned int slot;
-
- if (blk_ksm_is_passthrough(ksm))
- return;
-
- /* This is for device initialization, so don't resume the device */
- down_write(&ksm->lock);
- for (slot = 0; slot < ksm->num_slots; slot++) {
- const struct blk_crypto_key *key = ksm->slots[slot].key;
- int err;
-
- if (!key)
- continue;
-
- err = ksm->ksm_ll_ops.keyslot_program(ksm, key, slot);
- WARN_ON(err);
- }
- up_write(&ksm->lock);
-}
-EXPORT_SYMBOL_GPL(blk_ksm_reprogram_all_keys);
-
-void blk_ksm_destroy(struct blk_keyslot_manager *ksm)
-{
- if (!ksm)
- return;
- kvfree(ksm->slot_hashtable);
- kvfree_sensitive(ksm->slots, sizeof(ksm->slots[0]) * ksm->num_slots);
- memzero_explicit(ksm, sizeof(*ksm));
-}
-EXPORT_SYMBOL_GPL(blk_ksm_destroy);
-
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q)
-{
- if (blk_integrity_queue_supports_integrity(q)) {
- pr_warn("Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
- return false;
- }
- q->ksm = ksm;
- return true;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_register);
-
-void blk_ksm_unregister(struct request_queue *q)
-{
- q->ksm = NULL;
-}
-
-/**
- * blk_ksm_intersect_modes() - restrict supported modes by child device
- * @parent: The keyslot manager for parent device
- * @child: The keyslot manager for child device, or NULL
- *
- * Clear any crypto mode support bits in @parent that aren't set in @child.
- * If @child is NULL, then all parent bits are cleared.
- *
- * Only use this when setting up the keyslot manager for a layered device,
- * before it's been exposed yet.
- */
-void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent,
- const struct blk_keyslot_manager *child)
-{
- if (child) {
- unsigned int i;
-
- parent->max_dun_bytes_supported =
- min(parent->max_dun_bytes_supported,
- child->max_dun_bytes_supported);
- for (i = 0; i < ARRAY_SIZE(child->crypto_modes_supported);
- i++) {
- parent->crypto_modes_supported[i] &=
- child->crypto_modes_supported[i];
- }
- } else {
- parent->max_dun_bytes_supported = 0;
- memset(parent->crypto_modes_supported, 0,
- sizeof(parent->crypto_modes_supported));
- }
-}
-EXPORT_SYMBOL_GPL(blk_ksm_intersect_modes);
-
-/**
- * blk_ksm_is_superset() - Check if a KSM supports a superset of crypto modes
- * and DUN bytes that another KSM supports. Here,
- * "superset" refers to the mathematical meaning of the
- * word - i.e. if two KSMs have the *same* capabilities,
- * they *are* considered supersets of each other.
- * @ksm_superset: The KSM that we want to verify is a superset
- * @ksm_subset: The KSM that we want to verify is a subset
- *
- * Return: True if @ksm_superset supports a superset of the crypto modes and DUN
- * bytes that @ksm_subset supports.
- */
-bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset,
- struct blk_keyslot_manager *ksm_subset)
-{
- int i;
-
- if (!ksm_subset)
- return true;
-
- if (!ksm_superset)
- return false;
-
- for (i = 0; i < ARRAY_SIZE(ksm_superset->crypto_modes_supported); i++) {
- if (ksm_subset->crypto_modes_supported[i] &
- (~ksm_superset->crypto_modes_supported[i])) {
- return false;
- }
- }
-
- if (ksm_subset->max_dun_bytes_supported >
- ksm_superset->max_dun_bytes_supported) {
- return false;
- }
-
- return true;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_is_superset);
-
-/**
- * blk_ksm_update_capabilities() - Update the restrictions of a KSM to those of
- * another KSM
- * @target_ksm: The KSM whose restrictions to update.
- * @reference_ksm: The KSM to whose restrictions this function will update
- * @target_ksm's restrictions to.
- *
- * Blk-crypto requires that crypto capabilities that were
- * advertised when a bio was created continue to be supported by the
- * device until that bio is ended. This is turn means that a device cannot
- * shrink its advertised crypto capabilities without any explicit
- * synchronization with upper layers. So if there's no such explicit
- * synchronization, @reference_ksm must support all the crypto capabilities that
- * @target_ksm does
- * (i.e. we need blk_ksm_is_superset(@reference_ksm, @target_ksm) == true).
- *
- * Note also that as long as the crypto capabilities are being expanded, the
- * order of updates becoming visible is not important because it's alright
- * for blk-crypto to see stale values - they only cause blk-crypto to
- * believe that a crypto capability isn't supported when it actually is (which
- * might result in blk-crypto-fallback being used if available, or the bio being
- * failed).
- */
-void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm,
- struct blk_keyslot_manager *reference_ksm)
-{
- memcpy(target_ksm->crypto_modes_supported,
- reference_ksm->crypto_modes_supported,
- sizeof(target_ksm->crypto_modes_supported));
-
- target_ksm->max_dun_bytes_supported =
- reference_ksm->max_dun_bytes_supported;
-}
-EXPORT_SYMBOL_GPL(blk_ksm_update_capabilities);
-
-/**
- * blk_ksm_init_passthrough() - Init a passthrough keyslot manager
- * @ksm: The keyslot manager to init
- *
- * Initialize a passthrough keyslot manager.
- * Called by e.g. storage drivers to set up a keyslot manager in their
- * request_queue, when the storage driver wants to manage its keys by itself.
- * This is useful for inline encryption hardware that doesn't have the concept
- * of keyslots, and for layered devices.
- */
-void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm)
-{
- memset(ksm, 0, sizeof(*ksm));
- init_rwsem(&ksm->lock);
-}
-EXPORT_SYMBOL_GPL(blk_ksm_init_passthrough);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index 66ef9bc6d6a1..334b72ef1d73 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -425,6 +425,7 @@ out_del:
device_del(pdev);
out_put:
put_device(pdev);
+ return ERR_PTR(err);
out_put_disk:
put_disk(disk);
return ERR_PTR(err);
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index b9863e22b952..f0ed4414edb1 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -1035,13 +1035,8 @@ void acpi_turn_off_unused_power_resources(void)
list_for_each_entry_reverse(resource, &acpi_power_resource_list, list_node) {
mutex_lock(&resource->resource_lock);
- /*
- * Turn off power resources in an unknown state too, because the
- * platform firmware on some system expects the OS to turn off
- * power resources without any users unconditionally.
- */
if (!resource->ref_count &&
- resource->state != ACPI_POWER_RESOURCE_STATE_OFF) {
+ resource->state == ACPI_POWER_RESOURCE_STATE_ON) {
acpi_handle_debug(resource->device.handle, "Turning OFF\n");
__acpi_power_off(resource);
}
diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c
index f9383736fa0f..71419eb16e09 100644
--- a/drivers/acpi/tables.c
+++ b/drivers/acpi/tables.c
@@ -21,6 +21,7 @@
#include <linux/earlycpio.h>
#include <linux/initrd.h>
#include <linux/security.h>
+#include <linux/kmemleak.h>
#include "internal.h"
#ifdef CONFIG_ACPI_CUSTOM_DSDT
@@ -601,6 +602,8 @@ void __init acpi_table_upgrade(void)
*/
arch_reserve_mem_area(acpi_tables_addr, all_tables_size);
+ kmemleak_ignore_phys(acpi_tables_addr);
+
/*
* early_ioremap only can remap 256k one time. If we map all
* tables one time, we will hit the limit. Need to map chunks
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index 9d86203e1e7a..c53633d47bfb 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -3896,8 +3896,8 @@ static int mv_chip_id(struct ata_host *host, unsigned int board_idx)
break;
default:
- dev_err(host->dev, "BUG: invalid board index %u\n", board_idx);
- return 1;
+ dev_alert(host->dev, "BUG: invalid board index %u\n", board_idx);
+ return -EINVAL;
}
hpriv->hp_flags = hp_flags;
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index cfa29dc89bbf..fabf87058d80 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -281,14 +281,14 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
if (!blk)
return -ENOMEM;
+ rbnode->block = blk;
+
if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) {
present = krealloc(rbnode->cache_present,
BITS_TO_LONGS(blklen) * sizeof(*present),
GFP_KERNEL);
- if (!present) {
- kfree(blk);
+ if (!present)
return -ENOMEM;
- }
memset(present + BITS_TO_LONGS(rbnode->blklen), 0,
(BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen))
@@ -305,7 +305,6 @@ static int regcache_rbtree_insert_to_block(struct regmap *map,
}
/* update the rbnode block, its size and the base register */
- rbnode->block = blk;
rbnode->blklen = blklen;
rbnode->base_reg = base_reg;
rbnode->cache_present = present;
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ab3e37aa1830..f7f32eeaee63 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -180,14 +180,6 @@ config BLK_DEV_LOOP
bits of, say, a sound file). This is also safe if the file resides
on a remote file server.
- There are several ways of encrypting disks. Some of these require
- kernel patches. The vanilla kernel offers the cryptoloop option
- and a Device Mapper target (which is superior, as it supports all
- file systems). If you want to use the cryptoloop, say Y to both
- LOOP and CRYPTOLOOP, and make sure you have a recent (version 2.12
- or later) version of util-linux. Additionally, be aware that
- the cryptoloop is not safe for storing journaled filesystems.
-
Note that this loop device has nothing to do with the loopback
device used for network connections from the machine to itself.
@@ -211,21 +203,6 @@ config BLK_DEV_LOOP_MIN_COUNT
is used, it can be set to 0, since needed loop devices can be
dynamically allocated with the /dev/loop-control interface.
-config BLK_DEV_CRYPTOLOOP
- tristate "Cryptoloop Support (DEPRECATED)"
- select CRYPTO
- select CRYPTO_CBC
- depends on BLK_DEV_LOOP
- help
- Say Y here if you want to be able to use the ciphers that are
- provided by the CryptoAPI as loop transformation. This might be
- used as hard disk encryption.
-
- WARNING: This device is not safe for journaled file systems like
- ext3 or Reiserfs. Please use the Device Mapper crypto module
- instead, which can be configured to be on-disk compatible with the
- cryptoloop device. cryptoloop support will be removed in Linux 5.16.
-
source "drivers/block/drbd/Kconfig"
config BLK_DEV_NBD
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index bc68817ef496..11a74f17c9ad 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -24,7 +24,6 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
-obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 2909fd9e72fb..bf5c124c5452 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1780,6 +1780,7 @@ static const struct blk_mq_ops amiflop_mq_ops = {
static int fd_alloc_disk(int drive, int system)
{
struct gendisk *disk;
+ int err;
disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL);
if (IS_ERR(disk))
@@ -1798,8 +1799,10 @@ static int fd_alloc_disk(int drive, int system)
set_capacity(disk, 880 * 2);
unit[drive].gendisk[system] = disk;
- add_disk(disk);
- return 0;
+ err = add_disk(disk);
+ if (err)
+ blk_cleanup_disk(disk);
+ return err;
}
static int fd_alloc_drive(int drive)
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index 06b360f7123a..52484bcdedb9 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -37,8 +37,7 @@ static ssize_t aoedisk_show_state(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE,
- "%s%s\n",
+ return sysfs_emit(page, "%s%s\n",
(d->flags & DEVFL_UP) ? "up" : "down",
(d->flags & DEVFL_KICKME) ? ",kickme" :
(d->nopen && !(d->flags & DEVFL_UP)) ? ",closewait" : "");
@@ -52,8 +51,8 @@ static ssize_t aoedisk_show_mac(struct device *dev,
struct aoetgt *t = d->targets[0];
if (t == NULL)
- return snprintf(page, PAGE_SIZE, "none\n");
- return snprintf(page, PAGE_SIZE, "%pm\n", t->addr);
+ return sysfs_emit(page, "none\n");
+ return sysfs_emit(page, "%pm\n", t->addr);
}
static ssize_t aoedisk_show_netif(struct device *dev,
struct device_attribute *attr, char *page)
@@ -85,7 +84,7 @@ static ssize_t aoedisk_show_netif(struct device *dev,
ne = nd;
nd = nds;
if (*nd == NULL)
- return snprintf(page, PAGE_SIZE, "none\n");
+ return sysfs_emit(page, "none\n");
for (p = page; nd < ne; nd++)
p += scnprintf(p, PAGE_SIZE - (p-page), "%s%s",
p == page ? "" : ",", (*nd)->name);
@@ -99,7 +98,7 @@ static ssize_t aoedisk_show_fwver(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE, "0x%04x\n", (unsigned int) d->fw_ver);
+ return sysfs_emit(page, "0x%04x\n", (unsigned int) d->fw_ver);
}
static ssize_t aoedisk_show_payload(struct device *dev,
struct device_attribute *attr, char *page)
@@ -107,7 +106,7 @@ static ssize_t aoedisk_show_payload(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct aoedev *d = disk->private_data;
- return snprintf(page, PAGE_SIZE, "%lu\n", d->maxbcnt);
+ return sysfs_emit(page, "%lu\n", d->maxbcnt);
}
static int aoedisk_debugfs_show(struct seq_file *s, void *ignored)
@@ -417,7 +416,9 @@ aoeblk_gdalloc(void *vp)
spin_unlock_irqrestore(&d->lock, flags);
- device_add_disk(NULL, gd, aoe_attr_groups);
+ err = device_add_disk(NULL, gd, aoe_attr_groups);
+ if (err)
+ goto out_disk_cleanup;
aoedisk_add_debugfs(d);
spin_lock_irqsave(&d->lock, flags);
@@ -426,6 +427,8 @@ aoeblk_gdalloc(void *vp)
spin_unlock_irqrestore(&d->lock, flags);
return;
+out_disk_cleanup:
+ blk_cleanup_disk(gd);
err_tagset:
blk_mq_free_tag_set(set);
err_mempool:
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 58e921ab5729..d14bdc3589b2 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -299,6 +299,7 @@ static struct atari_floppy_struct {
disk change detection) */
int flags; /* flags */
struct gendisk *disk[NUM_DISK_MINORS];
+ bool registered[NUM_DISK_MINORS];
int ref;
int type;
struct blk_mq_tag_set tag_set;
@@ -457,10 +458,20 @@ static DEFINE_TIMER(fd_timer, check_change);
static void fd_end_request_cur(blk_status_t err)
{
+ DPRINT(("fd_end_request_cur(), bytes %d of %d\n",
+ blk_rq_cur_bytes(fd_request),
+ blk_rq_bytes(fd_request)));
+
if (!blk_update_request(fd_request, err,
blk_rq_cur_bytes(fd_request))) {
+ DPRINT(("calling __blk_mq_end_request()\n"));
__blk_mq_end_request(fd_request, err);
fd_request = NULL;
+ } else {
+ /* requeue rest of request */
+ DPRINT(("calling blk_mq_requeue_request()\n"));
+ blk_mq_requeue_request(fd_request, true);
+ fd_request = NULL;
}
}
@@ -654,9 +665,6 @@ static inline void copy_buffer(void *from, void *to)
*p2++ = *p1++;
}
-
-
-
/* General Interrupt Handling */
static void (*FloppyIRQHandler)( int status ) = NULL;
@@ -701,12 +709,21 @@ static void fd_error( void )
if (fd_request->error_count >= MAX_ERRORS) {
printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
fd_end_request_cur(BLK_STS_IOERR);
+ finish_fdc();
+ return;
}
else if (fd_request->error_count == RECALIBRATE_ERRORS) {
printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
if (SelectedDrive != -1)
SUD.track = -1;
}
+ /* need to re-run request to recalibrate */
+ atari_disable_irq( IRQ_MFP_FDC );
+
+ setup_req_params( SelectedDrive );
+ do_fd_action( SelectedDrive );
+
+ atari_enable_irq( IRQ_MFP_FDC );
}
@@ -733,8 +750,10 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
if (type) {
type--;
if (type >= NUM_DISK_MINORS ||
- minor2disktype[type].drive_types > DriveType)
+ minor2disktype[type].drive_types > DriveType) {
+ finish_fdc();
return -EINVAL;
+ }
}
q = unit[drive].disk[type]->queue;
@@ -752,6 +771,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
}
if (!UDT || desc->track >= UDT->blocks/UDT->spt/2 || desc->head >= 2) {
+ finish_fdc();
ret = -EINVAL;
goto out;
}
@@ -792,6 +812,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc)
wait_for_completion(&format_wait);
+ finish_fdc();
ret = FormatError ? -EIO : 0;
out:
blk_mq_unquiesce_queue(q);
@@ -826,6 +847,7 @@ static void do_fd_action( int drive )
else {
/* all sectors finished */
fd_end_request_cur(BLK_STS_OK);
+ finish_fdc();
return;
}
}
@@ -1230,6 +1252,7 @@ static void fd_rwsec_done1(int status)
else {
/* all sectors finished */
fd_end_request_cur(BLK_STS_OK);
+ finish_fdc();
}
return;
@@ -1351,7 +1374,7 @@ static void fd_times_out(struct timer_list *unused)
static void finish_fdc( void )
{
- if (!NeedSeek) {
+ if (!NeedSeek || !stdma_is_locked_by(floppy_irq)) {
finish_fdc_done( 0 );
}
else {
@@ -1386,7 +1409,8 @@ static void finish_fdc_done( int dummy )
start_motor_off_timer();
local_irq_save(flags);
- stdma_release();
+ if (stdma_is_locked_by(floppy_irq))
+ stdma_release();
local_irq_restore(flags);
DPRINT(("finish_fdc() finished\n"));
@@ -1436,8 +1460,7 @@ static int floppy_revalidate(struct gendisk *disk)
unsigned int drive = p - unit;
if (test_bit(drive, &changed_floppies) ||
- test_bit(drive, &fake_change) ||
- p->disktype == 0) {
+ test_bit(drive, &fake_change) || !p->disktype) {
if (UD.flags & FTD_MSG)
printk(KERN_ERR "floppy: clear format %p!\n", UDT);
BufferDrive = -1;
@@ -1476,15 +1499,6 @@ static void setup_req_params( int drive )
ReqTrack, ReqSector, (unsigned long)ReqData ));
}
-static void ataflop_commit_rqs(struct blk_mq_hw_ctx *hctx)
-{
- spin_lock_irq(&ataflop_lock);
- atari_disable_irq(IRQ_MFP_FDC);
- finish_fdc();
- atari_enable_irq(IRQ_MFP_FDC);
- spin_unlock_irq(&ataflop_lock);
-}
-
static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -1492,6 +1506,10 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
int drive = floppy - unit;
int type = floppy->type;
+ DPRINT(("Queue request: drive %d type %d sectors %d of %d last %d\n",
+ drive, type, blk_rq_cur_sectors(bd->rq),
+ blk_rq_sectors(bd->rq), bd->last));
+
spin_lock_irq(&ataflop_lock);
if (fd_request) {
spin_unlock_irq(&ataflop_lock);
@@ -1512,6 +1530,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
/* drive not connected */
printk(KERN_ERR "Unknown Device: fd%d\n", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
@@ -1528,11 +1547,13 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
if (--type >= NUM_DISK_MINORS) {
printk(KERN_WARNING "fd%d: invalid disk format", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
if (minor2disktype[type].drive_types > DriveType) {
printk(KERN_WARNING "fd%d: unsupported disk format", drive );
fd_end_request_cur(BLK_STS_IOERR);
+ stdma_release();
goto out;
}
type = minor2disktype[type].index;
@@ -1551,8 +1572,6 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx,
setup_req_params( drive );
do_fd_action( drive );
- if (bd->last)
- finish_fdc();
atari_enable_irq( IRQ_MFP_FDC );
out:
@@ -1635,6 +1654,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
/* what if type > 0 here? Overwrite specified entry ? */
if (type) {
/* refuse to re-set a predefined type for now */
+ finish_fdc();
return -EINVAL;
}
@@ -1702,8 +1722,10 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode,
/* sanity check */
if (setprm.track != dtp->blocks/dtp->spt/2 ||
- setprm.head != 2)
+ setprm.head != 2) {
+ finish_fdc();
return -EINVAL;
+ }
UDT = dtp;
set_capacity(disk, UDT->blocks);
@@ -1963,7 +1985,6 @@ static const struct block_device_operations floppy_fops = {
static const struct blk_mq_ops ataflop_mq_ops = {
.queue_rq = ataflop_queue_rq,
- .commit_rqs = ataflop_commit_rqs,
};
static int ataflop_alloc_disk(unsigned int drive, unsigned int type)
@@ -2001,12 +2022,28 @@ static void ataflop_probe(dev_t dev)
return;
mutex_lock(&ataflop_probe_lock);
if (!unit[drive].disk[type]) {
- if (ataflop_alloc_disk(drive, type) == 0)
+ if (ataflop_alloc_disk(drive, type) == 0) {
add_disk(unit[drive].disk[type]);
+ unit[drive].registered[type] = true;
+ }
}
mutex_unlock(&ataflop_probe_lock);
}
+static void atari_cleanup_floppy_disk(struct atari_floppy_struct *fs)
+{
+ int type;
+
+ for (type = 0; type < NUM_DISK_MINORS; type++) {
+ if (!fs->disk[type])
+ continue;
+ if (fs->registered[type])
+ del_gendisk(fs->disk[type]);
+ blk_cleanup_disk(fs->disk[type]);
+ }
+ blk_mq_free_tag_set(&fs->tag_set);
+}
+
static int __init atari_floppy_init (void)
{
int i;
@@ -2065,7 +2102,10 @@ static int __init atari_floppy_init (void)
for (i = 0; i < FD_MAX_UNITS; i++) {
unit[i].track = -1;
unit[i].flags = 0;
- add_disk(unit[i].disk[0]);
+ ret = add_disk(unit[i].disk[0]);
+ if (ret)
+ goto err_out_dma;
+ unit[i].registered[0] = true;
}
printk(KERN_INFO "Atari floppy driver: max. %cD, %strack buffering\n",
@@ -2075,12 +2115,11 @@ static int __init atari_floppy_init (void)
return 0;
+err_out_dma:
+ atari_stram_free(DMABuffer);
err:
- while (--i >= 0) {
- blk_cleanup_queue(unit[i].disk[0]->queue);
- put_disk(unit[i].disk[0]);
- blk_mq_free_tag_set(&unit[i].tag_set);
- }
+ while (--i >= 0)
+ atari_cleanup_floppy_disk(&unit[i]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
out_unlock:
@@ -2129,18 +2168,10 @@ __setup("floppy=", atari_floppy_setup);
static void __exit atari_floppy_exit(void)
{
- int i, type;
+ int i;
- for (i = 0; i < FD_MAX_UNITS; i++) {
- for (type = 0; type < NUM_DISK_MINORS; type++) {
- if (!unit[i].disk[type])
- continue;
- del_gendisk(unit[i].disk[type]);
- blk_cleanup_queue(unit[i].disk[type]->queue);
- put_disk(unit[i].disk[type]);
- }
- blk_mq_free_tag_set(&unit[i].tag_set);
- }
+ for (i = 0; i < FD_MAX_UNITS; i++)
+ atari_cleanup_floppy_disk(&unit[i]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
del_timer_sync(&fd_timer);
diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c
deleted file mode 100644
index f0a91faa43a8..000000000000
--- a/drivers/block/cryptoloop.c
+++ /dev/null
@@ -1,206 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- Linux loop encryption enabling module
-
- Copyright (C) 2002 Herbert Valerio Riedel <hvr@gnu.org>
- Copyright (C) 2003 Fruhwirth Clemens <clemens@endorphin.org>
-
- */
-
-#include <linux/module.h>
-
-#include <crypto/skcipher.h>
-#include <linux/init.h>
-#include <linux/string.h>
-#include <linux/blkdev.h>
-#include <linux/scatterlist.h>
-#include <linux/uaccess.h>
-#include "loop.h"
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("loop blockdevice transferfunction adaptor / CryptoAPI");
-MODULE_AUTHOR("Herbert Valerio Riedel <hvr@gnu.org>");
-
-#define LOOP_IV_SECTOR_BITS 9
-#define LOOP_IV_SECTOR_SIZE (1 << LOOP_IV_SECTOR_BITS)
-
-static int
-cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info)
-{
- int err = -EINVAL;
- int cipher_len;
- int mode_len;
- char cms[LO_NAME_SIZE]; /* cipher-mode string */
- char *mode;
- char *cmsp = cms; /* c-m string pointer */
- struct crypto_sync_skcipher *tfm;
-
- /* encryption breaks for non sector aligned offsets */
-
- if (info->lo_offset % LOOP_IV_SECTOR_SIZE)
- goto out;
-
- strncpy(cms, info->lo_crypt_name, LO_NAME_SIZE);
- cms[LO_NAME_SIZE - 1] = 0;
-
- cipher_len = strcspn(cmsp, "-");
-
- mode = cmsp + cipher_len;
- mode_len = 0;
- if (*mode) {
- mode++;
- mode_len = strcspn(mode, "-");
- }
-
- if (!mode_len) {
- mode = "cbc";
- mode_len = 3;
- }
-
- if (cipher_len + mode_len + 3 > LO_NAME_SIZE)
- return -EINVAL;
-
- memmove(cms, mode, mode_len);
- cmsp = cms + mode_len;
- *cmsp++ = '(';
- memcpy(cmsp, info->lo_crypt_name, cipher_len);
- cmsp += cipher_len;
- *cmsp++ = ')';
- *cmsp = 0;
-
- tfm = crypto_alloc_sync_skcipher(cms, 0, 0);
- if (IS_ERR(tfm))
- return PTR_ERR(tfm);
-
- err = crypto_sync_skcipher_setkey(tfm, info->lo_encrypt_key,
- info->lo_encrypt_key_size);
-
- if (err != 0)
- goto out_free_tfm;
-
- lo->key_data = tfm;
- return 0;
-
- out_free_tfm:
- crypto_free_sync_skcipher(tfm);
-
- out:
- return err;
-}
-
-
-typedef int (*encdec_cbc_t)(struct skcipher_request *req);
-
-static int
-cryptoloop_transfer(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t IV)
-{
- struct crypto_sync_skcipher *tfm = lo->key_data;
- SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm);
- struct scatterlist sg_out;
- struct scatterlist sg_in;
-
- encdec_cbc_t encdecfunc;
- struct page *in_page, *out_page;
- unsigned in_offs, out_offs;
- int err;
-
- skcipher_request_set_sync_tfm(req, tfm);
- skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP,
- NULL, NULL);
-
- sg_init_table(&sg_out, 1);
- sg_init_table(&sg_in, 1);
-
- if (cmd == READ) {
- in_page = raw_page;
- in_offs = raw_off;
- out_page = loop_page;
- out_offs = loop_off;
- encdecfunc = crypto_skcipher_decrypt;
- } else {
- in_page = loop_page;
- in_offs = loop_off;
- out_page = raw_page;
- out_offs = raw_off;
- encdecfunc = crypto_skcipher_encrypt;
- }
-
- while (size > 0) {
- const int sz = min(size, LOOP_IV_SECTOR_SIZE);
- u32 iv[4] = { 0, };
- iv[0] = cpu_to_le32(IV & 0xffffffff);
-
- sg_set_page(&sg_in, in_page, sz, in_offs);
- sg_set_page(&sg_out, out_page, sz, out_offs);
-
- skcipher_request_set_crypt(req, &sg_in, &sg_out, sz, iv);
- err = encdecfunc(req);
- if (err)
- goto out;
-
- IV++;
- size -= sz;
- in_offs += sz;
- out_offs += sz;
- }
-
- err = 0;
-
-out:
- skcipher_request_zero(req);
- return err;
-}
-
-static int
-cryptoloop_ioctl(struct loop_device *lo, int cmd, unsigned long arg)
-{
- return -EINVAL;
-}
-
-static int
-cryptoloop_release(struct loop_device *lo)
-{
- struct crypto_sync_skcipher *tfm = lo->key_data;
- if (tfm != NULL) {
- crypto_free_sync_skcipher(tfm);
- lo->key_data = NULL;
- return 0;
- }
- printk(KERN_ERR "cryptoloop_release(): tfm == NULL?\n");
- return -EINVAL;
-}
-
-static struct loop_func_table cryptoloop_funcs = {
- .number = LO_CRYPT_CRYPTOAPI,
- .init = cryptoloop_init,
- .ioctl = cryptoloop_ioctl,
- .transfer = cryptoloop_transfer,
- .release = cryptoloop_release,
- .owner = THIS_MODULE
-};
-
-static int __init
-init_cryptoloop(void)
-{
- int rc = loop_register_transfer(&cryptoloop_funcs);
-
- if (rc)
- printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n");
- else
- pr_warn("the cryptoloop driver has been deprecated and will be removed in in Linux 5.16\n");
- return rc;
-}
-
-static void __exit
-cleanup_cryptoloop(void)
-{
- if (loop_unregister_transfer(LO_CRYPT_CRYPTOAPI))
- printk(KERN_ERR
- "cryptoloop: loop_unregister_transfer failed\n");
-}
-
-module_init(init_cryptoloop);
-module_exit(cleanup_cryptoloop);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 55234a558e98..19db80a1e409 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2794,7 +2794,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
goto out_idr_remove_vol;
}
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
/* inherit the connection state */
device->state.conn = first_connection(resource)->cstate;
@@ -2808,6 +2810,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig
drbd_debugfs_device_add(device);
return NO_ERROR;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_idr_remove_vol:
idr_remove(&connection->peer_devices, vnr);
out_idr_remove_from_resource:
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 6288ce888414..3873e789478e 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -4479,6 +4479,7 @@ static const struct blk_mq_ops floppy_mq_ops = {
};
static struct platform_device floppy_device[N_DRIVE];
+static bool registered[N_DRIVE];
static bool floppy_available(int drive)
{
@@ -4694,8 +4695,12 @@ static int __init do_floppy_init(void)
if (err)
goto out_remove_drives;
- device_add_disk(&floppy_device[drive].dev, disks[drive][0],
- NULL);
+ registered[drive] = true;
+
+ err = device_add_disk(&floppy_device[drive].dev,
+ disks[drive][0], NULL);
+ if (err)
+ goto out_remove_drives;
}
return 0;
@@ -4704,7 +4709,8 @@ out_remove_drives:
while (drive--) {
if (floppy_available(drive)) {
del_gendisk(disks[drive][0]);
- platform_device_unregister(&floppy_device[drive]);
+ if (registered[drive])
+ platform_device_unregister(&floppy_device[drive]);
}
}
out_release_dma:
@@ -4947,30 +4953,14 @@ static void __exit floppy_module_exit(void)
if (disks[drive][i])
del_gendisk(disks[drive][i]);
}
- platform_device_unregister(&floppy_device[drive]);
+ if (registered[drive])
+ platform_device_unregister(&floppy_device[drive]);
}
for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
if (disks[drive][i])
- blk_cleanup_queue(disks[drive][i]->queue);
+ blk_cleanup_disk(disks[drive][i]);
}
blk_mq_free_tag_set(&tag_sets[drive]);
-
- /*
- * These disks have not called add_disk(). Don't put down
- * queue reference in put_disk().
- */
- if (!(allowed_drive_mask & (1 << drive)) ||
- fdc_state[FDC(drive)].version == FDC_NONE) {
- for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
- if (disks[drive][i])
- disks[drive][i]->queue = NULL;
- }
- }
-
- for (i = 0; i < ARRAY_SIZE(floppy_type); i++) {
- if (disks[drive][i])
- put_disk(disks[drive][i]);
- }
}
cancel_delayed_work_sync(&fd_timeout);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 7bf4686af774..f094de5f0056 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -133,58 +133,6 @@ static void loop_global_unlock(struct loop_device *lo, bool global)
static int max_part;
static int part_shift;
-static int transfer_xor(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block)
-{
- char *raw_buf = kmap_atomic(raw_page) + raw_off;
- char *loop_buf = kmap_atomic(loop_page) + loop_off;
- char *in, *out, *key;
- int i, keysize;
-
- if (cmd == READ) {
- in = raw_buf;
- out = loop_buf;
- } else {
- in = loop_buf;
- out = raw_buf;
- }
-
- key = lo->lo_encrypt_key;
- keysize = lo->lo_encrypt_key_size;
- for (i = 0; i < size; i++)
- *out++ = *in++ ^ key[(i & 511) % keysize];
-
- kunmap_atomic(loop_buf);
- kunmap_atomic(raw_buf);
- cond_resched();
- return 0;
-}
-
-static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
-{
- if (unlikely(info->lo_encrypt_key_size <= 0))
- return -EINVAL;
- return 0;
-}
-
-static struct loop_func_table none_funcs = {
- .number = LO_CRYPT_NONE,
-};
-
-static struct loop_func_table xor_funcs = {
- .number = LO_CRYPT_XOR,
- .transfer = transfer_xor,
- .init = xor_init
-};
-
-/* xfer_funcs[0] is special - its release function is never called */
-static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
- &none_funcs,
- &xor_funcs
-};
-
static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
loff_t loopsize;
@@ -228,8 +176,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
/*
* We support direct I/O only if lo_offset is aligned with the
* logical I/O size of backing device, and the logical block
- * size of loop is bigger than the backing device's and the loop
- * needn't transform transfer.
+ * size of loop is bigger than the backing device's.
*
* TODO: the above condition may be loosed in the future, and
* direct I/O may be switched runtime at that time because most
@@ -238,8 +185,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
if (dio) {
if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
!(lo->lo_offset & dio_align) &&
- mapping->a_ops->direct_IO &&
- !lo->transfer)
+ mapping->a_ops->direct_IO)
use_dio = true;
else
use_dio = false;
@@ -273,19 +219,6 @@ static void __loop_update_dio(struct loop_device *lo, bool dio)
}
/**
- * loop_validate_block_size() - validates the passed in block size
- * @bsize: size to validate
- */
-static int
-loop_validate_block_size(unsigned short bsize)
-{
- if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
- return -EINVAL;
-
- return 0;
-}
-
-/**
* loop_set_size() - sets device size and notifies userspace
* @lo: struct loop_device to set the size for
* @size: new size of the loop device
@@ -299,24 +232,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size)
kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
}
-static inline int
-lo_do_transfer(struct loop_device *lo, int cmd,
- struct page *rpage, unsigned roffs,
- struct page *lpage, unsigned loffs,
- int size, sector_t rblock)
-{
- int ret;
-
- ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
- if (likely(!ret))
- return 0;
-
- printk_ratelimited(KERN_ERR
- "loop: Transfer error at byte offset %llu, length %i.\n",
- (unsigned long long)rblock << 9, size);
- return ret;
-}
-
static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
struct iov_iter i;
@@ -356,41 +271,6 @@ static int lo_write_simple(struct loop_device *lo, struct request *rq,
return ret;
}
-/*
- * This is the slow, transforming version that needs to double buffer the
- * data as it cannot do the transformations in place without having direct
- * access to the destination pages of the backing file.
- */
-static int lo_write_transfer(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec, b;
- struct req_iterator iter;
- struct page *page;
- int ret = 0;
-
- page = alloc_page(GFP_NOIO);
- if (unlikely(!page))
- return -ENOMEM;
-
- rq_for_each_segment(bvec, rq, iter) {
- ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page,
- bvec.bv_offset, bvec.bv_len, pos >> 9);
- if (unlikely(ret))
- break;
-
- b.bv_page = page;
- b.bv_offset = 0;
- b.bv_len = bvec.bv_len;
- ret = lo_write_bvec(lo->lo_backing_file, &b, &pos);
- if (ret < 0)
- break;
- }
-
- __free_page(page);
- return ret;
-}
-
static int lo_read_simple(struct loop_device *lo, struct request *rq,
loff_t pos)
{
@@ -420,64 +300,12 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq,
return 0;
}
-static int lo_read_transfer(struct loop_device *lo, struct request *rq,
- loff_t pos)
-{
- struct bio_vec bvec, b;
- struct req_iterator iter;
- struct iov_iter i;
- struct page *page;
- ssize_t len;
- int ret = 0;
-
- page = alloc_page(GFP_NOIO);
- if (unlikely(!page))
- return -ENOMEM;
-
- rq_for_each_segment(bvec, rq, iter) {
- loff_t offset = pos;
-
- b.bv_page = page;
- b.bv_offset = 0;
- b.bv_len = bvec.bv_len;
-
- iov_iter_bvec(&i, READ, &b, 1, b.bv_len);
- len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
- if (len < 0) {
- ret = len;
- goto out_free_page;
- }
-
- ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page,
- bvec.bv_offset, len, offset >> 9);
- if (ret)
- goto out_free_page;
-
- flush_dcache_page(bvec.bv_page);
-
- if (len != bvec.bv_len) {
- struct bio *bio;
-
- __rq_for_each_bio(bio, rq)
- zero_fill_bio(bio);
- break;
- }
- }
-
- ret = 0;
-out_free_page:
- __free_page(page);
- return ret;
-}
-
static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos,
int mode)
{
/*
* We use fallocate to manipulate the space mappings used by the image
- * a.k.a. discard/zerorange. However we do not support this if
- * encryption is enabled, because it may give an attacker useful
- * information.
+ * a.k.a. discard/zerorange.
*/
struct file *file = lo->lo_backing_file;
struct request_queue *q = lo->lo_queue;
@@ -660,16 +488,12 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
case REQ_OP_DISCARD:
return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE);
case REQ_OP_WRITE:
- if (lo->transfer)
- return lo_write_transfer(lo, rq, pos);
- else if (cmd->use_aio)
+ if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, WRITE);
else
return lo_write_simple(lo, rq, pos);
case REQ_OP_READ:
- if (lo->transfer)
- return lo_read_transfer(lo, rq, pos);
- else if (cmd->use_aio)
+ if (cmd->use_aio)
return lo_rw_aio(lo, cmd, pos, READ);
else
return lo_read_simple(lo, rq, pos);
@@ -934,7 +758,7 @@ static void loop_config_discard(struct loop_device *lo)
* not blkdev_issue_discard(). This maintains consistent behavior with
* file-backed loop devices: discarded regions read back as zero.
*/
- if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) {
+ if (S_ISBLK(inode->i_mode)) {
struct request_queue *backingq = bdev_get_queue(I_BDEV(inode));
max_discard_sectors = backingq->limits.max_write_zeroes_sectors;
@@ -943,11 +767,9 @@ static void loop_config_discard(struct loop_device *lo)
/*
* We use punch hole to reclaim the free space used by the
- * image a.k.a. discard. However we do not support discard if
- * encryption is enabled, because it may give an attacker
- * useful information.
+ * image a.k.a. discard.
*/
- } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) {
+ } else if (!file->f_op->fallocate) {
max_discard_sectors = 0;
granularity = 0;
@@ -1084,43 +906,6 @@ static void loop_update_rotational(struct loop_device *lo)
blk_queue_flag_clear(QUEUE_FLAG_NONROT, q);
}
-static int
-loop_release_xfer(struct loop_device *lo)
-{
- int err = 0;
- struct loop_func_table *xfer = lo->lo_encryption;
-
- if (xfer) {
- if (xfer->release)
- err = xfer->release(lo);
- lo->transfer = NULL;
- lo->lo_encryption = NULL;
- module_put(xfer->owner);
- }
- return err;
-}
-
-static int
-loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
- const struct loop_info64 *i)
-{
- int err = 0;
-
- if (xfer) {
- struct module *owner = xfer->owner;
-
- if (!try_module_get(owner))
- return -EINVAL;
- if (xfer->init)
- err = xfer->init(lo, i);
- if (err)
- module_put(owner);
- else
- lo->lo_encryption = xfer;
- }
- return err;
-}
-
/**
* loop_set_status_from_info - configure device from loop_info
* @lo: struct loop_device to configure
@@ -1133,55 +918,27 @@ static int
loop_set_status_from_info(struct loop_device *lo,
const struct loop_info64 *info)
{
- int err;
- struct loop_func_table *xfer;
- kuid_t uid = current_uid();
-
if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
return -EINVAL;
- err = loop_release_xfer(lo);
- if (err)
- return err;
-
- if (info->lo_encrypt_type) {
- unsigned int type = info->lo_encrypt_type;
-
- if (type >= MAX_LO_CRYPT)
- return -EINVAL;
- xfer = xfer_funcs[type];
- if (xfer == NULL)
- return -EINVAL;
- } else
- xfer = NULL;
-
- err = loop_init_xfer(lo, xfer, info);
- if (err)
- return err;
+ switch (info->lo_encrypt_type) {
+ case LO_CRYPT_NONE:
+ break;
+ case LO_CRYPT_XOR:
+ pr_warn("support for the xor transformation has been removed.\n");
+ return -EINVAL;
+ case LO_CRYPT_CRYPTOAPI:
+ pr_warn("support for cryptoloop has been removed. Use dm-crypt instead.\n");
+ return -EINVAL;
+ default:
+ return -EINVAL;
+ }
lo->lo_offset = info->lo_offset;
lo->lo_sizelimit = info->lo_sizelimit;
memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
- memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
lo->lo_file_name[LO_NAME_SIZE-1] = 0;
- lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;
-
- if (!xfer)
- xfer = &none_funcs;
- lo->transfer = xfer->transfer;
- lo->ioctl = xfer->ioctl;
-
lo->lo_flags = info->lo_flags;
-
- lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
- lo->lo_init[0] = info->lo_init[0];
- lo->lo_init[1] = info->lo_init[1];
- if (info->lo_encrypt_key_size) {
- memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
- info->lo_encrypt_key_size);
- lo->lo_key_owner = uid;
- }
-
return 0;
}
@@ -1236,7 +993,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
}
if (config->block_size) {
- error = loop_validate_block_size(config->block_size);
+ error = blk_validate_block_size(config->block_size);
if (error)
goto out_unlock;
}
@@ -1329,7 +1086,6 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
{
struct file *filp = NULL;
gfp_t gfp = lo->old_gfp_mask;
- struct block_device *bdev = lo->lo_device;
int err = 0;
bool partscan = false;
int lo_number;
@@ -1381,36 +1137,23 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
lo->lo_backing_file = NULL;
spin_unlock_irq(&lo->lo_lock);
- loop_release_xfer(lo);
- lo->transfer = NULL;
- lo->ioctl = NULL;
lo->lo_device = NULL;
- lo->lo_encryption = NULL;
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
- lo->lo_encrypt_key_size = 0;
- memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
- memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
memset(lo->lo_file_name, 0, LO_NAME_SIZE);
blk_queue_logical_block_size(lo->lo_queue, 512);
blk_queue_physical_block_size(lo->lo_queue, 512);
blk_queue_io_min(lo->lo_queue, 512);
- if (bdev) {
- invalidate_bdev(bdev);
- bdev->bd_inode->i_mapping->wb_err = 0;
- }
- set_capacity(lo->lo_disk, 0);
+ invalidate_disk(lo->lo_disk);
loop_sysfs_exit(lo);
- if (bdev) {
- /* let user-space know about this change */
- kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
- }
+ /* let user-space know about this change */
+ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);
mapping_set_gfp_mask(filp->f_mapping, gfp);
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
blk_mq_unfreeze_queue(lo->lo_queue);
- partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev;
+ partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
lo_number = lo->lo_number;
disk_force_media_change(lo->lo_disk, DISK_EVENT_MEDIA_CHANGE);
out_unlock:
@@ -1498,7 +1241,6 @@ static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
int err;
- kuid_t uid = current_uid();
int prev_lo_flags;
bool partscan = false;
bool size_changed = false;
@@ -1506,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
err = mutex_lock_killable(&lo->lo_mutex);
if (err)
return err;
- if (lo->lo_encrypt_key_size &&
- !uid_eq(lo->lo_key_owner, uid) &&
- !capable(CAP_SYS_ADMIN)) {
- err = -EPERM;
- goto out_unlock;
- }
if (lo->lo_state != Lo_bound) {
err = -ENXIO;
goto out_unlock;
@@ -1597,14 +1333,6 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info)
info->lo_sizelimit = lo->lo_sizelimit;
info->lo_flags = lo->lo_flags;
memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
- memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
- info->lo_encrypt_type =
- lo->lo_encryption ? lo->lo_encryption->number : 0;
- if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
- info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
- memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
- lo->lo_encrypt_key_size);
- }
/* Drop lo_mutex while we call into the filesystem. */
path = lo->lo_backing_file->f_path;
@@ -1630,16 +1358,8 @@ loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
info64->lo_rdevice = info->lo_rdevice;
info64->lo_offset = info->lo_offset;
info64->lo_sizelimit = 0;
- info64->lo_encrypt_type = info->lo_encrypt_type;
- info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
info64->lo_flags = info->lo_flags;
- info64->lo_init[0] = info->lo_init[0];
- info64->lo_init[1] = info->lo_init[1];
- if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
- else
- memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
- memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
}
static int
@@ -1651,16 +1371,8 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
info->lo_inode = info64->lo_inode;
info->lo_rdevice = info64->lo_rdevice;
info->lo_offset = info64->lo_offset;
- info->lo_encrypt_type = info64->lo_encrypt_type;
- info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
info->lo_flags = info64->lo_flags;
- info->lo_init[0] = info64->lo_init[0];
- info->lo_init[1] = info64->lo_init[1];
- if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
- else
- memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
- memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info->lo_device != info64->lo_device ||
@@ -1759,7 +1471,7 @@ static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
if (lo->lo_state != Lo_bound)
return -ENXIO;
- err = loop_validate_block_size(arg);
+ err = blk_validate_block_size(arg);
if (err)
return err;
@@ -1809,7 +1521,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd,
err = loop_set_block_size(lo, arg);
break;
default:
- err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
+ err = -EINVAL;
}
mutex_unlock(&lo->lo_mutex);
return err;
@@ -1885,7 +1597,6 @@ struct compat_loop_info {
compat_ulong_t lo_inode; /* ioctl r/o */
compat_dev_t lo_rdevice; /* ioctl r/o */
compat_int_t lo_offset;
- compat_int_t lo_encrypt_type;
compat_int_t lo_encrypt_key_size; /* ioctl w/o */
compat_int_t lo_flags; /* ioctl r/o */
char lo_name[LO_NAME_SIZE];
@@ -1914,16 +1625,8 @@ loop_info64_from_compat(const struct compat_loop_info __user *arg,
info64->lo_rdevice = info.lo_rdevice;
info64->lo_offset = info.lo_offset;
info64->lo_sizelimit = 0;
- info64->lo_encrypt_type = info.lo_encrypt_type;
- info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
info64->lo_flags = info.lo_flags;
- info64->lo_init[0] = info.lo_init[0];
- info64->lo_init[1] = info.lo_init[1];
- if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
- else
- memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
- memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
return 0;
}
@@ -1943,24 +1646,14 @@ loop_info64_to_compat(const struct loop_info64 *info64,
info.lo_inode = info64->lo_inode;
info.lo_rdevice = info64->lo_rdevice;
info.lo_offset = info64->lo_offset;
- info.lo_encrypt_type = info64->lo_encrypt_type;
- info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
info.lo_flags = info64->lo_flags;
- info.lo_init[0] = info64->lo_init[0];
- info.lo_init[1] = info64->lo_init[1];
- if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
- memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
- else
- memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
- memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+ memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
/* error in case values were truncated */
if (info.lo_device != info64->lo_device ||
info.lo_rdevice != info64->lo_rdevice ||
info.lo_inode != info64->lo_inode ||
- info.lo_offset != info64->lo_offset ||
- info.lo_init[0] != info64->lo_init[0] ||
- info.lo_init[1] != info64->lo_init[1])
+ info.lo_offset != info64->lo_offset)
return -EOVERFLOW;
if (copy_to_user(arg, &info, sizeof(info)))
@@ -2101,43 +1794,6 @@ MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);
-int loop_register_transfer(struct loop_func_table *funcs)
-{
- unsigned int n = funcs->number;
-
- if (n >= MAX_LO_CRYPT || xfer_funcs[n])
- return -EINVAL;
- xfer_funcs[n] = funcs;
- return 0;
-}
-
-int loop_unregister_transfer(int number)
-{
- unsigned int n = number;
- struct loop_func_table *xfer;
-
- if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
- return -EINVAL;
- /*
- * This function is called from only cleanup_cryptoloop().
- * Given that each loop device that has a transfer enabled holds a
- * reference to the module implementing it we should never get here
- * with a transfer that is set (unless forced module unloading is
- * requested). Thus, check module's refcount and warn if this is
- * not a clean unloading.
- */
-#ifdef CONFIG_MODULE_UNLOAD
- if (xfer->owner && module_refcount(xfer->owner) != -1)
- pr_err("Danger! Unregistering an in use transfer function.\n");
-#endif
-
- xfer_funcs[n] = NULL;
- return 0;
-}
-
-EXPORT_SYMBOL(loop_register_transfer);
-EXPORT_SYMBOL(loop_unregister_transfer);
-
static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -2394,13 +2050,19 @@ static int loop_add(int i)
disk->event_flags = DISK_EVENT_FLAG_UEVENT;
sprintf(disk->disk_name, "loop%d", i);
/* Make this loop device reachable from pathname. */
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
+
/* Show this loop device. */
mutex_lock(&loop_ctl_mutex);
lo->idr_visible = true;
mutex_unlock(&loop_ctl_mutex);
+
return i;
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
out_cleanup_tags:
blk_mq_free_tag_set(&lo->tag_set);
out_free_idr:
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 04c88dd6eabd..082d4b6bfc6a 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -32,23 +32,10 @@ struct loop_device {
loff_t lo_offset;
loff_t lo_sizelimit;
int lo_flags;
- int (*transfer)(struct loop_device *, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block);
char lo_file_name[LO_NAME_SIZE];
- char lo_crypt_name[LO_NAME_SIZE];
- char lo_encrypt_key[LO_KEY_SIZE];
- int lo_encrypt_key_size;
- struct loop_func_table *lo_encryption;
- __u32 lo_init[2];
- kuid_t lo_key_owner; /* Who set the key */
- int (*ioctl)(struct loop_device *, int cmd,
- unsigned long arg);
struct file * lo_backing_file;
struct block_device *lo_device;
- void *key_data;
gfp_t old_gfp_mask;
@@ -82,21 +69,4 @@ struct loop_cmd {
struct cgroup_subsys_state *memcg_css;
};
-/* Support for loadable transfer modules */
-struct loop_func_table {
- int number; /* filter type */
- int (*transfer)(struct loop_device *lo, int cmd,
- struct page *raw_page, unsigned raw_off,
- struct page *loop_page, unsigned loop_off,
- int size, sector_t real_block);
- int (*init)(struct loop_device *, const struct loop_info64 *);
- /* release is called from loop_unregister_transfer or clr_fd */
- int (*release)(struct loop_device *);
- int (*ioctl)(struct loop_device *, int cmd, unsigned long arg);
- struct module *owner;
-};
-
-int loop_register_transfer(struct loop_func_table *funcs);
-int loop_unregister_transfer(int number);
-
#endif
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 901855717cb5..c91b9010c1a6 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -3633,7 +3633,9 @@ skip_create_disk:
set_capacity(dd->disk, capacity);
/* Enable the block device and add it to /dev */
- device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups);
+ rv = device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups);
+ if (rv)
+ goto read_capacity_error;
if (dd->mtip_svc_handler) {
set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag);
@@ -4061,7 +4063,6 @@ block_initialize_err:
msi_initialize_err:
if (dd->isr_workq) {
- flush_workqueue(dd->isr_workq);
destroy_workqueue(dd->isr_workq);
drop_cpu(dd->work[0].cpu_binding);
drop_cpu(dd->work[1].cpu_binding);
@@ -4119,7 +4120,6 @@ static void mtip_pci_remove(struct pci_dev *pdev)
mtip_block_remove(dd);
if (dd->isr_workq) {
- flush_workqueue(dd->isr_workq);
destroy_workqueue(dd->isr_workq);
drop_cpu(dd->work[0].cpu_binding);
drop_cpu(dd->work[1].cpu_binding);
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index b168ca25b6c9..78282f01f581 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -115,6 +115,7 @@ static const struct block_device_operations n64cart_fops = {
static int __init n64cart_probe(struct platform_device *pdev)
{
struct gendisk *disk;
+ int err = -ENOMEM;
if (!start || !size) {
pr_err("start or size not specified\n");
@@ -132,7 +133,7 @@ static int __init n64cart_probe(struct platform_device *pdev)
disk = blk_alloc_disk(NUMA_NO_NODE);
if (!disk)
- return -ENOMEM;
+ goto out;
disk->first_minor = 0;
disk->flags = GENHD_FL_NO_PART_SCAN;
@@ -147,11 +148,18 @@ static int __init n64cart_probe(struct platform_device *pdev)
blk_queue_physical_block_size(disk->queue, 4096);
blk_queue_logical_block_size(disk->queue, 4096);
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_cleanup_disk;
pr_info("n64cart: %u kb disk\n", size / 1024);
return 0;
+
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
+out:
+ return err;
}
static struct platform_driver n64cart_driver = {
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 1183f7872b71..b47b2a87ae8f 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -122,15 +122,21 @@ struct nbd_device {
struct work_struct remove_work;
struct list_head list;
- struct task_struct *task_recv;
struct task_struct *task_setup;
unsigned long flags;
+ pid_t pid; /* pid of nbd-client, if attached */
char *backend;
};
#define NBD_CMD_REQUEUED 1
+/*
+ * This flag will be set if nbd_queue_rq() succeed, and will be checked and
+ * cleared in completion. Both setting and clearing of the flag are protected
+ * by cmd->lock.
+ */
+#define NBD_CMD_INFLIGHT 2
struct nbd_cmd {
struct nbd_device *nbd;
@@ -217,7 +223,7 @@ static ssize_t pid_show(struct device *dev,
struct gendisk *disk = dev_to_disk(dev);
struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
- return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+ return sprintf(buf, "%d\n", nbd->pid);
}
static const struct device_attribute pid_attr = {
@@ -310,26 +316,19 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
nsock->sent = 0;
}
-static void nbd_size_clear(struct nbd_device *nbd)
-{
- if (nbd->config->bytesize) {
- set_capacity(nbd->disk, 0);
- kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
- }
-}
-
static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
loff_t blksize)
{
if (!blksize)
blksize = 1u << NBD_DEF_BLKSIZE_BITS;
- if (blksize < 512 || blksize > PAGE_SIZE || !is_power_of_2(blksize))
+
+ if (blk_validate_block_size(blksize))
return -EINVAL;
nbd->config->bytesize = bytesize;
nbd->config->blksize_bits = __ffs(blksize);
- if (!nbd->task_recv)
+ if (!nbd->pid)
return 0;
if (nbd->config->flags & NBD_FLAG_SEND_TRIM) {
@@ -405,6 +404,11 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
if (!mutex_trylock(&cmd->lock))
return BLK_EH_RESET_TIMER;
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ mutex_unlock(&cmd->lock);
+ return BLK_EH_DONE;
+ }
+
if (!refcount_inc_not_zero(&nbd->config_refs)) {
cmd->status = BLK_STS_TIMEOUT;
mutex_unlock(&cmd->lock);
@@ -484,7 +488,8 @@ done:
}
/*
- * Send or receive packet.
+ * Send or receive packet. Return a positive value on success and
+ * negtive value on failue, and never return 0.
*/
static int sock_xmit(struct nbd_device *nbd, int index, int send,
struct iov_iter *iter, int msg_flags, int *sent)
@@ -610,7 +615,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
result = sock_xmit(nbd, index, 1, &from,
(type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent);
trace_nbd_header_sent(req, handle);
- if (result <= 0) {
+ if (result < 0) {
if (was_interrupted(result)) {
/* If we havne't sent anything we can just return BUSY,
* however if we have sent something we need to make
@@ -654,7 +659,7 @@ send_pages:
skip = 0;
}
result = sock_xmit(nbd, index, 1, &from, flags, &sent);
- if (result <= 0) {
+ if (result < 0) {
if (was_interrupted(result)) {
/* We've already sent the header, we
* have no choice but to set pending and
@@ -688,38 +693,45 @@ out:
return 0;
}
-/* NULL returned = something went wrong, inform userspace */
-static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
+static int nbd_read_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
{
- struct nbd_config *config = nbd->config;
- int result;
- struct nbd_reply reply;
- struct nbd_cmd *cmd;
- struct request *req = NULL;
- u64 handle;
- u16 hwq;
- u32 tag;
- struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
+ struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)};
struct iov_iter to;
- int ret = 0;
+ int result;
- reply.magic = 0;
- iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply));
+ reply->magic = 0;
+ iov_iter_kvec(&to, READ, &iov, 1, sizeof(*reply));
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
- if (result <= 0) {
- if (!nbd_disconnected(config))
+ if (result < 0) {
+ if (!nbd_disconnected(nbd->config))
dev_err(disk_to_dev(nbd->disk),
"Receive control failed (result %d)\n", result);
- return ERR_PTR(result);
+ return result;
}
- if (ntohl(reply.magic) != NBD_REPLY_MAGIC) {
+ if (ntohl(reply->magic) != NBD_REPLY_MAGIC) {
dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n",
- (unsigned long)ntohl(reply.magic));
- return ERR_PTR(-EPROTO);
+ (unsigned long)ntohl(reply->magic));
+ return -EPROTO;
}
- memcpy(&handle, reply.handle, sizeof(handle));
+ return 0;
+}
+
+/* NULL returned = something went wrong, inform userspace */
+static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index,
+ struct nbd_reply *reply)
+{
+ int result;
+ struct nbd_cmd *cmd;
+ struct request *req = NULL;
+ u64 handle;
+ u16 hwq;
+ u32 tag;
+ int ret = 0;
+
+ memcpy(&handle, reply->handle, sizeof(handle));
tag = nbd_handle_to_tag(handle);
hwq = blk_mq_unique_tag_to_hwq(tag);
if (hwq < nbd->tag_set.nr_hw_queues)
@@ -734,6 +746,16 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
cmd = blk_mq_rq_to_pdu(req);
mutex_lock(&cmd->lock);
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)",
+ tag, cmd->status, cmd->flags);
+ ret = -ENOENT;
+ goto out;
+ }
+ if (cmd->index != index) {
+ dev_err(disk_to_dev(nbd->disk), "Unexpected reply %d from different sock %d (expected %d)",
+ tag, index, cmd->index);
+ }
if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
@@ -752,9 +774,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
ret = -ENOENT;
goto out;
}
- if (ntohl(reply.error)) {
+ if (ntohl(reply->error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
- ntohl(reply.error));
+ ntohl(reply->error));
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -763,11 +785,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
if (rq_data_dir(req) != WRITE) {
struct req_iterator iter;
struct bio_vec bvec;
+ struct iov_iter to;
rq_for_each_segment(bvec, req, iter) {
iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len);
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
- if (result <= 0) {
+ if (result < 0) {
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
/*
@@ -776,7 +799,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
* and let the timeout stuff handle resubmitting
* this request onto another connection.
*/
- if (nbd_disconnected(config)) {
+ if (nbd_disconnected(nbd->config)) {
cmd->status = BLK_STS_IOERR;
goto out;
}
@@ -800,24 +823,46 @@ static void recv_work(struct work_struct *work)
work);
struct nbd_device *nbd = args->nbd;
struct nbd_config *config = nbd->config;
+ struct request_queue *q = nbd->disk->queue;
+ struct nbd_sock *nsock;
struct nbd_cmd *cmd;
struct request *rq;
while (1) {
- cmd = nbd_read_stat(nbd, args->index);
- if (IS_ERR(cmd)) {
- struct nbd_sock *nsock = config->socks[args->index];
+ struct nbd_reply reply;
- mutex_lock(&nsock->tx_lock);
- nbd_mark_nsock_dead(nbd, nsock, 1);
- mutex_unlock(&nsock->tx_lock);
+ if (nbd_read_reply(nbd, args->index, &reply))
+ break;
+
+ /*
+ * Grab .q_usage_counter so request pool won't go away, then no
+ * request use-after-free is possible during nbd_handle_reply().
+ * If queue is frozen, there won't be any inflight requests, we
+ * needn't to handle the incoming garbage message.
+ */
+ if (!percpu_ref_tryget(&q->q_usage_counter)) {
+ dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n",
+ __func__);
+ break;
+ }
+
+ cmd = nbd_handle_reply(nbd, args->index, &reply);
+ if (IS_ERR(cmd)) {
+ percpu_ref_put(&q->q_usage_counter);
break;
}
rq = blk_mq_rq_from_pdu(cmd);
if (likely(!blk_should_fake_timeout(rq->q)))
blk_mq_complete_request(rq);
+ percpu_ref_put(&q->q_usage_counter);
}
+
+ nsock = config->socks[args->index];
+ mutex_lock(&nsock->tx_lock);
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+
nbd_config_put(nbd);
atomic_dec(&config->recv_threads);
wake_up(&config->recv_wq);
@@ -833,6 +878,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
return true;
mutex_lock(&cmd->lock);
+ if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) {
+ mutex_unlock(&cmd->lock);
+ return true;
+ }
cmd->status = BLK_STS_IOERR;
mutex_unlock(&cmd->lock);
@@ -914,7 +963,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
if (!refcount_inc_not_zero(&nbd->config_refs)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Socks array is empty\n");
- blk_mq_start_request(req);
return -EINVAL;
}
config = nbd->config;
@@ -923,7 +971,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on invalid socket\n");
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EINVAL;
}
cmd->status = BLK_STS_OK;
@@ -947,7 +994,6 @@ again:
*/
sock_shutdown(nbd);
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EIO;
}
goto again;
@@ -969,7 +1015,13 @@ again:
* returns EAGAIN can be retried on a different socket.
*/
ret = nbd_send_cmd(nbd, cmd, index);
- if (ret == -EAGAIN) {
+ /*
+ * Access to this flag is protected by cmd->lock, thus it's safe to set
+ * the flag after nbd_send_cmd() succeed to send request to server.
+ */
+ if (!ret)
+ __set_bit(NBD_CMD_INFLIGHT, &cmd->flags);
+ else if (ret == -EAGAIN) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Request send failed, requeueing\n");
nbd_mark_nsock_dead(nbd, nsock, 1);
@@ -1206,7 +1258,7 @@ static void send_disconnects(struct nbd_device *nbd)
iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request));
mutex_lock(&nsock->tx_lock);
ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
- if (ret <= 0)
+ if (ret < 0)
dev_err(disk_to_dev(nbd->disk),
"Send disconnect failed %d\n", ret);
mutex_unlock(&nsock->tx_lock);
@@ -1237,11 +1289,13 @@ static void nbd_config_put(struct nbd_device *nbd)
&nbd->config_lock)) {
struct nbd_config *config = nbd->config;
nbd_dev_dbg_close(nbd);
- nbd_size_clear(nbd);
+ invalidate_disk(nbd->disk);
+ if (nbd->config->bytesize)
+ kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
if (test_and_clear_bit(NBD_RT_HAS_PID_FILE,
&config->runtime_flags))
device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
- nbd->task_recv = NULL;
+ nbd->pid = 0;
if (test_and_clear_bit(NBD_RT_HAS_BACKEND_FILE,
&config->runtime_flags)) {
device_remove_file(disk_to_dev(nbd->disk), &backend_attr);
@@ -1282,7 +1336,7 @@ static int nbd_start_device(struct nbd_device *nbd)
int num_connections = config->num_connections;
int error = 0, i;
- if (nbd->task_recv)
+ if (nbd->pid)
return -EBUSY;
if (!config->socks)
return -EINVAL;
@@ -1301,7 +1355,7 @@ static int nbd_start_device(struct nbd_device *nbd)
}
blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
- nbd->task_recv = current;
+ nbd->pid = task_pid_nr(current);
nbd_parse_flags(nbd);
@@ -1557,8 +1611,8 @@ static int nbd_dbg_tasks_show(struct seq_file *s, void *unused)
{
struct nbd_device *nbd = s->private;
- if (nbd->task_recv)
- seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv));
+ if (nbd->pid)
+ seq_printf(s, "recv: %d\n", nbd->pid);
return 0;
}
@@ -1762,7 +1816,9 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
disk->fops = &nbd_fops;
disk->private_data = nbd;
sprintf(disk->disk_name, "nbd%d", index);
- add_disk(disk);
+ err = add_disk(disk);
+ if (err)
+ goto out_err_disk;
/*
* Now publish the device.
@@ -1771,6 +1827,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs)
nbd_total_devices++;
return nbd;
+out_err_disk:
+ blk_cleanup_disk(disk);
out_free_idr:
mutex_lock(&nbd_index_mutex);
idr_remove(&nbd_index_idr, index);
@@ -2135,7 +2193,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
mutex_lock(&nbd->config_lock);
config = nbd->config;
if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) ||
- !nbd->task_recv) {
+ !nbd->pid) {
dev_err(nbd_to_dev(nbd),
"not configured, cannot reconfigure\n");
ret = -EINVAL;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index e5cbcf582233..323af5c9c802 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -92,6 +92,10 @@ static int g_submit_queues = 1;
module_param_named(submit_queues, g_submit_queues, int, 0444);
MODULE_PARM_DESC(submit_queues, "Number of submission queues");
+static int g_poll_queues = 1;
+module_param_named(poll_queues, g_poll_queues, int, 0444);
+MODULE_PARM_DESC(poll_queues, "Number of IOPOLL submission queues");
+
static int g_home_node = NUMA_NO_NODE;
module_param_named(home_node, g_home_node, int, 0444);
MODULE_PARM_DESC(home_node, "Home node for the device");
@@ -324,29 +328,69 @@ nullb_device_##NAME##_store(struct config_item *item, const char *page, \
} \
CONFIGFS_ATTR(nullb_device_, NAME);
-static int nullb_apply_submit_queues(struct nullb_device *dev,
- unsigned int submit_queues)
+static int nullb_update_nr_hw_queues(struct nullb_device *dev,
+ unsigned int submit_queues,
+ unsigned int poll_queues)
+
{
- struct nullb *nullb = dev->nullb;
struct blk_mq_tag_set *set;
+ int ret, nr_hw_queues;
- if (!nullb)
+ if (!dev->nullb)
return 0;
/*
+ * Make sure at least one queue exists for each of submit and poll.
+ */
+ if (!submit_queues || !poll_queues)
+ return -EINVAL;
+
+ /*
* Make sure that null_init_hctx() does not access nullb->queues[] past
* the end of that array.
*/
- if (submit_queues > nr_cpu_ids)
+ if (submit_queues > nr_cpu_ids || poll_queues > g_poll_queues)
return -EINVAL;
- set = nullb->tag_set;
- blk_mq_update_nr_hw_queues(set, submit_queues);
- return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM;
+
+ /*
+ * Keep previous and new queue numbers in nullb_device for reference in
+ * the call back function null_map_queues().
+ */
+ dev->prev_submit_queues = dev->submit_queues;
+ dev->prev_poll_queues = dev->poll_queues;
+ dev->submit_queues = submit_queues;
+ dev->poll_queues = poll_queues;
+
+ set = dev->nullb->tag_set;
+ nr_hw_queues = submit_queues + poll_queues;
+ blk_mq_update_nr_hw_queues(set, nr_hw_queues);
+ ret = set->nr_hw_queues == nr_hw_queues ? 0 : -ENOMEM;
+
+ if (ret) {
+ /* on error, revert the queue numbers */
+ dev->submit_queues = dev->prev_submit_queues;
+ dev->poll_queues = dev->prev_poll_queues;
+ }
+
+ return ret;
+}
+
+static int nullb_apply_submit_queues(struct nullb_device *dev,
+ unsigned int submit_queues)
+{
+ return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues);
+}
+
+static int nullb_apply_poll_queues(struct nullb_device *dev,
+ unsigned int poll_queues)
+{
+ return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues);
}
NULLB_DEVICE_ATTR(size, ulong, NULL);
NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL);
NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues);
+NULLB_DEVICE_ATTR(poll_queues, uint, nullb_apply_poll_queues);
NULLB_DEVICE_ATTR(home_node, uint, NULL);
NULLB_DEVICE_ATTR(queue_mode, uint, NULL);
NULLB_DEVICE_ATTR(blocksize, uint, NULL);
@@ -466,6 +510,7 @@ static struct configfs_attribute *nullb_device_attrs[] = {
&nullb_device_attr_size,
&nullb_device_attr_completion_nsec,
&nullb_device_attr_submit_queues,
+ &nullb_device_attr_poll_queues,
&nullb_device_attr_home_node,
&nullb_device_attr_queue_mode,
&nullb_device_attr_blocksize,
@@ -593,6 +638,9 @@ static struct nullb_device *null_alloc_dev(void)
dev->size = g_gb * 1024;
dev->completion_nsec = g_completion_nsec;
dev->submit_queues = g_submit_queues;
+ dev->prev_submit_queues = g_submit_queues;
+ dev->poll_queues = g_poll_queues;
+ dev->prev_poll_queues = g_poll_queues;
dev->home_node = g_home_node;
dev->queue_mode = g_queue_mode;
dev->blocksize = g_bs;
@@ -1454,12 +1502,100 @@ static bool should_requeue_request(struct request *rq)
return false;
}
+static int null_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nullb *nullb = set->driver_data;
+ int i, qoff;
+ unsigned int submit_queues = g_submit_queues;
+ unsigned int poll_queues = g_poll_queues;
+
+ if (nullb) {
+ struct nullb_device *dev = nullb->dev;
+
+ /*
+ * Refer nr_hw_queues of the tag set to check if the expected
+ * number of hardware queues are prepared. If block layer failed
+ * to prepare them, use previous numbers of submit queues and
+ * poll queues to map queues.
+ */
+ if (set->nr_hw_queues ==
+ dev->submit_queues + dev->poll_queues) {
+ submit_queues = dev->submit_queues;
+ poll_queues = dev->poll_queues;
+ } else if (set->nr_hw_queues ==
+ dev->prev_submit_queues + dev->prev_poll_queues) {
+ submit_queues = dev->prev_submit_queues;
+ poll_queues = dev->prev_poll_queues;
+ } else {
+ pr_warn("tag set has unexpected nr_hw_queues: %d\n",
+ set->nr_hw_queues);
+ return -EINVAL;
+ }
+ }
+
+ for (i = 0, qoff = 0; i < set->nr_maps; i++) {
+ struct blk_mq_queue_map *map = &set->map[i];
+
+ switch (i) {
+ case HCTX_TYPE_DEFAULT:
+ map->nr_queues = submit_queues;
+ break;
+ case HCTX_TYPE_READ:
+ map->nr_queues = 0;
+ continue;
+ case HCTX_TYPE_POLL:
+ map->nr_queues = poll_queues;
+ break;
+ }
+ map->queue_offset = qoff;
+ qoff += map->nr_queues;
+ blk_mq_map_queues(map);
+ }
+
+ return 0;
+}
+
+static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
+{
+ struct nullb_queue *nq = hctx->driver_data;
+ LIST_HEAD(list);
+ int nr = 0;
+
+ spin_lock(&nq->poll_lock);
+ list_splice_init(&nq->poll_list, &list);
+ spin_unlock(&nq->poll_lock);
+
+ while (!list_empty(&list)) {
+ struct nullb_cmd *cmd;
+ struct request *req;
+
+ req = list_first_entry(&list, struct request, queuelist);
+ list_del_init(&req->queuelist);
+ cmd = blk_mq_rq_to_pdu(req);
+ cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req),
+ blk_rq_sectors(req));
+ end_cmd(cmd);
+ nr++;
+ }
+
+ return nr;
+}
+
static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
{
+ struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq);
pr_info("rq %p timed out\n", rq);
+ if (hctx->type == HCTX_TYPE_POLL) {
+ struct nullb_queue *nq = hctx->driver_data;
+
+ spin_lock(&nq->poll_lock);
+ list_del_init(&rq->queuelist);
+ spin_unlock(&nq->poll_lock);
+ }
+
/*
* If the device is marked as blocking (i.e. memory backed or zoned
* device), the submission path may be blocked waiting for resources
@@ -1480,10 +1616,11 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
struct nullb_queue *nq = hctx->driver_data;
sector_t nr_sectors = blk_rq_sectors(bd->rq);
sector_t sector = blk_rq_pos(bd->rq);
+ const bool is_poll = hctx->type == HCTX_TYPE_POLL;
might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
- if (nq->dev->irqmode == NULL_IRQ_TIMER) {
+ if (!is_poll && nq->dev->irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cmd->timer.function = null_cmd_timer_expired;
}
@@ -1507,6 +1644,13 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_STS_OK;
}
}
+
+ if (is_poll) {
+ spin_lock(&nq->poll_lock);
+ list_add_tail(&bd->rq->queuelist, &nq->poll_list);
+ spin_unlock(&nq->poll_lock);
+ return BLK_STS_OK;
+ }
if (cmd->fake_timeout)
return BLK_STS_OK;
@@ -1542,6 +1686,8 @@ static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
init_waitqueue_head(&nq->wait);
nq->queue_depth = nullb->queue_depth;
nq->dev = nullb->dev;
+ INIT_LIST_HEAD(&nq->poll_list);
+ spin_lock_init(&nq->poll_lock);
}
static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
@@ -1567,6 +1713,8 @@ static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
.complete = null_complete_rq,
.timeout = null_timeout_rq,
+ .poll = null_poll,
+ .map_queues = null_map_queues,
.init_hctx = null_init_hctx,
.exit_hctx = null_exit_hctx,
};
@@ -1663,13 +1811,17 @@ static int setup_commands(struct nullb_queue *nq)
static int setup_queues(struct nullb *nullb)
{
- nullb->queues = kcalloc(nr_cpu_ids, sizeof(struct nullb_queue),
+ int nqueues = nr_cpu_ids;
+
+ if (g_poll_queues)
+ nqueues += g_poll_queues;
+
+ nullb->queues = kcalloc(nqueues, sizeof(struct nullb_queue),
GFP_KERNEL);
if (!nullb->queues)
return -ENOMEM;
nullb->queue_depth = nullb->dev->hw_queue_depth;
-
return 0;
}
@@ -1721,9 +1873,14 @@ static int null_gendisk_register(struct nullb *nullb)
static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
{
+ int poll_queues;
+
set->ops = &null_mq_ops;
set->nr_hw_queues = nullb ? nullb->dev->submit_queues :
g_submit_queues;
+ poll_queues = nullb ? nullb->dev->poll_queues : g_poll_queues;
+ if (poll_queues)
+ set->nr_hw_queues += poll_queues;
set->queue_depth = nullb ? nullb->dev->hw_queue_depth :
g_hw_queue_depth;
set->numa_node = nullb ? nullb->dev->home_node : g_home_node;
@@ -1733,7 +1890,11 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
set->flags |= BLK_MQ_F_NO_SCHED;
if (g_shared_tag_bitmap)
set->flags |= BLK_MQ_F_TAG_HCTX_SHARED;
- set->driver_data = NULL;
+ set->driver_data = nullb;
+ if (g_poll_queues)
+ set->nr_maps = 3;
+ else
+ set->nr_maps = 1;
if ((nullb && nullb->dev->blocking) || g_blocking)
set->flags |= BLK_MQ_F_BLOCKING;
@@ -1753,6 +1914,13 @@ static int null_validate_conf(struct nullb_device *dev)
dev->submit_queues = nr_cpu_ids;
else if (dev->submit_queues == 0)
dev->submit_queues = 1;
+ dev->prev_submit_queues = dev->submit_queues;
+
+ if (dev->poll_queues > g_poll_queues)
+ dev->poll_queues = g_poll_queues;
+ else if (dev->poll_queues == 0)
+ dev->poll_queues = 1;
+ dev->prev_poll_queues = dev->poll_queues;
dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h
index 64bef125d1df..78eb56b0ca55 100644
--- a/drivers/block/null_blk/null_blk.h
+++ b/drivers/block/null_blk/null_blk.h
@@ -32,6 +32,9 @@ struct nullb_queue {
struct nullb_device *dev;
unsigned int requeue_selection;
+ struct list_head poll_list;
+ spinlock_t poll_lock;
+
struct nullb_cmd *cmds;
};
@@ -83,6 +86,9 @@ struct nullb_device {
unsigned int zone_max_open; /* max number of open zones */
unsigned int zone_max_active; /* max number of active zones */
unsigned int submit_queues; /* number of submission queues */
+ unsigned int prev_submit_queues; /* number of submission queues before change */
+ unsigned int poll_queues; /* number of IOPOLL submission queues */
+ unsigned int prev_poll_queues; /* number of IOPOLL submission queues before change */
unsigned int home_node; /* home node for the device */
unsigned int queue_mode; /* block interface */
unsigned int blocksize; /* block size */
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index f9cdd11f02f5..f6b1d63e96e1 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -183,8 +183,6 @@ static int pcd_audio_ioctl(struct cdrom_device_info *cdi,
static int pcd_packet(struct cdrom_device_info *cdi,
struct packet_command *cgc);
-static int pcd_detect(void);
-static void pcd_probe_capabilities(void);
static void do_pcd_read_drq(void);
static blk_status_t pcd_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd);
@@ -302,53 +300,6 @@ static const struct blk_mq_ops pcd_mq_ops = {
.queue_rq = pcd_queue_rq,
};
-static void pcd_init_units(void)
-{
- struct pcd_unit *cd;
- int unit;
-
- pcd_drive_count = 0;
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- struct gendisk *disk;
-
- if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
- BLK_MQ_F_SHOULD_MERGE))
- continue;
-
- disk = blk_mq_alloc_disk(&cd->tag_set, cd);
- if (IS_ERR(disk)) {
- blk_mq_free_tag_set(&cd->tag_set);
- continue;
- }
-
- INIT_LIST_HEAD(&cd->rq_list);
- blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
- cd->disk = disk;
- cd->pi = &cd->pia;
- cd->present = 0;
- cd->last_sense = 0;
- cd->changed = 1;
- cd->drive = (*drives[unit])[D_SLV];
- if ((*drives[unit])[D_PRT])
- pcd_drive_count++;
-
- cd->name = &cd->info.name[0];
- snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
- cd->info.ops = &pcd_dops;
- cd->info.handle = cd;
- cd->info.speed = 0;
- cd->info.capacity = 1;
- cd->info.mask = 0;
- disk->major = major;
- disk->first_minor = unit;
- disk->minors = 1;
- 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;
- }
-}
-
static int pcd_open(struct cdrom_device_info *cdi, int purpose)
{
struct pcd_unit *cd = cdi->handle;
@@ -630,10 +581,11 @@ static int pcd_drive_status(struct cdrom_device_info *cdi, int slot_nr)
return CDS_DISC_OK;
}
-static int pcd_identify(struct pcd_unit *cd, char *id)
+static int pcd_identify(struct pcd_unit *cd)
{
- int k, s;
char id_cmd[12] = { 0x12, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0 };
+ char id[18];
+ int k, s;
pcd_bufblk = -1;
@@ -661,108 +613,47 @@ static int pcd_identify(struct pcd_unit *cd, char *id)
}
/*
- * returns 0, with id set if drive is detected
- * -1, if drive detection failed
+ * returns 0, with id set if drive is detected, otherwise an error code.
*/
-static int pcd_probe(struct pcd_unit *cd, int ms, char *id)
+static int pcd_probe(struct pcd_unit *cd, int ms)
{
if (ms == -1) {
for (cd->drive = 0; cd->drive <= 1; cd->drive++)
- if (!pcd_reset(cd) && !pcd_identify(cd, id))
+ if (!pcd_reset(cd) && !pcd_identify(cd))
return 0;
} else {
cd->drive = ms;
- if (!pcd_reset(cd) && !pcd_identify(cd, id))
+ if (!pcd_reset(cd) && !pcd_identify(cd))
return 0;
}
- return -1;
+ return -ENODEV;
}
-static void pcd_probe_capabilities(void)
+static int pcd_probe_capabilities(struct pcd_unit *cd)
{
- int unit, r;
- char buffer[32];
char cmd[12] = { 0x5a, 1 << 3, 0x2a, 0, 0, 0, 0, 18, 0, 0, 0, 0 };
- struct pcd_unit *cd;
-
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->present)
- continue;
- r = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
- if (r)
- continue;
- /* we should now have the cap page */
- if ((buffer[11] & 1) == 0)
- cd->info.mask |= CDC_CD_R;
- if ((buffer[11] & 2) == 0)
- cd->info.mask |= CDC_CD_RW;
- if ((buffer[12] & 1) == 0)
- cd->info.mask |= CDC_PLAY_AUDIO;
- if ((buffer[14] & 1) == 0)
- cd->info.mask |= CDC_LOCK;
- if ((buffer[14] & 8) == 0)
- cd->info.mask |= CDC_OPEN_TRAY;
- if ((buffer[14] >> 6) == 0)
- cd->info.mask |= CDC_CLOSE_TRAY;
- }
-}
-
-static int pcd_detect(void)
-{
- char id[18];
- int k, unit;
- struct pcd_unit *cd;
+ char buffer[32];
+ int ret;
- printk("%s: %s version %s, major %d, nice %d\n",
- name, name, PCD_VERSION, major, nice);
+ ret = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities");
+ if (ret)
+ return ret;
+
+ /* we should now have the cap page */
+ if ((buffer[11] & 1) == 0)
+ cd->info.mask |= CDC_CD_R;
+ if ((buffer[11] & 2) == 0)
+ cd->info.mask |= CDC_CD_RW;
+ if ((buffer[12] & 1) == 0)
+ cd->info.mask |= CDC_PLAY_AUDIO;
+ if ((buffer[14] & 1) == 0)
+ cd->info.mask |= CDC_LOCK;
+ if ((buffer[14] & 8) == 0)
+ cd->info.mask |= CDC_OPEN_TRAY;
+ if ((buffer[14] >> 6) == 0)
+ cd->info.mask |= CDC_CLOSE_TRAY;
- par_drv = pi_register_driver(name);
- if (!par_drv) {
- pr_err("failed to register %s driver\n", name);
- return -1;
- }
-
- k = 0;
- if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
- cd = pcd;
- if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1,
- pcd_buffer, PI_PCD, verbose, cd->name)) {
- if (!pcd_probe(cd, -1, id)) {
- cd->present = 1;
- k++;
- } else
- pi_release(cd->pi);
- }
- } else {
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- int *conf = *drives[unit];
- if (!conf[D_PRT])
- continue;
- if (!cd->disk)
- continue;
- if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD],
- conf[D_UNI], conf[D_PRO], conf[D_DLY],
- pcd_buffer, PI_PCD, verbose, cd->name))
- continue;
- if (!pcd_probe(cd, conf[D_SLV], id)) {
- cd->present = 1;
- k++;
- } else
- pi_release(cd->pi);
- }
- }
- if (k)
- return 0;
-
- printk("%s: No CD-ROM drive found\n", name);
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
- continue;
- blk_cleanup_disk(cd->disk);
- blk_mq_free_tag_set(&cd->tag_set);
- }
- pi_unregister_driver(par_drv);
- return -1;
+ return 0;
}
/* I/O request processing */
@@ -999,43 +890,130 @@ static int pcd_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn)
return 0;
}
+static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port,
+ int mode, int unit, int protocol, int delay, int ms)
+{
+ struct gendisk *disk;
+ int ret;
+
+ ret = blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1,
+ BLK_MQ_F_SHOULD_MERGE);
+ if (ret)
+ return ret;
+
+ disk = blk_mq_alloc_disk(&cd->tag_set, cd);
+ if (IS_ERR(disk)) {
+ ret = PTR_ERR(disk);
+ goto out_free_tag_set;
+ }
+
+ INIT_LIST_HEAD(&cd->rq_list);
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
+ cd->disk = disk;
+ cd->pi = &cd->pia;
+ cd->present = 0;
+ cd->last_sense = 0;
+ cd->changed = 1;
+ cd->drive = (*drives[cd - pcd])[D_SLV];
+
+ cd->name = &cd->info.name[0];
+ snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit);
+ cd->info.ops = &pcd_dops;
+ cd->info.handle = cd;
+ cd->info.speed = 0;
+ cd->info.capacity = 1;
+ cd->info.mask = 0;
+ disk->major = major;
+ disk->first_minor = unit;
+ disk->minors = 1;
+ 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;
+
+ if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay,
+ pcd_buffer, PI_PCD, verbose, cd->name)) {
+ ret = -ENODEV;
+ goto out_free_disk;
+ }
+ ret = pcd_probe(cd, ms);
+ if (ret)
+ goto out_pi_release;
+
+ cd->present = 1;
+ pcd_probe_capabilities(cd);
+ ret = register_cdrom(cd->disk, &cd->info);
+ if (ret)
+ goto out_pi_release;
+ ret = add_disk(cd->disk);
+ if (ret)
+ goto out_unreg_cdrom;
+ return 0;
+
+out_unreg_cdrom:
+ unregister_cdrom(&cd->info);
+out_pi_release:
+ pi_release(cd->pi);
+out_free_disk:
+ blk_cleanup_disk(cd->disk);
+out_free_tag_set:
+ blk_mq_free_tag_set(&cd->tag_set);
+ return ret;
+}
+
static int __init pcd_init(void)
{
- struct pcd_unit *cd;
- int unit;
+ int found = 0, unit;
if (disable)
return -EINVAL;
- pcd_init_units();
+ if (register_blkdev(major, name))
+ return -EBUSY;
- if (pcd_detect())
- return -ENODEV;
+ pr_info("%s: %s version %s, major %d, nice %d\n",
+ name, name, PCD_VERSION, major, nice);
- /* get the atapi capabilities page */
- pcd_probe_capabilities();
+ par_drv = pi_register_driver(name);
+ if (!par_drv) {
+ pr_err("failed to register %s driver\n", name);
+ goto out_unregister_blkdev;
+ }
- if (register_blkdev(major, name)) {
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
- continue;
+ for (unit = 0; unit < PCD_UNITS; unit++) {
+ if ((*drives[unit])[D_PRT])
+ pcd_drive_count++;
+ }
+
+ if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
+ if (!pcd_init_unit(pcd, 1, -1, -1, -1, -1, -1, -1))
+ found++;
+ } else {
+ for (unit = 0; unit < PCD_UNITS; unit++) {
+ struct pcd_unit *cd = &pcd[unit];
+ int *conf = *drives[unit];
- blk_cleanup_queue(cd->disk->queue);
- blk_mq_free_tag_set(&cd->tag_set);
- put_disk(cd->disk);
+ if (!conf[D_PRT])
+ continue;
+ if (!pcd_init_unit(cd, 0, conf[D_PRT], conf[D_MOD],
+ conf[D_UNI], conf[D_PRO], conf[D_DLY],
+ conf[D_SLV]))
+ found++;
}
- return -EBUSY;
}
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (cd->present) {
- register_cdrom(cd->disk, &cd->info);
- cd->disk->private_data = cd;
- add_disk(cd->disk);
- }
+ if (!found) {
+ pr_info("%s: No CD-ROM drive found\n", name);
+ goto out_unregister_pi_driver;
}
return 0;
+
+out_unregister_pi_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
+ unregister_blkdev(major, name);
+ return -ENODEV;
}
static void __exit pcd_exit(void)
@@ -1044,20 +1022,18 @@ static void __exit pcd_exit(void)
int unit;
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
- if (!cd->disk)
+ if (!cd->present)
continue;
- if (cd->present) {
- del_gendisk(cd->disk);
- pi_release(cd->pi);
- unregister_cdrom(&cd->info);
- }
- blk_cleanup_queue(cd->disk->queue);
+ unregister_cdrom(&cd->info);
+ del_gendisk(cd->disk);
+ pi_release(cd->pi);
+ blk_cleanup_disk(cd->disk);
+
blk_mq_free_tag_set(&cd->tag_set);
- put_disk(cd->disk);
}
- unregister_blkdev(major, name);
pi_unregister_driver(par_drv);
+ unregister_blkdev(major, name);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 675327df6aff..e59759bcf416 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -875,9 +875,27 @@ static const struct blk_mq_ops pd_mq_ops = {
.queue_rq = pd_queue_rq,
};
-static void pd_probe_drive(struct pd_unit *disk)
+static int pd_probe_drive(struct pd_unit *disk, int autoprobe, int port,
+ int mode, int unit, int protocol, int delay)
{
+ int index = disk - pd;
+ int *parm = *drives[index];
struct gendisk *p;
+ int ret;
+
+ disk->pi = &disk->pia;
+ disk->access = 0;
+ disk->changed = 1;
+ disk->capacity = 0;
+ disk->drive = parm[D_SLV];
+ snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a' + index);
+ disk->alt_geom = parm[D_GEO];
+ disk->standby = parm[D_SBY];
+ INIT_LIST_HEAD(&disk->rq_list);
+
+ if (!pi_init(disk->pi, autoprobe, port, mode, unit, protocol, delay,
+ pd_scratch, PI_PD, verbose, disk->name))
+ return -ENXIO;
memset(&disk->tag_set, 0, sizeof(disk->tag_set));
disk->tag_set.ops = &pd_mq_ops;
@@ -887,14 +905,14 @@ static void pd_probe_drive(struct pd_unit *disk)
disk->tag_set.queue_depth = 2;
disk->tag_set.numa_node = NUMA_NO_NODE;
disk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING;
-
- if (blk_mq_alloc_tag_set(&disk->tag_set))
- return;
+ ret = blk_mq_alloc_tag_set(&disk->tag_set);
+ if (ret)
+ goto pi_release;
p = blk_mq_alloc_disk(&disk->tag_set, disk);
if (IS_ERR(p)) {
- blk_mq_free_tag_set(&disk->tag_set);
- return;
+ ret = PTR_ERR(p);
+ goto free_tag_set;
}
disk->gd = p;
@@ -905,102 +923,88 @@ static void pd_probe_drive(struct pd_unit *disk)
p->minors = 1 << PD_BITS;
p->events = DISK_EVENT_MEDIA_CHANGE;
p->private_data = disk;
-
blk_queue_max_hw_sectors(p->queue, cluster);
blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH);
if (disk->drive == -1) {
- for (disk->drive = 0; disk->drive <= 1; disk->drive++)
- if (pd_special_command(disk, pd_identify) == 0)
- return;
- } else if (pd_special_command(disk, pd_identify) == 0)
- return;
- disk->gd = NULL;
+ for (disk->drive = 0; disk->drive <= 1; disk->drive++) {
+ ret = pd_special_command(disk, pd_identify);
+ if (ret == 0)
+ break;
+ }
+ } else {
+ ret = pd_special_command(disk, pd_identify);
+ }
+ if (ret)
+ goto put_disk;
+ set_capacity(disk->gd, disk->capacity);
+ ret = add_disk(disk->gd);
+ if (ret)
+ goto cleanup_disk;
+ return 0;
+cleanup_disk:
+ blk_cleanup_disk(disk->gd);
+put_disk:
put_disk(p);
+ disk->gd = NULL;
+free_tag_set:
+ blk_mq_free_tag_set(&disk->tag_set);
+pi_release:
+ pi_release(disk->pi);
+ return ret;
}
-static int pd_detect(void)
+static int __init pd_init(void)
{
int found = 0, unit, pd_drive_count = 0;
struct pd_unit *disk;
- for (unit = 0; unit < PD_UNITS; unit++) {
- int *parm = *drives[unit];
- struct pd_unit *disk = pd + unit;
- disk->pi = &disk->pia;
- disk->access = 0;
- disk->changed = 1;
- disk->capacity = 0;
- disk->drive = parm[D_SLV];
- snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a'+unit);
- disk->alt_geom = parm[D_GEO];
- disk->standby = parm[D_SBY];
- if (parm[D_PRT])
- pd_drive_count++;
- INIT_LIST_HEAD(&disk->rq_list);
- }
+ if (disable)
+ return -ENODEV;
+
+ if (register_blkdev(major, name))
+ return -ENODEV;
+
+ printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
+ name, name, PD_VERSION, major, cluster, nice);
par_drv = pi_register_driver(name);
if (!par_drv) {
pr_err("failed to register %s driver\n", name);
- return -1;
+ goto out_unregister_blkdev;
}
- if (pd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
- disk = pd;
- if (pi_init(disk->pi, 1, -1, -1, -1, -1, -1, pd_scratch,
- PI_PD, verbose, disk->name)) {
- pd_probe_drive(disk);
- if (!disk->gd)
- pi_release(disk->pi);
- }
+ for (unit = 0; unit < PD_UNITS; unit++) {
+ int *parm = *drives[unit];
+ if (parm[D_PRT])
+ pd_drive_count++;
+ }
+
+ if (pd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */
+ if (!pd_probe_drive(pd, 1, -1, -1, -1, -1, -1))
+ found++;
} else {
for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) {
int *parm = *drives[unit];
if (!parm[D_PRT])
continue;
- if (pi_init(disk->pi, 0, parm[D_PRT], parm[D_MOD],
- parm[D_UNI], parm[D_PRO], parm[D_DLY],
- pd_scratch, PI_PD, verbose, disk->name)) {
- pd_probe_drive(disk);
- if (!disk->gd)
- pi_release(disk->pi);
- }
- }
- }
- for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) {
- if (disk->gd) {
- set_capacity(disk->gd, disk->capacity);
- add_disk(disk->gd);
- found = 1;
+ if (!pd_probe_drive(disk, 0, parm[D_PRT], parm[D_MOD],
+ parm[D_UNI], parm[D_PRO], parm[D_DLY]))
+ found++;
}
}
if (!found) {
printk("%s: no valid drive found\n", name);
- pi_unregister_driver(par_drv);
+ goto out_pi_unregister_driver;
}
- return found;
-}
-
-static int __init pd_init(void)
-{
- if (disable)
- goto out1;
-
- if (register_blkdev(major, name))
- goto out1;
-
- printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
- name, name, PD_VERSION, major, cluster, nice);
- if (!pd_detect())
- goto out2;
return 0;
-out2:
+out_pi_unregister_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
unregister_blkdev(major, name);
-out1:
return -ENODEV;
}
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index d5b9c88ba76f..bf8d0ef41a0a 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -214,7 +214,6 @@ static int pf_getgeo(struct block_device *bdev, struct hd_geometry *geo);
static void pf_release(struct gendisk *disk, fmode_t mode);
-static int pf_detect(void);
static void do_pf_read(void);
static void do_pf_read_start(void);
static void do_pf_write(void);
@@ -285,45 +284,6 @@ static const struct blk_mq_ops pf_mq_ops = {
.queue_rq = pf_queue_rq,
};
-static void __init pf_init_units(void)
-{
- struct pf_unit *pf;
- int unit;
-
- pf_drive_count = 0;
- for (unit = 0, pf = units; unit < PF_UNITS; unit++, pf++) {
- struct gendisk *disk;
-
- if (blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1,
- BLK_MQ_F_SHOULD_MERGE))
- continue;
-
- disk = blk_mq_alloc_disk(&pf->tag_set, pf);
- if (IS_ERR(disk)) {
- blk_mq_free_tag_set(&pf->tag_set);
- continue;
- }
-
- INIT_LIST_HEAD(&pf->rq_list);
- blk_queue_max_segments(disk->queue, cluster);
- blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
- pf->disk = disk;
- pf->pi = &pf->pia;
- pf->media_status = PF_NM;
- pf->drive = (*drives[unit])[D_SLV];
- pf->lun = (*drives[unit])[D_LUN];
- snprintf(pf->name, PF_NAMELEN, "%s%d", name, unit);
- disk->major = major;
- disk->first_minor = unit;
- disk->minors = 1;
- strcpy(disk->disk_name, pf->name);
- disk->fops = &pf_fops;
- disk->events = DISK_EVENT_MEDIA_CHANGE;
- if (!(*drives[unit])[D_PRT])
- pf_drive_count++;
- }
-}
-
static int pf_open(struct block_device *bdev, fmode_t mode)
{
struct pf_unit *pf = bdev->bd_disk->private_data;
@@ -691,9 +651,9 @@ static int pf_identify(struct pf_unit *pf)
return 0;
}
-/* returns 0, with id set if drive is detected
- -1, if drive detection failed
-*/
+/*
+ * returns 0, with id set if drive is detected, otherwise an error code.
+ */
static int pf_probe(struct pf_unit *pf)
{
if (pf->drive == -1) {
@@ -715,60 +675,7 @@ static int pf_probe(struct pf_unit *pf)
if (!pf_identify(pf))
return 0;
}
- return -1;
-}
-
-static int pf_detect(void)
-{
- struct pf_unit *pf = units;
- int k, unit;
-
- printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
- name, name, PF_VERSION, major, cluster, nice);
-
- par_drv = pi_register_driver(name);
- if (!par_drv) {
- pr_err("failed to register %s driver\n", name);
- return -1;
- }
- k = 0;
- if (pf_drive_count == 0) {
- if (pi_init(pf->pi, 1, -1, -1, -1, -1, -1, pf_scratch, PI_PF,
- verbose, pf->name)) {
- if (!pf_probe(pf) && pf->disk) {
- pf->present = 1;
- k++;
- } else
- pi_release(pf->pi);
- }
-
- } else
- for (unit = 0; unit < PF_UNITS; unit++, pf++) {
- int *conf = *drives[unit];
- if (!conf[D_PRT])
- continue;
- if (pi_init(pf->pi, 0, conf[D_PRT], conf[D_MOD],
- conf[D_UNI], conf[D_PRO], conf[D_DLY],
- pf_scratch, PI_PF, verbose, pf->name)) {
- if (pf->disk && !pf_probe(pf)) {
- pf->present = 1;
- k++;
- } else
- pi_release(pf->pi);
- }
- }
- if (k)
- return 0;
-
- printk("%s: No ATAPI disk detected\n", name);
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
- continue;
- blk_cleanup_disk(pf->disk);
- blk_mq_free_tag_set(&pf->tag_set);
- }
- pi_unregister_driver(par_drv);
- return -1;
+ return -ENODEV;
}
/* The i/o request engine */
@@ -1014,61 +921,134 @@ static void do_pf_write_done(void)
next_request(0);
}
+static int __init pf_init_unit(struct pf_unit *pf, bool autoprobe, int port,
+ int mode, int unit, int protocol, int delay, int ms)
+{
+ struct gendisk *disk;
+ int ret;
+
+ ret = blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1,
+ BLK_MQ_F_SHOULD_MERGE);
+ if (ret)
+ return ret;
+
+ disk = blk_mq_alloc_disk(&pf->tag_set, pf);
+ if (IS_ERR(disk)) {
+ ret = PTR_ERR(disk);
+ goto out_free_tag_set;
+ }
+ disk->major = major;
+ disk->first_minor = pf - units;
+ disk->minors = 1;
+ strcpy(disk->disk_name, pf->name);
+ disk->fops = &pf_fops;
+ disk->events = DISK_EVENT_MEDIA_CHANGE;
+ disk->private_data = pf;
+
+ blk_queue_max_segments(disk->queue, cluster);
+ blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH);
+
+ INIT_LIST_HEAD(&pf->rq_list);
+ pf->disk = disk;
+ pf->pi = &pf->pia;
+ pf->media_status = PF_NM;
+ pf->drive = (*drives[disk->first_minor])[D_SLV];
+ pf->lun = (*drives[disk->first_minor])[D_LUN];
+ snprintf(pf->name, PF_NAMELEN, "%s%d", name, disk->first_minor);
+
+ if (!pi_init(pf->pi, autoprobe, port, mode, unit, protocol, delay,
+ pf_scratch, PI_PF, verbose, pf->name)) {
+ ret = -ENODEV;
+ goto out_free_disk;
+ }
+ ret = pf_probe(pf);
+ if (ret)
+ goto out_pi_release;
+
+ ret = add_disk(disk);
+ if (ret)
+ goto out_pi_release;
+ pf->present = 1;
+ return 0;
+
+out_pi_release:
+ pi_release(pf->pi);
+out_free_disk:
+ blk_cleanup_disk(pf->disk);
+out_free_tag_set:
+ blk_mq_free_tag_set(&pf->tag_set);
+ return ret;
+}
+
static int __init pf_init(void)
{ /* preliminary initialisation */
struct pf_unit *pf;
- int unit;
+ int found = 0, unit;
if (disable)
return -EINVAL;
- pf_init_units();
+ if (register_blkdev(major, name))
+ return -EBUSY;
- if (pf_detect())
- return -ENODEV;
- pf_busy = 0;
+ printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
+ name, name, PF_VERSION, major, cluster, nice);
- if (register_blkdev(major, name)) {
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
- continue;
- blk_cleanup_queue(pf->disk->queue);
- blk_mq_free_tag_set(&pf->tag_set);
- put_disk(pf->disk);
- }
- return -EBUSY;
+ par_drv = pi_register_driver(name);
+ if (!par_drv) {
+ pr_err("failed to register %s driver\n", name);
+ goto out_unregister_blkdev;
}
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- struct gendisk *disk = pf->disk;
+ for (unit = 0; unit < PF_UNITS; unit++) {
+ if (!(*drives[unit])[D_PRT])
+ pf_drive_count++;
+ }
- if (!pf->present)
- continue;
- disk->private_data = pf;
- add_disk(disk);
+ pf = units;
+ if (pf_drive_count == 0) {
+ if (pf_init_unit(pf, 1, -1, -1, -1, -1, -1, verbose))
+ found++;
+ } else {
+ for (unit = 0; unit < PF_UNITS; unit++, pf++) {
+ int *conf = *drives[unit];
+ if (!conf[D_PRT])
+ continue;
+ if (pf_init_unit(pf, 0, conf[D_PRT], conf[D_MOD],
+ conf[D_UNI], conf[D_PRO], conf[D_DLY],
+ verbose))
+ found++;
+ }
+ }
+ if (!found) {
+ printk("%s: No ATAPI disk detected\n", name);
+ goto out_unregister_pi_driver;
}
+ pf_busy = 0;
return 0;
+
+out_unregister_pi_driver:
+ pi_unregister_driver(par_drv);
+out_unregister_blkdev:
+ unregister_blkdev(major, name);
+ return -ENODEV;
}
static void __exit pf_exit(void)
{
struct pf_unit *pf;
int unit;
- unregister_blkdev(major, name);
+
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
- if (!pf->disk)
+ if (!pf->present)
continue;
-
- if (pf->present)
- del_gendisk(pf->disk);
-
- blk_cleanup_queue(pf->disk->queue);
+ del_gendisk(pf->disk);
+ blk_cleanup_disk(pf->disk);
blk_mq_free_tag_set(&pf->tag_set);
- put_disk(pf->disk);
-
- if (pf->present)
- pi_release(pf->pi);
+ pi_release(pf->pi);
}
+
+ unregister_blkdev(major, name);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index cb52cce6fb03..e48d4771d4c1 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2728,7 +2728,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
/* inherit events of the host device */
disk->events = pd->bdev->bd_disk->events;
- add_disk(disk);
+ ret = add_disk(disk);
+ if (ret)
+ goto out_mem2;
pkt_sysfs_dev_new(pd);
pkt_debugfs_dev_new(pd);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index bf60aebd0cfb..953fa134cd3d 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7054,7 +7054,9 @@ static ssize_t do_rbd_add(struct bus_type *bus,
if (rc)
goto err_out_image_lock;
- device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
+ rc = device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL);
+ if (rc)
+ goto err_out_cleanup_disk;
spin_lock(&rbd_dev_list_lock);
list_add_tail(&rbd_dev->node, &rbd_dev_list);
@@ -7068,6 +7070,8 @@ out:
module_put(THIS_MODULE);
return rc;
+err_out_cleanup_disk:
+ rbd_free_disk(rbd_dev);
err_out_image_lock:
rbd_dev_image_unlock(rbd_dev);
rbd_dev_device_release(rbd_dev);
diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c
index 0ec0191d4196..2df0657cdf00 100644
--- a/drivers/block/rnbd/rnbd-clt.c
+++ b/drivers/block/rnbd/rnbd-clt.c
@@ -1384,8 +1384,10 @@ static void setup_request_queue(struct rnbd_clt_dev *dev)
blk_queue_write_cache(dev->queue, dev->wc, dev->fua);
}
-static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
+static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
{
+ int err;
+
dev->gd->major = rnbd_client_major;
dev->gd->first_minor = idx << RNBD_PART_BITS;
dev->gd->minors = 1 << RNBD_PART_BITS;
@@ -1410,7 +1412,11 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx)
if (!dev->rotational)
blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue);
- add_disk(dev->gd);
+ err = add_disk(dev->gd);
+ if (err)
+ blk_cleanup_disk(dev->gd);
+
+ return err;
}
static int rnbd_client_setup_device(struct rnbd_clt_dev *dev)
@@ -1426,8 +1432,7 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev)
rnbd_init_mq_hw_queues(dev);
setup_request_queue(dev);
- rnbd_clt_setup_gen_disk(dev, idx);
- return 0;
+ return rnbd_clt_setup_gen_disk(dev, idx);
}
static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess,
diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c
index 83636714b8d7..8d9d69f5dfbc 100644
--- a/drivers/block/rsxx/core.c
+++ b/drivers/block/rsxx/core.c
@@ -935,7 +935,9 @@ static int rsxx_pci_probe(struct pci_dev *dev,
card->size8 = 0;
}
- rsxx_attach_dev(card);
+ st = rsxx_attach_dev(card);
+ if (st)
+ goto failed_create_dev;
/************* Setup Debugfs *************/
rsxx_debugfs_dev_new(card);
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 268252380e88..dd33f1bdf3b8 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -191,6 +191,8 @@ static bool rsxx_discard_supported(struct rsxx_cardinfo *card)
int rsxx_attach_dev(struct rsxx_cardinfo *card)
{
+ int err = 0;
+
mutex_lock(&card->dev_lock);
/* The block device requires the stripe size from the config. */
@@ -199,13 +201,17 @@ int rsxx_attach_dev(struct rsxx_cardinfo *card)
set_capacity(card->gendisk, card->size8 >> 9);
else
set_capacity(card->gendisk, 0);
- device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL);
- card->bdev_attached = 1;
+ err = device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL);
+ if (err == 0)
+ card->bdev_attached = 1;
}
mutex_unlock(&card->dev_lock);
- return 0;
+ if (err)
+ blk_cleanup_disk(card->gendisk);
+
+ return err;
}
void rsxx_detach_dev(struct rsxx_cardinfo *card)
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index 3911d0833e1b..821594cd1315 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -185,6 +185,7 @@ struct floppy_state {
int track;
int ref_count;
+ bool registered;
struct gendisk *disk;
struct blk_mq_tag_set tag_set;
@@ -772,6 +773,20 @@ static const struct blk_mq_ops swim_mq_ops = {
.queue_rq = swim_queue_rq,
};
+static void swim_cleanup_floppy_disk(struct floppy_state *fs)
+{
+ struct gendisk *disk = fs->disk;
+
+ if (!disk)
+ return;
+
+ if (fs->registered)
+ del_gendisk(fs->disk);
+
+ blk_cleanup_disk(disk);
+ blk_mq_free_tag_set(&fs->tag_set);
+}
+
static int swim_floppy_init(struct swim_priv *swd)
{
int err;
@@ -828,7 +843,10 @@ static int swim_floppy_init(struct swim_priv *swd)
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);
+ err = add_disk(swd->unit[drive].disk);
+ if (err)
+ goto exit_put_disks;
+ swd->unit[drive].registered = true;
}
return 0;
@@ -836,12 +854,7 @@ static int swim_floppy_init(struct swim_priv *swd)
exit_put_disks:
unregister_blkdev(FLOPPY_MAJOR, "fd");
do {
- struct gendisk *disk = swd->unit[drive].disk;
-
- if (!disk)
- continue;
- blk_cleanup_disk(disk);
- blk_mq_free_tag_set(&swd->unit[drive].tag_set);
+ swim_cleanup_floppy_disk(&swd->unit[drive]);
} while (drive--);
return err;
}
@@ -910,12 +923,8 @@ static int swim_remove(struct platform_device *dev)
int drive;
struct resource *res;
- for (drive = 0; drive < swd->floppy_count; drive++) {
- del_gendisk(swd->unit[drive].disk);
- blk_cleanup_queue(swd->unit[drive].disk->queue);
- blk_mq_free_tag_set(&swd->unit[drive].tag_set);
- put_disk(swd->unit[drive].disk);
- }
+ for (drive = 0; drive < swd->floppy_count; drive++)
+ swim_cleanup_floppy_disk(&swd->unit[drive]);
unregister_blkdev(FLOPPY_MAJOR, "fd");
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 965af0a3e95b..4b91c9aa5892 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -27,6 +27,7 @@
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/wait.h>
+#include <linux/major.h>
#include <asm/io.h>
#include <asm/dbdma.h>
#include <asm/prom.h>
@@ -1229,7 +1230,9 @@ static int swim3_attach(struct macio_dev *mdev,
disk->flags |= GENHD_FL_REMOVABLE;
sprintf(disk->disk_name, "fd%d", floppy_count);
set_capacity(disk, 2880);
- add_disk(disk);
+ rc = add_disk(disk);
+ if (rc)
+ goto out_cleanup_disk;
disks[floppy_count++] = disk;
return 0;
diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c
index 420cd952ddc4..d1676fe0da1a 100644
--- a/drivers/block/sx8.c
+++ b/drivers/block/sx8.c
@@ -297,6 +297,7 @@ struct carm_host {
struct work_struct fsm_task;
+ int probe_err;
struct completion probe_comp;
};
@@ -1181,8 +1182,11 @@ static void carm_fsm_task (struct work_struct *work)
struct gendisk *disk = port->disk;
set_capacity(disk, port->capacity);
- add_disk(disk);
- activated++;
+ host->probe_err = add_disk(disk);
+ if (!host->probe_err)
+ activated++;
+ else
+ break;
}
printk(KERN_INFO DRV_NAME "(%s): %d ports activated\n",
@@ -1192,11 +1196,9 @@ static void carm_fsm_task (struct work_struct *work)
reschedule = 1;
break;
}
-
case HST_PROBE_FINISHED:
complete(&host->probe_comp);
break;
-
case HST_ERROR:
/* FIXME: TODO */
break;
@@ -1507,7 +1509,12 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent)
goto err_out_free_irq;
DPRINTK("waiting for probe_comp\n");
+ host->probe_err = -ENODEV;
wait_for_completion(&host->probe_comp);
+ if (host->probe_err) {
+ rc = host->probe_err;
+ goto err_out_free_irq;
+ }
printk(KERN_INFO "%s: pci %s, ports %d, io %llx, irq %u, major %d\n",
host->name, pci_name(pdev), (int) CARM_MAX_PORTS,
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 303caf2d17d0..fd086179f980 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -815,9 +815,17 @@ static int virtblk_probe(struct virtio_device *vdev)
err = virtio_cread_feature(vdev, VIRTIO_BLK_F_BLK_SIZE,
struct virtio_blk_config, blk_size,
&blk_size);
- if (!err)
+ if (!err) {
+ err = blk_validate_block_size(blk_size);
+ if (err) {
+ dev_err(&vdev->dev,
+ "virtio_blk: invalid block size: 0x%x\n",
+ blk_size);
+ goto out_cleanup_disk;
+ }
+
blk_queue_logical_block_size(q, blk_size);
- else
+ } else
blk_size = queue_logical_block_size(q);
/* Use topology information if available */
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index df0deb927760..8e3983e456f3 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -2386,7 +2386,13 @@ static void blkfront_connect(struct blkfront_info *info)
for_each_rinfo(info, rinfo, i)
kick_pending_request_queues(rinfo);
- device_add_disk(&info->xbdev->dev, info->gd, NULL);
+ err = device_add_disk(&info->xbdev->dev, info->gd, NULL);
+ if (err) {
+ blk_cleanup_disk(info->gd);
+ blk_mq_free_tag_set(&info->tag_set);
+ info->rq = NULL;
+ goto fail;
+ }
info->is_ready = 1;
return;
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 8e1fe75af93f..d50cc1fd34d5 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -805,9 +805,14 @@ static int probe_gdrom(struct platform_device *devptr)
err = -ENOMEM;
goto probe_fail_free_irqs;
}
- add_disk(gd.disk);
+ err = add_disk(gd.disk);
+ if (err)
+ goto probe_fail_add_disk;
+
return 0;
+probe_fail_add_disk:
+ kfree(gd.toc);
probe_fail_free_irqs:
free_irq(HW_EVENT_GDROM_DMA, &gd);
free_irq(HW_EVENT_GDROM_CMD, &gd);
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index d6ba644f6b00..4a5516406c22 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -76,7 +76,7 @@ config TCG_TIS_SPI_CR50
config TCG_TIS_SYNQUACER
tristate "TPM Interface Specification 1.2 Interface / TPM 2.0 FIFO Interface (MMIO - SynQuacer)"
- depends on ARCH_SYNQUACER
+ depends on ARCH_SYNQUACER || COMPILE_TEST
select TCG_TIS_CORE
help
If you have a TPM security chip that is compliant with the
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 784b8b3cb903..97e916856cf3 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -455,6 +455,9 @@ static int tpm2_map_response_body(struct tpm_chip *chip, u32 cc, u8 *rsp,
if (be32_to_cpu(data->capability) != TPM2_CAP_HANDLES)
return 0;
+ if (be32_to_cpu(data->count) > (UINT_MAX - TPM_HEADER_SIZE - 9) / 4)
+ return -EFAULT;
+
if (len != TPM_HEADER_SIZE + 9 + 4 * be32_to_cpu(data->count))
return -EFAULT;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 69579efb247b..b2659a4c4016 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -48,6 +48,7 @@ static int wait_for_tpm_stat(struct tpm_chip *chip, u8 mask,
unsigned long timeout, wait_queue_head_t *queue,
bool check_cancel)
{
+ struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
unsigned long stop;
long rc;
u8 status;
@@ -80,8 +81,8 @@ again:
}
} else {
do {
- usleep_range(TPM_TIMEOUT_USECS_MIN,
- TPM_TIMEOUT_USECS_MAX);
+ usleep_range(priv->timeout_min,
+ priv->timeout_max);
status = chip->ops->status(chip);
if ((status & mask) == mask)
return 0;
@@ -945,7 +946,22 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX);
chip->timeout_c = msecs_to_jiffies(TIS_TIMEOUT_C_MAX);
chip->timeout_d = msecs_to_jiffies(TIS_TIMEOUT_D_MAX);
+ priv->timeout_min = TPM_TIMEOUT_USECS_MIN;
+ priv->timeout_max = TPM_TIMEOUT_USECS_MAX;
priv->phy_ops = phy_ops;
+
+ rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor);
+ if (rc < 0)
+ goto out_err;
+
+ priv->manufacturer_id = vendor;
+
+ if (priv->manufacturer_id == TPM_VID_ATML &&
+ !(chip->flags & TPM_CHIP_FLAG_TPM2)) {
+ priv->timeout_min = TIS_TIMEOUT_MIN_ATML;
+ priv->timeout_max = TIS_TIMEOUT_MAX_ATML;
+ }
+
dev_set_drvdata(&chip->dev, priv);
if (is_bsw()) {
@@ -988,12 +1004,6 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
if (rc)
goto out_err;
- rc = tpm_tis_read32(priv, TPM_DID_VID(0), &vendor);
- if (rc < 0)
- goto out_err;
-
- priv->manufacturer_id = vendor;
-
rc = tpm_tis_read8(priv, TPM_RID(0), &rid);
if (rc < 0)
goto out_err;
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index b2a3c6c72882..3be24f221e32 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -54,6 +54,8 @@ enum tis_defaults {
TIS_MEM_LEN = 0x5000,
TIS_SHORT_TIMEOUT = 750, /* ms */
TIS_LONG_TIMEOUT = 2000, /* 2 sec */
+ TIS_TIMEOUT_MIN_ATML = 14700, /* usecs */
+ TIS_TIMEOUT_MAX_ATML = 15000, /* usecs */
};
/* Some timeout values are needed before it is known whether the chip is
@@ -98,6 +100,8 @@ struct tpm_tis_data {
wait_queue_head_t read_queue;
const struct tpm_tis_phy_ops *phy_ops;
unsigned short rng_quality;
+ unsigned int timeout_min; /* usecs */
+ unsigned int timeout_max; /* usecs */
};
struct tpm_tis_phy_ops {
diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c
index 54584b4b00d1..aaa59a00eeae 100644
--- a/drivers/char/tpm/tpm_tis_spi_main.c
+++ b/drivers/char/tpm/tpm_tis_spi_main.c
@@ -267,6 +267,7 @@ static const struct spi_device_id tpm_tis_spi_id[] = {
{ "st33htpm-spi", (unsigned long)tpm_tis_spi_probe },
{ "slb9670", (unsigned long)tpm_tis_spi_probe },
{ "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+ { "tpm_tis-spi", (unsigned long)tpm_tis_spi_probe },
{ "cr50", (unsigned long)cr50_spi_probe },
{}
};
diff --git a/drivers/clk/clk-composite.c b/drivers/clk/clk-composite.c
index 0506046a5f4b..510a9965633b 100644
--- a/drivers/clk/clk-composite.c
+++ b/drivers/clk/clk-composite.c
@@ -58,11 +58,8 @@ static int clk_composite_determine_rate(struct clk_hw *hw,
long rate;
int i;
- if (rate_hw && rate_ops && rate_ops->determine_rate) {
- __clk_hw_set_clk(rate_hw, hw);
- return rate_ops->determine_rate(rate_hw, req);
- } else if (rate_hw && rate_ops && rate_ops->round_rate &&
- mux_hw && mux_ops && mux_ops->set_parent) {
+ if (rate_hw && rate_ops && rate_ops->round_rate &&
+ mux_hw && mux_ops && mux_ops->set_parent) {
req->best_parent_hw = NULL;
if (clk_hw_get_flags(hw) & CLK_SET_RATE_NO_REPARENT) {
@@ -107,6 +104,9 @@ static int clk_composite_determine_rate(struct clk_hw *hw,
req->rate = best_rate;
return 0;
+ } else if (rate_hw && rate_ops && rate_ops->determine_rate) {
+ __clk_hw_set_clk(rate_hw, hw);
+ return rate_ops->determine_rate(rate_hw, req);
} else if (mux_hw && mux_ops && mux_ops->determine_rate) {
__clk_hw_set_clk(mux_hw, hw);
return mux_ops->determine_rate(mux_hw, req);
diff --git a/drivers/gpio/gpio-mlxbf2.c b/drivers/gpio/gpio-mlxbf2.c
index 177d03ef4529..40a052bc6784 100644
--- a/drivers/gpio/gpio-mlxbf2.c
+++ b/drivers/gpio/gpio-mlxbf2.c
@@ -256,6 +256,11 @@ mlxbf2_gpio_probe(struct platform_device *pdev)
NULL,
0);
+ if (ret) {
+ dev_err(dev, "bgpio_init failed\n");
+ return ret;
+ }
+
gc->direction_input = mlxbf2_gpio_direction_input;
gc->direction_output = mlxbf2_gpio_direction_output;
gc->ngpio = npins;
diff --git a/drivers/gpio/gpio-xgs-iproc.c b/drivers/gpio/gpio-xgs-iproc.c
index fa9b4d8c3ff5..43ca52fa6f9a 100644
--- a/drivers/gpio/gpio-xgs-iproc.c
+++ b/drivers/gpio/gpio-xgs-iproc.c
@@ -224,7 +224,7 @@ static int iproc_gpio_probe(struct platform_device *pdev)
}
chip->gc.label = dev_name(dev);
- if (of_property_read_u32(dn, "ngpios", &num_gpios))
+ if (!of_property_read_u32(dn, "ngpios", &num_gpios))
chip->gc.ngpio = num_gpios;
irq = platform_get_irq(pdev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index ff80786e3918..01efda4398e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -1257,7 +1257,7 @@ static int nv_common_early_init(void *handle)
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
if (adev->pdev->device == 0x1681)
- adev->external_rev_id = adev->rev_id + 0x19;
+ adev->external_rev_id = 0x20;
else
adev->external_rev_id = adev->rev_id + 0x01;
break;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 87daa78a32b8..8080bba5b7a7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -263,7 +263,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -487,7 +487,7 @@ static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -639,7 +639,7 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
if (!wr_buf)
return -ENOSPC;
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -914,7 +914,7 @@ static ssize_t dp_dsc_passthrough_set(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
&param, buf,
max_param_num,
&param_nums)) {
@@ -1211,7 +1211,7 @@ static ssize_t trigger_hotplug(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1396,7 +1396,7 @@ static ssize_t dp_dsc_clock_en_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1581,7 +1581,7 @@ static ssize_t dp_dsc_slice_width_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1766,7 +1766,7 @@ static ssize_t dp_dsc_slice_height_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -1944,7 +1944,7 @@ static ssize_t dp_dsc_bits_per_pixel_write(struct file *f, const char __user *bu
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
@@ -2382,7 +2382,7 @@ static ssize_t dp_max_bpc_write(struct file *f, const char __user *buf,
return -ENOSPC;
}
- if (parse_write_buffer_into_params(wr_buf, size,
+ if (parse_write_buffer_into_params(wr_buf, wr_buf_size,
(long *)param, buf,
max_param_num,
&param_nums)) {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index 4a4894e9d9c9..377c4e53a2b3 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -366,32 +366,32 @@ static struct wm_table lpddr5_wm_table = {
.wm_inst = WM_A,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 5.32,
- .sr_enter_plus_exit_time_us = 6.38,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_B,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.82,
- .sr_enter_plus_exit_time_us = 11.196,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_C,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.89,
- .sr_enter_plus_exit_time_us = 11.24,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
{
.wm_inst = WM_D,
.wm_type = WM_TYPE_PSTATE_CHG,
.pstate_latency_us = 11.65333,
- .sr_exit_time_us = 9.748,
- .sr_enter_plus_exit_time_us = 11.102,
+ .sr_exit_time_us = 11.5,
+ .sr_enter_plus_exit_time_us = 14.5,
.valid = true,
},
}
@@ -518,14 +518,21 @@ static unsigned int find_clk_for_voltage(
unsigned int voltage)
{
int i;
+ int max_voltage = 0;
+ int clock = 0;
for (i = 0; i < NUM_SOC_VOLTAGE_LEVELS; i++) {
- if (clock_table->SocVoltage[i] == voltage)
+ if (clock_table->SocVoltage[i] == voltage) {
return clocks[i];
+ } else if (clock_table->SocVoltage[i] >= max_voltage &&
+ clock_table->SocVoltage[i] < voltage) {
+ max_voltage = clock_table->SocVoltage[i];
+ clock = clocks[i];
+ }
}
- ASSERT(0);
- return 0;
+ ASSERT(clock);
+ return clock;
}
void dcn31_clk_mgr_helper_populate_bw_params(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 3f2333ec67e2..3afa1159a5f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -76,10 +76,6 @@ void dcn31_init_hw(struct dc *dc)
if (dc->clk_mgr && dc->clk_mgr->funcs->init_clocks)
dc->clk_mgr->funcs->init_clocks(dc->clk_mgr);
- // Initialize the dccg
- if (res_pool->dccg->funcs->dccg_init)
- res_pool->dccg->funcs->dccg_init(res_pool->dccg);
-
if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
REG_WRITE(REFCLK_CNTL, 0);
@@ -106,6 +102,9 @@ void dcn31_init_hw(struct dc *dc)
hws->funcs.bios_golden_init(dc);
hws->funcs.disable_vga(dc->hwseq);
}
+ // Initialize the dccg
+ if (res_pool->dccg->funcs->dccg_init)
+ res_pool->dccg->funcs->dccg_init(res_pool->dccg);
if (dc->debug.enable_mem_low_power.bits.dmcu) {
// Force ERAM to shutdown if DMCU is not enabled
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index 0006bbac466c..79e92ecca96c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -217,8 +217,8 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
.num_states = 5,
.sr_exit_time_us = 9.0,
.sr_enter_plus_exit_time_us = 11.0,
- .sr_exit_z8_time_us = 402.0,
- .sr_enter_plus_exit_z8_time_us = 520.0,
+ .sr_exit_z8_time_us = 442.0,
+ .sr_enter_plus_exit_z8_time_us = 560.0,
.writeback_latency_us = 12.0,
.dram_channel_width_bytes = 4,
.round_trip_ping_latency_dcfclk_cycles = 106,
@@ -928,7 +928,7 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_dcc = DCC_ENABLE,
.vsr_support = true,
.performance_trace = false,
- .max_downscale_src_width = 3840,/*upto 4K*/
+ .max_downscale_src_width = 4096,/*upto true 4K*/
.disable_pplib_wm_range = false,
.scl_reset_length10 = true,
.sanity_checks = false,
@@ -1590,6 +1590,13 @@ static int dcn31_populate_dml_pipes_from_context(
pipe = &res_ctx->pipe_ctx[i];
timing = &pipe->stream->timing;
+ /*
+ * Immediate flip can be set dynamically after enabling the plane.
+ * We need to require support for immediate flip or underflow can be
+ * intermittently experienced depending on peak b/w requirements.
+ */
+ pipes[pipe_cnt].pipe.src.immediate_flip = true;
+
pipes[pipe_cnt].pipe.src.unbounded_req_mode = false;
pipes[pipe_cnt].pipe.src.gpuvm = true;
pipes[pipe_cnt].pipe.src.dcc_fraction_of_zs_req_luma = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
index ce55c9caf9a2..d58925cff420 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn31/display_mode_vba_31.c
@@ -5398,9 +5398,9 @@ void dml31_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
v->MaximumReadBandwidthWithPrefetch =
v->MaximumReadBandwidthWithPrefetch
- + dml_max4(
- v->VActivePixelBandwidth[i][j][k],
- v->VActiveCursorBandwidth[i][j][k]
+ + dml_max3(
+ v->VActivePixelBandwidth[i][j][k]
+ + v->VActiveCursorBandwidth[i][j][k]
+ v->NoOfDPP[i][j][k]
* (v->meta_row_bandwidth[i][j][k]
+ v->dpte_row_bandwidth[i][j][k]),
diff --git a/drivers/gpu/drm/amd/display/include/dal_asic_id.h b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
index 5adc471bef57..3d2f0817e40a 100644
--- a/drivers/gpu/drm/amd/display/include/dal_asic_id.h
+++ b/drivers/gpu/drm/amd/display/include/dal_asic_id.h
@@ -227,7 +227,7 @@ enum {
#define FAMILY_YELLOW_CARP 146
#define YELLOW_CARP_A0 0x01
-#define YELLOW_CARP_B0 0x1A
+#define YELLOW_CARP_B0 0x20
#define YELLOW_CARP_UNKNOWN 0xFF
#ifndef ASICREV_IS_YELLOW_CARP
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
index e9bd84ec027d..be61975f1470 100644
--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -105,6 +105,7 @@ static enum mod_hdcp_status remove_display_from_topology_v3(
dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+ mutex_unlock(&psp->dtm_context.mutex);
if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
status = remove_display_from_topology_v2(hdcp, index);
@@ -115,8 +116,6 @@ static enum mod_hdcp_status remove_display_from_topology_v3(
HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index);
}
- mutex_unlock(&psp->dtm_context.mutex);
-
return status;
}
@@ -205,6 +204,7 @@ static enum mod_hdcp_status add_display_to_topology_v3(
dtm_cmd->dtm_in_message.topology_update_v3.link_hdcp_cap = link->hdcp_supported_informational;
psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+ mutex_unlock(&psp->dtm_context.mutex);
if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS) {
status = add_display_to_topology_v2(hdcp, display);
@@ -214,8 +214,6 @@ static enum mod_hdcp_status add_display_to_topology_v3(
HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index);
}
- mutex_unlock(&psp->dtm_context.mutex);
-
return status;
}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 6bfaefa01818..1e30eaeb0e1b 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -1300,18 +1300,6 @@ static enum drm_mode_status ast_mode_valid(struct drm_connector *connector,
return flags;
}
-static enum drm_connector_status ast_connector_detect(struct drm_connector
- *connector, bool force)
-{
- int r;
-
- r = ast_get_modes(connector);
- if (r <= 0)
- return connector_status_disconnected;
-
- return connector_status_connected;
-}
-
static void ast_connector_destroy(struct drm_connector *connector)
{
struct ast_connector *ast_connector = to_ast_connector(connector);
@@ -1327,7 +1315,6 @@ static const struct drm_connector_helper_funcs ast_connector_helper_funcs = {
static const struct drm_connector_funcs ast_connector_funcs = {
.reset = drm_atomic_helper_connector_reset,
- .detect = ast_connector_detect,
.fill_modes = drm_helper_probe_single_connector_modes,
.destroy = ast_connector_destroy,
.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -1355,8 +1342,7 @@ static int ast_connector_init(struct drm_device *dev)
connector->interlace_allowed = 0;
connector->doublescan_allowed = 0;
- connector->polled = DRM_CONNECTOR_POLL_CONNECT |
- DRM_CONNECTOR_POLL_DISCONNECT;
+ connector->polled = DRM_CONNECTOR_POLL_CONNECT;
drm_connector_attach_encoder(connector, encoder);
@@ -1425,8 +1411,6 @@ int ast_mode_config_init(struct ast_private *ast)
drm_mode_config_reset(dev);
- drm_kms_helper_poll_init(dev);
-
return 0;
}
diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
index f6bdec7fa925..e1b2ce4921ae 100644
--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
+++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
@@ -134,6 +134,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "T103HAF"),
},
.driver_data = (void *)&lcd800x1280_rightside_up,
+ }, { /* AYA NEO 2021 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "AYADEVICE"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "AYA NEO 2021"),
+ },
+ .driver_data = (void *)&lcd800x1280_rightside_up,
}, { /* GPD MicroPC (generic strings, also match on bios date) */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Default string"),
@@ -185,6 +191,12 @@ static const struct dmi_system_id orientation_data[] = {
DMI_EXACT_MATCH(DMI_BOARD_NAME, "Default string"),
},
.driver_data = (void *)&gpd_win2,
+ }, { /* GPD Win 3 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "GPD"),
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "G1618-03")
+ },
+ .driver_data = (void *)&lcd720x1280_rightside_up,
}, { /* I.T.Works TW891 */
.matches = {
DMI_EXACT_MATCH(DMI_SYS_VENDOR, "To be filled by O.E.M."),
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index abe3d61b6243..5cf152be4487 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1916,6 +1916,9 @@ void intel_dp_sync_state(struct intel_encoder *encoder,
{
struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+ if (!crtc_state)
+ return;
+
/*
* Don't clobber DPCD if it's been already read out during output
* setup (eDP) or detect.
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 1257f4f11e66..438bbc7b8147 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -64,7 +64,7 @@ intel_timeline_pin_map(struct intel_timeline *timeline)
timeline->hwsp_map = vaddr;
timeline->hwsp_seqno = memset(vaddr + ofs, 0, TIMELINE_SEQNO_BYTES);
- clflush(vaddr + ofs);
+ drm_clflush_virt_range(vaddr + ofs, TIMELINE_SEQNO_BYTES);
return 0;
}
@@ -225,7 +225,7 @@ void intel_timeline_reset_seqno(const struct intel_timeline *tl)
memset(hwsp_seqno + 1, 0, TIMELINE_SEQNO_BYTES - sizeof(*hwsp_seqno));
WRITE_ONCE(*hwsp_seqno, tl->seqno);
- clflush(hwsp_seqno);
+ drm_clflush_virt_range(hwsp_seqno, TIMELINE_SEQNO_BYTES);
}
void intel_timeline_enter(struct intel_timeline *tl)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4037030f0984..9023d4ecf3b3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -11048,12 +11048,6 @@ enum skl_power_gate {
#define DC_STATE_DEBUG_MASK_CORES (1 << 0)
#define DC_STATE_DEBUG_MASK_MEMORY_UP (1 << 1)
-#define BXT_P_CR_MC_BIOS_REQ_0_0_0 _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x7114)
-#define BXT_REQ_DATA_MASK 0x3F
-#define BXT_DRAM_CHANNEL_ACTIVE_SHIFT 12
-#define BXT_DRAM_CHANNEL_ACTIVE_MASK (0xF << 12)
-#define BXT_MEMORY_FREQ_MULTIPLIER_HZ 133333333
-
#define BXT_D_CR_DRP0_DUNIT8 0x1000
#define BXT_D_CR_DRP0_DUNIT9 0x1200
#define BXT_D_CR_DRP0_DUNIT_START 8
@@ -11084,9 +11078,7 @@ enum skl_power_gate {
#define BXT_DRAM_TYPE_LPDDR4 (0x2 << 22)
#define BXT_DRAM_TYPE_DDR4 (0x4 << 22)
-#define SKL_MEMORY_FREQ_MULTIPLIER_HZ 266666666
#define SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5E04)
-#define SKL_REQ_DATA_MASK (0xF << 0)
#define DG1_GEAR_TYPE REG_BIT(16)
#define SKL_MAD_INTER_CHANNEL_0_0_0_MCHBAR_MCMAIN _MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5000)
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 806ad688274b..63fec1c3c132 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -794,7 +794,6 @@ DECLARE_EVENT_CLASS(i915_request,
TP_STRUCT__entry(
__field(u32, dev)
__field(u64, ctx)
- __field(u32, guc_id)
__field(u16, class)
__field(u16, instance)
__field(u32, seqno)
@@ -805,16 +804,14 @@ DECLARE_EVENT_CLASS(i915_request,
__entry->dev = rq->engine->i915->drm.primary->index;
__entry->class = rq->engine->uabi_class;
__entry->instance = rq->engine->uabi_instance;
- __entry->guc_id = rq->context->guc_id;
__entry->ctx = rq->fence.context;
__entry->seqno = rq->fence.seqno;
__entry->tail = rq->tail;
),
- TP_printk("dev=%u, engine=%u:%u, guc_id=%u, ctx=%llu, seqno=%u, tail=%u",
+ TP_printk("dev=%u, engine=%u:%u, ctx=%llu, seqno=%u, tail=%u",
__entry->dev, __entry->class, __entry->instance,
- __entry->guc_id, __entry->ctx, __entry->seqno,
- __entry->tail)
+ __entry->ctx, __entry->seqno, __entry->tail)
);
DEFINE_EVENT(i915_request, i915_request_add,
diff --git a/drivers/gpu/drm/i915/intel_dram.c b/drivers/gpu/drm/i915/intel_dram.c
index 91866520c173..7acce64b0941 100644
--- a/drivers/gpu/drm/i915/intel_dram.c
+++ b/drivers/gpu/drm/i915/intel_dram.c
@@ -244,7 +244,6 @@ static int
skl_get_dram_info(struct drm_i915_private *i915)
{
struct dram_info *dram_info = &i915->dram_info;
- u32 mem_freq_khz, val;
int ret;
dram_info->type = skl_get_dram_type(i915);
@@ -255,17 +254,6 @@ skl_get_dram_info(struct drm_i915_private *i915)
if (ret)
return ret;
- val = intel_uncore_read(&i915->uncore,
- SKL_MC_BIOS_DATA_0_0_0_MCHBAR_PCU);
- mem_freq_khz = DIV_ROUND_UP((val & SKL_REQ_DATA_MASK) *
- SKL_MEMORY_FREQ_MULTIPLIER_HZ, 1000);
-
- if (dram_info->num_channels * mem_freq_khz == 0) {
- drm_info(&i915->drm,
- "Couldn't get system memory bandwidth\n");
- return -EINVAL;
- }
-
return 0;
}
@@ -350,24 +338,10 @@ static void bxt_get_dimm_info(struct dram_dimm_info *dimm, u32 val)
static int bxt_get_dram_info(struct drm_i915_private *i915)
{
struct dram_info *dram_info = &i915->dram_info;
- u32 dram_channels;
- u32 mem_freq_khz, val;
- u8 num_active_channels, valid_ranks = 0;
+ u32 val;
+ u8 valid_ranks = 0;
int i;
- val = intel_uncore_read(&i915->uncore, BXT_P_CR_MC_BIOS_REQ_0_0_0);
- mem_freq_khz = DIV_ROUND_UP((val & BXT_REQ_DATA_MASK) *
- BXT_MEMORY_FREQ_MULTIPLIER_HZ, 1000);
-
- dram_channels = val & BXT_DRAM_CHANNEL_ACTIVE_MASK;
- num_active_channels = hweight32(dram_channels);
-
- if (mem_freq_khz * num_active_channels == 0) {
- drm_info(&i915->drm,
- "Couldn't get system memory bandwidth\n");
- return -EINVAL;
- }
-
/*
* Now read each DUNIT8/9/10/11 to check the rank of each dimms.
*/
diff --git a/drivers/gpu/drm/kmb/kmb_crtc.c b/drivers/gpu/drm/kmb/kmb_crtc.c
index 44327bc629ca..06613ffeaaf8 100644
--- a/drivers/gpu/drm/kmb/kmb_crtc.c
+++ b/drivers/gpu/drm/kmb/kmb_crtc.c
@@ -66,7 +66,8 @@ static const struct drm_crtc_funcs kmb_crtc_funcs = {
.disable_vblank = kmb_crtc_disable_vblank,
};
-static void kmb_crtc_set_mode(struct drm_crtc *crtc)
+static void kmb_crtc_set_mode(struct drm_crtc *crtc,
+ struct drm_atomic_state *old_state)
{
struct drm_device *dev = crtc->dev;
struct drm_display_mode *m = &crtc->state->adjusted_mode;
@@ -75,7 +76,7 @@ static void kmb_crtc_set_mode(struct drm_crtc *crtc)
unsigned int val = 0;
/* Initialize mipi */
- kmb_dsi_mode_set(kmb->kmb_dsi, m, kmb->sys_clk_mhz);
+ kmb_dsi_mode_set(kmb->kmb_dsi, m, kmb->sys_clk_mhz, old_state);
drm_info(dev,
"vfp= %d vbp= %d vsync_len=%d hfp=%d hbp=%d hsync_len=%d\n",
m->crtc_vsync_start - m->crtc_vdisplay,
@@ -138,7 +139,7 @@ static void kmb_crtc_atomic_enable(struct drm_crtc *crtc,
struct kmb_drm_private *kmb = crtc_to_kmb_priv(crtc);
clk_prepare_enable(kmb->kmb_clk.clk_lcd);
- kmb_crtc_set_mode(crtc);
+ kmb_crtc_set_mode(crtc, state);
drm_crtc_vblank_on(crtc);
}
@@ -185,11 +186,45 @@ static void kmb_crtc_atomic_flush(struct drm_crtc *crtc,
spin_unlock_irq(&crtc->dev->event_lock);
}
+static enum drm_mode_status
+ kmb_crtc_mode_valid(struct drm_crtc *crtc,
+ const struct drm_display_mode *mode)
+{
+ int refresh;
+ struct drm_device *dev = crtc->dev;
+ int vfp = mode->vsync_start - mode->vdisplay;
+
+ if (mode->vdisplay < KMB_CRTC_MAX_HEIGHT) {
+ drm_dbg(dev, "height = %d less than %d",
+ mode->vdisplay, KMB_CRTC_MAX_HEIGHT);
+ return MODE_BAD_VVALUE;
+ }
+ if (mode->hdisplay < KMB_CRTC_MAX_WIDTH) {
+ drm_dbg(dev, "width = %d less than %d",
+ mode->hdisplay, KMB_CRTC_MAX_WIDTH);
+ return MODE_BAD_HVALUE;
+ }
+ refresh = drm_mode_vrefresh(mode);
+ if (refresh < KMB_MIN_VREFRESH || refresh > KMB_MAX_VREFRESH) {
+ drm_dbg(dev, "refresh = %d less than %d or greater than %d",
+ refresh, KMB_MIN_VREFRESH, KMB_MAX_VREFRESH);
+ return MODE_BAD;
+ }
+
+ if (vfp < KMB_CRTC_MIN_VFP) {
+ drm_dbg(dev, "vfp = %d less than %d", vfp, KMB_CRTC_MIN_VFP);
+ return MODE_BAD;
+ }
+
+ return MODE_OK;
+}
+
static const struct drm_crtc_helper_funcs kmb_crtc_helper_funcs = {
.atomic_begin = kmb_crtc_atomic_begin,
.atomic_enable = kmb_crtc_atomic_enable,
.atomic_disable = kmb_crtc_atomic_disable,
.atomic_flush = kmb_crtc_atomic_flush,
+ .mode_valid = kmb_crtc_mode_valid,
};
int kmb_setup_crtc(struct drm_device *drm)
diff --git a/drivers/gpu/drm/kmb/kmb_drv.c b/drivers/gpu/drm/kmb/kmb_drv.c
index 12ce669650cc..961ac6fb5fcf 100644
--- a/drivers/gpu/drm/kmb/kmb_drv.c
+++ b/drivers/gpu/drm/kmb/kmb_drv.c
@@ -380,7 +380,7 @@ static irqreturn_t handle_lcd_irq(struct drm_device *dev)
if (val & LAYER3_DMA_FIFO_UNDERFLOW)
drm_dbg(&kmb->drm,
"LAYER3:GL1 DMA UNDERFLOW val = 0x%lx", val);
- if (val & LAYER3_DMA_FIFO_UNDERFLOW)
+ if (val & LAYER3_DMA_FIFO_OVERFLOW)
drm_dbg(&kmb->drm,
"LAYER3:GL1 DMA OVERFLOW val = 0x%lx", val);
}
diff --git a/drivers/gpu/drm/kmb/kmb_drv.h b/drivers/gpu/drm/kmb/kmb_drv.h
index 69a62e2d03ff..bf085e95b28f 100644
--- a/drivers/gpu/drm/kmb/kmb_drv.h
+++ b/drivers/gpu/drm/kmb/kmb_drv.h
@@ -20,11 +20,18 @@
#define DRIVER_MAJOR 1
#define DRIVER_MINOR 1
+/* Platform definitions */
+#define KMB_CRTC_MIN_VFP 4
+#define KMB_CRTC_MAX_WIDTH 1920 /* max width in pixels */
+#define KMB_CRTC_MAX_HEIGHT 1080 /* max height in pixels */
+#define KMB_CRTC_MIN_WIDTH 1920
+#define KMB_CRTC_MIN_HEIGHT 1080
#define KMB_FB_MAX_WIDTH 1920
#define KMB_FB_MAX_HEIGHT 1080
#define KMB_FB_MIN_WIDTH 1
#define KMB_FB_MIN_HEIGHT 1
-
+#define KMB_MIN_VREFRESH 59 /*vertical refresh in Hz */
+#define KMB_MAX_VREFRESH 60 /*vertical refresh in Hz */
#define KMB_LCD_DEFAULT_CLK 200000000
#define KMB_SYS_CLK_MHZ 500
@@ -50,6 +57,7 @@ struct kmb_drm_private {
spinlock_t irq_lock;
int irq_lcd;
int sys_clk_mhz;
+ struct disp_cfg init_disp_cfg[KMB_MAX_PLANES];
struct layer_status plane_status[KMB_MAX_PLANES];
int kmb_under_flow;
int kmb_flush_done;
diff --git a/drivers/gpu/drm/kmb/kmb_dsi.c b/drivers/gpu/drm/kmb/kmb_dsi.c
index 1793cd31b117..f6071882054c 100644
--- a/drivers/gpu/drm/kmb/kmb_dsi.c
+++ b/drivers/gpu/drm/kmb/kmb_dsi.c
@@ -482,6 +482,10 @@ static u32 mipi_tx_fg_section_cfg(struct kmb_dsi *kmb_dsi,
return 0;
}
+#define CLK_DIFF_LOW 50
+#define CLK_DIFF_HI 60
+#define SYSCLK_500 500
+
static void mipi_tx_fg_cfg_regs(struct kmb_dsi *kmb_dsi, u8 frame_gen,
struct mipi_tx_frame_timing_cfg *fg_cfg)
{
@@ -492,7 +496,12 @@ static void mipi_tx_fg_cfg_regs(struct kmb_dsi *kmb_dsi, u8 frame_gen,
/* 500 Mhz system clock minus 50 to account for the difference in
* MIPI clock speed in RTL tests
*/
- sysclk = kmb_dsi->sys_clk_mhz - 50;
+ if (kmb_dsi->sys_clk_mhz == SYSCLK_500) {
+ sysclk = kmb_dsi->sys_clk_mhz - CLK_DIFF_LOW;
+ } else {
+ /* 700 Mhz clk*/
+ sysclk = kmb_dsi->sys_clk_mhz - CLK_DIFF_HI;
+ }
/* PPL-Pixel Packing Layer, LLP-Low Level Protocol
* Frame genartor timing parameters are clocked on the system clock,
@@ -1322,7 +1331,8 @@ static u32 mipi_tx_init_dphy(struct kmb_dsi *kmb_dsi,
return 0;
}
-static void connect_lcd_to_mipi(struct kmb_dsi *kmb_dsi)
+static void connect_lcd_to_mipi(struct kmb_dsi *kmb_dsi,
+ struct drm_atomic_state *old_state)
{
struct regmap *msscam;
@@ -1331,7 +1341,7 @@ static void connect_lcd_to_mipi(struct kmb_dsi *kmb_dsi)
dev_dbg(kmb_dsi->dev, "failed to get msscam syscon");
return;
}
-
+ drm_atomic_bridge_chain_enable(adv_bridge, old_state);
/* DISABLE MIPI->CIF CONNECTION */
regmap_write(msscam, MSS_MIPI_CIF_CFG, 0);
@@ -1342,7 +1352,7 @@ static void connect_lcd_to_mipi(struct kmb_dsi *kmb_dsi)
}
int kmb_dsi_mode_set(struct kmb_dsi *kmb_dsi, struct drm_display_mode *mode,
- int sys_clk_mhz)
+ int sys_clk_mhz, struct drm_atomic_state *old_state)
{
u64 data_rate;
@@ -1384,18 +1394,13 @@ int kmb_dsi_mode_set(struct kmb_dsi *kmb_dsi, struct drm_display_mode *mode,
mipi_tx_init_cfg.lane_rate_mbps = data_rate;
}
- kmb_write_mipi(kmb_dsi, DPHY_ENABLE, 0);
- kmb_write_mipi(kmb_dsi, DPHY_INIT_CTRL0, 0);
- kmb_write_mipi(kmb_dsi, DPHY_INIT_CTRL1, 0);
- kmb_write_mipi(kmb_dsi, DPHY_INIT_CTRL2, 0);
-
/* Initialize mipi controller */
mipi_tx_init_cntrl(kmb_dsi, &mipi_tx_init_cfg);
/* Dphy initialization */
mipi_tx_init_dphy(kmb_dsi, &mipi_tx_init_cfg);
- connect_lcd_to_mipi(kmb_dsi);
+ connect_lcd_to_mipi(kmb_dsi, old_state);
dev_info(kmb_dsi->dev, "mipi hw initialized");
return 0;
diff --git a/drivers/gpu/drm/kmb/kmb_dsi.h b/drivers/gpu/drm/kmb/kmb_dsi.h
index 66b7c500d9bc..09dc88743d77 100644
--- a/drivers/gpu/drm/kmb/kmb_dsi.h
+++ b/drivers/gpu/drm/kmb/kmb_dsi.h
@@ -380,7 +380,7 @@ int kmb_dsi_host_bridge_init(struct device *dev);
struct kmb_dsi *kmb_dsi_init(struct platform_device *pdev);
void kmb_dsi_host_unregister(struct kmb_dsi *kmb_dsi);
int kmb_dsi_mode_set(struct kmb_dsi *kmb_dsi, struct drm_display_mode *mode,
- int sys_clk_mhz);
+ int sys_clk_mhz, struct drm_atomic_state *old_state);
int kmb_dsi_map_mmio(struct kmb_dsi *kmb_dsi);
int kmb_dsi_clk_init(struct kmb_dsi *kmb_dsi);
int kmb_dsi_encoder_init(struct drm_device *dev, struct kmb_dsi *kmb_dsi);
diff --git a/drivers/gpu/drm/kmb/kmb_plane.c b/drivers/gpu/drm/kmb/kmb_plane.c
index 06b0c42c9e91..00404ba4126d 100644
--- a/drivers/gpu/drm/kmb/kmb_plane.c
+++ b/drivers/gpu/drm/kmb/kmb_plane.c
@@ -67,8 +67,21 @@ static const u32 kmb_formats_v[] = {
static unsigned int check_pixel_format(struct drm_plane *plane, u32 format)
{
+ struct kmb_drm_private *kmb;
+ struct kmb_plane *kmb_plane = to_kmb_plane(plane);
int i;
+ int plane_id = kmb_plane->id;
+ struct disp_cfg init_disp_cfg;
+ kmb = to_kmb(plane->dev);
+ init_disp_cfg = kmb->init_disp_cfg[plane_id];
+ /* Due to HW limitations, changing pixel format after initial
+ * plane configuration is not supported.
+ */
+ if (init_disp_cfg.format && init_disp_cfg.format != format) {
+ drm_dbg(&kmb->drm, "Cannot change format after initial plane configuration");
+ return -EINVAL;
+ }
for (i = 0; i < plane->format_count; i++) {
if (plane->format_types[i] == format)
return 0;
@@ -81,11 +94,17 @@ static int kmb_plane_atomic_check(struct drm_plane *plane,
{
struct drm_plane_state *new_plane_state = drm_atomic_get_new_plane_state(state,
plane);
+ struct kmb_drm_private *kmb;
+ struct kmb_plane *kmb_plane = to_kmb_plane(plane);
+ int plane_id = kmb_plane->id;
+ struct disp_cfg init_disp_cfg;
struct drm_framebuffer *fb;
int ret;
struct drm_crtc_state *crtc_state;
bool can_position;
+ kmb = to_kmb(plane->dev);
+ init_disp_cfg = kmb->init_disp_cfg[plane_id];
fb = new_plane_state->fb;
if (!fb || !new_plane_state->crtc)
return 0;
@@ -99,6 +118,16 @@ static int kmb_plane_atomic_check(struct drm_plane *plane,
new_plane_state->crtc_w < KMB_FB_MIN_WIDTH ||
new_plane_state->crtc_h < KMB_FB_MIN_HEIGHT)
return -EINVAL;
+
+ /* Due to HW limitations, changing plane height or width after
+ * initial plane configuration is not supported.
+ */
+ if ((init_disp_cfg.width && init_disp_cfg.height) &&
+ (init_disp_cfg.width != fb->width ||
+ init_disp_cfg.height != fb->height)) {
+ drm_dbg(&kmb->drm, "Cannot change plane height or width after initial configuration");
+ return -EINVAL;
+ }
can_position = (plane->type == DRM_PLANE_TYPE_OVERLAY);
crtc_state =
drm_atomic_get_existing_crtc_state(state,
@@ -335,6 +364,7 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
unsigned char plane_id;
int num_planes;
static dma_addr_t addr[MAX_SUB_PLANES];
+ struct disp_cfg *init_disp_cfg;
if (!plane || !new_plane_state || !old_plane_state)
return;
@@ -357,7 +387,8 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
}
spin_unlock_irq(&kmb->irq_lock);
- src_w = (new_plane_state->src_w >> 16);
+ init_disp_cfg = &kmb->init_disp_cfg[plane_id];
+ src_w = new_plane_state->src_w >> 16;
src_h = new_plane_state->src_h >> 16;
crtc_x = new_plane_state->crtc_x;
crtc_y = new_plane_state->crtc_y;
@@ -500,6 +531,16 @@ static void kmb_plane_atomic_update(struct drm_plane *plane,
/* Enable DMA */
kmb_write_lcd(kmb, LCD_LAYERn_DMA_CFG(plane_id), dma_cfg);
+
+ /* Save initial display config */
+ if (!init_disp_cfg->width ||
+ !init_disp_cfg->height ||
+ !init_disp_cfg->format) {
+ init_disp_cfg->width = width;
+ init_disp_cfg->height = height;
+ init_disp_cfg->format = fb->format->format;
+ }
+
drm_dbg(&kmb->drm, "dma_cfg=0x%x LCD_DMA_CFG=0x%x\n", dma_cfg,
kmb_read_lcd(kmb, LCD_LAYERn_DMA_CFG(plane_id)));
diff --git a/drivers/gpu/drm/kmb/kmb_plane.h b/drivers/gpu/drm/kmb/kmb_plane.h
index 6e8d22cf8819..b51144044fe8 100644
--- a/drivers/gpu/drm/kmb/kmb_plane.h
+++ b/drivers/gpu/drm/kmb/kmb_plane.h
@@ -63,6 +63,12 @@ struct layer_status {
u32 ctrl;
};
+struct disp_cfg {
+ unsigned int width;
+ unsigned int height;
+ unsigned int format;
+};
+
struct kmb_plane *kmb_plane_init(struct drm_device *drm);
void kmb_plane_destroy(struct drm_plane *plane);
#endif /* __KMB_PLANE_H__ */
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 33da25b81615..267a880811d6 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -1838,6 +1838,13 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev)
adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev)))
adreno_gpu->base.hw_apriv = true;
+ /*
+ * For now only clamp to idle freq for devices where this is known not
+ * to cause power supply issues:
+ */
+ if (info && (info->revn == 618))
+ gpu->clamp_to_idle = true;
+
a6xx_llc_slices_init(pdev, a6xx_gpu);
ret = a6xx_set_supported_hw(&pdev->dev, config->rev);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 030f82f149c2..ee25d556c8a1 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -203,6 +203,10 @@ struct msm_gpu {
uint32_t suspend_count;
struct msm_gpu_state *crashstate;
+
+ /* Enable clamping to idle freq when inactive: */
+ bool clamp_to_idle;
+
/* True if the hardware supports expanded apriv (a650 and newer) */
bool hw_apriv;
diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
index 84e98c07c900..20006d060b5b 100644
--- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c
+++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c
@@ -200,7 +200,8 @@ void msm_devfreq_idle(struct msm_gpu *gpu)
idle_freq = get_freq(gpu);
- msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0);
+ if (gpu->clamp_to_idle)
+ msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0);
df->idle_time = ktime_get();
df->idle_freq = idle_freq;
diff --git a/drivers/gpu/drm/mxsfb/mxsfb_drv.c b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
index ec0432fe1bdf..86d78634a979 100644
--- a/drivers/gpu/drm/mxsfb/mxsfb_drv.c
+++ b/drivers/gpu/drm/mxsfb/mxsfb_drv.c
@@ -173,7 +173,11 @@ static void mxsfb_irq_disable(struct drm_device *drm)
struct mxsfb_drm_private *mxsfb = drm->dev_private;
mxsfb_enable_axi_clk(mxsfb);
- mxsfb->crtc.funcs->disable_vblank(&mxsfb->crtc);
+
+ /* Disable and clear VBLANK IRQ */
+ writel(CTRL1_CUR_FRAME_DONE_IRQ_EN, mxsfb->base + LCDC_CTRL1 + REG_CLR);
+ writel(CTRL1_CUR_FRAME_DONE_IRQ, mxsfb->base + LCDC_CTRL1 + REG_CLR);
+
mxsfb_disable_axi_clk(mxsfb);
}
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index 0145129d7c66..534dd7414d42 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -590,14 +590,14 @@ static const struct drm_display_mode k101_im2byl02_default_mode = {
.clock = 69700,
.hdisplay = 800,
- .hsync_start = 800 + 6,
- .hsync_end = 800 + 6 + 15,
- .htotal = 800 + 6 + 15 + 16,
+ .hsync_start = 800 + 52,
+ .hsync_end = 800 + 52 + 8,
+ .htotal = 800 + 52 + 8 + 48,
.vdisplay = 1280,
- .vsync_start = 1280 + 8,
- .vsync_end = 1280 + 8 + 48,
- .vtotal = 1280 + 8 + 48 + 52,
+ .vsync_start = 1280 + 16,
+ .vsync_end = 1280 + 16 + 6,
+ .vtotal = 1280 + 16 + 6 + 15,
.width_mm = 135,
.height_mm = 217,
diff --git a/drivers/gpu/drm/selftests/test-drm_damage_helper.c b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
index 1c19a5d3eefb..8d8d8e214c28 100644
--- a/drivers/gpu/drm/selftests/test-drm_damage_helper.c
+++ b/drivers/gpu/drm/selftests/test-drm_damage_helper.c
@@ -30,6 +30,7 @@ static void mock_setup(struct drm_plane_state *state)
mock_device.driver = &mock_driver;
mock_device.mode_config.prop_fb_damage_clips = &mock_prop;
mock_plane.dev = &mock_device;
+ mock_obj_props.count = 0;
mock_plane.base.properties = &mock_obj_props;
mock_prop.base.id = 1; /* 0 is an invalid id */
mock_prop.dev = &mock_device;
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 1c5ffe2935af..abf2d7a4fdf1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -190,6 +190,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
struct ttm_transfer_obj *fbo;
fbo = container_of(bo, struct ttm_transfer_obj, base);
+ dma_resv_fini(&fbo->base.base._resv);
ttm_bo_put(fbo->bo);
kfree(fbo);
}
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 42f3d9d123a1..d030577ad6a2 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -13,6 +13,7 @@
#define _HYPERV_VMBUS_H
#include <linux/list.h>
+#include <linux/bitops.h>
#include <asm/sync_bitops.h>
#include <asm/hyperv-tlfs.h>
#include <linux/atomic.h>
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index a20b8108e160..c00f8e28aab7 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -706,8 +706,9 @@ static void ib_nl_set_path_rec_attrs(struct sk_buff *skb,
/* Construct the family header first */
header = skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
- memcpy(header->device_name, dev_name(&query->port->agent->device->dev),
- LS_DEVICE_NAME_MAX);
+ strscpy_pad(header->device_name,
+ dev_name(&query->port->agent->device->dev),
+ LS_DEVICE_NAME_MAX);
header->port_num = query->port->port_num;
if ((comp_mask & IB_SA_PATH_REC_REVERSIBLE) &&
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 489b436f19bb..3d42bd2b36bd 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -878,6 +878,7 @@ void sc_disable(struct send_context *sc)
{
u64 reg;
struct pio_buf *pbuf;
+ LIST_HEAD(wake_list);
if (!sc)
return;
@@ -912,19 +913,21 @@ void sc_disable(struct send_context *sc)
spin_unlock(&sc->release_lock);
write_seqlock(&sc->waitlock);
- while (!list_empty(&sc->piowait)) {
+ if (!list_empty(&sc->piowait))
+ list_move(&sc->piowait, &wake_list);
+ write_sequnlock(&sc->waitlock);
+ while (!list_empty(&wake_list)) {
struct iowait *wait;
struct rvt_qp *qp;
struct hfi1_qp_priv *priv;
- wait = list_first_entry(&sc->piowait, struct iowait, list);
+ wait = list_first_entry(&wake_list, struct iowait, list);
qp = iowait_to_qp(wait);
priv = qp->priv;
list_del_init(&priv->s_iowait.list);
priv->s_iowait.lock = NULL;
hfi1_qp_wakeup(qp, RVT_S_WAIT_PIO | HFI1_S_WAIT_PIO_DRAIN);
}
- write_sequnlock(&sc->waitlock);
spin_unlock_irq(&sc->alloc_lock);
}
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index 5fb92de1f015..9b544a3b1288 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -1092,12 +1092,12 @@ irdma_uk_cq_poll_cmpl(struct irdma_cq_uk *cq, struct irdma_cq_poll_info *info)
if (cq->avoid_mem_cflct) {
ext_cqe = (__le64 *)((u8 *)cqe + 32);
get_64bit_val(ext_cqe, 24, &qword7);
- polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+ polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
} else {
peek_head = (cq->cq_ring.head + 1) % cq->cq_ring.size;
ext_cqe = cq->cq_base[peek_head].buf;
get_64bit_val(ext_cqe, 24, &qword7);
- polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword3);
+ polarity = (u8)FIELD_GET(IRDMA_CQ_VALID, qword7);
if (!peek_head)
polarity ^= 1;
}
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 7110ebf834f9..102dc9342f2a 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -3399,9 +3399,13 @@ static void irdma_process_cqe(struct ib_wc *entry,
}
if (cq_poll_info->ud_vlan_valid) {
- entry->vlan_id = cq_poll_info->ud_vlan & VLAN_VID_MASK;
- entry->wc_flags |= IB_WC_WITH_VLAN;
+ u16 vlan = cq_poll_info->ud_vlan & VLAN_VID_MASK;
+
entry->sl = cq_poll_info->ud_vlan >> VLAN_PRIO_SHIFT;
+ if (vlan) {
+ entry->vlan_id = vlan;
+ entry->wc_flags |= IB_WC_WITH_VLAN;
+ }
} else {
entry->sl = 0;
}
diff --git a/drivers/infiniband/hw/irdma/ws.c b/drivers/infiniband/hw/irdma/ws.c
index b68c575eb78e..b0d6ee0739f5 100644
--- a/drivers/infiniband/hw/irdma/ws.c
+++ b/drivers/infiniband/hw/irdma/ws.c
@@ -330,8 +330,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
tc_node->enable = true;
ret = irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_MODIFY_NODE);
- if (ret)
+ if (ret) {
+ vsi->unregister_qset(vsi, tc_node);
goto reg_err;
+ }
}
ibdev_dbg(to_ibdev(vsi->dev),
"WS: Using node %d which represents VSI %d TC %d\n",
@@ -350,6 +352,10 @@ enum irdma_status_code irdma_ws_add(struct irdma_sc_vsi *vsi, u8 user_pri)
}
goto exit;
+reg_err:
+ irdma_ws_cqp_cmd(vsi, tc_node, IRDMA_OP_WS_DELETE_NODE);
+ list_del(&tc_node->siblings);
+ irdma_free_node(vsi, tc_node);
leaf_add_err:
if (list_empty(&vsi_node->child_list_head)) {
if (irdma_ws_cqp_cmd(vsi, vsi_node, IRDMA_OP_WS_DELETE_NODE))
@@ -369,11 +375,6 @@ vsi_add_err:
exit:
mutex_unlock(&vsi->dev->ws_mutex);
return ret;
-
-reg_err:
- mutex_unlock(&vsi->dev->ws_mutex);
- irdma_ws_remove(vsi, user_pri);
- return ret;
}
/**
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3be36ebbf67a..22e2f4d79743 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1339,7 +1339,6 @@ static struct mlx5_ib_mr *reg_create(struct ib_pd *pd, struct ib_umem *umem,
goto err_2;
}
mr->mmkey.type = MLX5_MKEY_MR;
- mr->desc_size = sizeof(struct mlx5_mtt);
mr->umem = umem;
set_mr_fields(dev, mr, umem->length, access_flags);
kvfree(in);
@@ -1533,6 +1532,7 @@ static struct ib_mr *create_user_odp_mr(struct ib_pd *pd, u64 start, u64 length,
ib_umem_release(&odp->umem);
return ERR_CAST(mr);
}
+ xa_init(&mr->implicit_children);
odp->private = mr;
err = mlx5r_store_odp_mkey(dev, &mr->mmkey);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index b2fca110346c..e5abbcfc1d57 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4458,6 +4458,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
MLX5_SET(dctc, dctc, mtu, attr->path_mtu);
MLX5_SET(dctc, dctc, my_addr_index, attr->ah_attr.grh.sgid_index);
MLX5_SET(dctc, dctc, hop_limit, attr->ah_attr.grh.hop_limit);
+ if (attr->ah_attr.type == RDMA_AH_ATTR_TYPE_ROCE)
+ MLX5_SET(dctc, dctc, eth_prio, attr->ah_attr.sl & 0x7);
err = mlx5_core_create_dct(dev, &qp->dct.mdct, qp->dct.in,
MLX5_ST_SZ_BYTES(create_dct_in), out,
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index 3cb4febaad0f..8def88cfa300 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -455,6 +455,7 @@ struct qedr_qp {
/* synchronization objects used with iwarp ep */
struct kref refcnt;
struct completion iwarp_cm_comp;
+ struct completion qp_rel_comp;
unsigned long iwarp_cm_flags; /* enum iwarp_cm_flags */
};
diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
index 1715fbe0719d..a51fc6854984 100644
--- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c
@@ -83,7 +83,7 @@ static void qedr_iw_free_qp(struct kref *ref)
{
struct qedr_qp *qp = container_of(ref, struct qedr_qp, refcnt);
- kfree(qp);
+ complete(&qp->qp_rel_comp);
}
static void
diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index 3fbf172dbbef..dcb3653db72d 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -1357,6 +1357,7 @@ static void qedr_set_common_qp_params(struct qedr_dev *dev,
if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
kref_init(&qp->refcnt);
init_completion(&qp->iwarp_cm_comp);
+ init_completion(&qp->qp_rel_comp);
}
qp->pd = pd;
@@ -2857,8 +2858,10 @@ int qedr_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
qedr_free_qp_resources(dev, qp, udata);
- if (rdma_protocol_iwarp(&dev->ibdev, 1))
+ if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
qedr_iw_qp_rem_ref(&qp->ibqp);
+ wait_for_completion(&qp->qp_rel_comp);
+ }
return 0;
}
diff --git a/drivers/infiniband/hw/qib/qib_user_sdma.c b/drivers/infiniband/hw/qib/qib_user_sdma.c
index a67599b5a550..ac11943a5ddb 100644
--- a/drivers/infiniband/hw/qib/qib_user_sdma.c
+++ b/drivers/infiniband/hw/qib/qib_user_sdma.c
@@ -602,7 +602,7 @@ done:
/*
* How many pages in this iovec element?
*/
-static int qib_user_sdma_num_pages(const struct iovec *iov)
+static size_t qib_user_sdma_num_pages(const struct iovec *iov)
{
const unsigned long addr = (unsigned long) iov->iov_base;
const unsigned long len = iov->iov_len;
@@ -658,7 +658,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
struct qib_user_sdma_queue *pq,
struct qib_user_sdma_pkt *pkt,
- unsigned long addr, int tlen, int npages)
+ unsigned long addr, int tlen, size_t npages)
{
struct page *pages[8];
int i, j;
@@ -722,7 +722,7 @@ static int qib_user_sdma_pin_pkt(const struct qib_devdata *dd,
unsigned long idx;
for (idx = 0; idx < niov; idx++) {
- const int npages = qib_user_sdma_num_pages(iov + idx);
+ const size_t npages = qib_user_sdma_num_pages(iov + idx);
const unsigned long addr = (unsigned long) iov[idx].iov_base;
ret = qib_user_sdma_pin_pages(dd, pq, pkt, addr,
@@ -824,8 +824,8 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
unsigned pktnw;
unsigned pktnwc;
int nfrags = 0;
- int npages = 0;
- int bytes_togo = 0;
+ size_t npages = 0;
+ size_t bytes_togo = 0;
int tiddma = 0;
int cfur;
@@ -885,7 +885,11 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
npages += qib_user_sdma_num_pages(&iov[idx]);
- bytes_togo += slen;
+ if (check_add_overflow(bytes_togo, slen, &bytes_togo) ||
+ bytes_togo > type_max(typeof(pkt->bytes_togo))) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
pktnwc += slen >> 2;
idx++;
nfrags++;
@@ -904,8 +908,7 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
}
if (frag_size) {
- int tidsmsize, n;
- size_t pktsize;
+ size_t tidsmsize, n, pktsize, sz, addrlimit;
n = npages*((2*PAGE_SIZE/frag_size)+1);
pktsize = struct_size(pkt, addr, n);
@@ -923,14 +926,24 @@ static int qib_user_sdma_queue_pkts(const struct qib_devdata *dd,
else
tidsmsize = 0;
- pkt = kmalloc(pktsize+tidsmsize, GFP_KERNEL);
+ if (check_add_overflow(pktsize, tidsmsize, &sz)) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
+ pkt = kmalloc(sz, GFP_KERNEL);
if (!pkt) {
ret = -ENOMEM;
goto free_pbc;
}
pkt->largepkt = 1;
pkt->frag_size = frag_size;
- pkt->addrlimit = n + ARRAY_SIZE(pkt->addr);
+ if (check_add_overflow(n, ARRAY_SIZE(pkt->addr),
+ &addrlimit) ||
+ addrlimit > type_max(typeof(pkt->addrlimit))) {
+ ret = -EINVAL;
+ goto free_pbc;
+ }
+ pkt->addrlimit = addrlimit;
if (tiddma) {
char *tidsm = (char *)pkt + pktsize;
diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c
index 49bdd78ac664..3305f2744bfa 100644
--- a/drivers/infiniband/sw/rdmavt/qp.c
+++ b/drivers/infiniband/sw/rdmavt/qp.c
@@ -1223,7 +1223,7 @@ int rvt_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
spin_lock(&rdi->n_qps_lock);
if (rdi->n_qps_allocated == rdi->dparms.props.max_qp) {
spin_unlock(&rdi->n_qps_lock);
- ret = ENOMEM;
+ ret = -ENOMEM;
goto bail_ip;
}
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index e501cb03f211..bd087cca1c1d 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1994,14 +1994,14 @@ setup_hw(struct hfc_pci *hc)
pci_set_master(hc->pdev);
if (!hc->irq) {
printk(KERN_WARNING "HFC-PCI: No IRQ for PCI card found\n");
- return 1;
+ return -EINVAL;
}
hc->hw.pci_io =
(char __iomem *)(unsigned long)hc->pdev->resource[1].start;
if (!hc->hw.pci_io) {
printk(KERN_WARNING "HFC-PCI: No IO-Mem for PCI card found\n");
- return 1;
+ return -ENOMEM;
}
/* Allocate memory for FIFOS */
/* the memory needs to be on a 32k boundary within the first 4G */
@@ -2012,7 +2012,7 @@ setup_hw(struct hfc_pci *hc)
if (!buffer) {
printk(KERN_WARNING
"HFC-PCI: Error allocating memory for FIFO!\n");
- return 1;
+ return -ENOMEM;
}
hc->hw.fifos = buffer;
pci_write_config_dword(hc->pdev, 0x80, hc->hw.dmahandle);
@@ -2022,7 +2022,7 @@ setup_hw(struct hfc_pci *hc)
"HFC-PCI: Error in ioremap for PCI!\n");
dma_free_coherent(&hc->pdev->dev, 0x8000, hc->hw.fifos,
hc->hw.dmahandle);
- return 1;
+ return -ENOMEM;
}
printk(KERN_INFO
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 5fc989a6d452..9ed9c955add7 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -178,7 +178,6 @@
#define pr_fmt(fmt) "bcache: %s() " fmt, __func__
-#include <linux/bcache.h>
#include <linux/bio.h>
#include <linux/kobject.h>
#include <linux/list.h>
@@ -190,6 +189,7 @@
#include <linux/workqueue.h>
#include <linux/kthread.h>
+#include "bcache_ondisk.h"
#include "bset.h"
#include "util.h"
#include "closure.h"
@@ -395,8 +395,6 @@ struct cached_dev {
atomic_t io_errors;
unsigned int error_limit;
unsigned int offline_seconds;
-
- char backing_dev_name[BDEVNAME_SIZE];
};
enum alloc_reserve {
@@ -470,8 +468,6 @@ struct cache {
atomic_long_t meta_sectors_written;
atomic_long_t btree_sectors_written;
atomic_long_t sectors_written;
-
- char cache_dev_name[BDEVNAME_SIZE];
};
struct gc_stat {
diff --git a/include/uapi/linux/bcache.h b/drivers/md/bcache/bcache_ondisk.h
index cf7399f03b71..97413586195b 100644
--- a/include/uapi/linux/bcache.h
+++ b/drivers/md/bcache/bcache_ondisk.h
@@ -43,9 +43,9 @@ static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \
#define KEY_MAX_U64S 8
KEY_FIELD(KEY_PTRS, high, 60, 3)
-KEY_FIELD(HEADER_SIZE, high, 58, 2)
+KEY_FIELD(__PAD0, high, 58, 2)
KEY_FIELD(KEY_CSUM, high, 56, 2)
-KEY_FIELD(KEY_PINNED, high, 55, 1)
+KEY_FIELD(__PAD1, high, 55, 1)
KEY_FIELD(KEY_DIRTY, high, 36, 1)
KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS)
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index a50dcfda656f..d795c84246b0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -2,10 +2,10 @@
#ifndef _BCACHE_BSET_H
#define _BCACHE_BSET_H
-#include <linux/bcache.h>
#include <linux/kernel.h>
#include <linux/types.h>
+#include "bcache_ondisk.h"
#include "util.h" /* for time_stats */
/*
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 0595559de174..93b67b8d31c3 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -141,7 +141,7 @@ static uint64_t btree_csum_set(struct btree *b, struct bset *i)
uint64_t crc = b->key.ptr[0];
void *data = (void *) i + 8, *end = bset_bkey_last(i);
- crc = bch_crc64_update(crc, data, end - data);
+ crc = crc64_be(crc, data, end - data);
return crc ^ 0xffffffffffffffffULL;
}
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 116edda845c3..6230dfdd9286 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -127,21 +127,20 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
citer.bi_size = UINT_MAX;
bio_for_each_segment(bv, bio, iter) {
- void *p1 = kmap_atomic(bv.bv_page);
+ void *p1 = bvec_kmap_local(&bv);
void *p2;
cbv = bio_iter_iovec(check, citer);
- p2 = page_address(cbv.bv_page);
+ p2 = bvec_kmap_local(&cbv);
- cache_set_err_on(memcmp(p1 + bv.bv_offset,
- p2 + bv.bv_offset,
- bv.bv_len),
+ cache_set_err_on(memcmp(p1, p2, bv.bv_len),
dc->disk.c,
- "verify failed at dev %s sector %llu",
- dc->backing_dev_name,
+ "verify failed at dev %pg sector %llu",
+ dc->bdev,
(uint64_t) bio->bi_iter.bi_sector);
- kunmap_atomic(p1);
+ kunmap_local(p2);
+ kunmap_local(p1);
bio_advance_iter(check, &citer, bv.bv_len);
}
diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c
index 6d2b7b84a7b7..634922c5601d 100644
--- a/drivers/md/bcache/features.c
+++ b/drivers/md/bcache/features.c
@@ -6,7 +6,7 @@
* Copyright 2020 Coly Li <colyli@suse.de>
*
*/
-#include <linux/bcache.h>
+#include "bcache_ondisk.h"
#include "bcache.h"
#include "features.h"
diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h
index d1c8fd3977fc..09161b89c63e 100644
--- a/drivers/md/bcache/features.h
+++ b/drivers/md/bcache/features.h
@@ -2,10 +2,11 @@
#ifndef _BCACHE_FEATURES_H
#define _BCACHE_FEATURES_H
-#include <linux/bcache.h>
#include <linux/kernel.h>
#include <linux/types.h>
+#include "bcache_ondisk.h"
+
#define BCH_FEATURE_COMPAT 0
#define BCH_FEATURE_RO_COMPAT 1
#define BCH_FEATURE_INCOMPAT 2
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index e4388fe3ab7e..9c6f9ec55b72 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -65,15 +65,15 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio)
* we shouldn't count failed REQ_RAHEAD bio to dc->io_errors.
*/
if (bio->bi_opf & REQ_RAHEAD) {
- pr_warn_ratelimited("%s: Read-ahead I/O failed on backing device, ignore\n",
- dc->backing_dev_name);
+ pr_warn_ratelimited("%pg: Read-ahead I/O failed on backing device, ignore\n",
+ dc->bdev);
return;
}
errors = atomic_add_return(1, &dc->io_errors);
if (errors < dc->error_limit)
- pr_err("%s: IO error on backing device, unrecoverable\n",
- dc->backing_dev_name);
+ pr_err("%pg: IO error on backing device, unrecoverable\n",
+ dc->bdev);
else
bch_cached_dev_error(dc);
}
@@ -123,13 +123,13 @@ void bch_count_io_errors(struct cache *ca,
errors >>= IO_ERROR_SHIFT;
if (errors < ca->set->error_limit)
- pr_err("%s: IO error on %s%s\n",
- ca->cache_dev_name, m,
+ pr_err("%pg: IO error on %s%s\n",
+ ca->bdev, m,
is_read ? ", recovering." : ".");
else
bch_cache_set_error(ca->set,
- "%s: too many IO errors %s\n",
- ca->cache_dev_name, m);
+ "%pg: too many IO errors %s\n",
+ ca->bdev, m);
}
}
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 23b28edae90f..d15aae6c51c1 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -46,7 +46,7 @@ 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);
+ csum = crc64_be(csum, d, bv.bv_len);
kunmap(bv.bv_page);
}
@@ -651,8 +651,8 @@ static void backing_request_endio(struct bio *bio)
*/
if (unlikely(s->iop.writeback &&
bio->bi_opf & REQ_PREFLUSH)) {
- pr_err("Can't flush %s: returned bi_status %i\n",
- dc->backing_dev_name, bio->bi_status);
+ pr_err("Can't flush %pg: returned bi_status %i\n",
+ dc->bdev, bio->bi_status);
} else {
/* set to orig_bio->bi_status in bio_complete() */
s->iop.status = bio->bi_status;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 4f89985abe4b..4a9a65dff95e 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1026,8 +1026,8 @@ static int cached_dev_status_update(void *arg)
dc->offline_seconds = 0;
if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) {
- pr_err("%s: device offline for %d seconds\n",
- dc->backing_dev_name,
+ pr_err("%pg: device offline for %d seconds\n",
+ dc->bdev,
BACKING_DEV_OFFLINE_TIMEOUT);
pr_err("%s: disable I/O request due to backing device offline\n",
dc->disk.name);
@@ -1058,15 +1058,13 @@ int bch_cached_dev_run(struct cached_dev *dc)
};
if (dc->io_disable) {
- pr_err("I/O disabled on cached dev %s\n",
- dc->backing_dev_name);
+ pr_err("I/O disabled on cached dev %pg\n", dc->bdev);
ret = -EIO;
goto out;
}
if (atomic_xchg(&dc->running, 1)) {
- pr_info("cached dev %s is running already\n",
- dc->backing_dev_name);
+ pr_info("cached dev %pg is running already\n", dc->bdev);
ret = -EBUSY;
goto out;
}
@@ -1082,7 +1080,9 @@ int bch_cached_dev_run(struct cached_dev *dc)
closure_sync(&cl);
}
- add_disk(d->disk);
+ ret = add_disk(d->disk);
+ if (ret)
+ goto out;
bd_link_disk_holder(dc->bdev, dc->disk.disk);
/*
* won't show up in the uevent file, use udevadm monitor -e instead
@@ -1154,16 +1154,16 @@ static void cached_dev_detach_finish(struct work_struct *w)
mutex_lock(&bch_register_lock);
- calc_cached_dev_sectors(dc->disk.c);
bcache_device_detach(&dc->disk);
list_move(&dc->list, &uncached_devices);
+ calc_cached_dev_sectors(dc->disk.c);
clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags);
clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags);
mutex_unlock(&bch_register_lock);
- pr_info("Caching disabled for %s\n", dc->backing_dev_name);
+ pr_info("Caching disabled for %pg\n", dc->bdev);
/* Drop ref we took in cached_dev_detach() */
closure_put(&dc->disk.cl);
@@ -1203,29 +1203,27 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
return -ENOENT;
if (dc->disk.c) {
- pr_err("Can't attach %s: already attached\n",
- dc->backing_dev_name);
+ pr_err("Can't attach %pg: already attached\n", dc->bdev);
return -EINVAL;
}
if (test_bit(CACHE_SET_STOPPING, &c->flags)) {
- pr_err("Can't attach %s: shutting down\n",
- dc->backing_dev_name);
+ pr_err("Can't attach %pg: shutting down\n", dc->bdev);
return -EINVAL;
}
if (dc->sb.block_size < c->cache->sb.block_size) {
/* Will die */
- pr_err("Couldn't attach %s: block size less than set's block size\n",
- dc->backing_dev_name);
+ pr_err("Couldn't attach %pg: block size less than set's block size\n",
+ dc->bdev);
return -EINVAL;
}
/* Check whether already attached */
list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) {
if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) {
- pr_err("Tried to attach %s but duplicate UUID already attached\n",
- dc->backing_dev_name);
+ pr_err("Tried to attach %pg but duplicate UUID already attached\n",
+ dc->bdev);
return -EINVAL;
}
@@ -1243,15 +1241,13 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
if (!u) {
if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) {
- pr_err("Couldn't find uuid for %s in set\n",
- dc->backing_dev_name);
+ pr_err("Couldn't find uuid for %pg in set\n", dc->bdev);
return -ENOENT;
}
u = uuid_find_empty(c);
if (!u) {
- pr_err("Not caching %s, no room for UUID\n",
- dc->backing_dev_name);
+ pr_err("Not caching %pg, no room for UUID\n", dc->bdev);
return -EINVAL;
}
}
@@ -1319,8 +1315,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
*/
kthread_stop(dc->writeback_thread);
cancel_writeback_rate_update_dwork(dc);
- pr_err("Couldn't run cached device %s\n",
- dc->backing_dev_name);
+ pr_err("Couldn't run cached device %pg\n", dc->bdev);
return ret;
}
@@ -1336,8 +1331,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
/* Allow the writeback thread to proceed */
up_write(&dc->writeback_lock);
- pr_info("Caching %s as %s on set %pU\n",
- dc->backing_dev_name,
+ pr_info("Caching %pg as %s on set %pU\n",
+ dc->bdev,
dc->disk.disk->disk_name,
dc->disk.c->set_uuid);
return 0;
@@ -1461,7 +1456,6 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
struct cache_set *c;
int ret = -ENOMEM;
- bdevname(bdev, dc->backing_dev_name);
memcpy(&dc->sb, sb, sizeof(struct cache_sb));
dc->bdev = bdev;
dc->bdev->bd_holder = dc;
@@ -1476,7 +1470,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj))
goto err;
- pr_info("registered backing device %s\n", dc->backing_dev_name);
+ pr_info("registered backing device %pg\n", dc->bdev);
list_add(&dc->list, &uncached_devices);
/* attach to a matched cache set if it exists */
@@ -1493,7 +1487,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
return 0;
err:
- pr_notice("error %s: %s\n", dc->backing_dev_name, err);
+ pr_notice("error %pg: %s\n", dc->bdev, err);
bcache_device_stop(&dc->disk);
return ret;
}
@@ -1534,10 +1528,11 @@ static void flash_dev_flush(struct closure *cl)
static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
{
+ int err = -ENOMEM;
struct bcache_device *d = kzalloc(sizeof(struct bcache_device),
GFP_KERNEL);
if (!d)
- return -ENOMEM;
+ goto err_ret;
closure_init(&d->cl, NULL);
set_closure_fn(&d->cl, flash_dev_flush, system_wq);
@@ -1551,9 +1546,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
bcache_device_attach(d, c, u - c->uuids);
bch_sectors_dirty_init(d);
bch_flash_dev_request_init(d);
- add_disk(d->disk);
+ err = add_disk(d->disk);
+ if (err)
+ goto err;
- if (kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache"))
+ err = kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache");
+ if (err)
goto err;
bcache_device_link(d, c, "volume");
@@ -1567,7 +1565,8 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u)
return 0;
err:
kobject_put(&d->kobj);
- return -ENOMEM;
+err_ret:
+ return err;
}
static int flash_devs_run(struct cache_set *c)
@@ -1621,8 +1620,8 @@ bool bch_cached_dev_error(struct cached_dev *dc)
/* make others know io_disable is true earlier */
smp_mb();
- pr_err("stop %s: too many IO errors on backing device %s\n",
- dc->disk.disk->disk_name, dc->backing_dev_name);
+ pr_err("stop %s: too many IO errors on backing device %pg\n",
+ dc->disk.disk->disk_name, dc->bdev);
bcache_device_stop(&dc->disk);
return true;
@@ -2338,7 +2337,7 @@ err_btree_alloc:
err_free:
module_put(THIS_MODULE);
if (err)
- pr_notice("error %s: %s\n", ca->cache_dev_name, err);
+ pr_notice("error %pg: %s\n", ca->bdev, err);
return ret;
}
@@ -2348,7 +2347,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
const char *err = NULL; /* must be set for any error case */
int ret = 0;
- bdevname(bdev, ca->cache_dev_name);
memcpy(&ca->sb, sb, sizeof(struct cache_sb));
ca->bdev = bdev;
ca->bdev->bd_holder = ca;
@@ -2390,14 +2388,14 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk,
goto out;
}
- pr_info("registered cache device %s\n", ca->cache_dev_name);
+ pr_info("registered cache device %pg\n", ca->bdev);
out:
kobject_put(&ca->kobj);
err:
if (err)
- pr_notice("error %s: %s\n", ca->cache_dev_name, err);
+ pr_notice("error %pg: %s\n", ca->bdev, err);
return ret;
}
@@ -2617,8 +2615,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
if (SB_IS_BDEV(sb)) {
struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL);
- if (!dc)
+ if (!dc) {
+ ret = -ENOMEM;
+ err = "cannot allocate memory";
goto out_put_sb_page;
+ }
mutex_lock(&bch_register_lock);
ret = register_bdev(sb, sb_disk, bdev, dc);
@@ -2629,11 +2630,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
} else {
struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
- if (!ca)
+ if (!ca) {
+ ret = -ENOMEM;
+ err = "cannot allocate memory";
goto out_put_sb_page;
+ }
/* blkdev_put() will be called in bch_cache_release() */
- if (register_cache(sb, sb_disk, bdev, ca) != 0)
+ ret = register_cache(sb, sb_disk, bdev, ca);
+ if (ret)
goto out_free_sb;
}
@@ -2750,7 +2755,7 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x)
* The reason bch_register_lock is not held to call
* bch_cache_set_stop() and bcache_device_stop() is to
* avoid potential deadlock during reboot, because cache
- * set or bcache device stopping process will acqurie
+ * set or bcache device stopping process will acquire
* bch_register_lock too.
*
* We are safe here because bcache_is_reboot sets to
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 05ac1d6fbbf3..1f0dce30fa75 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -271,7 +271,7 @@ SHOW(__bch_cached_dev)
}
if (attr == &sysfs_backing_dev_name) {
- snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name);
+ snprintf(buf, BDEVNAME_SIZE + 1, "%pg", dc->bdev);
strcat(buf, "\n");
return strlen(buf);
}
diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h
index 215df32f567b..c1752ba2e05b 100644
--- a/drivers/md/bcache/sysfs.h
+++ b/drivers/md/bcache/sysfs.h
@@ -51,13 +51,27 @@ STORE(fn) \
#define sysfs_printf(file, fmt, ...) \
do { \
if (attr == &sysfs_ ## file) \
- return snprintf(buf, PAGE_SIZE, fmt "\n", __VA_ARGS__); \
+ return sysfs_emit(buf, fmt "\n", __VA_ARGS__); \
} while (0)
#define sysfs_print(file, var) \
do { \
if (attr == &sysfs_ ## file) \
- return snprint(buf, PAGE_SIZE, var); \
+ return sysfs_emit(buf, \
+ __builtin_types_compatible_p(typeof(var), int) \
+ ? "%i\n" : \
+ __builtin_types_compatible_p(typeof(var), unsigned int) \
+ ? "%u\n" : \
+ __builtin_types_compatible_p(typeof(var), long) \
+ ? "%li\n" : \
+ __builtin_types_compatible_p(typeof(var), unsigned long)\
+ ? "%lu\n" : \
+ __builtin_types_compatible_p(typeof(var), int64_t) \
+ ? "%lli\n" : \
+ __builtin_types_compatible_p(typeof(var), uint64_t) \
+ ? "%llu\n" : \
+ __builtin_types_compatible_p(typeof(var), const char *) \
+ ? "%s\n" : "%i\n", var); \
} while (0)
#define sysfs_hprint(file, val) \
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index a7da7930a7fd..6f3cb7c92130 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -340,23 +340,6 @@ static inline int bch_strtoul_h(const char *cp, long *res)
_r; \
})
-#define snprint(buf, size, var) \
- snprintf(buf, size, \
- __builtin_types_compatible_p(typeof(var), int) \
- ? "%i\n" : \
- __builtin_types_compatible_p(typeof(var), unsigned int) \
- ? "%u\n" : \
- __builtin_types_compatible_p(typeof(var), long) \
- ? "%li\n" : \
- __builtin_types_compatible_p(typeof(var), unsigned long)\
- ? "%lu\n" : \
- __builtin_types_compatible_p(typeof(var), int64_t) \
- ? "%lli\n" : \
- __builtin_types_compatible_p(typeof(var), uint64_t) \
- ? "%llu\n" : \
- __builtin_types_compatible_p(typeof(var), const char *) \
- ? "%s\n" : "%i\n", var)
-
ssize_t bch_hprint(char *buf, int64_t v);
bool bch_is_zero(const char *p, size_t n);
@@ -548,14 +531,6 @@ static inline uint64_t bch_crc64(const void *p, size_t 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;
-}
-
/*
* A stepwise-linear pseudo-exponential. This returns 1 << (x >>
* frac_bits), with the less-significant bits filled in by linear
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 55dccdfbcb22..b855fef4f38a 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -13,7 +13,7 @@
#include <linux/ktime.h>
#include <linux/genhd.h>
#include <linux/blk-mq.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <trace/events/block.h>
@@ -200,7 +200,7 @@ struct dm_table {
struct dm_md_mempools *mempools;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- struct blk_keyslot_manager *ksm;
+ struct blk_crypto_profile *crypto_profile;
#endif
};
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index d95142102bd2..bcddc5effd15 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -170,7 +170,7 @@ static void free_devices(struct list_head *devices, struct mapped_device *md)
}
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t);
+static void dm_table_destroy_crypto_profile(struct dm_table *t);
void dm_table_destroy(struct dm_table *t)
{
@@ -200,7 +200,7 @@ void dm_table_destroy(struct dm_table *t)
dm_free_md_mempools(t->mempools);
- dm_table_destroy_keyslot_manager(t);
+ dm_table_destroy_crypto_profile(t);
kfree(t);
}
@@ -1186,8 +1186,8 @@ static int dm_table_register_integrity(struct dm_table *t)
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-struct dm_keyslot_manager {
- struct blk_keyslot_manager ksm;
+struct dm_crypto_profile {
+ struct blk_crypto_profile profile;
struct mapped_device *md;
};
@@ -1213,13 +1213,11 @@ static int dm_keyslot_evict_callback(struct dm_target *ti, struct dm_dev *dev,
* When an inline encryption key is evicted from a device-mapper device, evict
* it from all the underlying devices.
*/
-static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int dm_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key, unsigned int slot)
{
- struct dm_keyslot_manager *dksm = container_of(ksm,
- struct dm_keyslot_manager,
- ksm);
- struct mapped_device *md = dksm->md;
+ struct mapped_device *md =
+ container_of(profile, struct dm_crypto_profile, profile)->md;
struct dm_keyslot_evict_args args = { key };
struct dm_table *t;
int srcu_idx;
@@ -1239,150 +1237,148 @@ static int dm_keyslot_evict(struct blk_keyslot_manager *ksm,
return args.err;
}
-static const struct blk_ksm_ll_ops dm_ksm_ll_ops = {
- .keyslot_evict = dm_keyslot_evict,
-};
-
-static int device_intersect_crypto_modes(struct dm_target *ti,
- struct dm_dev *dev, sector_t start,
- sector_t len, void *data)
+static int
+device_intersect_crypto_capabilities(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
{
- struct blk_keyslot_manager *parent = data;
- struct blk_keyslot_manager *child = bdev_get_queue(dev->bdev)->ksm;
+ struct blk_crypto_profile *parent = data;
+ struct blk_crypto_profile *child =
+ bdev_get_queue(dev->bdev)->crypto_profile;
- blk_ksm_intersect_modes(parent, child);
+ blk_crypto_intersect_capabilities(parent, child);
return 0;
}
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile)
{
- struct dm_keyslot_manager *dksm = container_of(ksm,
- struct dm_keyslot_manager,
- ksm);
+ struct dm_crypto_profile *dmcp = container_of(profile,
+ struct dm_crypto_profile,
+ profile);
- if (!ksm)
+ if (!profile)
return;
- blk_ksm_destroy(ksm);
- kfree(dksm);
+ blk_crypto_profile_destroy(profile);
+ kfree(dmcp);
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+static void dm_table_destroy_crypto_profile(struct dm_table *t)
{
- dm_destroy_keyslot_manager(t->ksm);
- t->ksm = NULL;
+ dm_destroy_crypto_profile(t->crypto_profile);
+ t->crypto_profile = NULL;
}
/*
- * Constructs and initializes t->ksm with a keyslot manager that
- * represents the common set of crypto capabilities of the devices
- * described by the dm_table. However, if the constructed keyslot
- * manager does not support a superset of the crypto capabilities
- * supported by the current keyslot manager of the mapped_device,
- * it returns an error instead, since we don't support restricting
- * crypto capabilities on table changes. Finally, if the constructed
- * keyslot manager doesn't actually support any crypto modes at all,
- * it just returns NULL.
+ * Constructs and initializes t->crypto_profile with a crypto profile that
+ * represents the common set of crypto capabilities of the devices described by
+ * the dm_table. However, if the constructed crypto profile doesn't support all
+ * crypto capabilities that are supported by the current mapped_device, it
+ * returns an error instead, since we don't support removing crypto capabilities
+ * on table changes. Finally, if the constructed crypto profile is "empty" (has
+ * no crypto capabilities at all), it just sets t->crypto_profile to NULL.
*/
-static int dm_table_construct_keyslot_manager(struct dm_table *t)
+static int dm_table_construct_crypto_profile(struct dm_table *t)
{
- struct dm_keyslot_manager *dksm;
- struct blk_keyslot_manager *ksm;
+ struct dm_crypto_profile *dmcp;
+ struct blk_crypto_profile *profile;
struct dm_target *ti;
unsigned int i;
- bool ksm_is_empty = true;
+ bool empty_profile = true;
- dksm = kmalloc(sizeof(*dksm), GFP_KERNEL);
- if (!dksm)
+ dmcp = kmalloc(sizeof(*dmcp), GFP_KERNEL);
+ if (!dmcp)
return -ENOMEM;
- dksm->md = t->md;
+ dmcp->md = t->md;
- ksm = &dksm->ksm;
- blk_ksm_init_passthrough(ksm);
- ksm->ksm_ll_ops = dm_ksm_ll_ops;
- ksm->max_dun_bytes_supported = UINT_MAX;
- memset(ksm->crypto_modes_supported, 0xFF,
- sizeof(ksm->crypto_modes_supported));
+ profile = &dmcp->profile;
+ blk_crypto_profile_init(profile, 0);
+ profile->ll_ops.keyslot_evict = dm_keyslot_evict;
+ profile->max_dun_bytes_supported = UINT_MAX;
+ memset(profile->modes_supported, 0xFF,
+ sizeof(profile->modes_supported));
for (i = 0; i < dm_table_get_num_targets(t); i++) {
ti = dm_table_get_target(t, i);
if (!dm_target_passes_crypto(ti->type)) {
- blk_ksm_intersect_modes(ksm, NULL);
+ blk_crypto_intersect_capabilities(profile, NULL);
break;
}
if (!ti->type->iterate_devices)
continue;
- ti->type->iterate_devices(ti, device_intersect_crypto_modes,
- ksm);
+ ti->type->iterate_devices(ti,
+ device_intersect_crypto_capabilities,
+ profile);
}
- if (t->md->queue && !blk_ksm_is_superset(ksm, t->md->queue->ksm)) {
+ if (t->md->queue &&
+ !blk_crypto_has_capabilities(profile,
+ t->md->queue->crypto_profile)) {
DMWARN("Inline encryption capabilities of new DM table were more restrictive than the old table's. This is not supported!");
- dm_destroy_keyslot_manager(ksm);
+ dm_destroy_crypto_profile(profile);
return -EINVAL;
}
/*
- * If the new KSM doesn't actually support any crypto modes, we may as
- * well represent it with a NULL ksm.
+ * If the new profile doesn't actually support any crypto capabilities,
+ * we may as well represent it with a NULL profile.
*/
- ksm_is_empty = true;
- for (i = 0; i < ARRAY_SIZE(ksm->crypto_modes_supported); i++) {
- if (ksm->crypto_modes_supported[i]) {
- ksm_is_empty = false;
+ for (i = 0; i < ARRAY_SIZE(profile->modes_supported); i++) {
+ if (profile->modes_supported[i]) {
+ empty_profile = false;
break;
}
}
- if (ksm_is_empty) {
- dm_destroy_keyslot_manager(ksm);
- ksm = NULL;
+ if (empty_profile) {
+ dm_destroy_crypto_profile(profile);
+ profile = NULL;
}
/*
- * t->ksm is only set temporarily while the table is being set
- * up, and it gets set to NULL after the capabilities have
- * been transferred to the request_queue.
+ * t->crypto_profile is only set temporarily while the table is being
+ * set up, and it gets set to NULL after the profile has been
+ * transferred to the request_queue.
*/
- t->ksm = ksm;
+ t->crypto_profile = profile;
return 0;
}
-static void dm_update_keyslot_manager(struct request_queue *q,
- struct dm_table *t)
+static void dm_update_crypto_profile(struct request_queue *q,
+ struct dm_table *t)
{
- if (!t->ksm)
+ if (!t->crypto_profile)
return;
- /* Make the ksm less restrictive */
- if (!q->ksm) {
- blk_ksm_register(t->ksm, q);
+ /* Make the crypto profile less restrictive. */
+ if (!q->crypto_profile) {
+ blk_crypto_register(t->crypto_profile, q);
} else {
- blk_ksm_update_capabilities(q->ksm, t->ksm);
- dm_destroy_keyslot_manager(t->ksm);
+ blk_crypto_update_capabilities(q->crypto_profile,
+ t->crypto_profile);
+ dm_destroy_crypto_profile(t->crypto_profile);
}
- t->ksm = NULL;
+ t->crypto_profile = NULL;
}
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static int dm_table_construct_keyslot_manager(struct dm_table *t)
+static int dm_table_construct_crypto_profile(struct dm_table *t)
{
return 0;
}
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm)
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile)
{
}
-static void dm_table_destroy_keyslot_manager(struct dm_table *t)
+static void dm_table_destroy_crypto_profile(struct dm_table *t)
{
}
-static void dm_update_keyslot_manager(struct request_queue *q,
- struct dm_table *t)
+static void dm_update_crypto_profile(struct request_queue *q,
+ struct dm_table *t)
{
}
@@ -1414,9 +1410,9 @@ int dm_table_complete(struct dm_table *t)
return r;
}
- r = dm_table_construct_keyslot_manager(t);
+ r = dm_table_construct_crypto_profile(t);
if (r) {
- DMERR("could not construct keyslot manager.");
+ DMERR("could not construct crypto profile.");
return r;
}
@@ -2070,7 +2066,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
return r;
}
- dm_update_keyslot_manager(q, t);
+ dm_update_crypto_profile(q, t);
disk_update_readahead(t->md->disk);
return 0;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 7870e6460633..63aa52263658 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -29,7 +29,7 @@
#include <linux/refcount.h>
#include <linux/part_stat.h>
#include <linux/blk-crypto.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#define DM_MSG_PREFIX "core"
@@ -1663,14 +1663,14 @@ static const struct dax_operations dm_dax_ops;
static void dm_wq_work(struct work_struct *work);
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-static void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+static void dm_queue_destroy_crypto_profile(struct request_queue *q)
{
- dm_destroy_keyslot_manager(q->ksm);
+ dm_destroy_crypto_profile(q->crypto_profile);
}
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline void dm_queue_destroy_keyslot_manager(struct request_queue *q)
+static inline void dm_queue_destroy_crypto_profile(struct request_queue *q)
{
}
#endif /* !CONFIG_BLK_INLINE_ENCRYPTION */
@@ -1696,7 +1696,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
dm_sysfs_exit(md);
del_gendisk(md->disk);
}
- dm_queue_destroy_keyslot_manager(md->queue);
+ dm_queue_destroy_crypto_profile(md->queue);
blk_cleanup_disk(md->disk);
}
@@ -2078,7 +2078,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t)
if (r)
return r;
- add_disk(md->disk);
+ r = add_disk(md->disk);
+ if (r)
+ return r;
r = dm_sysfs_init(md);
if (r) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d964da436383..5111ed966947 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -354,7 +354,7 @@ static bool create_on_open = true;
*/
static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters);
static atomic_t md_event_count;
-void md_new_event(struct mddev *mddev)
+void md_new_event(void)
{
atomic_inc(&md_event_count);
wake_up(&md_event_waiters);
@@ -2882,7 +2882,7 @@ static int add_bound_rdev(struct md_rdev *rdev)
if (mddev->degraded)
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
- md_new_event(mddev);
+ md_new_event();
md_wakeup_thread(mddev->thread);
return 0;
}
@@ -2972,7 +2972,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
* -write_error - clears WriteErrorSeen
* {,-}failfast - set/clear FailFast
*/
+
+ struct mddev *mddev = rdev->mddev;
int err = -EINVAL;
+ bool need_update_sb = false;
+
if (cmd_match(buf, "faulty") && rdev->mddev->pers) {
md_error(rdev->mddev, rdev);
if (test_bit(Faulty, &rdev->flags))
@@ -2987,7 +2991,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
if (rdev->raid_disk >= 0)
err = -EBUSY;
else {
- struct mddev *mddev = rdev->mddev;
err = 0;
if (mddev_is_clustered(mddev))
err = md_cluster_ops->remove_disk(mddev, rdev);
@@ -2998,16 +3001,18 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
md_wakeup_thread(mddev->thread);
}
- md_new_event(mddev);
+ md_new_event();
}
}
} else if (cmd_match(buf, "writemostly")) {
set_bit(WriteMostly, &rdev->flags);
mddev_create_serial_pool(rdev->mddev, rdev, false);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-writemostly")) {
mddev_destroy_serial_pool(rdev->mddev, rdev, false);
clear_bit(WriteMostly, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "blocked")) {
set_bit(Blocked, &rdev->flags);
@@ -3033,9 +3038,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
err = 0;
} else if (cmd_match(buf, "failfast")) {
set_bit(FailFast, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-failfast")) {
clear_bit(FailFast, &rdev->flags);
+ need_update_sb = true;
err = 0;
} else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 &&
!test_bit(Journal, &rdev->flags)) {
@@ -3114,6 +3121,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)
clear_bit(ExternalBbl, &rdev->flags);
err = 0;
}
+ if (need_update_sb)
+ md_update_sb(mddev, 1);
if (!err)
sysfs_notify_dirent_safe(rdev->sysfs_state);
return err ? err : len;
@@ -4095,7 +4104,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len)
if (!mddev->thread)
md_update_sb(mddev, 1);
sysfs_notify_dirent_safe(mddev->sysfs_level);
- md_new_event(mddev);
+ md_new_event();
rv = len;
out_unlock:
mddev_unlock(mddev);
@@ -4616,7 +4625,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len)
export_rdev(rdev);
mddev_unlock(mddev);
if (!err)
- md_new_event(mddev);
+ md_new_event();
return err ? err : len;
}
@@ -5486,6 +5495,10 @@ static struct attribute *md_default_attrs[] = {
NULL,
};
+static const struct attribute_group md_default_group = {
+ .attrs = md_default_attrs,
+};
+
static struct attribute *md_redundancy_attrs[] = {
&md_scan_mode.attr,
&md_last_scan_mode.attr,
@@ -5508,6 +5521,12 @@ static const struct attribute_group md_redundancy_group = {
.attrs = md_redundancy_attrs,
};
+static const struct attribute_group *md_attr_groups[] = {
+ &md_default_group,
+ &md_bitmap_group,
+ NULL,
+};
+
static ssize_t
md_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
@@ -5583,7 +5602,7 @@ static const struct sysfs_ops md_sysfs_ops = {
static struct kobj_type md_ktype = {
.release = md_free,
.sysfs_ops = &md_sysfs_ops,
- .default_attrs = md_default_attrs,
+ .default_groups = md_attr_groups,
};
int mdp_major = 0;
@@ -5592,7 +5611,6 @@ static void mddev_delayed_delete(struct work_struct *ws)
{
struct mddev *mddev = container_of(ws, struct mddev, del_work);
- sysfs_remove_group(&mddev->kobj, &md_bitmap_group);
kobject_del(&mddev->kobj);
kobject_put(&mddev->kobj);
}
@@ -5659,7 +5677,7 @@ static int md_alloc(dev_t dev, char *name)
strcmp(mddev2->gendisk->disk_name, name) == 0) {
spin_unlock(&all_mddevs_lock);
error = -EEXIST;
- goto abort;
+ goto out_unlock_disks_mutex;
}
spin_unlock(&all_mddevs_lock);
}
@@ -5672,7 +5690,7 @@ static int md_alloc(dev_t dev, char *name)
error = -ENOMEM;
disk = blk_alloc_disk(NUMA_NO_NODE);
if (!disk)
- goto abort;
+ goto out_unlock_disks_mutex;
disk->major = MAJOR(mddev->unit);
disk->first_minor = unit << shift;
@@ -5696,27 +5714,25 @@ static int md_alloc(dev_t dev, char *name)
disk->flags |= GENHD_FL_EXT_DEVT;
disk->events |= DISK_EVENT_MEDIA_CHANGE;
mddev->gendisk = disk;
- add_disk(disk);
+ error = add_disk(disk);
+ if (error)
+ goto out_cleanup_disk;
error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md");
- if (error) {
- /* This isn't possible, but as kobject_init_and_add is marked
- * __must_check, we must do something with the result
- */
- pr_debug("md: cannot register %s/md - name in use\n",
- disk->disk_name);
- error = 0;
- }
- if (mddev->kobj.sd &&
- sysfs_create_group(&mddev->kobj, &md_bitmap_group))
- pr_debug("pointless warning\n");
- abort:
+ if (error)
+ goto out_del_gendisk;
+
+ kobject_uevent(&mddev->kobj, KOBJ_ADD);
+ mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
+ mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
+ goto out_unlock_disks_mutex;
+
+out_del_gendisk:
+ del_gendisk(disk);
+out_cleanup_disk:
+ blk_cleanup_disk(disk);
+out_unlock_disks_mutex:
mutex_unlock(&disks_mutex);
- if (!error && mddev->kobj.sd) {
- kobject_uevent(&mddev->kobj, KOBJ_ADD);
- mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state");
- mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level");
- }
mddev_put(mddev);
return error;
}
@@ -6030,7 +6046,7 @@ int md_run(struct mddev *mddev)
if (mddev->sb_flags)
md_update_sb(mddev, 0);
- md_new_event(mddev);
+ md_new_event();
return 0;
bitmap_abort:
@@ -6420,7 +6436,7 @@ static int do_md_stop(struct mddev *mddev, int mode,
if (mddev->hold_active == UNTIL_STOP)
mddev->hold_active = 0;
}
- md_new_event(mddev);
+ md_new_event();
sysfs_notify_dirent_safe(mddev->sysfs_state);
return 0;
}
@@ -6924,7 +6940,7 @@ kick_rdev:
md_wakeup_thread(mddev->thread);
else
md_update_sb(mddev, 1);
- md_new_event(mddev);
+ md_new_event();
return 0;
busy:
@@ -6997,7 +7013,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev)
*/
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
abort_export:
@@ -7971,7 +7987,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev)
md_wakeup_thread(mddev->thread);
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
- md_new_event(mddev);
+ md_new_event();
}
EXPORT_SYMBOL(md_error);
@@ -8855,7 +8871,7 @@ void md_do_sync(struct md_thread *thread)
mddev->curr_resync = 3; /* no longer delayed */
mddev->curr_resync_completed = j;
sysfs_notify_dirent_safe(mddev->sysfs_completed);
- md_new_event(mddev);
+ md_new_event();
update_time = jiffies;
blk_start_plug(&plug);
@@ -8926,7 +8942,7 @@ void md_do_sync(struct md_thread *thread)
/* this is the earliest that rebuild will be
* visible in /proc/mdstat
*/
- md_new_event(mddev);
+ md_new_event();
if (last_check + window > io_sectors || j == max_sectors)
continue;
@@ -9150,7 +9166,7 @@ static int remove_and_add_spares(struct mddev *mddev,
sysfs_link_rdev(mddev, rdev);
if (!test_bit(Journal, &rdev->flags))
spares++;
- md_new_event(mddev);
+ md_new_event();
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
}
}
@@ -9184,7 +9200,7 @@ static void md_start_sync(struct work_struct *ws)
} else
md_wakeup_thread(mddev->sync_thread);
sysfs_notify_dirent_safe(mddev->sysfs_action);
- md_new_event(mddev);
+ md_new_event();
}
/*
@@ -9443,7 +9459,7 @@ void md_reap_sync_thread(struct mddev *mddev)
/* flag recovery needed just to double check */
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
sysfs_notify_dirent_safe(mddev->sysfs_action);
- md_new_event(mddev);
+ md_new_event();
if (mddev->event_work.func)
queue_work(md_misc_wq, &mddev->event_work);
}
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 4c96c36bd01a..53ea7a6961de 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -731,7 +731,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size,
struct page *page, int op, int op_flags,
bool metadata_op);
extern void md_do_sync(struct md_thread *thread);
-extern void md_new_event(struct mddev *mddev);
+extern void md_new_event(void);
extern void md_allow_write(struct mddev *mddev);
extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev);
extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 19598bd38939..7dc8026cf6ee 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1496,7 +1496,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
if (!r1_bio->bios[i])
continue;
- if (first_clone) {
+ if (first_clone && test_bit(WriteMostly, &rdev->flags)) {
/* do behind I/O ?
* Not if there are too many, or cannot
* allocate memory, or a reader on WriteMostly
@@ -1529,13 +1529,12 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
r1_bio->bios[i] = mbio;
- mbio->bi_iter.bi_sector = (r1_bio->sector +
- conf->mirrors[i].rdev->data_offset);
- bio_set_dev(mbio, conf->mirrors[i].rdev->bdev);
+ mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset);
+ bio_set_dev(mbio, rdev->bdev);
mbio->bi_end_io = raid1_end_write_request;
mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
- if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
- !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
+ if (test_bit(FailFast, &rdev->flags) &&
+ !test_bit(WriteMostly, &rdev->flags) &&
conf->raid_disks - mddev->degraded > 1)
mbio->bi_opf |= MD_FAILFAST;
mbio->bi_private = r1_bio;
@@ -1546,7 +1545,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
trace_block_bio_remap(mbio, disk_devt(mddev->gendisk),
r1_bio->sector);
/* flush_pending_writes() needs access to the rdev so...*/
- mbio->bi_bdev = (void *)conf->mirrors[i].rdev;
+ mbio->bi_bdev = (void *)rdev;
cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
if (cb)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index aa2636582841..dde98f65bd04 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4647,7 +4647,7 @@ out:
}
conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
abort:
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 02ed53b20654..9c1a5877cf9f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7732,10 +7732,7 @@ static int raid5_run(struct mddev *mddev)
* discard data disk but write parity disk
*/
stripe = stripe * PAGE_SIZE;
- /* Round up to power of 2, as discard handling
- * currently assumes that */
- while ((stripe-1) & stripe)
- stripe = (stripe | (stripe-1)) + 1;
+ stripe = roundup_pow_of_two(stripe);
mddev->queue->limits.discard_alignment = stripe;
mddev->queue->limits.discard_granularity = stripe;
@@ -8282,7 +8279,7 @@ static int raid5_start_reshape(struct mddev *mddev)
}
conf->reshape_checkpoint = jiffies;
md_wakeup_thread(mddev->sync_thread);
- md_new_event(mddev);
+ md_new_event();
return 0;
}
diff --git a/drivers/mmc/core/crypto.c b/drivers/mmc/core/crypto.c
index 67557808cada..fec4fbf16a5b 100644
--- a/drivers/mmc/core/crypto.c
+++ b/drivers/mmc/core/crypto.c
@@ -16,13 +16,13 @@ void mmc_crypto_set_initial_state(struct mmc_host *host)
{
/* Reset might clear all keys, so reprogram all the keys. */
if (host->caps2 & MMC_CAP2_CRYPTO)
- blk_ksm_reprogram_all_keys(&host->ksm);
+ blk_crypto_reprogram_all_keys(&host->crypto_profile);
}
void mmc_crypto_setup_queue(struct request_queue *q, struct mmc_host *host)
{
if (host->caps2 & MMC_CAP2_CRYPTO)
- blk_ksm_register(&host->ksm, q);
+ blk_crypto_register(&host->crypto_profile, q);
}
EXPORT_SYMBOL_GPL(mmc_crypto_setup_queue);
@@ -30,12 +30,15 @@ void mmc_crypto_prepare_req(struct mmc_queue_req *mqrq)
{
struct request *req = mmc_queue_req_to_req(mqrq);
struct mmc_request *mrq = &mqrq->brq.mrq;
+ struct blk_crypto_keyslot *keyslot;
if (!req->crypt_ctx)
return;
mrq->crypto_ctx = req->crypt_ctx;
- if (req->crypt_keyslot)
- mrq->crypto_key_slot = blk_ksm_get_slot_idx(req->crypt_keyslot);
+
+ keyslot = req->crypt_keyslot;
+ if (keyslot)
+ mrq->crypto_key_slot = blk_crypto_keyslot_index(keyslot);
}
EXPORT_SYMBOL_GPL(mmc_crypto_prepare_req);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 95b3511b0560..ccc148cdb5ee 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -506,7 +506,7 @@ config MMC_OMAP_HS
config MMC_WBSD
tristate "Winbond W83L51xD SD/MMC Card Interface support"
- depends on ISA_DMA_API
+ depends on ISA_DMA_API && !M68K
help
This selects the Winbond(R) W83L51xD Secure digital and
Multimedia card Interface.
diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
index 38559a956330..31f841231609 100644
--- a/drivers/mmc/host/cqhci-core.c
+++ b/drivers/mmc/host/cqhci-core.c
@@ -282,6 +282,9 @@ static void __cqhci_enable(struct cqhci_host *cq_host)
cqhci_writel(cq_host, cqcfg, CQHCI_CFG);
+ if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT)
+ cqhci_writel(cq_host, 0, CQHCI_CTL);
+
mmc->cqe_on = true;
if (cq_host->ops->enable)
diff --git a/drivers/mmc/host/cqhci-crypto.c b/drivers/mmc/host/cqhci-crypto.c
index 6419cfbb4ab7..d5f4b6972f63 100644
--- a/drivers/mmc/host/cqhci-crypto.c
+++ b/drivers/mmc/host/cqhci-crypto.c
@@ -6,7 +6,7 @@
*/
#include <linux/blk-crypto.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include <linux/mmc/host.h>
#include "cqhci-crypto.h"
@@ -23,9 +23,10 @@ static const struct cqhci_crypto_alg_entry {
};
static inline struct cqhci_host *
-cqhci_host_from_ksm(struct blk_keyslot_manager *ksm)
+cqhci_host_from_crypto_profile(struct blk_crypto_profile *profile)
{
- struct mmc_host *mmc = container_of(ksm, struct mmc_host, ksm);
+ struct mmc_host *mmc =
+ container_of(profile, struct mmc_host, crypto_profile);
return mmc->cqe_private;
}
@@ -57,12 +58,12 @@ static int cqhci_crypto_program_key(struct cqhci_host *cq_host,
return 0;
}
-static int cqhci_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
+static int cqhci_crypto_keyslot_program(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm);
+ struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile);
const union cqhci_crypto_cap_entry *ccap_array =
cq_host->crypto_cap_array;
const struct cqhci_crypto_alg_entry *alg =
@@ -115,11 +116,11 @@ static int cqhci_crypto_clear_keyslot(struct cqhci_host *cq_host, int slot)
return cqhci_crypto_program_key(cq_host, &cfg, slot);
}
-static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int cqhci_crypto_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct cqhci_host *cq_host = cqhci_host_from_ksm(ksm);
+ struct cqhci_host *cq_host = cqhci_host_from_crypto_profile(profile);
return cqhci_crypto_clear_keyslot(cq_host, slot);
}
@@ -132,7 +133,7 @@ static int cqhci_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
* "enabled" when these are called, i.e. CQHCI_ENABLE might not be set in the
* CQHCI_CFG register. But the hardware allows that.
*/
-static const struct blk_ksm_ll_ops cqhci_ksm_ops = {
+static const struct blk_crypto_ll_ops cqhci_crypto_ops = {
.keyslot_program = cqhci_crypto_keyslot_program,
.keyslot_evict = cqhci_crypto_keyslot_evict,
};
@@ -157,8 +158,8 @@ cqhci_find_blk_crypto_mode(union cqhci_crypto_cap_entry cap)
*
* If the driver previously set MMC_CAP2_CRYPTO and the CQE declares
* CQHCI_CAP_CS, initialize the crypto support. This involves reading the
- * crypto capability registers, initializing the keyslot manager, clearing all
- * keyslots, and enabling 128-bit task descriptors.
+ * crypto capability registers, initializing the blk_crypto_profile, clearing
+ * all keyslots, and enabling 128-bit task descriptors.
*
* Return: 0 if crypto was initialized or isn't supported; whether
* MMC_CAP2_CRYPTO remains set indicates which one of those cases it is.
@@ -168,7 +169,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
{
struct mmc_host *mmc = cq_host->mmc;
struct device *dev = mmc_dev(mmc);
- struct blk_keyslot_manager *ksm = &mmc->ksm;
+ struct blk_crypto_profile *profile = &mmc->crypto_profile;
unsigned int num_keyslots;
unsigned int cap_idx;
enum blk_crypto_mode_num blk_mode_num;
@@ -199,15 +200,15 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
*/
num_keyslots = cq_host->crypto_capabilities.config_count + 1;
- err = devm_blk_ksm_init(dev, ksm, num_keyslots);
+ err = devm_blk_crypto_profile_init(dev, profile, num_keyslots);
if (err)
goto out;
- ksm->ksm_ll_ops = cqhci_ksm_ops;
- ksm->dev = dev;
+ profile->ll_ops = cqhci_crypto_ops;
+ profile->dev = dev;
/* Unfortunately, CQHCI crypto only supports 32 DUN bits. */
- ksm->max_dun_bytes_supported = 4;
+ profile->max_dun_bytes_supported = 4;
/*
* Cache all the crypto capabilities and advertise the supported crypto
@@ -223,7 +224,7 @@ int cqhci_crypto_init(struct cqhci_host *cq_host)
cq_host->crypto_cap_array[cap_idx]);
if (blk_mode_num == BLK_ENCRYPTION_MODE_INVALID)
continue;
- ksm->crypto_modes_supported[blk_mode_num] |=
+ profile->modes_supported[blk_mode_num] |=
cq_host->crypto_cap_array[cap_idx].sdus_mask * 512;
}
diff --git a/drivers/mmc/host/dw_mmc-exynos.c b/drivers/mmc/host/dw_mmc-exynos.c
index 0c75810812a0..1f8a3c0ddfe1 100644
--- a/drivers/mmc/host/dw_mmc-exynos.c
+++ b/drivers/mmc/host/dw_mmc-exynos.c
@@ -464,6 +464,18 @@ static s8 dw_mci_exynos_get_best_clksmpl(u8 candiates)
}
}
+ /*
+ * If there is no cadiates value, then it needs to return -EIO.
+ * If there are candiates values and don't find bset clk sample value,
+ * then use a first candiates clock sample value.
+ */
+ for (i = 0; i < iter; i++) {
+ __c = ror8(candiates, i);
+ if ((__c & 0x1) == 0x1) {
+ loc = i;
+ goto out;
+ }
+ }
out:
return loc;
}
@@ -494,6 +506,8 @@ static int dw_mci_exynos_execute_tuning(struct dw_mci_slot *slot, u32 opcode)
priv->tuned_sample = found;
} else {
ret = -EIO;
+ dev_warn(&mmc->class_dev,
+ "There is no candiates value about clksmpl!\n");
}
return ret;
diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
index 4dfc246c5f95..b06b4dcb7c78 100644
--- a/drivers/mmc/host/mtk-sd.c
+++ b/drivers/mmc/host/mtk-sd.c
@@ -2577,6 +2577,25 @@ static int msdc_drv_probe(struct platform_device *pdev)
host->dma_mask = DMA_BIT_MASK(32);
mmc_dev(mmc)->dma_mask = &host->dma_mask;
+ host->timeout_clks = 3 * 1048576;
+ host->dma.gpd = dma_alloc_coherent(&pdev->dev,
+ 2 * sizeof(struct mt_gpdma_desc),
+ &host->dma.gpd_addr, GFP_KERNEL);
+ host->dma.bd = dma_alloc_coherent(&pdev->dev,
+ MAX_BD_NUM * sizeof(struct mt_bdma_desc),
+ &host->dma.bd_addr, GFP_KERNEL);
+ if (!host->dma.gpd || !host->dma.bd) {
+ ret = -ENOMEM;
+ goto release_mem;
+ }
+ msdc_init_gpd_bd(host, &host->dma);
+ INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
+ spin_lock_init(&host->lock);
+
+ platform_set_drvdata(pdev, mmc);
+ msdc_ungate_clock(host);
+ msdc_init_hw(host);
+
if (mmc->caps2 & MMC_CAP2_CQE) {
host->cq_host = devm_kzalloc(mmc->parent,
sizeof(*host->cq_host),
@@ -2597,25 +2616,6 @@ static int msdc_drv_probe(struct platform_device *pdev)
mmc->max_seg_size = 64 * 1024;
}
- host->timeout_clks = 3 * 1048576;
- host->dma.gpd = dma_alloc_coherent(&pdev->dev,
- 2 * sizeof(struct mt_gpdma_desc),
- &host->dma.gpd_addr, GFP_KERNEL);
- host->dma.bd = dma_alloc_coherent(&pdev->dev,
- MAX_BD_NUM * sizeof(struct mt_bdma_desc),
- &host->dma.bd_addr, GFP_KERNEL);
- if (!host->dma.gpd || !host->dma.bd) {
- ret = -ENOMEM;
- goto release_mem;
- }
- msdc_init_gpd_bd(host, &host->dma);
- INIT_DELAYED_WORK(&host->req_timeout, msdc_request_timeout);
- spin_lock_init(&host->lock);
-
- platform_set_drvdata(pdev, mmc);
- msdc_ungate_clock(host);
- msdc_init_hw(host);
-
ret = devm_request_irq(&pdev->dev, host->irq, msdc_irq,
IRQF_TRIGGER_NONE, pdev->name, host);
if (ret)
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index f18d169bc8ff..e658f0174242 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1187,6 +1187,7 @@ static void esdhc_reset_tuning(struct sdhci_host *host)
struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
struct pltfm_imx_data *imx_data = sdhci_pltfm_priv(pltfm_host);
u32 ctrl;
+ int ret;
/* Reset the tuning circuit */
if (esdhc_is_usdhc(imx_data)) {
@@ -1199,7 +1200,22 @@ static void esdhc_reset_tuning(struct sdhci_host *host)
} else if (imx_data->socdata->flags & ESDHC_FLAG_STD_TUNING) {
ctrl = readl(host->ioaddr + SDHCI_AUTO_CMD_STATUS);
ctrl &= ~ESDHC_MIX_CTRL_SMPCLK_SEL;
+ ctrl &= ~ESDHC_MIX_CTRL_EXE_TUNE;
writel(ctrl, host->ioaddr + SDHCI_AUTO_CMD_STATUS);
+ /* Make sure ESDHC_MIX_CTRL_EXE_TUNE cleared */
+ ret = readl_poll_timeout(host->ioaddr + SDHCI_AUTO_CMD_STATUS,
+ ctrl, !(ctrl & ESDHC_MIX_CTRL_EXE_TUNE), 1, 50);
+ if (ret == -ETIMEDOUT)
+ dev_warn(mmc_dev(host->mmc),
+ "Warning! clear execute tuning bit failed\n");
+ /*
+ * SDHCI_INT_DATA_AVAIL is W1C bit, set this bit will clear the
+ * usdhc IP internal logic flag execute_tuning_with_clr_buf, which
+ * will finally make sure the normal data transfer logic correct.
+ */
+ ctrl = readl(host->ioaddr + SDHCI_INT_STATUS);
+ ctrl |= SDHCI_INT_DATA_AVAIL;
+ writel(ctrl, host->ioaddr + SDHCI_INT_STATUS);
}
}
}
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index be19785227fe..d0f2edfe296c 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -616,16 +616,12 @@ static int intel_select_drive_strength(struct mmc_card *card,
return intel_host->drv_strength;
}
-static int bxt_get_cd(struct mmc_host *mmc)
+static int sdhci_get_cd_nogpio(struct mmc_host *mmc)
{
- int gpio_cd = mmc_gpio_get_cd(mmc);
struct sdhci_host *host = mmc_priv(mmc);
unsigned long flags;
int ret = 0;
- if (!gpio_cd)
- return 0;
-
spin_lock_irqsave(&host->lock, flags);
if (host->flags & SDHCI_DEVICE_DEAD)
@@ -638,6 +634,21 @@ out:
return ret;
}
+static int bxt_get_cd(struct mmc_host *mmc)
+{
+ int gpio_cd = mmc_gpio_get_cd(mmc);
+
+ if (!gpio_cd)
+ return 0;
+
+ return sdhci_get_cd_nogpio(mmc);
+}
+
+static int mrfld_get_cd(struct mmc_host *mmc)
+{
+ return sdhci_get_cd_nogpio(mmc);
+}
+
#define SDHCI_INTEL_PWR_TIMEOUT_CNT 20
#define SDHCI_INTEL_PWR_TIMEOUT_UDELAY 100
@@ -1341,6 +1352,14 @@ static int intel_mrfld_mmc_probe_slot(struct sdhci_pci_slot *slot)
MMC_CAP_1_8V_DDR;
break;
case INTEL_MRFLD_SD:
+ slot->cd_idx = 0;
+ slot->cd_override_level = true;
+ /*
+ * There are two PCB designs of SD card slot with the opposite
+ * card detection sense. Quirk this out by ignoring GPIO state
+ * completely in the custom ->get_cd() callback.
+ */
+ slot->host->mmc_host_ops.get_cd = mrfld_get_cd;
slot->host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
break;
case INTEL_MRFLD_SDIO:
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index 8eefa7d5fe85..2d80a04e11d8 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2042,6 +2042,12 @@ void sdhci_set_power_noreg(struct sdhci_host *host, unsigned char mode,
break;
case MMC_VDD_32_33:
case MMC_VDD_33_34:
+ /*
+ * 3.4 ~ 3.6V are valid only for those platforms where it's
+ * known that the voltage range is supported by hardware.
+ */
+ case MMC_VDD_34_35:
+ case MMC_VDD_35_36:
pwr = SDHCI_POWER_330;
break;
default:
diff --git a/drivers/mmc/host/tmio_mmc_core.c b/drivers/mmc/host/tmio_mmc_core.c
index 7dfc26f48c18..e2affa52ef46 100644
--- a/drivers/mmc/host/tmio_mmc_core.c
+++ b/drivers/mmc/host/tmio_mmc_core.c
@@ -195,6 +195,10 @@ static void tmio_mmc_reset(struct tmio_mmc_host *host)
sd_ctrl_write32_as_16_and_16(host, CTL_IRQ_MASK, host->sdcard_irq_mask_all);
host->sdcard_irq_mask = host->sdcard_irq_mask_all;
+ if (host->native_hotplug)
+ tmio_mmc_enable_mmc_irqs(host,
+ TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
+
tmio_mmc_set_bus_width(host, host->mmc->ios.bus_width);
if (host->pdata->flags & TMIO_MMC_SDIO_IRQ) {
@@ -956,8 +960,15 @@ static void tmio_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
case MMC_POWER_OFF:
tmio_mmc_power_off(host);
/* For R-Car Gen2+, we need to reset SDHI specific SCC */
- if (host->pdata->flags & TMIO_MMC_MIN_RCAR2)
+ if (host->pdata->flags & TMIO_MMC_MIN_RCAR2) {
host->reset(host);
+
+ if (host->native_hotplug)
+ tmio_mmc_enable_mmc_irqs(host,
+ TMIO_STAT_CARD_REMOVE |
+ TMIO_STAT_CARD_INSERT);
+ }
+
host->set_clock(host, 0);
break;
case MMC_POWER_UP:
@@ -1185,10 +1196,6 @@ int tmio_mmc_host_probe(struct tmio_mmc_host *_host)
_host->set_clock(_host, 0);
tmio_mmc_reset(_host);
- if (_host->native_hotplug)
- tmio_mmc_enable_mmc_irqs(_host,
- TMIO_STAT_CARD_REMOVE | TMIO_STAT_CARD_INSERT);
-
spin_lock_init(&_host->lock);
mutex_init(&_host->ios_lock);
diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c
index 4950d10d3a19..97beece62fec 100644
--- a/drivers/mmc/host/vub300.c
+++ b/drivers/mmc/host/vub300.c
@@ -576,7 +576,7 @@ static void check_vub300_port_status(struct vub300_mmc_host *vub300)
GET_SYSTEM_PORT_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->system_port_status,
- sizeof(vub300->system_port_status), HZ);
+ sizeof(vub300->system_port_status), 1000);
if (sizeof(vub300->system_port_status) == retval)
new_system_port_status(vub300);
}
@@ -1241,7 +1241,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300,
SET_INTERRUPT_PSEUDOCODE,
USB_DIR_OUT | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0x0000, 0x0000,
- xfer_buffer, xfer_length, HZ);
+ xfer_buffer, xfer_length, 1000);
kfree(xfer_buffer);
if (retval < 0)
goto copy_error_message;
@@ -1284,7 +1284,7 @@ static void __download_offload_pseudocode(struct vub300_mmc_host *vub300,
SET_TRANSFER_PSEUDOCODE,
USB_DIR_OUT | USB_TYPE_VENDOR |
USB_RECIP_DEVICE, 0x0000, 0x0000,
- xfer_buffer, xfer_length, HZ);
+ xfer_buffer, xfer_length, 1000);
kfree(xfer_buffer);
if (retval < 0)
goto copy_error_message;
@@ -1991,7 +1991,7 @@ static void __set_clock_speed(struct vub300_mmc_host *vub300, u8 buf[8],
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_CLOCK_SPEED,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x00, 0x00, buf, buf_array_size, HZ);
+ 0x00, 0x00, buf, buf_array_size, 1000);
if (retval != 8) {
dev_err(&vub300->udev->dev, "SET_CLOCK_SPEED"
" %dkHz failed with retval=%d\n", kHzClock, retval);
@@ -2013,14 +2013,14 @@ static void vub300_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_SD_POWER,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x0000, 0x0000, NULL, 0, HZ);
+ 0x0000, 0x0000, NULL, 0, 1000);
/* must wait for the VUB300 u-proc to boot up */
msleep(600);
} else if ((ios->power_mode == MMC_POWER_UP) && !vub300->card_powered) {
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_SD_POWER,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- 0x0001, 0x0000, NULL, 0, HZ);
+ 0x0001, 0x0000, NULL, 0, 1000);
msleep(600);
vub300->card_powered = 1;
} else if (ios->power_mode == MMC_POWER_ON) {
@@ -2275,14 +2275,14 @@ static int vub300_probe(struct usb_interface *interface,
GET_HC_INF0,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->hc_info,
- sizeof(vub300->hc_info), HZ);
+ sizeof(vub300->hc_info), 1000);
if (retval < 0)
goto error5;
retval =
usb_control_msg(vub300->udev, usb_sndctrlpipe(vub300->udev, 0),
SET_ROM_WAIT_STATES,
USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
- firmware_rom_wait_states, 0x0000, NULL, 0, HZ);
+ firmware_rom_wait_states, 0x0000, NULL, 0, 1000);
if (retval < 0)
goto error5;
dev_info(&vub300->udev->dev,
@@ -2297,7 +2297,7 @@ static int vub300_probe(struct usb_interface *interface,
GET_SYSTEM_PORT_STATUS,
USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
0x0000, 0x0000, &vub300->system_port_status,
- sizeof(vub300->system_port_status), HZ);
+ sizeof(vub300->system_port_status), 1000);
if (retval < 0) {
goto error4;
} else if (sizeof(vub300->system_port_status) == retval) {
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index b8ae1ec14e17..4eaba6f4ec68 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -384,7 +384,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
if (new->readonly)
set_disk_ro(gd, 1);
- device_add_disk(&new->mtd->dev, gd, NULL);
+ ret = device_add_disk(&new->mtd->dev, gd, NULL);
+ if (ret)
+ goto out_cleanup_disk;
if (new->disk_attributes) {
ret = sysfs_create_group(&disk_to_dev(gd)->kobj,
@@ -393,6 +395,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new)
}
return 0;
+out_cleanup_disk:
+ blk_cleanup_disk(new->disk);
out_free_tag_set:
blk_mq_free_tag_set(new->tag_set);
out_kfree_tag_set:
diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c
index 308d4f2fff00..eee47bad0592 100644
--- a/drivers/net/can/m_can/m_can_platform.c
+++ b/drivers/net/can/m_can/m_can_platform.c
@@ -32,8 +32,13 @@ static u32 iomap_read_reg(struct m_can_classdev *cdev, int reg)
static int iomap_read_fifo(struct m_can_classdev *cdev, int offset, void *val, size_t val_count)
{
struct m_can_plat_priv *priv = cdev_to_priv(cdev);
+ void __iomem *src = priv->mram_base + offset;
- ioread32_rep(priv->mram_base + offset, val, val_count);
+ while (val_count--) {
+ *(unsigned int *)val = ioread32(src);
+ val += 4;
+ src += 4;
+ }
return 0;
}
@@ -51,8 +56,13 @@ static int iomap_write_fifo(struct m_can_classdev *cdev, int offset,
const void *val, size_t val_count)
{
struct m_can_plat_priv *priv = cdev_to_priv(cdev);
+ void __iomem *dst = priv->mram_base + offset;
- iowrite32_rep(priv->base + offset, val, val_count);
+ while (val_count--) {
+ iowrite32(*(unsigned int *)val, dst);
+ val += 4;
+ dst += 4;
+ }
return 0;
}
diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c
index 00e4533c8bdd..8999ec9455ec 100644
--- a/drivers/net/can/rcar/rcar_can.c
+++ b/drivers/net/can/rcar/rcar_can.c
@@ -846,10 +846,12 @@ static int __maybe_unused rcar_can_suspend(struct device *dev)
struct rcar_can_priv *priv = netdev_priv(ndev);
u16 ctlr;
- if (netif_running(ndev)) {
- netif_stop_queue(ndev);
- netif_device_detach(ndev);
- }
+ if (!netif_running(ndev))
+ return 0;
+
+ netif_stop_queue(ndev);
+ netif_device_detach(ndev);
+
ctlr = readw(&priv->regs->ctlr);
ctlr |= RCAR_CAN_CTLR_CANM_HALT;
writew(ctlr, &priv->regs->ctlr);
@@ -868,6 +870,9 @@ static int __maybe_unused rcar_can_resume(struct device *dev)
u16 ctlr;
int err;
+ if (!netif_running(ndev))
+ return 0;
+
err = clk_enable(priv->clk);
if (err) {
netdev_err(ndev, "clk_enable() failed, error %d\n", err);
@@ -881,10 +886,9 @@ static int __maybe_unused rcar_can_resume(struct device *dev)
writew(ctlr, &priv->regs->ctlr);
priv->can.state = CAN_STATE_ERROR_ACTIVE;
- if (netif_running(ndev)) {
- netif_device_attach(ndev);
- netif_start_queue(ndev);
- }
+ netif_device_attach(ndev);
+ netif_start_queue(ndev);
+
return 0;
}
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 6db90dc4bc9d..84f34020aafb 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -752,16 +752,15 @@ static void peak_pci_remove(struct pci_dev *pdev)
struct net_device *prev_dev = chan->prev_dev;
dev_info(&pdev->dev, "removing device %s\n", dev->name);
+ /* do that only for first channel */
+ if (!prev_dev && chan->pciec_card)
+ peak_pciec_remove(chan->pciec_card);
unregister_sja1000dev(dev);
free_sja1000dev(dev);
dev = prev_dev;
- if (!dev) {
- /* do that only for first channel */
- if (chan->pciec_card)
- peak_pciec_remove(chan->pciec_card);
+ if (!dev)
break;
- }
priv = netdev_priv(dev);
chan = priv->priv;
}
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
index b11eabad575b..09029a3bad1a 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_fd.c
@@ -551,11 +551,10 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if,
} else if (sm->channel_p_w_b & PUCAN_BUS_WARNING) {
new_state = CAN_STATE_ERROR_WARNING;
} else {
- /* no error bit (so, no error skb, back to active state) */
- dev->can.state = CAN_STATE_ERROR_ACTIVE;
+ /* back to (or still in) ERROR_ACTIVE state */
+ new_state = CAN_STATE_ERROR_ACTIVE;
pdev->bec.txerr = 0;
pdev->bec.rxerr = 0;
- return 0;
}
/* state hasn't changed */
@@ -568,8 +567,7 @@ static int pcan_usb_fd_decode_status(struct pcan_usb_fd_if *usb_if,
/* allocate an skb to store the error frame */
skb = alloc_can_err_skb(netdev, &cf);
- if (skb)
- can_change_state(netdev, cf, tx_state, rx_state);
+ can_change_state(netdev, cf, tx_state, rx_state);
/* things must be done even in case of OOM */
if (new_state == CAN_STATE_BUS_OFF)
diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c
index 3ff4b7e177f3..dbd4486a173f 100644
--- a/drivers/net/dsa/lantiq_gswip.c
+++ b/drivers/net/dsa/lantiq_gswip.c
@@ -230,7 +230,7 @@
#define GSWIP_SDMA_PCTRLp(p) (0xBC0 + ((p) * 0x6))
#define GSWIP_SDMA_PCTRL_EN BIT(0) /* SDMA Port Enable */
#define GSWIP_SDMA_PCTRL_FCEN BIT(1) /* Flow Control Enable */
-#define GSWIP_SDMA_PCTRL_PAUFWD BIT(1) /* Pause Frame Forwarding */
+#define GSWIP_SDMA_PCTRL_PAUFWD BIT(3) /* Pause Frame Forwarding */
#define GSWIP_TABLE_ACTIVE_VLAN 0x01
#define GSWIP_TABLE_VLAN_MAPPING 0x02
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 094737e5084a..9890672a206d 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -1035,9 +1035,6 @@ mt7530_port_enable(struct dsa_switch *ds, int port,
{
struct mt7530_priv *priv = ds->priv;
- if (!dsa_is_user_port(ds, port))
- return 0;
-
mutex_lock(&priv->reg_mutex);
/* Allow the user port gets connected to the cpu port and also
@@ -1060,9 +1057,6 @@ mt7530_port_disable(struct dsa_switch *ds, int port)
{
struct mt7530_priv *priv = ds->priv;
- if (!dsa_is_user_port(ds, port))
- return;
-
mutex_lock(&priv->reg_mutex);
/* Clear up all port matrix which could be restored in the next
@@ -3211,7 +3205,7 @@ mt7530_probe(struct mdio_device *mdiodev)
return -ENOMEM;
priv->ds->dev = &mdiodev->dev;
- priv->ds->num_ports = DSA_MAX_PORTS;
+ priv->ds->num_ports = MT7530_NUM_PORTS;
/* Use medatek,mcm property to distinguish hardware type that would
* casues a little bit differences on power-on sequence.
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 691e1475d55e..0fbecd093fa1 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -1193,7 +1193,7 @@ static int nic_register_interrupts(struct nicpf *nic)
dev_err(&nic->pdev->dev,
"Request for #%d msix vectors failed, returned %d\n",
nic->num_vec, ret);
- return 1;
+ return ret;
}
/* Register mailbox interrupt handler */
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index d1667b759522..a27227aeae88 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1224,7 +1224,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic)
if (ret < 0) {
netdev_err(nic->netdev,
"Req for #%d msix vectors failed\n", nic->num_vec);
- return 1;
+ return ret;
}
sprintf(nic->irq_name[irq], "%s Mbox", "NICVF");
@@ -1243,7 +1243,7 @@ static int nicvf_register_misc_interrupt(struct nicvf *nic)
if (!nicvf_check_pf_ready(nic)) {
nicvf_disable_intr(nic, NICVF_INTR_MBOX, 0);
nicvf_unregister_interrupts(nic);
- return 1;
+ return -EIO;
}
return 0;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index 9690e36e9e85..910b9f722504 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -157,7 +157,7 @@ static const struct {
{ ENETC_PM0_TFRM, "MAC tx frames" },
{ ENETC_PM0_TFCS, "MAC tx fcs errors" },
{ ENETC_PM0_TVLAN, "MAC tx VLAN frames" },
- { ENETC_PM0_TERR, "MAC tx frames" },
+ { ENETC_PM0_TERR, "MAC tx frame errors" },
{ ENETC_PM0_TUCA, "MAC tx unicast frames" },
{ ENETC_PM0_TMCA, "MAC tx multicast frames" },
{ ENETC_PM0_TBCA, "MAC tx broadcast frames" },
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
index 4c977dfc44f0..d522bd5c90b4 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -517,10 +517,13 @@ static void enetc_port_si_configure(struct enetc_si *si)
static void enetc_configure_port_mac(struct enetc_hw *hw)
{
+ int tc;
+
enetc_port_wr(hw, ENETC_PM0_MAXFRM,
ENETC_SET_MAXFRM(ENETC_RX_MAXFRM_SIZE));
- enetc_port_wr(hw, ENETC_PTCMSDUR(0), ENETC_MAC_MAXFRM_SIZE);
+ for (tc = 0; tc < 8; tc++)
+ enetc_port_wr(hw, ENETC_PTCMSDUR(tc), ENETC_MAC_MAXFRM_SIZE);
enetc_port_wr(hw, ENETC_PM0_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
ENETC_PM0_CMD_TXP | ENETC_PM0_PROMISC);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index eef1b2764d34..67b0bf310daa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -10,6 +10,27 @@ static LIST_HEAD(hnae3_ae_algo_list);
static LIST_HEAD(hnae3_client_list);
static LIST_HEAD(hnae3_ae_dev_list);
+void hnae3_unregister_ae_algo_prepare(struct hnae3_ae_algo *ae_algo)
+{
+ const struct pci_device_id *pci_id;
+ struct hnae3_ae_dev *ae_dev;
+
+ if (!ae_algo)
+ return;
+
+ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
+ if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+ continue;
+
+ pci_id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
+ if (!pci_id)
+ continue;
+ if (IS_ENABLED(CONFIG_PCI_IOV))
+ pci_disable_sriov(ae_dev->pdev);
+ }
+}
+EXPORT_SYMBOL(hnae3_unregister_ae_algo_prepare);
+
/* we are keeping things simple and using single lock for all the
* list. This is a non-critical code so other updations, if happen
* in parallel, can wait.
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 8ba21d6dc220..d701451596c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -853,6 +853,7 @@ struct hnae3_handle {
int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
+void hnae3_unregister_ae_algo_prepare(struct hnae3_ae_algo *ae_algo);
void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo);
void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 2b66c59f5eaf..e54f96251fea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -137,7 +137,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "uc",
.cmd = HNAE3_DBG_CMD_MAC_UC,
.dentry = HNS3_DBG_DENTRY_MAC,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -256,7 +256,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "tqp",
.cmd = HNAE3_DBG_CMD_REG_TQP,
.dentry = HNS3_DBG_DENTRY_REG,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_128KB,
.init = hns3_dbg_common_file_init,
},
{
@@ -298,7 +298,7 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = {
.name = "fd_tcam",
.cmd = HNAE3_DBG_CMD_FD_TCAM,
.dentry = HNS3_DBG_DENTRY_FD,
- .buf_len = HNS3_DBG_READ_LEN,
+ .buf_len = HNS3_DBG_READ_LEN_1MB,
.init = hns3_dbg_common_file_init,
},
{
@@ -462,7 +462,7 @@ static const struct hns3_dbg_item rx_queue_info_items[] = {
{ "TAIL", 2 },
{ "HEAD", 2 },
{ "FBDNUM", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "COPYBREAK", 2 },
{ "RING_EN", 2 },
{ "RX_RING_EN", 2 },
@@ -565,7 +565,7 @@ static const struct hns3_dbg_item tx_queue_info_items[] = {
{ "HEAD", 2 },
{ "FBDNUM", 2 },
{ "OFFSET", 2 },
- { "PKTNUM", 2 },
+ { "PKTNUM", 5 },
{ "RING_EN", 2 },
{ "TX_RING_EN", 2 },
{ "BASE_ADDR", 10 },
@@ -790,13 +790,13 @@ static int hns3_dbg_rx_bd_info(struct hns3_dbg_data *d, char *buf, int len)
}
static const struct hns3_dbg_item tx_bd_info_items[] = {
- { "BD_IDX", 5 },
- { "ADDRESS", 2 },
+ { "BD_IDX", 2 },
+ { "ADDRESS", 13 },
{ "VLAN_TAG", 2 },
{ "SIZE", 2 },
{ "T_CS_VLAN_TSO", 2 },
{ "OT_VLAN_TAG", 3 },
- { "TV", 2 },
+ { "TV", 5 },
{ "OLT_VLAN_LEN", 2 },
{ "PAYLEN_OL4CS", 2 },
{ "BD_FE_SC_VLD", 2 },
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 468b8f07bf47..4b886a13e079 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1847,7 +1847,6 @@ void hns3_shinfo_pack(struct skb_shared_info *shinfo, __u32 *size)
static int hns3_skb_linearize(struct hns3_enet_ring *ring,
struct sk_buff *skb,
- u8 max_non_tso_bd_num,
unsigned int bd_num)
{
/* 'bd_num == UINT_MAX' means the skb' fraglist has a
@@ -1864,8 +1863,7 @@ static int hns3_skb_linearize(struct hns3_enet_ring *ring,
* will not help.
*/
if (skb->len > HNS3_MAX_TSO_SIZE ||
- (!skb_is_gso(skb) && skb->len >
- HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num))) {
+ (!skb_is_gso(skb) && skb->len > HNS3_MAX_NON_TSO_SIZE)) {
u64_stats_update_begin(&ring->syncp);
ring->stats.hw_limitation++;
u64_stats_update_end(&ring->syncp);
@@ -1900,8 +1898,7 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring,
goto out;
}
- if (hns3_skb_linearize(ring, skb, max_non_tso_bd_num,
- bd_num))
+ if (hns3_skb_linearize(ring, skb, bd_num))
return -ENOMEM;
bd_num = hns3_tx_bd_count(skb->len);
@@ -3258,6 +3255,7 @@ static void hns3_buffer_detach(struct hns3_enet_ring *ring, int i)
{
hns3_unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc[i].addr = 0;
+ ring->desc_cb[i].refill = 0;
}
static void hns3_free_buffer_detach(struct hns3_enet_ring *ring, int i,
@@ -3336,6 +3334,7 @@ static int hns3_alloc_and_attach_buffer(struct hns3_enet_ring *ring, int i)
ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
ring->desc_cb[i].page_offset);
+ ring->desc_cb[i].refill = 1;
return 0;
}
@@ -3365,6 +3364,7 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
{
hns3_unmap_buffer(ring, &ring->desc_cb[i]);
ring->desc_cb[i] = *res_cb;
+ ring->desc_cb[i].refill = 1;
ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
ring->desc_cb[i].page_offset);
ring->desc[i].rx.bd_base_info = 0;
@@ -3373,6 +3373,7 @@ static void hns3_replace_buffer(struct hns3_enet_ring *ring, int i,
static void hns3_reuse_buffer(struct hns3_enet_ring *ring, int i)
{
ring->desc_cb[i].reuse_flag = 0;
+ ring->desc_cb[i].refill = 1;
ring->desc[i].addr = cpu_to_le64(ring->desc_cb[i].dma +
ring->desc_cb[i].page_offset);
ring->desc[i].rx.bd_base_info = 0;
@@ -3479,10 +3480,14 @@ static int hns3_desc_unused(struct hns3_enet_ring *ring)
int ntc = ring->next_to_clean;
int ntu = ring->next_to_use;
+ if (unlikely(ntc == ntu && !ring->desc_cb[ntc].refill))
+ return ring->desc_num;
+
return ((ntc >= ntu) ? 0 : ring->desc_num) + ntc - ntu;
}
-static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
+/* Return true if there is any allocation failure */
+static bool hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
int cleand_count)
{
struct hns3_desc_cb *desc_cb;
@@ -3507,7 +3512,10 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
hns3_rl_err(ring_to_netdev(ring),
"alloc rx buffer failed: %d\n",
ret);
- break;
+
+ writel(i, ring->tqp->io_base +
+ HNS3_RING_RX_RING_HEAD_REG);
+ return true;
}
hns3_replace_buffer(ring, ring->next_to_use, &res_cbs);
@@ -3520,6 +3528,7 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring,
}
writel(i, ring->tqp->io_base + HNS3_RING_RX_RING_HEAD_REG);
+ return false;
}
static bool hns3_can_reuse_page(struct hns3_desc_cb *cb)
@@ -3824,6 +3833,7 @@ static void hns3_rx_ring_move_fw(struct hns3_enet_ring *ring)
{
ring->desc[ring->next_to_clean].rx.bd_base_info &=
cpu_to_le32(~BIT(HNS3_RXD_VLD_B));
+ ring->desc_cb[ring->next_to_clean].refill = 0;
ring->next_to_clean += 1;
if (unlikely(ring->next_to_clean == ring->desc_num))
@@ -4170,6 +4180,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
{
#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
int unused_count = hns3_desc_unused(ring);
+ bool failure = false;
int recv_pkts = 0;
int err;
@@ -4178,9 +4189,9 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
while (recv_pkts < budget) {
/* Reuse or realloc buffers */
if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) {
- hns3_nic_alloc_rx_buffers(ring, unused_count);
- unused_count = hns3_desc_unused(ring) -
- ring->pending_buf;
+ failure = failure ||
+ hns3_nic_alloc_rx_buffers(ring, unused_count);
+ unused_count = 0;
}
/* Poll one pkt */
@@ -4199,11 +4210,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget,
}
out:
- /* Make all data has been write before submit */
- if (unused_count > 0)
- hns3_nic_alloc_rx_buffers(ring, unused_count);
-
- return recv_pkts;
+ return failure ? budget : recv_pkts;
}
static void hns3_update_rx_int_coalesce(struct hns3_enet_tqp_vector *tqp_vector)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 6162d9f88e37..f09a61d9c626 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -186,11 +186,9 @@ enum hns3_nic_state {
#define HNS3_MAX_BD_SIZE 65535
#define HNS3_MAX_TSO_BD_NUM 63U
-#define HNS3_MAX_TSO_SIZE \
- (HNS3_MAX_BD_SIZE * HNS3_MAX_TSO_BD_NUM)
+#define HNS3_MAX_TSO_SIZE 1048576U
+#define HNS3_MAX_NON_TSO_SIZE 9728U
-#define HNS3_MAX_NON_TSO_SIZE(max_non_tso_bd_num) \
- (HNS3_MAX_BD_SIZE * (max_non_tso_bd_num))
#define HNS3_VECTOR_GL0_OFFSET 0x100
#define HNS3_VECTOR_GL1_OFFSET 0x200
@@ -332,6 +330,7 @@ struct hns3_desc_cb {
u32 length; /* length of the buffer */
u16 reuse_flag;
+ u16 refill;
/* desc type, used by the ring user to mark the type of the priv data */
u16 type;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 307c9e830510..91cb578f56b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -137,6 +137,15 @@ static int hclge_ets_sch_mode_validate(struct hclge_dev *hdev,
*changed = true;
break;
case IEEE_8021QAZ_TSA_ETS:
+ /* The hardware will switch to sp mode if bandwidth is
+ * 0, so limit ets bandwidth must be greater than 0.
+ */
+ if (!ets->tc_tx_bw[i]) {
+ dev_err(&hdev->pdev->dev,
+ "tc%u ets bw cannot be 0\n", i);
+ return -EINVAL;
+ }
+
if (hdev->tm_info.tc_info[i].tc_sch_mode !=
HCLGE_SCH_MODE_DWRR)
*changed = true;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index 32f62cd2dd99..9cda8b3562b8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -391,7 +391,7 @@ static int hclge_dbg_dump_mac(struct hclge_dev *hdev, char *buf, int len)
static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u16 qset_id, qset_num;
int ret;
@@ -408,12 +408,12 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%04u %#x %#x %#x %#x\n",
- qset_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2, bitmap->bit3);
+ qset_id, req.bit0, req.bit1, req.bit2,
+ req.bit3);
}
return 0;
@@ -422,7 +422,7 @@ static int hclge_dbg_dump_dcb_qset(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pri_id, pri_num;
int ret;
@@ -439,12 +439,11 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pri_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pri_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -453,7 +452,7 @@ static int hclge_dbg_dump_dcb_pri(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 pg_id;
int ret;
@@ -466,12 +465,11 @@ static int hclge_dbg_dump_dcb_pg(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos,
"%03u %#x %#x %#x\n",
- pg_id, bitmap->bit0, bitmap->bit1,
- bitmap->bit2);
+ pg_id, req.bit0, req.bit1, req.bit2);
}
return 0;
@@ -511,7 +509,7 @@ static int hclge_dbg_dump_dcb_queue(struct hclge_dev *hdev, char *buf, int len,
static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
int *pos)
{
- struct hclge_dbg_bitmap_cmd *bitmap;
+ struct hclge_dbg_bitmap_cmd req;
struct hclge_desc desc;
u8 port_id = 0;
int ret;
@@ -521,12 +519,12 @@ static int hclge_dbg_dump_dcb_port(struct hclge_dev *hdev, char *buf, int len,
if (ret)
return ret;
- bitmap = (struct hclge_dbg_bitmap_cmd *)&desc.data[1];
+ req.bitmap = (u8)le32_to_cpu(desc.data[1]);
*pos += scnprintf(buf + *pos, len - *pos, "port_mask: %#x\n",
- bitmap->bit0);
+ req.bit0);
*pos += scnprintf(buf + *pos, len - *pos, "port_shaping_pass: %#x\n",
- bitmap->bit1);
+ req.bit1);
return 0;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index bb9b026ae88e..93aa7f2bdc13 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -1560,8 +1560,11 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
/* configure TM QCN hw errors */
hclge_cmd_setup_basic_desc(&desc, HCLGE_TM_QCN_MEM_INT_CFG, false);
- if (en)
+ desc.data[0] = cpu_to_le32(HCLGE_TM_QCN_ERR_INT_TYPE);
+ if (en) {
+ desc.data[0] |= cpu_to_le32(HCLGE_TM_QCN_FIFO_INT_EN);
desc.data[1] = cpu_to_le32(HCLGE_TM_QCN_MEM_ERR_INT_EN);
+ }
ret = hclge_cmd_send(&hdev->hw, &desc, 1);
if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index 07987fb8332e..d811eeefe2c0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -50,6 +50,8 @@
#define HCLGE_PPP_MPF_ECC_ERR_INT3_EN 0x003F
#define HCLGE_PPP_MPF_ECC_ERR_INT3_EN_MASK 0x003F
#define HCLGE_TM_SCH_ECC_ERR_INT_EN 0x3
+#define HCLGE_TM_QCN_ERR_INT_TYPE 0x29
+#define HCLGE_TM_QCN_FIFO_INT_EN 0xFFFF00
#define HCLGE_TM_QCN_MEM_ERR_INT_EN 0xFFFFFF
#define HCLGE_NCSI_ERR_INT_EN 0x3
#define HCLGE_NCSI_ERR_INT_TYPE 0x9
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index f5b8d1fee0f1..d891390d492f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2847,33 +2847,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_reset_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
static void hclge_errhand_task_schedule(struct hclge_dev *hdev)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_and_set_bit(HCLGE_STATE_ERR_SERVICE_SCHED, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task, 0);
+ mod_delayed_work(hclge_wq, &hdev->service_task, 0);
}
void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time)
{
if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) &&
!test_bit(HCLGE_STATE_RST_FAIL, &hdev->state))
- mod_delayed_work_on(cpumask_first(&hdev->affinity_mask),
- hclge_wq, &hdev->service_task,
- delay_time);
+ mod_delayed_work(hclge_wq, &hdev->service_task, delay_time);
}
static int hclge_get_mac_link_status(struct hclge_dev *hdev, int *link_status)
@@ -3491,33 +3487,14 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev)
hdev->num_msi_used += 1;
}
-static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify,
- const cpumask_t *mask)
-{
- struct hclge_dev *hdev = container_of(notify, struct hclge_dev,
- affinity_notify);
-
- cpumask_copy(&hdev->affinity_mask, mask);
-}
-
-static void hclge_irq_affinity_release(struct kref *ref)
-{
-}
-
static void hclge_misc_affinity_setup(struct hclge_dev *hdev)
{
irq_set_affinity_hint(hdev->misc_vector.vector_irq,
&hdev->affinity_mask);
-
- hdev->affinity_notify.notify = hclge_irq_affinity_notify;
- hdev->affinity_notify.release = hclge_irq_affinity_release;
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq,
- &hdev->affinity_notify);
}
static void hclge_misc_affinity_teardown(struct hclge_dev *hdev)
{
- irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL);
irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL);
}
@@ -13052,7 +13029,7 @@ static int hclge_init(void)
{
pr_info("%s is initializing\n", HCLGE_NAME);
- hclge_wq = alloc_workqueue("%s", 0, 0, HCLGE_NAME);
+ hclge_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGE_NAME);
if (!hclge_wq) {
pr_err("%s: failed to create workqueue\n", HCLGE_NAME);
return -ENOMEM;
@@ -13065,6 +13042,7 @@ static int hclge_init(void)
static void hclge_exit(void)
{
+ hnae3_unregister_ae_algo_prepare(&ae_algo);
hnae3_unregister_ae_algo(&ae_algo);
destroy_workqueue(hclge_wq);
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index de6afbcbfbac..69cd8f87b4c8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -944,7 +944,6 @@ struct hclge_dev {
/* affinity mask and notify for misc interrupt */
cpumask_t affinity_mask;
- struct irq_affinity_notify affinity_notify;
struct hclge_ptp *ptp;
struct devlink *devlink;
};
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index f314dbd3ce11..95074e91a846 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -752,6 +752,8 @@ static void hclge_tm_pg_info_init(struct hclge_dev *hdev)
hdev->tm_info.pg_info[i].tc_bit_map = hdev->hw_tc_map;
for (k = 0; k < hdev->tm_info.num_tc; k++)
hdev->tm_info.pg_info[i].tc_dwrr[k] = BW_PERCENT;
+ for (; k < HNAE3_MAX_TC; k++)
+ hdev->tm_info.pg_info[i].tc_dwrr[k] = 0;
}
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 5fdac8685f95..cf00ad7bb881 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2232,6 +2232,7 @@ static void hclgevf_get_misc_vector(struct hclgevf_dev *hdev)
void hclgevf_reset_task_schedule(struct hclgevf_dev *hdev)
{
if (!test_bit(HCLGEVF_STATE_REMOVING, &hdev->state) &&
+ test_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state) &&
!test_and_set_bit(HCLGEVF_STATE_RST_SERVICE_SCHED,
&hdev->state))
mod_delayed_work(hclgevf_wq, &hdev->service_task, 0);
@@ -2273,9 +2274,9 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev)
hdev->reset_attempts = 0;
hdev->last_reset_time = jiffies;
- while ((hdev->reset_type =
- hclgevf_get_reset_level(hdev, &hdev->reset_pending))
- != HNAE3_NONE_RESET)
+ hdev->reset_type =
+ hclgevf_get_reset_level(hdev, &hdev->reset_pending);
+ if (hdev->reset_type != HNAE3_NONE_RESET)
hclgevf_reset(hdev);
} else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED,
&hdev->reset_state)) {
@@ -3449,6 +3450,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
hclgevf_init_rxd_adv_layout(hdev);
+ set_bit(HCLGEVF_STATE_SERVICE_INITED, &hdev->state);
+
hdev->last_reset_time = jiffies;
dev_info(&hdev->pdev->dev, "finished initializing %s driver\n",
HCLGEVF_DRIVER_NAME);
@@ -3899,7 +3902,7 @@ static int hclgevf_init(void)
{
pr_info("%s is initializing\n", HCLGEVF_NAME);
- hclgevf_wq = alloc_workqueue("%s", 0, 0, HCLGEVF_NAME);
+ hclgevf_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, HCLGEVF_NAME);
if (!hclgevf_wq) {
pr_err("%s: failed to create workqueue\n", HCLGEVF_NAME);
return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 883130a9b48f..28288d7e3303 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -146,6 +146,7 @@ enum hclgevf_states {
HCLGEVF_STATE_REMOVING,
HCLGEVF_STATE_NIC_REGISTERED,
HCLGEVF_STATE_ROCE_REGISTERED,
+ HCLGEVF_STATE_SERVICE_INITED,
/* task states */
HCLGEVF_STATE_RST_SERVICE_SCHED,
HCLGEVF_STATE_RST_HANDLING,
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 5b2143f4b1f8..3178efd98006 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -113,7 +113,8 @@ enum e1000_boards {
board_pch2lan,
board_pch_lpt,
board_pch_spt,
- board_pch_cnp
+ board_pch_cnp,
+ board_pch_tgp
};
struct e1000_ps_page {
@@ -499,6 +500,7 @@ extern const struct e1000_info e1000_pch2_info;
extern const struct e1000_info e1000_pch_lpt_info;
extern const struct e1000_info e1000_pch_spt_info;
extern const struct e1000_info e1000_pch_cnp_info;
+extern const struct e1000_info e1000_pch_tgp_info;
extern const struct e1000_info e1000_es2_info;
void e1000e_ptp_init(struct e1000_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c
index 60c582a16821..5e4fc9b4e2ad 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.c
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c
@@ -4813,7 +4813,7 @@ static s32 e1000_reset_hw_ich8lan(struct e1000_hw *hw)
static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw)
{
struct e1000_mac_info *mac = &hw->mac;
- u32 ctrl_ext, txdctl, snoop;
+ u32 ctrl_ext, txdctl, snoop, fflt_dbg;
s32 ret_val;
u16 i;
@@ -4872,6 +4872,15 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw)
snoop = (u32)~(PCIE_NO_SNOOP_ALL);
e1000e_set_pcie_no_snoop(hw, snoop);
+ /* Enable workaround for packet loss issue on TGP PCH
+ * Do not gate DMA clock from the modPHY block
+ */
+ if (mac->type >= e1000_pch_tgp) {
+ fflt_dbg = er32(FFLT_DBG);
+ fflt_dbg |= E1000_FFLT_DBG_DONT_GATE_WAKE_DMA_CLK;
+ ew32(FFLT_DBG, fflt_dbg);
+ }
+
ctrl_ext = er32(CTRL_EXT);
ctrl_ext |= E1000_CTRL_EXT_RO_DIS;
ew32(CTRL_EXT, ctrl_ext);
@@ -5992,3 +6001,23 @@ const struct e1000_info e1000_pch_cnp_info = {
.phy_ops = &ich8_phy_ops,
.nvm_ops = &spt_nvm_ops,
};
+
+const struct e1000_info e1000_pch_tgp_info = {
+ .mac = e1000_pch_tgp,
+ .flags = FLAG_IS_ICH
+ | FLAG_HAS_WOL
+ | FLAG_HAS_HW_TIMESTAMP
+ | FLAG_HAS_CTRLEXT_ON_LOAD
+ | FLAG_HAS_AMT
+ | FLAG_HAS_FLASH
+ | FLAG_HAS_JUMBO_FRAMES
+ | FLAG_APME_IN_WUC,
+ .flags2 = FLAG2_HAS_PHY_STATS
+ | FLAG2_HAS_EEE,
+ .pba = 26,
+ .max_hw_frame_size = 9022,
+ .get_variants = e1000_get_variants_ich8lan,
+ .mac_ops = &ich8_mac_ops,
+ .phy_ops = &ich8_phy_ops,
+ .nvm_ops = &spt_nvm_ops,
+};
diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h
index d6a092e5ee74..2504b11c3169 100644
--- a/drivers/net/ethernet/intel/e1000e/ich8lan.h
+++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h
@@ -289,6 +289,9 @@
/* Proprietary Latency Tolerance Reporting PCI Capability */
#define E1000_PCI_LTR_CAP_LPT 0xA8
+/* Don't gate wake DMA clock */
+#define E1000_FFLT_DBG_DONT_GATE_WAKE_DMA_CLK 0x1000
+
void e1000e_write_protect_nvm_ich8lan(struct e1000_hw *hw);
void e1000e_set_kmrn_lock_loss_workaround_ich8lan(struct e1000_hw *hw,
bool state);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 900b3ab998bd..ebcb2a30add0 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -51,6 +51,7 @@ static const struct e1000_info *e1000_info_tbl[] = {
[board_pch_lpt] = &e1000_pch_lpt_info,
[board_pch_spt] = &e1000_pch_spt_info,
[board_pch_cnp] = &e1000_pch_cnp_info,
+ [board_pch_tgp] = &e1000_pch_tgp_info,
};
struct e1000_reg_info {
@@ -7896,28 +7897,28 @@ static const struct pci_device_id e1000_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V11), board_pch_cnp },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_LM12), board_pch_spt },
{ PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_CMP_I219_V12), board_pch_spt },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM13), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V13), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_cnp },
- { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_cnp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM13), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V13), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM14), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V14), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_LM15), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_TGP_I219_V15), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM23), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V23), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM16), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V16), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_LM17), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_ADP_I219_V17), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_LM22), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_RPL_I219_V22), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM18), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V18), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_LM19), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_MTP_I219_V19), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM20), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V20), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_LM21), board_pch_tgp },
+ { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LNP_I219_V21), board_pch_tgp },
{ 0, 0, 0, 0, 0, 0, 0 } /* terminate list */
};
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 2fb81e359cdf..df5ad4de1f00 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -25,6 +25,8 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw)
case ICE_DEV_ID_E810C_BACKPLANE:
case ICE_DEV_ID_E810C_QSFP:
case ICE_DEV_ID_E810C_SFP:
+ case ICE_DEV_ID_E810_XXV_BACKPLANE:
+ case ICE_DEV_ID_E810_XXV_QSFP:
case ICE_DEV_ID_E810_XXV_SFP:
hw->mac_type = ICE_MAC_E810;
break;
diff --git a/drivers/net/ethernet/intel/ice/ice_devids.h b/drivers/net/ethernet/intel/ice/ice_devids.h
index 9d8194671f6a..ef4392e6e244 100644
--- a/drivers/net/ethernet/intel/ice/ice_devids.h
+++ b/drivers/net/ethernet/intel/ice/ice_devids.h
@@ -21,6 +21,10 @@
#define ICE_DEV_ID_E810C_QSFP 0x1592
/* Intel(R) Ethernet Controller E810-C for SFP */
#define ICE_DEV_ID_E810C_SFP 0x1593
+/* Intel(R) Ethernet Controller E810-XXV for backplane */
+#define ICE_DEV_ID_E810_XXV_BACKPLANE 0x1599
+/* Intel(R) Ethernet Controller E810-XXV for QSFP */
+#define ICE_DEV_ID_E810_XXV_QSFP 0x159A
/* Intel(R) Ethernet Controller E810-XXV for SFP */
#define ICE_DEV_ID_E810_XXV_SFP 0x159B
/* Intel(R) Ethernet Connection E823-C for backplane */
diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c
index 14afce82ef63..da7288bdc9a3 100644
--- a/drivers/net/ethernet/intel/ice/ice_devlink.c
+++ b/drivers/net/ethernet/intel/ice/ice_devlink.c
@@ -63,7 +63,8 @@ static int ice_info_fw_api(struct ice_pf *pf, struct ice_info_ctx *ctx)
{
struct ice_hw *hw = &pf->hw;
- snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u", hw->api_maj_ver, hw->api_min_ver);
+ snprintf(ctx->buf, sizeof(ctx->buf), "%u.%u.%u", hw->api_maj_ver,
+ hw->api_min_ver, hw->api_patch);
return 0;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
index 06ac9badee77..1ac96dc66d0d 100644
--- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
+++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c
@@ -1668,7 +1668,7 @@ static u16 ice_tunnel_idx_to_entry(struct ice_hw *hw, enum ice_tunnel_type type,
for (i = 0; i < hw->tnl.count && i < ICE_TUNNEL_MAX_ENTRIES; i++)
if (hw->tnl.tbl[i].valid &&
hw->tnl.tbl[i].type == type &&
- idx--)
+ idx-- == 0)
return i;
WARN_ON_ONCE(1);
@@ -1828,7 +1828,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table,
u16 index;
tnl_type = ti->type == UDP_TUNNEL_TYPE_VXLAN ? TNL_VXLAN : TNL_GENEVE;
- index = ice_tunnel_idx_to_entry(&pf->hw, idx, tnl_type);
+ index = ice_tunnel_idx_to_entry(&pf->hw, tnl_type, idx);
status = ice_create_tunnel(&pf->hw, index, tnl_type, ntohs(ti->port));
if (status) {
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 37c18c66b5c7..e375ac849aec 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -100,9 +100,9 @@ static void ice_display_lag_info(struct ice_lag *lag)
*/
static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
{
- struct net_device *event_netdev, *netdev_tmp;
struct netdev_notifier_bonding_info *info;
struct netdev_bonding_info *bonding_info;
+ struct net_device *event_netdev;
const char *lag_netdev_name;
event_netdev = netdev_notifier_info_to_dev(ptr);
@@ -123,19 +123,6 @@ static void ice_lag_info_event(struct ice_lag *lag, void *ptr)
goto lag_out;
}
- rcu_read_lock();
- for_each_netdev_in_bond_rcu(lag->upper_netdev, netdev_tmp) {
- if (!netif_is_ice(netdev_tmp))
- continue;
-
- if (netdev_tmp && netdev_tmp != lag->netdev &&
- lag->peer_netdev != netdev_tmp) {
- dev_hold(netdev_tmp);
- lag->peer_netdev = netdev_tmp;
- }
- }
- rcu_read_unlock();
-
if (bonding_info->slave.state)
ice_lag_set_backup(lag);
else
@@ -319,6 +306,9 @@ ice_lag_event_handler(struct notifier_block *notif_blk, unsigned long event,
case NETDEV_BONDING_INFO:
ice_lag_info_event(lag, ptr);
break;
+ case NETDEV_UNREGISTER:
+ ice_lag_unlink(lag, ptr);
+ break;
default:
break;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index dde9802c6c72..b718e196af2a 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2841,6 +2841,7 @@ void ice_napi_del(struct ice_vsi *vsi)
*/
int ice_vsi_release(struct ice_vsi *vsi)
{
+ enum ice_status err;
struct ice_pf *pf;
if (!vsi->back)
@@ -2912,6 +2913,10 @@ int ice_vsi_release(struct ice_vsi *vsi)
ice_fltr_remove_all(vsi);
ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+ err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
+ if (err)
+ dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
+ vsi->vsi_num, err);
ice_vsi_delete(vsi);
ice_vsi_free_q_vectors(vsi);
@@ -3092,6 +3097,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi)
prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+ ret = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
+ if (ret)
+ dev_err(ice_pf_to_dev(vsi->back), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
+ vsi->vsi_num, ret);
ice_vsi_free_q_vectors(vsi);
/* SR-IOV determines needed MSIX resources all at once instead of per
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 0d6c143f6653..06fa93e597fb 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4224,6 +4224,9 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
if (!pf)
return -ENOMEM;
+ /* initialize Auxiliary index to invalid value */
+ pf->aux_idx = -1;
+
/* set up for high or low DMA */
err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
if (err)
@@ -4615,7 +4618,8 @@ static void ice_remove(struct pci_dev *pdev)
ice_aq_cancel_waiting_tasks(pf);
ice_unplug_aux_dev(pf);
- ida_free(&ice_aux_ida, pf->aux_idx);
+ if (pf->aux_idx >= 0)
+ ida_free(&ice_aux_ida, pf->aux_idx);
set_bit(ICE_DOWN, pf->state);
mutex_destroy(&(&pf->hw)->fdir_fltr_lock);
@@ -5016,6 +5020,8 @@ static const struct pci_device_id ice_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 },
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 80380aed8882..d1ef3d48a4b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1571,6 +1571,9 @@ err_kworker:
*/
void ice_ptp_release(struct ice_pf *pf)
{
+ if (!test_bit(ICE_FLAG_PTP, pf->flags))
+ return;
+
/* Disable timestamping for both Tx and Rx */
ice_ptp_cfg_timestamp(pf, false);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 9f07b6641705..2d9b10277186 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -2071,6 +2071,19 @@ enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle)
}
/**
+ * ice_rm_vsi_rdma_cfg - remove VSI and its RDMA children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function clears the VSI and its RDMA children nodes from scheduler tree
+ * for all TCs.
+ */
+enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle)
+{
+ return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_RDMA);
+}
+
+/**
* ice_get_agg_info - get the aggregator ID
* @hw: pointer to the hardware structure
* @agg_id: aggregator ID
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 9beef8f0ec76..fdf7a5882f07 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -89,6 +89,7 @@ enum ice_status
ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
u8 owner, bool enable);
enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle);
+enum ice_status ice_rm_vsi_rdma_cfg(struct ice_port_info *pi, u16 vsi_handle);
/* Tx scheduler rate limiter functions */
enum ice_status
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index 4461f8b9a864..4e0203336c6b 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -22,8 +22,8 @@
#define IGC_DEV_ID_I220_V 0x15F7
#define IGC_DEV_ID_I225_K 0x3100
#define IGC_DEV_ID_I225_K2 0x3101
+#define IGC_DEV_ID_I226_K 0x3102
#define IGC_DEV_ID_I225_LMVP 0x5502
-#define IGC_DEV_ID_I226_K 0x5504
#define IGC_DEV_ID_I225_IT 0x0D9F
#define IGC_DEV_ID_I226_LM 0x125B
#define IGC_DEV_ID_I226_V 0x125C
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 9338765da048..49d822a98ada 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -226,18 +226,85 @@ static const struct file_operations rvu_dbg_##name##_fops = { \
static void print_nix_qsize(struct seq_file *filp, struct rvu_pfvf *pfvf);
+static void get_lf_str_list(struct rvu_block block, int pcifunc,
+ char *lfs)
+{
+ int lf = 0, seq = 0, len = 0, prev_lf = block.lf.max;
+
+ for_each_set_bit(lf, block.lf.bmap, block.lf.max) {
+ if (lf >= block.lf.max)
+ break;
+
+ if (block.fn_map[lf] != pcifunc)
+ continue;
+
+ if (lf == prev_lf + 1) {
+ prev_lf = lf;
+ seq = 1;
+ continue;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d,%d", prev_lf, lf);
+ else
+ len += (len ? sprintf(lfs + len, ",%d", lf) :
+ sprintf(lfs + len, "%d", lf));
+
+ prev_lf = lf;
+ seq = 0;
+ }
+
+ if (seq)
+ len += sprintf(lfs + len, "-%d", prev_lf);
+
+ lfs[len] = '\0';
+}
+
+static int get_max_column_width(struct rvu *rvu)
+{
+ int index, pf, vf, lf_str_size = 12, buf_size = 256;
+ struct rvu_block block;
+ u16 pcifunc;
+ char *buf;
+
+ buf = kzalloc(buf_size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+ for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ pcifunc = pf << 10 | vf;
+ if (!pcifunc)
+ continue;
+
+ for (index = 0; index < BLK_COUNT; index++) {
+ block = rvu->hw->block[index];
+ if (!strlen(block.name))
+ continue;
+
+ get_lf_str_list(block, pcifunc, buf);
+ if (lf_str_size <= strlen(buf))
+ lf_str_size = strlen(buf) + 1;
+ }
+ }
+ }
+
+ kfree(buf);
+ return lf_str_size;
+}
+
/* Dumps current provisioning status of all RVU block LFs */
static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
char __user *buffer,
size_t count, loff_t *ppos)
{
- int index, off = 0, flag = 0, go_back = 0, len = 0;
+ int index, off = 0, flag = 0, len = 0, i = 0;
struct rvu *rvu = filp->private_data;
- int lf, pf, vf, pcifunc;
+ int bytes_not_copied = 0;
struct rvu_block block;
- int bytes_not_copied;
- int lf_str_size = 12;
+ int pf, vf, pcifunc;
int buf_size = 2048;
+ int lf_str_size;
char *lfs;
char *buf;
@@ -249,6 +316,9 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
if (!buf)
return -ENOSPC;
+ /* Get the maximum width of a column */
+ lf_str_size = get_max_column_width(rvu);
+
lfs = kzalloc(lf_str_size, GFP_KERNEL);
if (!lfs) {
kfree(buf);
@@ -262,65 +332,69 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
"%-*s", lf_str_size,
rvu->hw->block[index].name);
}
+
off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer + (i * off), buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
+ off = 0;
+ flag = 0;
pcifunc = pf << 10 | vf;
if (!pcifunc)
continue;
if (vf) {
sprintf(lfs, "PF%d:VF%d", pf, vf - 1);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
} else {
sprintf(lfs, "PF%d", pf);
- go_back = scnprintf(&buf[off],
- buf_size - 1 - off,
- "%-*s", lf_str_size, lfs);
+ off = scnprintf(&buf[off],
+ buf_size - 1 - off,
+ "%-*s", lf_str_size, lfs);
}
- off += go_back;
- for (index = 0; index < BLKTYPE_MAX; index++) {
+ for (index = 0; index < BLK_COUNT; index++) {
block = rvu->hw->block[index];
if (!strlen(block.name))
continue;
len = 0;
lfs[len] = '\0';
- for (lf = 0; lf < block.lf.max; lf++) {
- if (block.fn_map[lf] != pcifunc)
- continue;
+ get_lf_str_list(block, pcifunc, lfs);
+ if (strlen(lfs))
flag = 1;
- len += sprintf(&lfs[len], "%d,", lf);
- }
- if (flag)
- len--;
- lfs[len] = '\0';
off += scnprintf(&buf[off], buf_size - 1 - off,
"%-*s", lf_str_size, lfs);
- if (!strlen(lfs))
- go_back += lf_str_size;
}
- if (!flag)
- off -= go_back;
- else
- flag = 0;
- off--;
- off += scnprintf(&buf[off], buf_size - 1 - off, "\n");
+ if (flag) {
+ off += scnprintf(&buf[off],
+ buf_size - 1 - off, "\n");
+ bytes_not_copied = copy_to_user(buffer +
+ (i * off),
+ buf, off);
+ if (bytes_not_copied)
+ goto out;
+
+ i++;
+ *ppos += off;
+ }
}
}
- bytes_not_copied = copy_to_user(buffer, buf, off);
+out:
kfree(lfs);
kfree(buf);
-
if (bytes_not_copied)
return -EFAULT;
- *ppos = off;
- return off;
+ return *ppos;
}
RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL);
@@ -504,7 +578,7 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp,
if (cmd_buf)
ret = -EINVAL;
- if (!strncmp(subtoken, "help", 4) || ret < 0) {
+ if (ret < 0 || !strncmp(subtoken, "help", 4)) {
dev_info(rvu->dev, "Use echo <%s-lf > qsize\n", blk_string);
goto qsize_write_done;
}
@@ -1719,6 +1793,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused)
u16 pcifunc;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
if (layer == BAND_PROF_INVAL_LAYER)
continue;
@@ -1768,6 +1846,10 @@ static int rvu_dbg_nix_band_prof_rsrc_display(struct seq_file *m, void *unused)
int layer;
char *str;
+ /* Ingress policers do not exist on all platforms */
+ if (!nix_hw->ipolicer)
+ return 0;
+
seq_puts(m, "\nBandwidth profile resource free count\n");
seq_puts(m, "=====================================\n");
for (layer = 0; layer < BAND_PROF_NUM_LAYERS; layer++) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 9ef4e942e31e..6970540dc470 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -2507,6 +2507,9 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc)
return;
nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ if (!nix_hw)
+ return;
+
vlan = &nix_hw->txvlan;
mutex_lock(&vlan->rsrc_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 41684a6c44e9..a88a1a48229f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -199,6 +199,9 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
+int mlx5e_fs_init(struct mlx5e_priv *priv);
+void mlx5e_fs_cleanup(struct mlx5e_priv *priv);
+
int mlx5e_add_vlan_trap(struct mlx5e_priv *priv, int trap_id, int tir_num);
void mlx5e_remove_vlan_trap(struct mlx5e_priv *priv);
int mlx5e_add_mac_trap(struct mlx5e_priv *priv, int trap_id, int tir_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index b4e986818794..4a13ef561587 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -10,6 +10,8 @@
#include "en_tc.h"
#include "rep/tc.h"
#include "rep/neigh.h"
+#include "lag.h"
+#include "lag_mp.h"
struct mlx5e_tc_tun_route_attr {
struct net_device *out_dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 33de8f0092a6..fb5397324aa4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -141,8 +141,7 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
* Pkt: MAC IP ESP IP L4
*
* Transport Mode:
- * SWP: OutL3 InL4
- * InL3
+ * SWP: OutL3 OutL4
* Pkt: MAC IP ESP L4
*
* Tunnel(VXLAN TCP/UDP) over Transport Mode
@@ -171,31 +170,35 @@ static void mlx5e_ipsec_set_swp(struct sk_buff *skb,
return;
if (!xo->inner_ipproto) {
- eseg->swp_inner_l3_offset = skb_network_offset(skb) / 2;
- eseg->swp_inner_l4_offset = skb_inner_transport_offset(skb) / 2;
- if (skb->protocol == htons(ETH_P_IPV6))
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
- if (xo->proto == IPPROTO_UDP)
+ switch (xo->proto) {
+ case IPPROTO_UDP:
+ eseg->swp_flags |= MLX5_ETH_WQE_SWP_OUTER_L4_UDP;
+ fallthrough;
+ case IPPROTO_TCP:
+ /* IP | ESP | TCP */
+ eseg->swp_outer_l4_offset = skb_inner_transport_offset(skb) / 2;
+ break;
+ default:
+ break;
+ }
+ } else {
+ /* Tunnel(VXLAN TCP/UDP) over Transport Mode */
+ switch (xo->inner_ipproto) {
+ case IPPROTO_UDP:
eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
- return;
- }
-
- /* Tunnel(VXLAN TCP/UDP) over Transport Mode */
- switch (xo->inner_ipproto) {
- case IPPROTO_UDP:
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L4_UDP;
- fallthrough;
- case IPPROTO_TCP:
- eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
- eseg->swp_inner_l4_offset = (skb->csum_start + skb->head - skb->data) / 2;
- if (skb->protocol == htons(ETH_P_IPV6))
- eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
- break;
- default:
- break;
+ fallthrough;
+ case IPPROTO_TCP:
+ eseg->swp_inner_l3_offset = skb_inner_network_offset(skb) / 2;
+ eseg->swp_inner_l4_offset =
+ (skb->csum_start + skb->head - skb->data) / 2;
+ if (skb->protocol == htons(ETH_P_IPV6))
+ eseg->swp_flags |= MLX5_ETH_WQE_SWP_INNER_L3_IPV6;
+ break;
+ default:
+ break;
+ }
}
- return;
}
void mlx5e_ipsec_set_iv_esn(struct sk_buff *skb, struct xfrm_state *x,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
index c06b4b938ae7..d226cc5ab1d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c
@@ -1186,10 +1186,6 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
struct mlx5e_flow_table *ft;
int err;
- priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL);
- if (!priv->fs.vlan)
- return -ENOMEM;
-
ft = &priv->fs.vlan->ft;
ft->num_groups = 0;
@@ -1198,10 +1194,8 @@ static int mlx5e_create_vlan_table(struct mlx5e_priv *priv)
ft_attr.prio = MLX5E_NIC_PRIO;
ft->t = mlx5_create_flow_table(priv->fs.ns, &ft_attr);
- if (IS_ERR(ft->t)) {
- err = PTR_ERR(ft->t);
- goto err_free_t;
- }
+ if (IS_ERR(ft->t))
+ return PTR_ERR(ft->t);
ft->g = kcalloc(MLX5E_NUM_VLAN_GROUPS, sizeof(*ft->g), GFP_KERNEL);
if (!ft->g) {
@@ -1221,9 +1215,6 @@ err_free_g:
kfree(ft->g);
err_destroy_vlan_table:
mlx5_destroy_flow_table(ft->t);
-err_free_t:
- kvfree(priv->fs.vlan);
- priv->fs.vlan = NULL;
return err;
}
@@ -1232,7 +1223,6 @@ static void mlx5e_destroy_vlan_table(struct mlx5e_priv *priv)
{
mlx5e_del_vlan_rules(priv);
mlx5e_destroy_flow_table(&priv->fs.vlan->ft);
- kvfree(priv->fs.vlan);
}
static void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv)
@@ -1351,3 +1341,17 @@ void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv)
mlx5e_arfs_destroy_tables(priv);
mlx5e_ethtool_cleanup_steering(priv);
}
+
+int mlx5e_fs_init(struct mlx5e_priv *priv)
+{
+ priv->fs.vlan = kvzalloc(sizeof(*priv->fs.vlan), GFP_KERNEL);
+ if (!priv->fs.vlan)
+ return -ENOMEM;
+ return 0;
+}
+
+void mlx5e_fs_cleanup(struct mlx5e_priv *priv)
+{
+ kvfree(priv->fs.vlan);
+ priv->fs.vlan = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 09c8b71b186c..41ef6eb70a58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4578,6 +4578,12 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
mlx5e_timestamp_init(priv);
+ err = mlx5e_fs_init(priv);
+ if (err) {
+ mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+ return err;
+ }
+
err = mlx5e_ipsec_init(priv);
if (err)
mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err);
@@ -4595,6 +4601,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
mlx5e_health_destroy_reporters(priv);
mlx5e_tls_cleanup(priv);
mlx5e_ipsec_cleanup(priv);
+ mlx5e_fs_cleanup(priv);
}
static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index ba8164792016..129ff7e0d65c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -67,6 +67,8 @@
#include "lib/fs_chains.h"
#include "diag/en_tc_tracepoint.h"
#include <asm/div64.h>
+#include "lag.h"
+#include "lag_mp.h"
#define nic_chains(priv) ((priv)->fs.tc.chains)
#define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index c63d78eda606..188994d091c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -213,19 +213,18 @@ static inline void mlx5e_insert_vlan(void *start, struct sk_buff *skb, u16 ihs)
memcpy(&vhdr->h_vlan_encapsulated_proto, skb->data + cpy1_sz, cpy2_sz);
}
-/* If packet is not IP's CHECKSUM_PARTIAL (e.g. icmd packet),
- * need to set L3 checksum flag for IPsec
- */
static void
ipsec_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5_wqe_eth_seg *eseg)
{
+ struct xfrm_offload *xo = xfrm_offload(skb);
+
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
- if (skb->encapsulation) {
- eseg->cs_flags |= MLX5_ETH_WQE_L3_INNER_CSUM;
+ if (xo->inner_ipproto) {
+ eseg->cs_flags |= MLX5_ETH_WQE_L4_INNER_CSUM | MLX5_ETH_WQE_L3_INNER_CSUM;
+ } else if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
+ eseg->cs_flags |= MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial_inner++;
- } else {
- sq->stats->csum_partial++;
}
}
@@ -234,6 +233,11 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
struct mlx5e_accel_tx_state *accel,
struct mlx5_wqe_eth_seg *eseg)
{
+ if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) {
+ ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
+ return;
+ }
+
if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM;
if (skb->encapsulation) {
@@ -249,8 +253,6 @@ mlx5e_txwqe_build_eseg_csum(struct mlx5e_txqsq *sq, struct sk_buff *skb,
eseg->cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
sq->stats->csum_partial++;
#endif
- } else if (unlikely(mlx5e_ipsec_eseg_meta(eseg))) {
- ipsec_txwqe_build_eseg_csum(sq, skb, eseg);
} else
sq->stats->csum_none++;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 985e305179d1..c6cc67cb4f6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -473,10 +473,9 @@ esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
err_min_rate:
list_del(&group->list);
- err = mlx5_destroy_scheduling_element_cmd(esw->dev,
- SCHEDULING_HIERARCHY_E_SWITCH,
- group->tsar_ix);
- if (err)
+ if (mlx5_destroy_scheduling_element_cmd(esw->dev,
+ SCHEDULING_HIERARCHY_E_SWITCH,
+ group->tsar_ix))
NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed");
err_sched_elem:
kfree(group);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index ca5690b0a7ab..d2105c1635c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -442,6 +442,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
if (!mlx5_lag_is_ready(ldev)) {
do_bond = false;
} else {
+ /* VF LAG is in multipath mode, ignore bond change requests */
+ if (mlx5_lag_is_multipath(dev0))
+ return;
+
tracker = ldev->tracker;
do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index f239b352a58a..21fdaf708f1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -9,20 +9,23 @@
#include "eswitch.h"
#include "lib/mlx5.h"
+static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
+{
+ return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
+}
+
static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
{
if (!mlx5_lag_is_ready(ldev))
return false;
+ if (__mlx5_lag_is_active(ldev) && !__mlx5_lag_is_multipath(ldev))
+ return false;
+
return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev,
ldev->pf[MLX5_LAG_P2].dev);
}
-static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
-{
- return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
-}
-
bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
{
struct mlx5_lag *ldev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
index 729c839397a8..dea199e79bed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -24,12 +24,14 @@ struct lag_mp {
void mlx5_lag_mp_reset(struct mlx5_lag *ldev);
int mlx5_lag_mp_init(struct mlx5_lag *ldev);
void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
#else /* CONFIG_MLX5_ESWITCH */
static inline void mlx5_lag_mp_reset(struct mlx5_lag *ldev) {};
static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev) { return false; }
#endif /* CONFIG_MLX5_ESWITCH */
#endif /* __MLX5_LAG_MP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 13b0259f7ea6..fcace73eae40 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -353,13 +353,10 @@ static int mlxsw_pci_rdq_skb_alloc(struct mlxsw_pci *mlxsw_pci,
struct sk_buff *skb;
int err;
- elem_info->u.rdq.skb = NULL;
skb = netdev_alloc_skb_ip_align(NULL, buf_len);
if (!skb)
return -ENOMEM;
- /* Assume that wqe was previously zeroed. */
-
err = mlxsw_pci_wqe_frag_map(mlxsw_pci, wqe, 0, skb->data,
buf_len, DMA_FROM_DEVICE);
if (err)
@@ -597,21 +594,26 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
struct pci_dev *pdev = mlxsw_pci->pdev;
struct mlxsw_pci_queue_elem_info *elem_info;
struct mlxsw_rx_info rx_info = {};
- char *wqe;
+ char wqe[MLXSW_PCI_WQE_SIZE];
struct sk_buff *skb;
u16 byte_count;
int err;
elem_info = mlxsw_pci_queue_elem_info_consumer_get(q);
- skb = elem_info->u.sdq.skb;
- if (!skb)
- return;
- wqe = elem_info->elem;
- mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+ skb = elem_info->u.rdq.skb;
+ memcpy(wqe, elem_info->elem, MLXSW_PCI_WQE_SIZE);
if (q->consumer_counter++ != consumer_counter_limit)
dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
+ err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
+ if (err) {
+ dev_err_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+ goto out;
+ }
+
+ mlxsw_pci_wqe_frag_unmap(mlxsw_pci, wqe, 0, DMA_FROM_DEVICE);
+
if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) {
rx_info.is_lag = true;
rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe);
@@ -647,10 +649,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
skb_put(skb, byte_count);
mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
- memset(wqe, 0, q->elem_size);
- err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
- if (err)
- dev_dbg_ratelimited(&pdev->dev, "Failed to alloc skb for RDQ\n");
+out:
/* Everything is set up, ring doorbell to pass elem to HW */
q->producer_counter++;
mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 9e8561cdc32a..4d5a5d6595b3 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1743,6 +1743,16 @@ static int lan743x_tx_ring_init(struct lan743x_tx *tx)
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&tx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&tx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(tx->ring_size *
sizeof(struct lan743x_tx_descriptor),
PAGE_SIZE);
@@ -1934,7 +1944,8 @@ static void lan743x_rx_update_tail(struct lan743x_rx *rx, int index)
index);
}
-static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+ gfp_t gfp)
{
struct net_device *netdev = rx->adapter->netdev;
struct device *dev = &rx->adapter->pdev->dev;
@@ -1948,7 +1959,7 @@ static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index)
descriptor = &rx->ring_cpu_ptr[index];
buffer_info = &rx->buffer_info[index];
- skb = __netdev_alloc_skb(netdev, buffer_length, GFP_ATOMIC | GFP_DMA);
+ skb = __netdev_alloc_skb(netdev, buffer_length, gfp);
if (!skb)
return -ENOMEM;
dma_ptr = dma_map_single(dev, skb->data, buffer_length, DMA_FROM_DEVICE);
@@ -2110,7 +2121,8 @@ static int lan743x_rx_process_buffer(struct lan743x_rx *rx)
/* save existing skb, allocate new skb and map to dma */
skb = buffer_info->skb;
- if (lan743x_rx_init_ring_element(rx, rx->last_head)) {
+ if (lan743x_rx_init_ring_element(rx, rx->last_head,
+ GFP_ATOMIC | GFP_DMA)) {
/* failed to allocate next skb.
* Memory is very low.
* Drop this packet and reuse buffer.
@@ -2276,6 +2288,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
ret = -EINVAL;
goto cleanup;
}
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(64))) {
+ if (dma_set_mask_and_coherent(&rx->adapter->pdev->dev,
+ DMA_BIT_MASK(32))) {
+ dev_warn(&rx->adapter->pdev->dev,
+ "lan743x_: No suitable DMA available\n");
+ ret = -ENOMEM;
+ goto cleanup;
+ }
+ }
ring_allocation_size = ALIGN(rx->ring_size *
sizeof(struct lan743x_rx_descriptor),
PAGE_SIZE);
@@ -2315,13 +2337,16 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
rx->last_head = 0;
for (index = 0; index < rx->ring_size; index++) {
- ret = lan743x_rx_init_ring_element(rx, index);
+ ret = lan743x_rx_init_ring_element(rx, index, GFP_KERNEL);
if (ret)
goto cleanup;
}
return 0;
cleanup:
+ netif_warn(rx->adapter, ifup, rx->adapter->netdev,
+ "Error allocating memory for LAN743x\n");
+
lan743x_rx_ring_cleanup(rx);
return ret;
}
@@ -3019,6 +3044,8 @@ static int lan743x_pm_resume(struct device *dev)
if (ret) {
netif_err(adapter, probe, adapter->netdev,
"lan743x_hardware_init returned %d\n", ret);
+ lan743x_pci_cleanup(adapter);
+ return ret;
}
/* open netdev when netdev is at running state while resume.
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index cbece6e9bff2..5030dfca3879 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -758,6 +758,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev)
err = dev_err_probe(sparx5->dev, PTR_ERR(serdes),
"port %u: missing serdes\n",
portno);
+ of_node_put(portnp);
goto cleanup_config;
}
config->portno = portno;
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 291ae6817c26..d51f799e4e86 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -969,6 +969,7 @@ static int mscc_ocelot_init_ports(struct platform_device *pdev,
target = ocelot_regmap_init(ocelot, res);
if (IS_ERR(target)) {
err = PTR_ERR(target);
+ of_node_put(portnp);
goto out_teardown;
}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 11c83a99b014..f469950c7265 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -182,15 +182,21 @@ static int
nfp_bpf_check_mtu(struct nfp_app *app, struct net_device *netdev, int new_mtu)
{
struct nfp_net *nn = netdev_priv(netdev);
- unsigned int max_mtu;
+ struct nfp_bpf_vnic *bv;
+ struct bpf_prog *prog;
if (~nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF)
return 0;
- max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- if (new_mtu > max_mtu) {
- nn_info(nn, "BPF offload active, MTU over %u not supported\n",
- max_mtu);
+ if (nn->xdp_hw.prog) {
+ prog = nn->xdp_hw.prog;
+ } else {
+ bv = nn->app_priv;
+ prog = bv->tc_prog;
+ }
+
+ if (nfp_bpf_offload_check_mtu(nn, prog, new_mtu)) {
+ nn_info(nn, "BPF offload active, potential packet access beyond hardware packet boundary");
return -EBUSY;
}
return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index d0e17eebddd9..16841bb750b7 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -560,6 +560,8 @@ bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
int nfp_bpf_jit(struct nfp_prog *prog);
bool nfp_bpf_supported_opcode(u8 code);
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu);
int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
int prev_insn_idx);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 53851853562c..9d97cd281f18 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -481,19 +481,28 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
return 0;
}
+bool nfp_bpf_offload_check_mtu(struct nfp_net *nn, struct bpf_prog *prog,
+ unsigned int mtu)
+{
+ unsigned int fw_mtu, pkt_off;
+
+ fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
+ pkt_off = min(prog->aux->max_pkt_offset, mtu);
+
+ return fw_mtu < pkt_off;
+}
+
static int
nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
- unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
+ unsigned int max_stack, max_prog_len;
dma_addr_t dma_addr;
void *img;
int err;
- fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
- pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
- if (fw_mtu < pkt_off) {
+ if (nfp_bpf_offload_check_mtu(nn, prog, nn->dp.netdev->mtu)) {
NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.c b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
index 2643ea5948f4..154399c5453f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.c
@@ -196,7 +196,7 @@ int swreg_to_unrestricted(swreg dst, swreg lreg, swreg rreg,
}
reg->dst_lmextn = swreg_lmextn(dst);
- reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
+ reg->src_lmextn = swreg_lmextn(lreg) || swreg_lmextn(rreg);
return 0;
}
@@ -277,7 +277,7 @@ int swreg_to_restricted(swreg dst, swreg lreg, swreg rreg,
}
reg->dst_lmextn = swreg_lmextn(dst);
- reg->src_lmextn = swreg_lmextn(lreg) | swreg_lmextn(rreg);
+ reg->src_lmextn = swreg_lmextn(lreg) || swreg_lmextn(rreg);
return 0;
}
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index d29fe562b3de..c910fa2f40a4 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -1015,9 +1015,6 @@ static int lpc_eth_close(struct net_device *ndev)
napi_disable(&pldat->napi);
netif_stop_queue(ndev);
- if (ndev->phydev)
- phy_stop(ndev->phydev);
-
spin_lock_irqsave(&pldat->lock, flags);
__lpc_eth_reset(pldat);
netif_carrier_off(ndev);
@@ -1025,6 +1022,8 @@ static int lpc_eth_close(struct net_device *ndev)
writel(0, LPC_ENET_MAC2(pldat->net_base));
spin_unlock_irqrestore(&pldat->lock, flags);
+ if (ndev->phydev)
+ phy_stop(ndev->phydev);
clk_disable_unprepare(pldat->clk);
return 0;
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 46a6ff9a782d..2918947dd57c 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -157,6 +157,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
{ PCI_VDEVICE(REALTEK, 0x8129) },
{ PCI_VDEVICE(REALTEK, 0x8136), RTL_CFG_NO_GBIT },
{ PCI_VDEVICE(REALTEK, 0x8161) },
+ { PCI_VDEVICE(REALTEK, 0x8162) },
{ PCI_VDEVICE(REALTEK, 0x8167) },
{ PCI_VDEVICE(REALTEK, 0x8168) },
{ PCI_VDEVICE(NCUBE, 0x8168) },
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
index 4bd3ef8f3384..c4fe3c48ac46 100644
--- a/drivers/net/ethernet/sfc/mcdi_port_common.c
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -132,16 +132,27 @@ void mcdi_to_ethtool_linkset(u32 media, u32 cap, unsigned long *linkset)
case MC_CMD_MEDIA_SFP_PLUS:
case MC_CMD_MEDIA_QSFP_PLUS:
SET_BIT(FIBRE);
- if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN))
+ if (cap & (1 << MC_CMD_PHY_CAP_1000FDX_LBN)) {
SET_BIT(1000baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN))
- SET_BIT(10000baseT_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
+ SET_BIT(1000baseX_Full);
+ }
+ if (cap & (1 << MC_CMD_PHY_CAP_10000FDX_LBN)) {
+ SET_BIT(10000baseCR_Full);
+ SET_BIT(10000baseLR_Full);
+ SET_BIT(10000baseSR_Full);
+ }
+ if (cap & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) {
SET_BIT(40000baseCR4_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN))
+ SET_BIT(40000baseSR4_Full);
+ }
+ if (cap & (1 << MC_CMD_PHY_CAP_100000FDX_LBN)) {
SET_BIT(100000baseCR4_Full);
- if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN))
+ SET_BIT(100000baseSR4_Full);
+ }
+ if (cap & (1 << MC_CMD_PHY_CAP_25000FDX_LBN)) {
SET_BIT(25000baseCR_Full);
+ SET_BIT(25000baseSR_Full);
+ }
if (cap & (1 << MC_CMD_PHY_CAP_50000FDX_LBN))
SET_BIT(50000baseCR2_Full);
break;
@@ -192,15 +203,19 @@ u32 ethtool_linkset_to_mcdi_cap(const unsigned long *linkset)
result |= (1 << MC_CMD_PHY_CAP_100FDX_LBN);
if (TEST_BIT(1000baseT_Half))
result |= (1 << MC_CMD_PHY_CAP_1000HDX_LBN);
- if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full))
+ if (TEST_BIT(1000baseT_Full) || TEST_BIT(1000baseKX_Full) ||
+ TEST_BIT(1000baseX_Full))
result |= (1 << MC_CMD_PHY_CAP_1000FDX_LBN);
- if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full))
+ if (TEST_BIT(10000baseT_Full) || TEST_BIT(10000baseKX4_Full) ||
+ TEST_BIT(10000baseCR_Full) || TEST_BIT(10000baseLR_Full) ||
+ TEST_BIT(10000baseSR_Full))
result |= (1 << MC_CMD_PHY_CAP_10000FDX_LBN);
- if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full))
+ if (TEST_BIT(40000baseCR4_Full) || TEST_BIT(40000baseKR4_Full) ||
+ TEST_BIT(40000baseSR4_Full))
result |= (1 << MC_CMD_PHY_CAP_40000FDX_LBN);
- if (TEST_BIT(100000baseCR4_Full))
+ if (TEST_BIT(100000baseCR4_Full) || TEST_BIT(100000baseSR4_Full))
result |= (1 << MC_CMD_PHY_CAP_100000FDX_LBN);
- if (TEST_BIT(25000baseCR_Full))
+ if (TEST_BIT(25000baseCR_Full) || TEST_BIT(25000baseSR_Full))
result |= (1 << MC_CMD_PHY_CAP_25000FDX_LBN);
if (TEST_BIT(50000baseCR2_Full))
result |= (1 << MC_CMD_PHY_CAP_50000FDX_LBN);
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
index a39c5143b386..797e51802ccb 100644
--- a/drivers/net/ethernet/sfc/ptp.c
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -648,7 +648,7 @@ static int efx_ptp_get_attributes(struct efx_nic *efx)
} else if (rc == -EINVAL) {
fmt = MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS;
} else if (rc == -EPERM) {
- netif_info(efx, probe, efx->net_dev, "no PTP support\n");
+ pci_info(efx->pci_dev, "no PTP support\n");
return rc;
} else {
efx_mcdi_display_error(efx, MC_CMD_PTP, sizeof(inbuf),
@@ -824,7 +824,7 @@ static int efx_ptp_disable(struct efx_nic *efx)
* should only have been called during probe.
*/
if (rc == -ENOSYS || rc == -EPERM)
- netif_info(efx, probe, efx->net_dev, "no PTP support\n");
+ pci_info(efx->pci_dev, "no PTP support\n");
else if (rc)
efx_mcdi_display_error(efx, MC_CMD_PTP,
MC_CMD_PTP_IN_DISABLE_LEN,
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
index 83dcfcae3d4b..441e7f3e5375 100644
--- a/drivers/net/ethernet/sfc/siena_sriov.c
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -1057,7 +1057,7 @@ void efx_siena_sriov_probe(struct efx_nic *efx)
return;
if (efx_siena_sriov_cmd(efx, false, &efx->vi_scale, &count)) {
- netif_info(efx, probe, efx->net_dev, "no SR-IOV VFs probed\n");
+ pci_info(efx->pci_dev, "no SR-IOV VFs probed\n");
return;
}
if (count > 0 && count > max_vfs)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eb3b7bf771d7..3d67d1fa3690 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -736,7 +736,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
ptp_v2 = PTP_TCR_TSVER2ENA;
snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
- if (priv->synopsys_id != DWMAC_CORE_5_10)
+ if (priv->synopsys_id < DWMAC_CORE_4_10)
ts_event_en = PTP_TCR_TSEVNTENA;
ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index 775dcf4ebde5..6b6f28d5b8d5 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -623,16 +623,16 @@ static int receive(struct net_device *dev, int cnt)
/* --------------------------------------------------------------------- */
-#ifdef __i386__
+#if defined(__i386__) && !defined(CONFIG_UML)
#include <asm/msr.h>
#define GETTICK(x) \
({ \
if (boot_cpu_has(X86_FEATURE_TSC)) \
x = (unsigned int)rdtsc(); \
})
-#else /* __i386__ */
+#else /* __i386__ && !CONFIG_UML */
#define GETTICK(x)
-#endif /* __i386__ */
+#endif /* __i386__ && !CONFIG_UML */
static void epp_bh(struct work_struct *work)
{
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f124a8a58bd4..a3bfb156c83d 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -243,62 +243,10 @@ static void phy_sanitize_settings(struct phy_device *phydev)
}
}
-int phy_ethtool_ksettings_set(struct phy_device *phydev,
- const struct ethtool_link_ksettings *cmd)
-{
- __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
- u8 autoneg = cmd->base.autoneg;
- u8 duplex = cmd->base.duplex;
- u32 speed = cmd->base.speed;
-
- if (cmd->base.phy_address != phydev->mdio.addr)
- return -EINVAL;
-
- linkmode_copy(advertising, cmd->link_modes.advertising);
-
- /* We make sure that we don't pass unsupported values in to the PHY */
- linkmode_and(advertising, advertising, phydev->supported);
-
- /* Verify the settings we care about. */
- if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
- return -EINVAL;
-
- if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
- return -EINVAL;
-
- if (autoneg == AUTONEG_DISABLE &&
- ((speed != SPEED_1000 &&
- speed != SPEED_100 &&
- speed != SPEED_10) ||
- (duplex != DUPLEX_HALF &&
- duplex != DUPLEX_FULL)))
- return -EINVAL;
-
- phydev->autoneg = autoneg;
-
- if (autoneg == AUTONEG_DISABLE) {
- phydev->speed = speed;
- phydev->duplex = duplex;
- }
-
- linkmode_copy(phydev->advertising, advertising);
-
- linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
- phydev->advertising, autoneg == AUTONEG_ENABLE);
-
- phydev->master_slave_set = cmd->base.master_slave_cfg;
- phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
-
- /* Restart the PHY */
- phy_start_aneg(phydev);
-
- return 0;
-}
-EXPORT_SYMBOL(phy_ethtool_ksettings_set);
-
void phy_ethtool_ksettings_get(struct phy_device *phydev,
struct ethtool_link_ksettings *cmd)
{
+ mutex_lock(&phydev->lock);
linkmode_copy(cmd->link_modes.supported, phydev->supported);
linkmode_copy(cmd->link_modes.advertising, phydev->advertising);
linkmode_copy(cmd->link_modes.lp_advertising, phydev->lp_advertising);
@@ -317,6 +265,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev,
cmd->base.autoneg = phydev->autoneg;
cmd->base.eth_tp_mdix_ctrl = phydev->mdix_ctrl;
cmd->base.eth_tp_mdix = phydev->mdix;
+ mutex_unlock(&phydev->lock);
}
EXPORT_SYMBOL(phy_ethtool_ksettings_get);
@@ -751,7 +700,7 @@ static int phy_check_link_status(struct phy_device *phydev)
}
/**
- * phy_start_aneg - start auto-negotiation for this PHY device
+ * _phy_start_aneg - start auto-negotiation for this PHY device
* @phydev: the phy_device struct
*
* Description: Sanitizes the settings (if we're not autonegotiating
@@ -759,25 +708,43 @@ static int phy_check_link_status(struct phy_device *phydev)
* If the PHYCONTROL Layer is operating, we change the state to
* reflect the beginning of Auto-negotiation or forcing.
*/
-int phy_start_aneg(struct phy_device *phydev)
+static int _phy_start_aneg(struct phy_device *phydev)
{
int err;
+ lockdep_assert_held(&phydev->lock);
+
if (!phydev->drv)
return -EIO;
- mutex_lock(&phydev->lock);
-
if (AUTONEG_DISABLE == phydev->autoneg)
phy_sanitize_settings(phydev);
err = phy_config_aneg(phydev);
if (err < 0)
- goto out_unlock;
+ return err;
if (phy_is_started(phydev))
err = phy_check_link_status(phydev);
-out_unlock:
+
+ return err;
+}
+
+/**
+ * phy_start_aneg - start auto-negotiation for this PHY device
+ * @phydev: the phy_device struct
+ *
+ * Description: Sanitizes the settings (if we're not autonegotiating
+ * them), and then calls the driver's config_aneg function.
+ * If the PHYCONTROL Layer is operating, we change the state to
+ * reflect the beginning of Auto-negotiation or forcing.
+ */
+int phy_start_aneg(struct phy_device *phydev)
+{
+ int err;
+
+ mutex_lock(&phydev->lock);
+ err = _phy_start_aneg(phydev);
mutex_unlock(&phydev->lock);
return err;
@@ -800,6 +767,61 @@ static int phy_poll_aneg_done(struct phy_device *phydev)
return ret < 0 ? ret : 0;
}
+int phy_ethtool_ksettings_set(struct phy_device *phydev,
+ const struct ethtool_link_ksettings *cmd)
+{
+ __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising);
+ u8 autoneg = cmd->base.autoneg;
+ u8 duplex = cmd->base.duplex;
+ u32 speed = cmd->base.speed;
+
+ if (cmd->base.phy_address != phydev->mdio.addr)
+ return -EINVAL;
+
+ linkmode_copy(advertising, cmd->link_modes.advertising);
+
+ /* We make sure that we don't pass unsupported values in to the PHY */
+ linkmode_and(advertising, advertising, phydev->supported);
+
+ /* Verify the settings we care about. */
+ if (autoneg != AUTONEG_ENABLE && autoneg != AUTONEG_DISABLE)
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_ENABLE && linkmode_empty(advertising))
+ return -EINVAL;
+
+ if (autoneg == AUTONEG_DISABLE &&
+ ((speed != SPEED_1000 &&
+ speed != SPEED_100 &&
+ speed != SPEED_10) ||
+ (duplex != DUPLEX_HALF &&
+ duplex != DUPLEX_FULL)))
+ return -EINVAL;
+
+ mutex_lock(&phydev->lock);
+ phydev->autoneg = autoneg;
+
+ if (autoneg == AUTONEG_DISABLE) {
+ phydev->speed = speed;
+ phydev->duplex = duplex;
+ }
+
+ linkmode_copy(phydev->advertising, advertising);
+
+ linkmode_mod_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+ phydev->advertising, autoneg == AUTONEG_ENABLE);
+
+ phydev->master_slave_set = cmd->base.master_slave_cfg;
+ phydev->mdix_ctrl = cmd->base.eth_tp_mdix_ctrl;
+
+ /* Restart the PHY */
+ _phy_start_aneg(phydev);
+
+ mutex_unlock(&phydev->lock);
+ return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_ksettings_set);
+
/**
* phy_speed_down - set speed to lowest speed supported by both link partners
* @phydev: the phy_device struct
diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index f87f17503373..b554054a7560 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -117,6 +117,7 @@ config USB_LAN78XX
select PHYLIB
select MICROCHIP_PHY
select FIXED_PHY
+ select CRC32
help
This option adds support for Microchip LAN78XX based USB 2
& USB 3 10/100/1000 Ethernet adapters.
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 793f8fbe0069..63cd72c5f580 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -4122,6 +4122,12 @@ static int lan78xx_probe(struct usb_interface *intf,
dev->maxpacket = usb_maxpacket(dev->udev, dev->pipe_out, 1);
+ /* Reject broken descriptors. */
+ if (dev->maxpacket == 0) {
+ ret = -ENODEV;
+ goto out4;
+ }
+
/* driver requires remote-wakeup capability during autosuspend. */
intf->needs_remote_wakeup = 1;
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 840c1c2ab16a..a33d7fb82a00 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1788,6 +1788,11 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
if (!dev->rx_urb_size)
dev->rx_urb_size = dev->hard_mtu;
dev->maxpacket = usb_maxpacket (dev->udev, dev->out, 1);
+ if (dev->maxpacket == 0) {
+ /* that is a broken device */
+ status = -ENODEV;
+ goto out4;
+ }
/* let userspace know we have a random address */
if (ether_addr_equal(net->dev_addr, node_id))
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 142f70670f5c..8799854bacb2 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -3833,7 +3833,6 @@ vmxnet3_suspend(struct device *device)
vmxnet3_free_intr_resources(adapter);
netif_device_detach(netdev);
- netif_tx_stop_all_queues(netdev);
/* Create wake-up filters. */
pmConf = adapter->pm_conf;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index bf2fac913942..662e26117353 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1360,8 +1360,6 @@ static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
bool is_ndisc = ipv6_ndisc_frame(skb);
- nf_reset_ct(skb);
-
/* loopback, multicast & non-ND link-local traffic; do not push through
* packet taps again. Reset pkt_type for upper layers to process skb.
* For strict packets with a source LLA, determine the dst using the
@@ -1424,8 +1422,6 @@ static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
skb->skb_iif = vrf_dev->ifindex;
IPCB(skb)->flags |= IPSKB_L3SLAVE;
- nf_reset_ct(skb);
-
if (ipv4_is_multicast(ip_hdr(skb)->daddr))
goto out;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index e31b98403f31..fc41ba95f81d 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1730,6 +1730,10 @@ static int netfront_resume(struct xenbus_device *dev)
dev_dbg(&dev->dev, "%s\n", dev->nodename);
+ netif_tx_lock_bh(info->netdev);
+ netif_device_detach(info->netdev);
+ netif_tx_unlock_bh(info->netdev);
+
xennet_disconnect_backend(info);
return 0;
}
@@ -2349,6 +2353,10 @@ static int xennet_connect(struct net_device *dev)
* domain a kick because we've probably just requeued some
* packets.
*/
+ netif_tx_lock_bh(np->netdev);
+ netif_device_attach(np->netdev);
+ netif_tx_unlock_bh(np->netdev);
+
netif_carrier_on(np->netdev);
for (j = 0; j < num_queues; ++j) {
queue = &np->queues[j];
diff --git a/drivers/nfc/port100.c b/drivers/nfc/port100.c
index 517376c43b86..16ceb763594f 100644
--- a/drivers/nfc/port100.c
+++ b/drivers/nfc/port100.c
@@ -1006,11 +1006,11 @@ static u64 port100_get_command_type_mask(struct port100 *dev)
skb = port100_alloc_skb(dev, 0);
if (!skb)
- return -ENOMEM;
+ return 0;
resp = port100_send_cmd_sync(dev, PORT100_CMD_GET_COMMAND_TYPE, skb);
if (IS_ERR(resp))
- return PTR_ERR(resp);
+ return 0;
if (resp->len < 8)
mask = 0;
diff --git a/drivers/nfc/st95hf/core.c b/drivers/nfc/st95hf/core.c
index d16cf3ff644e..b23f47936473 100644
--- a/drivers/nfc/st95hf/core.c
+++ b/drivers/nfc/st95hf/core.c
@@ -1226,11 +1226,9 @@ static int st95hf_remove(struct spi_device *nfc_spi_dev)
&reset_cmd,
ST95HF_RESET_CMD_LEN,
ASYNC);
- if (result) {
+ if (result)
dev_err(&spictx->spidev->dev,
"ST95HF reset failed in remove() err = %d\n", result);
- return result;
- }
/* wait for 3 ms to complete the controller reset process */
usleep_range(3000, 4000);
@@ -1239,7 +1237,7 @@ static int st95hf_remove(struct spi_device *nfc_spi_dev)
if (stcontext->st95hf_supply)
regulator_disable(stcontext->st95hf_supply);
- return result;
+ return 0;
}
/* Register as SPI protocol driver */
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index a67a3ad1d413..c74d7bceb222 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -332,26 +332,6 @@ static const struct attribute_group *pmem_attribute_groups[] = {
NULL,
};
-static void pmem_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
- struct pmem_device *pmem = pgmap->owner;
-
- blk_cleanup_disk(pmem->disk);
-}
-
-static void pmem_release_queue(void *pgmap)
-{
- pmem_pagemap_cleanup(pgmap);
-}
-
-static void pmem_pagemap_kill(struct dev_pagemap *pgmap)
-{
- struct request_queue *q =
- container_of(pgmap->ref, struct request_queue, q_usage_counter);
-
- blk_freeze_queue_start(q);
-}
-
static void pmem_release_disk(void *__pmem)
{
struct pmem_device *pmem = __pmem;
@@ -359,12 +339,9 @@ static void pmem_release_disk(void *__pmem)
kill_dax(pmem->dax_dev);
put_dax(pmem->dax_dev);
del_gendisk(pmem->disk);
-}
-static const struct dev_pagemap_ops fsdax_pagemap_ops = {
- .kill = pmem_pagemap_kill,
- .cleanup = pmem_pagemap_cleanup,
-};
+ blk_cleanup_disk(pmem->disk);
+}
static int pmem_attach_disk(struct device *dev,
struct nd_namespace_common *ndns)
@@ -426,10 +403,8 @@ static int pmem_attach_disk(struct device *dev,
pmem->disk = disk;
pmem->pgmap.owner = pmem;
pmem->pfn_flags = PFN_DEV;
- pmem->pgmap.ref = &q->q_usage_counter;
if (is_nd_pfn(dev)) {
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
- pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pfn_sb = nd_pfn->pfn_sb;
pmem->data_offset = le64_to_cpu(pfn_sb->dataoff);
@@ -443,16 +418,12 @@ static int pmem_attach_disk(struct device *dev,
pmem->pgmap.range.end = res->end;
pmem->pgmap.nr_range = 1;
pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
- pmem->pgmap.ops = &fsdax_pagemap_ops;
addr = devm_memremap_pages(dev, &pmem->pgmap);
pmem->pfn_flags |= PFN_MAP;
bb_range = pmem->pgmap.range;
} else {
addr = devm_memremap(dev, pmem->phys_addr,
pmem->size, ARCH_MEMREMAP_PMEM);
- if (devm_add_action_or_reset(dev, pmem_release_queue,
- &pmem->pgmap))
- return -ENOMEM;
bb_range.start = res->start;
bb_range.end = res->end;
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3109bdf137e4..838b5e2058be 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -119,25 +119,6 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
struct nvme_command *cmd);
-/*
- * Prepare a queue for teardown.
- *
- * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
- * the capacity to 0 after that to avoid blocking dispatchers that may be
- * holding bd_butex. This will end buffered writers dirtying pages that can't
- * be synced.
- */
-static void nvme_set_queue_dying(struct nvme_ns *ns)
-{
- if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
- return;
-
- blk_set_queue_dying(ns->queue);
- blk_mq_unquiesce_queue(ns->queue);
-
- set_capacity_and_notify(ns->disk, 0);
-}
-
void nvme_queue_scan(struct nvme_ctrl *ctrl)
{
/*
@@ -222,7 +203,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
{
dev_info(ctrl->device,
- "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn);
+ "Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl));
flush_work(&ctrl->reset_work);
nvme_stop_ctrl(ctrl);
@@ -834,6 +815,7 @@ static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
static inline void nvme_setup_flush(struct nvme_ns *ns,
struct nvme_command *cmnd)
{
+ memset(cmnd, 0, sizeof(*cmnd));
cmnd->common.opcode = nvme_cmd_flush;
cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
}
@@ -885,6 +867,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
return BLK_STS_IOERR;
}
+ memset(cmnd, 0, sizeof(*cmnd));
cmnd->dsm.opcode = nvme_cmd_dsm;
cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
cmnd->dsm.nr = cpu_to_le32(segments - 1);
@@ -901,6 +884,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
struct request *req, struct nvme_command *cmnd)
{
+ memset(cmnd, 0, sizeof(*cmnd));
+
if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
return nvme_setup_discard(ns, req, cmnd);
@@ -934,9 +919,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
cmnd->rw.opcode = op;
+ cmnd->rw.flags = 0;
cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
+ cmnd->rw.rsvd2 = 0;
+ cmnd->rw.metadata = 0;
cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+ cmnd->rw.reftag = 0;
+ cmnd->rw.apptag = 0;
+ cmnd->rw.appmask = 0;
if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);
@@ -993,10 +984,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
blk_status_t ret = BLK_STS_OK;
- if (!(req->rq_flags & RQF_DONTPREP)) {
+ if (!(req->rq_flags & RQF_DONTPREP))
nvme_clear_nvme_request(req);
- memset(cmd, 0, sizeof(*cmd));
- }
switch (req_op(req)) {
case REQ_OP_DRV_IN:
@@ -2612,6 +2601,24 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev,
}
static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);
+static ssize_t nvme_subsys_show_type(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct nvme_subsystem *subsys =
+ container_of(dev, struct nvme_subsystem, dev);
+
+ switch (subsys->subtype) {
+ case NVME_NQN_DISC:
+ return sysfs_emit(buf, "discovery\n");
+ case NVME_NQN_NVME:
+ return sysfs_emit(buf, "nvm\n");
+ default:
+ return sysfs_emit(buf, "reserved\n");
+ }
+}
+static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type);
+
#define nvme_subsys_show_str_function(field) \
static ssize_t subsys_##field##_show(struct device *dev, \
struct device_attribute *attr, char *buf) \
@@ -2632,6 +2639,7 @@ static struct attribute *nvme_subsys_attrs[] = {
&subsys_attr_serial.attr,
&subsys_attr_firmware_rev.attr,
&subsys_attr_subsysnqn.attr,
+ &subsys_attr_subsystype.attr,
#ifdef CONFIG_NVME_MULTIPATH
&subsys_attr_iopolicy.attr,
#endif
@@ -2702,6 +2710,21 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
subsys->vendor_id = le16_to_cpu(id->vid);
subsys->cmic = id->cmic;
+
+ /* Versions prior to 1.4 don't necessarily report a valid type */
+ if (id->cntrltype == NVME_CTRL_DISC ||
+ !strcmp(subsys->subnqn, NVME_DISC_SUBSYS_NAME))
+ subsys->subtype = NVME_NQN_DISC;
+ else
+ subsys->subtype = NVME_NQN_NVME;
+
+ if (nvme_discovery_ctrl(ctrl) && subsys->subtype != NVME_NQN_DISC) {
+ dev_err(ctrl->device,
+ "Subsystem %s is not a discovery controller",
+ subsys->subnqn);
+ kfree(subsys);
+ return -EINVAL;
+ }
subsys->awupf = le16_to_cpu(id->awupf);
#ifdef CONFIG_NVME_MULTIPATH
subsys->iopolicy = NVME_IOPOLICY_NUMA;
@@ -4485,6 +4508,37 @@ out:
}
EXPORT_SYMBOL_GPL(nvme_init_ctrl);
+static void nvme_start_ns_queue(struct nvme_ns *ns)
+{
+ if (test_and_clear_bit(NVME_NS_STOPPED, &ns->flags))
+ blk_mq_unquiesce_queue(ns->queue);
+}
+
+static void nvme_stop_ns_queue(struct nvme_ns *ns)
+{
+ if (!test_and_set_bit(NVME_NS_STOPPED, &ns->flags))
+ blk_mq_quiesce_queue(ns->queue);
+}
+
+/*
+ * Prepare a queue for teardown.
+ *
+ * This must forcibly unquiesce queues to avoid blocking dispatch, and only set
+ * the capacity to 0 after that to avoid blocking dispatchers that may be
+ * holding bd_butex. This will end buffered writers dirtying pages that can't
+ * be synced.
+ */
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+ if (test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+ return;
+
+ blk_set_queue_dying(ns->queue);
+ nvme_start_ns_queue(ns);
+
+ set_capacity_and_notify(ns->disk, 0);
+}
+
/**
* nvme_kill_queues(): Ends all namespace queues
* @ctrl: the dead controller that needs to end
@@ -4500,7 +4554,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
/* Forcibly unquiesce queues to avoid blocking dispatch */
if (ctrl->admin_q && !blk_queue_dying(ctrl->admin_q))
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
list_for_each_entry(ns, &ctrl->namespaces, list)
nvme_set_queue_dying(ns);
@@ -4563,7 +4617,7 @@ void nvme_stop_queues(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_quiesce_queue(ns->queue);
+ nvme_stop_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_stop_queues);
@@ -4574,11 +4628,25 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_unquiesce_queue(ns->queue);
+ nvme_start_ns_queue(ns);
up_read(&ctrl->namespaces_rwsem);
}
EXPORT_SYMBOL_GPL(nvme_start_queues);
+void nvme_stop_admin_queue(struct nvme_ctrl *ctrl)
+{
+ if (!test_and_set_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
+ blk_mq_quiesce_queue(ctrl->admin_q);
+}
+EXPORT_SYMBOL_GPL(nvme_stop_admin_queue);
+
+void nvme_start_admin_queue(struct nvme_ctrl *ctrl)
+{
+ if (test_and_clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->flags))
+ blk_mq_unquiesce_queue(ctrl->admin_q);
+}
+EXPORT_SYMBOL_GPL(nvme_start_admin_queue);
+
void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 668c6bb7a567..c5a2b71c5268 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -548,6 +548,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" },
{ NVMF_OPT_TOS, "tos=%d" },
{ NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" },
+ { NVMF_OPT_DISCOVERY, "discovery" },
{ NVMF_OPT_ERR, NULL }
};
@@ -823,6 +824,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
opts->tos = token;
break;
+ case NVMF_OPT_DISCOVERY:
+ opts->discovery_nqn = true;
+ break;
default:
pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
p);
@@ -949,7 +953,7 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
#define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
- NVMF_OPT_DISABLE_SQFLOW |\
+ NVMF_OPT_DISABLE_SQFLOW | NVMF_OPT_DISCOVERY |\
NVMF_OPT_FAIL_FAST_TMO)
static struct nvme_ctrl *
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index a146cb903869..c3203ff1c654 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -67,6 +67,7 @@ enum {
NVMF_OPT_TOS = 1 << 19,
NVMF_OPT_FAIL_FAST_TMO = 1 << 20,
NVMF_OPT_HOST_IFACE = 1 << 21,
+ NVMF_OPT_DISCOVERY = 1 << 22,
};
/**
@@ -178,6 +179,13 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
return true;
}
+static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl)
+{
+ if (!ctrl->subsys)
+ return ctrl->opts->subsysnqn;
+ return ctrl->subsys->subnqn;
+}
+
int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index aa14ad963d91..71b3108c22f0 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -16,6 +16,7 @@
#include <linux/nvme-fc.h>
#include "fc.h"
#include <scsi/scsi_transport_fc.h>
+#include <linux/blk-mq-pci.h>
/* *************************** Data Structures/Defines ****************** */
@@ -2382,7 +2383,7 @@ nvme_fc_ctrl_free(struct kref *ref)
list_del(&ctrl->ctrl_list);
spin_unlock_irqrestore(&ctrl->rport->lock, flags);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
blk_cleanup_queue(ctrl->ctrl.admin_q);
blk_cleanup_queue(ctrl->ctrl.fabrics_q);
blk_mq_free_tag_set(&ctrl->admin_tag_set);
@@ -2510,7 +2511,7 @@ __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
/*
* clean up the admin queue. Same thing as above.
*/
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_fc_terminate_exchange, &ctrl->ctrl);
@@ -2841,6 +2842,28 @@ nvme_fc_complete_rq(struct request *rq)
nvme_fc_ctrl_put(ctrl);
}
+static int nvme_fc_map_queues(struct blk_mq_tag_set *set)
+{
+ struct nvme_fc_ctrl *ctrl = set->driver_data;
+ int i;
+
+ for (i = 0; i < set->nr_maps; i++) {
+ struct blk_mq_queue_map *map = &set->map[i];
+
+ if (!map->nr_queues) {
+ WARN_ON(i == HCTX_TYPE_DEFAULT);
+ continue;
+ }
+
+ /* Call LLDD map queue functionality if defined */
+ if (ctrl->lport->ops->map_queues)
+ ctrl->lport->ops->map_queues(&ctrl->lport->localport,
+ map);
+ else
+ blk_mq_map_queues(map);
+ }
+ return 0;
+}
static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
@@ -2849,6 +2872,7 @@ static const struct blk_mq_ops nvme_fc_mq_ops = {
.exit_request = nvme_fc_exit_request,
.init_hctx = nvme_fc_init_hctx,
.timeout = nvme_fc_timeout,
+ .map_queues = nvme_fc_map_queues,
};
static int
@@ -3095,7 +3119,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
ctrl->ctrl.max_hw_sectors = ctrl->ctrl.max_segments <<
(ilog2(SZ_4K) - 9);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
ret = nvme_init_ctrl_finish(&ctrl->ctrl);
if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
@@ -3249,7 +3273,7 @@ nvme_fc_delete_association(struct nvme_fc_ctrl *ctrl)
nvme_fc_free_queue(&ctrl->queues[0]);
/* re-enable the admin_q so anything new can fast fail */
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
/* resume the io queues so that things will fast fail */
nvme_start_queues(&ctrl->ctrl);
@@ -3572,7 +3596,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
dev_info(ctrl->ctrl.device,
"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
- ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
+ ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
return &ctrl->ctrl;
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 11440c86881e..7f2071f2460c 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -105,8 +105,11 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list) {
- if (ns->head->disk)
- kblockd_schedule_work(&ns->head->requeue_work);
+ if (!ns->head->disk)
+ continue;
+ kblockd_schedule_work(&ns->head->requeue_work);
+ if (ctrl->state == NVME_CTRL_LIVE)
+ disk_uevent(ns->head->disk, KOBJ_CHANGE);
}
up_read(&ctrl->namespaces_rwsem);
}
@@ -143,13 +146,12 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
struct nvme_ns *ns;
- mutex_lock(&ctrl->scan_lock);
down_read(&ctrl->namespaces_rwsem);
- list_for_each_entry(ns, &ctrl->namespaces, list)
- if (nvme_mpath_clear_current_path(ns))
- kblockd_schedule_work(&ns->head->requeue_work);
+ list_for_each_entry(ns, &ctrl->namespaces, list) {
+ nvme_mpath_clear_current_path(ns);
+ kblockd_schedule_work(&ns->head->requeue_work);
+ }
up_read(&ctrl->namespaces_rwsem);
- mutex_unlock(&ctrl->scan_lock);
}
void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -506,13 +508,23 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
static void nvme_mpath_set_live(struct nvme_ns *ns)
{
struct nvme_ns_head *head = ns->head;
+ int rc;
if (!head->disk)
return;
+ /*
+ * test_and_set_bit() is used because it is protecting against two nvme
+ * paths simultaneously calling device_add_disk() on the same namespace
+ * head.
+ */
if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
- device_add_disk(&head->subsys->dev, head->disk,
- nvme_ns_id_attr_groups);
+ rc = device_add_disk(&head->subsys->dev, head->disk,
+ nvme_ns_id_attr_groups);
+ if (rc) {
+ clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+ return;
+ }
nvme_add_ns_head_cdev(head);
}
@@ -550,7 +562,7 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
return -EINVAL;
nr_nsids = le32_to_cpu(desc->nnsids);
- nsid_buf_size = nr_nsids * sizeof(__le32);
+ nsid_buf_size = flex_array_size(desc, nsids, nr_nsids);
if (WARN_ON_ONCE(desc->grpid == 0))
return -EINVAL;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ef2467b93adb..b334af8aa264 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -342,6 +342,7 @@ struct nvme_ctrl {
int nr_reconnects;
unsigned long flags;
#define NVME_CTRL_FAILFAST_EXPIRED 0
+#define NVME_CTRL_ADMIN_Q_STOPPED 1
struct nvmf_ctrl_options *opts;
struct page *discard_page;
@@ -372,6 +373,7 @@ struct nvme_subsystem {
char model[40];
char firmware_rev[8];
u8 cmic;
+ enum nvme_subsys_type subtype;
u16 vendor_id;
u16 awupf; /* 0's based awupf value. */
struct ida ns_ida;
@@ -463,6 +465,7 @@ struct nvme_ns {
#define NVME_NS_ANA_PENDING 2
#define NVME_NS_FORCE_RO 3
#define NVME_NS_READY 4
+#define NVME_NS_STOPPED 5
struct cdev cdev;
struct device cdev_device;
@@ -679,6 +682,8 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
void nvme_stop_queues(struct nvme_ctrl *ctrl);
void nvme_start_queues(struct nvme_ctrl *ctrl);
+void nvme_stop_admin_queue(struct nvme_ctrl *ctrl);
+void nvme_start_admin_queue(struct nvme_ctrl *ctrl);
void nvme_kill_queues(struct nvme_ctrl *ctrl);
void nvme_sync_queues(struct nvme_ctrl *ctrl);
void nvme_sync_io_queues(struct nvme_ctrl *ctrl);
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ed684874842f..ca2ee806d74b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -245,8 +245,15 @@ static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
{
unsigned int mem_size = nvme_dbbuf_size(dev);
- if (dev->dbbuf_dbs)
+ if (dev->dbbuf_dbs) {
+ /*
+ * Clear the dbbuf memory so the driver doesn't observe stale
+ * values from the previous instantiation.
+ */
+ memset(dev->dbbuf_dbs, 0, mem_size);
+ memset(dev->dbbuf_eis, 0, mem_size);
return 0;
+ }
dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
&dev->dbbuf_dbs_dma_addr,
@@ -1414,7 +1421,7 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq)
nvmeq->dev->online_queues--;
if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q)
- blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q);
+ nvme_stop_admin_queue(&nvmeq->dev->ctrl);
if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags))
pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq);
return 0;
@@ -1673,7 +1680,7 @@ static void nvme_dev_remove_admin(struct nvme_dev *dev)
* user requests may be waiting on a stopped queue. Start the
* queue to flush these to completion.
*/
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
blk_cleanup_queue(dev->ctrl.admin_q);
blk_mq_free_tag_set(&dev->admin_tagset);
}
@@ -1707,7 +1714,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
return -ENODEV;
}
} else
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
return 0;
}
@@ -2642,7 +2649,7 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
if (shutdown) {
nvme_start_queues(&dev->ctrl);
if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
- blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+ nvme_start_admin_queue(&dev->ctrl);
}
mutex_unlock(&dev->shutdown_lock);
}
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 1624da3702d4..850f84d204d0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -919,7 +919,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
else
ctrl->ctrl.max_integrity_segments = 0;
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
error = nvme_init_ctrl_finish(&ctrl->ctrl);
if (error)
@@ -928,7 +928,7 @@ static int nvme_rdma_configure_admin_queue(struct nvme_rdma_ctrl *ctrl,
return 0;
out_quiesce_queue:
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
out_stop_queue:
nvme_rdma_stop_queue(&ctrl->queues[0]);
@@ -1026,12 +1026,12 @@ out_free_io_queues:
static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
bool remove)
{
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_cancel_admin_tagset(&ctrl->ctrl);
if (remove)
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
nvme_rdma_destroy_admin_queue(ctrl, remove);
}
@@ -1096,11 +1096,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
return ret;
if (ctrl->ctrl.icdoff) {
+ ret = -EOPNOTSUPP;
dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
goto destroy_admin;
}
if (!(ctrl->ctrl.sgls & (1 << 2))) {
+ ret = -EOPNOTSUPP;
dev_err(ctrl->ctrl.device,
"Mandatory keyed sgls are not supported!\n");
goto destroy_admin;
@@ -1112,6 +1114,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
}
+ if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+ dev_warn(ctrl->ctrl.device,
+ "ctrl sqsize %u > max queue size %u, clamping down\n",
+ ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
+ ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+ }
+
if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
dev_warn(ctrl->ctrl.device,
"sqsize %u > ctrl maxcmd %u, clamping down\n",
@@ -1154,7 +1163,7 @@ destroy_io:
nvme_rdma_destroy_io_queues(ctrl, new);
}
destroy_admin:
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
blk_sync_queue(ctrl->ctrl.admin_q);
nvme_rdma_stop_queue(&ctrl->queues[0]);
nvme_cancel_admin_tagset(&ctrl->ctrl);
@@ -1194,7 +1203,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
nvme_rdma_teardown_io_queues(ctrl, false);
nvme_start_queues(&ctrl->ctrl);
nvme_rdma_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we started ctrl delete */
@@ -2232,7 +2241,7 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&ctrl->reconnect_work);
nvme_rdma_teardown_io_queues(ctrl, shutdown);
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
if (shutdown)
nvme_shutdown_ctrl(&ctrl->ctrl);
else
@@ -2386,7 +2395,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
goto out_uninit_ctrl;
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
- ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
mutex_lock(&nvme_rdma_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 9ce3458ee1dd..33bc83d8d992 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -926,12 +926,14 @@ static void nvme_tcp_fail_request(struct nvme_tcp_request *req)
static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
{
struct nvme_tcp_queue *queue = req->queue;
+ int req_data_len = req->data_len;
while (true) {
struct page *page = nvme_tcp_req_cur_page(req);
size_t offset = nvme_tcp_req_cur_offset(req);
size_t len = nvme_tcp_req_cur_length(req);
bool last = nvme_tcp_pdu_last_send(req, len);
+ int req_data_sent = req->data_sent;
int ret, flags = MSG_DONTWAIT;
if (last && !queue->data_digest && !nvme_tcp_queue_more(queue))
@@ -958,7 +960,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
* in the request where we don't want to modify it as we may
* compete with the RX path completing the request.
*/
- if (req->data_sent + ret < req->data_len)
+ if (req_data_sent + ret < req_data_len)
nvme_tcp_advance_req(req, ret);
/* fully successful last send in current PDU */
@@ -1048,10 +1050,11 @@ static int nvme_tcp_try_send_data_pdu(struct nvme_tcp_request *req)
static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
{
struct nvme_tcp_queue *queue = req->queue;
+ size_t offset = req->offset;
int ret;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
- .iov_base = &req->ddgst + req->offset,
+ .iov_base = (u8 *)&req->ddgst + req->offset,
.iov_len = NVME_TCP_DIGEST_LENGTH - req->offset
};
@@ -1064,7 +1067,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
if (unlikely(ret <= 0))
return ret;
- if (req->offset + ret == NVME_TCP_DIGEST_LENGTH) {
+ if (offset + ret == NVME_TCP_DIGEST_LENGTH) {
nvme_tcp_done_send_req(queue);
return 1;
}
@@ -1915,7 +1918,7 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
if (error)
goto out_stop_queue;
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
error = nvme_init_ctrl_finish(ctrl);
if (error)
@@ -1924,7 +1927,7 @@ static int nvme_tcp_configure_admin_queue(struct nvme_ctrl *ctrl, bool new)
return 0;
out_quiesce_queue:
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
out_stop_queue:
nvme_tcp_stop_queue(ctrl, 0);
@@ -1946,12 +1949,12 @@ out_free_queue:
static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl,
bool remove)
{
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
nvme_cancel_admin_tagset(ctrl);
if (remove)
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
nvme_tcp_destroy_admin_queue(ctrl, remove);
}
@@ -1960,7 +1963,7 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
{
if (ctrl->queue_count <= 1)
return;
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
nvme_start_freeze(ctrl);
nvme_stop_queues(ctrl);
nvme_sync_io_queues(ctrl);
@@ -2055,7 +2058,7 @@ destroy_io:
nvme_tcp_destroy_io_queues(ctrl, new);
}
destroy_admin:
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
blk_sync_queue(ctrl->admin_q);
nvme_tcp_stop_queue(ctrl, 0);
nvme_cancel_admin_tagset(ctrl);
@@ -2098,7 +2101,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
/* unquiesce to fail fast pending requests */
nvme_start_queues(ctrl);
nvme_tcp_teardown_admin_queue(ctrl, false);
- blk_mq_unquiesce_queue(ctrl->admin_q);
+ nvme_start_admin_queue(ctrl);
if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_CONNECTING)) {
/* state change failure is ok if we started ctrl delete */
@@ -2116,7 +2119,7 @@ static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work);
nvme_tcp_teardown_io_queues(ctrl, shutdown);
- blk_mq_quiesce_queue(ctrl->admin_q);
+ nvme_stop_admin_queue(ctrl);
if (shutdown)
nvme_shutdown_ctrl(ctrl);
else
@@ -2582,7 +2585,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
goto out_uninit_ctrl;
dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
- ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+ nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
mutex_lock(&nvme_tcp_ctrl_mutex);
list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index d95010481fce..bfc259e0d7b8 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -233,6 +233,8 @@ out_free:
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *c, enum nvme_zone_mgmt_action action)
{
+ memset(c, 0, sizeof(*c));
+
c->zms.opcode = nvme_cmd_zone_mgmt_send;
c->zms.nsid = cpu_to_le32(ns->head->ns_id);
c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index aa6d84d8848e..6fb24746de06 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -264,7 +264,7 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
desc->state = req->port->ana_state[grpid];
memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
- return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+ return struct_size(desc, nsids, count);
}
static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
@@ -278,8 +278,8 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
u16 status;
status = NVME_SC_INTERNAL;
- desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
- NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+ desc = kmalloc(struct_size(desc, nsids, NVMET_MAX_NAMESPACES),
+ GFP_KERNEL);
if (!desc)
goto out;
@@ -374,13 +374,19 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
id->rab = 6;
+ if (nvmet_is_disc_subsys(ctrl->subsys))
+ id->cntrltype = NVME_CTRL_DISC;
+ else
+ id->cntrltype = NVME_CTRL_IO;
+
/*
* XXX: figure out how we can assign a IEEE OUI, but until then
* the safest is to leave it as zeroes.
*/
/* we support multiple ports, multiples hosts and ANA: */
- id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
+ id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL |
+ NVME_CTRL_CMIC_ANA;
/* Limit MDTS according to transport capability */
if (ctrl->ops->get_mdts)
@@ -536,7 +542,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
* Our namespace might always be shared. Not just with other
* controllers, but also with any other user of the block device.
*/
- id->nmic = (1 << 0);
+ id->nmic = NVME_NS_NMIC_SHARED;
id->anagrpid = cpu_to_le32(req->ns->anagrpid);
memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));
@@ -1008,7 +1014,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
if (nvme_is_fabrics(cmd))
return nvmet_parse_fabrics_cmd(req);
- if (nvmet_req_subsys(req)->type == NVME_NQN_DISC)
+ if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
return nvmet_parse_discovery_cmd(req);
ret = nvmet_check_ctrl_status(req);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index be5d82421e3a..091a0ca16361 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1233,6 +1233,44 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
}
CONFIGFS_ATTR(nvmet_subsys_, attr_model);
+static ssize_t nvmet_subsys_attr_discovery_nqn_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%s\n",
+ nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_subsys_attr_discovery_nqn_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct nvmet_subsys *subsys = to_subsys(item);
+ char *subsysnqn;
+ int len;
+
+ len = strcspn(page, "\n");
+ if (!len)
+ return -EINVAL;
+
+ subsysnqn = kmemdup_nul(page, len, GFP_KERNEL);
+ if (!subsysnqn)
+ return -ENOMEM;
+
+ /*
+ * The discovery NQN must be different from subsystem NQN.
+ */
+ if (!strcmp(subsysnqn, subsys->subsysnqn)) {
+ kfree(subsysnqn);
+ return -EBUSY;
+ }
+ down_write(&nvmet_config_sem);
+ kfree(nvmet_disc_subsys->subsysnqn);
+ nvmet_disc_subsys->subsysnqn = subsysnqn;
+ up_write(&nvmet_config_sem);
+
+ return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_discovery_nqn);
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
static ssize_t nvmet_subsys_attr_pi_enable_show(struct config_item *item,
char *page)
@@ -1262,6 +1300,7 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = {
&nvmet_subsys_attr_attr_cntlid_min,
&nvmet_subsys_attr_attr_cntlid_max,
&nvmet_subsys_attr_attr_model,
+ &nvmet_subsys_attr_attr_discovery_nqn,
#ifdef CONFIG_BLK_DEV_INTEGRITY
&nvmet_subsys_attr_attr_pi_enable,
#endif
@@ -1553,6 +1592,8 @@ static void nvmet_port_release(struct config_item *item)
{
struct nvmet_port *port = to_nvmet_port(item);
+ /* Let inflight controllers teardown complete */
+ flush_scheduled_work();
list_del(&port->global_entry);
kfree(port->ana_state);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b8425fa34300..5119c687de68 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1140,7 +1140,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
* should verify iosqes,iocqes are zeroed, however that
* would break backwards compatibility, so don't enforce it.
*/
- if (ctrl->subsys->type != NVME_NQN_DISC &&
+ if (!nvmet_is_disc_subsys(ctrl->subsys) &&
(nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
ctrl->csts = NVME_CSTS_CFS;
@@ -1205,7 +1205,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
/* CC.EN timeout in 500msec units: */
ctrl->cap |= (15ULL << 24);
/* maximum queue entries supported: */
- ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+ if (ctrl->ops->get_max_queue_size)
+ ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+ else
+ ctrl->cap |= NVMET_QUEUE_SIZE - 1;
if (nvmet_is_passthru_subsys(ctrl->subsys))
nvmet_passthrough_override_cap(ctrl);
@@ -1278,7 +1281,7 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn)
if (subsys->allow_any_host)
return true;
- if (subsys->type == NVME_NQN_DISC) /* allow all access to disc subsys */
+ if (nvmet_is_disc_subsys(subsys)) /* allow all access to disc subsys */
return true;
list_for_each_entry(p, &subsys->hosts, entry) {
@@ -1367,6 +1370,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
mutex_init(&ctrl->lock);
ctrl->port = req->port;
+ ctrl->ops = req->ops;
INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
INIT_LIST_HEAD(&ctrl->async_events);
@@ -1405,13 +1409,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
}
ctrl->cntlid = ret;
- ctrl->ops = req->ops;
-
/*
* Discovery controllers may use some arbitrary high value
* in order to cleanup stale discovery sessions
*/
- if ((ctrl->subsys->type == NVME_NQN_DISC) && !kato)
+ if (nvmet_is_disc_subsys(ctrl->subsys) && !kato)
kato = NVMET_DISC_KATO_MS;
/* keep-alive timeout in seconds */
@@ -1491,7 +1493,8 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
if (!port)
return NULL;
- if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn)) {
+ if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn) ||
+ !strcmp(nvmet_disc_subsys->subsysnqn, subsysnqn)) {
if (!kref_get_unless_zero(&nvmet_disc_subsys->ref))
return NULL;
return nvmet_disc_subsys;
@@ -1538,6 +1541,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
subsys->max_qid = NVMET_NR_QUEUES;
break;
case NVME_NQN_DISC:
+ case NVME_NQN_CURR:
subsys->max_qid = 0;
break;
default:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 7aa62bc6ae84..c2162eef8ce1 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -146,7 +146,7 @@ static size_t discovery_log_entries(struct nvmet_req *req)
struct nvmet_ctrl *ctrl = req->sq->ctrl;
struct nvmet_subsys_link *p;
struct nvmet_port *r;
- size_t entries = 0;
+ size_t entries = 1;
list_for_each_entry(p, &req->port->subsystems, entry) {
if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
@@ -171,6 +171,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
u32 numrec = 0;
u16 status = 0;
void *buffer;
+ char traddr[NVMF_TRADDR_SIZE];
if (!nvmet_check_transfer_len(req, data_len))
return;
@@ -203,15 +204,19 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
status = NVME_SC_INTERNAL;
goto out;
}
-
hdr = buffer;
- list_for_each_entry(p, &req->port->subsystems, entry) {
- char traddr[NVMF_TRADDR_SIZE];
+ nvmet_set_disc_traddr(req, req->port, traddr);
+
+ nvmet_format_discovery_entry(hdr, req->port,
+ nvmet_disc_subsys->subsysnqn,
+ traddr, NVME_NQN_CURR, numrec);
+ numrec++;
+
+ list_for_each_entry(p, &req->port->subsystems, entry) {
if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
continue;
- nvmet_set_disc_traddr(req, req->port, traddr);
nvmet_format_discovery_entry(hdr, req->port,
p->subsys->subsysnqn, traddr,
NVME_NQN_NVME, numrec);
@@ -268,6 +273,8 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
memcpy_and_pad(id->fr, sizeof(id->fr),
UTS_RELEASE, strlen(UTS_RELEASE), ' ');
+ id->cntrltype = NVME_CTRL_DISC;
+
/* no limit on data transfer sizes for now */
id->mdts = 0;
id->cntlid = cpu_to_le16(ctrl->cntlid);
@@ -387,7 +394,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
int __init nvmet_init_discovery(void)
{
nvmet_disc_subsys =
- nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
+ nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_CURR);
return PTR_ERR_OR_ZERO(nvmet_disc_subsys);
}
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 7d0454cee920..70fb587e9413 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -221,7 +221,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
goto out;
}
- pr_info("creating controller %d for subsystem %s for NQN %s%s.\n",
+ pr_info("creating %s controller %d for subsystem %s for NQN %s%s.\n",
+ nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm",
ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn,
ctrl->pi_support ? " T10-PI is enabled" : "");
req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index 0285ccc7541f..eb1094254c82 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -384,6 +384,8 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
error = PTR_ERR(ctrl->ctrl.admin_q);
goto out_cleanup_fabrics_q;
}
+ /* reset stopped state for the fresh admin queue */
+ clear_bit(NVME_CTRL_ADMIN_Q_STOPPED, &ctrl->ctrl.flags);
error = nvmf_connect_admin_queue(&ctrl->ctrl);
if (error)
@@ -398,7 +400,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
ctrl->ctrl.max_hw_sectors =
(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
- blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+ nvme_start_admin_queue(&ctrl->ctrl);
error = nvme_init_ctrl_finish(&ctrl->ctrl);
if (error)
@@ -428,7 +430,7 @@ static void nvme_loop_shutdown_ctrl(struct nvme_loop_ctrl *ctrl)
nvme_loop_destroy_io_queues(ctrl);
}
- blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+ nvme_stop_admin_queue(&ctrl->ctrl);
if (ctrl->ctrl.state == NVME_CTRL_LIVE)
nvme_shutdown_ctrl(&ctrl->ctrl);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7143c7fa7464..af193423c10b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -309,6 +309,7 @@ struct nvmet_fabrics_ops {
u16 (*install_queue)(struct nvmet_sq *nvme_sq);
void (*discovery_chg)(struct nvmet_port *port);
u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
+ u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl);
};
#define NVMET_MAX_INLINE_BIOVEC 8
@@ -576,6 +577,11 @@ static inline struct nvmet_subsys *nvmet_req_subsys(struct nvmet_req *req)
return req->sq->ctrl->subsys;
}
+static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys)
+{
+ return subsys->type != NVME_NQN_NVME;
+}
+
#ifdef CONFIG_NVME_TARGET_PASSTHRU
void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys);
int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 38d1f292ecc2..1deb4043e242 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1819,12 +1819,36 @@ restart:
mutex_unlock(&nvmet_rdma_queue_mutex);
}
+static void nvmet_rdma_destroy_port_queues(struct nvmet_rdma_port *port)
+{
+ struct nvmet_rdma_queue *queue, *tmp;
+ struct nvmet_port *nport = port->nport;
+
+ mutex_lock(&nvmet_rdma_queue_mutex);
+ list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+ queue_list) {
+ if (queue->port != nport)
+ continue;
+
+ list_del_init(&queue->queue_list);
+ __nvmet_rdma_queue_disconnect(queue);
+ }
+ mutex_unlock(&nvmet_rdma_queue_mutex);
+}
+
static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port)
{
struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL);
if (cm_id)
rdma_destroy_id(cm_id);
+
+ /*
+ * Destroy the remaining queues, which are not belong to any
+ * controller yet. Do it here after the RDMA-CM was destroyed
+ * guarantees that no new queue will be created.
+ */
+ nvmet_rdma_destroy_port_queues(port);
}
static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
@@ -1976,6 +2000,11 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
return NVMET_RDMA_MAX_MDTS;
}
+static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
+{
+ return NVME_RDMA_MAX_QUEUE_SIZE;
+}
+
static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.owner = THIS_MODULE,
.type = NVMF_TRTYPE_RDMA,
@@ -1987,6 +2016,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
.delete_ctrl = nvmet_rdma_delete_ctrl,
.disc_traddr = nvmet_rdma_disc_port_addr,
.get_mdts = nvmet_rdma_get_mdts,
+ .get_max_queue_size = nvmet_rdma_get_max_queue_size,
};
static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 07ee347ea3f3..84c387e4bf43 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -702,7 +702,7 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd, bool last_in_batch)
struct nvmet_tcp_queue *queue = cmd->queue;
struct msghdr msg = { .msg_flags = MSG_DONTWAIT };
struct kvec iov = {
- .iov_base = &cmd->exp_ddgst + cmd->offset,
+ .iov_base = (u8 *)&cmd->exp_ddgst + cmd->offset,
.iov_len = NVME_TCP_DIGEST_LENGTH - cmd->offset
};
int ret;
@@ -1096,7 +1096,7 @@ recv:
}
if (queue->hdr_digest &&
- nvmet_tcp_verify_hdgst(queue, &queue->pdu, queue->offset)) {
+ nvmet_tcp_verify_hdgst(queue, &queue->pdu, hdr->hlen)) {
nvmet_tcp_fatal_error(queue); /* fatal */
return -EPROTO;
}
@@ -1428,6 +1428,7 @@ static void nvmet_tcp_uninit_data_in_cmds(struct nvmet_tcp_queue *queue)
static void nvmet_tcp_release_queue_work(struct work_struct *w)
{
+ struct page *page;
struct nvmet_tcp_queue *queue =
container_of(w, struct nvmet_tcp_queue, release_work);
@@ -1447,6 +1448,8 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w)
nvmet_tcp_free_crypto(queue);
ida_simple_remove(&nvmet_tcp_queue_ida, queue->idx);
+ page = virt_to_head_page(queue->pf_cache.va);
+ __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
kfree(queue);
}
@@ -1737,6 +1740,17 @@ err_port:
return ret;
}
+static void nvmet_tcp_destroy_port_queues(struct nvmet_tcp_port *port)
+{
+ struct nvmet_tcp_queue *queue;
+
+ mutex_lock(&nvmet_tcp_queue_mutex);
+ list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
+ if (queue->port == port)
+ kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+ mutex_unlock(&nvmet_tcp_queue_mutex);
+}
+
static void nvmet_tcp_remove_port(struct nvmet_port *nport)
{
struct nvmet_tcp_port *port = nport->priv;
@@ -1746,6 +1760,11 @@ static void nvmet_tcp_remove_port(struct nvmet_port *nport)
port->sock->sk->sk_user_data = NULL;
write_unlock_bh(&port->sock->sk->sk_callback_lock);
cancel_work_sync(&port->accept_work);
+ /*
+ * Destroy the remaining queues, which are not belong to any
+ * controller yet.
+ */
+ nvmet_tcp_destroy_port_queues(port);
sock_release(port->sock);
kfree(port);
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 59c1390cdf42..9da8835ba5a5 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -21,6 +21,7 @@
#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/memblock.h>
+#include <linux/kmemleak.h>
#include "of_private.h"
@@ -46,6 +47,7 @@ static int __init early_init_dt_alloc_reserved_memory_arch(phys_addr_t size,
err = memblock_mark_nomap(base, size);
if (err)
memblock_free(base, size);
+ kmemleak_ignore_phys(base);
}
return err;
diff --git a/drivers/pinctrl/bcm/pinctrl-ns.c b/drivers/pinctrl/bcm/pinctrl-ns.c
index e79690bd8b85..d7f8175d2c1c 100644
--- a/drivers/pinctrl/bcm/pinctrl-ns.c
+++ b/drivers/pinctrl/bcm/pinctrl-ns.c
@@ -5,7 +5,6 @@
#include <linux/err.h>
#include <linux/io.h>
-#include <linux/mfd/syscon.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_device.h>
@@ -13,7 +12,6 @@
#include <linux/pinctrl/pinctrl.h>
#include <linux/pinctrl/pinmux.h>
#include <linux/platform_device.h>
-#include <linux/regmap.h>
#include <linux/slab.h>
#define FLAG_BCM4708 BIT(1)
@@ -24,8 +22,7 @@ struct ns_pinctrl {
struct device *dev;
unsigned int chipset_flag;
struct pinctrl_dev *pctldev;
- struct regmap *regmap;
- u32 offset;
+ void __iomem *base;
struct pinctrl_desc pctldesc;
struct ns_pinctrl_group *groups;
@@ -232,9 +229,9 @@ static int ns_pinctrl_set_mux(struct pinctrl_dev *pctrl_dev,
unset |= BIT(pin_number);
}
- regmap_read(ns_pinctrl->regmap, ns_pinctrl->offset, &tmp);
+ tmp = readl(ns_pinctrl->base);
tmp &= ~unset;
- regmap_write(ns_pinctrl->regmap, ns_pinctrl->offset, tmp);
+ writel(tmp, ns_pinctrl->base);
return 0;
}
@@ -266,13 +263,13 @@ static const struct of_device_id ns_pinctrl_of_match_table[] = {
static int ns_pinctrl_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
- struct device_node *np = dev->of_node;
const struct of_device_id *of_id;
struct ns_pinctrl *ns_pinctrl;
struct pinctrl_desc *pctldesc;
struct pinctrl_pin_desc *pin;
struct ns_pinctrl_group *group;
struct ns_pinctrl_function *function;
+ struct resource *res;
int i;
ns_pinctrl = devm_kzalloc(dev, sizeof(*ns_pinctrl), GFP_KERNEL);
@@ -290,18 +287,12 @@ static int ns_pinctrl_probe(struct platform_device *pdev)
return -EINVAL;
ns_pinctrl->chipset_flag = (uintptr_t)of_id->data;
- ns_pinctrl->regmap = syscon_node_to_regmap(of_get_parent(np));
- if (IS_ERR(ns_pinctrl->regmap)) {
- int err = PTR_ERR(ns_pinctrl->regmap);
-
- dev_err(dev, "Failed to map pinctrl regs: %d\n", err);
-
- return err;
- }
-
- if (of_property_read_u32(np, "offset", &ns_pinctrl->offset)) {
- dev_err(dev, "Failed to get register offset\n");
- return -ENOENT;
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+ "cru_gpio_control");
+ ns_pinctrl->base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(ns_pinctrl->base)) {
+ dev_err(dev, "Failed to map pinctrl regs\n");
+ return PTR_ERR(ns_pinctrl->base);
}
memcpy(pctldesc, &ns_pinctrl_desc, sizeof(*pctldesc));
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 8d0f88e9ca88..bae9d429b813 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -840,6 +840,34 @@ static const struct pinconf_ops amd_pinconf_ops = {
.pin_config_group_set = amd_pinconf_group_set,
};
+static void amd_gpio_irq_init(struct amd_gpio *gpio_dev)
+{
+ struct pinctrl_desc *desc = gpio_dev->pctrl->desc;
+ unsigned long flags;
+ u32 pin_reg, mask;
+ int i;
+
+ mask = BIT(WAKE_CNTRL_OFF_S0I3) | BIT(WAKE_CNTRL_OFF_S3) |
+ BIT(INTERRUPT_MASK_OFF) | BIT(INTERRUPT_ENABLE_OFF) |
+ BIT(WAKE_CNTRL_OFF_S4);
+
+ for (i = 0; i < desc->npins; i++) {
+ int pin = desc->pins[i].number;
+ const struct pin_desc *pd = pin_desc_get(gpio_dev->pctrl, pin);
+
+ if (!pd)
+ continue;
+
+ raw_spin_lock_irqsave(&gpio_dev->lock, flags);
+
+ pin_reg = readl(gpio_dev->base + i * 4);
+ pin_reg &= ~mask;
+ writel(pin_reg, gpio_dev->base + i * 4);
+
+ raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
+ }
+}
+
#ifdef CONFIG_PM_SLEEP
static bool amd_gpio_should_save(struct amd_gpio *gpio_dev, unsigned int pin)
{
@@ -976,6 +1004,9 @@ static int amd_gpio_probe(struct platform_device *pdev)
return PTR_ERR(gpio_dev->pctrl);
}
+ /* Disable and mask interrupts */
+ amd_gpio_irq_init(gpio_dev);
+
girq = &gpio_dev->gc.irq;
girq->chip = &amd_gpio_irqchip;
/* This will let us handle the parent IRQ in the driver */
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 68b3886f9f0f..dfd8888a222a 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -1644,8 +1644,8 @@ int __maybe_unused stm32_pinctrl_resume(struct device *dev)
struct stm32_pinctrl_group *g = pctl->groups;
int i;
- for (i = g->pin; i < g->pin + pctl->ngroups; i++)
- stm32_pinctrl_restore_gpio_regs(pctl, i);
+ for (i = 0; i < pctl->ngroups; i++, g++)
+ stm32_pinctrl_restore_gpio_regs(pctl, g->pin);
return 0;
}
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 4dfc52e06704..f9b2d66b0443 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -170,6 +170,7 @@ static void ptp_clock_release(struct device *dev)
struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
ptp_cleanup_pin_groups(ptp);
+ kfree(ptp->vclock_index);
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
mutex_destroy(&ptp->n_vclocks_mux);
@@ -283,15 +284,20 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
/* Create a posix clock and link it to the device. */
err = posix_clock_register(&ptp->clock, &ptp->dev);
if (err) {
+ if (ptp->pps_source)
+ pps_unregister_source(ptp->pps_source);
+
+ if (ptp->kworker)
+ kthread_destroy_worker(ptp->kworker);
+
+ put_device(&ptp->dev);
+
pr_err("failed to create posix clock\n");
- goto no_clock;
+ return ERR_PTR(err);
}
return ptp;
-no_clock:
- if (ptp->pps_source)
- pps_unregister_source(ptp->pps_source);
no_pps:
ptp_cleanup_pin_groups(ptp);
no_pin_groups:
@@ -321,8 +327,6 @@ int ptp_clock_unregister(struct ptp_clock *ptp)
ptp->defunct = 1;
wake_up_interruptible(&ptp->tsev_wq);
- kfree(ptp->vclock_index);
-
if (ptp->kworker) {
kthread_cancel_delayed_work_sync(&ptp->aux_work);
kthread_destroy_worker(ptp->kworker);
diff --git a/drivers/ptp/ptp_kvm_x86.c b/drivers/ptp/ptp_kvm_x86.c
index d0096cd7096a..4991054a2135 100644
--- a/drivers/ptp/ptp_kvm_x86.c
+++ b/drivers/ptp/ptp_kvm_x86.c
@@ -31,10 +31,10 @@ int kvm_arch_ptp_init(void)
ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa,
KVM_CLOCK_PAIRING_WALLCLOCK);
- if (ret == -KVM_ENOSYS || ret == -KVM_EOPNOTSUPP)
+ if (ret == -KVM_ENOSYS)
return -ENODEV;
- return 0;
+ return ret;
}
int kvm_arch_ptp_get_clock(struct timespec64 *ts)
diff --git a/drivers/reset/Kconfig b/drivers/reset/Kconfig
index be799a5abf8a..b0056ae5d463 100644
--- a/drivers/reset/Kconfig
+++ b/drivers/reset/Kconfig
@@ -147,8 +147,8 @@ config RESET_OXNAS
bool
config RESET_PISTACHIO
- bool "Pistachio Reset Driver" if COMPILE_TEST
- default MACH_PISTACHIO
+ bool "Pistachio Reset Driver"
+ depends on MIPS || COMPILE_TEST
help
This enables the reset driver for ImgTec Pistachio SoCs.
diff --git a/drivers/reset/reset-brcmstb-rescal.c b/drivers/reset/reset-brcmstb-rescal.c
index b6f074d6a65f..433fa0c40e47 100644
--- a/drivers/reset/reset-brcmstb-rescal.c
+++ b/drivers/reset/reset-brcmstb-rescal.c
@@ -38,7 +38,7 @@ static int brcm_rescal_reset_set(struct reset_controller_dev *rcdev,
}
ret = readl_poll_timeout(base + BRCM_RESCAL_STATUS, reg,
- !(reg & BRCM_RESCAL_STATUS_BIT), 100, 1000);
+ (reg & BRCM_RESCAL_STATUS_BIT), 100, 1000);
if (ret) {
dev_err(data->dev, "time out on SATA/PCIe rescal\n");
return ret;
diff --git a/drivers/reset/reset-socfpga.c b/drivers/reset/reset-socfpga.c
index 2a72f861f798..8c6492e5693c 100644
--- a/drivers/reset/reset-socfpga.c
+++ b/drivers/reset/reset-socfpga.c
@@ -92,3 +92,29 @@ void __init socfpga_reset_init(void)
for_each_matching_node(np, socfpga_early_reset_dt_ids)
a10_reset_init(np);
}
+
+/*
+ * The early driver is problematic, because it doesn't register
+ * itself as a driver. This causes certain device links to prevent
+ * consumer devices from probing. The hacky solution is to register
+ * an empty driver, whose only job is to attach itself to the reset
+ * manager and call probe.
+ */
+static const struct of_device_id socfpga_reset_dt_ids[] = {
+ { .compatible = "altr,rst-mgr", },
+ { /* sentinel */ },
+};
+
+static int reset_simple_probe(struct platform_device *pdev)
+{
+ return 0;
+}
+
+static struct platform_driver reset_socfpga_driver = {
+ .probe = reset_simple_probe,
+ .driver = {
+ .name = "socfpga-reset",
+ .of_match_table = socfpga_reset_dt_ids,
+ },
+};
+builtin_platform_driver(reset_socfpga_driver);
diff --git a/drivers/reset/tegra/reset-bpmp.c b/drivers/reset/tegra/reset-bpmp.c
index 24d3395964cc..4c5bba52b105 100644
--- a/drivers/reset/tegra/reset-bpmp.c
+++ b/drivers/reset/tegra/reset-bpmp.c
@@ -20,6 +20,7 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
struct tegra_bpmp *bpmp = to_tegra_bpmp(rstc);
struct mrq_reset_request request;
struct tegra_bpmp_message msg;
+ int err;
memset(&request, 0, sizeof(request));
request.cmd = command;
@@ -30,7 +31,13 @@ static int tegra_bpmp_reset_common(struct reset_controller_dev *rstc,
msg.tx.data = &request;
msg.tx.size = sizeof(request);
- return tegra_bpmp_transfer(bpmp, &msg);
+ err = tegra_bpmp_transfer(bpmp, &msg);
+ if (err)
+ return err;
+ if (msg.rx.ret)
+ return -EINVAL;
+
+ return 0;
}
static int tegra_bpmp_reset_module(struct reset_controller_dev *rstc,
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index e34c6cc61983..8e87a31e329d 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2077,12 +2077,15 @@ static void __dasd_device_check_path_events(struct dasd_device *device)
if (device->stopped & ~(DASD_STOPPED_DC_WAIT))
return;
+
+ dasd_path_clear_all_verify(device);
+ dasd_path_clear_all_fcsec(device);
+
rc = device->discipline->pe_handler(device, tbvpm, fcsecpm);
if (rc) {
+ dasd_path_add_tbvpm(device, tbvpm);
+ dasd_path_add_fcsecpm(device, fcsecpm);
dasd_device_set_timer(device, 50);
- } else {
- dasd_path_clear_all_verify(device);
- dasd_path_clear_all_fcsec(device);
}
};
diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
index 4691a3c35d72..299001ad9a32 100644
--- a/drivers/s390/block/dasd_3990_erp.c
+++ b/drivers/s390/block/dasd_3990_erp.c
@@ -201,7 +201,7 @@ dasd_3990_erp_DCTL(struct dasd_ccw_req * erp, char modifier)
struct ccw1 *ccw;
struct dasd_ccw_req *dctl_cqr;
- dctl_cqr = dasd_alloc_erp_request((char *) &erp->magic, 1,
+ dctl_cqr = dasd_alloc_erp_request(erp->magic, 1,
sizeof(struct DCTL_data),
device);
if (IS_ERR(dctl_cqr)) {
@@ -1652,7 +1652,7 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense)
}
/* Build new ERP request including DE/LO */
- erp = dasd_alloc_erp_request((char *) &cqr->magic,
+ erp = dasd_alloc_erp_request(cqr->magic,
2 + 1,/* DE/LO + TIC */
sizeof(struct DE_eckd_data) +
sizeof(struct LO_eckd_data), device);
@@ -2388,7 +2388,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr)
}
/* allocate additional request block */
- erp = dasd_alloc_erp_request((char *) &cqr->magic,
+ erp = dasd_alloc_erp_request(cqr->magic,
cplength, datasize, device);
if (IS_ERR(erp)) {
if (cqr->retries <= 0) {
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 460e0f1cca53..8410a25a65c1 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -560,8 +560,8 @@ static int prefix_LRE(struct ccw1 *ccw, struct PFX_eckd_data *pfxdata,
return -EINVAL;
}
pfxdata->format = format;
- pfxdata->base_address = basepriv->ned->unit_addr;
- pfxdata->base_lss = basepriv->ned->ID;
+ pfxdata->base_address = basepriv->conf.ned->unit_addr;
+ pfxdata->base_lss = basepriv->conf.ned->ID;
pfxdata->validity.define_extent = 1;
/* private uid is kept up to date, conf_data may be outdated */
@@ -736,32 +736,30 @@ dasd_eckd_cdl_reclen(int recid)
return LABEL_SIZE;
}
/* create unique id from private structure. */
-static void create_uid(struct dasd_eckd_private *private)
+static void create_uid(struct dasd_conf *conf, struct dasd_uid *uid)
{
int count;
- struct dasd_uid *uid;
- uid = &private->uid;
memset(uid, 0, sizeof(struct dasd_uid));
- memcpy(uid->vendor, private->ned->HDA_manufacturer,
+ memcpy(uid->vendor, conf->ned->HDA_manufacturer,
sizeof(uid->vendor) - 1);
EBCASC(uid->vendor, sizeof(uid->vendor) - 1);
- memcpy(uid->serial, &private->ned->serial,
+ memcpy(uid->serial, &conf->ned->serial,
sizeof(uid->serial) - 1);
EBCASC(uid->serial, sizeof(uid->serial) - 1);
- uid->ssid = private->gneq->subsystemID;
- uid->real_unit_addr = private->ned->unit_addr;
- if (private->sneq) {
- uid->type = private->sneq->sua_flags;
+ uid->ssid = conf->gneq->subsystemID;
+ uid->real_unit_addr = conf->ned->unit_addr;
+ if (conf->sneq) {
+ uid->type = conf->sneq->sua_flags;
if (uid->type == UA_BASE_PAV_ALIAS)
- uid->base_unit_addr = private->sneq->base_unit_addr;
+ uid->base_unit_addr = conf->sneq->base_unit_addr;
} else {
uid->type = UA_BASE_DEVICE;
}
- if (private->vdsneq) {
+ if (conf->vdsneq) {
for (count = 0; count < 16; count++) {
sprintf(uid->vduit+2*count, "%02x",
- private->vdsneq->uit[count]);
+ conf->vdsneq->uit[count]);
}
}
}
@@ -776,10 +774,10 @@ static int dasd_eckd_generate_uid(struct dasd_device *device)
if (!private)
return -ENODEV;
- if (!private->ned || !private->gneq)
+ if (!private->conf.ned || !private->conf.gneq)
return -ENODEV;
spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags);
- create_uid(private);
+ create_uid(&private->conf, &private->uid);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
return 0;
}
@@ -803,14 +801,15 @@ static int dasd_eckd_get_uid(struct dasd_device *device, struct dasd_uid *uid)
* return 0 for match
*/
static int dasd_eckd_compare_path_uid(struct dasd_device *device,
- struct dasd_eckd_private *private)
+ struct dasd_conf *path_conf)
{
struct dasd_uid device_uid;
+ struct dasd_uid path_uid;
- create_uid(private);
+ create_uid(path_conf, &path_uid);
dasd_eckd_get_uid(device, &device_uid);
- return memcmp(&device_uid, &private->uid, sizeof(struct dasd_uid));
+ return memcmp(&device_uid, &path_uid, sizeof(struct dasd_uid));
}
static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device,
@@ -946,34 +945,34 @@ out_error:
return ret;
}
-static int dasd_eckd_identify_conf_parts(struct dasd_eckd_private *private)
+static int dasd_eckd_identify_conf_parts(struct dasd_conf *conf)
{
struct dasd_sneq *sneq;
int i, count;
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
- count = private->conf_len / sizeof(struct dasd_sneq);
- sneq = (struct dasd_sneq *)private->conf_data;
+ conf->ned = NULL;
+ conf->sneq = NULL;
+ conf->vdsneq = NULL;
+ conf->gneq = NULL;
+ count = conf->len / sizeof(struct dasd_sneq);
+ sneq = (struct dasd_sneq *)conf->data;
for (i = 0; i < count; ++i) {
if (sneq->flags.identifier == 1 && sneq->format == 1)
- private->sneq = sneq;
+ conf->sneq = sneq;
else if (sneq->flags.identifier == 1 && sneq->format == 4)
- private->vdsneq = (struct vd_sneq *)sneq;
+ conf->vdsneq = (struct vd_sneq *)sneq;
else if (sneq->flags.identifier == 2)
- private->gneq = (struct dasd_gneq *)sneq;
+ conf->gneq = (struct dasd_gneq *)sneq;
else if (sneq->flags.identifier == 3 && sneq->res1 == 1)
- private->ned = (struct dasd_ned *)sneq;
+ conf->ned = (struct dasd_ned *)sneq;
sneq++;
}
- if (!private->ned || !private->gneq) {
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
+ if (!conf->ned || !conf->gneq) {
+ conf->ned = NULL;
+ conf->sneq = NULL;
+ conf->vdsneq = NULL;
+ conf->gneq = NULL;
return -EINVAL;
}
return 0;
@@ -1016,9 +1015,9 @@ static void dasd_eckd_store_conf_data(struct dasd_device *device,
* with the new one if this points to the same data
*/
cdp = device->path[chp].conf_data;
- if (private->conf_data == cdp) {
- private->conf_data = (void *)conf_data;
- dasd_eckd_identify_conf_parts(private);
+ if (private->conf.data == cdp) {
+ private->conf.data = (void *)conf_data;
+ dasd_eckd_identify_conf_parts(&private->conf);
}
ccw_device_get_schid(device->cdev, &sch_id);
device->path[chp].conf_data = conf_data;
@@ -1036,8 +1035,8 @@ static void dasd_eckd_clear_conf_data(struct dasd_device *device)
struct dasd_eckd_private *private = device->private;
int i;
- private->conf_data = NULL;
- private->conf_len = 0;
+ private->conf.data = NULL;
+ private->conf.len = 0;
for (i = 0; i < 8; i++) {
kfree(device->path[i].conf_data);
device->path[i].conf_data = NULL;
@@ -1071,15 +1070,55 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device)
}
}
+static void dasd_eckd_get_uid_string(struct dasd_conf *conf,
+ char *print_uid)
+{
+ struct dasd_uid uid;
+
+ create_uid(conf, &uid);
+ if (strlen(uid.vduit) > 0)
+ snprintf(print_uid, sizeof(*print_uid),
+ "%s.%s.%04x.%02x.%s",
+ uid.vendor, uid.serial, uid.ssid,
+ uid.real_unit_addr, uid.vduit);
+ else
+ snprintf(print_uid, sizeof(*print_uid),
+ "%s.%s.%04x.%02x",
+ uid.vendor, uid.serial, uid.ssid,
+ uid.real_unit_addr);
+}
+
+static int dasd_eckd_check_cabling(struct dasd_device *device,
+ void *conf_data, __u8 lpm)
+{
+ struct dasd_eckd_private *private = device->private;
+ char print_path_uid[60], print_device_uid[60];
+ struct dasd_conf path_conf;
+
+ path_conf.data = conf_data;
+ path_conf.len = DASD_ECKD_RCD_DATA_SIZE;
+ if (dasd_eckd_identify_conf_parts(&path_conf))
+ return 1;
+
+ if (dasd_eckd_compare_path_uid(device, &path_conf)) {
+ dasd_eckd_get_uid_string(&path_conf, print_path_uid);
+ dasd_eckd_get_uid_string(&private->conf, print_device_uid);
+ dev_err(&device->cdev->dev,
+ "Not all channel paths lead to the same device, path %02X leads to device %s instead of %s\n",
+ lpm, print_path_uid, print_device_uid);
+ return 1;
+ }
+
+ return 0;
+}
+
static int dasd_eckd_read_conf(struct dasd_device *device)
{
void *conf_data;
int conf_len, conf_data_saved;
int rc, path_err, pos;
__u8 lpm, opm;
- struct dasd_eckd_private *private, path_private;
- struct dasd_uid *uid;
- char print_path_uid[60], print_device_uid[60];
+ struct dasd_eckd_private *private;
private = device->private;
opm = ccw_device_get_path_mask(device->cdev);
@@ -1109,11 +1148,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
if (!conf_data_saved) {
/* initially clear previously stored conf_data */
dasd_eckd_clear_conf_data(device);
- private->conf_data = conf_data;
- private->conf_len = conf_len;
- if (dasd_eckd_identify_conf_parts(private)) {
- private->conf_data = NULL;
- private->conf_len = 0;
+ private->conf.data = conf_data;
+ private->conf.len = conf_len;
+ if (dasd_eckd_identify_conf_parts(&private->conf)) {
+ private->conf.data = NULL;
+ private->conf.len = 0;
kfree(conf_data);
continue;
}
@@ -1123,59 +1162,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
*/
dasd_eckd_generate_uid(device);
conf_data_saved++;
- } else {
- path_private.conf_data = conf_data;
- path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE;
- if (dasd_eckd_identify_conf_parts(
- &path_private)) {
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
- kfree(conf_data);
- continue;
- }
- if (dasd_eckd_compare_path_uid(
- device, &path_private)) {
- uid = &path_private.uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_path_uid,
- sizeof(print_path_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_path_uid,
- sizeof(print_path_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
- uid = &private->uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_device_uid,
- sizeof(print_device_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_device_uid,
- sizeof(print_device_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
- dev_err(&device->cdev->dev,
- "Not all channel paths lead to "
- "the same device, path %02X leads to "
- "device %s instead of %s\n", lpm,
- print_path_uid, print_device_uid);
- path_err = -EINVAL;
- dasd_path_add_cablepm(device, lpm);
- continue;
- }
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
+ } else if (dasd_eckd_check_cabling(device, conf_data, lpm)) {
+ dasd_path_add_cablepm(device, lpm);
+ path_err = -EINVAL;
+ kfree(conf_data);
+ continue;
}
pos = pathmask_to_pos(lpm);
@@ -1197,8 +1188,6 @@ static int dasd_eckd_read_conf(struct dasd_device *device)
}
}
- dasd_eckd_read_fc_security(device);
-
return path_err;
}
@@ -1213,7 +1202,7 @@ static u32 get_fcx_max_data(struct dasd_device *device)
return 0;
/* is transport mode supported? */
fcx_in_css = css_general_characteristics.fcx;
- fcx_in_gneq = private->gneq->reserved2[7] & 0x04;
+ fcx_in_gneq = private->conf.gneq->reserved2[7] & 0x04;
fcx_in_features = private->features.feature[40] & 0x80;
tpm = fcx_in_css && fcx_in_gneq && fcx_in_features;
@@ -1282,9 +1271,9 @@ static int rebuild_device_uid(struct dasd_device *device,
"returned error %d", rc);
break;
}
- memcpy(private->conf_data, data->rcd_buffer,
+ memcpy(private->conf.data, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
- if (dasd_eckd_identify_conf_parts(private)) {
+ if (dasd_eckd_identify_conf_parts(&private->conf)) {
rc = -ENODEV;
} else /* first valid path is enough */
break;
@@ -1299,11 +1288,10 @@ static int rebuild_device_uid(struct dasd_device *device,
static void dasd_eckd_path_available_action(struct dasd_device *device,
struct pe_handler_work_data *data)
{
- struct dasd_eckd_private path_private;
- struct dasd_uid *uid;
__u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE];
__u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm;
struct dasd_conf_data *conf_data;
+ struct dasd_conf path_conf;
unsigned long flags;
char print_uid[60];
int rc, pos;
@@ -1367,11 +1355,11 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
*/
memcpy(&path_rcd_buf, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
- path_private.conf_data = (void *) &path_rcd_buf;
- path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE;
- if (dasd_eckd_identify_conf_parts(&path_private)) {
- path_private.conf_data = NULL;
- path_private.conf_len = 0;
+ path_conf.data = (void *)&path_rcd_buf;
+ path_conf.len = DASD_ECKD_RCD_DATA_SIZE;
+ if (dasd_eckd_identify_conf_parts(&path_conf)) {
+ path_conf.data = NULL;
+ path_conf.len = 0;
continue;
}
@@ -1382,7 +1370,7 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
* the first working path UID will be used as device UID
*/
if (dasd_path_get_opm(device) &&
- dasd_eckd_compare_path_uid(device, &path_private)) {
+ dasd_eckd_compare_path_uid(device, &path_conf)) {
/*
* the comparison was not successful
* rebuild the device UID with at least one
@@ -1396,20 +1384,8 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
*/
if (rebuild_device_uid(device, data) ||
dasd_eckd_compare_path_uid(
- device, &path_private)) {
- uid = &path_private.uid;
- if (strlen(uid->vduit) > 0)
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x.%s",
- uid->vendor, uid->serial,
- uid->ssid, uid->real_unit_addr,
- uid->vduit);
- else
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x",
- uid->vendor, uid->serial,
- uid->ssid,
- uid->real_unit_addr);
+ device, &path_conf)) {
+ dasd_eckd_get_uid_string(&path_conf, print_uid);
dev_err(&device->cdev->dev,
"The newly added channel path %02X "
"will not be used because it leads "
@@ -1427,6 +1403,14 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
if (conf_data) {
memcpy(conf_data, data->rcd_buffer,
DASD_ECKD_RCD_DATA_SIZE);
+ } else {
+ /*
+ * path is operational but path config data could not
+ * be stored due to low mem condition
+ * add it to the error path mask and schedule a path
+ * verification later that this could be added again
+ */
+ epm |= lpm;
}
pos = pathmask_to_pos(lpm);
dasd_eckd_store_conf_data(device, conf_data, pos);
@@ -1447,7 +1431,10 @@ static void dasd_eckd_path_available_action(struct dasd_device *device,
}
dasd_path_add_nppm(device, npm);
dasd_path_add_ppm(device, ppm);
- dasd_path_add_tbvpm(device, epm);
+ if (epm) {
+ dasd_path_add_tbvpm(device, epm);
+ dasd_device_set_timer(device, 50);
+ }
dasd_path_add_cablepm(device, cablepm);
dasd_path_add_nohpfpm(device, hpfpm);
spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags);
@@ -1625,8 +1612,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device)
prssdp = cqr->data;
prssdp->order = PSF_ORDER_PRSSD;
prssdp->suborder = PSF_SUBORDER_VSQ; /* Volume Storage Query */
- prssdp->lss = private->ned->ID;
- prssdp->volume = private->ned->unit_addr;
+ prssdp->lss = private->conf.ned->ID;
+ prssdp->volume = private->conf.ned->unit_addr;
ccw = cqr->cpaddr;
ccw->cmd_code = DASD_ECKD_CCW_PSF;
@@ -2085,11 +2072,11 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
device->path_thrhld = DASD_ECKD_PATH_THRHLD;
device->path_interval = DASD_ECKD_PATH_INTERVAL;
- if (private->gneq) {
+ if (private->conf.gneq) {
value = 1;
- for (i = 0; i < private->gneq->timeout.value; i++)
+ for (i = 0; i < private->conf.gneq->timeout.value; i++)
value = 10 * value;
- value = value * private->gneq->timeout.number;
+ value = value * private->conf.gneq->timeout.number;
/* do not accept useless values */
if (value != 0 && value <= DASD_EXPIRES_MAX)
device->default_expires = value;
@@ -2121,6 +2108,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device)
if (rc)
goto out_err3;
+ dasd_eckd_read_fc_security(device);
dasd_path_create_kobjects(device);
/* Read Feature Codes */
@@ -2195,10 +2183,10 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
return;
dasd_alias_disconnect_device_from_lcu(device);
- private->ned = NULL;
- private->sneq = NULL;
- private->vdsneq = NULL;
- private->gneq = NULL;
+ private->conf.ned = NULL;
+ private->conf.sneq = NULL;
+ private->conf.vdsneq = NULL;
+ private->conf.gneq = NULL;
dasd_eckd_clear_conf_data(device);
dasd_path_remove_kobjects(device);
}
@@ -3750,8 +3738,8 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block,
* subset.
*/
ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01);
- ras_data->lss = private->ned->ID;
- ras_data->dev_addr = private->ned->unit_addr;
+ ras_data->lss = private->conf.ned->ID;
+ ras_data->dev_addr = private->conf.ned->unit_addr;
ras_data->nr_exts = nr_exts;
if (by_extent) {
@@ -4293,8 +4281,8 @@ static int prepare_itcw(struct itcw *itcw,
memset(&pfxdata, 0, sizeof(pfxdata));
pfxdata.format = 1; /* PFX with LRE */
- pfxdata.base_address = basepriv->ned->unit_addr;
- pfxdata.base_lss = basepriv->ned->ID;
+ pfxdata.base_address = basepriv->conf.ned->unit_addr;
+ pfxdata.base_lss = basepriv->conf.ned->ID;
pfxdata.validity.define_extent = 1;
/* private uid is kept up to date, conf_data may be outdated */
@@ -4963,9 +4951,9 @@ dasd_eckd_fill_info(struct dasd_device * device,
info->characteristics_size = sizeof(private->rdc_data);
memcpy(info->characteristics, &private->rdc_data,
sizeof(private->rdc_data));
- info->confdata_size = min((unsigned long)private->conf_len,
- sizeof(info->configuration_data));
- memcpy(info->configuration_data, private->conf_data,
+ info->confdata_size = min_t(unsigned long, private->conf.len,
+ sizeof(info->configuration_data));
+ memcpy(info->configuration_data, private->conf.data,
info->confdata_size);
return 0;
}
@@ -5808,6 +5796,8 @@ static int dasd_eckd_reload_device(struct dasd_device *device)
if (rc)
goto out_err;
+ dasd_eckd_read_fc_security(device);
+
rc = dasd_eckd_generate_uid(device);
if (rc)
goto out_err;
@@ -5820,15 +5810,7 @@ static int dasd_eckd_reload_device(struct dasd_device *device)
dasd_eckd_get_uid(device, &uid);
if (old_base != uid.base_unit_addr) {
- if (strlen(uid.vduit) > 0)
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x.%s", uid.vendor, uid.serial,
- uid.ssid, uid.base_unit_addr, uid.vduit);
- else
- snprintf(print_uid, sizeof(print_uid),
- "%s.%s.%04x.%02x", uid.vendor, uid.serial,
- uid.ssid, uid.base_unit_addr);
-
+ dasd_eckd_get_uid_string(&private->conf, print_uid);
dev_info(&device->cdev->dev,
"An Alias device was reassigned to a new base device "
"with UID: %s\n", print_uid);
@@ -5966,8 +5948,8 @@ static int dasd_eckd_query_host_access(struct dasd_device *device,
prssdp->order = PSF_ORDER_PRSSD;
prssdp->suborder = PSF_SUBORDER_QHA; /* query host access */
/* LSS and Volume that will be queried */
- prssdp->lss = private->ned->ID;
- prssdp->volume = private->ned->unit_addr;
+ prssdp->lss = private->conf.ned->ID;
+ prssdp->volume = private->conf.ned->unit_addr;
/* all other bytes of prssdp must be zero */
ccw = cqr->cpaddr;
diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h
index 65e4630ad2ae..a91b265441cc 100644
--- a/drivers/s390/block/dasd_eckd.h
+++ b/drivers/s390/block/dasd_eckd.h
@@ -658,16 +658,19 @@ struct dasd_conf_data {
struct dasd_gneq gneq;
} __packed;
-struct dasd_eckd_private {
- struct dasd_eckd_characteristics rdc_data;
- u8 *conf_data;
- int conf_len;
-
+struct dasd_conf {
+ u8 *data;
+ int len;
/* pointers to specific parts in the conf_data */
struct dasd_ned *ned;
struct dasd_sneq *sneq;
struct vd_sneq *vdsneq;
struct dasd_gneq *gneq;
+};
+
+struct dasd_eckd_private {
+ struct dasd_eckd_characteristics rdc_data;
+ struct dasd_conf conf;
struct eckd_count count_area[5];
int init_cqr_status;
diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c
index ba4fa372d02d..c07e6e713518 100644
--- a/drivers/s390/block/dasd_erp.c
+++ b/drivers/s390/block/dasd_erp.c
@@ -24,7 +24,7 @@
#include "dasd_int.h"
struct dasd_ccw_req *
-dasd_alloc_erp_request(char *magic, int cplength, int datasize,
+dasd_alloc_erp_request(unsigned int magic, int cplength, int datasize,
struct dasd_device * device)
{
unsigned long flags;
@@ -33,8 +33,8 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize,
int size;
/* Sanity checks */
- BUG_ON( magic == NULL || datasize > PAGE_SIZE ||
- (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
+ BUG_ON(datasize > PAGE_SIZE ||
+ (cplength*sizeof(struct ccw1)) > PAGE_SIZE);
size = (sizeof(struct dasd_ccw_req) + 7L) & -8L;
if (cplength > 0)
@@ -62,7 +62,7 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize,
cqr->data = data;
memset(cqr->data, 0, datasize);
}
- strncpy((char *) &cqr->magic, magic, 4);
+ cqr->magic = magic;
ASCEBC((char *) &cqr->magic, 4);
set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags);
dasd_get_device(device);
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 155428bfed8a..8b458010f88a 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -887,7 +887,7 @@ void dasd_proc_exit(void);
/* externals in dasd_erp.c */
struct dasd_ccw_req *dasd_default_erp_action(struct dasd_ccw_req *);
struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *);
-struct dasd_ccw_req *dasd_alloc_erp_request(char *, int, int,
+struct dasd_ccw_req *dasd_alloc_erp_request(unsigned int, int, int,
struct dasd_device *);
void dasd_free_erp_request(struct dasd_ccw_req *, struct dasd_device *);
void dasd_log_sense(struct dasd_ccw_req *, struct irb *);
@@ -1305,6 +1305,15 @@ static inline void dasd_path_add_ppm(struct dasd_device *device, __u8 pm)
dasd_path_preferred(device, chp);
}
+static inline void dasd_path_add_fcsecpm(struct dasd_device *device, __u8 pm)
+{
+ int chp;
+
+ for (chp = 0; chp < 8; chp++)
+ if (pm & (0x80 >> chp))
+ dasd_path_fcsec(device, chp);
+}
+
/*
* set functions for path masks
* the existing path mask will be replaced by the given path mask
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 468cbeb539ff..95349f95758c 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -650,8 +650,8 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode,
/**
* dasd_biodasdinfo() - fill out the dasd information structure
- * @disk [in]: pointer to gendisk structure that references a DASD
- * @info [out]: pointer to the dasd_information2_t structure
+ * @disk: [in] pointer to gendisk structure that references a DASD
+ * @info: [out] pointer to the dasd_information2_t structure
*
* Provide access to DASD specific information.
* The gendisk structure is checked if it belongs to the DASD driver by
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 3f6f14f0cafb..24b72ee4246f 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -220,7 +220,8 @@ int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
goto fail;
}
- shost->cmd_per_lun = min_t(short, shost->cmd_per_lun,
+ /* Use min_t(int, ...) in case shost->can_queue exceeds SHRT_MAX */
+ shost->cmd_per_lun = min_t(int, shost->cmd_per_lun,
shost->can_queue);
error = scsi_init_sense_cache(shost);
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index 1f1586ad48fe..01f79991bf4a 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1696,6 +1696,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
spin_lock_irqsave(&evt->queue->l_lock, flags);
list_add_tail(&evt->queue_list, &evt->queue->sent);
+ atomic_set(&evt->active, 1);
mb();
@@ -1710,6 +1711,7 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
be64_to_cpu(crq_as_u64[1]));
if (rc) {
+ atomic_set(&evt->active, 0);
list_del(&evt->queue_list);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
del_timer(&evt->timer);
@@ -1737,7 +1739,6 @@ static int ibmvfc_send_event(struct ibmvfc_event *evt,
evt->done(evt);
} else {
- atomic_set(&evt->active, 1);
spin_unlock_irqrestore(&evt->queue->l_lock, flags);
ibmvfc_trc_start(evt);
}
diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
index 2197988333fe..3cae8803383b 100644
--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
+++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
@@ -3736,7 +3736,7 @@ mpi3mr_probe(struct pci_dev *pdev, const struct pci_device_id *id)
shost->max_lun = -1;
shost->unique_id = mrioc->id;
- shost->max_channel = 1;
+ shost->max_channel = 0;
shost->max_id = 0xFFFFFFFF;
if (prot_mask >= 0)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d383d4a03436..ad1b6c2b37a7 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -5065,9 +5065,12 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
if (scmd->prot_flags & SCSI_PROT_GUARD_CHECK)
eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
- if (scmd->prot_flags & SCSI_PROT_REF_CHECK) {
- eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG |
- MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG;
+ if (scmd->prot_flags & SCSI_PROT_REF_CHECK)
+ eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG;
+
+ if (scmd->prot_flags & SCSI_PROT_REF_INCREMENT) {
+ eedp_flags |= MPI2_SCSIIO_EEDPFLAGS_INC_PRI_REFTAG;
+
mpi_request->CDB.EEDP32.PrimaryReferenceTag =
cpu_to_be32(scsi_prot_ref_tag(scmd));
}
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 4b5d28d89d69..655cf5de604b 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -431,7 +431,7 @@ done_unmap_sg:
goto done_free_fcport;
done_free_fcport:
- if (bsg_request->msgcode == FC_BSG_RPT_ELS)
+ if (bsg_request->msgcode != FC_BSG_RPT_ELS)
qla2x00_free_fcport(fcport);
done:
return rval;
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index 1c5da2dbd6f9..253055cf9daf 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -8,6 +8,8 @@
#include <linux/delay.h>
#include <linux/nvme.h>
#include <linux/nvme-fc.h>
+#include <linux/blk-mq-pci.h>
+#include <linux/blk-mq.h>
static struct nvme_fc_port_template qla_nvme_fc_transport;
@@ -642,6 +644,18 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport,
return rval;
}
+static void qla_nvme_map_queues(struct nvme_fc_local_port *lport,
+ struct blk_mq_queue_map *map)
+{
+ struct scsi_qla_host *vha = lport->private;
+ int rc;
+
+ rc = blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset);
+ if (rc)
+ ql_log(ql_log_warn, vha, 0x21de,
+ "pci map queue failed 0x%x", rc);
+}
+
static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport)
{
struct scsi_qla_host *vha = lport->private;
@@ -676,6 +690,7 @@ static struct nvme_fc_port_template qla_nvme_fc_transport = {
.ls_abort = qla_nvme_ls_abort,
.fcp_io = qla_nvme_post_cmd,
.fcp_abort = qla_nvme_fcp_abort,
+ .map_queues = qla_nvme_map_queues,
.max_hw_queues = 8,
.max_sgl_segments = 1024,
.max_dif_sgl_segments = 64,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index d2e40aaba734..836fedcea241 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4157,7 +4157,7 @@ qla2x00_mem_alloc(struct qla_hw_data *ha, uint16_t req_len, uint16_t rsp_len,
ql_dbg_pci(ql_dbg_init, ha->pdev,
0xe0ee, "%s: failed alloc dsd\n",
__func__);
- return 1;
+ return -ENOMEM;
}
ha->dif_bundle_kallocs++;
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b3478ed9b12e..7d8242c120fc 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3319,8 +3319,7 @@ int qlt_xmit_response(struct qla_tgt_cmd *cmd, int xmit_type,
"RESET-RSP online/active/old-count/new-count = %d/%d/%d/%d.\n",
vha->flags.online, qla2x00_reset_active(vha),
cmd->reset_count, qpair->chip_reset);
- spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
- return 0;
+ goto out_unmap_unlock;
}
/* Does F/W have an IOCBs for this request */
@@ -3445,10 +3444,6 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
prm.sg = NULL;
prm.req_cnt = 1;
- /* Calculate number of entries and segments required */
- if (qlt_pci_map_calc_cnt(&prm) != 0)
- return -EAGAIN;
-
if (!qpair->fw_started || (cmd->reset_count != qpair->chip_reset) ||
(cmd->sess && cmd->sess->deleted)) {
/*
@@ -3466,6 +3461,10 @@ int qlt_rdy_to_xfer(struct qla_tgt_cmd *cmd)
return 0;
}
+ /* Calculate number of entries and segments required */
+ if (qlt_pci_map_calc_cnt(&prm) != 0)
+ return -EAGAIN;
+
spin_lock_irqsave(qpair->qp_lock_ptr, flags);
/* Does F/W have an IOCBs for this request */
res = qlt_check_reserve_free_req(qpair, prm.req_cnt);
@@ -3870,9 +3869,6 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
BUG_ON(cmd->cmd_in_wq);
- if (cmd->sg_mapped)
- qlt_unmap_sg(cmd->vha, cmd);
-
if (!cmd->q_full)
qlt_decr_num_pend_cmds(cmd->vha);
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index b241f9e3885c..291ecc33b1fe 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -553,8 +553,10 @@ EXPORT_SYMBOL(scsi_device_get);
*/
void scsi_device_put(struct scsi_device *sdev)
{
- module_put(sdev->host->hostt->module);
+ struct module *mod = sdev->host->hostt->module;
+
put_device(&sdev->sdev_gendev);
+ module_put(mod);
}
EXPORT_SYMBOL(scsi_device_put);
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 86793259e541..a35841b34bfd 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -449,9 +449,12 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
struct scsi_vpd *vpd_pg80 = NULL, *vpd_pg83 = NULL;
struct scsi_vpd *vpd_pg0 = NULL, *vpd_pg89 = NULL;
unsigned long flags;
+ struct module *mod;
sdev = container_of(work, struct scsi_device, ew.work);
+ mod = sdev->host->hostt->module;
+
scsi_dh_release_device(sdev);
parent = sdev->sdev_gendev.parent;
@@ -502,11 +505,17 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
if (parent)
put_device(parent);
+ module_put(mod);
}
static void scsi_device_dev_release(struct device *dev)
{
struct scsi_device *sdp = to_scsi_device(dev);
+
+ /* Set module pointer as NULL in case of module unloading */
+ if (!try_module_get(sdp->host->hostt->module))
+ sdp->host->hostt->module = NULL;
+
execute_in_process_context(scsi_device_dev_release_usercontext,
&sdp->ew);
}
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 922e4c7bd88e..78343d3f9385 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2930,8 +2930,6 @@ iscsi_set_param(struct iscsi_transport *transport, struct iscsi_uevent *ev)
session->recovery_tmo = value;
break;
default:
- err = transport->set_param(conn, ev->u.set_param.param,
- data, ev->u.set_param.len);
if ((conn->state == ISCSI_CONN_BOUND) ||
(conn->state == ISCSI_CONN_UP)) {
err = transport->set_param(conn, ev->u.set_param.param,
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index d8f6add416c0..9bdee968d3b5 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3684,7 +3684,12 @@ static int sd_resume(struct device *dev)
static int sd_resume_runtime(struct device *dev)
{
struct scsi_disk *sdkp = dev_get_drvdata(dev);
- struct scsi_device *sdp = sdkp->device;
+ struct scsi_device *sdp;
+
+ if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */
+ return 0;
+
+ sdp = sdkp->device;
if (sdp->ignore_media_change) {
/* clear the device's sense data */
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index ebbbc1299c62..9eb1b88a29dd 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -1285,11 +1285,15 @@ static void storvsc_on_channel_callback(void *context)
foreach_vmbus_pkt(desc, channel) {
struct vstor_packet *packet = hv_pkt_data(desc);
struct storvsc_cmd_request *request = NULL;
+ u32 pktlen = hv_pkt_datalen(desc);
u64 rqst_id = desc->trans_id;
+ u32 minlen = rqst_id ? sizeof(struct vstor_packet) -
+ stor_device->vmscsi_size_delta : sizeof(enum vstor_packet_operation);
- if (hv_pkt_datalen(desc) < sizeof(struct vstor_packet) -
- stor_device->vmscsi_size_delta) {
- dev_err(&device->device, "Invalid packet len\n");
+ if (pktlen < minlen) {
+ dev_err(&device->device,
+ "Invalid pkt: id=%llu, len=%u, minlen=%u\n",
+ rqst_id, pktlen, minlen);
continue;
}
@@ -1302,13 +1306,23 @@ static void storvsc_on_channel_callback(void *context)
if (rqst_id == 0) {
/*
* storvsc_on_receive() looks at the vstor_packet in the message
- * from the ring buffer. If the operation in the vstor_packet is
- * COMPLETE_IO, then we call storvsc_on_io_completion(), and
- * dereference the guest memory address. Make sure we don't call
- * storvsc_on_io_completion() with a guest memory address that is
- * zero if Hyper-V were to construct and send such a bogus packet.
+ * from the ring buffer.
+ *
+ * - If the operation in the vstor_packet is COMPLETE_IO, then
+ * we call storvsc_on_io_completion(), and dereference the
+ * guest memory address. Make sure we don't call
+ * storvsc_on_io_completion() with a guest memory address
+ * that is zero if Hyper-V were to construct and send such
+ * a bogus packet.
+ *
+ * - If the operation in the vstor_packet is FCHBA_DATA, then
+ * we call cache_wwn(), and access the data payload area of
+ * the packet (wwn_packet); however, there is no guarantee
+ * that the packet is big enough to contain such area.
+ * Future-proof the code by rejecting such a bogus packet.
*/
- if (packet->operation == VSTOR_OPERATION_COMPLETE_IO) {
+ if (packet->operation == VSTOR_OPERATION_COMPLETE_IO ||
+ packet->operation == VSTOR_OPERATION_FCHBA_DATA) {
dev_err(&device->device, "Invalid packet with ID of 0\n");
continue;
}
diff --git a/drivers/scsi/ufs/ufs-exynos.c b/drivers/scsi/ufs/ufs-exynos.c
index a14dd8ce56d4..bb2dd79a1bcd 100644
--- a/drivers/scsi/ufs/ufs-exynos.c
+++ b/drivers/scsi/ufs/ufs-exynos.c
@@ -642,9 +642,9 @@ static int exynos_ufs_pre_pwr_mode(struct ufs_hba *hba,
}
/* setting for three timeout values for traffic class #0 */
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA0), 8064);
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA1), 28224);
- ufshcd_dme_set(hba, UIC_ARG_MIB(PA_PWRMODEUSERDATA2), 20160);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_FC0PROTTIMEOUTVAL), 8064);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_TC0REPLAYTIMEOUTVAL), 28224);
+ ufshcd_dme_set(hba, UIC_ARG_MIB(DL_AFC0REQTIMEOUTVAL), 20160);
return 0;
out:
diff --git a/drivers/scsi/ufs/ufshcd-crypto.c b/drivers/scsi/ufs/ufshcd-crypto.c
index d70cdcd35e43..67402baf6fae 100644
--- a/drivers/scsi/ufs/ufshcd-crypto.c
+++ b/drivers/scsi/ufs/ufshcd-crypto.c
@@ -48,11 +48,12 @@ out:
return err;
}
-static int ufshcd_crypto_keyslot_program(struct blk_keyslot_manager *ksm,
+static int ufshcd_crypto_keyslot_program(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm);
+ struct ufs_hba *hba =
+ container_of(profile, struct ufs_hba, crypto_profile);
const union ufs_crypto_cap_entry *ccap_array = hba->crypto_cap_array;
const struct ufs_crypto_alg_entry *alg =
&ufs_crypto_algs[key->crypto_cfg.crypto_mode];
@@ -105,11 +106,12 @@ static int ufshcd_clear_keyslot(struct ufs_hba *hba, int slot)
return ufshcd_program_key(hba, &cfg, slot);
}
-static int ufshcd_crypto_keyslot_evict(struct blk_keyslot_manager *ksm,
+static int ufshcd_crypto_keyslot_evict(struct blk_crypto_profile *profile,
const struct blk_crypto_key *key,
unsigned int slot)
{
- struct ufs_hba *hba = container_of(ksm, struct ufs_hba, ksm);
+ struct ufs_hba *hba =
+ container_of(profile, struct ufs_hba, crypto_profile);
return ufshcd_clear_keyslot(hba, slot);
}
@@ -120,11 +122,11 @@ bool ufshcd_crypto_enable(struct ufs_hba *hba)
return false;
/* Reset might clear all keys, so reprogram all the keys. */
- blk_ksm_reprogram_all_keys(&hba->ksm);
+ blk_crypto_reprogram_all_keys(&hba->crypto_profile);
return true;
}
-static const struct blk_ksm_ll_ops ufshcd_ksm_ops = {
+static const struct blk_crypto_ll_ops ufshcd_crypto_ops = {
.keyslot_program = ufshcd_crypto_keyslot_program,
.keyslot_evict = ufshcd_crypto_keyslot_evict,
};
@@ -179,15 +181,16 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
}
/* The actual number of configurations supported is (CFGC+1) */
- err = devm_blk_ksm_init(hba->dev, &hba->ksm,
- hba->crypto_capabilities.config_count + 1);
+ err = devm_blk_crypto_profile_init(
+ hba->dev, &hba->crypto_profile,
+ hba->crypto_capabilities.config_count + 1);
if (err)
goto out;
- hba->ksm.ksm_ll_ops = ufshcd_ksm_ops;
+ hba->crypto_profile.ll_ops = ufshcd_crypto_ops;
/* UFS only supports 8 bytes for any DUN */
- hba->ksm.max_dun_bytes_supported = 8;
- hba->ksm.dev = hba->dev;
+ hba->crypto_profile.max_dun_bytes_supported = 8;
+ hba->crypto_profile.dev = hba->dev;
/*
* Cache all the UFS crypto capabilities and advertise the supported
@@ -202,7 +205,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
blk_mode_num = ufshcd_find_blk_crypto_mode(
hba->crypto_cap_array[cap_idx]);
if (blk_mode_num != BLK_ENCRYPTION_MODE_INVALID)
- hba->ksm.crypto_modes_supported[blk_mode_num] |=
+ hba->crypto_profile.modes_supported[blk_mode_num] |=
hba->crypto_cap_array[cap_idx].sdus_mask * 512;
}
@@ -230,9 +233,8 @@ void ufshcd_init_crypto(struct ufs_hba *hba)
ufshcd_clear_keyslot(hba, slot);
}
-void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q)
+void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q)
{
if (hba->caps & UFSHCD_CAP_CRYPTO)
- blk_ksm_register(&hba->ksm, q);
+ blk_crypto_register(&hba->crypto_profile, q);
}
diff --git a/drivers/scsi/ufs/ufshcd-crypto.h b/drivers/scsi/ufs/ufshcd-crypto.h
index 78a58e788dff..e18c01276873 100644
--- a/drivers/scsi/ufs/ufshcd-crypto.h
+++ b/drivers/scsi/ufs/ufshcd-crypto.h
@@ -18,7 +18,7 @@ static inline void ufshcd_prepare_lrbp_crypto(struct request *rq,
return;
}
- lrbp->crypto_key_slot = blk_ksm_get_slot_idx(rq->crypt_keyslot);
+ lrbp->crypto_key_slot = blk_crypto_keyslot_index(rq->crypt_keyslot);
lrbp->data_unit_num = rq->crypt_ctx->bc_dun[0];
}
@@ -40,8 +40,7 @@ int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba);
void ufshcd_init_crypto(struct ufs_hba *hba);
-void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q);
+void ufshcd_crypto_register(struct ufs_hba *hba, struct request_queue *q);
#else /* CONFIG_SCSI_UFS_CRYPTO */
@@ -64,8 +63,8 @@ static inline int ufshcd_hba_init_crypto_capabilities(struct ufs_hba *hba)
static inline void ufshcd_init_crypto(struct ufs_hba *hba) { }
-static inline void ufshcd_crypto_setup_rq_keyslot_manager(struct ufs_hba *hba,
- struct request_queue *q) { }
+static inline void ufshcd_crypto_register(struct ufs_hba *hba,
+ struct request_queue *q) { }
#endif /* CONFIG_SCSI_UFS_CRYPTO */
diff --git a/drivers/scsi/ufs/ufshcd-pci.c b/drivers/scsi/ufs/ufshcd-pci.c
index 149c1aa09103..51424557810d 100644
--- a/drivers/scsi/ufs/ufshcd-pci.c
+++ b/drivers/scsi/ufs/ufshcd-pci.c
@@ -370,20 +370,6 @@ static void ufs_intel_common_exit(struct ufs_hba *hba)
static int ufs_intel_resume(struct ufs_hba *hba, enum ufs_pm_op op)
{
- /*
- * To support S4 (suspend-to-disk) with spm_lvl other than 5, the base
- * address registers must be restored because the restore kernel can
- * have used different addresses.
- */
- ufshcd_writel(hba, lower_32_bits(hba->utrdl_dma_addr),
- REG_UTP_TRANSFER_REQ_LIST_BASE_L);
- ufshcd_writel(hba, upper_32_bits(hba->utrdl_dma_addr),
- REG_UTP_TRANSFER_REQ_LIST_BASE_H);
- ufshcd_writel(hba, lower_32_bits(hba->utmrdl_dma_addr),
- REG_UTP_TASK_REQ_LIST_BASE_L);
- ufshcd_writel(hba, upper_32_bits(hba->utmrdl_dma_addr),
- REG_UTP_TASK_REQ_LIST_BASE_H);
-
if (ufshcd_is_link_hibern8(hba)) {
int ret = ufshcd_uic_hibern8_exit(hba);
@@ -463,6 +449,18 @@ static struct ufs_hba_variant_ops ufs_intel_lkf_hba_vops = {
.device_reset = ufs_intel_device_reset,
};
+#ifdef CONFIG_PM_SLEEP
+static int ufshcd_pci_restore(struct device *dev)
+{
+ struct ufs_hba *hba = dev_get_drvdata(dev);
+
+ /* Force a full reset and restore */
+ ufshcd_set_link_off(hba);
+
+ return ufshcd_system_resume(dev);
+}
+#endif
+
/**
* ufshcd_pci_shutdown - main function to put the controller in reset state
* @pdev: pointer to PCI device handle
@@ -546,9 +544,14 @@ ufshcd_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
}
static const struct dev_pm_ops ufshcd_pci_pm_ops = {
- SET_SYSTEM_SLEEP_PM_OPS(ufshcd_system_suspend, ufshcd_system_resume)
SET_RUNTIME_PM_OPS(ufshcd_runtime_suspend, ufshcd_runtime_resume, NULL)
#ifdef CONFIG_PM_SLEEP
+ .suspend = ufshcd_system_suspend,
+ .resume = ufshcd_system_resume,
+ .freeze = ufshcd_system_suspend,
+ .thaw = ufshcd_system_resume,
+ .poweroff = ufshcd_system_suspend,
+ .restore = ufshcd_pci_restore,
.prepare = ufshcd_suspend_prepare,
.complete = ufshcd_resume_complete,
#endif
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 95be7ecdfe10..1157b24963ef 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -2737,12 +2737,7 @@ static int ufshcd_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmd)
lrbp->req_abort_skip = false;
- err = ufshpb_prep(hba, lrbp);
- if (err == -EAGAIN) {
- lrbp->cmd = NULL;
- ufshcd_release(hba);
- goto out;
- }
+ ufshpb_prep(hba, lrbp);
ufshcd_comp_scsi_upiu(hba, lrbp);
@@ -4986,7 +4981,7 @@ static int ufshcd_slave_configure(struct scsi_device *sdev)
else if (ufshcd_is_rpm_autosuspend_allowed(hba))
sdev->rpm_autosuspend = 1;
- ufshcd_crypto_setup_rq_keyslot_manager(hba, q);
+ ufshcd_crypto_register(hba, q);
return 0;
}
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index 41f6e06f9185..62bdc412d38a 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -32,7 +32,7 @@
#include <linux/regulator/consumer.h>
#include <linux/bitfield.h>
#include <linux/devfreq.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
#include "unipro.h"
#include <asm/irq.h>
@@ -766,7 +766,7 @@ struct ufs_hba_monitor {
* @crypto_capabilities: Content of crypto capabilities register (0x100)
* @crypto_cap_array: Array of crypto capabilities
* @crypto_cfg_register: Start of the crypto cfg array
- * @ksm: the keyslot manager tied to this hba
+ * @crypto_profile: the crypto profile of this hba (if applicable)
*/
struct ufs_hba {
void __iomem *mmio_base;
@@ -911,7 +911,7 @@ struct ufs_hba {
union ufs_crypto_capabilities crypto_capabilities;
union ufs_crypto_cap_entry *crypto_cap_array;
u32 crypto_cfg_register;
- struct blk_keyslot_manager ksm;
+ struct blk_crypto_profile crypto_profile;
#endif
#ifdef CONFIG_DEBUG_FS
struct dentry *debugfs_root;
diff --git a/drivers/scsi/ufs/ufshpb.c b/drivers/scsi/ufs/ufshpb.c
index 589af5f6b940..026a133149dc 100644
--- a/drivers/scsi/ufs/ufshpb.c
+++ b/drivers/scsi/ufs/ufshpb.c
@@ -84,16 +84,6 @@ static bool ufshpb_is_supported_chunk(struct ufshpb_lu *hpb, int transfer_len)
return transfer_len <= hpb->pre_req_max_tr_len;
}
-/*
- * In this driver, WRITE_BUFFER CMD support 36KB (len=9) ~ 1MB (len=256) as
- * default. It is possible to change range of transfer_len through sysfs.
- */
-static inline bool ufshpb_is_required_wb(struct ufshpb_lu *hpb, int len)
-{
- return len > hpb->pre_req_min_tr_len &&
- len <= hpb->pre_req_max_tr_len;
-}
-
static bool ufshpb_is_general_lun(int lun)
{
return lun < UFS_UPIU_MAX_UNIT_NUM_ID;
@@ -334,7 +324,7 @@ ufshpb_get_pos_from_lpn(struct ufshpb_lu *hpb, unsigned long lpn, int *rgn_idx,
static void
ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
- __be64 ppn, u8 transfer_len, int read_id)
+ __be64 ppn, u8 transfer_len)
{
unsigned char *cdb = lrbp->cmd->cmnd;
__be64 ppn_tmp = ppn;
@@ -346,256 +336,11 @@ ufshpb_set_hpb_read_to_upiu(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
/* ppn value is stored as big-endian in the host memory */
memcpy(&cdb[6], &ppn_tmp, sizeof(__be64));
cdb[14] = transfer_len;
- cdb[15] = read_id;
+ cdb[15] = 0;
lrbp->cmd->cmd_len = UFS_CDB_SIZE;
}
-static inline void ufshpb_set_write_buf_cmd(unsigned char *cdb,
- unsigned long lpn, unsigned int len,
- int read_id)
-{
- cdb[0] = UFSHPB_WRITE_BUFFER;
- cdb[1] = UFSHPB_WRITE_BUFFER_PREFETCH_ID;
-
- put_unaligned_be32(lpn, &cdb[2]);
- cdb[6] = read_id;
- put_unaligned_be16(len * HPB_ENTRY_SIZE, &cdb[7]);
-
- cdb[9] = 0x00; /* Control = 0x00 */
-}
-
-static struct ufshpb_req *ufshpb_get_pre_req(struct ufshpb_lu *hpb)
-{
- struct ufshpb_req *pre_req;
-
- if (hpb->num_inflight_pre_req >= hpb->throttle_pre_req) {
- dev_info(&hpb->sdev_ufs_lu->sdev_dev,
- "pre_req throttle. inflight %d throttle %d",
- hpb->num_inflight_pre_req, hpb->throttle_pre_req);
- return NULL;
- }
-
- pre_req = list_first_entry_or_null(&hpb->lh_pre_req_free,
- struct ufshpb_req, list_req);
- if (!pre_req) {
- dev_info(&hpb->sdev_ufs_lu->sdev_dev, "There is no pre_req");
- return NULL;
- }
-
- list_del_init(&pre_req->list_req);
- hpb->num_inflight_pre_req++;
-
- return pre_req;
-}
-
-static inline void ufshpb_put_pre_req(struct ufshpb_lu *hpb,
- struct ufshpb_req *pre_req)
-{
- pre_req->req = NULL;
- bio_reset(pre_req->bio);
- list_add_tail(&pre_req->list_req, &hpb->lh_pre_req_free);
- hpb->num_inflight_pre_req--;
-}
-
-static void ufshpb_pre_req_compl_fn(struct request *req, blk_status_t error)
-{
- struct ufshpb_req *pre_req = (struct ufshpb_req *)req->end_io_data;
- struct ufshpb_lu *hpb = pre_req->hpb;
- unsigned long flags;
-
- if (error) {
- struct scsi_cmnd *cmd = blk_mq_rq_to_pdu(req);
- struct scsi_sense_hdr sshdr;
-
- dev_err(&hpb->sdev_ufs_lu->sdev_dev, "block status %d", error);
- scsi_command_normalize_sense(cmd, &sshdr);
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "code %x sense_key %x asc %x ascq %x",
- sshdr.response_code,
- sshdr.sense_key, sshdr.asc, sshdr.ascq);
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "byte4 %x byte5 %x byte6 %x additional_len %x",
- sshdr.byte4, sshdr.byte5,
- sshdr.byte6, sshdr.additional_length);
- }
-
- blk_mq_free_request(req);
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- ufshpb_put_pre_req(pre_req->hpb, pre_req);
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-}
-
-static int ufshpb_prep_entry(struct ufshpb_req *pre_req, struct page *page)
-{
- struct ufshpb_lu *hpb = pre_req->hpb;
- struct ufshpb_region *rgn;
- struct ufshpb_subregion *srgn;
- __be64 *addr;
- int offset = 0;
- int copied;
- unsigned long lpn = pre_req->wb.lpn;
- int rgn_idx, srgn_idx, srgn_offset;
- unsigned long flags;
-
- addr = page_address(page);
- ufshpb_get_pos_from_lpn(hpb, lpn, &rgn_idx, &srgn_idx, &srgn_offset);
-
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
-
-next_offset:
- rgn = hpb->rgn_tbl + rgn_idx;
- srgn = rgn->srgn_tbl + srgn_idx;
-
- if (!ufshpb_is_valid_srgn(rgn, srgn))
- goto mctx_error;
-
- if (!srgn->mctx)
- goto mctx_error;
-
- copied = ufshpb_fill_ppn_from_page(hpb, srgn->mctx, srgn_offset,
- pre_req->wb.len - offset,
- &addr[offset]);
-
- if (copied < 0)
- goto mctx_error;
-
- offset += copied;
- srgn_offset += copied;
-
- if (srgn_offset == hpb->entries_per_srgn) {
- srgn_offset = 0;
-
- if (++srgn_idx == hpb->srgns_per_rgn) {
- srgn_idx = 0;
- rgn_idx++;
- }
- }
-
- if (offset < pre_req->wb.len)
- goto next_offset;
-
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- return 0;
-mctx_error:
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- return -ENOMEM;
-}
-
-static int ufshpb_pre_req_add_bio_page(struct ufshpb_lu *hpb,
- struct request_queue *q,
- struct ufshpb_req *pre_req)
-{
- struct page *page = pre_req->wb.m_page;
- struct bio *bio = pre_req->bio;
- int entries_bytes, ret;
-
- if (!page)
- return -ENOMEM;
-
- if (ufshpb_prep_entry(pre_req, page))
- return -ENOMEM;
-
- entries_bytes = pre_req->wb.len * sizeof(__be64);
-
- ret = bio_add_pc_page(q, bio, page, entries_bytes, 0);
- if (ret != entries_bytes) {
- dev_err(&hpb->sdev_ufs_lu->sdev_dev,
- "bio_add_pc_page fail: %d", ret);
- return -ENOMEM;
- }
- return 0;
-}
-
-static inline int ufshpb_get_read_id(struct ufshpb_lu *hpb)
-{
- if (++hpb->cur_read_id >= MAX_HPB_READ_ID)
- hpb->cur_read_id = 1;
- return hpb->cur_read_id;
-}
-
-static int ufshpb_execute_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
- struct ufshpb_req *pre_req, int read_id)
-{
- struct scsi_device *sdev = cmd->device;
- struct request_queue *q = sdev->request_queue;
- struct request *req;
- struct scsi_request *rq;
- struct bio *bio = pre_req->bio;
-
- pre_req->hpb = hpb;
- pre_req->wb.lpn = sectors_to_logical(cmd->device,
- blk_rq_pos(scsi_cmd_to_rq(cmd)));
- pre_req->wb.len = sectors_to_logical(cmd->device,
- blk_rq_sectors(scsi_cmd_to_rq(cmd)));
- if (ufshpb_pre_req_add_bio_page(hpb, q, pre_req))
- return -ENOMEM;
-
- req = pre_req->req;
-
- /* 1. request setup */
- blk_rq_append_bio(req, bio);
- req->rq_disk = NULL;
- req->end_io_data = (void *)pre_req;
- req->end_io = ufshpb_pre_req_compl_fn;
-
- /* 2. scsi_request setup */
- rq = scsi_req(req);
- rq->retries = 1;
-
- ufshpb_set_write_buf_cmd(rq->cmd, pre_req->wb.lpn, pre_req->wb.len,
- read_id);
- rq->cmd_len = scsi_command_size(rq->cmd);
-
- if (blk_insert_cloned_request(q, req) != BLK_STS_OK)
- return -EAGAIN;
-
- hpb->stats.pre_req_cnt++;
-
- return 0;
-}
-
-static int ufshpb_issue_pre_req(struct ufshpb_lu *hpb, struct scsi_cmnd *cmd,
- int *read_id)
-{
- struct ufshpb_req *pre_req;
- struct request *req = NULL;
- unsigned long flags;
- int _read_id;
- int ret = 0;
-
- req = blk_get_request(cmd->device->request_queue,
- REQ_OP_DRV_OUT | REQ_SYNC, BLK_MQ_REQ_NOWAIT);
- if (IS_ERR(req))
- return -EAGAIN;
-
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- pre_req = ufshpb_get_pre_req(hpb);
- if (!pre_req) {
- ret = -EAGAIN;
- goto unlock_out;
- }
- _read_id = ufshpb_get_read_id(hpb);
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
-
- pre_req->req = req;
-
- ret = ufshpb_execute_pre_req(hpb, cmd, pre_req, _read_id);
- if (ret)
- goto free_pre_req;
-
- *read_id = _read_id;
-
- return ret;
-free_pre_req:
- spin_lock_irqsave(&hpb->rgn_state_lock, flags);
- ufshpb_put_pre_req(hpb, pre_req);
-unlock_out:
- spin_unlock_irqrestore(&hpb->rgn_state_lock, flags);
- blk_put_request(req);
- return ret;
-}
-
/*
* This function will set up HPB read command using host-side L2P map data.
*/
@@ -609,7 +354,6 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
__be64 ppn;
unsigned long flags;
int transfer_len, rgn_idx, srgn_idx, srgn_offset;
- int read_id = 0;
int err = 0;
hpb = ufshpb_get_hpb_data(cmd->device);
@@ -685,24 +429,8 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
dev_err(hba->dev, "get ppn failed. err %d\n", err);
return err;
}
- if (!ufshpb_is_legacy(hba) &&
- ufshpb_is_required_wb(hpb, transfer_len)) {
- err = ufshpb_issue_pre_req(hpb, cmd, &read_id);
- if (err) {
- unsigned long timeout;
-
- timeout = cmd->jiffies_at_alloc + msecs_to_jiffies(
- hpb->params.requeue_timeout_ms);
-
- if (time_before(jiffies, timeout))
- return -EAGAIN;
-
- hpb->stats.miss_cnt++;
- return 0;
- }
- }
- ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len, read_id);
+ ufshpb_set_hpb_read_to_upiu(hba, lrbp, ppn, transfer_len);
hpb->stats.hit_cnt++;
return 0;
@@ -1841,16 +1569,11 @@ static void ufshpb_lu_parameter_init(struct ufs_hba *hba,
u32 entries_per_rgn;
u64 rgn_mem_size, tmp;
- /* for pre_req */
- hpb->pre_req_min_tr_len = hpb_dev_info->max_hpb_single_cmd + 1;
-
if (ufshpb_is_legacy(hba))
hpb->pre_req_max_tr_len = HPB_LEGACY_CHUNK_HIGH;
else
hpb->pre_req_max_tr_len = HPB_MULTI_CHUNK_HIGH;
- hpb->cur_read_id = 0;
-
hpb->lu_pinned_start = hpb_lu_info->pinned_start;
hpb->lu_pinned_end = hpb_lu_info->num_pinned ?
(hpb_lu_info->pinned_start + hpb_lu_info->num_pinned - 1)
diff --git a/drivers/scsi/ufs/ufshpb.h b/drivers/scsi/ufs/ufshpb.h
index a79e07398970..f15d8fdbce2e 100644
--- a/drivers/scsi/ufs/ufshpb.h
+++ b/drivers/scsi/ufs/ufshpb.h
@@ -241,8 +241,6 @@ struct ufshpb_lu {
spinlock_t param_lock;
struct list_head lh_pre_req_free;
- int cur_read_id;
- int pre_req_min_tr_len;
int pre_req_max_tr_len;
/* cached L2P map management worker */
diff --git a/drivers/spi/spi-altera-dfl.c b/drivers/spi/spi-altera-dfl.c
index 44fc9ee13fc7..ca40923258af 100644
--- a/drivers/spi/spi-altera-dfl.c
+++ b/drivers/spi/spi-altera-dfl.c
@@ -134,7 +134,7 @@ static int dfl_spi_altera_probe(struct dfl_device *dfl_dev)
if (!master)
return -ENOMEM;
- master->bus_num = dfl_dev->id;
+ master->bus_num = -1;
hw = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-altera-platform.c b/drivers/spi/spi-altera-platform.c
index f7a7c14e3679..65147aae82a1 100644
--- a/drivers/spi/spi-altera-platform.c
+++ b/drivers/spi/spi-altera-platform.c
@@ -48,7 +48,7 @@ static int altera_spi_probe(struct platform_device *pdev)
return err;
/* setup the master state. */
- master->bus_num = pdev->id;
+ master->bus_num = -1;
if (pdata) {
if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) {
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index feebda66f56e..e4484ace584e 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -1716,12 +1716,13 @@ static int verify_controller_parameters(struct pl022 *pl022,
return -EINVAL;
}
} else {
- if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX)
+ if (chip_info->duplex != SSP_MICROWIRE_CHANNEL_FULL_DUPLEX) {
dev_err(&pl022->adev->dev,
"Microwire half duplex mode requested,"
" but this is only available in the"
" ST version of PL022\n");
- return -EINVAL;
+ return -EINVAL;
+ }
}
}
return 0;
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
index 713292b0c71e..3226c4e1c7c0 100644
--- a/drivers/spi/spi-tegra20-slink.c
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -1194,7 +1194,7 @@ static int __maybe_unused tegra_slink_runtime_suspend(struct device *dev)
return 0;
}
-static int tegra_slink_runtime_resume(struct device *dev)
+static int __maybe_unused tegra_slink_runtime_resume(struct device *dev)
{
struct spi_master *master = dev_get_drvdata(dev);
struct tegra_slink_data *tspi = spi_master_get_devdata(master);
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
index 26e3d90d1e7c..841667a896dd 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -80,6 +80,7 @@ struct vduse_dev {
struct vdpa_callback config_cb;
struct work_struct inject;
spinlock_t irq_lock;
+ struct rw_semaphore rwsem;
int minor;
bool broken;
bool connected;
@@ -410,6 +411,8 @@ static void vduse_dev_reset(struct vduse_dev *dev)
if (domain->bounce_map)
vduse_domain_reset_bounce_map(domain);
+ down_write(&dev->rwsem);
+
dev->status = 0;
dev->driver_features = 0;
dev->generation++;
@@ -443,6 +446,8 @@ static void vduse_dev_reset(struct vduse_dev *dev)
flush_work(&vq->inject);
flush_work(&vq->kick);
}
+
+ up_write(&dev->rwsem);
}
static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx,
@@ -885,6 +890,23 @@ static void vduse_vq_irq_inject(struct work_struct *work)
spin_unlock_irq(&vq->irq_lock);
}
+static int vduse_dev_queue_irq_work(struct vduse_dev *dev,
+ struct work_struct *irq_work)
+{
+ int ret = -EINVAL;
+
+ down_read(&dev->rwsem);
+ if (!(dev->status & VIRTIO_CONFIG_S_DRIVER_OK))
+ goto unlock;
+
+ ret = 0;
+ queue_work(vduse_irq_wq, irq_work);
+unlock:
+ up_read(&dev->rwsem);
+
+ return ret;
+}
+
static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
@@ -966,8 +988,7 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
break;
}
case VDUSE_DEV_INJECT_CONFIG_IRQ:
- ret = 0;
- queue_work(vduse_irq_wq, &dev->inject);
+ ret = vduse_dev_queue_irq_work(dev, &dev->inject);
break;
case VDUSE_VQ_SETUP: {
struct vduse_vq_config config;
@@ -1053,9 +1074,8 @@ static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
if (index >= dev->vq_num)
break;
- ret = 0;
index = array_index_nospec(index, dev->vq_num);
- queue_work(vduse_irq_wq, &dev->vqs[index].inject);
+ ret = vduse_dev_queue_irq_work(dev, &dev->vqs[index].inject);
break;
}
default:
@@ -1136,6 +1156,7 @@ static struct vduse_dev *vduse_dev_create(void)
INIT_LIST_HEAD(&dev->send_list);
INIT_LIST_HEAD(&dev->recv_list);
spin_lock_init(&dev->irq_lock);
+ init_rwsem(&dev->rwsem);
INIT_WORK(&dev->inject, vduse_dev_irq_inject);
init_waitqueue_head(&dev->waitq);
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index dd95dfd85e98..3035bb6f5458 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -576,7 +576,7 @@ static inline int virtqueue_add_split(struct virtqueue *_vq,
/* Last one doesn't continue. */
desc[prev].flags &= cpu_to_virtio16(_vq->vdev, ~VRING_DESC_F_NEXT);
if (!indirect && vq->use_dma_api)
- vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags =
+ vq->split.desc_extra[prev & (vq->split.vring.num - 1)].flags &=
~VRING_DESC_F_NEXT;
if (indirect) {
diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c
index 643c6c2d0b72..ced2fc0deb8c 100644
--- a/drivers/watchdog/iTCO_wdt.c
+++ b/drivers/watchdog/iTCO_wdt.c
@@ -71,8 +71,6 @@
#define TCOBASE(p) ((p)->tco_res->start)
/* SMI Control and Enable Register */
#define SMI_EN(p) ((p)->smi_res->start)
-#define TCO_EN (1 << 13)
-#define GBL_SMI_EN (1 << 0)
#define TCO_RLD(p) (TCOBASE(p) + 0x00) /* TCO Timer Reload/Curr. Value */
#define TCOv1_TMR(p) (TCOBASE(p) + 0x01) /* TCOv1 Timer Initial Value*/
@@ -357,12 +355,8 @@ static int iTCO_wdt_set_timeout(struct watchdog_device *wd_dev, unsigned int t)
tmrval = seconds_to_ticks(p, t);
- /*
- * If TCO SMIs are off, the timer counts down twice before rebooting.
- * Otherwise, the BIOS generally reboots when the SMI triggers.
- */
- if (p->smi_res &&
- (inl(SMI_EN(p)) & (TCO_EN | GBL_SMI_EN)) != (TCO_EN | GBL_SMI_EN))
+ /* For TCO v1 the timer counts down twice before rebooting */
+ if (p->iTCO_version == 1)
tmrval /= 2;
/* from the specs: */
@@ -527,7 +521,7 @@ static int iTCO_wdt_probe(struct platform_device *pdev)
* Disables TCO logic generating an SMI#
*/
val32 = inl(SMI_EN(p));
- val32 &= ~TCO_EN; /* Turn off SMI clearing watchdog */
+ val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */
outl(val32, SMI_EN(p));
}
diff --git a/drivers/watchdog/ixp4xx_wdt.c b/drivers/watchdog/ixp4xx_wdt.c
index 2693ffb24ac7..31b03fa71341 100644
--- a/drivers/watchdog/ixp4xx_wdt.c
+++ b/drivers/watchdog/ixp4xx_wdt.c
@@ -119,7 +119,7 @@ static int ixp4xx_wdt_probe(struct platform_device *pdev)
iwdt = devm_kzalloc(dev, sizeof(*iwdt), GFP_KERNEL);
if (!iwdt)
return -ENOMEM;
- iwdt->base = dev->platform_data;
+ iwdt->base = (void __iomem *)dev->platform_data;
/*
* Retrieve rate from a fixed clock from the device tree if
diff --git a/drivers/watchdog/omap_wdt.c b/drivers/watchdog/omap_wdt.c
index 1616f93dfad7..74d785b2b478 100644
--- a/drivers/watchdog/omap_wdt.c
+++ b/drivers/watchdog/omap_wdt.c
@@ -268,8 +268,12 @@ static int omap_wdt_probe(struct platform_device *pdev)
wdev->wdog.bootstatus = WDIOF_CARDRESET;
}
- if (!early_enable)
+ if (early_enable) {
+ omap_wdt_start(&wdev->wdog);
+ set_bit(WDOG_HW_RUNNING, &wdev->wdog.status);
+ } else {
omap_wdt_disable(wdev);
+ }
ret = watchdog_register_device(&wdev->wdog);
if (ret) {
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index ee9ff38929eb..9791c74aebd4 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -130,7 +130,7 @@ static u64 sbsa_gwdt_reg_read(struct sbsa_gwdt *gwdt)
if (gwdt->version == 0)
return readl(gwdt->control_base + SBSA_GWDT_WOR);
else
- return readq(gwdt->control_base + SBSA_GWDT_WOR);
+ return lo_hi_readq(gwdt->control_base + SBSA_GWDT_WOR);
}
static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt)
@@ -138,7 +138,7 @@ static void sbsa_gwdt_reg_write(u64 val, struct sbsa_gwdt *gwdt)
if (gwdt->version == 0)
writel((u32)val, gwdt->control_base + SBSA_GWDT_WOR);
else
- writeq(val, gwdt->control_base + SBSA_GWDT_WOR);
+ lo_hi_writeq(val, gwdt->control_base + SBSA_GWDT_WOR);
}
/*
@@ -411,4 +411,3 @@ MODULE_AUTHOR("Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>");
MODULE_AUTHOR("Al Stone <al.stone@linaro.org>");
MODULE_AUTHOR("Timur Tabi <timur@codeaurora.org>");
MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/fs/afs/write.c b/fs/afs/write.c
index f24370f5c774..8b1d9c2f6bec 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -861,7 +861,8 @@ int afs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
*/
vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
{
- struct page *page = thp_head(vmf->page);
+ struct folio *folio = page_folio(vmf->page);
+ struct page *page = &folio->page;
struct file *file = vmf->vma->vm_file;
struct inode *inode = file_inode(file);
struct afs_vnode *vnode = AFS_FS_I(inode);
@@ -884,7 +885,7 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
goto out;
#endif
- if (wait_on_page_writeback_killable(page))
+ if (folio_wait_writeback_killable(folio))
goto out;
if (lock_page_killable(page) < 0)
@@ -894,8 +895,8 @@ vm_fault_t afs_page_mkwrite(struct vm_fault *vmf)
* details the portion of the page we need to write back and we might
* need to redirty the page if there's a problem.
*/
- if (wait_on_page_writeback_killable(page) < 0) {
- unlock_page(page);
+ if (folio_wait_writeback_killable(folio) < 0) {
+ folio_unlock(folio);
goto out;
}
diff --git a/fs/autofs/waitq.c b/fs/autofs/waitq.c
index 16b5fca0626e..54c1f8b8b075 100644
--- a/fs/autofs/waitq.c
+++ b/fs/autofs/waitq.c
@@ -358,7 +358,7 @@ int autofs_wait(struct autofs_sb_info *sbi,
qstr.len = strlen(p);
offset = p - name;
}
- qstr.hash = full_name_hash(dentry, name, qstr.len);
+ qstr.hash = full_name_hash(dentry, qstr.name, qstr.len);
if (mutex_lock_interruptible(&sbi->wq_mutex)) {
kfree(name);
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index ddc4f5436cc9..6c7eb80220ca 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -173,9 +173,10 @@ static int check_compressed_csum(struct btrfs_inode *inode, struct bio *bio,
/* Hash through the page sector by sector */
for (pg_offset = 0; pg_offset < bytes_left;
pg_offset += sectorsize) {
- kaddr = page_address(page);
+ kaddr = kmap_atomic(page);
crypto_shash_digest(shash, kaddr + pg_offset,
sectorsize, csum);
+ kunmap_atomic(kaddr);
if (memcmp(&csum, cb_sum, csum_size) != 0) {
btrfs_print_data_csum_error(inode, disk_start,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 04090ba0ef73..954b53a90f04 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -288,8 +288,9 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
cur_size = min_t(unsigned long, compressed_size,
PAGE_SIZE);
- kaddr = page_address(cpage);
+ kaddr = kmap_atomic(cpage);
write_extent_buffer(leaf, kaddr, ptr, cur_size);
+ kunmap_atomic(kaddr);
i++;
ptr += cur_size;
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index c25dfd1a8a54..3dbe6eb5fda7 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -141,7 +141,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
*total_in = 0;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
/*
* store the size of all chunks of compressed data in
@@ -152,7 +152,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
out_offset = LZO_LEN;
tot_out = LZO_LEN;
pages[0] = out_page;
@@ -210,6 +210,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
if (out_len == 0 && tot_in >= len)
break;
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -221,7 +222,7 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[nr_pages++] = out_page;
pg_bytes_left = PAGE_SIZE;
@@ -243,11 +244,12 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
break;
bytes_left = len - tot_in;
+ kunmap(in_page);
put_page(in_page);
start += PAGE_SIZE;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
in_len = min(bytes_left, PAGE_SIZE);
}
@@ -257,17 +259,22 @@ int lzo_compress_pages(struct list_head *ws, struct address_space *mapping,
}
/* store the size of all chunks of compressed data */
- sizes_ptr = page_address(pages[0]);
+ sizes_ptr = kmap_local_page(pages[0]);
write_compress_length(sizes_ptr, tot_out);
+ kunmap_local(sizes_ptr);
ret = 0;
*total_out = tot_out;
*total_in = tot_in;
out:
*out_pages = nr_pages;
+ if (out_page)
+ kunmap(out_page);
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
return ret;
}
@@ -283,6 +290,7 @@ static void copy_compressed_segment(struct compressed_bio *cb,
u32 orig_in = *cur_in;
while (*cur_in < orig_in + len) {
+ char *kaddr;
struct page *cur_page;
u32 copy_len = min_t(u32, PAGE_SIZE - offset_in_page(*cur_in),
orig_in + len - *cur_in);
@@ -290,9 +298,11 @@ static void copy_compressed_segment(struct compressed_bio *cb,
ASSERT(copy_len);
cur_page = cb->compressed_pages[*cur_in / PAGE_SIZE];
+ kaddr = kmap(cur_page);
memcpy(dest + *cur_in - orig_in,
- page_address(cur_page) + offset_in_page(*cur_in),
+ kaddr + offset_in_page(*cur_in),
copy_len);
+ kunmap(cur_page);
*cur_in += copy_len;
}
@@ -303,6 +313,7 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
struct workspace *workspace = list_entry(ws, struct workspace, list);
const struct btrfs_fs_info *fs_info = btrfs_sb(cb->inode->i_sb);
const u32 sectorsize = fs_info->sectorsize;
+ char *kaddr;
int ret;
/* Compressed data length, can be unaligned */
u32 len_in;
@@ -311,7 +322,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
/* Bytes decompressed so far */
u32 cur_out = 0;
- len_in = read_compress_length(page_address(cb->compressed_pages[0]));
+ kaddr = kmap(cb->compressed_pages[0]);
+ len_in = read_compress_length(kaddr);
+ kunmap(cb->compressed_pages[0]);
cur_in += LZO_LEN;
/*
@@ -344,9 +357,9 @@ int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
ASSERT(cur_in / sectorsize ==
(cur_in + LZO_LEN - 1) / sectorsize);
cur_page = cb->compressed_pages[cur_in / PAGE_SIZE];
+ kaddr = kmap(cur_page);
ASSERT(cur_page);
- seg_len = read_compress_length(page_address(cur_page) +
- offset_in_page(cur_in));
+ seg_len = read_compress_length(kaddr + offset_in_page(cur_in));
cur_in += LZO_LEN;
/* Copy the compressed segment payload into workspace */
@@ -431,7 +444,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
destlen = min_t(unsigned long, destlen, PAGE_SIZE);
bytes = min_t(unsigned long, destlen, out_len - start_byte);
- kaddr = page_address(dest_page);
+ kaddr = kmap_local_page(dest_page);
memcpy(kaddr, workspace->buf + start_byte, bytes);
/*
@@ -441,6 +454,7 @@ int lzo_decompress(struct list_head *ws, unsigned char *data_in,
*/
if (bytes < destlen)
memset(kaddr+bytes, 0, destlen-bytes);
+ kunmap_local(kaddr);
out:
return ret;
}
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 8afa90074891..767a0c6c9694 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -126,7 +126,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[0] = out_page;
nr_pages = 1;
@@ -148,22 +148,26 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
int i;
for (i = 0; i < in_buf_pages; i++) {
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
in_page = find_get_page(mapping,
start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
memcpy(workspace->buf + i * PAGE_SIZE,
data_in, PAGE_SIZE);
start += PAGE_SIZE;
}
workspace->strm.next_in = workspace->buf;
} else {
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
in_page = find_get_page(mapping,
start >> PAGE_SHIFT);
- data_in = page_address(in_page);
+ data_in = kmap(in_page);
start += PAGE_SIZE;
workspace->strm.next_in = data_in;
}
@@ -192,6 +196,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
* the stream end if required
*/
if (workspace->strm.avail_out == 0) {
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -202,7 +207,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[nr_pages] = out_page;
nr_pages++;
workspace->strm.avail_out = PAGE_SIZE;
@@ -229,6 +234,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
} else if (workspace->strm.avail_out == 0) {
/* get another page for the stream end */
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -239,7 +245,7 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
ret = -ENOMEM;
goto out;
}
- cpage_out = page_address(out_page);
+ cpage_out = kmap(out_page);
pages[nr_pages] = out_page;
nr_pages++;
workspace->strm.avail_out = PAGE_SIZE;
@@ -258,8 +264,13 @@ int zlib_compress_pages(struct list_head *ws, struct address_space *mapping,
*total_in = workspace->strm.total_in;
out:
*out_pages = nr_pages;
- if (in_page)
+ if (out_page)
+ kunmap(out_page);
+
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
return ret;
}
@@ -276,7 +287,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
unsigned long buf_start;
struct page **pages_in = cb->compressed_pages;
- data_in = page_address(pages_in[page_in_index]);
+ data_in = kmap(pages_in[page_in_index]);
workspace->strm.next_in = data_in;
workspace->strm.avail_in = min_t(size_t, srclen, PAGE_SIZE);
workspace->strm.total_in = 0;
@@ -298,6 +309,7 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
if (Z_OK != zlib_inflateInit2(&workspace->strm, wbits)) {
pr_warn("BTRFS: inflateInit failed\n");
+ kunmap(pages_in[page_in_index]);
return -EIO;
}
while (workspace->strm.total_in < srclen) {
@@ -324,13 +336,13 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
if (workspace->strm.avail_in == 0) {
unsigned long tmp;
-
+ kunmap(pages_in[page_in_index]);
page_in_index++;
if (page_in_index >= total_pages_in) {
data_in = NULL;
break;
}
- data_in = page_address(pages_in[page_in_index]);
+ data_in = kmap(pages_in[page_in_index]);
workspace->strm.next_in = data_in;
tmp = srclen - workspace->strm.total_in;
workspace->strm.avail_in = min(tmp, PAGE_SIZE);
@@ -342,6 +354,8 @@ int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
ret = 0;
done:
zlib_inflateEnd(&workspace->strm);
+ if (data_in)
+ kunmap(pages_in[page_in_index]);
if (!ret)
zero_fill_bio(cb->orig_bio);
return ret;
diff --git a/fs/btrfs/zstd.c b/fs/btrfs/zstd.c
index 56dce9f00988..f06b68040352 100644
--- a/fs/btrfs/zstd.c
+++ b/fs/btrfs/zstd.c
@@ -399,7 +399,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
/* map in the first page of input data */
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- workspace->in_buf.src = page_address(in_page);
+ workspace->in_buf.src = kmap(in_page);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
@@ -411,7 +411,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
@@ -446,6 +446,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
if (workspace->out_buf.pos == workspace->out_buf.size) {
tot_out += PAGE_SIZE;
max_out -= PAGE_SIZE;
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -457,7 +458,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out,
PAGE_SIZE);
@@ -472,12 +473,13 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
/* Check if we need more input */
if (workspace->in_buf.pos == workspace->in_buf.size) {
tot_in += PAGE_SIZE;
+ kunmap(in_page);
put_page(in_page);
start += PAGE_SIZE;
len -= PAGE_SIZE;
in_page = find_get_page(mapping, start >> PAGE_SHIFT);
- workspace->in_buf.src = page_address(in_page);
+ workspace->in_buf.src = kmap(in_page);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, len, PAGE_SIZE);
}
@@ -504,6 +506,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
tot_out += PAGE_SIZE;
max_out -= PAGE_SIZE;
+ kunmap(out_page);
if (nr_pages == nr_dest_pages) {
out_page = NULL;
ret = -E2BIG;
@@ -515,7 +518,7 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
goto out;
}
pages[nr_pages++] = out_page;
- workspace->out_buf.dst = page_address(out_page);
+ workspace->out_buf.dst = kmap(out_page);
workspace->out_buf.pos = 0;
workspace->out_buf.size = min_t(size_t, max_out, PAGE_SIZE);
}
@@ -531,8 +534,12 @@ int zstd_compress_pages(struct list_head *ws, struct address_space *mapping,
out:
*out_pages = nr_pages;
/* Cleanup */
- if (in_page)
+ if (in_page) {
+ kunmap(in_page);
put_page(in_page);
+ }
+ if (out_page)
+ kunmap(out_page);
return ret;
}
@@ -556,7 +563,7 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
goto done;
}
- workspace->in_buf.src = page_address(pages_in[page_in_index]);
+ workspace->in_buf.src = kmap(pages_in[page_in_index]);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
@@ -592,14 +599,14 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
break;
if (workspace->in_buf.pos == workspace->in_buf.size) {
- page_in_index++;
+ kunmap(pages_in[page_in_index++]);
if (page_in_index >= total_pages_in) {
workspace->in_buf.src = NULL;
ret = -EIO;
goto done;
}
srclen -= PAGE_SIZE;
- workspace->in_buf.src = page_address(pages_in[page_in_index]);
+ workspace->in_buf.src = kmap(pages_in[page_in_index]);
workspace->in_buf.pos = 0;
workspace->in_buf.size = min_t(size_t, srclen, PAGE_SIZE);
}
@@ -607,6 +614,8 @@ int zstd_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
ret = 0;
zero_fill_bio(cb->orig_bio);
done:
+ if (workspace->in_buf.src)
+ kunmap(pages_in[page_in_index]);
return ret;
}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 8ffc40e84a59..fcf4f3b72923 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -25,20 +25,20 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
struct cachefiles_object *object;
struct fscache_retrieval *op = monitor->op;
struct wait_page_key *key = _key;
- struct page *page = wait->private;
+ struct folio *folio = wait->private;
ASSERT(key);
_enter("{%lu},%u,%d,{%p,%u}",
monitor->netfs_page->index, mode, sync,
- key->page, key->bit_nr);
+ key->folio, key->bit_nr);
- if (key->page != page || key->bit_nr != PG_locked)
+ if (key->folio != folio || key->bit_nr != PG_locked)
return 0;
- _debug("--- monitor %p %lx ---", page, page->flags);
+ _debug("--- monitor %p %lx ---", folio, folio->flags);
- if (!PageUptodate(page) && !PageError(page)) {
+ if (!folio_test_uptodate(folio) && !folio_test_error(folio)) {
/* unlocked, not uptodate and not erronous? */
_debug("page probably truncated");
}
@@ -107,7 +107,7 @@ static int cachefiles_read_reissue(struct cachefiles_object *object,
put_page(backpage2);
INIT_LIST_HEAD(&monitor->op_link);
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
if (trylock_page(backpage)) {
ret = -EIO;
@@ -294,7 +294,7 @@ monitor_backing_page:
get_page(backpage);
monitor->back_page = backpage;
monitor->monitor.private = backpage;
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
monitor = NULL;
/* but the page may have been read before the monitor was installed, so
@@ -548,7 +548,7 @@ static int cachefiles_read_backing_file(struct cachefiles_object *object,
get_page(backpage);
monitor->back_page = backpage;
monitor->monitor.private = backpage;
- add_page_wait_queue(backpage, &monitor->monitor);
+ folio_add_wait_queue(page_folio(backpage), &monitor->monitor);
monitor = NULL;
/* but the page may have been read before the monitor was
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 3e42d0466521..8f537f1d9d1d 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2330,7 +2330,6 @@ retry:
int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
- struct ceph_file_info *fi = file->private_data;
struct inode *inode = file->f_mapping->host;
struct ceph_inode_info *ci = ceph_inode(inode);
u64 flush_tid;
@@ -2365,14 +2364,9 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
if (err < 0)
ret = err;
- if (errseq_check(&ci->i_meta_err, READ_ONCE(fi->meta_err))) {
- spin_lock(&file->f_lock);
- err = errseq_check_and_advance(&ci->i_meta_err,
- &fi->meta_err);
- spin_unlock(&file->f_lock);
- if (err < 0)
- ret = err;
- }
+ err = file_check_and_advance_wb_err(file);
+ if (err < 0)
+ ret = err;
out:
dout("fsync %p%s result=%d\n", inode, datasync ? " datasync" : "", ret);
return ret;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d16fd2d5fd42..e61018d9764e 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -233,7 +233,6 @@ static int ceph_init_file_info(struct inode *inode, struct file *file,
spin_lock_init(&fi->rw_contexts_lock);
INIT_LIST_HEAD(&fi->rw_contexts);
- fi->meta_err = errseq_sample(&ci->i_meta_err);
fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);
return 0;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 2df1e1284451..1c7574105478 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -541,8 +541,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
ceph_fscache_inode_init(ci);
- ci->i_meta_err = 0;
-
return &ci->vfs_inode;
}
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index bdeb271f47d9..d8c31069fbf2 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -302,9 +302,6 @@ int ceph_flock(struct file *file, int cmd, struct file_lock *fl)
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- /* No mandatory locks */
- if (fl->fl_type & LOCK_MAND)
- return -EOPNOTSUPP;
dout("ceph_flock, fl_file: %p\n", fl->fl_file);
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 7cad180d6deb..d64413adc0fd 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -1493,7 +1493,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
{
struct ceph_mds_request *req;
struct rb_node *p;
- struct ceph_inode_info *ci;
dout("cleanup_session_requests mds%d\n", session->s_mds);
mutex_lock(&mdsc->mutex);
@@ -1502,16 +1501,10 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
struct ceph_mds_request, r_unsafe_item);
pr_warn_ratelimited(" dropping unsafe request %llu\n",
req->r_tid);
- if (req->r_target_inode) {
- /* dropping unsafe change of inode's attributes */
- ci = ceph_inode(req->r_target_inode);
- errseq_set(&ci->i_meta_err, -EIO);
- }
- if (req->r_unsafe_dir) {
- /* dropping unsafe directory operation */
- ci = ceph_inode(req->r_unsafe_dir);
- errseq_set(&ci->i_meta_err, -EIO);
- }
+ if (req->r_target_inode)
+ mapping_set_error(req->r_target_inode->i_mapping, -EIO);
+ if (req->r_unsafe_dir)
+ mapping_set_error(req->r_unsafe_dir->i_mapping, -EIO);
__unregister_request(mdsc, req);
}
/* zero r_attempts, so kick_requests() will re-send requests */
@@ -1678,7 +1671,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
spin_unlock(&mdsc->cap_dirty_lock);
if (dirty_dropped) {
- errseq_set(&ci->i_meta_err, -EIO);
+ mapping_set_error(inode->i_mapping, -EIO);
if (ci->i_wrbuffer_ref_head == 0 &&
ci->i_wr_ref == 0 &&
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 9b1b7f4cfdd4..fd8742bae847 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1002,16 +1002,16 @@ static int ceph_compare_super(struct super_block *sb, struct fs_context *fc)
struct ceph_fs_client *new = fc->s_fs_info;
struct ceph_mount_options *fsopt = new->mount_options;
struct ceph_options *opt = new->client->options;
- struct ceph_fs_client *other = ceph_sb_to_client(sb);
+ struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
dout("ceph_compare_super %p\n", sb);
- if (compare_mount_options(fsopt, opt, other)) {
+ if (compare_mount_options(fsopt, opt, fsc)) {
dout("monitor(s)/mount options don't match\n");
return 0;
}
if ((opt->flags & CEPH_OPT_FSID) &&
- ceph_fsid_compare(&opt->fsid, &other->client->fsid)) {
+ ceph_fsid_compare(&opt->fsid, &fsc->client->fsid)) {
dout("fsid doesn't match\n");
return 0;
}
@@ -1019,6 +1019,17 @@ static int ceph_compare_super(struct super_block *sb, struct fs_context *fc)
dout("flags differ\n");
return 0;
}
+
+ if (fsc->blocklisted && !ceph_test_mount_opt(fsc, CLEANRECOVER)) {
+ dout("client is blocklisted (and CLEANRECOVER is not set)\n");
+ return 0;
+ }
+
+ if (fsc->mount_state == CEPH_MOUNT_SHUTDOWN) {
+ dout("client has been forcibly unmounted\n");
+ return 0;
+ }
+
return 1;
}
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a40eb14c282a..14f951cd5b61 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -429,8 +429,6 @@ struct ceph_inode_info {
#ifdef CONFIG_CEPH_FSCACHE
struct fscache_cookie *fscache;
#endif
- errseq_t i_meta_err;
-
struct inode vfs_inode; /* at end */
};
@@ -774,7 +772,6 @@ struct ceph_file_info {
spinlock_t rw_contexts_lock;
struct list_head rw_contexts;
- errseq_t meta_err;
u32 filp_gen;
atomic_t num_locks;
};
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 81ec192ce067..4124a89a1a5d 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1893,7 +1893,8 @@ static long writeback_sb_inodes(struct super_block *sb,
* unplug, so get our IOs out the door before we
* give up the CPU.
*/
- blk_flush_plug(current);
+ if (current->plug)
+ blk_flush_plug(current->plug, false);
cond_resched();
}
@@ -2291,7 +2292,7 @@ void wakeup_flusher_threads(enum wb_reason reason)
* If we are expecting writeback progress we must submit plugged IO.
*/
if (blk_needs_flush_plug(current))
- blk_schedule_flush_plug(current);
+ blk_flush_plug(current->plug, true);
rcu_read_lock();
list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 319596df5dc6..f55f9f94b1a4 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1121,6 +1121,9 @@ int fuse_init_fs_context_submount(struct fs_context *fsc);
*/
void fuse_conn_destroy(struct fuse_mount *fm);
+/* Drop the connection and free the fuse mount */
+void fuse_mount_destroy(struct fuse_mount *fm);
+
/**
* Add connection to control filesystem
*/
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 36cd03114b6d..12d49a1914e8 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -457,14 +457,6 @@ static void fuse_send_destroy(struct fuse_mount *fm)
}
}
-static void fuse_put_super(struct super_block *sb)
-{
- struct fuse_mount *fm = get_fuse_mount_super(sb);
-
- fuse_conn_put(fm->fc);
- kfree(fm);
-}
-
static void convert_fuse_statfs(struct kstatfs *stbuf, struct fuse_kstatfs *attr)
{
stbuf->f_type = FUSE_SUPER_MAGIC;
@@ -1003,7 +995,6 @@ static const struct super_operations fuse_super_operations = {
.evict_inode = fuse_evict_inode,
.write_inode = fuse_write_inode,
.drop_inode = generic_delete_inode,
- .put_super = fuse_put_super,
.umount_begin = fuse_umount_begin,
.statfs = fuse_statfs,
.sync_fs = fuse_sync_fs,
@@ -1424,20 +1415,17 @@ static int fuse_get_tree_submount(struct fs_context *fsc)
if (!fm)
return -ENOMEM;
+ fm->fc = fuse_conn_get(fc);
fsc->s_fs_info = fm;
sb = sget_fc(fsc, NULL, set_anon_super_fc);
- if (IS_ERR(sb)) {
- kfree(fm);
+ if (fsc->s_fs_info)
+ fuse_mount_destroy(fm);
+ if (IS_ERR(sb))
return PTR_ERR(sb);
- }
- fm->fc = fuse_conn_get(fc);
/* Initialize superblock, making @mp_fi its root */
err = fuse_fill_super_submount(sb, mp_fi);
if (err) {
- fuse_conn_put(fc);
- kfree(fm);
- sb->s_fs_info = NULL;
deactivate_locked_super(sb);
return err;
}
@@ -1569,8 +1557,6 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc)
{
struct fuse_fs_context *ctx = fsc->fs_private;
int err;
- struct fuse_conn *fc;
- struct fuse_mount *fm;
if (!ctx->file || !ctx->rootmode_present ||
!ctx->user_id_present || !ctx->group_id_present)
@@ -1580,42 +1566,18 @@ static int fuse_fill_super(struct super_block *sb, struct fs_context *fsc)
* Require mount to happen from the same user namespace which
* opened /dev/fuse to prevent potential attacks.
*/
- err = -EINVAL;
if ((ctx->file->f_op != &fuse_dev_operations) ||
(ctx->file->f_cred->user_ns != sb->s_user_ns))
- goto err;
+ return -EINVAL;
ctx->fudptr = &ctx->file->private_data;
- fc = kmalloc(sizeof(*fc), GFP_KERNEL);
- err = -ENOMEM;
- if (!fc)
- goto err;
-
- fm = kzalloc(sizeof(*fm), GFP_KERNEL);
- if (!fm) {
- kfree(fc);
- goto err;
- }
-
- fuse_conn_init(fc, fm, sb->s_user_ns, &fuse_dev_fiq_ops, NULL);
- fc->release = fuse_free_conn;
-
- sb->s_fs_info = fm;
-
err = fuse_fill_super_common(sb, ctx);
if (err)
- goto err_put_conn;
+ return err;
/* file->private_data shall be visible on all CPUs after this */
smp_mb();
fuse_send_init(get_fuse_mount_super(sb));
return 0;
-
- err_put_conn:
- fuse_conn_put(fc);
- kfree(fm);
- sb->s_fs_info = NULL;
- err:
- return err;
}
/*
@@ -1637,22 +1599,40 @@ static int fuse_get_tree(struct fs_context *fsc)
{
struct fuse_fs_context *ctx = fsc->fs_private;
struct fuse_dev *fud;
+ struct fuse_conn *fc;
+ struct fuse_mount *fm;
struct super_block *sb;
int err;
+ fc = kmalloc(sizeof(*fc), GFP_KERNEL);
+ if (!fc)
+ return -ENOMEM;
+
+ fm = kzalloc(sizeof(*fm), GFP_KERNEL);
+ if (!fm) {
+ kfree(fc);
+ return -ENOMEM;
+ }
+
+ fuse_conn_init(fc, fm, fsc->user_ns, &fuse_dev_fiq_ops, NULL);
+ fc->release = fuse_free_conn;
+
+ fsc->s_fs_info = fm;
+
if (ctx->fd_present)
ctx->file = fget(ctx->fd);
if (IS_ENABLED(CONFIG_BLOCK) && ctx->is_bdev) {
err = get_tree_bdev(fsc, fuse_fill_super);
- goto out_fput;
+ goto out;
}
/*
* While block dev mount can be initialized with a dummy device fd
* (found by device name), normal fuse mounts can't
*/
+ err = -EINVAL;
if (!ctx->file)
- return -EINVAL;
+ goto out;
/*
* Allow creating a fuse mount with an already initialized fuse
@@ -1668,7 +1648,9 @@ static int fuse_get_tree(struct fs_context *fsc)
} else {
err = get_tree_nodev(fsc, fuse_fill_super);
}
-out_fput:
+out:
+ if (fsc->s_fs_info)
+ fuse_mount_destroy(fm);
if (ctx->file)
fput(ctx->file);
return err;
@@ -1747,17 +1729,25 @@ static void fuse_sb_destroy(struct super_block *sb)
struct fuse_mount *fm = get_fuse_mount_super(sb);
bool last;
- if (fm) {
+ if (sb->s_root) {
last = fuse_mount_remove(fm);
if (last)
fuse_conn_destroy(fm);
}
}
+void fuse_mount_destroy(struct fuse_mount *fm)
+{
+ fuse_conn_put(fm->fc);
+ kfree(fm);
+}
+EXPORT_SYMBOL(fuse_mount_destroy);
+
static void fuse_kill_sb_anon(struct super_block *sb)
{
fuse_sb_destroy(sb);
kill_anon_super(sb);
+ fuse_mount_destroy(get_fuse_mount_super(sb));
}
static struct file_system_type fuse_fs_type = {
@@ -1775,6 +1765,7 @@ static void fuse_kill_sb_blk(struct super_block *sb)
{
fuse_sb_destroy(sb);
kill_block_super(sb);
+ fuse_mount_destroy(get_fuse_mount_super(sb));
}
static struct file_system_type fuseblk_fs_type = {
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 0ad89c6629d7..94fc874f5de7 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -1394,12 +1394,13 @@ static void virtio_kill_sb(struct super_block *sb)
bool last;
/* If mount failed, we can still be called without any fc */
- if (fm) {
+ if (sb->s_root) {
last = fuse_mount_remove(fm);
if (last)
virtio_fs_conn_destroy(fm);
}
kill_anon_super(sb);
+ fuse_mount_destroy(fm);
}
static int virtio_fs_test_super(struct super_block *sb,
@@ -1455,19 +1456,14 @@ static int virtio_fs_get_tree(struct fs_context *fsc)
fsc->s_fs_info = fm;
sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc);
- if (fsc->s_fs_info) {
- fuse_conn_put(fc);
- kfree(fm);
- }
+ if (fsc->s_fs_info)
+ fuse_mount_destroy(fm);
if (IS_ERR(sb))
return PTR_ERR(sb);
if (!sb->s_root) {
err = virtio_fs_fill_super(sb, fsc);
if (err) {
- fuse_conn_put(fc);
- kfree(fm);
- sb->s_fs_info = NULL;
deactivate_locked_super(sb);
return err;
}
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 635f0e3f10ec..5436a688157a 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1338,8 +1338,6 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
{
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- if (fl->fl_type & LOCK_MAND)
- return -EOPNOTSUPP;
if (fl->fl_type == F_UNLCK) {
do_unflock(file, fl);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 5bf8aa81715e..38b33ad9e8cf 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker);
static bool io_acct_cancel_pending_work(struct io_wqe *wqe,
struct io_wqe_acct *acct,
struct io_cb_cancel_data *match);
+static void create_worker_cb(struct callback_head *cb);
static bool io_worker_get(struct io_worker *worker)
{
@@ -174,12 +175,46 @@ static void io_worker_ref_put(struct io_wq *wq)
complete(&wq->worker_done);
}
+static void io_worker_cancel_cb(struct io_worker *worker)
+{
+ struct io_wqe_acct *acct = io_wqe_get_acct(worker);
+ struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
+
+ atomic_dec(&acct->nr_running);
+ raw_spin_lock(&worker->wqe->lock);
+ acct->nr_workers--;
+ raw_spin_unlock(&worker->wqe->lock);
+ io_worker_ref_put(wq);
+ clear_bit_unlock(0, &worker->create_state);
+ io_worker_release(worker);
+}
+
+static bool io_task_worker_match(struct callback_head *cb, void *data)
+{
+ struct io_worker *worker;
+
+ if (cb->func != create_worker_cb)
+ return false;
+ worker = container_of(cb, struct io_worker, create_work);
+ return worker == data;
+}
+
static void io_worker_exit(struct io_worker *worker)
{
struct io_wqe *wqe = worker->wqe;
+ struct io_wq *wq = wqe->wq;
- if (refcount_dec_and_test(&worker->ref))
- complete(&worker->ref_done);
+ while (1) {
+ struct callback_head *cb = task_work_cancel_match(wq->task,
+ io_task_worker_match, worker);
+
+ if (!cb)
+ break;
+ io_worker_cancel_cb(worker);
+ }
+
+ io_worker_release(worker);
wait_for_completion(&worker->ref_done);
raw_spin_lock(&wqe->lock);
@@ -253,7 +288,7 @@ static bool io_wqe_create_worker(struct io_wqe *wqe, struct io_wqe_acct *acct)
pr_warn_once("io-wq is not configured for unbound workers");
raw_spin_lock(&wqe->lock);
- if (acct->nr_workers == acct->max_workers) {
+ if (acct->nr_workers >= acct->max_workers) {
raw_spin_unlock(&wqe->lock);
return true;
}
@@ -323,8 +358,10 @@ static bool io_queue_worker_create(struct io_worker *worker,
init_task_work(&worker->create_work, func);
worker->create_index = acct->index;
- if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL))
+ if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) {
+ clear_bit_unlock(0, &worker->create_state);
return true;
+ }
clear_bit_unlock(0, &worker->create_state);
fail_release:
io_worker_release(worker);
@@ -716,11 +753,8 @@ static void io_workqueue_create(struct work_struct *work)
struct io_worker *worker = container_of(work, struct io_worker, work);
struct io_wqe_acct *acct = io_wqe_get_acct(worker);
- if (!io_queue_worker_create(worker, acct, create_worker_cont)) {
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
+ if (!io_queue_worker_create(worker, acct, create_worker_cont))
kfree(worker);
- }
}
static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index)
@@ -1150,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq)
while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
struct io_worker *worker;
- struct io_wqe_acct *acct;
worker = container_of(cb, struct io_worker, create_work);
- acct = io_wqe_get_acct(worker);
- atomic_dec(&acct->nr_running);
- raw_spin_lock(&worker->wqe->lock);
- acct->nr_workers--;
- raw_spin_unlock(&worker->wqe->lock);
- io_worker_ref_put(wq);
- clear_bit_unlock(0, &worker->create_state);
- io_worker_release(worker);
+ io_worker_cancel_cb(worker);
}
rcu_read_lock();
@@ -1291,15 +1317,18 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count)
rcu_read_lock();
for_each_node(node) {
+ struct io_wqe *wqe = wq->wqes[node];
struct io_wqe_acct *acct;
+ raw_spin_lock(&wqe->lock);
for (i = 0; i < IO_WQ_ACCT_NR; i++) {
- acct = &wq->wqes[node]->acct[i];
+ acct = &wqe->acct[i];
prev = max_t(int, acct->max_workers, prev);
if (new_count[i])
acct->max_workers = new_count[i];
new_count[i] = prev;
}
+ raw_spin_unlock(&wqe->lock);
}
rcu_read_unlock();
return 0;
diff --git a/fs/io-wq.h b/fs/io-wq.h
index bf5c4c533760..41bf37674a49 100644
--- a/fs/io-wq.h
+++ b/fs/io-wq.h
@@ -29,6 +29,17 @@ struct io_wq_work_list {
struct io_wq_work_node *last;
};
+#define wq_list_for_each(pos, prv, head) \
+ for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_for_each_resume(pos, prv) \
+ for (; pos; prv = pos, pos = (pos)->next)
+
+#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
+#define INIT_WQ_LIST(list) do { \
+ (list)->first = NULL; \
+} while (0)
+
static inline void wq_list_add_after(struct io_wq_work_node *node,
struct io_wq_work_node *pos,
struct io_wq_work_list *list)
@@ -54,6 +65,15 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node,
}
}
+static inline void wq_list_add_head(struct io_wq_work_node *node,
+ struct io_wq_work_list *list)
+{
+ node->next = list->first;
+ if (!node->next)
+ list->last = node;
+ WRITE_ONCE(list->first, node);
+}
+
static inline void wq_list_cut(struct io_wq_work_list *list,
struct io_wq_work_node *last,
struct io_wq_work_node *prev)
@@ -69,6 +89,31 @@ static inline void wq_list_cut(struct io_wq_work_list *list,
last->next = NULL;
}
+static inline void __wq_list_splice(struct io_wq_work_list *list,
+ struct io_wq_work_node *to)
+{
+ list->last->next = to->next;
+ to->next = list->first;
+ INIT_WQ_LIST(list);
+}
+
+static inline bool wq_list_splice(struct io_wq_work_list *list,
+ struct io_wq_work_node *to)
+{
+ if (!wq_list_empty(list)) {
+ __wq_list_splice(list, to);
+ return true;
+ }
+ return false;
+}
+
+static inline void wq_stack_add_head(struct io_wq_work_node *node,
+ struct io_wq_work_node *stack)
+{
+ node->next = stack->next;
+ stack->next = node;
+}
+
static inline void wq_list_del(struct io_wq_work_list *list,
struct io_wq_work_node *node,
struct io_wq_work_node *prev)
@@ -76,14 +121,14 @@ static inline void wq_list_del(struct io_wq_work_list *list,
wq_list_cut(list, node, prev);
}
-#define wq_list_for_each(pos, prv, head) \
- for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next)
+static inline
+struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack)
+{
+ struct io_wq_work_node *node = stack->next;
-#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL)
-#define INIT_WQ_LIST(list) do { \
- (list)->first = NULL; \
- (list)->last = NULL; \
-} while (0)
+ stack->next = node->next;
+ return node;
+}
struct io_wq_work {
struct io_wq_work_node list;
diff --git a/fs/io_uring.c b/fs/io_uring.c
index d4631a55a692..ca10dbb01201 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -103,11 +103,14 @@
#define IORING_MAX_REG_BUFFERS (1U << 14)
-#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \
- IOSQE_IO_HARDLINK | IOSQE_ASYNC | \
- IOSQE_BUFFER_SELECT)
+#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
+ IOSQE_IO_HARDLINK | IOSQE_ASYNC)
+
+#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS|IOSQE_BUFFER_SELECT|IOSQE_IO_DRAIN)
+
#define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \
- REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS)
+ REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \
+ REQ_F_ASYNC_DATA)
#define IO_TCTX_REFS_CACHE_NR (1U << 10)
@@ -195,8 +198,10 @@ struct io_rings {
};
enum io_uring_cmd_flags {
- IO_URING_F_NONBLOCK = 1,
- IO_URING_F_COMPLETE_DEFER = 2,
+ IO_URING_F_COMPLETE_DEFER = 1,
+ IO_URING_F_UNLOCKED = 2,
+ /* int's last bit, sign checks are usually faster than a bit test */
+ IO_URING_F_NONBLOCK = INT_MIN,
};
struct io_mapped_ubuf {
@@ -305,26 +310,16 @@ struct io_submit_link {
};
struct io_submit_state {
- struct blk_plug plug;
+ /* inline/task_work completion list, under ->uring_lock */
+ struct io_wq_work_node free_list;
+ /* batch completion logic */
+ struct io_wq_work_list compl_reqs;
struct io_submit_link link;
- /*
- * io_kiocb alloc cache
- */
- void *reqs[IO_REQ_CACHE_SIZE];
- unsigned int free_reqs;
-
bool plug_started;
-
- /*
- * Batch completion logic
- */
- struct io_kiocb *compl_reqs[IO_COMPL_BATCH];
- unsigned int compl_nr;
- /* inline/task_work completion list, under ->uring_lock */
- struct list_head free_list;
-
- unsigned int ios_left;
+ bool need_plug;
+ unsigned short submit_nr;
+ struct blk_plug plug;
};
struct io_ring_ctx {
@@ -368,6 +363,7 @@ struct io_ring_ctx {
* uring_lock, and updated through io_uring_register(2)
*/
struct io_rsrc_node *rsrc_node;
+ int rsrc_cached_refs;
struct io_file_table file_table;
unsigned nr_user_files;
unsigned nr_user_bufs;
@@ -384,7 +380,7 @@ struct io_ring_ctx {
} ____cacheline_aligned_in_smp;
/* IRQ completion list, under ->completion_lock */
- struct list_head locked_free_list;
+ struct io_wq_work_list locked_free_list;
unsigned int locked_free_nr;
const struct cred *sq_creds; /* cred used for __io_sq_thread() */
@@ -399,7 +395,6 @@ struct io_ring_ctx {
unsigned cached_cq_tail;
unsigned cq_entries;
struct eventfd_ctx *cq_ev_fd;
- struct wait_queue_head poll_wait;
struct wait_queue_head cq_wait;
unsigned cq_extra;
atomic_t cq_timeouts;
@@ -417,7 +412,7 @@ struct io_ring_ctx {
* For SQPOLL, only the single threaded io_sq_thread() will
* manipulate the list, hence no extra locking is needed there.
*/
- struct list_head iopoll_list;
+ struct io_wq_work_list iopoll_list;
struct hlist_head *cancel_hash;
unsigned cancel_hash_bits;
bool poll_multi_queue;
@@ -456,6 +451,8 @@ struct io_ring_ctx {
struct work_struct exit_work;
struct list_head tctx_list;
struct completion ref_comp;
+ u32 iowq_limits[2];
+ bool iowq_limits_set;
};
};
@@ -578,7 +575,6 @@ struct io_sr_msg {
int msg_flags;
int bgid;
size_t len;
- struct io_buffer *kbuf;
};
struct io_open {
@@ -690,11 +686,6 @@ struct io_hardlink {
int flags;
};
-struct io_completion {
- struct file *file;
- u32 cflags;
-};
-
struct io_async_connect {
struct sockaddr_storage address;
};
@@ -708,11 +699,15 @@ struct io_async_msghdr {
struct sockaddr_storage addr;
};
-struct io_async_rw {
- struct iovec fast_iov[UIO_FASTIOV];
- const struct iovec *free_iovec;
+struct io_rw_state {
struct iov_iter iter;
struct iov_iter_state iter_state;
+ struct iovec fast_iov[UIO_FASTIOV];
+};
+
+struct io_async_rw {
+ struct io_rw_state s;
+ const struct iovec *free_iovec;
size_t bytes_done;
struct wait_page_queue wpq;
};
@@ -739,9 +734,9 @@ enum {
REQ_F_CREDS_BIT,
REQ_F_REFCOUNT_BIT,
REQ_F_ARM_LTIMEOUT_BIT,
+ REQ_F_ASYNC_DATA_BIT,
/* keep async read/write and isreg together and in order */
- REQ_F_NOWAIT_READ_BIT,
- REQ_F_NOWAIT_WRITE_BIT,
+ REQ_F_SUPPORT_NOWAIT_BIT,
REQ_F_ISREG_BIT,
/* not a real bit, just to check we're not overflowing the space */
@@ -782,10 +777,8 @@ enum {
REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT),
/* caller should reissue async */
REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT),
- /* supports async reads */
- REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT),
- /* supports async writes */
- REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT),
+ /* supports async reads/writes */
+ REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT),
/* regular file */
REQ_F_ISREG = BIT(REQ_F_ISREG_BIT),
/* has creds assigned */
@@ -794,6 +787,8 @@ enum {
REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT),
/* there is a linked timeout that has to be armed */
REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT),
+ /* ->async_data allocated */
+ REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT),
};
struct async_poll {
@@ -850,39 +845,41 @@ struct io_kiocb {
struct io_mkdir mkdir;
struct io_symlink symlink;
struct io_hardlink hardlink;
- /* use only after cleaning per-op data, see io_clean_op() */
- struct io_completion compl;
};
- /* opcode allocated if it needs to store data for async defer */
- void *async_data;
u8 opcode;
/* polled IO has completed */
u8 iopoll_completed;
-
u16 buf_index;
+ unsigned int flags;
+
+ u64 user_data;
u32 result;
+ u32 cflags;
struct io_ring_ctx *ctx;
- unsigned int flags;
- atomic_t refs;
struct task_struct *task;
- u64 user_data;
- struct io_kiocb *link;
struct percpu_ref *fixed_rsrc_refs;
+ /* store used ubuf, so we can prevent reloading */
+ struct io_mapped_ubuf *imu;
- /* used with ctx->iopoll_list with reads/writes */
- struct list_head inflight_entry;
+ /* used by request caches, completion batching and iopoll */
+ struct io_wq_work_node comp_list;
+ atomic_t refs;
+ struct io_kiocb *link;
struct io_task_work io_task_work;
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
struct hlist_node hash_node;
+ /* internal polling, see IORING_FEAT_FAST_POLL */
struct async_poll *apoll;
+ /* opcode allocated if it needs to store data for async defer */
+ void *async_data;
struct io_wq_work work;
+ /* custom credentials, valid IFF REQ_F_CREDS is set */
const struct cred *creds;
-
- /* store used ubuf, so we can prevent reloading */
- struct io_mapped_ubuf *imu;
+ /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
+ struct io_buffer *kbuf;
};
struct io_tctx_node {
@@ -900,12 +897,12 @@ struct io_defer_entry {
struct io_op_def {
/* needs req->file assigned */
unsigned needs_file : 1;
+ /* should block plug */
+ unsigned plug : 1;
/* hash wq insertion if file is a regular file */
unsigned hash_reg_file : 1;
/* unbound wq insertion if file is a non-regular file */
unsigned unbound_nonreg_file : 1;
- /* opcode is not supported by this kernel */
- unsigned not_supported : 1;
/* set if opcode supports polled "wait" */
unsigned pollin : 1;
unsigned pollout : 1;
@@ -913,8 +910,8 @@ struct io_op_def {
unsigned buffer_select : 1;
/* do prep async if is going to be punted */
unsigned needs_async_setup : 1;
- /* should block plug */
- unsigned plug : 1;
+ /* opcode is not supported by this kernel */
+ unsigned not_supported : 1;
/* size of async data needed, if any */
unsigned short async_size;
};
@@ -1078,7 +1075,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags);
+ s32 res, u32 cflags);
static void io_put_req(struct io_kiocb *req);
static void io_put_req_deferred(struct io_kiocb *req);
static void io_dismantle_req(struct io_kiocb *req);
@@ -1093,7 +1090,7 @@ static void __io_queue_sqe(struct io_kiocb *req);
static void io_rsrc_put_work(struct work_struct *work);
static void io_req_task_queue(struct io_kiocb *req);
-static void io_submit_flush_completions(struct io_ring_ctx *ctx);
+static void __io_submit_flush_completions(struct io_ring_ctx *ctx);
static int io_req_prep_async(struct io_kiocb *req);
static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
@@ -1165,6 +1162,12 @@ static inline void req_ref_get(struct io_kiocb *req)
atomic_inc(&req->refs);
}
+static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
+{
+ if (!wq_list_empty(&ctx->submit_state.compl_reqs))
+ __io_submit_flush_completions(ctx);
+}
+
static inline void __io_req_set_refcount(struct io_kiocb *req, int nr)
{
if (!(req->flags & REQ_F_REFCOUNT)) {
@@ -1178,13 +1181,52 @@ static inline void io_req_set_refcount(struct io_kiocb *req)
__io_req_set_refcount(req, 1);
}
-static inline void io_req_set_rsrc_node(struct io_kiocb *req)
+#define IO_RSRC_REF_BATCH 100
+
+static inline void io_req_put_rsrc_locked(struct io_kiocb *req,
+ struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
{
- struct io_ring_ctx *ctx = req->ctx;
+ struct percpu_ref *ref = req->fixed_rsrc_refs;
+
+ if (ref) {
+ if (ref == &ctx->rsrc_node->refs)
+ ctx->rsrc_cached_refs++;
+ else
+ percpu_ref_put(ref);
+ }
+}
+
+static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx)
+{
+ if (req->fixed_rsrc_refs)
+ percpu_ref_put(req->fixed_rsrc_refs);
+}
+
+static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
+{
+ if (ctx->rsrc_cached_refs) {
+ percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs);
+ ctx->rsrc_cached_refs = 0;
+ }
+}
+
+static void io_rsrc_refs_refill(struct io_ring_ctx *ctx)
+ __must_hold(&ctx->uring_lock)
+{
+ ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH;
+ percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH);
+}
+static inline void io_req_set_rsrc_node(struct io_kiocb *req,
+ struct io_ring_ctx *ctx)
+{
if (!req->fixed_rsrc_refs) {
req->fixed_rsrc_refs = &ctx->rsrc_node->refs;
- percpu_ref_get(req->fixed_rsrc_refs);
+ ctx->rsrc_cached_refs--;
+ if (unlikely(ctx->rsrc_cached_refs < 0))
+ io_rsrc_refs_refill(ctx);
}
}
@@ -1217,6 +1259,11 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
return false;
}
+static inline bool req_has_async_data(struct io_kiocb *req)
+{
+ return req->flags & REQ_F_ASYNC_DATA;
+}
+
static inline void req_set_fail(struct io_kiocb *req)
{
req->flags |= REQ_F_FAIL;
@@ -1228,7 +1275,7 @@ static inline void req_fail_link_node(struct io_kiocb *req, int res)
req->result = res;
}
-static void io_ring_ctx_ref_free(struct percpu_ref *ref)
+static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref)
{
struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
@@ -1240,7 +1287,7 @@ static inline bool io_is_timeout_noseq(struct io_kiocb *req)
return !req->timeout.off;
}
-static void io_fallback_req_func(struct work_struct *work)
+static __cold void io_fallback_req_func(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx,
fallback_work.work);
@@ -1253,15 +1300,13 @@ static void io_fallback_req_func(struct work_struct *work)
req->io_task_work.func(req, &locked);
if (locked) {
- if (ctx->submit_state.compl_nr)
- io_submit_flush_completions(ctx);
+ io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
}
percpu_ref_put(&ctx->refs);
-
}
-static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
+static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
{
struct io_ring_ctx *ctx;
int hash_bits;
@@ -1298,7 +1343,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
ctx->flags = p->flags;
init_waitqueue_head(&ctx->sqo_sq_wait);
INIT_LIST_HEAD(&ctx->sqd_list);
- init_waitqueue_head(&ctx->poll_wait);
INIT_LIST_HEAD(&ctx->cq_overflow_list);
init_completion(&ctx->ref_comp);
xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1);
@@ -1307,7 +1351,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
init_waitqueue_head(&ctx->cq_wait);
spin_lock_init(&ctx->completion_lock);
spin_lock_init(&ctx->timeout_lock);
- INIT_LIST_HEAD(&ctx->iopoll_list);
+ INIT_WQ_LIST(&ctx->iopoll_list);
INIT_LIST_HEAD(&ctx->defer_list);
INIT_LIST_HEAD(&ctx->timeout_list);
INIT_LIST_HEAD(&ctx->ltimeout_list);
@@ -1316,9 +1360,10 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work);
init_llist_head(&ctx->rsrc_put_llist);
INIT_LIST_HEAD(&ctx->tctx_list);
- INIT_LIST_HEAD(&ctx->submit_state.free_list);
- INIT_LIST_HEAD(&ctx->locked_free_list);
+ ctx->submit_state.free_list.next = NULL;
+ INIT_WQ_LIST(&ctx->locked_free_list);
INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func);
+ INIT_WQ_LIST(&ctx->submit_state.compl_reqs);
return ctx;
err:
kfree(ctx->dummy_ubuf);
@@ -1346,21 +1391,16 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq)
return false;
}
-#define FFS_ASYNC_READ 0x1UL
-#define FFS_ASYNC_WRITE 0x2UL
-#ifdef CONFIG_64BIT
-#define FFS_ISREG 0x4UL
-#else
-#define FFS_ISREG 0x0UL
-#endif
-#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG)
+#define FFS_NOWAIT 0x1UL
+#define FFS_ISREG 0x2UL
+#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG)
static inline bool io_req_ffs_set(struct io_kiocb *req)
{
- return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE);
+ return req->flags & REQ_F_FIXED_FILE;
}
-static void io_req_track_inflight(struct io_kiocb *req)
+static inline void io_req_track_inflight(struct io_kiocb *req)
{
if (!(req->flags & REQ_F_INFLIGHT)) {
req->flags |= REQ_F_INFLIGHT;
@@ -1368,11 +1408,6 @@ static void io_req_track_inflight(struct io_kiocb *req)
}
}
-static inline void io_unprep_linked_timeout(struct io_kiocb *req)
-{
- req->flags &= ~REQ_F_LINK_TIMEOUT;
-}
-
static struct io_kiocb *__io_prep_linked_timeout(struct io_kiocb *req)
{
if (WARN_ON_ONCE(!req->link))
@@ -1443,15 +1478,19 @@ static void io_prep_async_link(struct io_kiocb *req)
}
}
-static void io_queue_async_work(struct io_kiocb *req, bool *locked)
+static inline void io_req_add_compl_list(struct io_kiocb *req)
+{
+ struct io_submit_state *state = &req->ctx->submit_state;
+
+ wq_list_add_tail(&req->comp_list, &state->compl_reqs);
+}
+
+static void io_queue_async_work(struct io_kiocb *req, bool *dont_use)
{
struct io_ring_ctx *ctx = req->ctx;
struct io_kiocb *link = io_prep_linked_timeout(req);
struct io_uring_task *tctx = req->task->io_uring;
- /* must not take the lock, NULL it as a precaution */
- locked = NULL;
-
BUG_ON(!tctx);
BUG_ON(!tctx->io_wq);
@@ -1492,7 +1531,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status)
}
}
-static void io_queue_deferred(struct io_ring_ctx *ctx)
+static __cold void io_queue_deferred(struct io_ring_ctx *ctx)
{
while (!list_empty(&ctx->defer_list)) {
struct io_defer_entry *de = list_first_entry(&ctx->defer_list,
@@ -1506,7 +1545,7 @@ static void io_queue_deferred(struct io_ring_ctx *ctx)
}
}
-static void io_flush_timeouts(struct io_ring_ctx *ctx)
+static __cold void io_flush_timeouts(struct io_ring_ctx *ctx)
__must_hold(&ctx->completion_lock)
{
u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
@@ -1539,7 +1578,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
spin_unlock_irq(&ctx->timeout_lock);
}
-static void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
+static __cold void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
{
if (ctx->off_timeout_used)
io_flush_timeouts(ctx);
@@ -1609,12 +1648,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx)
*/
if (wq_has_sleeper(&ctx->cq_wait))
wake_up_all(&ctx->cq_wait);
- if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait))
- wake_up(&ctx->sq_data->wait);
if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
- if (waitqueue_active(&ctx->poll_wait))
- wake_up_interruptible(&ctx->poll_wait);
}
static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
@@ -1628,8 +1663,6 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
}
if (io_should_trigger_evfd(ctx))
eventfd_signal(ctx->cq_ev_fd, 1);
- if (waitqueue_active(&ctx->poll_wait))
- wake_up_interruptible(&ctx->poll_wait);
}
/* Returns true if there are no backlogged entries after the flush */
@@ -1725,7 +1758,7 @@ static inline void io_get_task_refs(int nr)
}
static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
struct io_overflow_cqe *ocqe;
@@ -1753,7 +1786,7 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
}
static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
struct io_uring_cqe *cqe;
@@ -1776,13 +1809,13 @@ static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data
/* not as hot to bloat with inlining */
static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data,
- long res, unsigned int cflags)
+ s32 res, u32 cflags)
{
return __io_cqring_fill_event(ctx, user_data, res, cflags);
}
-static void io_req_complete_post(struct io_kiocb *req, long res,
- unsigned int cflags)
+static void io_req_complete_post(struct io_kiocb *req, s32 res,
+ u32 cflags)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -1801,40 +1834,27 @@ static void io_req_complete_post(struct io_kiocb *req, long res,
req->link = NULL;
}
}
+ io_req_put_rsrc(req, ctx);
io_dismantle_req(req);
io_put_task(req->task, 1);
- list_add(&req->inflight_entry, &ctx->locked_free_list);
+ wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
ctx->locked_free_nr++;
- } else {
- if (!percpu_ref_tryget(&ctx->refs))
- req = NULL;
}
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
-
- if (req) {
- io_cqring_ev_posted(ctx);
- percpu_ref_put(&ctx->refs);
- }
-}
-
-static inline bool io_req_needs_clean(struct io_kiocb *req)
-{
- return req->flags & IO_REQ_CLEAN_FLAGS;
+ io_cqring_ev_posted(ctx);
}
-static void io_req_complete_state(struct io_kiocb *req, long res,
- unsigned int cflags)
+static inline void io_req_complete_state(struct io_kiocb *req, s32 res,
+ u32 cflags)
{
- if (io_req_needs_clean(req))
- io_clean_op(req);
req->result = res;
- req->compl.cflags = cflags;
+ req->cflags = cflags;
req->flags |= REQ_F_COMPLETE_INLINE;
}
static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
- long res, unsigned cflags)
+ s32 res, u32 cflags)
{
if (issue_flags & IO_URING_F_COMPLETE_DEFER)
io_req_complete_state(req, res, cflags);
@@ -1842,12 +1862,12 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags,
io_req_complete_post(req, res, cflags);
}
-static inline void io_req_complete(struct io_kiocb *req, long res)
+static inline void io_req_complete(struct io_kiocb *req, s32 res)
{
__io_req_complete(req, 0, res, 0);
}
-static void io_req_complete_failed(struct io_kiocb *req, long res)
+static void io_req_complete_failed(struct io_kiocb *req, s32 res)
{
req_set_fail(req);
io_req_complete_post(req, res, 0);
@@ -1881,7 +1901,7 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
struct io_submit_state *state)
{
spin_lock(&ctx->completion_lock);
- list_splice_init(&ctx->locked_free_list, &state->free_list);
+ wq_list_splice(&ctx->locked_free_list, &state->free_list);
ctx->locked_free_nr = 0;
spin_unlock(&ctx->completion_lock);
}
@@ -1890,7 +1910,6 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx,
static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
- int nr;
/*
* If we have more than a batch's worth of requests in our IRQ side
@@ -1899,20 +1918,7 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
*/
if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH)
io_flush_cached_locked_reqs(ctx, state);
-
- nr = state->free_reqs;
- while (!list_empty(&state->free_list)) {
- struct io_kiocb *req = list_first_entry(&state->free_list,
- struct io_kiocb, inflight_entry);
-
- list_del(&req->inflight_entry);
- state->reqs[nr++] = req;
- if (nr == ARRAY_SIZE(state->reqs))
- break;
- }
-
- state->free_reqs = nr;
- return nr != 0;
+ return !!state->free_list.next;
}
/*
@@ -1921,38 +1927,54 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx)
* Because of that, io_alloc_req() should be called only under ->uring_lock
* and with extra caution to not get a request that is still worked on.
*/
-static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
+static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
struct io_submit_state *state = &ctx->submit_state;
gfp_t gfp = GFP_KERNEL | __GFP_NOWARN;
+ void *reqs[IO_REQ_ALLOC_BATCH];
+ struct io_kiocb *req;
int ret, i;
- BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH);
-
- if (likely(state->free_reqs || io_flush_cached_reqs(ctx)))
- goto got_req;
+ if (likely(state->free_list.next || io_flush_cached_reqs(ctx)))
+ return true;
- ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH,
- state->reqs);
+ ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs);
/*
* Bulk alloc is all-or-nothing. If we fail to get a batch,
* retry single alloc to be on the safe side.
*/
if (unlikely(ret <= 0)) {
- state->reqs[0] = kmem_cache_alloc(req_cachep, gfp);
- if (!state->reqs[0])
- return NULL;
+ reqs[0] = kmem_cache_alloc(req_cachep, gfp);
+ if (!reqs[0])
+ return false;
ret = 1;
}
- for (i = 0; i < ret; i++)
- io_preinit_req(state->reqs[i], ctx);
- state->free_reqs = ret;
-got_req:
- state->free_reqs--;
- return state->reqs[state->free_reqs];
+ percpu_ref_get_many(&ctx->refs, ret);
+ for (i = 0; i < ret; i++) {
+ req = reqs[i];
+
+ io_preinit_req(req, ctx);
+ wq_stack_add_head(&req->comp_list, &state->free_list);
+ }
+ return true;
+}
+
+static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx)
+{
+ if (unlikely(!ctx->submit_state.free_list.next))
+ return __io_alloc_req_refill(ctx);
+ return true;
+}
+
+static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx)
+{
+ struct io_wq_work_node *node;
+
+ node = wq_stack_extract(&ctx->submit_state.free_list);
+ return container_of(node, struct io_kiocb, comp_list);
}
static inline void io_put_file(struct file *file)
@@ -1961,35 +1983,28 @@ static inline void io_put_file(struct file *file)
fput(file);
}
-static void io_dismantle_req(struct io_kiocb *req)
+static inline void io_dismantle_req(struct io_kiocb *req)
{
unsigned int flags = req->flags;
- if (io_req_needs_clean(req))
+ if (unlikely(flags & IO_REQ_CLEAN_FLAGS))
io_clean_op(req);
if (!(flags & REQ_F_FIXED_FILE))
io_put_file(req->file);
- if (req->fixed_rsrc_refs)
- percpu_ref_put(req->fixed_rsrc_refs);
- if (req->async_data) {
- kfree(req->async_data);
- req->async_data = NULL;
- }
}
-static void __io_free_req(struct io_kiocb *req)
+static __cold void __io_free_req(struct io_kiocb *req)
{
struct io_ring_ctx *ctx = req->ctx;
+ io_req_put_rsrc(req, ctx);
io_dismantle_req(req);
io_put_task(req->task, 1);
spin_lock(&ctx->completion_lock);
- list_add(&req->inflight_entry, &ctx->locked_free_list);
+ wq_list_add_head(&req->comp_list, &ctx->locked_free_list);
ctx->locked_free_nr++;
spin_unlock(&ctx->completion_lock);
-
- percpu_ref_put(&ctx->refs);
}
static inline void io_remove_next_linked(struct io_kiocb *req)
@@ -2075,47 +2090,45 @@ static bool io_disarm_next(struct io_kiocb *req)
return posted;
}
-static struct io_kiocb *__io_req_find_next(struct io_kiocb *req)
+static void __io_req_find_next_prep(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ bool posted;
+
+ spin_lock(&ctx->completion_lock);
+ posted = io_disarm_next(req);
+ if (posted)
+ io_commit_cqring(req->ctx);
+ spin_unlock(&ctx->completion_lock);
+ if (posted)
+ io_cqring_ev_posted(ctx);
+}
+
+static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
{
struct io_kiocb *nxt;
+ if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
+ return NULL;
/*
* If LINK is set, we have dependent requests in this chain. If we
* didn't fail this request, queue the first one up, moving any other
* dependencies to the next request. In case of failure, fail the rest
* of the chain.
*/
- if (req->flags & IO_DISARM_MASK) {
- struct io_ring_ctx *ctx = req->ctx;
- bool posted;
-
- spin_lock(&ctx->completion_lock);
- posted = io_disarm_next(req);
- if (posted)
- io_commit_cqring(req->ctx);
- spin_unlock(&ctx->completion_lock);
- if (posted)
- io_cqring_ev_posted(ctx);
- }
+ if (unlikely(req->flags & IO_DISARM_MASK))
+ __io_req_find_next_prep(req);
nxt = req->link;
req->link = NULL;
return nxt;
}
-static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req)
-{
- if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK))))
- return NULL;
- return __io_req_find_next(req);
-}
-
static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked)
{
if (!ctx)
return;
if (*locked) {
- if (ctx->submit_state.compl_nr)
- io_submit_flush_completions(ctx);
+ io_submit_flush_completions(ctx);
mutex_unlock(&ctx->uring_lock);
*locked = false;
}
@@ -2132,7 +2145,7 @@ static void tctx_task_work(struct callback_head *cb)
while (1) {
struct io_wq_work_node *node;
- if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr)
+ if (!tctx->task_list.first && locked)
io_submit_flush_completions(ctx);
spin_lock_irq(&tctx->task_lock);
@@ -2195,8 +2208,9 @@ static void io_req_task_work_add(struct io_kiocb *req)
* will do the job.
*/
notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL;
- if (!task_work_add(tsk, &tctx->task_work, notify)) {
- wake_up_process(tsk);
+ if (likely(!task_work_add(tsk, &tctx->task_work, notify))) {
+ if (notify == TWA_NONE)
+ wake_up_process(tsk);
return;
}
@@ -2274,77 +2288,62 @@ static void io_free_req_work(struct io_kiocb *req, bool *locked)
io_free_req(req);
}
-struct req_batch {
- struct task_struct *task;
- int task_refs;
- int ctx_refs;
-};
-
-static inline void io_init_req_batch(struct req_batch *rb)
+static void io_free_batch_list(struct io_ring_ctx *ctx,
+ struct io_wq_work_node *node)
+ __must_hold(&ctx->uring_lock)
{
- rb->task_refs = 0;
- rb->ctx_refs = 0;
- rb->task = NULL;
-}
+ struct task_struct *task = NULL;
+ int task_refs = 0;
-static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
- struct req_batch *rb)
-{
- if (rb->ctx_refs)
- percpu_ref_put_many(&ctx->refs, rb->ctx_refs);
- if (rb->task)
- io_put_task(rb->task, rb->task_refs);
-}
+ do {
+ struct io_kiocb *req = container_of(node, struct io_kiocb,
+ comp_list);
-static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
- struct io_submit_state *state)
-{
- io_queue_next(req);
- io_dismantle_req(req);
+ if (unlikely(req->flags & REQ_F_REFCOUNT)) {
+ node = req->comp_list.next;
+ if (!req_ref_put_and_test(req))
+ continue;
+ }
- if (req->task != rb->task) {
- if (rb->task)
- io_put_task(rb->task, rb->task_refs);
- rb->task = req->task;
- rb->task_refs = 0;
- }
- rb->task_refs++;
- rb->ctx_refs++;
+ io_req_put_rsrc_locked(req, ctx);
+ io_queue_next(req);
+ io_dismantle_req(req);
- if (state->free_reqs != ARRAY_SIZE(state->reqs))
- state->reqs[state->free_reqs++] = req;
- else
- list_add(&req->inflight_entry, &state->free_list);
+ if (req->task != task) {
+ if (task)
+ io_put_task(task, task_refs);
+ task = req->task;
+ task_refs = 0;
+ }
+ task_refs++;
+ node = req->comp_list.next;
+ wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
+ } while (node);
+
+ if (task)
+ io_put_task(task, task_refs);
}
-static void io_submit_flush_completions(struct io_ring_ctx *ctx)
+static void __io_submit_flush_completions(struct io_ring_ctx *ctx)
__must_hold(&ctx->uring_lock)
{
+ struct io_wq_work_node *node, *prev;
struct io_submit_state *state = &ctx->submit_state;
- int i, nr = state->compl_nr;
- struct req_batch rb;
spin_lock(&ctx->completion_lock);
- for (i = 0; i < nr; i++) {
- struct io_kiocb *req = state->compl_reqs[i];
+ wq_list_for_each(node, prev, &state->compl_reqs) {
+ struct io_kiocb *req = container_of(node, struct io_kiocb,
+ comp_list);
__io_cqring_fill_event(ctx, req->user_data, req->result,
- req->compl.cflags);
+ req->cflags);
}
io_commit_cqring(ctx);
spin_unlock(&ctx->completion_lock);
io_cqring_ev_posted(ctx);
- io_init_req_batch(&rb);
- for (i = 0; i < nr; i++) {
- struct io_kiocb *req = state->compl_reqs[i];
-
- if (req_ref_put_and_test(req))
- io_req_free_batch(&rb, req, &ctx->submit_state);
- }
-
- io_req_free_batch_finish(ctx, &rb);
- state->compl_nr = 0;
+ io_free_batch_list(ctx, state->compl_reqs.first);
+ INIT_WQ_LIST(&state->compl_reqs);
}
/*
@@ -2404,12 +2403,9 @@ static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf)
static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req)
{
- struct io_buffer *kbuf;
-
if (likely(!(req->flags & REQ_F_BUFFER_SELECTED)))
return 0;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
- return io_put_kbuf(req, kbuf);
+ return io_put_kbuf(req, req->kbuf);
}
static inline bool io_run_task_work(void)
@@ -2423,52 +2419,22 @@ static inline bool io_run_task_work(void)
return false;
}
-/*
- * Find and free completed poll iocbs
- */
-static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
- struct list_head *done)
+static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin)
{
- struct req_batch rb;
- struct io_kiocb *req;
-
- /* order with ->result store in io_complete_rw_iopoll() */
- smp_rmb();
-
- io_init_req_batch(&rb);
- while (!list_empty(done)) {
- req = list_first_entry(done, struct io_kiocb, inflight_entry);
- list_del(&req->inflight_entry);
-
- __io_cqring_fill_event(ctx, req->user_data, req->result,
- io_put_rw_kbuf(req));
- (*nr_events)++;
-
- if (req_ref_put_and_test(req))
- io_req_free_batch(&rb, req, &ctx->submit_state);
- }
-
- io_commit_cqring(ctx);
- io_cqring_ev_posted_iopoll(ctx);
- io_req_free_batch_finish(ctx, &rb);
-}
-
-static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
- long min)
-{
- struct io_kiocb *req, *tmp;
+ struct io_wq_work_node *pos, *start, *prev;
unsigned int poll_flags = BLK_POLL_NOSLEEP;
DEFINE_IO_COMP_BATCH(iob);
- LIST_HEAD(done);
+ int nr_events = 0;
/*
* Only spin for completions if we don't have multiple devices hanging
- * off our complete list, and we're under the requested amount.
+ * off our complete list.
*/
- if (ctx->poll_multi_queue || *nr_events >= min)
+ if (ctx->poll_multi_queue || force_nonspin)
poll_flags |= BLK_POLL_ONESHOT;
- list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) {
+ wq_list_for_each(pos, start, &ctx->iopoll_list) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
struct kiocb *kiocb = &req->rw.kiocb;
int ret;
@@ -2477,11 +2443,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
* If we find a request that requires polling, break out
* and complete those lists first, if we have entries there.
*/
- if (READ_ONCE(req->iopoll_completed)) {
- list_move_tail(&req->inflight_entry, &done);
- continue;
- }
- if (!list_empty(&done))
+ if (READ_ONCE(req->iopoll_completed))
break;
ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags);
@@ -2493,34 +2455,50 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
/* iopoll may have completed current req */
if (!rq_list_empty(iob.req_list) ||
READ_ONCE(req->iopoll_completed))
- list_move_tail(&req->inflight_entry, &done);
+ break;
}
if (!rq_list_empty(iob.req_list))
iob.complete(&iob);
- if (!list_empty(&done))
- io_iopoll_complete(ctx, nr_events, &done);
+ else if (!pos)
+ return 0;
- return 0;
+ prev = start;
+ wq_list_for_each_resume(pos, prev) {
+ struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list);
+
+ /* order with io_complete_rw_iopoll(), e.g. ->result updates */
+ if (!smp_load_acquire(&req->iopoll_completed))
+ break;
+ __io_cqring_fill_event(ctx, req->user_data, req->result,
+ io_put_rw_kbuf(req));
+ nr_events++;
+ }
+
+ if (unlikely(!nr_events))
+ return 0;
+
+ io_commit_cqring(ctx);
+ io_cqring_ev_posted_iopoll(ctx);
+ pos = start ? start->next : ctx->iopoll_list.first;
+ wq_list_cut(&ctx->iopoll_list, prev, start);
+ io_free_batch_list(ctx, pos);
+ return nr_events;
}
/*
* We can't just wait for polled events to come to us, we have to actively
* find and complete them.
*/
-static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
+static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
{
if (!(ctx->flags & IORING_SETUP_IOPOLL))
return;
mutex_lock(&ctx->uring_lock);
- while (!list_empty(&ctx->iopoll_list)) {
- unsigned int nr_events = 0;
-
- io_do_iopoll(ctx, &nr_events, 0);
-
+ while (!wq_list_empty(&ctx->iopoll_list)) {
/* let it sleep and repeat later if can't complete a request */
- if (nr_events == 0)
+ if (io_do_iopoll(ctx, true) == 0)
break;
/*
* Ensure we allow local-to-the-cpu processing to take place,
@@ -2567,7 +2545,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
* forever, while the workqueue is stuck trying to acquire the
* very same mutex.
*/
- if (list_empty(&ctx->iopoll_list)) {
+ if (wq_list_empty(&ctx->iopoll_list)) {
u32 tail = ctx->cached_cq_tail;
mutex_unlock(&ctx->uring_lock);
@@ -2576,11 +2554,15 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
/* some requests don't go through iopoll_list */
if (tail != ctx->cached_cq_tail ||
- list_empty(&ctx->iopoll_list))
+ wq_list_empty(&ctx->iopoll_list))
break;
}
- ret = io_do_iopoll(ctx, &nr_events, min);
- } while (!ret && nr_events < min && !need_resched());
+ ret = io_do_iopoll(ctx, !min);
+ if (ret < 0)
+ break;
+ nr_events += ret;
+ ret = 0;
+ } while (nr_events < min && !need_resched());
out:
mutex_unlock(&ctx->uring_lock);
return ret;
@@ -2605,9 +2587,9 @@ static bool io_resubmit_prep(struct io_kiocb *req)
{
struct io_async_rw *rw = req->async_data;
- if (!rw)
+ if (!req_has_async_data(req))
return !io_req_prep_async(req);
- iov_iter_restore(&rw->iter, &rw->iter_state);
+ iov_iter_restore(&rw->s.iter, &rw->s.iter_state);
return true;
}
@@ -2651,7 +2633,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
{
if (req->rw.kiocb.ki_flags & IOCB_WRITE)
kiocb_end_write(req);
- if (res != req->result) {
+ if (unlikely(res != req->result)) {
if ((res == -EAGAIN || res == -EOPNOTSUPP) &&
io_rw_should_reissue(req)) {
req->flags |= REQ_F_REISSUE;
@@ -2666,16 +2648,11 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res)
static void io_req_task_complete(struct io_kiocb *req, bool *locked)
{
unsigned int cflags = io_put_rw_kbuf(req);
- long res = req->result;
+ int res = req->result;
if (*locked) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_state *state = &ctx->submit_state;
-
io_req_complete_state(req, res, cflags);
- state->compl_reqs[state->compl_nr++] = req;
- if (state->compl_nr == ARRAY_SIZE(state->compl_reqs))
- io_submit_flush_completions(ctx);
+ io_req_add_compl_list(req);
} else {
io_req_complete_post(req, res, cflags);
}
@@ -2711,12 +2688,11 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
req->flags |= REQ_F_REISSUE;
return;
}
+ req->result = res;
}
- WRITE_ONCE(req->result, res);
- /* order with io_iopoll_complete() checking ->result */
- smp_wmb();
- WRITE_ONCE(req->iopoll_completed, 1);
+ /* order with io_iopoll_complete() checking ->iopoll_completed */
+ smp_store_release(&req->iopoll_completed, 1);
}
/*
@@ -2725,13 +2701,13 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
* find it from a io_do_iopoll() thread before the issuer is done
* accessing the kiocb cookie.
*/
-static void io_iopoll_req_issued(struct io_kiocb *req)
+static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
- const bool in_async = io_wq_current_is_worker();
+ const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
/* workqueue context doesn't hold uring_lock, grab it now */
- if (unlikely(in_async))
+ if (unlikely(needs_lock))
mutex_lock(&ctx->uring_lock);
/*
@@ -2739,14 +2715,13 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
* how we do polling eventually, not spinning if we're on potentially
* different devices.
*/
- if (list_empty(&ctx->iopoll_list)) {
+ if (wq_list_empty(&ctx->iopoll_list)) {
ctx->poll_multi_queue = false;
} else if (!ctx->poll_multi_queue) {
struct io_kiocb *list_req;
- list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb,
- inflight_entry);
-
+ list_req = container_of(ctx->iopoll_list.first, struct io_kiocb,
+ comp_list);
if (list_req->file != req->file)
ctx->poll_multi_queue = true;
}
@@ -2756,11 +2731,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
* it to the front so we find it first.
*/
if (READ_ONCE(req->iopoll_completed))
- list_add(&req->inflight_entry, &ctx->iopoll_list);
+ wq_list_add_head(&req->comp_list, &ctx->iopoll_list);
else
- list_add_tail(&req->inflight_entry, &ctx->iopoll_list);
+ wq_list_add_tail(&req->comp_list, &ctx->iopoll_list);
- if (unlikely(in_async)) {
+ if (unlikely(needs_lock)) {
/*
* If IORING_SETUP_SQPOLL is enabled, sqes are either handle
* in sq thread task context or in io worker task context. If
@@ -2785,10 +2760,8 @@ static bool io_bdev_nowait(struct block_device *bdev)
* any file. For now, just ensure that anything potentially problematic is done
* inline.
*/
-static bool __io_file_supports_nowait(struct file *file, int rw)
+static bool __io_file_supports_nowait(struct file *file, umode_t mode)
{
- umode_t mode = file_inode(file)->i_mode;
-
if (S_ISBLK(mode)) {
if (IS_ENABLED(CONFIG_BLOCK) &&
io_bdev_nowait(I_BDEV(file->f_mapping->host)))
@@ -2808,28 +2781,32 @@ static bool __io_file_supports_nowait(struct file *file, int rw)
/* any ->read/write should understand O_NONBLOCK */
if (file->f_flags & O_NONBLOCK)
return true;
+ return file->f_mode & FMODE_NOWAIT;
+}
- if (!(file->f_mode & FMODE_NOWAIT))
- return false;
-
- if (rw == READ)
- return file->f_op->read_iter != NULL;
+/*
+ * If we tracked the file through the SCM inflight mechanism, we could support
+ * any file. For now, just ensure that anything potentially problematic is done
+ * inline.
+ */
+static unsigned int io_file_get_flags(struct file *file)
+{
+ umode_t mode = file_inode(file)->i_mode;
+ unsigned int res = 0;
- return file->f_op->write_iter != NULL;
+ if (S_ISREG(mode))
+ res |= FFS_ISREG;
+ if (__io_file_supports_nowait(file, mode))
+ res |= FFS_NOWAIT;
+ return res;
}
-static bool io_file_supports_nowait(struct io_kiocb *req, int rw)
+static inline bool io_file_supports_nowait(struct io_kiocb *req)
{
- if (rw == READ && (req->flags & REQ_F_NOWAIT_READ))
- return true;
- else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE))
- return true;
-
- return __io_file_supports_nowait(req->file, rw);
+ return req->flags & REQ_F_SUPPORT_NOWAIT;
}
-static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- int rw)
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw.kiocb;
@@ -2837,16 +2814,15 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
unsigned ioprio;
int ret;
- if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode))
- req->flags |= REQ_F_ISREG;
+ if (!io_req_ffs_set(req))
+ req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT;
kiocb->ki_pos = READ_ONCE(sqe->off);
if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) {
req->flags |= REQ_F_CUR_POS;
kiocb->ki_pos = file->f_pos;
}
- kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
- kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
+ kiocb->ki_flags = iocb_flags(file);
ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
if (unlikely(ret))
return ret;
@@ -2857,22 +2833,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
* reliably. If not, or it IOCB_NOWAIT is set, don't retry.
*/
if ((kiocb->ki_flags & IOCB_NOWAIT) ||
- ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw)))
+ ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req)))
req->flags |= REQ_F_NOWAIT;
- ioprio = READ_ONCE(sqe->ioprio);
- if (ioprio) {
- ret = ioprio_check_cap(ioprio);
- if (ret)
- return ret;
-
- kiocb->ki_ioprio = ioprio;
- } else
- kiocb->ki_ioprio = get_current_ioprio();
-
if (ctx->flags & IORING_SETUP_IOPOLL) {
- if (!(kiocb->ki_flags & IOCB_DIRECT) ||
- !kiocb->ki_filp->f_op->iopoll)
+ if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
return -EOPNOTSUPP;
kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE;
@@ -2884,12 +2849,18 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_complete = io_complete_rw;
}
- if (req->opcode == IORING_OP_READ_FIXED ||
- req->opcode == IORING_OP_WRITE_FIXED) {
- req->imu = NULL;
- io_req_set_rsrc_node(req);
+ ioprio = READ_ONCE(sqe->ioprio);
+ if (ioprio) {
+ ret = ioprio_check_cap(ioprio);
+ if (ret)
+ return ret;
+
+ kiocb->ki_ioprio = ioprio;
+ } else {
+ kiocb->ki_ioprio = get_current_ioprio();
}
+ req->imu = NULL;
req->rw.addr = READ_ONCE(sqe->addr);
req->rw.len = READ_ONCE(sqe->len);
req->buf_index = READ_ONCE(sqe->buf_index);
@@ -2924,7 +2895,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
struct io_async_rw *io = req->async_data;
/* add previously done IO, if any */
- if (io && io->bytes_done > 0) {
+ if (req_has_async_data(req) && io->bytes_done > 0) {
if (ret < 0)
ret = io->bytes_done;
else
@@ -2947,7 +2918,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
struct io_ring_ctx *ctx = req->ctx;
req_set_fail(req);
- if (!(issue_flags & IO_URING_F_NONBLOCK)) {
+ if (issue_flags & IO_URING_F_UNLOCKED) {
mutex_lock(&ctx->uring_lock);
__io_req_complete(req, issue_flags, ret, cflags);
mutex_unlock(&ctx->uring_lock);
@@ -3018,13 +2989,15 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter
static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter)
{
- struct io_ring_ctx *ctx = req->ctx;
struct io_mapped_ubuf *imu = req->imu;
u16 index, buf_index = req->buf_index;
if (likely(!imu)) {
+ struct io_ring_ctx *ctx = req->ctx;
+
if (unlikely(buf_index >= ctx->nr_user_bufs))
return -EFAULT;
+ io_req_set_rsrc_node(req, ctx);
index = array_index_nospec(buf_index, ctx->nr_user_bufs);
imu = READ_ONCE(ctx->user_bufs[index]);
req->imu = imu;
@@ -3051,10 +3024,11 @@ static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock)
}
static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
- int bgid, struct io_buffer *kbuf,
- bool needs_lock)
+ int bgid, unsigned int issue_flags)
{
+ struct io_buffer *kbuf = req->kbuf;
struct io_buffer *head;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
if (req->flags & REQ_F_BUFFER_SELECTED)
return kbuf;
@@ -3075,34 +3049,32 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len,
}
if (*len > kbuf->len)
*len = kbuf->len;
+ req->flags |= REQ_F_BUFFER_SELECTED;
+ req->kbuf = kbuf;
} else {
kbuf = ERR_PTR(-ENOBUFS);
}
io_ring_submit_unlock(req->ctx, needs_lock);
-
return kbuf;
}
static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct io_buffer *kbuf;
u16 bgid;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
bgid = req->buf_index;
- kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock);
+ kbuf = io_buffer_select(req, len, bgid, issue_flags);
if (IS_ERR(kbuf))
return kbuf;
- req->rw.addr = (u64) (unsigned long) kbuf;
- req->flags |= REQ_F_BUFFER_SELECTED;
return u64_to_user_ptr(kbuf->addr);
}
#ifdef CONFIG_COMPAT
static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct compat_iovec __user *uiov;
compat_ssize_t clen;
@@ -3118,7 +3090,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
return -EINVAL;
len = clen;
- buf = io_rw_buffer_select(req, &len, needs_lock);
+ buf = io_rw_buffer_select(req, &len, issue_flags);
if (IS_ERR(buf))
return PTR_ERR(buf);
iov[0].iov_base = buf;
@@ -3128,7 +3100,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov,
#endif
static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr);
void __user *buf;
@@ -3140,7 +3112,7 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
len = iov[0].iov_len;
if (len < 0)
return -EINVAL;
- buf = io_rw_buffer_select(req, &len, needs_lock);
+ buf = io_rw_buffer_select(req, &len, issue_flags);
if (IS_ERR(buf))
return PTR_ERR(buf);
iov[0].iov_base = buf;
@@ -3149,12 +3121,11 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
}
static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
- bool needs_lock)
+ unsigned int issue_flags)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
- struct io_buffer *kbuf;
+ struct io_buffer *kbuf = req->kbuf;
- kbuf = (struct io_buffer *) (unsigned long) req->rw.addr;
iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
iov[0].iov_len = kbuf->len;
return 0;
@@ -3164,52 +3135,72 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov,
#ifdef CONFIG_COMPAT
if (req->ctx->compat)
- return io_compat_import(req, iov, needs_lock);
+ return io_compat_import(req, iov, issue_flags);
#endif
- return __io_iov_buffer_select(req, iov, needs_lock);
+ return __io_iov_buffer_select(req, iov, issue_flags);
}
-static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec,
- struct iov_iter *iter, bool needs_lock)
+static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req,
+ struct io_rw_state *s,
+ unsigned int issue_flags)
{
- void __user *buf = u64_to_user_ptr(req->rw.addr);
- size_t sqe_len = req->rw.len;
+ struct iov_iter *iter = &s->iter;
u8 opcode = req->opcode;
+ struct iovec *iovec;
+ void __user *buf;
+ size_t sqe_len;
ssize_t ret;
- if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) {
- *iovec = NULL;
- return io_import_fixed(req, rw, iter);
- }
+ BUILD_BUG_ON(ERR_PTR(0) != NULL);
+
+ if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED)
+ return ERR_PTR(io_import_fixed(req, rw, iter));
/* buffer index only valid with fixed read/write, or buffer select */
- if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))
- return -EINVAL;
+ if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)))
+ return ERR_PTR(-EINVAL);
+
+ buf = u64_to_user_ptr(req->rw.addr);
+ sqe_len = req->rw.len;
if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) {
if (req->flags & REQ_F_BUFFER_SELECT) {
- buf = io_rw_buffer_select(req, &sqe_len, needs_lock);
+ buf = io_rw_buffer_select(req, &sqe_len, issue_flags);
if (IS_ERR(buf))
- return PTR_ERR(buf);
+ return ERR_CAST(buf);
req->rw.len = sqe_len;
}
- ret = import_single_range(rw, buf, sqe_len, *iovec, iter);
- *iovec = NULL;
- return ret;
+ ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter);
+ return ERR_PTR(ret);
}
+ iovec = s->fast_iov;
if (req->flags & REQ_F_BUFFER_SELECT) {
- ret = io_iov_buffer_select(req, *iovec, needs_lock);
+ ret = io_iov_buffer_select(req, iovec, issue_flags);
if (!ret)
- iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len);
- *iovec = NULL;
- return ret;
+ iov_iter_init(iter, rw, iovec, 1, iovec->iov_len);
+ return ERR_PTR(ret);
}
- return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter,
+ ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter,
req->ctx->compat);
+ if (unlikely(ret < 0))
+ return ERR_PTR(ret);
+ return iovec;
+}
+
+static inline int io_import_iovec(int rw, struct io_kiocb *req,
+ struct iovec **iovec, struct io_rw_state *s,
+ unsigned int issue_flags)
+{
+ *iovec = __io_import_iovec(rw, req, s, issue_flags);
+ if (unlikely(IS_ERR(*iovec)))
+ return PTR_ERR(*iovec);
+
+ iov_iter_save_state(&s->iter, &s->iter_state);
+ return 0;
}
static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb)
@@ -3234,7 +3225,8 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter)
*/
if (kiocb->ki_flags & IOCB_HIPRI)
return -EOPNOTSUPP;
- if (kiocb->ki_flags & IOCB_NOWAIT)
+ if ((kiocb->ki_flags & IOCB_NOWAIT) &&
+ !(kiocb->ki_filp->f_flags & O_NONBLOCK))
return -EAGAIN;
while (iov_iter_count(iter)) {
@@ -3280,7 +3272,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
{
struct io_async_rw *rw = req->async_data;
- memcpy(&rw->iter, iter, sizeof(*iter));
+ memcpy(&rw->s.iter, iter, sizeof(*iter));
rw->free_iovec = iovec;
rw->bytes_done = 0;
/* can only be fixed buffers, no need to do anything */
@@ -3289,33 +3281,36 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec,
if (!iovec) {
unsigned iov_off = 0;
- rw->iter.iov = rw->fast_iov;
+ rw->s.iter.iov = rw->s.fast_iov;
if (iter->iov != fast_iov) {
iov_off = iter->iov - fast_iov;
- rw->iter.iov += iov_off;
+ rw->s.iter.iov += iov_off;
}
- if (rw->fast_iov != fast_iov)
- memcpy(rw->fast_iov + iov_off, fast_iov + iov_off,
+ if (rw->s.fast_iov != fast_iov)
+ memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off,
sizeof(struct iovec) * iter->nr_segs);
} else {
req->flags |= REQ_F_NEED_CLEANUP;
}
}
-static inline int io_alloc_async_data(struct io_kiocb *req)
+static inline bool io_alloc_async_data(struct io_kiocb *req)
{
WARN_ON_ONCE(!io_op_defs[req->opcode].async_size);
req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL);
- return req->async_data == NULL;
+ if (req->async_data) {
+ req->flags |= REQ_F_ASYNC_DATA;
+ return false;
+ }
+ return true;
}
static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
- const struct iovec *fast_iov,
- struct iov_iter *iter, bool force)
+ struct io_rw_state *s, bool force)
{
if (!force && !io_op_defs[req->opcode].needs_async_setup)
return 0;
- if (!req->async_data) {
+ if (!req_has_async_data(req)) {
struct io_async_rw *iorw;
if (io_alloc_async_data(req)) {
@@ -3323,10 +3318,10 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
return -ENOMEM;
}
- io_req_map_rw(req, iovec, fast_iov, iter);
+ io_req_map_rw(req, iovec, s->fast_iov, &s->iter);
iorw = req->async_data;
/* we've copied and mapped the iter, ensure state is saved */
- iov_iter_save_state(&iorw->iter, &iorw->iter_state);
+ iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state);
}
return 0;
}
@@ -3334,10 +3329,11 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec,
static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
{
struct io_async_rw *iorw = req->async_data;
- struct iovec *iov = iorw->fast_iov;
+ struct iovec *iov;
int ret;
- ret = io_import_iovec(rw, req, &iov, &iorw->iter, false);
+ /* submission path, ->uring_lock should already be taken */
+ ret = io_import_iovec(rw, req, &iov, &iorw->s, 0);
if (unlikely(ret < 0))
return ret;
@@ -3345,7 +3341,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw)
iorw->free_iovec = iov;
if (iov)
req->flags |= REQ_F_NEED_CLEANUP;
- iov_iter_save_state(&iorw->iter, &iorw->iter_state);
return 0;
}
@@ -3353,11 +3348,11 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
if (unlikely(!(req->file->f_mode & FMODE_READ)))
return -EBADF;
- return io_prep_rw(req, sqe, READ);
+ return io_prep_rw(req, sqe);
}
/*
- * This is our waitqueue callback handler, registered through lock_page_async()
+ * This is our waitqueue callback handler, registered through __folio_lock_async()
* when we initially tried to do the IO with the iocb armed our waitqueue.
* This gets called when the page is unlocked, and we generally expect that to
* happen when the page IO is completed and the page is now uptodate. This will
@@ -3429,7 +3424,7 @@ static bool io_rw_should_retry(struct io_kiocb *req)
static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter)
{
- if (req->file->f_op->read_iter)
+ if (likely(req->file->f_op->read_iter))
return call_read_iter(req->file, &req->rw.kiocb, iter);
else if (req->file->f_op->read)
return loop_rw_iter(READ, req, iter);
@@ -3445,43 +3440,40 @@ static bool need_read_all(struct io_kiocb *req)
static int io_read(struct io_kiocb *req, unsigned int issue_flags)
{
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
struct kiocb *kiocb = &req->rw.kiocb;
- struct iov_iter __iter, *iter = &__iter;
- struct io_async_rw *rw = req->async_data;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- struct iov_iter_state __state, *state;
+ struct io_async_rw *rw;
ssize_t ret, ret2;
- if (rw) {
- iter = &rw->iter;
- state = &rw->iter_state;
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(READ, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
+ return ret;
+ } else {
+ rw = req->async_data;
+ s = &rw->s;
/*
* We come here from an earlier attempt, restore our state to
* match in case it doesn't. It's cheap enough that we don't
* need to make this conditional.
*/
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
iovec = NULL;
- } else {
- ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock);
- if (ret < 0)
- return ret;
- state = &__state;
- iov_iter_save_state(iter, state);
}
- req->result = iov_iter_count(iter);
+ req->result = iov_iter_count(&s->iter);
- /* Ensure we clear previously set non-block flag */
- if (!force_nonblock)
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- else
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req))) {
+ ret = io_setup_async_rw(req, iovec, s, true);
+ return ret ?: -EAGAIN;
+ }
kiocb->ki_flags |= IOCB_NOWAIT;
-
- /* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_nowait(req, READ)) {
- ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
- return ret ?: -EAGAIN;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
}
ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result);
@@ -3490,7 +3482,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
return ret;
}
- ret = io_iter_do_read(req, iter);
+ ret = io_iter_do_read(req, &s->iter);
if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
req->flags &= ~REQ_F_REISSUE;
@@ -3503,7 +3495,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
ret = 0;
} else if (ret == -EIOCBQUEUED) {
goto out_free;
- } else if (ret <= 0 || ret == req->result || !force_nonblock ||
+ } else if (ret == req->result || ret <= 0 || !force_nonblock ||
(req->flags & REQ_F_NOWAIT) || !need_read_all(req)) {
/* read all, failed, already did sync or don't want to retry */
goto done;
@@ -3514,22 +3506,19 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* untouched in case of error. Restore it and we'll advance it
* manually if we need to.
*/
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
- ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true);
+ ret2 = io_setup_async_rw(req, iovec, s, true);
if (ret2)
return ret2;
iovec = NULL;
rw = req->async_data;
+ s = &rw->s;
/*
* Now use our persistent iterator and state, if we aren't already.
* We've restored and mapped the iter to match.
*/
- if (iter != &rw->iter) {
- iter = &rw->iter;
- state = &rw->iter_state;
- }
do {
/*
@@ -3537,11 +3526,11 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* above or inside this loop. Advance the iter by the bytes
* that were consumed.
*/
- iov_iter_advance(iter, ret);
- if (!iov_iter_count(iter))
+ iov_iter_advance(&s->iter, ret);
+ if (!iov_iter_count(&s->iter))
break;
rw->bytes_done += ret;
- iov_iter_save_state(iter, state);
+ iov_iter_save_state(&s->iter, &s->iter_state);
/* if we can retry, do so with the callbacks armed */
if (!io_rw_should_retry(req)) {
@@ -3555,12 +3544,12 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags)
* desired page gets unlocked. We can also get a partial read
* here, and if we do, then just retry at the new offset.
*/
- ret = io_iter_do_read(req, iter);
+ ret = io_iter_do_read(req, &s->iter);
if (ret == -EIOCBQUEUED)
return 0;
/* we got some bytes, but not all. retry. */
kiocb->ki_flags &= ~IOCB_WAITQ;
- iov_iter_restore(iter, state);
+ iov_iter_restore(&s->iter, &s->iter_state);
} while (ret > 0);
done:
kiocb_done(kiocb, ret, issue_flags);
@@ -3575,47 +3564,46 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
{
if (unlikely(!(req->file->f_mode & FMODE_WRITE)))
return -EBADF;
- return io_prep_rw(req, sqe, WRITE);
+ req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file));
+ return io_prep_rw(req, sqe);
}
static int io_write(struct io_kiocb *req, unsigned int issue_flags)
{
- struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct io_rw_state __s, *s = &__s;
+ struct iovec *iovec;
struct kiocb *kiocb = &req->rw.kiocb;
- struct iov_iter __iter, *iter = &__iter;
- struct io_async_rw *rw = req->async_data;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- struct iov_iter_state __state, *state;
ssize_t ret, ret2;
- if (rw) {
- iter = &rw->iter;
- state = &rw->iter_state;
- iov_iter_restore(iter, state);
- iovec = NULL;
- } else {
- ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock);
- if (ret < 0)
+ if (!req_has_async_data(req)) {
+ ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags);
+ if (unlikely(ret < 0))
return ret;
- state = &__state;
- iov_iter_save_state(iter, state);
+ } else {
+ struct io_async_rw *rw = req->async_data;
+
+ s = &rw->s;
+ iov_iter_restore(&s->iter, &s->iter_state);
+ iovec = NULL;
}
- req->result = iov_iter_count(iter);
+ req->result = iov_iter_count(&s->iter);
- /* Ensure we clear previously set non-block flag */
- if (!force_nonblock)
- kiocb->ki_flags &= ~IOCB_NOWAIT;
- else
- kiocb->ki_flags |= IOCB_NOWAIT;
+ if (force_nonblock) {
+ /* If the file doesn't support async, just async punt */
+ if (unlikely(!io_file_supports_nowait(req)))
+ goto copy_iov;
- /* If the file doesn't support async, just async punt */
- if (force_nonblock && !io_file_supports_nowait(req, WRITE))
- goto copy_iov;
+ /* file path doesn't support NOWAIT for non-direct_IO */
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
+ (req->flags & REQ_F_ISREG))
+ goto copy_iov;
- /* file path doesn't support NOWAIT for non-direct_IO */
- if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) &&
- (req->flags & REQ_F_ISREG))
- goto copy_iov;
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ } else {
+ /* Ensure we clear previously set non-block flag */
+ kiocb->ki_flags &= ~IOCB_NOWAIT;
+ }
ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result);
if (unlikely(ret))
@@ -3635,10 +3623,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
}
kiocb->ki_flags |= IOCB_WRITE;
- if (req->file->f_op->write_iter)
- ret2 = call_write_iter(req->file, kiocb, iter);
+ if (likely(req->file->f_op->write_iter))
+ ret2 = call_write_iter(req->file, kiocb, &s->iter);
else if (req->file->f_op->write)
- ret2 = loop_rw_iter(WRITE, req, iter);
+ ret2 = loop_rw_iter(WRITE, req, &s->iter);
else
ret2 = -EINVAL;
@@ -3658,14 +3646,14 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags)
goto done;
if (!force_nonblock || ret2 != -EAGAIN) {
/* IOPOLL retry should happen for io-wq threads */
- if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN)
+ if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL))
goto copy_iov;
done:
kiocb_done(kiocb, ret2, issue_flags);
} else {
copy_iov:
- iov_iter_restore(iter, state);
- ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false);
+ iov_iter_restore(&s->iter, &s->iter_state);
+ ret = io_setup_async_rw(req, iovec, s, false);
return ret ?: -EAGAIN;
}
out_free:
@@ -3801,7 +3789,7 @@ static int io_mkdirat_prep(struct io_kiocb *req,
return 0;
}
-static int io_mkdirat(struct io_kiocb *req, int issue_flags)
+static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_mkdir *mkd = &req->mkdir;
int ret;
@@ -3850,7 +3838,7 @@ static int io_symlinkat_prep(struct io_kiocb *req,
return 0;
}
-static int io_symlinkat(struct io_kiocb *req, int issue_flags)
+static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_symlink *sl = &req->symlink;
int ret;
@@ -3900,7 +3888,7 @@ static int io_linkat_prep(struct io_kiocb *req,
return 0;
}
-static int io_linkat(struct io_kiocb *req, int issue_flags)
+static int io_linkat(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_hardlink *lnk = &req->hardlink;
int ret;
@@ -4319,9 +4307,9 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer *head;
int ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
lockdep_assert_held(&ctx->uring_lock);
@@ -4334,7 +4322,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags)
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
return 0;
}
@@ -4406,9 +4394,9 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
struct io_ring_ctx *ctx = req->ctx;
struct io_buffer *head, *list;
int ret = 0;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
lockdep_assert_held(&ctx->uring_lock);
@@ -4424,7 +4412,7 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
req_set_fail(req);
/* complete before unlock, IOPOLL may need the lock */
__io_req_complete(req, issue_flags, ret, 0);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
return 0;
}
@@ -4757,8 +4745,9 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(!sock))
return -ENOTSOCK;
- kmsg = req->async_data;
- if (!kmsg) {
+ if (req_has_async_data(req)) {
+ kmsg = req->async_data;
+ } else {
ret = io_sendmsg_copy_hdr(req, &iomsg);
if (ret)
return ret;
@@ -4917,23 +4906,16 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req,
}
static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req,
- bool needs_lock)
+ unsigned int issue_flags)
{
struct io_sr_msg *sr = &req->sr_msg;
- struct io_buffer *kbuf;
- kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock);
- if (IS_ERR(kbuf))
- return kbuf;
-
- sr->kbuf = kbuf;
- req->flags |= REQ_F_BUFFER_SELECTED;
- return kbuf;
+ return io_buffer_select(req, &sr->len, sr->bgid, issue_flags);
}
static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req)
{
- return io_put_kbuf(req, req->sr_msg.kbuf);
+ return io_put_kbuf(req, req->kbuf);
}
static int io_recvmsg_prep_async(struct io_kiocb *req)
@@ -4981,8 +4963,9 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely(!sock))
return -ENOTSOCK;
- kmsg = req->async_data;
- if (!kmsg) {
+ if (req_has_async_data(req)) {
+ kmsg = req->async_data;
+ } else {
ret = io_recvmsg_copy_hdr(req, &iomsg);
if (ret)
return ret;
@@ -4990,7 +4973,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags)
}
if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, !force_nonblock);
+ kbuf = io_recv_buffer_select(req, issue_flags);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr);
@@ -5042,7 +5025,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags)
return -ENOTSOCK;
if (req->flags & REQ_F_BUFFER_SELECT) {
- kbuf = io_recv_buffer_select(req, !force_nonblock);
+ kbuf = io_recv_buffer_select(req, issue_flags);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
buf = u64_to_user_ptr(kbuf->addr);
@@ -5173,7 +5156,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
int ret;
bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
- if (req->async_data) {
+ if (req_has_async_data(req)) {
io = req->async_data;
} else {
ret = move_addr_to_kernel(req->connect.addr,
@@ -5189,7 +5172,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags)
ret = __sys_connect_file(req->file, &io->address,
req->connect.addr_len, file_flags);
if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) {
- if (req->async_data)
+ if (req_has_async_data(req))
return -EAGAIN;
if (io_alloc_async_data(req)) {
ret = -ENOMEM;
@@ -5349,16 +5332,6 @@ static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask)
return !(flags & IORING_CQE_F_MORE);
}
-static inline bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
- __must_hold(&req->ctx->completion_lock)
-{
- bool done;
-
- done = __io_poll_complete(req, mask);
- io_commit_cqring(req->ctx);
- return done;
-}
-
static void io_poll_task_func(struct io_kiocb *req, bool *locked)
{
struct io_ring_ctx *ctx = req->ctx;
@@ -5480,7 +5453,10 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake);
req_ref_get(req);
poll->wait.private = req;
+
*poll_ptr = poll;
+ if (req->opcode == IORING_OP_POLL_ADD)
+ req->flags |= REQ_F_ASYNC_DATA;
}
pt->nr_entries++;
@@ -5604,17 +5580,13 @@ static int io_arm_poll_handler(struct io_kiocb *req)
struct async_poll *apoll;
struct io_poll_table ipt;
__poll_t ret, mask = EPOLLONESHOT | POLLERR | POLLPRI;
- int rw;
- if (!req->file || !file_can_poll(req->file))
- return IO_APOLL_ABORTED;
- if (req->flags & REQ_F_POLLED)
- return IO_APOLL_ABORTED;
if (!def->pollin && !def->pollout)
return IO_APOLL_ABORTED;
+ if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED))
+ return IO_APOLL_ABORTED;
if (def->pollin) {
- rw = READ;
mask |= POLLIN | POLLRDNORM;
/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
@@ -5622,14 +5594,9 @@ static int io_arm_poll_handler(struct io_kiocb *req)
(req->sr_msg.msg_flags & MSG_ERRQUEUE))
mask &= ~POLLIN;
} else {
- rw = WRITE;
mask |= POLLOUT | POLLWRNORM;
}
- /* if we can't nonblock try, then no point in arming a poll handler */
- if (!io_file_supports_nowait(req, rw))
- return IO_APOLL_ABORTED;
-
apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC);
if (unlikely(!apoll))
return IO_APOLL_ABORTED;
@@ -5690,8 +5657,8 @@ static bool io_poll_remove_one(struct io_kiocb *req)
/*
* Returns true if we found and killed one or more poll requests
*/
-static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk,
- bool cancel_all)
+static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx,
+ struct task_struct *tsk, bool cancel_all)
{
struct hlist_node *tmp;
struct io_kiocb *req;
@@ -5845,7 +5812,8 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
if (mask) { /* no async, we'd stolen it */
ipt.error = 0;
- done = io_poll_complete(req, mask);
+ done = __io_poll_complete(req, mask);
+ io_commit_cqring(req->ctx);
}
spin_unlock(&ctx->completion_lock);
@@ -5921,7 +5889,10 @@ err:
static void io_req_task_timeout(struct io_kiocb *req, bool *locked)
{
- req_set_fail(req);
+ struct io_timeout_data *data = req->async_data;
+
+ if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS))
+ req_set_fail(req);
io_req_complete_post(req, -ETIME, 0);
}
@@ -6127,7 +6098,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (off && is_timeout_link)
return -EINVAL;
flags = READ_ONCE(sqe->timeout_flags);
- if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK))
+ if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK |
+ IORING_TIMEOUT_ETIME_SUCCESS))
return -EINVAL;
/* more than one clock specified is invalid, obviously */
if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1)
@@ -6138,7 +6110,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
if (unlikely(off && !req->ctx->off_timeout_used))
req->ctx->off_timeout_used = true;
- if (!req->async_data && io_alloc_async_data(req))
+ if (WARN_ON_ONCE(req_has_async_data(req)))
+ return -EFAULT;
+ if (io_alloc_async_data(req))
return -ENOMEM;
data = req->async_data;
@@ -6295,6 +6269,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
u64 sqe_addr = req->cancel.addr;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_tctx_node *node;
int ret;
@@ -6303,7 +6278,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
goto done;
/* slow path, try all io-wq's */
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = -ENOENT;
list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
struct io_uring_task *tctx = node->task->io_uring;
@@ -6312,7 +6287,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags)
if (ret != -ENOENT)
break;
}
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
done:
if (ret < 0)
req_set_fail(req);
@@ -6339,6 +6314,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req,
static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
{
struct io_ring_ctx *ctx = req->ctx;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_uring_rsrc_update2 up;
int ret;
@@ -6348,10 +6324,10 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags)
up.tags = 0;
up.resv = 0;
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE,
&up, req->rsrc_update.nr_args);
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
if (ret < 0)
req_set_fail(req);
@@ -6447,7 +6423,7 @@ static int io_req_prep_async(struct io_kiocb *req)
{
if (!io_op_defs[req->opcode].needs_async_setup)
return 0;
- if (WARN_ON_ONCE(req->async_data))
+ if (WARN_ON_ONCE(req_has_async_data(req)))
return -EFAULT;
if (io_alloc_async_data(req))
return -EAGAIN;
@@ -6479,68 +6455,39 @@ static u32 io_get_sequence(struct io_kiocb *req)
return seq;
}
-static bool io_drain_req(struct io_kiocb *req)
+static __cold void io_drain_req(struct io_kiocb *req)
{
- struct io_kiocb *pos;
struct io_ring_ctx *ctx = req->ctx;
struct io_defer_entry *de;
int ret;
- u32 seq;
-
- if (req->flags & REQ_F_FAIL) {
- io_req_complete_fail_submit(req);
- return true;
- }
-
- /*
- * If we need to drain a request in the middle of a link, drain the
- * head request and the next request/link after the current link.
- * Considering sequential execution of links, IOSQE_IO_DRAIN will be
- * maintained for every request of our link.
- */
- if (ctx->drain_next) {
- req->flags |= REQ_F_IO_DRAIN;
- ctx->drain_next = false;
- }
- /* not interested in head, start from the first linked */
- io_for_each_link(pos, req->link) {
- if (pos->flags & REQ_F_IO_DRAIN) {
- ctx->drain_next = true;
- req->flags |= REQ_F_IO_DRAIN;
- break;
- }
- }
+ u32 seq = io_get_sequence(req);
/* Still need defer if there is pending req in defer list. */
- if (likely(list_empty_careful(&ctx->defer_list) &&
- !(req->flags & REQ_F_IO_DRAIN))) {
+ if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) {
+queue:
ctx->drain_active = false;
- return false;
+ io_req_task_queue(req);
+ return;
}
- seq = io_get_sequence(req);
- /* Still a chance to pass the sequence check */
- if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list))
- return false;
-
ret = io_req_prep_async(req);
- if (ret)
- goto fail;
+ if (ret) {
+fail:
+ io_req_complete_failed(req, ret);
+ return;
+ }
io_prep_async_link(req);
de = kmalloc(sizeof(*de), GFP_KERNEL);
if (!de) {
ret = -ENOMEM;
-fail:
- io_req_complete_failed(req, ret);
- return true;
+ goto fail;
}
spin_lock(&ctx->completion_lock);
if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) {
spin_unlock(&ctx->completion_lock);
kfree(de);
- io_queue_async_work(req, NULL);
- return true;
+ goto queue;
}
trace_io_uring_defer(ctx, req, req->user_data);
@@ -6548,23 +6495,13 @@ fail:
de->seq = seq;
list_add_tail(&de->list, &ctx->defer_list);
spin_unlock(&ctx->completion_lock);
- return true;
}
static void io_clean_op(struct io_kiocb *req)
{
if (req->flags & REQ_F_BUFFER_SELECTED) {
- switch (req->opcode) {
- case IORING_OP_READV:
- case IORING_OP_READ_FIXED:
- case IORING_OP_READ:
- kfree((void *)(unsigned long)req->rw.addr);
- break;
- case IORING_OP_RECVMSG:
- case IORING_OP_RECV:
- kfree(req->sr_msg.kbuf);
- break;
- }
+ kfree(req->kbuf);
+ req->kbuf = NULL;
}
if (req->flags & REQ_F_NEED_CLEANUP) {
@@ -6629,17 +6566,19 @@ static void io_clean_op(struct io_kiocb *req)
}
if (req->flags & REQ_F_CREDS)
put_cred(req->creds);
-
+ if (req->flags & REQ_F_ASYNC_DATA) {
+ kfree(req->async_data);
+ req->async_data = NULL;
+ }
req->flags &= ~IO_REQ_CLEAN_FLAGS;
}
static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
{
- struct io_ring_ctx *ctx = req->ctx;
const struct cred *creds = NULL;
int ret;
- if ((req->flags & REQ_F_CREDS) && req->creds != current_cred())
+ if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
switch (req->opcode) {
@@ -6762,8 +6701,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (ret)
return ret;
/* If the op doesn't have a file, we're not polling for it */
- if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file)
- io_iopoll_req_issued(req);
+ if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file)
+ io_iopoll_req_issued(req, issue_flags);
return 0;
}
@@ -6779,6 +6718,8 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work)
static void io_wq_submit_work(struct io_wq_work *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ unsigned int issue_flags = IO_URING_F_UNLOCKED;
+ bool needs_poll = false;
struct io_kiocb *timeout;
int ret = 0;
@@ -6793,23 +6734,42 @@ static void io_wq_submit_work(struct io_wq_work *work)
io_queue_linked_timeout(timeout);
/* either cancelled or io-wq is dying, so don't touch tctx->iowq */
- if (work->flags & IO_WQ_WORK_CANCEL)
- ret = -ECANCELED;
+ if (work->flags & IO_WQ_WORK_CANCEL) {
+ io_req_task_queue_fail(req, -ECANCELED);
+ return;
+ }
- if (!ret) {
- do {
- ret = io_issue_sqe(req, 0);
- /*
- * We can get EAGAIN for polled IO even though we're
- * forcing a sync submission from here, since we can't
- * wait for request slots on the block side.
- */
- if (ret != -EAGAIN)
- break;
- cond_resched();
- } while (1);
+ if (req->flags & REQ_F_FORCE_ASYNC) {
+ const struct io_op_def *def = &io_op_defs[req->opcode];
+ bool opcode_poll = def->pollin || def->pollout;
+
+ if (opcode_poll && file_can_poll(req->file)) {
+ needs_poll = true;
+ issue_flags |= IO_URING_F_NONBLOCK;
+ }
}
+ do {
+ ret = io_issue_sqe(req, issue_flags);
+ if (ret != -EAGAIN)
+ break;
+ /*
+ * We can get EAGAIN for iopolled IO even though we're
+ * forcing a sync submission from here, since we can't
+ * wait for request slots on the block side.
+ */
+ if (!needs_poll) {
+ cond_resched();
+ continue;
+ }
+
+ if (io_arm_poll_handler(req) == IO_APOLL_OK)
+ return;
+ /* aborted or ready, in either case retry blocking */
+ needs_poll = false;
+ issue_flags &= ~IO_URING_F_NONBLOCK;
+ } while (1);
+
/* avoid locking problems by failing it from a clean context */
if (ret)
io_req_task_queue_fail(req, ret);
@@ -6833,12 +6793,7 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file
{
unsigned long file_ptr = (unsigned long) file;
- if (__io_file_supports_nowait(file, READ))
- file_ptr |= FFS_ASYNC_READ;
- if (__io_file_supports_nowait(file, WRITE))
- file_ptr |= FFS_ASYNC_WRITE;
- if (S_ISREG(file_inode(file)->i_mode))
- file_ptr |= FFS_ISREG;
+ file_ptr |= io_file_get_flags(file);
file_slot->file_ptr = file_ptr;
}
@@ -6855,8 +6810,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx,
file = (struct file *) (file_ptr & FFS_MASK);
file_ptr &= ~FFS_MASK;
/* mask in overlapping REQ_F and FFS bits */
- req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT);
- io_req_set_rsrc_node(req);
+ req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT);
+ io_req_set_rsrc_node(req, ctx);
return file;
}
@@ -6948,67 +6903,66 @@ static void io_queue_linked_timeout(struct io_kiocb *req)
io_put_req(req);
}
-static void __io_queue_sqe(struct io_kiocb *req)
+static void io_queue_sqe_arm_apoll(struct io_kiocb *req)
+ __must_hold(&req->ctx->uring_lock)
+{
+ struct io_kiocb *linked_timeout = io_prep_linked_timeout(req);
+
+ switch (io_arm_poll_handler(req)) {
+ case IO_APOLL_READY:
+ if (linked_timeout) {
+ io_queue_linked_timeout(linked_timeout);
+ linked_timeout = NULL;
+ }
+ io_req_task_queue(req);
+ break;
+ case IO_APOLL_ABORTED:
+ /*
+ * Queued up for async execution, worker will release
+ * submit reference when the iocb is actually submitted.
+ */
+ io_queue_async_work(req, NULL);
+ break;
+ }
+
+ if (linked_timeout)
+ io_queue_linked_timeout(linked_timeout);
+}
+
+static inline void __io_queue_sqe(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
struct io_kiocb *linked_timeout;
int ret;
-issue_sqe:
ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
+ if (req->flags & REQ_F_COMPLETE_INLINE) {
+ io_req_add_compl_list(req);
+ return;
+ }
/*
* We async punt it if the file wasn't marked NOWAIT, or if the file
* doesn't support non-blocking read/write attempts
*/
if (likely(!ret)) {
- if (req->flags & REQ_F_COMPLETE_INLINE) {
- struct io_ring_ctx *ctx = req->ctx;
- struct io_submit_state *state = &ctx->submit_state;
-
- state->compl_reqs[state->compl_nr++] = req;
- if (state->compl_nr == ARRAY_SIZE(state->compl_reqs))
- io_submit_flush_completions(ctx);
- return;
- }
-
linked_timeout = io_prep_linked_timeout(req);
if (linked_timeout)
io_queue_linked_timeout(linked_timeout);
} else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) {
- linked_timeout = io_prep_linked_timeout(req);
-
- switch (io_arm_poll_handler(req)) {
- case IO_APOLL_READY:
- if (linked_timeout)
- io_unprep_linked_timeout(req);
- goto issue_sqe;
- case IO_APOLL_ABORTED:
- /*
- * Queued up for async execution, worker will release
- * submit reference when the iocb is actually submitted.
- */
- io_queue_async_work(req, NULL);
- break;
- }
-
- if (linked_timeout)
- io_queue_linked_timeout(linked_timeout);
+ io_queue_sqe_arm_apoll(req);
} else {
io_req_complete_failed(req, ret);
}
}
-static inline void io_queue_sqe(struct io_kiocb *req)
+static void io_queue_sqe_fallback(struct io_kiocb *req)
__must_hold(&req->ctx->uring_lock)
{
- if (unlikely(req->ctx->drain_active) && io_drain_req(req))
- return;
-
- if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) {
- __io_queue_sqe(req);
- } else if (req->flags & REQ_F_FAIL) {
+ if (req->flags & REQ_F_FAIL) {
io_req_complete_fail_submit(req);
+ } else if (unlikely(req->ctx->drain_active)) {
+ io_drain_req(req);
} else {
int ret = io_req_prep_async(req);
@@ -7019,6 +6973,15 @@ static inline void io_queue_sqe(struct io_kiocb *req)
}
}
+static inline void io_queue_sqe(struct io_kiocb *req)
+ __must_hold(&req->ctx->uring_lock)
+{
+ if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL))))
+ __io_queue_sqe(req);
+ else
+ io_queue_sqe_fallback(req);
+}
+
/*
* Check SQE restrictions (opcode and flags).
*
@@ -7028,9 +6991,6 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
struct io_kiocb *req,
unsigned int sqe_flags)
{
- if (likely(!ctx->restricted))
- return true;
-
if (!test_bit(req->opcode, ctx->restrictions.sqe_op))
return false;
@@ -7045,16 +7005,35 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx,
return true;
}
+static void io_init_req_drain(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ struct io_kiocb *head = ctx->submit_state.link.head;
+
+ ctx->drain_active = true;
+ if (head) {
+ /*
+ * If we need to drain a request in the middle of a link, drain
+ * the head request and the next request/link after the current
+ * link. Considering sequential execution of links,
+ * IOSQE_IO_DRAIN will be maintained for every request of our
+ * link.
+ */
+ head->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC;
+ ctx->drain_next = true;
+ }
+}
+
static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct io_uring_sqe *sqe)
__must_hold(&ctx->uring_lock)
{
- struct io_submit_state *state;
unsigned int sqe_flags;
- int personality, ret = 0;
+ int personality;
+ u8 opcode;
/* req is partially pre-initialised, see io_preinit_req() */
- req->opcode = READ_ONCE(sqe->opcode);
+ req->opcode = opcode = READ_ONCE(sqe->opcode);
/* same numerical values with corresponding REQ_F_*, safe to copy */
req->flags = sqe_flags = READ_ONCE(sqe->flags);
req->user_data = READ_ONCE(sqe->user_data);
@@ -7062,19 +7041,52 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
req->fixed_rsrc_refs = NULL;
req->task = current;
- /* enforce forwards compatibility on users */
- if (unlikely(sqe_flags & ~SQE_VALID_FLAGS))
- return -EINVAL;
- if (unlikely(req->opcode >= IORING_OP_LAST))
+ if (unlikely(opcode >= IORING_OP_LAST)) {
+ req->opcode = 0;
return -EINVAL;
- if (!io_check_restriction(ctx, req, sqe_flags))
- return -EACCES;
+ }
+ if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
+ /* enforce forwards compatibility on users */
+ if (sqe_flags & ~SQE_VALID_FLAGS)
+ return -EINVAL;
+ if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
+ !io_op_defs[opcode].buffer_select)
+ return -EOPNOTSUPP;
+ if (sqe_flags & IOSQE_IO_DRAIN)
+ io_init_req_drain(req);
+ }
+ if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) {
+ if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags))
+ return -EACCES;
+ /* knock it to the slow queue path, will be drained there */
+ if (ctx->drain_active)
+ req->flags |= REQ_F_FORCE_ASYNC;
+ /* if there is no link, we're at "next" request and need to drain */
+ if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) {
+ ctx->drain_next = false;
+ ctx->drain_active = true;
+ req->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC;
+ }
+ }
- if ((sqe_flags & IOSQE_BUFFER_SELECT) &&
- !io_op_defs[req->opcode].buffer_select)
- return -EOPNOTSUPP;
- if (unlikely(sqe_flags & IOSQE_IO_DRAIN))
- ctx->drain_active = true;
+ if (io_op_defs[opcode].needs_file) {
+ struct io_submit_state *state = &ctx->submit_state;
+
+ /*
+ * Plug now if we have more than 2 IO left after this, and the
+ * target is potentially a read/write to block based storage.
+ */
+ if (state->need_plug && io_op_defs[opcode].plug) {
+ state->plug_started = true;
+ state->need_plug = false;
+ blk_start_plug_nr_ios(&state->plug, state->submit_nr);
+ }
+
+ req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
+ (sqe_flags & IOSQE_FIXED_FILE));
+ if (unlikely(!req->file))
+ return -EBADF;
+ }
personality = READ_ONCE(sqe->personality);
if (personality) {
@@ -7084,27 +7096,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
get_cred(req->creds);
req->flags |= REQ_F_CREDS;
}
- state = &ctx->submit_state;
- /*
- * Plug now if we have more than 1 IO left after this, and the target
- * is potentially a read/write to block based storage.
- */
- if (!state->plug_started && state->ios_left > 1 &&
- io_op_defs[req->opcode].plug) {
- blk_start_plug(&state->plug);
- state->plug_started = true;
- }
-
- if (io_op_defs[req->opcode].needs_file) {
- req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd),
- (sqe_flags & IOSQE_FIXED_FILE));
- if (unlikely(!req->file))
- ret = -EBADF;
- }
-
- state->ios_left--;
- return ret;
+ return io_req_prep(req, sqe);
}
static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
@@ -7116,7 +7109,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_init_req(ctx, req, sqe);
if (unlikely(ret)) {
-fail_req:
+ trace_io_uring_req_failed(sqe, ret);
+
/* fail even hard links since we don't submit */
if (link->head) {
/*
@@ -7139,10 +7133,6 @@ fail_req:
return ret;
}
req_fail_link_node(req, ret);
- } else {
- ret = io_req_prep(req, sqe);
- if (unlikely(ret))
- goto fail_req;
}
/* don't need @sqe from now on */
@@ -7172,33 +7162,32 @@ fail_req:
link->last->link = req;
link->last = req;
+ if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK))
+ return 0;
/* last request of a link, enqueue the link */
- if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) {
- link->head = NULL;
- io_queue_sqe(head);
- }
- } else {
- if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
- link->head = req;
- link->last = req;
- } else {
- io_queue_sqe(req);
- }
+ link->head = NULL;
+ req = head;
+ } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) {
+ link->head = req;
+ link->last = req;
+ return 0;
}
+ io_queue_sqe(req);
return 0;
}
/*
* Batched submission is done, ensure local IO is flushed out.
*/
-static void io_submit_state_end(struct io_submit_state *state,
- struct io_ring_ctx *ctx)
+static void io_submit_state_end(struct io_ring_ctx *ctx)
{
+ struct io_submit_state *state = &ctx->submit_state;
+
if (state->link.head)
io_queue_sqe(state->link.head);
- if (state->compl_nr)
- io_submit_flush_completions(ctx);
+ /* flush only after queuing links as they can generate completions */
+ io_submit_flush_completions(ctx);
if (state->plug_started)
blk_finish_plug(&state->plug);
}
@@ -7210,7 +7199,8 @@ static void io_submit_state_start(struct io_submit_state *state,
unsigned int max_ios)
{
state->plug_started = false;
- state->ios_left = max_ios;
+ state->need_plug = max_ios > 2;
+ state->submit_nr = max_ios;
/* set only head, no need to init link_last in advance */
state->link.head = NULL;
}
@@ -7262,45 +7252,45 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx)
static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr)
__must_hold(&ctx->uring_lock)
{
+ unsigned int entries = io_sqring_entries(ctx);
int submitted = 0;
+ if (unlikely(!entries))
+ return 0;
/* make sure SQ entry isn't read before tail */
- nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx));
- if (!percpu_ref_tryget_many(&ctx->refs, nr))
- return -EAGAIN;
+ nr = min3(nr, ctx->sq_entries, entries);
io_get_task_refs(nr);
io_submit_state_start(&ctx->submit_state, nr);
- while (submitted < nr) {
+ do {
const struct io_uring_sqe *sqe;
struct io_kiocb *req;
- req = io_alloc_req(ctx);
- if (unlikely(!req)) {
+ if (unlikely(!io_alloc_req_refill(ctx))) {
if (!submitted)
submitted = -EAGAIN;
break;
}
+ req = io_alloc_req(ctx);
sqe = io_get_sqe(ctx);
if (unlikely(!sqe)) {
- list_add(&req->inflight_entry, &ctx->submit_state.free_list);
+ wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list);
break;
}
/* will complete beyond this point, count as submitted */
submitted++;
if (io_submit_sqe(ctx, req, sqe))
break;
- }
+ } while (submitted < nr);
if (unlikely(submitted != nr)) {
int ref_used = (submitted == -EAGAIN) ? 0 : submitted;
int unused = nr - ref_used;
current->io_uring->cached_refs += unused;
- percpu_ref_put_many(&ctx->refs, unused);
}
- io_submit_state_end(&ctx->submit_state, ctx);
+ io_submit_state_end(ctx);
/* Commit SQ ring head once we've consumed and submitted all SQEs */
io_commit_sqring(ctx);
@@ -7339,16 +7329,15 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE)
to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE;
- if (!list_empty(&ctx->iopoll_list) || to_submit) {
- unsigned nr_events = 0;
+ if (!wq_list_empty(&ctx->iopoll_list) || to_submit) {
const struct cred *creds = NULL;
if (ctx->sq_creds != current_cred())
creds = override_creds(ctx->sq_creds);
mutex_lock(&ctx->uring_lock);
- if (!list_empty(&ctx->iopoll_list))
- io_do_iopoll(ctx, &nr_events, 0);
+ if (!wq_list_empty(&ctx->iopoll_list))
+ io_do_iopoll(ctx, true);
/*
* Don't submit if refs are dying, good for io_uring_register(),
@@ -7368,7 +7357,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
return ret;
}
-static void io_sqd_update_thread_idle(struct io_sq_data *sqd)
+static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd)
{
struct io_ring_ctx *ctx;
unsigned sq_thread_idle = 0;
@@ -7425,7 +7414,7 @@ static int io_sq_thread(void *data)
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) {
int ret = __io_sq_thread(ctx, cap_entries);
- if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list)))
+ if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list)))
sqt_spin = true;
}
if (io_run_task_work())
@@ -7446,7 +7435,7 @@ static int io_sq_thread(void *data)
io_ring_set_wakeup_flag(ctx);
if ((ctx->flags & IORING_SETUP_IOPOLL) &&
- !list_empty_careful(&ctx->iopoll_list)) {
+ !wq_list_empty(&ctx->iopoll_list)) {
needs_sched = false;
break;
}
@@ -7622,7 +7611,7 @@ static void io_free_page_table(void **table, size_t size)
kfree(table);
}
-static void **io_alloc_page_table(size_t size)
+static __cold void **io_alloc_page_table(size_t size)
{
unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE);
size_t init_size = size;
@@ -7651,7 +7640,7 @@ static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node)
kfree(ref_node);
}
-static void io_rsrc_node_ref_zero(struct percpu_ref *ref)
+static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref)
{
struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs);
struct io_ring_ctx *ctx = node->rsrc_data->ctx;
@@ -7697,10 +7686,13 @@ static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx)
static void io_rsrc_node_switch(struct io_ring_ctx *ctx,
struct io_rsrc_data *data_to_kill)
+ __must_hold(&ctx->uring_lock)
{
WARN_ON_ONCE(!ctx->rsrc_backup_node);
WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node);
+ io_rsrc_refs_drop(ctx);
+
if (data_to_kill) {
struct io_rsrc_node *rsrc_node = ctx->rsrc_node;
@@ -7728,7 +7720,8 @@ static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx)
return ctx->rsrc_backup_node ? 0 : -ENOMEM;
}
-static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx)
+static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data,
+ struct io_ring_ctx *ctx)
{
int ret;
@@ -7784,9 +7777,9 @@ static void io_rsrc_data_free(struct io_rsrc_data *data)
kfree(data);
}
-static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
- u64 __user *utags, unsigned nr,
- struct io_rsrc_data **pdata)
+static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put,
+ u64 __user *utags, unsigned nr,
+ struct io_rsrc_data **pdata)
{
struct io_rsrc_data *data;
int ret = -ENOMEM;
@@ -8354,12 +8347,12 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
unsigned int issue_flags, u32 slot_index)
{
struct io_ring_ctx *ctx = req->ctx;
- bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
bool needs_switch = false;
struct io_fixed_file *file_slot;
int ret = -EBADF;
- io_ring_submit_lock(ctx, !force_nonblock);
+ io_ring_submit_lock(ctx, needs_lock);
if (file->f_op == &io_uring_fops)
goto err;
ret = -ENXIO;
@@ -8400,7 +8393,7 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file,
err:
if (needs_switch)
io_rsrc_node_switch(ctx, ctx->file_data);
- io_ring_submit_unlock(ctx, !force_nonblock);
+ io_ring_submit_unlock(ctx, needs_lock);
if (ret)
fput(file);
return ret;
@@ -8410,11 +8403,12 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
{
unsigned int offset = req->close.file_slot - 1;
struct io_ring_ctx *ctx = req->ctx;
+ bool needs_lock = issue_flags & IO_URING_F_UNLOCKED;
struct io_fixed_file *file_slot;
struct file *file;
int ret, i;
- io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_lock(ctx, needs_lock);
ret = -ENXIO;
if (unlikely(!ctx->file_data))
goto out;
@@ -8440,7 +8434,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags)
io_rsrc_node_switch(ctx, ctx->file_data);
ret = 0;
out:
- io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK));
+ io_ring_submit_unlock(ctx, needs_lock);
return ret;
}
@@ -8556,8 +8550,8 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
return io_wq_create(concurrency, &data);
}
-static int io_uring_alloc_task_context(struct task_struct *task,
- struct io_ring_ctx *ctx)
+static __cold int io_uring_alloc_task_context(struct task_struct *task,
+ struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx;
int ret;
@@ -8604,8 +8598,8 @@ void __io_uring_free(struct task_struct *tsk)
tsk->io_uring = NULL;
}
-static int io_sq_offload_create(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
+static __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
{
int ret;
@@ -9216,29 +9210,25 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx)
}
}
-static void io_req_cache_free(struct list_head *list)
-{
- struct io_kiocb *req, *nxt;
-
- list_for_each_entry_safe(req, nxt, list, inflight_entry) {
- list_del(&req->inflight_entry);
- kmem_cache_free(req_cachep, req);
- }
-}
-
static void io_req_caches_free(struct io_ring_ctx *ctx)
{
struct io_submit_state *state = &ctx->submit_state;
+ int nr = 0;
mutex_lock(&ctx->uring_lock);
+ io_flush_cached_locked_reqs(ctx, state);
- if (state->free_reqs) {
- kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs);
- state->free_reqs = 0;
- }
+ while (state->free_list.next) {
+ struct io_wq_work_node *node;
+ struct io_kiocb *req;
- io_flush_cached_locked_reqs(ctx, state);
- io_req_cache_free(&state->free_list);
+ node = wq_stack_extract(&state->free_list);
+ req = container_of(node, struct io_kiocb, comp_list);
+ kmem_cache_free(req_cachep, req);
+ nr++;
+ }
+ if (nr)
+ percpu_ref_put_many(&ctx->refs, nr);
mutex_unlock(&ctx->uring_lock);
}
@@ -9248,7 +9238,7 @@ static void io_wait_rsrc_data(struct io_rsrc_data *data)
wait_for_completion(&data->done);
}
-static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
io_sq_thread_finish(ctx);
@@ -9257,6 +9247,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
ctx->mm_account = NULL;
}
+ io_rsrc_refs_drop(ctx);
/* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */
io_wait_rsrc_data(ctx->buf_data);
io_wait_rsrc_data(ctx->file_data);
@@ -9280,6 +9271,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
if (ctx->rsrc_backup_node)
io_rsrc_node_destroy(ctx->rsrc_backup_node);
flush_delayed_work(&ctx->rsrc_put_work);
+ flush_delayed_work(&ctx->fallback_work);
WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list));
WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist));
@@ -9310,7 +9302,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait)
struct io_ring_ctx *ctx = file->private_data;
__poll_t mask = 0;
- poll_wait(file, &ctx->poll_wait, wait);
+ poll_wait(file, &ctx->cq_wait, wait);
/*
* synchronizes with barrier from wq_has_sleeper call in
* io_commit_cqring
@@ -9357,7 +9349,7 @@ struct io_tctx_exit {
struct io_ring_ctx *ctx;
};
-static void io_tctx_exit_cb(struct callback_head *cb)
+static __cold void io_tctx_exit_cb(struct callback_head *cb)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_exit *work;
@@ -9372,14 +9364,14 @@ static void io_tctx_exit_cb(struct callback_head *cb)
complete(&work->completion);
}
-static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
+static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
return req->ctx == data;
}
-static void io_ring_exit_work(struct work_struct *work)
+static __cold void io_ring_exit_work(struct work_struct *work)
{
struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work);
unsigned long timeout = jiffies + HZ * 60 * 5;
@@ -9408,6 +9400,8 @@ static void io_ring_exit_work(struct work_struct *work)
io_sq_thread_unpark(sqd);
}
+ io_req_caches_free(ctx);
+
if (WARN_ON_ONCE(time_after(jiffies, timeout))) {
/* there is little hope left, don't run it too often */
interval = HZ * 60;
@@ -9434,7 +9428,6 @@ static void io_ring_exit_work(struct work_struct *work)
ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL);
if (WARN_ON_ONCE(ret))
continue;
- wake_up_process(node->task);
mutex_unlock(&ctx->uring_lock);
wait_for_completion(&exit.completion);
@@ -9448,8 +9441,8 @@ static void io_ring_exit_work(struct work_struct *work)
}
/* Returns true if we found and killed one or more timeouts */
-static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
- bool cancel_all)
+static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx,
+ struct task_struct *tsk, bool cancel_all)
{
struct io_kiocb *req, *tmp;
int canceled = 0;
@@ -9471,7 +9464,7 @@ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk,
return canceled != 0;
}
-static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
+static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
{
unsigned long index;
struct creds *creds;
@@ -9533,8 +9526,9 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data)
return ret;
}
-static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
- struct task_struct *task, bool cancel_all)
+static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ bool cancel_all)
{
struct io_defer_entry *de;
LIST_HEAD(list);
@@ -9559,7 +9553,7 @@ static bool io_cancel_defer_files(struct io_ring_ctx *ctx,
return true;
}
-static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
+static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
{
struct io_tctx_node *node;
enum io_wq_cancel cret;
@@ -9583,9 +9577,9 @@ static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx)
return ret;
}
-static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
- struct task_struct *task,
- bool cancel_all)
+static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
+ struct task_struct *task,
+ bool cancel_all)
{
struct io_task_cancel cancel = { .task = task, .all = cancel_all, };
struct io_uring_task *tctx = task ? task->io_uring : NULL;
@@ -9609,7 +9603,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
/* SQPOLL thread does its own polling */
if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) ||
(ctx->sq_data && ctx->sq_data->thread == current)) {
- while (!list_empty_careful(&ctx->iopoll_list)) {
+ while (!wq_list_empty(&ctx->iopoll_list)) {
io_iopoll_try_reap_events(ctx);
ret = true;
}
@@ -9636,7 +9630,16 @@ static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
ret = io_uring_alloc_task_context(current, ctx);
if (unlikely(ret))
return ret;
+
tctx = current->io_uring;
+ if (ctx->iowq_limits_set) {
+ unsigned int limits[2] = { ctx->iowq_limits[0],
+ ctx->iowq_limits[1], };
+
+ ret = io_wq_max_workers(tctx->io_wq, limits);
+ if (ret)
+ return ret;
+ }
}
if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
node = kmalloc(sizeof(*node), GFP_KERNEL);
@@ -9675,7 +9678,7 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx)
/*
* Remove this io_uring_file -> task mapping.
*/
-static void io_uring_del_tctx_node(unsigned long index)
+static __cold void io_uring_del_tctx_node(unsigned long index)
{
struct io_uring_task *tctx = current->io_uring;
struct io_tctx_node *node;
@@ -9698,7 +9701,7 @@ static void io_uring_del_tctx_node(unsigned long index)
kfree(node);
}
-static void io_uring_clean_tctx(struct io_uring_task *tctx)
+static __cold void io_uring_clean_tctx(struct io_uring_task *tctx)
{
struct io_wq *wq = tctx->io_wq;
struct io_tctx_node *node;
@@ -9725,7 +9728,7 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked)
return percpu_counter_sum(&tctx->inflight);
}
-static void io_uring_drop_tctx_refs(struct task_struct *task)
+static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
{
struct io_uring_task *tctx = task->io_uring;
unsigned int refs = tctx->cached_refs;
@@ -9741,7 +9744,8 @@ static void io_uring_drop_tctx_refs(struct task_struct *task)
* Find any io_uring ctx that this task has registered or done IO on, and cancel
* requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation.
*/
-static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
+static __cold void io_uring_cancel_generic(bool cancel_all,
+ struct io_sq_data *sqd)
{
struct io_uring_task *tctx = current->io_uring;
struct io_ring_ctx *ctx;
@@ -9834,7 +9838,7 @@ static void *io_uring_validate_mmap_request(struct file *file,
#ifdef CONFIG_MMU
-static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
{
size_t sz = vma->vm_end - vma->vm_start;
unsigned long pfn;
@@ -10019,7 +10023,7 @@ out_fput:
}
#ifdef CONFIG_PROC_FS
-static int io_uring_show_cred(struct seq_file *m, unsigned int id,
+static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id,
const struct cred *cred)
{
struct user_namespace *uns = seq_user_ns(m);
@@ -10051,11 +10055,59 @@ static int io_uring_show_cred(struct seq_file *m, unsigned int id,
return 0;
}
-static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
+static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx,
+ struct seq_file *m)
{
struct io_sq_data *sq = NULL;
+ struct io_overflow_cqe *ocqe;
+ struct io_rings *r = ctx->rings;
+ unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1;
+ unsigned int sq_head = READ_ONCE(r->sq.head);
+ unsigned int sq_tail = READ_ONCE(r->sq.tail);
+ unsigned int cq_head = READ_ONCE(r->cq.head);
+ unsigned int cq_tail = READ_ONCE(r->cq.tail);
+ unsigned int sq_entries, cq_entries;
bool has_lock;
- int i;
+ unsigned int i;
+
+ /*
+ * we may get imprecise sqe and cqe info if uring is actively running
+ * since we get cached_sq_head and cached_cq_tail without uring_lock
+ * and sq_tail and cq_head are changed by userspace. But it's ok since
+ * we usually use these info when it is stuck.
+ */
+ seq_printf(m, "SqMask:\t\t0x%x\n", sq_mask);
+ seq_printf(m, "SqHead:\t%u\n", sq_head);
+ seq_printf(m, "SqTail:\t%u\n", sq_tail);
+ seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head);
+ seq_printf(m, "CqMask:\t0x%x\n", cq_mask);
+ seq_printf(m, "CqHead:\t%u\n", cq_head);
+ seq_printf(m, "CqTail:\t%u\n", cq_tail);
+ seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail);
+ seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head);
+ sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
+ for (i = 0; i < sq_entries; i++) {
+ unsigned int entry = i + sq_head;
+ unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+ struct io_uring_sqe *sqe = &ctx->sq_sqes[sq_idx];
+
+ if (sq_idx > sq_mask)
+ continue;
+ sqe = &ctx->sq_sqes[sq_idx];
+ seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n",
+ sq_idx, sqe->opcode, sqe->fd, sqe->flags,
+ sqe->user_data);
+ }
+ seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
+ cq_entries = min(cq_tail - cq_head, ctx->cq_entries);
+ for (i = 0; i < cq_entries; i++) {
+ unsigned int entry = i + cq_head;
+ struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask];
+
+ seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n",
+ entry & cq_mask, cqe->user_data, cqe->res,
+ cqe->flags);
+ }
/*
* Avoid ABBA deadlock between the seq lock and the io_uring mutex,
@@ -10097,7 +10149,10 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
xa_for_each(&ctx->personalities, index, cred)
io_uring_show_cred(m, index, cred);
}
- seq_printf(m, "PollList:\n");
+ if (has_lock)
+ mutex_unlock(&ctx->uring_lock);
+
+ seq_puts(m, "PollList:\n");
spin_lock(&ctx->completion_lock);
for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) {
struct hlist_head *list = &ctx->cancel_hash[i];
@@ -10107,12 +10162,20 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
seq_printf(m, " op=%d, task_works=%d\n", req->opcode,
req->task->task_works != NULL);
}
+
+ seq_puts(m, "CqOverflowList:\n");
+ list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) {
+ struct io_uring_cqe *cqe = &ocqe->cqe;
+
+ seq_printf(m, " user_data=%llu, res=%d, flags=%x\n",
+ cqe->user_data, cqe->res, cqe->flags);
+
+ }
+
spin_unlock(&ctx->completion_lock);
- if (has_lock)
- mutex_unlock(&ctx->uring_lock);
}
-static void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
+static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f)
{
struct io_ring_ctx *ctx = f->private_data;
@@ -10136,8 +10199,8 @@ static const struct file_operations io_uring_fops = {
#endif
};
-static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
- struct io_uring_params *p)
+static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
{
struct io_rings *rings;
size_t size, sq_array_offset;
@@ -10226,8 +10289,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
return file;
}
-static int io_uring_create(unsigned entries, struct io_uring_params *p,
- struct io_uring_params __user *params)
+static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
+ struct io_uring_params __user *params)
{
struct io_ring_ctx *ctx;
struct file *file;
@@ -10385,7 +10448,8 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
return io_uring_setup(entries, params);
}
-static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args)
+static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
{
struct io_uring_probe *p;
size_t size;
@@ -10441,8 +10505,8 @@ static int io_register_personality(struct io_ring_ctx *ctx)
return id;
}
-static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg,
- unsigned int nr_args)
+static __cold int io_register_restrictions(struct io_ring_ctx *ctx,
+ void __user *arg, unsigned int nr_args)
{
struct io_uring_restriction *res;
size_t size;
@@ -10576,7 +10640,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
return __io_register_rsrc_update(ctx, type, &up, up.nr);
}
-static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
+static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
unsigned int size, unsigned int type)
{
struct io_uring_rsrc_register rr;
@@ -10602,8 +10666,8 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
return -EINVAL;
}
-static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg,
- unsigned len)
+static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx,
+ void __user *arg, unsigned len)
{
struct io_uring_task *tctx = current->io_uring;
cpumask_var_t new_mask;
@@ -10629,7 +10693,7 @@ static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg,
return ret;
}
-static int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
+static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
{
struct io_uring_task *tctx = current->io_uring;
@@ -10639,9 +10703,11 @@ static int io_unregister_iowq_aff(struct io_ring_ctx *ctx)
return io_wq_cpu_affinity(tctx->io_wq, NULL);
}
-static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
- void __user *arg)
+static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
+ void __user *arg)
+ __must_hold(&ctx->uring_lock)
{
+ struct io_tctx_node *node;
struct io_uring_task *tctx = NULL;
struct io_sq_data *sqd = NULL;
__u32 new_count[2];
@@ -10672,13 +10738,19 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
tctx = current->io_uring;
}
- ret = -EINVAL;
- if (!tctx || !tctx->io_wq)
- goto err;
+ BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
- ret = io_wq_max_workers(tctx->io_wq, new_count);
- if (ret)
- goto err;
+ memcpy(ctx->iowq_limits, new_count, sizeof(new_count));
+ ctx->iowq_limits_set = true;
+
+ ret = -EINVAL;
+ if (tctx && tctx->io_wq) {
+ ret = io_wq_max_workers(tctx->io_wq, new_count);
+ if (ret)
+ goto err;
+ } else {
+ memset(new_count, 0, sizeof(new_count));
+ }
if (sqd) {
mutex_unlock(&sqd->lock);
@@ -10688,6 +10760,22 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
if (copy_to_user(arg, new_count, sizeof(new_count)))
return -EFAULT;
+ /* that's it for SQPOLL, only the SQPOLL task creates requests */
+ if (sqd)
+ return 0;
+
+ /* now propagate the restriction to all registered users */
+ list_for_each_entry(node, &ctx->tctx_list, ctx_node) {
+ struct io_uring_task *tctx = node->task->io_uring;
+
+ if (WARN_ON_ONCE(!tctx->io_wq))
+ continue;
+
+ for (i = 0; i < ARRAY_SIZE(new_count); i++)
+ new_count[i] = ctx->iowq_limits[i];
+ /* ignore errors, it always returns zero anyway */
+ (void)io_wq_max_workers(tctx->io_wq, new_count);
+ }
return 0;
err:
if (sqd) {
@@ -10721,7 +10809,7 @@ static bool io_register_op_must_quiesce(int op)
}
}
-static int io_ctx_quiesce(struct io_ring_ctx *ctx)
+static __cold int io_ctx_quiesce(struct io_ring_ctx *ctx)
{
long ret;
@@ -10736,10 +10824,14 @@ static int io_ctx_quiesce(struct io_ring_ctx *ctx)
*/
mutex_unlock(&ctx->uring_lock);
do {
- ret = wait_for_completion_interruptible(&ctx->ref_comp);
- if (!ret)
+ ret = wait_for_completion_interruptible_timeout(&ctx->ref_comp, HZ);
+ if (ret) {
+ ret = min(0L, ret);
break;
+ }
+
ret = io_run_task_work_sig();
+ io_req_caches_free(ctx);
} while (ret >= 0);
mutex_lock(&ctx->uring_lock);
@@ -10970,6 +11062,8 @@ static int __init io_uring_init(void)
/* should fit into one byte */
BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
+ BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8));
+ BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS);
BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 176580f54af9..104ae698443e 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -13,6 +13,7 @@
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/seq_file.h>
+#include <linux/writeback.h>
#include "jfs_incore.h"
#include "jfs_superblock.h"
#include "jfs_filsys.h"
diff --git a/fs/kernel_read_file.c b/fs/kernel_read_file.c
index 87aac4c72c37..1b07550485b9 100644
--- a/fs/kernel_read_file.c
+++ b/fs/kernel_read_file.c
@@ -178,7 +178,7 @@ int kernel_read_file_from_fd(int fd, loff_t offset, void **buf,
struct fd f = fdget(fd);
int ret = -EBADF;
- if (!f.file)
+ if (!f.file || !(f.file->f_mode & FMODE_READ))
goto out;
ret = kernel_read_file(f.file, offset, buf, buf_size, file_size, id);
diff --git a/fs/ksmbd/auth.c b/fs/ksmbd/auth.c
index 71c989f1568d..30a92ddc1817 100644
--- a/fs/ksmbd/auth.c
+++ b/fs/ksmbd/auth.c
@@ -298,8 +298,8 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
int blob_len, struct ksmbd_session *sess)
{
char *domain_name;
- unsigned int lm_off, nt_off;
- unsigned short nt_len;
+ unsigned int nt_off, dn_off;
+ unsigned short nt_len, dn_len;
int ret;
if (blob_len < sizeof(struct authenticate_message)) {
@@ -314,15 +314,17 @@ int ksmbd_decode_ntlmssp_auth_blob(struct authenticate_message *authblob,
return -EINVAL;
}
- lm_off = le32_to_cpu(authblob->LmChallengeResponse.BufferOffset);
nt_off = le32_to_cpu(authblob->NtChallengeResponse.BufferOffset);
nt_len = le16_to_cpu(authblob->NtChallengeResponse.Length);
+ dn_off = le32_to_cpu(authblob->DomainName.BufferOffset);
+ dn_len = le16_to_cpu(authblob->DomainName.Length);
+
+ if (blob_len < (u64)dn_off + dn_len || blob_len < (u64)nt_off + nt_len)
+ return -EINVAL;
/* TODO : use domain name that imported from configuration file */
- domain_name = smb_strndup_from_utf16((const char *)authblob +
- le32_to_cpu(authblob->DomainName.BufferOffset),
- le16_to_cpu(authblob->DomainName.Length), true,
- sess->conn->local_nls);
+ domain_name = smb_strndup_from_utf16((const char *)authblob + dn_off,
+ dn_len, true, sess->conn->local_nls);
if (IS_ERR(domain_name))
return PTR_ERR(domain_name);
diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c
index 48b18b4ec117..b57a0d8a392f 100644
--- a/fs/ksmbd/connection.c
+++ b/fs/ksmbd/connection.c
@@ -61,6 +61,8 @@ struct ksmbd_conn *ksmbd_conn_alloc(void)
conn->local_nls = load_nls_default();
atomic_set(&conn->req_running, 0);
atomic_set(&conn->r_count, 0);
+ conn->total_credits = 1;
+
init_waitqueue_head(&conn->req_running_q);
INIT_LIST_HEAD(&conn->conns_list);
INIT_LIST_HEAD(&conn->sessions);
diff --git a/fs/ksmbd/ksmbd_netlink.h b/fs/ksmbd/ksmbd_netlink.h
index 2fbe2bc1e093..c6718a05d347 100644
--- a/fs/ksmbd/ksmbd_netlink.h
+++ b/fs/ksmbd/ksmbd_netlink.h
@@ -211,6 +211,7 @@ struct ksmbd_tree_disconnect_request {
*/
struct ksmbd_logout_request {
__s8 account[KSMBD_REQ_MAX_ACCOUNT_NAME_SZ]; /* user account name */
+ __u32 account_flags;
};
/*
@@ -317,6 +318,7 @@ enum KSMBD_TREE_CONN_STATUS {
#define KSMBD_USER_FLAG_BAD_UID BIT(2)
#define KSMBD_USER_FLAG_BAD_USER BIT(3)
#define KSMBD_USER_FLAG_GUEST_ACCOUNT BIT(4)
+#define KSMBD_USER_FLAG_DELAY_SESSION BIT(5)
/*
* Share config flags.
diff --git a/fs/ksmbd/mgmt/user_config.c b/fs/ksmbd/mgmt/user_config.c
index d21629ae5c89..1019d3677d55 100644
--- a/fs/ksmbd/mgmt/user_config.c
+++ b/fs/ksmbd/mgmt/user_config.c
@@ -55,7 +55,7 @@ struct ksmbd_user *ksmbd_alloc_user(struct ksmbd_login_response *resp)
void ksmbd_free_user(struct ksmbd_user *user)
{
- ksmbd_ipc_logout_request(user->name);
+ ksmbd_ipc_logout_request(user->name, user->flags);
kfree(user->name);
kfree(user->passkey);
kfree(user);
diff --git a/fs/ksmbd/mgmt/user_config.h b/fs/ksmbd/mgmt/user_config.h
index b2bb074a0150..aff80b029579 100644
--- a/fs/ksmbd/mgmt/user_config.h
+++ b/fs/ksmbd/mgmt/user_config.h
@@ -18,6 +18,7 @@ struct ksmbd_user {
size_t passkey_sz;
char *passkey;
+ unsigned int failed_login_count;
};
static inline bool user_guest(struct ksmbd_user *user)
diff --git a/fs/ksmbd/smb2misc.c b/fs/ksmbd/smb2misc.c
index 9edd9c161b27..030ca57c3784 100644
--- a/fs/ksmbd/smb2misc.c
+++ b/fs/ksmbd/smb2misc.c
@@ -284,11 +284,13 @@ static inline int smb2_ioctl_resp_len(struct smb2_ioctl_req *h)
le32_to_cpu(h->MaxOutputResponse);
}
-static int smb2_validate_credit_charge(struct smb2_hdr *hdr)
+static int smb2_validate_credit_charge(struct ksmbd_conn *conn,
+ struct smb2_hdr *hdr)
{
- int req_len = 0, expect_resp_len = 0, calc_credit_num, max_len;
- int credit_charge = le16_to_cpu(hdr->CreditCharge);
+ unsigned int req_len = 0, expect_resp_len = 0, calc_credit_num, max_len;
+ unsigned short credit_charge = le16_to_cpu(hdr->CreditCharge);
void *__hdr = hdr;
+ int ret;
switch (hdr->Command) {
case SMB2_QUERY_INFO:
@@ -310,21 +312,37 @@ static int smb2_validate_credit_charge(struct smb2_hdr *hdr)
req_len = smb2_ioctl_req_len(__hdr);
expect_resp_len = smb2_ioctl_resp_len(__hdr);
break;
- default:
+ case SMB2_CANCEL:
return 0;
+ default:
+ req_len = 1;
+ break;
}
- credit_charge = max(1, credit_charge);
- max_len = max(req_len, expect_resp_len);
+ credit_charge = max_t(unsigned short, credit_charge, 1);
+ max_len = max_t(unsigned int, req_len, expect_resp_len);
calc_credit_num = DIV_ROUND_UP(max_len, SMB2_MAX_BUFFER_SIZE);
if (credit_charge < calc_credit_num) {
- pr_err("Insufficient credit charge, given: %d, needed: %d\n",
- credit_charge, calc_credit_num);
+ ksmbd_debug(SMB, "Insufficient credit charge, given: %d, needed: %d\n",
+ credit_charge, calc_credit_num);
+ return 1;
+ } else if (credit_charge > conn->max_credits) {
+ ksmbd_debug(SMB, "Too large credit charge: %d\n", credit_charge);
return 1;
}
- return 0;
+ spin_lock(&conn->credits_lock);
+ if (credit_charge <= conn->total_credits) {
+ conn->total_credits -= credit_charge;
+ ret = 0;
+ } else {
+ ksmbd_debug(SMB, "Insufficient credits granted, given: %u, granted: %u\n",
+ credit_charge, conn->total_credits);
+ ret = 1;
+ }
+ spin_unlock(&conn->credits_lock);
+ return ret;
}
int ksmbd_smb2_check_message(struct ksmbd_work *work)
@@ -382,26 +400,20 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work)
}
}
- if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) &&
- smb2_validate_credit_charge(hdr)) {
- work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER);
- return 1;
- }
-
if (smb2_calc_size(hdr, &clc_len))
return 1;
if (len != clc_len) {
/* client can return one byte more due to implied bcc[0] */
if (clc_len == len + 1)
- return 0;
+ goto validate_credit;
/*
* Some windows servers (win2016) will pad also the final
* PDU in a compound to 8 bytes.
*/
if (ALIGN(clc_len, 8) == len)
- return 0;
+ goto validate_credit;
/*
* windows client also pad up to 8 bytes when compounding.
@@ -414,7 +426,7 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work)
"cli req padded more than expected. Length %d not %d for cmd:%d mid:%llu\n",
len, clc_len, command,
le64_to_cpu(hdr->MessageId));
- return 0;
+ goto validate_credit;
}
ksmbd_debug(SMB,
@@ -425,6 +437,13 @@ int ksmbd_smb2_check_message(struct ksmbd_work *work)
return 1;
}
+validate_credit:
+ if ((work->conn->vals->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU) &&
+ smb2_validate_credit_charge(work->conn, hdr)) {
+ work->conn->ops->set_rsp_status(work, STATUS_INVALID_PARAMETER);
+ return 1;
+ }
+
return 0;
}
diff --git a/fs/ksmbd/smb2ops.c b/fs/ksmbd/smb2ops.c
index b06456eb587b..fb6a65d23139 100644
--- a/fs/ksmbd/smb2ops.c
+++ b/fs/ksmbd/smb2ops.c
@@ -284,6 +284,7 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
void init_smb2_max_read_size(unsigned int sz)
{
+ sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE);
smb21_server_values.max_read_size = sz;
smb30_server_values.max_read_size = sz;
smb302_server_values.max_read_size = sz;
@@ -292,6 +293,7 @@ void init_smb2_max_read_size(unsigned int sz)
void init_smb2_max_write_size(unsigned int sz)
{
+ sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE);
smb21_server_values.max_write_size = sz;
smb30_server_values.max_write_size = sz;
smb302_server_values.max_write_size = sz;
@@ -300,6 +302,7 @@ void init_smb2_max_write_size(unsigned int sz)
void init_smb2_max_trans_size(unsigned int sz)
{
+ sz = clamp_val(sz, SMB3_MIN_IOSIZE, SMB3_MAX_IOSIZE);
smb21_server_values.max_trans_size = sz;
smb30_server_values.max_trans_size = sz;
smb302_server_values.max_trans_size = sz;
diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c
index 005aa93a49d6..7e448df3f847 100644
--- a/fs/ksmbd/smb2pdu.c
+++ b/fs/ksmbd/smb2pdu.c
@@ -292,22 +292,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work)
return 0;
}
-static int smb2_consume_credit_charge(struct ksmbd_work *work,
- unsigned short credit_charge)
-{
- struct ksmbd_conn *conn = work->conn;
- unsigned int rsp_credits = 1;
-
- if (!conn->total_credits)
- return 0;
-
- if (credit_charge > 0)
- rsp_credits = credit_charge;
-
- conn->total_credits -= rsp_credits;
- return rsp_credits;
-}
-
/**
* smb2_set_rsp_credits() - set number of credits in response buffer
* @work: smb work containing smb response buffer
@@ -317,49 +301,43 @@ int smb2_set_rsp_credits(struct ksmbd_work *work)
struct smb2_hdr *req_hdr = ksmbd_req_buf_next(work);
struct smb2_hdr *hdr = ksmbd_resp_buf_next(work);
struct ksmbd_conn *conn = work->conn;
- unsigned short credits_requested = le16_to_cpu(req_hdr->CreditRequest);
- unsigned short credit_charge = 1, credits_granted = 0;
- unsigned short aux_max, aux_credits, min_credits;
- int rsp_credit_charge;
+ unsigned short credits_requested;
+ unsigned short credit_charge, credits_granted = 0;
+ unsigned short aux_max, aux_credits;
- if (hdr->Command == SMB2_CANCEL)
- goto out;
+ if (work->send_no_response)
+ return 0;
- /* get default minimum credits by shifting maximum credits by 4 */
- min_credits = conn->max_credits >> 4;
+ hdr->CreditCharge = req_hdr->CreditCharge;
- if (conn->total_credits >= conn->max_credits) {
+ if (conn->total_credits > conn->max_credits) {
+ hdr->CreditRequest = 0;
pr_err("Total credits overflow: %d\n", conn->total_credits);
- conn->total_credits = min_credits;
- }
-
- rsp_credit_charge =
- smb2_consume_credit_charge(work, le16_to_cpu(req_hdr->CreditCharge));
- if (rsp_credit_charge < 0)
return -EINVAL;
+ }
- hdr->CreditCharge = cpu_to_le16(rsp_credit_charge);
+ credit_charge = max_t(unsigned short,
+ le16_to_cpu(req_hdr->CreditCharge), 1);
+ credits_requested = max_t(unsigned short,
+ le16_to_cpu(req_hdr->CreditRequest), 1);
- if (credits_requested > 0) {
- aux_credits = credits_requested - 1;
- aux_max = 32;
- if (hdr->Command == SMB2_NEGOTIATE)
- aux_max = 0;
- aux_credits = (aux_credits < aux_max) ? aux_credits : aux_max;
- credits_granted = aux_credits + credit_charge;
+ /* according to smb2.credits smbtorture, Windows server
+ * 2016 or later grant up to 8192 credits at once.
+ *
+ * TODO: Need to adjuct CreditRequest value according to
+ * current cpu load
+ */
+ aux_credits = credits_requested - 1;
+ if (hdr->Command == SMB2_NEGOTIATE)
+ aux_max = 0;
+ else
+ aux_max = conn->max_credits - credit_charge;
+ aux_credits = min_t(unsigned short, aux_credits, aux_max);
+ credits_granted = credit_charge + aux_credits;
- /* if credits granted per client is getting bigger than default
- * minimum credits then we should wrap it up within the limits.
- */
- if ((conn->total_credits + credits_granted) > min_credits)
- credits_granted = min_credits - conn->total_credits;
- /*
- * TODO: Need to adjuct CreditRequest value according to
- * current cpu load
- */
- } else if (conn->total_credits == 0) {
- credits_granted = 1;
- }
+ if (conn->max_credits - conn->total_credits < credits_granted)
+ credits_granted = conn->max_credits -
+ conn->total_credits;
conn->total_credits += credits_granted;
work->credits_granted += credits_granted;
@@ -368,7 +346,6 @@ int smb2_set_rsp_credits(struct ksmbd_work *work)
/* Update CreditRequest in last request */
hdr->CreditRequest = cpu_to_le16(work->credits_granted);
}
-out:
ksmbd_debug(SMB,
"credits: requested[%d] granted[%d] total_granted[%d]\n",
credits_requested, credits_granted,
@@ -472,6 +449,12 @@ bool is_chained_smb2_message(struct ksmbd_work *work)
return false;
}
+ if ((u64)get_rfc1002_len(work->response_buf) + MAX_CIFS_SMALL_BUFFER_SIZE >
+ work->response_sz) {
+ pr_err("next response offset exceeds response buffer size\n");
+ return false;
+ }
+
ksmbd_debug(SMB, "got SMB2 chained command\n");
init_chained_smb2_rsp(work);
return true;
@@ -541,7 +524,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work)
{
struct smb2_hdr *hdr = work->request_buf;
size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE;
- size_t large_sz = work->conn->vals->max_trans_size + MAX_SMB2_HDR_SIZE;
+ size_t large_sz = small_sz + work->conn->vals->max_trans_size;
size_t sz = small_sz;
int cmd = le16_to_cpu(hdr->Command);
@@ -1274,19 +1257,13 @@ static int generate_preauth_hash(struct ksmbd_work *work)
return 0;
}
-static int decode_negotiation_token(struct ksmbd_work *work,
- struct negotiate_message *negblob)
+static int decode_negotiation_token(struct ksmbd_conn *conn,
+ struct negotiate_message *negblob,
+ size_t sz)
{
- struct ksmbd_conn *conn = work->conn;
- struct smb2_sess_setup_req *req;
- int sz;
-
if (!conn->use_spnego)
return -EINVAL;
- req = work->request_buf;
- sz = le16_to_cpu(req->SecurityBufferLength);
-
if (ksmbd_decode_negTokenInit((char *)negblob, sz, conn)) {
if (ksmbd_decode_negTokenTarg((char *)negblob, sz, conn)) {
conn->auth_mechs |= KSMBD_AUTH_NTLMSSP;
@@ -1298,9 +1275,9 @@ static int decode_negotiation_token(struct ksmbd_work *work,
}
static int ntlm_negotiate(struct ksmbd_work *work,
- struct negotiate_message *negblob)
+ struct negotiate_message *negblob,
+ size_t negblob_len)
{
- struct smb2_sess_setup_req *req = work->request_buf;
struct smb2_sess_setup_rsp *rsp = work->response_buf;
struct challenge_message *chgblob;
unsigned char *spnego_blob = NULL;
@@ -1309,8 +1286,7 @@ static int ntlm_negotiate(struct ksmbd_work *work,
int sz, rc;
ksmbd_debug(SMB, "negotiate phase\n");
- sz = le16_to_cpu(req->SecurityBufferLength);
- rc = ksmbd_decode_ntlmssp_neg_blob(negblob, sz, work->sess);
+ rc = ksmbd_decode_ntlmssp_neg_blob(negblob, negblob_len, work->sess);
if (rc)
return rc;
@@ -1378,12 +1354,23 @@ static struct ksmbd_user *session_user(struct ksmbd_conn *conn,
struct authenticate_message *authblob;
struct ksmbd_user *user;
char *name;
- int sz;
+ unsigned int auth_msg_len, name_off, name_len, secbuf_len;
+ secbuf_len = le16_to_cpu(req->SecurityBufferLength);
+ if (secbuf_len < sizeof(struct authenticate_message)) {
+ ksmbd_debug(SMB, "blob len %d too small\n", secbuf_len);
+ return NULL;
+ }
authblob = user_authblob(conn, req);
- sz = le32_to_cpu(authblob->UserName.BufferOffset);
- name = smb_strndup_from_utf16((const char *)authblob + sz,
- le16_to_cpu(authblob->UserName.Length),
+ name_off = le32_to_cpu(authblob->UserName.BufferOffset);
+ name_len = le16_to_cpu(authblob->UserName.Length);
+ auth_msg_len = le16_to_cpu(req->SecurityBufferOffset) + secbuf_len;
+
+ if (auth_msg_len < (u64)name_off + name_len)
+ return NULL;
+
+ name = smb_strndup_from_utf16((const char *)authblob + name_off,
+ name_len,
true,
conn->local_nls);
if (IS_ERR(name)) {
@@ -1629,6 +1616,7 @@ int smb2_sess_setup(struct ksmbd_work *work)
struct smb2_sess_setup_rsp *rsp = work->response_buf;
struct ksmbd_session *sess;
struct negotiate_message *negblob;
+ unsigned int negblob_len, negblob_off;
int rc = 0;
ksmbd_debug(SMB, "Received request for session setup\n");
@@ -1709,10 +1697,16 @@ int smb2_sess_setup(struct ksmbd_work *work)
if (sess->state == SMB2_SESSION_EXPIRED)
sess->state = SMB2_SESSION_IN_PROGRESS;
+ negblob_off = le16_to_cpu(req->SecurityBufferOffset);
+ negblob_len = le16_to_cpu(req->SecurityBufferLength);
+ if (negblob_off < (offsetof(struct smb2_sess_setup_req, Buffer) - 4) ||
+ negblob_len < offsetof(struct negotiate_message, NegotiateFlags))
+ return -EINVAL;
+
negblob = (struct negotiate_message *)((char *)&req->hdr.ProtocolId +
- le16_to_cpu(req->SecurityBufferOffset));
+ negblob_off);
- if (decode_negotiation_token(work, negblob) == 0) {
+ if (decode_negotiation_token(conn, negblob, negblob_len) == 0) {
if (conn->mechToken)
negblob = (struct negotiate_message *)conn->mechToken;
}
@@ -1736,7 +1730,7 @@ int smb2_sess_setup(struct ksmbd_work *work)
sess->Preauth_HashValue = NULL;
} else if (conn->preferred_auth_mech == KSMBD_AUTH_NTLMSSP) {
if (negblob->MessageType == NtLmNegotiate) {
- rc = ntlm_negotiate(work, negblob);
+ rc = ntlm_negotiate(work, negblob, negblob_len);
if (rc)
goto out_err;
rsp->hdr.Status =
@@ -1796,9 +1790,30 @@ out_err:
conn->mechToken = NULL;
}
- if (rc < 0 && sess) {
- ksmbd_session_destroy(sess);
- work->sess = NULL;
+ if (rc < 0) {
+ /*
+ * SecurityBufferOffset should be set to zero
+ * in session setup error response.
+ */
+ rsp->SecurityBufferOffset = 0;
+
+ if (sess) {
+ bool try_delay = false;
+
+ /*
+ * To avoid dictionary attacks (repeated session setups rapidly sent) to
+ * connect to server, ksmbd make a delay of a 5 seconds on session setup
+ * failure to make it harder to send enough random connection requests
+ * to break into a server.
+ */
+ if (sess->user && sess->user->flags & KSMBD_USER_FLAG_DELAY_SESSION)
+ try_delay = true;
+
+ ksmbd_session_destroy(sess);
+ work->sess = NULL;
+ if (try_delay)
+ ssleep(5);
+ }
}
return rc;
@@ -3779,6 +3794,24 @@ static int verify_info_level(int info_level)
return 0;
}
+static int smb2_calc_max_out_buf_len(struct ksmbd_work *work,
+ unsigned short hdr2_len,
+ unsigned int out_buf_len)
+{
+ int free_len;
+
+ if (out_buf_len > work->conn->vals->max_trans_size)
+ return -EINVAL;
+
+ free_len = (int)(work->response_sz -
+ (get_rfc1002_len(work->response_buf) + 4)) -
+ hdr2_len;
+ if (free_len < 0)
+ return -EINVAL;
+
+ return min_t(int, out_buf_len, free_len);
+}
+
int smb2_query_dir(struct ksmbd_work *work)
{
struct ksmbd_conn *conn = work->conn;
@@ -3855,9 +3888,13 @@ int smb2_query_dir(struct ksmbd_work *work)
memset(&d_info, 0, sizeof(struct ksmbd_dir_info));
d_info.wptr = (char *)rsp->Buffer;
d_info.rptr = (char *)rsp->Buffer;
- d_info.out_buf_len = (work->response_sz - (get_rfc1002_len(rsp_org) + 4));
- d_info.out_buf_len = min_t(int, d_info.out_buf_len, le32_to_cpu(req->OutputBufferLength)) -
- sizeof(struct smb2_query_directory_rsp);
+ d_info.out_buf_len =
+ smb2_calc_max_out_buf_len(work, 8,
+ le32_to_cpu(req->OutputBufferLength));
+ if (d_info.out_buf_len < 0) {
+ rc = -EINVAL;
+ goto err_out;
+ }
d_info.flags = srch_flag;
/*
@@ -4091,12 +4128,11 @@ static int smb2_get_ea(struct ksmbd_work *work, struct ksmbd_file *fp,
le32_to_cpu(req->Flags));
}
- buf_free_len = work->response_sz -
- (get_rfc1002_len(rsp_org) + 4) -
- sizeof(struct smb2_query_info_rsp);
-
- if (le32_to_cpu(req->OutputBufferLength) < buf_free_len)
- buf_free_len = le32_to_cpu(req->OutputBufferLength);
+ buf_free_len =
+ smb2_calc_max_out_buf_len(work, 8,
+ le32_to_cpu(req->OutputBufferLength));
+ if (buf_free_len < 0)
+ return -EINVAL;
rc = ksmbd_vfs_listxattr(path->dentry, &xattr_list);
if (rc < 0) {
@@ -4407,6 +4443,8 @@ static void get_file_stream_info(struct ksmbd_work *work,
struct path *path = &fp->filp->f_path;
ssize_t xattr_list_len;
int nbytes = 0, streamlen, stream_name_len, next, idx = 0;
+ int buf_free_len;
+ struct smb2_query_info_req *req = ksmbd_req_buf_next(work);
generic_fillattr(file_mnt_user_ns(fp->filp), file_inode(fp->filp),
&stat);
@@ -4420,6 +4458,12 @@ static void get_file_stream_info(struct ksmbd_work *work,
goto out;
}
+ buf_free_len =
+ smb2_calc_max_out_buf_len(work, 8,
+ le32_to_cpu(req->OutputBufferLength));
+ if (buf_free_len < 0)
+ goto out;
+
while (idx < xattr_list_len) {
stream_name = xattr_list + idx;
streamlen = strlen(stream_name);
@@ -4444,6 +4488,10 @@ static void get_file_stream_info(struct ksmbd_work *work,
streamlen = snprintf(stream_buf, streamlen + 1,
":%s", &stream_name[XATTR_NAME_STREAM_LEN]);
+ next = sizeof(struct smb2_file_stream_info) + streamlen * 2;
+ if (next > buf_free_len)
+ break;
+
file_info = (struct smb2_file_stream_info *)&rsp->Buffer[nbytes];
streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName,
stream_buf, streamlen,
@@ -4454,12 +4502,13 @@ static void get_file_stream_info(struct ksmbd_work *work,
file_info->StreamSize = cpu_to_le64(stream_name_len);
file_info->StreamAllocationSize = cpu_to_le64(stream_name_len);
- next = sizeof(struct smb2_file_stream_info) + streamlen;
nbytes += next;
+ buf_free_len -= next;
file_info->NextEntryOffset = cpu_to_le32(next);
}
- if (!S_ISDIR(stat.mode)) {
+ if (!S_ISDIR(stat.mode) &&
+ buf_free_len >= sizeof(struct smb2_file_stream_info) + 7 * 2) {
file_info = (struct smb2_file_stream_info *)
&rsp->Buffer[nbytes];
streamlen = smbConvertToUTF16((__le16 *)file_info->StreamName,
@@ -6220,8 +6269,7 @@ static noinline int smb2_write_pipe(struct ksmbd_work *work)
(offsetof(struct smb2_write_req, Buffer) - 4)) {
data_buf = (char *)&req->Buffer[0];
} else {
- if ((le16_to_cpu(req->DataOffset) > get_rfc1002_len(req)) ||
- (le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req))) {
+ if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) {
pr_err("invalid write data offset %u, smb_len %u\n",
le16_to_cpu(req->DataOffset),
get_rfc1002_len(req));
@@ -6379,8 +6427,7 @@ int smb2_write(struct ksmbd_work *work)
(offsetof(struct smb2_write_req, Buffer) - 4)) {
data_buf = (char *)&req->Buffer[0];
} else {
- if ((le16_to_cpu(req->DataOffset) > get_rfc1002_len(req)) ||
- (le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req))) {
+ if ((u64)le16_to_cpu(req->DataOffset) + length > get_rfc1002_len(req)) {
pr_err("invalid write data offset %u, smb_len %u\n",
le16_to_cpu(req->DataOffset),
get_rfc1002_len(req));
@@ -7023,24 +7070,26 @@ out2:
return err;
}
-static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req,
+static int fsctl_copychunk(struct ksmbd_work *work,
+ struct copychunk_ioctl_req *ci_req,
+ unsigned int cnt_code,
+ unsigned int input_count,
+ unsigned long long volatile_id,
+ unsigned long long persistent_id,
struct smb2_ioctl_rsp *rsp)
{
- struct copychunk_ioctl_req *ci_req;
struct copychunk_ioctl_rsp *ci_rsp;
struct ksmbd_file *src_fp = NULL, *dst_fp = NULL;
struct srv_copychunk *chunks;
unsigned int i, chunk_count, chunk_count_written = 0;
unsigned int chunk_size_written = 0;
loff_t total_size_written = 0;
- int ret, cnt_code;
+ int ret = 0;
- cnt_code = le32_to_cpu(req->CntCode);
- ci_req = (struct copychunk_ioctl_req *)&req->Buffer[0];
ci_rsp = (struct copychunk_ioctl_rsp *)&rsp->Buffer[0];
- rsp->VolatileFileId = req->VolatileFileId;
- rsp->PersistentFileId = req->PersistentFileId;
+ rsp->VolatileFileId = cpu_to_le64(volatile_id);
+ rsp->PersistentFileId = cpu_to_le64(persistent_id);
ci_rsp->ChunksWritten =
cpu_to_le32(ksmbd_server_side_copy_max_chunk_count());
ci_rsp->ChunkBytesWritten =
@@ -7050,12 +7099,13 @@ static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req,
chunks = (struct srv_copychunk *)&ci_req->Chunks[0];
chunk_count = le32_to_cpu(ci_req->ChunkCount);
+ if (chunk_count == 0)
+ goto out;
total_size_written = 0;
/* verify the SRV_COPYCHUNK_COPY packet */
if (chunk_count > ksmbd_server_side_copy_max_chunk_count() ||
- le32_to_cpu(req->InputCount) <
- offsetof(struct copychunk_ioctl_req, Chunks) +
+ input_count < offsetof(struct copychunk_ioctl_req, Chunks) +
chunk_count * sizeof(struct srv_copychunk)) {
rsp->hdr.Status = STATUS_INVALID_PARAMETER;
return -EINVAL;
@@ -7076,9 +7126,7 @@ static int fsctl_copychunk(struct ksmbd_work *work, struct smb2_ioctl_req *req,
src_fp = ksmbd_lookup_foreign_fd(work,
le64_to_cpu(ci_req->ResumeKey[0]));
- dst_fp = ksmbd_lookup_fd_slow(work,
- le64_to_cpu(req->VolatileFileId),
- le64_to_cpu(req->PersistentFileId));
+ dst_fp = ksmbd_lookup_fd_slow(work, volatile_id, persistent_id);
ret = -EINVAL;
if (!src_fp ||
src_fp->persistent_id != le64_to_cpu(ci_req->ResumeKey[1])) {
@@ -7153,8 +7201,8 @@ static __be32 idev_ipv4_address(struct in_device *idev)
}
static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
- struct smb2_ioctl_req *req,
- struct smb2_ioctl_rsp *rsp)
+ struct smb2_ioctl_rsp *rsp,
+ unsigned int out_buf_len)
{
struct network_interface_info_ioctl_rsp *nii_rsp = NULL;
int nbytes = 0;
@@ -7166,6 +7214,12 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
rtnl_lock();
for_each_netdev(&init_net, netdev) {
+ if (out_buf_len <
+ nbytes + sizeof(struct network_interface_info_ioctl_rsp)) {
+ rtnl_unlock();
+ return -ENOSPC;
+ }
+
if (netdev->type == ARPHRD_LOOPBACK)
continue;
@@ -7245,11 +7299,6 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
if (nii_rsp)
nii_rsp->Next = 0;
- if (!nbytes) {
- rsp->hdr.Status = STATUS_BUFFER_TOO_SMALL;
- return -EINVAL;
- }
-
rsp->PersistentFileId = cpu_to_le64(SMB2_NO_FID);
rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID);
return nbytes;
@@ -7257,11 +7306,16 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
static int fsctl_validate_negotiate_info(struct ksmbd_conn *conn,
struct validate_negotiate_info_req *neg_req,
- struct validate_negotiate_info_rsp *neg_rsp)
+ struct validate_negotiate_info_rsp *neg_rsp,
+ unsigned int in_buf_len)
{
int ret = 0;
int dialect;
+ if (in_buf_len < sizeof(struct validate_negotiate_info_req) +
+ le16_to_cpu(neg_req->DialectCount) * sizeof(__le16))
+ return -EINVAL;
+
dialect = ksmbd_lookup_dialect_by_id(neg_req->Dialects,
neg_req->DialectCount);
if (dialect == BAD_PROT_ID || dialect != conn->dialect) {
@@ -7295,7 +7349,7 @@ err_out:
static int fsctl_query_allocated_ranges(struct ksmbd_work *work, u64 id,
struct file_allocated_range_buffer *qar_req,
struct file_allocated_range_buffer *qar_rsp,
- int in_count, int *out_count)
+ unsigned int in_count, unsigned int *out_count)
{
struct ksmbd_file *fp;
loff_t start, length;
@@ -7322,7 +7376,8 @@ static int fsctl_query_allocated_ranges(struct ksmbd_work *work, u64 id,
}
static int fsctl_pipe_transceive(struct ksmbd_work *work, u64 id,
- int out_buf_len, struct smb2_ioctl_req *req,
+ unsigned int out_buf_len,
+ struct smb2_ioctl_req *req,
struct smb2_ioctl_rsp *rsp)
{
struct ksmbd_rpc_command *rpc_resp;
@@ -7436,8 +7491,7 @@ int smb2_ioctl(struct ksmbd_work *work)
{
struct smb2_ioctl_req *req;
struct smb2_ioctl_rsp *rsp, *rsp_org;
- int cnt_code, nbytes = 0;
- int out_buf_len;
+ unsigned int cnt_code, nbytes = 0, out_buf_len, in_buf_len;
u64 id = KSMBD_NO_FID;
struct ksmbd_conn *conn = work->conn;
int ret = 0;
@@ -7465,8 +7519,14 @@ int smb2_ioctl(struct ksmbd_work *work)
}
cnt_code = le32_to_cpu(req->CntCode);
- out_buf_len = le32_to_cpu(req->MaxOutputResponse);
- out_buf_len = min(KSMBD_IPC_MAX_PAYLOAD, out_buf_len);
+ ret = smb2_calc_max_out_buf_len(work, 48,
+ le32_to_cpu(req->MaxOutputResponse));
+ if (ret < 0) {
+ rsp->hdr.Status = STATUS_INVALID_PARAMETER;
+ goto out;
+ }
+ out_buf_len = (unsigned int)ret;
+ in_buf_len = le32_to_cpu(req->InputCount);
switch (cnt_code) {
case FSCTL_DFS_GET_REFERRALS:
@@ -7494,6 +7554,7 @@ int smb2_ioctl(struct ksmbd_work *work)
break;
}
case FSCTL_PIPE_TRANSCEIVE:
+ out_buf_len = min_t(u32, KSMBD_IPC_MAX_PAYLOAD, out_buf_len);
nbytes = fsctl_pipe_transceive(work, id, out_buf_len, req, rsp);
break;
case FSCTL_VALIDATE_NEGOTIATE_INFO:
@@ -7502,9 +7563,16 @@ int smb2_ioctl(struct ksmbd_work *work)
goto out;
}
+ if (in_buf_len < sizeof(struct validate_negotiate_info_req))
+ return -EINVAL;
+
+ if (out_buf_len < sizeof(struct validate_negotiate_info_rsp))
+ return -EINVAL;
+
ret = fsctl_validate_negotiate_info(conn,
(struct validate_negotiate_info_req *)&req->Buffer[0],
- (struct validate_negotiate_info_rsp *)&rsp->Buffer[0]);
+ (struct validate_negotiate_info_rsp *)&rsp->Buffer[0],
+ in_buf_len);
if (ret < 0)
goto out;
@@ -7513,9 +7581,10 @@ int smb2_ioctl(struct ksmbd_work *work)
rsp->VolatileFileId = cpu_to_le64(SMB2_NO_FID);
break;
case FSCTL_QUERY_NETWORK_INTERFACE_INFO:
- nbytes = fsctl_query_iface_info_ioctl(conn, req, rsp);
- if (nbytes < 0)
+ ret = fsctl_query_iface_info_ioctl(conn, rsp, out_buf_len);
+ if (ret < 0)
goto out;
+ nbytes = ret;
break;
case FSCTL_REQUEST_RESUME_KEY:
if (out_buf_len < sizeof(struct resume_key_ioctl_rsp)) {
@@ -7540,15 +7609,33 @@ int smb2_ioctl(struct ksmbd_work *work)
goto out;
}
+ if (in_buf_len < sizeof(struct copychunk_ioctl_req)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
if (out_buf_len < sizeof(struct copychunk_ioctl_rsp)) {
ret = -EINVAL;
goto out;
}
nbytes = sizeof(struct copychunk_ioctl_rsp);
- fsctl_copychunk(work, req, rsp);
+ rsp->VolatileFileId = req->VolatileFileId;
+ rsp->PersistentFileId = req->PersistentFileId;
+ fsctl_copychunk(work,
+ (struct copychunk_ioctl_req *)&req->Buffer[0],
+ le32_to_cpu(req->CntCode),
+ le32_to_cpu(req->InputCount),
+ le64_to_cpu(req->VolatileFileId),
+ le64_to_cpu(req->PersistentFileId),
+ rsp);
break;
case FSCTL_SET_SPARSE:
+ if (in_buf_len < sizeof(struct file_sparse)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
ret = fsctl_set_sparse(work, id,
(struct file_sparse *)&req->Buffer[0]);
if (ret < 0)
@@ -7567,6 +7654,11 @@ int smb2_ioctl(struct ksmbd_work *work)
goto out;
}
+ if (in_buf_len < sizeof(struct file_zero_data_information)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
zero_data =
(struct file_zero_data_information *)&req->Buffer[0];
@@ -7586,6 +7678,11 @@ int smb2_ioctl(struct ksmbd_work *work)
break;
}
case FSCTL_QUERY_ALLOCATED_RANGES:
+ if (in_buf_len < sizeof(struct file_allocated_range_buffer)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
ret = fsctl_query_allocated_ranges(work, id,
(struct file_allocated_range_buffer *)&req->Buffer[0],
(struct file_allocated_range_buffer *)&rsp->Buffer[0],
@@ -7626,6 +7723,11 @@ int smb2_ioctl(struct ksmbd_work *work)
struct duplicate_extents_to_file *dup_ext;
loff_t src_off, dst_off, length, cloned;
+ if (in_buf_len < sizeof(struct duplicate_extents_to_file)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
dup_ext = (struct duplicate_extents_to_file *)&req->Buffer[0];
fp_in = ksmbd_lookup_fd_slow(work, dup_ext->VolatileFileHandle,
@@ -7696,6 +7798,8 @@ out:
rsp->hdr.Status = STATUS_OBJECT_NAME_NOT_FOUND;
else if (ret == -EOPNOTSUPP)
rsp->hdr.Status = STATUS_NOT_SUPPORTED;
+ else if (ret == -ENOSPC)
+ rsp->hdr.Status = STATUS_BUFFER_TOO_SMALL;
else if (ret < 0 || rsp->hdr.Status == 0)
rsp->hdr.Status = STATUS_INVALID_PARAMETER;
smb2_set_err_rsp(work);
diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h
index a6dec5ec6a54..ff5a2f01d34a 100644
--- a/fs/ksmbd/smb2pdu.h
+++ b/fs/ksmbd/smb2pdu.h
@@ -113,6 +113,8 @@
#define SMB21_DEFAULT_IOSIZE (1024 * 1024)
#define SMB3_DEFAULT_IOSIZE (4 * 1024 * 1024)
#define SMB3_DEFAULT_TRANS_SIZE (1024 * 1024)
+#define SMB3_MIN_IOSIZE (64 * 1024)
+#define SMB3_MAX_IOSIZE (8 * 1024 * 1024)
/*
* SMB2 Header Definition
diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c
index 44aea33a67fa..1acf1892a466 100644
--- a/fs/ksmbd/transport_ipc.c
+++ b/fs/ksmbd/transport_ipc.c
@@ -601,7 +601,7 @@ int ksmbd_ipc_tree_disconnect_request(unsigned long long session_id,
return ret;
}
-int ksmbd_ipc_logout_request(const char *account)
+int ksmbd_ipc_logout_request(const char *account, int flags)
{
struct ksmbd_ipc_msg *msg;
struct ksmbd_logout_request *req;
@@ -616,6 +616,7 @@ int ksmbd_ipc_logout_request(const char *account)
msg->type = KSMBD_EVENT_LOGOUT_REQUEST;
req = (struct ksmbd_logout_request *)msg->payload;
+ req->account_flags = flags;
strscpy(req->account, account, KSMBD_REQ_MAX_ACCOUNT_NAME_SZ);
ret = ipc_msg_send(msg);
diff --git a/fs/ksmbd/transport_ipc.h b/fs/ksmbd/transport_ipc.h
index 9eacc895ffdb..5e5b90a0c187 100644
--- a/fs/ksmbd/transport_ipc.h
+++ b/fs/ksmbd/transport_ipc.h
@@ -25,7 +25,7 @@ ksmbd_ipc_tree_connect_request(struct ksmbd_session *sess,
struct sockaddr *peer_addr);
int ksmbd_ipc_tree_disconnect_request(unsigned long long session_id,
unsigned long long connect_id);
-int ksmbd_ipc_logout_request(const char *account);
+int ksmbd_ipc_logout_request(const char *account, int flags);
struct ksmbd_share_config_response *
ksmbd_ipc_share_config_request(const char *name);
struct ksmbd_spnego_authen_response *
diff --git a/fs/ksmbd/transport_rdma.c b/fs/ksmbd/transport_rdma.c
index 3a7fa23ba850..a2fd5a4d4cd5 100644
--- a/fs/ksmbd/transport_rdma.c
+++ b/fs/ksmbd/transport_rdma.c
@@ -549,6 +549,10 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
switch (recvmsg->type) {
case SMB_DIRECT_MSG_NEGOTIATE_REQ:
+ if (wc->byte_len < sizeof(struct smb_direct_negotiate_req)) {
+ put_empty_recvmsg(t, recvmsg);
+ return;
+ }
t->negotiation_requested = true;
t->full_packet_received = true;
wake_up_interruptible(&t->wait_status);
@@ -556,10 +560,23 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
case SMB_DIRECT_MSG_DATA_TRANSFER: {
struct smb_direct_data_transfer *data_transfer =
(struct smb_direct_data_transfer *)recvmsg->packet;
- int data_length = le32_to_cpu(data_transfer->data_length);
+ unsigned int data_length;
int avail_recvmsg_count, receive_credits;
+ if (wc->byte_len <
+ offsetof(struct smb_direct_data_transfer, padding)) {
+ put_empty_recvmsg(t, recvmsg);
+ return;
+ }
+
+ data_length = le32_to_cpu(data_transfer->data_length);
if (data_length) {
+ if (wc->byte_len < sizeof(struct smb_direct_data_transfer) +
+ (u64)data_length) {
+ put_empty_recvmsg(t, recvmsg);
+ return;
+ }
+
if (t->full_packet_received)
recvmsg->first_segment = true;
@@ -568,7 +585,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
else
t->full_packet_received = true;
- enqueue_reassembly(t, recvmsg, data_length);
+ enqueue_reassembly(t, recvmsg, (int)data_length);
wake_up_interruptible(&t->wait_reassembly_queue);
spin_lock(&t->receive_credit_lock);
diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c
index b41954294d38..835b384b0895 100644
--- a/fs/ksmbd/vfs.c
+++ b/fs/ksmbd/vfs.c
@@ -1023,7 +1023,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp,
int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
struct file_allocated_range_buffer *ranges,
- int in_count, int *out_count)
+ unsigned int in_count, unsigned int *out_count)
{
struct file *f = fp->filp;
struct inode *inode = file_inode(fp->filp);
diff --git a/fs/ksmbd/vfs.h b/fs/ksmbd/vfs.h
index 7b1dcaa3fbdc..b0d5b8feb4a3 100644
--- a/fs/ksmbd/vfs.h
+++ b/fs/ksmbd/vfs.h
@@ -166,7 +166,7 @@ int ksmbd_vfs_zero_data(struct ksmbd_work *work, struct ksmbd_file *fp,
struct file_allocated_range_buffer;
int ksmbd_vfs_fqar_lseek(struct ksmbd_file *fp, loff_t start, loff_t length,
struct file_allocated_range_buffer *ranges,
- int in_count, int *out_count);
+ unsigned int in_count, unsigned int *out_count);
int ksmbd_vfs_unlink(struct user_namespace *user_ns,
struct dentry *dir, struct dentry *dentry);
void *ksmbd_vfs_init_kstat(char **p, struct ksmbd_kstat *ksmbd_kstat);
diff --git a/fs/locks.c b/fs/locks.c
index 3d6fb4ae847b..0fca9d680978 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2,117 +2,11 @@
/*
* linux/fs/locks.c
*
- * Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls.
- * Doug Evans (dje@spiff.uucp), August 07, 1992
+ * We implement four types of file locks: BSD locks, posix locks, open
+ * file description locks, and leases. For details about BSD locks,
+ * see the flock(2) man page; for details about the other three, see
+ * fcntl(2).
*
- * Deadlock detection added.
- * FIXME: one thing isn't handled yet:
- * - mandatory locks (requires lots of changes elsewhere)
- * Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994.
- *
- * Miscellaneous edits, and a total rewrite of posix_lock_file() code.
- * Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994
- *
- * Converted file_lock_table to a linked list from an array, which eliminates
- * the limits on how many active file locks are open.
- * Chad Page (pageone@netcom.com), November 27, 1994
- *
- * Removed dependency on file descriptors. dup()'ed file descriptors now
- * get the same locks as the original file descriptors, and a close() on
- * any file descriptor removes ALL the locks on the file for the current
- * process. Since locks still depend on the process id, locks are inherited
- * after an exec() but not after a fork(). This agrees with POSIX, and both
- * BSD and SVR4 practice.
- * Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995
- *
- * Scrapped free list which is redundant now that we allocate locks
- * dynamically with kmalloc()/kfree().
- * Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995
- *
- * Implemented two lock personalities - FL_FLOCK and FL_POSIX.
- *
- * FL_POSIX locks are created with calls to fcntl() and lockf() through the
- * fcntl() system call. They have the semantics described above.
- *
- * FL_FLOCK locks are created with calls to flock(), through the flock()
- * system call, which is new. Old C libraries implement flock() via fcntl()
- * and will continue to use the old, broken implementation.
- *
- * FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated
- * with a file pointer (filp). As a result they can be shared by a parent
- * process and its children after a fork(). They are removed when the last
- * file descriptor referring to the file pointer is closed (unless explicitly
- * unlocked).
- *
- * FL_FLOCK locks never deadlock, an existing lock is always removed before
- * upgrading from shared to exclusive (or vice versa). When this happens
- * any processes blocked by the current lock are woken up and allowed to
- * run before the new lock is applied.
- * Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995
- *
- * Removed some race conditions in flock_lock_file(), marked other possible
- * races. Just grep for FIXME to see them.
- * Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996.
- *
- * Addressed Dmitry's concerns. Deadlock checking no longer recursive.
- * Lock allocation changed to GFP_ATOMIC as we can't afford to sleep
- * once we've checked for blocking and deadlocking.
- * Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996.
- *
- * Initial implementation of mandatory locks. SunOS turned out to be
- * a rotten model, so I implemented the "obvious" semantics.
- * See 'Documentation/filesystems/mandatory-locking.rst' for details.
- * Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996.
- *
- * Don't allow mandatory locks on mmap()'ed files. Added simple functions to
- * check if a file has mandatory locks, used by mmap(), open() and creat() to
- * see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference
- * Manual, Section 2.
- * Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996.
- *
- * Tidied up block list handling. Added '/proc/locks' interface.
- * Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996.
- *
- * Fixed deadlock condition for pathological code that mixes calls to
- * flock() and fcntl().
- * Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996.
- *
- * Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use
- * for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to
- * guarantee sensible behaviour in the case where file system modules might
- * be compiled with different options than the kernel itself.
- * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
- *
- * Added a couple of missing wake_up() calls. Thanks to Thomas Meckel
- * (Thomas.Meckel@mni.fh-giessen.de) for spotting this.
- * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996.
- *
- * Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK
- * locks. Changed process synchronisation to avoid dereferencing locks that
- * have already been freed.
- * Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996.
- *
- * Made the block list a circular list to minimise searching in the list.
- * Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996.
- *
- * Made mandatory locking a mount option. Default is not to allow mandatory
- * locking.
- * Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996.
- *
- * Some adaptations for NFS support.
- * Olaf Kirch (okir@monad.swb.de), Dec 1996,
- *
- * Fixed /proc/locks interface so that we can't overrun the buffer we are handed.
- * Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997.
- *
- * Use slab allocator instead of kmalloc/kfree.
- * Use generic list implementation from <linux/list.h>.
- * Sped up posix_locks_deadlock by only considering blocked locks.
- * Matthew Wilcox <willy@debian.org>, March, 2000.
- *
- * Leases and LOCK_MAND
- * Matthew Wilcox <willy@debian.org>, June, 2000.
- * Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000.
*
* Locking conflicts and dependencies:
* If multiple threads attempt to lock the same byte (or flock the same file)
@@ -461,8 +355,6 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl)
}
static inline int flock_translate_cmd(int cmd) {
- if (cmd & LOCK_MAND)
- return cmd & (LOCK_MAND | LOCK_RW);
switch (cmd) {
case LOCK_SH:
return F_RDLCK;
@@ -942,8 +834,6 @@ static bool flock_locks_conflict(struct file_lock *caller_fl,
*/
if (caller_fl->fl_file == sys_fl->fl_file)
return false;
- if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND))
- return false;
return locks_conflict(caller_fl, sys_fl);
}
@@ -2116,11 +2006,9 @@ EXPORT_SYMBOL(locks_lock_inode_wait);
* - %LOCK_SH -- a shared lock.
* - %LOCK_EX -- an exclusive lock.
* - %LOCK_UN -- remove an existing lock.
- * - %LOCK_MAND -- a 'mandatory' flock.
- * This exists to emulate Windows Share Modes.
+ * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED)
*
- * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other
- * processes read and write access respectively.
+ * %LOCK_MAND support has been removed from the kernel.
*/
SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
{
@@ -2137,9 +2025,22 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd)
cmd &= ~LOCK_NB;
unlock = (cmd == LOCK_UN);
- if (!unlock && !(cmd & LOCK_MAND) &&
- !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
+ if (!unlock && !(f.file->f_mode & (FMODE_READ|FMODE_WRITE)))
+ goto out_putf;
+
+ /*
+ * LOCK_MAND locks were broken for a long time in that they never
+ * conflicted with one another and didn't prevent any sort of open,
+ * read or write activity.
+ *
+ * Just ignore these requests now, to preserve legacy behavior, but
+ * throw a warning to let people know that they don't actually work.
+ */
+ if (cmd & LOCK_MAND) {
+ pr_warn_once("Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n");
+ error = 0;
goto out_putf;
+ }
lock = flock_make_lock(f.file, cmd, NULL);
if (IS_ERR(lock)) {
@@ -2718,6 +2619,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
struct inode *inode = NULL;
unsigned int fl_pid;
struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb);
+ int type;
fl_pid = locks_translate_pid(fl, proc_pidns);
/*
@@ -2745,11 +2647,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
seq_printf(f, " %s ",
(inode == NULL) ? "*NOINODE*" : "ADVISORY ");
} else if (IS_FLOCK(fl)) {
- if (fl->fl_type & LOCK_MAND) {
- seq_puts(f, "FLOCK MSNFS ");
- } else {
- seq_puts(f, "FLOCK ADVISORY ");
- }
+ seq_puts(f, "FLOCK ADVISORY ");
} else if (IS_LEASE(fl)) {
if (fl->fl_flags & FL_DELEG)
seq_puts(f, "DELEG ");
@@ -2765,17 +2663,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
} else {
seq_puts(f, "UNKNOWN UNKNOWN ");
}
- if (fl->fl_type & LOCK_MAND) {
- seq_printf(f, "%s ",
- (fl->fl_type & LOCK_READ)
- ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ "
- : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE ");
- } else {
- int type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
+ type = IS_LEASE(fl) ? target_leasetype(fl) : fl->fl_type;
- seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
- (type == F_RDLCK) ? "READ" : "UNLCK");
- }
+ seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" :
+ (type == F_RDLCK) ? "READ" : "UNLCK");
if (inode) {
/* userspace relies on this representation of dev_t */
seq_printf(f, "%d %02x:%02x:%lu ", fl_pid,
diff --git a/fs/namei.c b/fs/namei.c
index 1946d9667790..1f9d2187c765 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3076,9 +3076,7 @@ static int handle_truncate(struct user_namespace *mnt_userns, struct file *filp)
int error = get_write_access(inode);
if (error)
return error;
- /*
- * Refuse to truncate files with mandatory locks held on them.
- */
+
error = security_path_truncate(path);
if (!error) {
error = do_truncate(mnt_userns, path->dentry, 0,
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index aa353fd58240..24e7dccce355 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -843,15 +843,6 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
if (!(fl->fl_flags & FL_FLOCK))
return -ENOLCK;
- /*
- * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of
- * any standard. In principle we might be able to support LOCK_MAND
- * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the
- * NFS code is not set up for it.
- */
- if (fl->fl_type & LOCK_MAND)
- return -EINVAL;
-
if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
is_local = 1;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index f1cc8258d34a..5d9ae17bd443 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -7045,7 +7045,7 @@ void ocfs2_set_inode_data_inline(struct inode *inode, struct ocfs2_dinode *di)
int ocfs2_convert_inline_data_to_extents(struct inode *inode,
struct buffer_head *di_bh)
{
- int ret, i, has_data, num_pages = 0;
+ int ret, has_data, num_pages = 0;
int need_free = 0;
u32 bit_off, num;
handle_t *handle;
@@ -7054,26 +7054,17 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
struct ocfs2_alloc_context *data_ac = NULL;
- struct page **pages = NULL;
- loff_t end = osb->s_clustersize;
+ struct page *page = NULL;
struct ocfs2_extent_tree et;
int did_quota = 0;
has_data = i_size_read(inode) ? 1 : 0;
if (has_data) {
- pages = kcalloc(ocfs2_pages_per_cluster(osb->sb),
- sizeof(struct page *), GFP_NOFS);
- if (pages == NULL) {
- ret = -ENOMEM;
- mlog_errno(ret);
- return ret;
- }
-
ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
if (ret) {
mlog_errno(ret);
- goto free_pages;
+ goto out;
}
}
@@ -7093,7 +7084,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
}
if (has_data) {
- unsigned int page_end;
+ unsigned int page_end = min_t(unsigned, PAGE_SIZE,
+ osb->s_clustersize);
u64 phys;
ret = dquot_alloc_space_nodirty(inode,
@@ -7117,15 +7109,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
*/
block = phys = ocfs2_clusters_to_blocks(inode->i_sb, bit_off);
- /*
- * Non sparse file systems zero on extend, so no need
- * to do that now.
- */
- if (!ocfs2_sparse_alloc(osb) &&
- PAGE_SIZE < osb->s_clustersize)
- end = PAGE_SIZE;
-
- ret = ocfs2_grab_eof_pages(inode, 0, end, pages, &num_pages);
+ ret = ocfs2_grab_eof_pages(inode, 0, page_end, &page,
+ &num_pages);
if (ret) {
mlog_errno(ret);
need_free = 1;
@@ -7136,20 +7121,15 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
* This should populate the 1st page for us and mark
* it up to date.
*/
- ret = ocfs2_read_inline_data(inode, pages[0], di_bh);
+ ret = ocfs2_read_inline_data(inode, page, di_bh);
if (ret) {
mlog_errno(ret);
need_free = 1;
goto out_unlock;
}
- page_end = PAGE_SIZE;
- if (PAGE_SIZE > osb->s_clustersize)
- page_end = osb->s_clustersize;
-
- for (i = 0; i < num_pages; i++)
- ocfs2_map_and_dirty_page(inode, handle, 0, page_end,
- pages[i], i > 0, &phys);
+ ocfs2_map_and_dirty_page(inode, handle, 0, page_end, page, 0,
+ &phys);
}
spin_lock(&oi->ip_lock);
@@ -7180,8 +7160,8 @@ int ocfs2_convert_inline_data_to_extents(struct inode *inode,
}
out_unlock:
- if (pages)
- ocfs2_unlock_and_free_pages(pages, num_pages);
+ if (page)
+ ocfs2_unlock_and_free_pages(&page, num_pages);
out_commit:
if (ret < 0 && did_quota)
@@ -7205,8 +7185,6 @@ out_commit:
out:
if (data_ac)
ocfs2_free_alloc_context(data_ac);
-free_pages:
- kfree(pages);
return ret;
}
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 8521942f5af2..481017e1dac5 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1251,7 +1251,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
{
struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
struct journal_head *jh;
- int ret;
+ int ret = 1;
if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
return 0;
@@ -1259,14 +1259,18 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
if (!buffer_jbd(bg_bh))
return 1;
- jh = bh2jh(bg_bh);
- spin_lock(&jh->b_state_lock);
- bg = (struct ocfs2_group_desc *) jh->b_committed_data;
- if (bg)
- ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
- else
- ret = 1;
- spin_unlock(&jh->b_state_lock);
+ jbd_lock_bh_journal_head(bg_bh);
+ if (buffer_jbd(bg_bh)) {
+ jh = bh2jh(bg_bh);
+ spin_lock(&jh->b_state_lock);
+ bg = (struct ocfs2_group_desc *) jh->b_committed_data;
+ if (bg)
+ ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
+ else
+ ret = 1;
+ spin_unlock(&jh->b_state_lock);
+ }
+ jbd_unlock_bh_journal_head(bg_bh);
return ret;
}
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index c86bd4e60e20..5c914ce9b3ac 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2167,11 +2167,17 @@ static int ocfs2_initialize_super(struct super_block *sb,
}
if (ocfs2_clusterinfo_valid(osb)) {
+ /*
+ * ci_stack and ci_cluster in ocfs2_cluster_info may not be null
+ * terminated, so make sure no overflow happens here by using
+ * memcpy. Destination strings will always be null terminated
+ * because osb is allocated using kzalloc.
+ */
osb->osb_stackflags =
OCFS2_RAW_SB(di)->s_cluster_info.ci_stackflags;
- strlcpy(osb->osb_cluster_stack,
+ memcpy(osb->osb_cluster_stack,
OCFS2_RAW_SB(di)->s_cluster_info.ci_stack,
- OCFS2_STACK_LABEL_LEN + 1);
+ OCFS2_STACK_LABEL_LEN);
if (strlen(osb->osb_cluster_stack) != OCFS2_STACK_LABEL_LEN) {
mlog(ML_ERROR,
"couldn't mount because of an invalid "
@@ -2180,9 +2186,9 @@ static int ocfs2_initialize_super(struct super_block *sb,
status = -EINVAL;
goto bail;
}
- strlcpy(osb->osb_cluster_name,
+ memcpy(osb->osb_cluster_name,
OCFS2_RAW_SB(di)->s_cluster_info.ci_cluster,
- OCFS2_CLUSTER_NAME_LEN + 1);
+ OCFS2_CLUSTER_NAME_LEN);
} else {
/* The empty string is identical with classic tools that
* don't know about s_cluster_info. */
diff --git a/fs/read_write.c b/fs/read_write.c
index af057c57bdc6..0074afa7ecb3 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -368,10 +368,6 @@ int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t
if (unlikely((ssize_t) count < 0))
return -EINVAL;
- /*
- * ranged mandatory locking does not apply to streams - it makes sense
- * only for files where position has a meaning.
- */
if (ppos) {
loff_t pos = *ppos;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 003f0d31743e..22bf14ab2d16 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1827,9 +1827,15 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
if (mode_wp && mode_dontwake)
return -EINVAL;
- ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
- uffdio_wp.range.len, mode_wp,
- &ctx->mmap_changing);
+ if (mmget_not_zero(ctx->mm)) {
+ ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
+ uffdio_wp.range.len, mode_wp,
+ &ctx->mmap_changing);
+ mmput(ctx->mm);
+ } else {
+ return -ESRCH;
+ }
+
if (ret)
return ret;
diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
index fb172a03a753..20ecb004f5a4 100644
--- a/include/acpi/platform/acgcc.h
+++ b/include/acpi/platform/acgcc.h
@@ -22,9 +22,14 @@ typedef __builtin_va_list va_list;
#define va_arg(v, l) __builtin_va_arg(v, l)
#define va_copy(d, s) __builtin_va_copy(d, s)
#else
+#ifdef __KERNEL__
#include <linux/stdarg.h>
-#endif
-#endif
+#else
+/* Used to build acpi tools */
+#include <stdarg.h>
+#endif /* __KERNEL__ */
+#endif /* ACPI_USE_BUILTIN_STDARG */
+#endif /* ! va_arg */
#define ACPI_INLINE __inline__
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index 4a674db4e1fa..fedc0dfa4877 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -49,9 +49,15 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
static inline void flush_dcache_page(struct page *page)
{
}
+
+static inline void flush_dcache_folio(struct folio *folio) { }
#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
#endif
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio);
+#endif
#ifndef flush_dcache_mmap_lock
static inline void flush_dcache_mmap_lock(struct address_space *mapping)
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 4ac7ce096013..9c14f0a8dbe5 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -64,7 +64,7 @@ static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi)
return atomic_long_read(&bdi->tot_write_bandwidth);
}
-static inline void __add_wb_stat(struct bdi_writeback *wb,
+static inline void wb_stat_mod(struct bdi_writeback *wb,
enum wb_stat_item item, s64 amount)
{
percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
@@ -72,12 +72,12 @@ static inline void __add_wb_stat(struct bdi_writeback *wb,
static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
- __add_wb_stat(wb, item, 1);
+ wb_stat_mod(wb, item, 1);
}
static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
{
- __add_wb_stat(wb, item, -1);
+ wb_stat_mod(wb, item, -1);
}
static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 9538f20ffaa5..fe6bdfbbef66 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -417,7 +417,8 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page,
void __bio_add_page(struct bio *bio, struct page *page,
unsigned int len, unsigned int off);
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-void bio_release_pages(struct bio *bio, bool mark_dirty);
+void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
+void __bio_release_pages(struct bio *bio, bool mark_dirty);
extern void bio_set_pages_dirty(struct bio *bio);
extern void bio_check_pages_dirty(struct bio *bio);
@@ -428,23 +429,13 @@ extern void bio_free_pages(struct bio *bio);
void guard_bio_eod(struct bio *bio);
void zero_fill_bio(struct bio *bio);
-extern const char *bio_devname(struct bio *bio, char *buffer);
+static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
+{
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ __bio_release_pages(bio, mark_dirty);
+}
-#define bio_set_dev(bio, bdev) \
-do { \
- bio_clear_flag(bio, BIO_REMAPPED); \
- if ((bio)->bi_bdev != (bdev)) \
- bio_clear_flag(bio, BIO_THROTTLED); \
- (bio)->bi_bdev = (bdev); \
- bio_associate_blkg(bio); \
-} while (0)
-
-#define bio_copy_dev(dst, src) \
-do { \
- bio_clear_flag(dst, BIO_REMAPPED); \
- (dst)->bi_bdev = (src)->bi_bdev; \
- bio_clone_blkg_association(dst, src); \
-} while (0)
+extern const char *bio_devname(struct bio *bio, char *buffer);
#define bio_dev(bio) \
disk_devt((bio)->bi_bdev->bd_disk)
@@ -463,6 +454,22 @@ static inline void bio_clone_blkg_association(struct bio *dst,
struct bio *src) { }
#endif /* CONFIG_BLK_CGROUP */
+static inline void bio_set_dev(struct bio *bio, struct block_device *bdev)
+{
+ bio_clear_flag(bio, BIO_REMAPPED);
+ if (bio->bi_bdev != bdev)
+ bio_clear_flag(bio, BIO_THROTTLED);
+ bio->bi_bdev = bdev;
+ bio_associate_blkg(bio);
+}
+
+static inline void bio_copy_dev(struct bio *dst, struct bio *src)
+{
+ bio_clear_flag(dst, BIO_REMAPPED);
+ dst->bi_bdev = src->bi_bdev;
+ bio_clone_blkg_association(dst, src);
+}
+
/*
* BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
*
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
new file mode 100644
index 000000000000..bbab65bd5428
--- /dev/null
+++ b/include/linux/blk-crypto-profile.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2019 Google LLC
+ */
+
+#ifndef __LINUX_BLK_CRYPTO_PROFILE_H
+#define __LINUX_BLK_CRYPTO_PROFILE_H
+
+#include <linux/bio.h>
+#include <linux/blk-crypto.h>
+
+struct blk_crypto_profile;
+
+/**
+ * struct blk_crypto_ll_ops - functions to control inline encryption hardware
+ *
+ * Low-level operations for controlling inline encryption hardware. This
+ * interface must be implemented by storage drivers that support inline
+ * encryption. All functions may sleep, are serialized by profile->lock, and
+ * are never called while profile->dev (if set) is runtime-suspended.
+ */
+struct blk_crypto_ll_ops {
+
+ /**
+ * @keyslot_program: Program a key into the inline encryption hardware.
+ *
+ * Program @key into the specified @slot in the inline encryption
+ * hardware, overwriting any key that the keyslot may already contain.
+ * The keyslot is guaranteed to not be in-use by any I/O.
+ *
+ * This is required if the device has keyslots. Otherwise (i.e. if the
+ * device is a layered device, or if the device is real hardware that
+ * simply doesn't have the concept of keyslots) it is never called.
+ *
+ * Must return 0 on success, or -errno on failure.
+ */
+ int (*keyslot_program)(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot);
+
+ /**
+ * @keyslot_evict: Evict a key from the inline encryption hardware.
+ *
+ * If the device has keyslots, this function must evict the key from the
+ * specified @slot. The slot will contain @key, but there should be no
+ * need for the @key argument to be used as @slot should be sufficient.
+ * The keyslot is guaranteed to not be in-use by any I/O.
+ *
+ * If the device doesn't have keyslots itself, this function must evict
+ * @key from any underlying devices. @slot won't be valid in this case.
+ *
+ * If there are no keyslots and no underlying devices, this function
+ * isn't required.
+ *
+ * Must return 0 on success, or -errno on failure.
+ */
+ int (*keyslot_evict)(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ unsigned int slot);
+};
+
+/**
+ * struct blk_crypto_profile - inline encryption profile for a device
+ *
+ * This struct contains a storage device's inline encryption capabilities (e.g.
+ * the supported crypto algorithms), driver-provided functions to control the
+ * inline encryption hardware (e.g. programming and evicting keys), and optional
+ * device-independent keyslot management data.
+ */
+struct blk_crypto_profile {
+
+ /* public: Drivers must initialize the following fields. */
+
+ /**
+ * @ll_ops: Driver-provided functions to control the inline encryption
+ * hardware, e.g. program and evict keys.
+ */
+ struct blk_crypto_ll_ops ll_ops;
+
+ /**
+ * @max_dun_bytes_supported: The maximum number of bytes supported for
+ * specifying the data unit number (DUN). Specifically, the range of
+ * supported DUNs is 0 through (1 << (8 * max_dun_bytes_supported)) - 1.
+ */
+ unsigned int max_dun_bytes_supported;
+
+ /**
+ * @modes_supported: Array of bitmasks that specifies whether each
+ * combination of crypto mode and data unit size is supported.
+ * Specifically, the i'th bit of modes_supported[crypto_mode] is set if
+ * crypto_mode can be used with a data unit size of (1 << i). Note that
+ * only data unit sizes that are powers of 2 can be supported.
+ */
+ unsigned int modes_supported[BLK_ENCRYPTION_MODE_MAX];
+
+ /**
+ * @dev: An optional device for runtime power management. If the driver
+ * provides this device, it will be runtime-resumed before any function
+ * in @ll_ops is called and will remain resumed during the call.
+ */
+ struct device *dev;
+
+ /* private: The following fields shouldn't be accessed by drivers. */
+
+ /* Number of keyslots, or 0 if not applicable */
+ unsigned int num_slots;
+
+ /*
+ * Serializes all calls to functions in @ll_ops as well as all changes
+ * to @slot_hashtable. This can also be taken in read mode to look up
+ * keyslots while ensuring that they can't be changed concurrently.
+ */
+ struct rw_semaphore lock;
+
+ /* List of idle slots, with least recently used slot at front */
+ wait_queue_head_t idle_slots_wait_queue;
+ struct list_head idle_slots;
+ spinlock_t idle_slots_lock;
+
+ /*
+ * Hash table which maps struct *blk_crypto_key to keyslots, so that we
+ * can find a key's keyslot in O(1) time rather than O(num_slots).
+ * Protected by 'lock'.
+ */
+ struct hlist_head *slot_hashtable;
+ unsigned int log_slot_ht_size;
+
+ /* Per-keyslot data */
+ struct blk_crypto_keyslot *slots;
+};
+
+int blk_crypto_profile_init(struct blk_crypto_profile *profile,
+ unsigned int num_slots);
+
+int devm_blk_crypto_profile_init(struct device *dev,
+ struct blk_crypto_profile *profile,
+ unsigned int num_slots);
+
+unsigned int blk_crypto_keyslot_index(struct blk_crypto_keyslot *slot);
+
+blk_status_t blk_crypto_get_keyslot(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key,
+ struct blk_crypto_keyslot **slot_ptr);
+
+void blk_crypto_put_keyslot(struct blk_crypto_keyslot *slot);
+
+bool __blk_crypto_cfg_supported(struct blk_crypto_profile *profile,
+ const struct blk_crypto_config *cfg);
+
+int __blk_crypto_evict_key(struct blk_crypto_profile *profile,
+ const struct blk_crypto_key *key);
+
+void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile);
+
+void blk_crypto_profile_destroy(struct blk_crypto_profile *profile);
+
+void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
+ const struct blk_crypto_profile *child);
+
+bool blk_crypto_has_capabilities(const struct blk_crypto_profile *target,
+ const struct blk_crypto_profile *reference);
+
+void blk_crypto_update_capabilities(struct blk_crypto_profile *dst,
+ const struct blk_crypto_profile *src);
+
+#endif /* __LINUX_BLK_CRYPTO_PROFILE_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 656fe34bdb6c..b4039fdf1b04 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -7,6 +7,7 @@
#include <linux/srcu.h>
#include <linux/lockdep.h>
#include <linux/scatterlist.h>
+#include <linux/prefetch.h>
struct blk_mq_tags;
struct blk_flush_queue;
@@ -132,7 +133,7 @@ struct request {
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
struct bio_crypt_ctx *crypt_ctx;
- struct blk_ksm_keyslot *crypt_keyslot;
+ struct blk_crypto_keyslot *crypt_keyslot;
#endif
unsigned short write_hint;
@@ -655,8 +656,6 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
unsigned int set_flags);
void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
-void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule);
-
void blk_mq_free_request(struct request *rq);
bool blk_mq_queue_inflight(struct request_queue *q);
@@ -675,7 +674,40 @@ struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags,
unsigned int hctx_idx);
-struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag);
+
+/*
+ * Tag address space map.
+ */
+struct blk_mq_tags {
+ unsigned int nr_tags;
+ unsigned int nr_reserved_tags;
+
+ atomic_t active_queues;
+
+ struct sbitmap_queue bitmap_tags;
+ struct sbitmap_queue breserved_tags;
+
+ struct request **rqs;
+ struct request **static_rqs;
+ struct list_head page_list;
+
+ /*
+ * used to clear request reference in rqs[] before freeing one
+ * request pool
+ */
+ spinlock_t lock;
+};
+
+static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags,
+ unsigned int tag)
+{
+ if (tag < tags->nr_tags) {
+ prefetch(tags->rqs[tag]);
+ return tags->rqs[tag];
+ }
+
+ return NULL;
+}
enum {
BLK_MQ_UNIQUE_TAG_BITS = 16,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index abe721591e80..ed5be661dd0c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -30,7 +30,7 @@ struct pr_ops;
struct rq_qos;
struct blk_queue_stats;
struct blk_stat_callback;
-struct blk_keyslot_manager;
+struct blk_crypto_profile;
/* Must be consistent with blk_mq_poll_stats_bkt() */
#define BLK_MQ_POLL_STATS_BKTS 16
@@ -44,6 +44,14 @@ struct blk_keyslot_manager;
*/
#define BLKCG_MAX_POLS 6
+static inline int blk_validate_block_size(unsigned int bsize)
+{
+ if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+ return -EINVAL;
+
+ return 0;
+}
+
static inline bool blk_op_is_passthrough(unsigned int op)
{
op &= REQ_OP_MASK;
@@ -150,6 +158,34 @@ static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
#endif /* CONFIG_BLK_DEV_ZONED */
+/*
+ * Independent access ranges: struct blk_independent_access_range describes
+ * a range of contiguous sectors that can be accessed using device command
+ * execution resources that are independent from the resources used for
+ * other access ranges. This is typically found with single-LUN multi-actuator
+ * HDDs where each access range is served by a different set of heads.
+ * The set of independent ranges supported by the device is defined using
+ * struct blk_independent_access_ranges. The independent ranges must not overlap
+ * and must include all sectors within the disk capacity (no sector holes
+ * allowed).
+ * For a device with multiple ranges, requests targeting sectors in different
+ * ranges can be executed in parallel. A request can straddle an access range
+ * boundary.
+ */
+struct blk_independent_access_range {
+ struct kobject kobj;
+ struct request_queue *queue;
+ sector_t sector;
+ sector_t nr_sectors;
+};
+
+struct blk_independent_access_ranges {
+ struct kobject kobj;
+ bool sysfs_registered;
+ unsigned int nr_ia_ranges;
+ struct blk_independent_access_range ia_range[];
+};
+
struct request_queue {
struct request *last_merge;
struct elevator_queue *elevator;
@@ -224,8 +260,7 @@ struct request_queue {
unsigned int dma_alignment;
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
- /* Inline crypto capabilities */
- struct blk_keyslot_manager *ksm;
+ struct blk_crypto_profile *crypto_profile;
#endif
unsigned int rq_timeout;
@@ -315,6 +350,8 @@ struct request_queue {
*/
struct mutex mq_freeze_lock;
+ int quiesce_depth;
+
struct blk_mq_tag_set *tag_set;
struct list_head tag_set_list;
struct bio_set bio_split;
@@ -330,6 +367,12 @@ struct request_queue {
#define BLK_MAX_WRITE_HINTS 5
u64 write_hints[BLK_MAX_WRITE_HINTS];
+
+ /*
+ * Independent sector access ranges. This is always NULL for
+ * devices that do not have multiple independent access ranges.
+ */
+ struct blk_independent_access_ranges *ia_ranges;
};
/* Keep blk_queue_flag_name[] in sync with the definitions below */
@@ -680,6 +723,11 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int);
extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
+struct blk_independent_access_ranges *
+disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
+void disk_set_independent_access_ranges(struct gendisk *disk,
+ struct blk_independent_access_ranges *iars);
+
/*
* Elevator features for blk_queue_required_elevator_features:
*/
@@ -706,12 +754,11 @@ extern void blk_set_queue_dying(struct request_queue *);
* as the lock contention for request_queue lock is reduced.
*
* It is ok not to disable preemption when adding the request to the plug list
- * or when attempting a merge, because blk_schedule_flush_list() will only flush
- * the plug list when the task sleeps by itself. For details, please see
- * schedule() where blk_schedule_flush_plug() is called.
+ * or when attempting a merge. For details, please see schedule() where
+ * blk_flush_plug() is called.
*/
struct blk_plug {
- struct list_head mq_list; /* blk-mq requests */
+ struct request *mq_list; /* blk-mq requests */
/* if ios_left is > 1, we can batch tag/rq allocations */
struct request *cached_rq;
@@ -720,6 +767,7 @@ struct blk_plug {
unsigned short rq_count;
bool multiple_queues;
+ bool has_elevator;
bool nowait;
struct list_head cb_list; /* md requires an unplug callback */
@@ -737,31 +785,15 @@ extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug,
extern void blk_start_plug(struct blk_plug *);
extern void blk_start_plug_nr_ios(struct blk_plug *, unsigned short);
extern void blk_finish_plug(struct blk_plug *);
-extern void blk_flush_plug_list(struct blk_plug *, bool);
-
-static inline void blk_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
-
- if (plug)
- blk_flush_plug_list(plug, false);
-}
-
-static inline void blk_schedule_flush_plug(struct task_struct *tsk)
-{
- struct blk_plug *plug = tsk->plug;
- if (plug)
- blk_flush_plug_list(plug, true);
-}
+void blk_flush_plug(struct blk_plug *plug, bool from_schedule);
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
struct blk_plug *plug = tsk->plug;
return plug &&
- (!list_empty(&plug->mq_list) ||
- !list_empty(&plug->cb_list));
+ (plug->mq_list || !list_empty(&plug->cb_list));
}
int blkdev_issue_flush(struct block_device *bdev);
@@ -783,15 +815,10 @@ static inline void blk_finish_plug(struct blk_plug *plug)
{
}
-static inline void blk_flush_plug(struct task_struct *task)
+static inline void blk_flush_plug(struct blk_plug *plug, bool async)
{
}
-static inline void blk_schedule_flush_plug(struct task_struct *task)
-{
-}
-
-
static inline bool blk_needs_flush_plug(struct task_struct *tsk)
{
return false;
@@ -1144,19 +1171,20 @@ int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned lo
#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q);
+bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q);
-void blk_ksm_unregister(struct request_queue *q);
+void blk_crypto_unregister(struct request_queue *q);
#else /* CONFIG_BLK_INLINE_ENCRYPTION */
-static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm,
- struct request_queue *q)
+static inline bool blk_crypto_register(struct blk_crypto_profile *profile,
+ struct request_queue *q)
{
return true;
}
-static inline void blk_ksm_unregister(struct request_queue *q) { }
+static inline void blk_crypto_unregister(struct request_queue *q) { }
#endif /* CONFIG_BLK_INLINE_ENCRYPTION */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 020a7d5bf470..3db6f6c95489 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -929,8 +929,11 @@ struct bpf_array_aux {
* stored in the map to make sure that all callers and callees have
* the same prog type and JITed flag.
*/
- enum bpf_prog_type type;
- bool jited;
+ struct {
+ spinlock_t lock;
+ enum bpf_prog_type type;
+ bool jited;
+ } owner;
/* Programs with direct jumps into programs part of this array. */
struct list_head poke_progs;
struct bpf_map *map;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9c81724e4b98..bbe1eefa4c8a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -101,14 +101,14 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK_TRACE, stack_trace_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY_OF_MAPS, array_of_maps_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_HASH_OF_MAPS, htab_of_maps_map_ops)
-#ifdef CONFIG_NET
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
-BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
#ifdef CONFIG_BPF_LSM
BPF_MAP_TYPE(BPF_MAP_TYPE_INODE_STORAGE, inode_storage_map_ops)
#endif
BPF_MAP_TYPE(BPF_MAP_TYPE_TASK_STORAGE, task_storage_map_ops)
+#ifdef CONFIG_NET
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP_HASH, dev_map_hash_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_SK_STORAGE, sk_storage_map_ops)
BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
#if defined(CONFIG_XDP_SOCKETS)
BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 832d8a74fa59..991911048857 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -72,6 +72,8 @@ enum cpuhp_state {
CPUHP_SLUB_DEAD,
CPUHP_DEBUG_OBJ_DEAD,
CPUHP_MM_WRITEBACK_DEAD,
+ /* Must be after CPUHP_MM_VMSTAT_DEAD */
+ CPUHP_MM_DEMOTION_DEAD,
CPUHP_MM_VMSTAT_DEAD,
CPUHP_SOFTIRQ_DEAD,
CPUHP_NET_MVNETA_DEAD,
@@ -240,6 +242,8 @@ enum cpuhp_state {
CPUHP_AP_BASE_CACHEINFO_ONLINE,
CPUHP_AP_ONLINE_DYN,
CPUHP_AP_ONLINE_DYN_END = CPUHP_AP_ONLINE_DYN + 30,
+ /* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
+ CPUHP_AP_MM_DEMOTION_ONLINE,
CPUHP_AP_X86_HPET_ONLINE,
CPUHP_AP_X86_KVM_CLK_ONLINE,
CPUHP_AP_DTPM_CPU_ONLINE,
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 114553b487ef..a7df155ea49b 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -576,9 +576,9 @@ struct dm_table *dm_swap_table(struct mapped_device *md,
struct dm_table *t);
/*
- * Table keyslot manager functions
+ * Table blk_crypto_profile functions
*/
-void dm_destroy_keyslot_manager(struct blk_keyslot_manager *ksm);
+void dm_destroy_crypto_profile(struct blk_crypto_profile *profile);
/*-----------------------------------------------------------------
* Macros.
diff --git a/include/linux/elfcore.h b/include/linux/elfcore.h
index 2aaa15779d50..957ebec35aad 100644
--- a/include/linux/elfcore.h
+++ b/include/linux/elfcore.h
@@ -109,7 +109,7 @@ static inline int elf_core_copy_task_fpregs(struct task_struct *t, struct pt_reg
#endif
}
-#if defined(CONFIG_UM) || defined(CONFIG_IA64)
+#if (defined(CONFIG_UML) && defined(CONFIG_X86_32)) || defined(CONFIG_IA64)
/*
* These functions parameterize elf_core_dump in fs/binfmt_elf.c to write out
* extra segments containing the gate DSO contents. Dumping its
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4a93c12543ee..ef03ff34234d 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1051,6 +1051,7 @@ extern int bpf_jit_enable;
extern int bpf_jit_harden;
extern int bpf_jit_kallsyms;
extern long bpf_jit_limit;
+extern long bpf_jit_limit_max;
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index c12df59d3f5f..3e378b1fb0bc 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -83,9 +83,10 @@ struct fprop_local_percpu {
int fprop_local_init_percpu(struct fprop_local_percpu *pl, gfp_t gfp);
void fprop_local_destroy_percpu(struct fprop_local_percpu *pl);
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl);
-void __fprop_inc_percpu_max(struct fprop_global *p, struct fprop_local_percpu *pl,
- int max_frac);
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+ long nr);
+void __fprop_add_percpu_max(struct fprop_global *p,
+ struct fprop_local_percpu *pl, int max_frac, long nr);
void fprop_fraction_percpu(struct fprop_global *p,
struct fprop_local_percpu *pl, unsigned long *numerator,
unsigned long *denominator);
@@ -96,7 +97,7 @@ void fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
unsigned long flags;
local_irq_save(flags);
- __fprop_inc_percpu(p, pl);
+ __fprop_add_percpu(p, pl, 1);
local_irq_restore(flags);
}
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 900325aa5d31..59eabbc3a36b 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -213,6 +213,8 @@ static inline int add_disk(struct gendisk *disk)
}
extern void del_gendisk(struct gendisk *gp);
+void invalidate_disk(struct gendisk *disk);
+
void set_disk_ro(struct gendisk *disk, bool read_only);
static inline int get_disk_ro(struct gendisk *disk)
@@ -221,6 +223,11 @@ static inline int get_disk_ro(struct gendisk *disk)
test_bit(GD_READ_ONLY, &disk->state);
}
+static inline int bdev_read_only(struct block_device *bdev)
+{
+ return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
+}
+
extern void disk_block_events(struct gendisk *disk);
extern void disk_unblock_events(struct gendisk *disk);
extern void disk_flush_events(struct gendisk *disk, unsigned int mask);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 55b2ec1f965a..3745efd21cf6 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -520,15 +520,11 @@ static inline void arch_free_page(struct page *page, int order) { }
#ifndef HAVE_ARCH_ALLOC_PAGE
static inline void arch_alloc_page(struct page *page, int order) { }
#endif
-#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
-static inline int arch_make_page_accessible(struct page *page)
-{
- return 0;
-}
-#endif
struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
nodemask_t *nodemask);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+ nodemask_t *nodemask);
unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
nodemask_t *nodemask, int nr_pages,
@@ -570,6 +566,15 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
return __alloc_pages(gfp_mask, order, nid, NULL);
}
+static inline
+struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
+{
+ VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+ VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+
+ return __folio_alloc(gfp, order, nid, NULL);
+}
+
/*
* Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
* prefer the current CPU's closest node. Otherwise node must be valid and
@@ -586,6 +591,7 @@ static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
#ifdef CONFIG_NUMA
struct page *alloc_pages(gfp_t gfp, unsigned int order);
+struct folio *folio_alloc(gfp_t gfp, unsigned order);
extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
struct vm_area_struct *vma, unsigned long addr,
int node, bool hugepage);
@@ -596,6 +602,10 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
{
return alloc_pages_node(numa_node_id(), gfp_mask, order);
}
+static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
+{
+ return __folio_alloc_node(gfp, order, numa_node_id());
+}
#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\
alloc_pages(gfp_mask, order)
#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 4aa1031d3e4c..0a0b2b09b1b8 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -73,6 +73,12 @@ static inline void *kmap_local_page(struct page *page)
return __kmap_local_page_prot(page, kmap_prot);
}
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+ struct page *page = folio_page(folio, offset / PAGE_SIZE);
+ return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE;
+}
+
static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
{
return __kmap_local_page_prot(page, prot);
@@ -171,6 +177,11 @@ static inline void *kmap_local_page(struct page *page)
return page_address(page);
}
+static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+{
+ return page_address(&folio->page) + offset;
+}
+
static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
{
return kmap_local_page(page);
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index b4c49f9cc379..27cdd715c5f9 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -97,6 +97,43 @@ static inline void kmap_flush_unused(void);
static inline void *kmap_local_page(struct page *page);
/**
+ * kmap_local_folio - Map a page in this folio for temporary usage
+ * @folio: The folio containing the page.
+ * @offset: The byte offset within the folio which identifies the page.
+ *
+ * Requires careful handling when nesting multiple mappings because the map
+ * management is stack based. The unmap has to be in the reverse order of
+ * the map operation::
+ *
+ * addr1 = kmap_local_folio(folio1, offset1);
+ * addr2 = kmap_local_folio(folio2, offset2);
+ * ...
+ * kunmap_local(addr2);
+ * kunmap_local(addr1);
+ *
+ * Unmapping addr1 before addr2 is invalid and causes malfunction.
+ *
+ * Contrary to kmap() mappings the mapping is only valid in the context of
+ * the caller and cannot be handed to other contexts.
+ *
+ * On CONFIG_HIGHMEM=n kernels and for low memory pages this returns the
+ * virtual address of the direct mapping. Only real highmem pages are
+ * temporarily mapped.
+ *
+ * While it is significantly faster than kmap() for the higmem case it
+ * comes with restrictions about the pointer validity. Only use when really
+ * necessary.
+ *
+ * On HIGHMEM enabled systems mapping a highmem page has the side effect of
+ * disabling migration in order to keep the virtual address stable across
+ * preemption. No caller of kmap_local_folio() can rely on this side effect.
+ *
+ * Context: Can be invoked from any context.
+ * Return: The virtual address of @offset.
+ */
+static inline void *kmap_local_folio(struct folio *folio, size_t offset);
+
+/**
* kmap_atomic - Atomically map a page for temporary usage - Deprecated!
* @page: Pointer to the page to be mapped
*
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index f123e15d966e..f280f33ff223 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -251,15 +251,6 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
}
/**
- * thp_head - Head page of a transparent huge page.
- * @page: Any page (tail, head or regular) found in the page cache.
- */
-static inline struct page *thp_head(struct page *page)
-{
- return compound_head(page);
-}
-
-/**
* thp_order - Order of a transparent huge page.
* @page: Head page of a transparent huge page.
*/
@@ -336,12 +327,6 @@ static inline struct list_head *page_deferred_list(struct page *page)
#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
-static inline struct page *thp_head(struct page *page)
-{
- VM_BUG_ON_PGFLAGS(PageTail(page), page);
- return page;
-}
-
static inline unsigned int thp_order(struct page *page)
{
VM_BUG_ON_PGFLAGS(PageTail(page), page);
diff --git a/include/linux/keyslot-manager.h b/include/linux/keyslot-manager.h
deleted file mode 100644
index a27605e2f826..000000000000
--- a/include/linux/keyslot-manager.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright 2019 Google LLC
- */
-
-#ifndef __LINUX_KEYSLOT_MANAGER_H
-#define __LINUX_KEYSLOT_MANAGER_H
-
-#include <linux/bio.h>
-#include <linux/blk-crypto.h>
-
-struct blk_keyslot_manager;
-
-/**
- * struct blk_ksm_ll_ops - functions to manage keyslots in hardware
- * @keyslot_program: Program the specified key into the specified slot in the
- * inline encryption hardware.
- * @keyslot_evict: Evict key from the specified keyslot in the hardware.
- * The key is provided so that e.g. dm layers can evict
- * keys from the devices that they map over.
- * Returns 0 on success, -errno otherwise.
- *
- * This structure should be provided by storage device drivers when they set up
- * a keyslot manager - this structure holds the function ptrs that the keyslot
- * manager will use to manipulate keyslots in the hardware.
- */
-struct blk_ksm_ll_ops {
- int (*keyslot_program)(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot);
- int (*keyslot_evict)(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- unsigned int slot);
-};
-
-struct blk_keyslot_manager {
- /*
- * The struct blk_ksm_ll_ops that this keyslot manager will use
- * to perform operations like programming and evicting keys on the
- * device
- */
- struct blk_ksm_ll_ops ksm_ll_ops;
-
- /*
- * The maximum number of bytes supported for specifying the data unit
- * number.
- */
- unsigned int max_dun_bytes_supported;
-
- /*
- * Array of size BLK_ENCRYPTION_MODE_MAX of bitmasks that represents
- * whether a crypto mode and data unit size are supported. The i'th
- * bit of crypto_mode_supported[crypto_mode] is set iff a data unit
- * size of (1 << i) is supported. We only support data unit sizes
- * that are powers of 2.
- */
- unsigned int crypto_modes_supported[BLK_ENCRYPTION_MODE_MAX];
-
- /* Device for runtime power management (NULL if none) */
- struct device *dev;
-
- /* Here onwards are *private* fields for internal keyslot manager use */
-
- unsigned int num_slots;
-
- /* Protects programming and evicting keys from the device */
- struct rw_semaphore lock;
-
- /* List of idle slots, with least recently used slot at front */
- wait_queue_head_t idle_slots_wait_queue;
- struct list_head idle_slots;
- spinlock_t idle_slots_lock;
-
- /*
- * Hash table which maps struct *blk_crypto_key to keyslots, so that we
- * can find a key's keyslot in O(1) time rather than O(num_slots).
- * Protected by 'lock'.
- */
- struct hlist_head *slot_hashtable;
- unsigned int log_slot_ht_size;
-
- /* Per-keyslot data */
- struct blk_ksm_keyslot *slots;
-};
-
-int blk_ksm_init(struct blk_keyslot_manager *ksm, unsigned int num_slots);
-
-int devm_blk_ksm_init(struct device *dev, struct blk_keyslot_manager *ksm,
- unsigned int num_slots);
-
-blk_status_t blk_ksm_get_slot_for_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key,
- struct blk_ksm_keyslot **slot_ptr);
-
-unsigned int blk_ksm_get_slot_idx(struct blk_ksm_keyslot *slot);
-
-void blk_ksm_put_slot(struct blk_ksm_keyslot *slot);
-
-bool blk_ksm_crypto_cfg_supported(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_config *cfg);
-
-int blk_ksm_evict_key(struct blk_keyslot_manager *ksm,
- const struct blk_crypto_key *key);
-
-void blk_ksm_reprogram_all_keys(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_destroy(struct blk_keyslot_manager *ksm);
-
-void blk_ksm_intersect_modes(struct blk_keyslot_manager *parent,
- const struct blk_keyslot_manager *child);
-
-void blk_ksm_init_passthrough(struct blk_keyslot_manager *ksm);
-
-bool blk_ksm_is_superset(struct blk_keyslot_manager *ksm_superset,
- struct blk_keyslot_manager *ksm_subset);
-
-void blk_ksm_update_capabilities(struct blk_keyslot_manager *target_ksm,
- struct blk_keyslot_manager *reference_ksm);
-
-#endif /* __LINUX_KEYSLOT_MANAGER_H */
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 161e8164abcf..a38a5bca1ba5 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -52,7 +52,7 @@ struct page *ksm_might_need_to_copy(struct page *page,
struct vm_area_struct *vma, unsigned long address);
void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
-void ksm_migrate_page(struct page *newpage, struct page *oldpage);
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
#else /* !CONFIG_KSM */
@@ -83,7 +83,7 @@ static inline void rmap_walk_ksm(struct page *page,
{
}
-static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old)
{
}
#endif /* CONFIG_MMU */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3096c9a0ee01..e34bf0cbdf55 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -369,7 +369,7 @@ enum page_memcg_data_flags {
#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
-static inline bool PageMemcgKmem(struct page *page);
+static inline bool folio_memcg_kmem(struct folio *folio);
/*
* After the initialization objcg->memcg is always pointing at
@@ -384,89 +384,95 @@ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
}
/*
- * __page_memcg - get the memory cgroup associated with a non-kmem page
- * @page: a pointer to the page struct
+ * __folio_memcg - Get the memory cgroup associated with a non-kmem folio
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the memory cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages or
- * kmem pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios or
+ * kmem folios.
*/
-static inline struct mem_cgroup *__page_memcg(struct page *page)
+static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
{
- unsigned long memcg_data = page->memcg_data;
+ unsigned long memcg_data = folio->memcg_data;
- VM_BUG_ON_PAGE(PageSlab(page), page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
- * __page_objcg - get the object cgroup associated with a kmem page
- * @page: a pointer to the page struct
+ * __folio_objcg - get the object cgroup associated with a kmem folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the object cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the object cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper object cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages or
- * LRU pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios or
+ * LRU folios.
*/
-static inline struct obj_cgroup *__page_objcg(struct page *page)
+static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
{
- unsigned long memcg_data = page->memcg_data;
+ unsigned long memcg_data = folio->memcg_data;
- VM_BUG_ON_PAGE(PageSlab(page), page);
- VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page);
- VM_BUG_ON_PAGE(!(memcg_data & MEMCG_DATA_KMEM), page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
+ VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+ VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
}
/*
- * page_memcg - get the memory cgroup associated with a page
- * @page: a pointer to the page struct
+ * folio_memcg - Get the memory cgroup associated with a folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * Returns a pointer to the memory cgroup associated with the folio,
+ * or NULL. This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios.
*
- * For a non-kmem page any of the following ensures page and memcg binding
+ * For a non-kmem folio any of the following ensures folio and memcg binding
* stability:
*
- * - the page lock
+ * - the folio lock
* - LRU isolation
* - lock_page_memcg()
* - exclusive reference
*
- * For a kmem page a caller should hold an rcu read lock to protect memcg
- * associated with a kmem page from being released.
+ * For a kmem folio a caller should hold an rcu read lock to protect memcg
+ * associated with a kmem folio from being released.
*/
+static inline struct mem_cgroup *folio_memcg(struct folio *folio)
+{
+ if (folio_memcg_kmem(folio))
+ return obj_cgroup_memcg(__folio_objcg(folio));
+ return __folio_memcg(folio);
+}
+
static inline struct mem_cgroup *page_memcg(struct page *page)
{
- if (PageMemcgKmem(page))
- return obj_cgroup_memcg(__page_objcg(page));
- else
- return __page_memcg(page);
+ return folio_memcg(page_folio(page));
}
-/*
- * page_memcg_rcu - locklessly get the memory cgroup associated with a page
- * @page: a pointer to the page struct
+/**
+ * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio.
+ * @folio: Pointer to the folio.
*
- * Returns a pointer to the memory cgroup associated with the page,
- * or NULL. This function assumes that the page is known to have a
+ * This function assumes that the folio is known to have a
* proper memory cgroup pointer. It's not safe to call this function
- * against some type of pages, e.g. slab pages or ex-slab pages.
+ * against some type of folios, e.g. slab folios or ex-slab folios.
+ *
+ * Return: A pointer to the memory cgroup associated with the folio,
+ * or NULL.
*/
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
- unsigned long memcg_data = READ_ONCE(page->memcg_data);
+ unsigned long memcg_data = READ_ONCE(folio->memcg_data);
- VM_BUG_ON_PAGE(PageSlab(page), page);
+ VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
WARN_ON_ONCE(!rcu_read_lock_held());
if (memcg_data & MEMCG_DATA_KMEM) {
@@ -523,17 +529,18 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
#ifdef CONFIG_MEMCG_KMEM
/*
- * PageMemcgKmem - check if the page has MemcgKmem flag set
- * @page: a pointer to the page struct
+ * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
+ * @folio: Pointer to the folio.
*
- * Checks if the page has MemcgKmem flag set. The caller must ensure that
- * the page has an associated memory cgroup. It's not safe to call this function
- * against some types of pages, e.g. slab pages.
+ * Checks if the folio has MemcgKmem flag set. The caller must ensure
+ * that the folio has an associated memory cgroup. It's not safe to call
+ * this function against some types of folios, e.g. slab folios.
*/
-static inline bool PageMemcgKmem(struct page *page)
+static inline bool folio_memcg_kmem(struct folio *folio)
{
- VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page);
- return page->memcg_data & MEMCG_DATA_KMEM;
+ VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page);
+ VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio);
+ return folio->memcg_data & MEMCG_DATA_KMEM;
}
/*
@@ -577,7 +584,7 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
}
#else
-static inline bool PageMemcgKmem(struct page *page)
+static inline bool folio_memcg_kmem(struct folio *folio)
{
return false;
}
@@ -593,6 +600,11 @@ static inline struct obj_cgroup **page_objcgs_check(struct page *page)
}
#endif
+static inline bool PageMemcgKmem(struct page *page)
+{
+ return folio_memcg_kmem(page_folio(page));
+}
+
static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
{
return (memcg == root_mem_cgroup);
@@ -684,26 +696,47 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
page_counter_read(&memcg->memory);
}
-int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask);
-static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp);
+
+/**
+ * mem_cgroup_charge - Charge a newly allocated folio to a cgroup.
+ * @folio: Folio to charge.
+ * @mm: mm context of the allocating task.
+ * @gfp: Reclaim mode.
+ *
+ * Try to charge @folio to the memcg that @mm belongs to, reclaiming
+ * pages according to @gfp if necessary. If @mm is NULL, try to
+ * charge to the active memcg.
+ *
+ * Do not use this for folios allocated for swapin.
+ *
+ * Return: 0 on success. Otherwise, an error code is returned.
+ */
+static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
+ gfp_t gfp)
{
if (mem_cgroup_disabled())
return 0;
- return __mem_cgroup_charge(page, mm, gfp_mask);
+ return __mem_cgroup_charge(folio, mm, gfp);
}
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry);
void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
-void __mem_cgroup_uncharge(struct page *page);
-static inline void mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct folio *folio);
+
+/**
+ * mem_cgroup_uncharge - Uncharge a folio.
+ * @folio: Folio to uncharge.
+ *
+ * Uncharge a folio previously charged with mem_cgroup_charge().
+ */
+static inline void mem_cgroup_uncharge(struct folio *folio)
{
if (mem_cgroup_disabled())
return;
- __mem_cgroup_uncharge(page);
+ __mem_cgroup_uncharge(folio);
}
void __mem_cgroup_uncharge_list(struct list_head *page_list);
@@ -714,7 +747,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
__mem_cgroup_uncharge_list(page_list);
}
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
+void mem_cgroup_migrate(struct folio *old, struct folio *new);
/**
* mem_cgroup_lruvec - get the lru list vector for a memcg & node
@@ -753,33 +786,33 @@ out:
}
/**
- * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
- * @page: the page
+ * folio_lruvec - return lruvec for isolating/putting an LRU folio
+ * @folio: Pointer to the folio.
*
- * This function relies on page->mem_cgroup being stable.
+ * This function relies on folio->mem_cgroup being stable.
*/
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec(struct folio *folio)
{
- pg_data_t *pgdat = page_pgdat(page);
- struct mem_cgroup *memcg = page_memcg(page);
+ struct mem_cgroup *memcg = folio_memcg(folio);
- VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
- return mem_cgroup_lruvec(memcg, pgdat);
+ VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio);
+ return mem_cgroup_lruvec(memcg, folio_pgdat(folio));
}
struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
-struct lruvec *lock_page_lruvec(struct page *page);
-struct lruvec *lock_page_lruvec_irq(struct page *page);
-struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+struct lruvec *folio_lruvec_lock(struct folio *folio);
+struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
+struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flags);
#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page);
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio);
#else
-static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+static inline
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
#endif
@@ -947,6 +980,8 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
extern bool cgroup_memory_noswap;
#endif
+void folio_memcg_lock(struct folio *folio);
+void folio_memcg_unlock(struct folio *folio);
void lock_page_memcg(struct page *page);
void unlock_page_memcg(struct page *page);
@@ -1115,12 +1150,17 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
#define MEM_CGROUP_ID_SHIFT 0
#define MEM_CGROUP_ID_MAX 0
+static inline struct mem_cgroup *folio_memcg(struct folio *folio)
+{
+ return NULL;
+}
+
static inline struct mem_cgroup *page_memcg(struct page *page)
{
return NULL;
}
-static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
{
WARN_ON_ONCE(!rcu_read_lock_held());
return NULL;
@@ -1131,6 +1171,11 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page)
return NULL;
}
+static inline bool folio_memcg_kmem(struct folio *folio)
+{
+ return false;
+}
+
static inline bool PageMemcgKmem(struct page *page)
{
return false;
@@ -1179,8 +1224,8 @@ static inline bool mem_cgroup_below_min(struct mem_cgroup *memcg)
return false;
}
-static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+static inline int mem_cgroup_charge(struct folio *folio,
+ struct mm_struct *mm, gfp_t gfp)
{
return 0;
}
@@ -1195,7 +1240,7 @@ static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
{
}
-static inline void mem_cgroup_uncharge(struct page *page)
+static inline void mem_cgroup_uncharge(struct folio *folio)
{
}
@@ -1203,7 +1248,7 @@ static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
{
}
-static inline void mem_cgroup_migrate(struct page *old, struct page *new)
+static inline void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
}
@@ -1213,14 +1258,14 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
return &pgdat->__lruvec;
}
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec(struct folio *folio)
{
- pg_data_t *pgdat = page_pgdat(page);
-
+ struct pglist_data *pgdat = folio_pgdat(folio);
return &pgdat->__lruvec;
}
-static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+static inline
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
}
@@ -1250,26 +1295,26 @@ static inline void mem_cgroup_put(struct mem_cgroup *memcg)
{
}
-static inline struct lruvec *lock_page_lruvec(struct page *page)
+static inline struct lruvec *folio_lruvec_lock(struct folio *folio)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
-static inline struct lruvec *lock_page_lruvec_irq(struct page *page)
+static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irq(&pgdat->__lruvec.lru_lock);
return &pgdat->__lruvec;
}
-static inline struct lruvec *lock_page_lruvec_irqsave(struct page *page,
+static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
unsigned long *flagsp)
{
- struct pglist_data *pgdat = page_pgdat(page);
+ struct pglist_data *pgdat = folio_pgdat(folio);
spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp);
return &pgdat->__lruvec;
@@ -1356,6 +1401,14 @@ static inline void unlock_page_memcg(struct page *page)
{
}
+static inline void folio_memcg_lock(struct folio *folio)
+{
+}
+
+static inline void folio_memcg_unlock(struct folio *folio)
+{
+}
+
static inline void mem_cgroup_handle_over_high(void)
{
}
@@ -1517,38 +1570,39 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
}
/* Test requires a stable page->memcg binding, see page_memcg() */
-static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec)
+static inline bool folio_matches_lruvec(struct folio *folio,
+ struct lruvec *lruvec)
{
- return lruvec_pgdat(lruvec) == page_pgdat(page) &&
- lruvec_memcg(lruvec) == page_memcg(page);
+ return lruvec_pgdat(lruvec) == folio_pgdat(folio) &&
+ lruvec_memcg(lruvec) == folio_memcg(folio);
}
/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
+static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
struct lruvec *locked_lruvec)
{
if (locked_lruvec) {
- if (page_matches_lruvec(page, locked_lruvec))
+ if (folio_matches_lruvec(folio, locked_lruvec))
return locked_lruvec;
unlock_page_lruvec_irq(locked_lruvec);
}
- return lock_page_lruvec_irq(page);
+ return folio_lruvec_lock_irq(folio);
}
/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
+static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio,
struct lruvec *locked_lruvec, unsigned long *flags)
{
if (locked_lruvec) {
- if (page_matches_lruvec(page, locked_lruvec))
+ if (folio_matches_lruvec(folio, locked_lruvec))
return locked_lruvec;
unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
}
- return lock_page_lruvec_irqsave(page, flags);
+ return folio_lruvec_lock_irqsave(folio, flags);
}
#ifdef CONFIG_CGROUP_WRITEBACK
@@ -1558,17 +1612,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
unsigned long *pheadroom, unsigned long *pdirty,
unsigned long *pwriteback);
-void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb);
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
if (mem_cgroup_disabled())
return;
- if (unlikely(&page_memcg(page)->css != wb->memcg_css))
- mem_cgroup_track_foreign_dirty_slowpath(page, wb);
+ if (unlikely(&folio_memcg(folio)->css != wb->memcg_css))
+ mem_cgroup_track_foreign_dirty_slowpath(folio, wb);
}
void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
@@ -1588,7 +1642,7 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
{
}
-static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+static inline void mem_cgroup_track_foreign_dirty(struct folio *folio,
struct bdi_writeback *wb)
{
}
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 7efc0a7c14c9..182c606adb06 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -160,7 +160,10 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
#define register_hotmemory_notifier(nb) register_memory_notifier(nb)
#define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb)
#else
-#define hotplug_memory_notifier(fn, pri) ({ 0; })
+static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
+{
+ return 0;
+}
/* These aren't inline functions due to a GCC bug. */
#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; })
#define unregister_hotmemory_notifier(nb) ({ (void)(nb); })
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index c8077e936691..0d2aeb9b0f66 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -57,6 +57,10 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
+int folio_migrate_mapping(struct address_space *mapping,
+ struct folio *newfolio, struct folio *folio, int extra_count);
#else
static inline void putback_movable_pages(struct list_head *l) {}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e23417424373..f17d2101af7a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1138,7 +1138,6 @@ int mlx5_cmd_create_vport_lag(struct mlx5_core_dev *dev);
int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
bool mlx5_lag_is_roce(struct mlx5_core_dev *dev);
bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
-bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev);
bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
bool mlx5_lag_is_master(struct mlx5_core_dev *dev);
bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 73a52aba448f..40ff114aaf9e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -36,10 +36,7 @@
struct mempolicy;
struct anon_vma;
struct anon_vma_chain;
-struct file_ra_state;
struct user_struct;
-struct writeback_control;
-struct bdi_writeback;
struct pt_regs;
extern int sysctl_page_lock_unfairness;
@@ -216,13 +213,6 @@ int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
loff_t *);
int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
loff_t *);
-/*
- * Any attempt to mark this function as static leads to build failure
- * when CONFIG_DEBUG_INFO_BTF is enabled because __add_to_page_cache_locked()
- * is referred to by BPF code. This must be visible for error injection.
- */
-int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp, void **shadowp);
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
@@ -748,13 +738,18 @@ static inline int put_page_testzero(struct page *page)
return page_ref_dec_and_test(page);
}
+static inline int folio_put_testzero(struct folio *folio)
+{
+ return put_page_testzero(&folio->page);
+}
+
/*
* Try to grab a ref unless the page has a refcount of zero, return false if
* that is the case.
* This can be called when MMU is off so it must not access
* any of the virtual mappings.
*/
-static inline int get_page_unless_zero(struct page *page)
+static inline bool get_page_unless_zero(struct page *page)
{
return page_ref_add_unless(page, 1, 0);
}
@@ -907,7 +902,7 @@ void __put_page(struct page *page);
void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
-void copy_huge_page(struct page *dst, struct page *src);
+void folio_copy(struct folio *dst, struct folio *src);
/*
* Compound pages have a destructor function. Provide a
@@ -950,6 +945,20 @@ static inline unsigned int compound_order(struct page *page)
return page[1].compound_order;
}
+/**
+ * folio_order - The allocation order of a folio.
+ * @folio: The folio.
+ *
+ * A folio is composed of 2^order pages. See get_order() for the definition
+ * of order.
+ *
+ * Return: The order of the folio.
+ */
+static inline unsigned int folio_order(struct folio *folio)
+{
+ return compound_order(&folio->page);
+}
+
static inline bool hpage_pincount_available(struct page *page)
{
/*
@@ -1131,6 +1140,11 @@ static inline enum zone_type page_zonenum(const struct page *page)
return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
}
+static inline enum zone_type folio_zonenum(const struct folio *folio)
+{
+ return page_zonenum(&folio->page);
+}
+
#ifdef CONFIG_ZONE_DEVICE
static inline bool is_zone_device_page(const struct page *page)
{
@@ -1200,18 +1214,26 @@ static inline bool is_pci_p2pdma_page(const struct page *page)
}
/* 127: arbitrary random number, small enough to assemble well */
-#define page_ref_zero_or_close_to_overflow(page) \
- ((unsigned int) page_ref_count(page) + 127u <= 127u)
+#define folio_ref_zero_or_close_to_overflow(folio) \
+ ((unsigned int) folio_ref_count(folio) + 127u <= 127u)
+
+/**
+ * folio_get - Increment the reference count on a folio.
+ * @folio: The folio.
+ *
+ * Context: May be called in any context, as long as you know that
+ * you have a refcount on the folio. If you do not already have one,
+ * folio_try_get() may be the right interface for you to use.
+ */
+static inline void folio_get(struct folio *folio)
+{
+ VM_BUG_ON_FOLIO(folio_ref_zero_or_close_to_overflow(folio), folio);
+ folio_ref_inc(folio);
+}
static inline void get_page(struct page *page)
{
- page = compound_head(page);
- /*
- * Getting a normal page or the head of a compound page
- * requires to already have an elevated page->_refcount.
- */
- VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page);
- page_ref_inc(page);
+ folio_get(page_folio(page));
}
bool __must_check try_grab_page(struct page *page, unsigned int flags);
@@ -1228,9 +1250,28 @@ static inline __must_check bool try_get_page(struct page *page)
return true;
}
+/**
+ * folio_put - Decrement the reference count on a folio.
+ * @folio: The folio.
+ *
+ * If the folio's reference count reaches zero, the memory will be
+ * released back to the page allocator and may be used by another
+ * allocation immediately. Do not access the memory or the struct folio
+ * after calling folio_put() unless you can be sure that it wasn't the
+ * last reference.
+ *
+ * Context: May be called in process or interrupt context, but not in NMI
+ * context. May be called while holding a spinlock.
+ */
+static inline void folio_put(struct folio *folio)
+{
+ if (folio_put_testzero(folio))
+ __put_page(&folio->page);
+}
+
static inline void put_page(struct page *page)
{
- page = compound_head(page);
+ struct folio *folio = page_folio(page);
/*
* For devmap managed pages we need to catch refcount transition from
@@ -1238,13 +1279,12 @@ static inline void put_page(struct page *page)
* need to inform the device driver through callback. See
* include/linux/memremap.h and HMM for details.
*/
- if (page_is_devmap_managed(page)) {
- put_devmap_managed_page(page);
+ if (page_is_devmap_managed(&folio->page)) {
+ put_devmap_managed_page(&folio->page);
return;
}
- if (put_page_testzero(page))
- __put_page(page);
+ folio_put(folio);
}
/*
@@ -1379,6 +1419,11 @@ static inline int page_to_nid(const struct page *page)
}
#endif
+static inline int folio_nid(const struct folio *folio)
+{
+ return page_to_nid(&folio->page);
+}
+
#ifdef CONFIG_NUMA_BALANCING
static inline int cpu_pid_to_cpupid(int cpu, int pid)
{
@@ -1546,6 +1591,16 @@ static inline pg_data_t *page_pgdat(const struct page *page)
return NODE_DATA(page_to_nid(page));
}
+static inline struct zone *folio_zone(const struct folio *folio)
+{
+ return page_zone(&folio->page);
+}
+
+static inline pg_data_t *folio_pgdat(const struct folio *folio)
+{
+ return page_pgdat(&folio->page);
+}
+
#ifdef SECTION_IN_PAGE_FLAGS
static inline void set_page_section(struct page *page, unsigned long section)
{
@@ -1559,6 +1614,20 @@ static inline unsigned long page_to_section(const struct page *page)
}
#endif
+/**
+ * folio_pfn - Return the Page Frame Number of a folio.
+ * @folio: The folio.
+ *
+ * A folio may contain multiple pages. The pages have consecutive
+ * Page Frame Numbers.
+ *
+ * Return: The Page Frame Number of the first page in the folio.
+ */
+static inline unsigned long folio_pfn(struct folio *folio)
+{
+ return page_to_pfn(&folio->page);
+}
+
/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
#ifdef CONFIG_MIGRATION
static inline bool is_pinnable_page(struct page *page)
@@ -1595,6 +1664,89 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
#endif
}
+/**
+ * folio_nr_pages - The number of pages in the folio.
+ * @folio: The folio.
+ *
+ * Return: A positive power of two.
+ */
+static inline long folio_nr_pages(struct folio *folio)
+{
+ return compound_nr(&folio->page);
+}
+
+/**
+ * folio_next - Move to the next physical folio.
+ * @folio: The folio we're currently operating on.
+ *
+ * If you have physically contiguous memory which may span more than
+ * one folio (eg a &struct bio_vec), use this function to move from one
+ * folio to the next. Do not use it if the memory is only virtually
+ * contiguous as the folios are almost certainly not adjacent to each
+ * other. This is the folio equivalent to writing ``page++``.
+ *
+ * Context: We assume that the folios are refcounted and/or locked at a
+ * higher level and do not adjust the reference counts.
+ * Return: The next struct folio.
+ */
+static inline struct folio *folio_next(struct folio *folio)
+{
+ return (struct folio *)folio_page(folio, folio_nr_pages(folio));
+}
+
+/**
+ * folio_shift - The size of the memory described by this folio.
+ * @folio: The folio.
+ *
+ * A folio represents a number of bytes which is a power-of-two in size.
+ * This function tells you which power-of-two the folio is. See also
+ * folio_size() and folio_order().
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split. It is not necessary for the folio to be locked.
+ * Return: The base-2 logarithm of the size of this folio.
+ */
+static inline unsigned int folio_shift(struct folio *folio)
+{
+ return PAGE_SHIFT + folio_order(folio);
+}
+
+/**
+ * folio_size - The number of bytes in a folio.
+ * @folio: The folio.
+ *
+ * Context: The caller should have a reference on the folio to prevent
+ * it from being split. It is not necessary for the folio to be locked.
+ * Return: The number of bytes in this folio.
+ */
+static inline size_t folio_size(struct folio *folio)
+{
+ return PAGE_SIZE << folio_order(folio);
+}
+
+#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
+static inline int arch_make_page_accessible(struct page *page)
+{
+ return 0;
+}
+#endif
+
+#ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
+static inline int arch_make_folio_accessible(struct folio *folio)
+{
+ int ret;
+ long i, nr = folio_nr_pages(folio);
+
+ for (i = 0; i < nr; i++) {
+ ret = arch_make_page_accessible(folio_page(folio, i));
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+#endif
+
/*
* Some inline functions in vmstat.h depend on page_zone()
*/
@@ -1635,19 +1787,6 @@ void page_address_init(void);
extern void *page_rmapping(struct page *page);
extern struct anon_vma *page_anon_vma(struct page *page);
-extern struct address_space *page_mapping(struct page *page);
-
-extern struct address_space *__page_file_mapping(struct page *);
-
-static inline
-struct address_space *page_file_mapping(struct page *page)
-{
- if (unlikely(PageSwapCache(page)))
- return __page_file_mapping(page);
-
- return page->mapping;
-}
-
extern pgoff_t __page_file_index(struct page *page);
/*
@@ -1662,7 +1801,7 @@ static inline pgoff_t page_index(struct page *page)
}
bool page_mapped(struct page *page);
-struct address_space *page_mapping(struct page *page);
+bool folio_mapped(struct folio *folio);
/*
* Return true only if the page has been allocated with
@@ -1700,6 +1839,7 @@ extern void pagefault_out_of_memory(void);
#define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK)
#define offset_in_thp(page, p) ((unsigned long)(p) & (thp_size(page) - 1))
+#define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1))
/*
* Flags passed to show_mem() and show_free_areas() to suppress output in
@@ -1854,20 +1994,9 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned int offset,
unsigned int length);
-int redirty_page_for_writepage(struct writeback_control *wbc,
- struct page *page);
-void account_page_cleaned(struct page *page, struct address_space *mapping,
- struct bdi_writeback *wb);
-int set_page_dirty(struct page *page);
+bool folio_mark_dirty(struct folio *folio);
+bool set_page_dirty(struct page *page);
int set_page_dirty_lock(struct page *page);
-void __cancel_dirty_page(struct page *page);
-static inline void cancel_dirty_page(struct page *page)
-{
- /* Avoid atomic ops, locking, etc. when not actually needed. */
- if (PageDirty(page))
- __cancel_dirty_page(page);
-}
-int clear_page_dirty_for_io(struct page *page);
int get_cmdline(struct task_struct *task, char *buffer, int buflen);
@@ -2659,10 +2788,6 @@ extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
pgoff_t start_pgoff, pgoff_t end_pgoff);
extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
-/* mm/page-writeback.c */
-int __must_check write_one_page(struct page *page);
-void task_dirty_inc(struct task_struct *tsk);
-
extern unsigned long stack_guard_gap;
/* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 355ea1ee32bd..e2ec68b0515c 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -6,27 +6,33 @@
#include <linux/swap.h>
/**
- * page_is_file_lru - should the page be on a file LRU or anon LRU?
- * @page: the page to test
- *
- * Returns 1 if @page is a regular filesystem backed page cache page or a lazily
- * freed anonymous page (e.g. via MADV_FREE). Returns 0 if @page is a normal
- * anonymous page, a tmpfs page or otherwise ram or swap backed page. Used by
- * functions that manipulate the LRU lists, to sort a page onto the right LRU
- * list.
+ * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
+ * @folio: The folio to test.
*
* We would like to get this info without a page flag, but the state
- * needs to survive until the page is last deleted from the LRU, which
+ * needs to survive until the folio is last deleted from the LRU, which
* could be as far down as __page_cache_release.
+ *
+ * Return: An integer (not a boolean!) used to sort a folio onto the
+ * right LRU list and to account folios correctly.
+ * 1 if @folio is a regular filesystem backed page cache folio
+ * or a lazily freed anonymous folio (e.g. via MADV_FREE).
+ * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
+ * ram or swap backed folio.
*/
+static inline int folio_is_file_lru(struct folio *folio)
+{
+ return !folio_test_swapbacked(folio);
+}
+
static inline int page_is_file_lru(struct page *page)
{
- return !PageSwapBacked(page);
+ return folio_is_file_lru(page_folio(page));
}
static __always_inline void update_lru_size(struct lruvec *lruvec,
enum lru_list lru, enum zone_type zid,
- int nr_pages)
+ long nr_pages)
{
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
@@ -39,69 +45,94 @@ static __always_inline void update_lru_size(struct lruvec *lruvec,
}
/**
- * __clear_page_lru_flags - clear page lru flags before releasing a page
- * @page: the page that was on lru and now has a zero reference
+ * __folio_clear_lru_flags - Clear page lru flags before releasing a page.
+ * @folio: The folio that was on lru and now has a zero reference.
*/
-static __always_inline void __clear_page_lru_flags(struct page *page)
+static __always_inline void __folio_clear_lru_flags(struct folio *folio)
{
- VM_BUG_ON_PAGE(!PageLRU(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_lru(folio), folio);
- __ClearPageLRU(page);
+ __folio_clear_lru(folio);
/* this shouldn't happen, so leave the flags to bad_page() */
- if (PageActive(page) && PageUnevictable(page))
+ if (folio_test_active(folio) && folio_test_unevictable(folio))
return;
- __ClearPageActive(page);
- __ClearPageUnevictable(page);
+ __folio_clear_active(folio);
+ __folio_clear_unevictable(folio);
+}
+
+static __always_inline void __clear_page_lru_flags(struct page *page)
+{
+ __folio_clear_lru_flags(page_folio(page));
}
/**
- * page_lru - which LRU list should a page be on?
- * @page: the page to test
+ * folio_lru_list - Which LRU list should a folio be on?
+ * @folio: The folio to test.
*
- * Returns the LRU list a page should be on, as an index
+ * Return: The LRU list a folio should be on, as an index
* into the array of LRU lists.
*/
-static __always_inline enum lru_list page_lru(struct page *page)
+static __always_inline enum lru_list folio_lru_list(struct folio *folio)
{
enum lru_list lru;
- VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
+ VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
- if (PageUnevictable(page))
+ if (folio_test_unevictable(folio))
return LRU_UNEVICTABLE;
- lru = page_is_file_lru(page) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
- if (PageActive(page))
+ lru = folio_is_file_lru(folio) ? LRU_INACTIVE_FILE : LRU_INACTIVE_ANON;
+ if (folio_test_active(folio))
lru += LRU_ACTIVE;
return lru;
}
+static __always_inline
+void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
+{
+ enum lru_list lru = folio_lru_list(folio);
+
+ update_lru_size(lruvec, lru, folio_zonenum(folio),
+ folio_nr_pages(folio));
+ list_add(&folio->lru, &lruvec->lists[lru]);
+}
+
static __always_inline void add_page_to_lru_list(struct page *page,
struct lruvec *lruvec)
{
- enum lru_list lru = page_lru(page);
+ lruvec_add_folio(lruvec, page_folio(page));
+}
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
+{
+ enum lru_list lru = folio_lru_list(folio);
+
+ update_lru_size(lruvec, lru, folio_zonenum(folio),
+ folio_nr_pages(folio));
+ list_add_tail(&folio->lru, &lruvec->lists[lru]);
}
static __always_inline void add_page_to_lru_list_tail(struct page *page,
struct lruvec *lruvec)
{
- enum lru_list lru = page_lru(page);
+ lruvec_add_folio_tail(lruvec, page_folio(page));
+}
- update_lru_size(lruvec, lru, page_zonenum(page), thp_nr_pages(page));
- list_add_tail(&page->lru, &lruvec->lists[lru]);
+static __always_inline
+void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
+{
+ list_del(&folio->lru);
+ update_lru_size(lruvec, folio_lru_list(folio), folio_zonenum(folio),
+ -folio_nr_pages(folio));
}
static __always_inline void del_page_from_lru_list(struct page *page,
struct lruvec *lruvec)
{
- list_del(&page->lru);
- update_lru_size(lruvec, page_lru(page), page_zonenum(page),
- -thp_nr_pages(page));
+ lruvec_del_folio(lruvec, page_folio(page));
}
#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7f8ee09c711f..82dab23205c3 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -239,6 +239,72 @@ struct page {
#endif
} _struct_page_alignment;
+/**
+ * struct folio - Represents a contiguous set of bytes.
+ * @flags: Identical to the page flags.
+ * @lru: Least Recently Used list; tracks how recently this folio was used.
+ * @mapping: The file this page belongs to, or refers to the anon_vma for
+ * anonymous memory.
+ * @index: Offset within the file, in units of pages. For anonymous memory,
+ * this is the index from the beginning of the mmap.
+ * @private: Filesystem per-folio data (see folio_attach_private()).
+ * Used for swp_entry_t if folio_test_swapcache().
+ * @_mapcount: Do not access this member directly. Use folio_mapcount() to
+ * find out how many times this folio is mapped by userspace.
+ * @_refcount: Do not access this member directly. Use folio_ref_count()
+ * to find how many references there are to this folio.
+ * @memcg_data: Memory Control Group data.
+ *
+ * A folio is a physically, virtually and logically contiguous set
+ * of bytes. It is a power-of-two in size, and it is aligned to that
+ * same power-of-two. It is at least as large as %PAGE_SIZE. If it is
+ * in the page cache, it is at a file offset which is a multiple of that
+ * power-of-two. It may be mapped into userspace at an address which is
+ * at an arbitrary page offset, but its kernel virtual address is aligned
+ * to its size.
+ */
+struct folio {
+ /* private: don't document the anon union */
+ union {
+ struct {
+ /* public: */
+ unsigned long flags;
+ struct list_head lru;
+ struct address_space *mapping;
+ pgoff_t index;
+ void *private;
+ atomic_t _mapcount;
+ atomic_t _refcount;
+#ifdef CONFIG_MEMCG
+ unsigned long memcg_data;
+#endif
+ /* private: the union with struct page is transitional */
+ };
+ struct page page;
+ };
+};
+
+static_assert(sizeof(struct page) == sizeof(struct folio));
+#define FOLIO_MATCH(pg, fl) \
+ static_assert(offsetof(struct page, pg) == offsetof(struct folio, fl))
+FOLIO_MATCH(flags, flags);
+FOLIO_MATCH(lru, lru);
+FOLIO_MATCH(compound_head, lru);
+FOLIO_MATCH(index, index);
+FOLIO_MATCH(private, private);
+FOLIO_MATCH(_mapcount, _mapcount);
+FOLIO_MATCH(_refcount, _refcount);
+#ifdef CONFIG_MEMCG
+FOLIO_MATCH(memcg_data, memcg_data);
+#endif
+#undef FOLIO_MATCH
+
+static inline atomic_t *folio_mapcount_ptr(struct folio *folio)
+{
+ struct page *tail = &folio->page + 1;
+ return &tail->compound_mapcount;
+}
+
static inline atomic_t *compound_mapcount_ptr(struct page *page)
{
return &page[1].compound_mapcount;
@@ -257,6 +323,12 @@ static inline atomic_t *compound_pincount_ptr(struct page *page)
#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK)
#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+/*
+ * page_private can be used on tail pages. However, PagePrivate is only
+ * checked by the VM on the head page. So page_private on the tail pages
+ * should be used for data that's ancillary to the head page (eg attaching
+ * buffer heads to tail pages after attaching buffer heads to the head page)
+ */
#define page_private(page) ((page)->private)
static inline void set_page_private(struct page *page, unsigned long private)
@@ -264,6 +336,11 @@ static inline void set_page_private(struct page *page, unsigned long private)
page->private = private;
}
+static inline void *folio_get_private(struct folio *folio)
+{
+ return folio->private;
+}
+
struct page_frag_cache {
void * va;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 0c0c9a0fdf57..52eae8c45b8d 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -15,7 +15,7 @@
#include <linux/mmc/card.h>
#include <linux/mmc/pm.h>
#include <linux/dma-direction.h>
-#include <linux/keyslot-manager.h>
+#include <linux/blk-crypto-profile.h>
struct mmc_ios {
unsigned int clock; /* clock rate */
@@ -492,7 +492,7 @@ struct mmc_host {
/* Inline encryption support */
#ifdef CONFIG_MMC_CRYPTO
- struct blk_keyslot_manager ksm;
+ struct blk_crypto_profile crypto_profile;
#endif
/* Host Software Queue support */
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 1935d4c72d10..d7285f8148a3 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -22,6 +22,13 @@ void dump_mm(const struct mm_struct *mm);
BUG(); \
} \
} while (0)
+#define VM_BUG_ON_FOLIO(cond, folio) \
+ do { \
+ if (unlikely(cond)) { \
+ dump_page(&folio->page, "VM_BUG_ON_FOLIO(" __stringify(cond)")");\
+ BUG(); \
+ } \
+ } while (0)
#define VM_BUG_ON_VMA(cond, vma) \
do { \
if (unlikely(cond)) { \
@@ -47,6 +54,17 @@ void dump_mm(const struct mm_struct *mm);
} \
unlikely(__ret_warn_once); \
})
+#define VM_WARN_ON_ONCE_FOLIO(cond, folio) ({ \
+ static bool __section(".data.once") __warned; \
+ int __ret_warn_once = !!(cond); \
+ \
+ if (unlikely(__ret_warn_once && !__warned)) { \
+ dump_page(&folio->page, "VM_WARN_ON_ONCE_FOLIO(" __stringify(cond)")");\
+ __warned = true; \
+ WARN_ON(1); \
+ } \
+ unlikely(__ret_warn_once); \
+})
#define VM_WARN_ON(cond) (void)WARN_ON(cond)
#define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
@@ -55,11 +73,13 @@ void dump_mm(const struct mm_struct *mm);
#else
#define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond)
+#define VM_BUG_ON_FOLIO(cond, folio) VM_BUG_ON(cond)
#define VM_BUG_ON_VMA(cond, vma) VM_BUG_ON(cond)
#define VM_BUG_ON_MM(cond, mm) VM_BUG_ON(cond)
#define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ON_ONCE_PAGE(cond, page) BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_FOLIO(cond, folio) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
#define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
#endif
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 5d6a4158a9a6..12c4177f7703 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -22,6 +22,7 @@
* Overload PG_private_2 to give us PG_fscache - this is used to indicate that
* a page is currently backed by a local disk cache
*/
+#define folio_test_fscache(folio) folio_test_private_2(folio)
#define PageFsCache(page) PagePrivate2((page))
#define SetPageFsCache(page) SetPagePrivate2((page))
#define ClearPageFsCache(page) ClearPagePrivate2((page))
@@ -29,60 +30,80 @@
#define TestClearPageFsCache(page) TestClearPagePrivate2((page))
/**
- * set_page_fscache - Set PG_fscache on a page and take a ref
- * @page: The page.
+ * folio_start_fscache - Start an fscache write on a folio.
+ * @folio: The folio.
*
- * Set the PG_fscache (PG_private_2) flag on a page and take the reference
- * needed for the VM to handle its lifetime correctly. This sets the flag and
- * takes the reference unconditionally, so care must be taken not to set the
- * flag again if it's already set.
+ * Call this function before writing a folio to a local cache. Starting a
+ * second write before the first one finishes is not allowed.
*/
-static inline void set_page_fscache(struct page *page)
+static inline void folio_start_fscache(struct folio *folio)
{
- set_page_private_2(page);
+ VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio);
+ folio_get(folio);
+ folio_set_private_2(folio);
}
/**
- * end_page_fscache - Clear PG_fscache and release any waiters
- * @page: The page
- *
- * Clear the PG_fscache (PG_private_2) bit on a page and wake up any sleepers
- * waiting for this. The page ref held for PG_private_2 being set is released.
+ * folio_end_fscache - End an fscache write on a folio.
+ * @folio: The folio.
*
- * This is, for example, used when a netfs page is being written to a local
- * disk cache, thereby allowing writes to the cache for the same page to be
- * serialised.
+ * Call this function after the folio has been written to the local cache.
+ * This will wake any sleepers waiting on this folio.
*/
-static inline void end_page_fscache(struct page *page)
+static inline void folio_end_fscache(struct folio *folio)
{
- end_page_private_2(page);
+ folio_end_private_2(folio);
}
/**
- * wait_on_page_fscache - Wait for PG_fscache to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_fscache - Wait for an fscache write on this folio to end.
+ * @folio: The folio.
*
- * Wait for PG_fscache (aka PG_private_2) to be cleared on a page.
+ * If this folio is currently being written to a local cache, wait for
+ * the write to finish. Another write may start after this one finishes,
+ * unless the caller holds the folio lock.
*/
-static inline void wait_on_page_fscache(struct page *page)
+static inline void folio_wait_fscache(struct folio *folio)
{
- wait_on_page_private_2(page);
+ folio_wait_private_2(folio);
}
/**
- * wait_on_page_fscache_killable - Wait for PG_fscache to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_fscache_killable - Wait for an fscache write on this folio to end.
+ * @folio: The folio.
*
- * Wait for PG_fscache (aka PG_private_2) to be cleared on a page or until a
- * fatal signal is received by the calling task.
+ * If this folio is currently being written to a local cache, wait
+ * for the write to finish or for a fatal signal to be received.
+ * Another write may start after this one finishes, unless the caller
+ * holds the folio lock.
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
+static inline int folio_wait_fscache_killable(struct folio *folio)
+{
+ return folio_wait_private_2_killable(folio);
+}
+
+static inline void set_page_fscache(struct page *page)
+{
+ folio_start_fscache(page_folio(page));
+}
+
+static inline void end_page_fscache(struct page *page)
+{
+ folio_end_private_2(page_folio(page));
+}
+
+static inline void wait_on_page_fscache(struct page *page)
+{
+ folio_wait_private_2(page_folio(page));
+}
+
static inline int wait_on_page_fscache_killable(struct page *page)
{
- return wait_on_page_private_2_killable(page);
+ return folio_wait_private_2_killable(page_folio(page));
}
enum netfs_read_source {
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index 2a38f2b477a5..cb909edb76c4 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -7,6 +7,7 @@
#define _NVME_FC_DRIVER_H 1
#include <linux/scatterlist.h>
+#include <linux/blk-mq.h>
/*
@@ -497,6 +498,8 @@ struct nvme_fc_port_template {
int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport,
struct nvme_fc_remote_port *rport,
struct nvmefc_ls_rsp *ls_rsp);
+ void (*map_queues)(struct nvme_fc_local_port *localport,
+ struct blk_mq_queue_map *map);
u32 max_hw_queues;
u16 max_sgl_segments;
@@ -779,6 +782,10 @@ struct nvmet_fc_target_port {
* LS received.
* Entrypoint is Mandatory.
*
+ * @map_queues: This functions lets the driver expose the queue mapping
+ * to the block layer.
+ * Entrypoint is Optional.
+ *
* @fcp_op: Called to perform a data transfer or transmit a response.
* The nvmefc_tgt_fcp_req structure is the same LLDD-supplied
* exchange structure specified in the nvmet_fc_rcv_fcp_req() call
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 3ec8e50efa16..4dd7e6fe92fb 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,6 +6,8 @@
#ifndef _LINUX_NVME_RDMA_H
#define _LINUX_NVME_RDMA_H
+#define NVME_RDMA_MAX_QUEUE_SIZE 128
+
enum nvme_rdma_cm_fmt {
NVME_RDMA_CM_FMT_1_0 = 0x0,
};
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index b7c4c4130b65..855dd9b3e84b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -27,8 +27,20 @@
#define NVME_NSID_ALL 0xffffffff
enum nvme_subsys_type {
- NVME_NQN_DISC = 1, /* Discovery type target subsystem */
- NVME_NQN_NVME = 2, /* NVME type target subsystem */
+ /* Referral to another discovery type target subsystem */
+ NVME_NQN_DISC = 1,
+
+ /* NVME type target subsystem */
+ NVME_NQN_NVME = 2,
+
+ /* Current discovery type target subsystem */
+ NVME_NQN_CURR = 3,
+};
+
+enum nvme_ctrl_type {
+ NVME_CTRL_IO = 1, /* I/O controller */
+ NVME_CTRL_DISC = 2, /* Discovery controller */
+ NVME_CTRL_ADMIN = 3, /* Administrative controller */
};
/* Address Family codes for Discovery Log Page entry ADRFAM field */
@@ -244,7 +256,9 @@ struct nvme_id_ctrl {
__le32 rtd3e;
__le32 oaes;
__le32 ctratt;
- __u8 rsvd100[28];
+ __u8 rsvd100[11];
+ __u8 cntrltype;
+ __u8 fguid[16];
__le16 crdt1;
__le16 crdt2;
__le16 crdt3;
@@ -312,6 +326,7 @@ struct nvme_id_ctrl {
};
enum {
+ NVME_CTRL_CMIC_MULTI_PORT = 1 << 0,
NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1,
NVME_CTRL_CMIC_ANA = 1 << 3,
NVME_CTRL_ONCS_COMPARE = 1 << 0,
@@ -1303,6 +1318,12 @@ struct nvmf_common_command {
#define MAX_DISC_LOGS 255
+/* Discovery log page entry flags (EFLAGS): */
+enum {
+ NVME_DISC_EFLAGS_EPCSD = (1 << 1),
+ NVME_DISC_EFLAGS_DUPRETINFO = (1 << 0),
+};
+
/* Discovery log page entry */
struct nvmf_disc_rsp_page_entry {
__u8 trtype;
@@ -1312,7 +1333,8 @@ struct nvmf_disc_rsp_page_entry {
__le16 portid;
__le16 cntlid;
__le16 asqsz;
- __u8 resv8[22];
+ __le16 eflags;
+ __u8 resv10[20];
char trsvcid[NVMF_TRSVCID_SIZE];
__u8 resv64[192];
char subnqn[NVMF_NQN_FIELD_LEN];
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a558d67ee86f..d8623d6e1141 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -143,6 +143,8 @@ enum pageflags {
#endif
__NR_PAGEFLAGS,
+ PG_readahead = PG_reclaim,
+
/* Filesystems */
PG_checked = PG_owner_priv_1,
@@ -171,6 +173,15 @@ enum pageflags {
/* Compound pages. Stored in first tail page's flags */
PG_double_map = PG_workingset,
+#ifdef CONFIG_MEMORY_FAILURE
+ /*
+ * Compound pages. Stored in first tail page's flags.
+ * Indicates that at least one subpage is hwpoisoned in the
+ * THP.
+ */
+ PG_has_hwpoisoned = PG_mappedtodisk,
+#endif
+
/* non-lru isolated movable page */
PG_isolated = PG_reclaim,
@@ -193,6 +204,34 @@ static inline unsigned long _compound_head(const struct page *page)
#define compound_head(page) ((typeof(page))_compound_head(page))
+/**
+ * page_folio - Converts from page to folio.
+ * @p: The page.
+ *
+ * Every page is part of a folio. This function cannot be called on a
+ * NULL pointer.
+ *
+ * Context: No reference, nor lock is required on @page. If the caller
+ * does not hold a reference, this call may race with a folio split, so
+ * it should re-check the folio still contains this page after gaining
+ * a reference on the folio.
+ * Return: The folio which contains this page.
+ */
+#define page_folio(p) (_Generic((p), \
+ const struct page *: (const struct folio *)_compound_head(p), \
+ struct page *: (struct folio *)_compound_head(p)))
+
+/**
+ * folio_page - Return a page from a folio.
+ * @folio: The folio.
+ * @n: The page number to return.
+ *
+ * @n is relative to the start of the folio. This function does not
+ * check that the page number lies within @folio; the caller is presumed
+ * to have a reference to the page.
+ */
+#define folio_page(folio, n) nth_page(&(folio)->page, n)
+
static __always_inline int PageTail(struct page *page)
{
return READ_ONCE(page->compound_head) & 1;
@@ -217,6 +256,15 @@ static inline void page_init_poison(struct page *page, size_t size)
}
#endif
+static unsigned long *folio_flags(struct folio *folio, unsigned n)
+{
+ struct page *page = &folio->page;
+
+ VM_BUG_ON_PGFLAGS(PageTail(page), page);
+ VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
+ return &page[n].flags;
+}
+
/*
* Page flags policies wrt compound pages
*
@@ -261,36 +309,64 @@ static inline void page_init_poison(struct page *page, size_t size)
VM_BUG_ON_PGFLAGS(!PageHead(page), page); \
PF_POISONED_CHECK(&page[1]); })
+/* Which page is the flag stored in */
+#define FOLIO_PF_ANY 0
+#define FOLIO_PF_HEAD 0
+#define FOLIO_PF_ONLY_HEAD 0
+#define FOLIO_PF_NO_TAIL 0
+#define FOLIO_PF_NO_COMPOUND 0
+#define FOLIO_PF_SECOND 1
+
/*
* Macros to create function definitions for page flags
*/
#define TESTPAGEFLAG(uname, lname, policy) \
+static __always_inline bool folio_test_##lname(struct folio *folio) \
+{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int Page##uname(struct page *page) \
- { return test_bit(PG_##lname, &policy(page, 0)->flags); }
+{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
#define SETPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void folio_set_##lname(struct folio *folio) \
+{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void SetPage##uname(struct page *page) \
- { set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ set_bit(PG_##lname, &policy(page, 1)->flags); }
#define CLEARPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void folio_clear_##lname(struct folio *folio) \
+{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void ClearPage##uname(struct page *page) \
- { clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define __SETPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void __folio_set_##lname(struct folio *folio) \
+{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void __SetPage##uname(struct page *page) \
- { __set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
#define __CLEARPAGEFLAG(uname, lname, policy) \
+static __always_inline \
+void __folio_clear_##lname(struct folio *folio) \
+{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline void __ClearPage##uname(struct page *page) \
- { __clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTSETFLAG(uname, lname, policy) \
+static __always_inline \
+bool folio_test_set_##lname(struct folio *folio) \
+{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int TestSetPage##uname(struct page *page) \
- { return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
#define TESTCLEARFLAG(uname, lname, policy) \
+static __always_inline \
+bool folio_test_clear_##lname(struct folio *folio) \
+{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
static __always_inline int TestClearPage##uname(struct page *page) \
- { return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
#define PAGEFLAG(uname, lname, policy) \
TESTPAGEFLAG(uname, lname, policy) \
@@ -306,29 +382,37 @@ static __always_inline int TestClearPage##uname(struct page *page) \
TESTSETFLAG(uname, lname, policy) \
TESTCLEARFLAG(uname, lname, policy)
-#define TESTPAGEFLAG_FALSE(uname) \
+#define TESTPAGEFLAG_FALSE(uname, lname) \
+static inline bool folio_test_##lname(const struct folio *folio) { return 0; } \
static inline int Page##uname(const struct page *page) { return 0; }
-#define SETPAGEFLAG_NOOP(uname) \
+#define SETPAGEFLAG_NOOP(uname, lname) \
+static inline void folio_set_##lname(struct folio *folio) { } \
static inline void SetPage##uname(struct page *page) { }
-#define CLEARPAGEFLAG_NOOP(uname) \
+#define CLEARPAGEFLAG_NOOP(uname, lname) \
+static inline void folio_clear_##lname(struct folio *folio) { } \
static inline void ClearPage##uname(struct page *page) { }
-#define __CLEARPAGEFLAG_NOOP(uname) \
+#define __CLEARPAGEFLAG_NOOP(uname, lname) \
+static inline void __folio_clear_##lname(struct folio *folio) { } \
static inline void __ClearPage##uname(struct page *page) { }
-#define TESTSETFLAG_FALSE(uname) \
+#define TESTSETFLAG_FALSE(uname, lname) \
+static inline bool folio_test_set_##lname(struct folio *folio) \
+{ return 0; } \
static inline int TestSetPage##uname(struct page *page) { return 0; }
-#define TESTCLEARFLAG_FALSE(uname) \
+#define TESTCLEARFLAG_FALSE(uname, lname) \
+static inline bool folio_test_clear_##lname(struct folio *folio) \
+{ return 0; } \
static inline int TestClearPage##uname(struct page *page) { return 0; }
-#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \
- SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname)
+#define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname) \
+ SETPAGEFLAG_NOOP(uname, lname) CLEARPAGEFLAG_NOOP(uname, lname)
-#define TESTSCFLAG_FALSE(uname) \
- TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname)
+#define TESTSCFLAG_FALSE(uname, lname) \
+ TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname)
__PAGEFLAG(Locked, locked, PF_NO_TAIL)
PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD) __CLEARPAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
@@ -384,8 +468,8 @@ PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
/* PG_readahead is only used for reads; PG_reclaim is only for writes */
PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
-PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
- TESTCLEARFLAG(Readahead, reclaim, PF_NO_COMPOUND)
+PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND)
+ TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND)
#ifdef CONFIG_HIGHMEM
/*
@@ -394,22 +478,25 @@ PAGEFLAG(Readahead, reclaim, PF_NO_COMPOUND)
*/
#define PageHighMem(__p) is_highmem_idx(page_zonenum(__p))
#else
-PAGEFLAG_FALSE(HighMem)
+PAGEFLAG_FALSE(HighMem, highmem)
#endif
#ifdef CONFIG_SWAP
-static __always_inline int PageSwapCache(struct page *page)
+static __always_inline bool folio_test_swapcache(struct folio *folio)
{
-#ifdef CONFIG_THP_SWAP
- page = compound_head(page);
-#endif
- return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
+ return folio_test_swapbacked(folio) &&
+ test_bit(PG_swapcache, folio_flags(folio, 0));
+}
+static __always_inline bool PageSwapCache(struct page *page)
+{
+ return folio_test_swapcache(page_folio(page));
}
+
SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
#else
-PAGEFLAG_FALSE(SwapCache)
+PAGEFLAG_FALSE(SwapCache, swapcache)
#endif
PAGEFLAG(Unevictable, unevictable, PF_HEAD)
@@ -421,14 +508,14 @@ PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
__CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
#else
-PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked)
- TESTSCFLAG_FALSE(Mlocked)
+PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked)
+ TESTSCFLAG_FALSE(Mlocked, mlocked)
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
#else
-PAGEFLAG_FALSE(Uncached)
+PAGEFLAG_FALSE(Uncached, uncached)
#endif
#ifdef CONFIG_MEMORY_FAILURE
@@ -437,7 +524,7 @@ TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
#define __PG_HWPOISON (1UL << PG_hwpoison)
extern bool take_page_off_buddy(struct page *page);
#else
-PAGEFLAG_FALSE(HWPoison)
+PAGEFLAG_FALSE(HWPoison, hwpoison)
#define __PG_HWPOISON 0
#endif
@@ -451,7 +538,7 @@ PAGEFLAG(Idle, idle, PF_ANY)
#ifdef CONFIG_KASAN_HW_TAGS
PAGEFLAG(SkipKASanPoison, skip_kasan_poison, PF_HEAD)
#else
-PAGEFLAG_FALSE(SkipKASanPoison)
+PAGEFLAG_FALSE(SkipKASanPoison, skip_kasan_poison)
#endif
/*
@@ -489,10 +576,14 @@ static __always_inline int PageMappingFlags(struct page *page)
return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
}
-static __always_inline int PageAnon(struct page *page)
+static __always_inline bool folio_test_anon(struct folio *folio)
+{
+ return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
+}
+
+static __always_inline bool PageAnon(struct page *page)
{
- page = compound_head(page);
- return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
+ return folio_test_anon(page_folio(page));
}
static __always_inline int __PageMovable(struct page *page)
@@ -508,30 +599,32 @@ static __always_inline int __PageMovable(struct page *page)
* is found in VM_MERGEABLE vmas. It's a PageAnon page, pointing not to any
* anon_vma, but to that page's node of the stable tree.
*/
-static __always_inline int PageKsm(struct page *page)
+static __always_inline bool folio_test_ksm(struct folio *folio)
{
- page = compound_head(page);
- return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
+ return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
PAGE_MAPPING_KSM;
}
+
+static __always_inline bool PageKsm(struct page *page)
+{
+ return folio_test_ksm(page_folio(page));
+}
#else
-TESTPAGEFLAG_FALSE(Ksm)
+TESTPAGEFLAG_FALSE(Ksm, ksm)
#endif
u64 stable_page_flags(struct page *page);
-static inline int PageUptodate(struct page *page)
+static inline bool folio_test_uptodate(struct folio *folio)
{
- int ret;
- page = compound_head(page);
- ret = test_bit(PG_uptodate, &(page)->flags);
+ bool ret = test_bit(PG_uptodate, folio_flags(folio, 0));
/*
- * Must ensure that the data we read out of the page is loaded
- * _after_ we've loaded page->flags to check for PageUptodate.
- * We can skip the barrier if the page is not uptodate, because
+ * Must ensure that the data we read out of the folio is loaded
+ * _after_ we've loaded folio->flags to check the uptodate bit.
+ * We can skip the barrier if the folio is not uptodate, because
* we wouldn't be reading anything from it.
*
- * See SetPageUptodate() for the other side of the story.
+ * See folio_mark_uptodate() for the other side of the story.
*/
if (ret)
smp_rmb();
@@ -539,47 +632,71 @@ static inline int PageUptodate(struct page *page)
return ret;
}
-static __always_inline void __SetPageUptodate(struct page *page)
+static inline int PageUptodate(struct page *page)
+{
+ return folio_test_uptodate(page_folio(page));
+}
+
+static __always_inline void __folio_mark_uptodate(struct folio *folio)
{
- VM_BUG_ON_PAGE(PageTail(page), page);
smp_wmb();
- __set_bit(PG_uptodate, &page->flags);
+ __set_bit(PG_uptodate, folio_flags(folio, 0));
}
-static __always_inline void SetPageUptodate(struct page *page)
+static __always_inline void folio_mark_uptodate(struct folio *folio)
{
- VM_BUG_ON_PAGE(PageTail(page), page);
/*
* Memory barrier must be issued before setting the PG_uptodate bit,
- * so that all previous stores issued in order to bring the page
- * uptodate are actually visible before PageUptodate becomes true.
+ * so that all previous stores issued in order to bring the folio
+ * uptodate are actually visible before folio_test_uptodate becomes true.
*/
smp_wmb();
- set_bit(PG_uptodate, &page->flags);
+ set_bit(PG_uptodate, folio_flags(folio, 0));
+}
+
+static __always_inline void __SetPageUptodate(struct page *page)
+{
+ __folio_mark_uptodate((struct folio *)page);
+}
+
+static __always_inline void SetPageUptodate(struct page *page)
+{
+ folio_mark_uptodate((struct folio *)page);
}
CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
-int test_clear_page_writeback(struct page *page);
-int __test_set_page_writeback(struct page *page, bool keep_write);
+bool __folio_start_writeback(struct folio *folio, bool keep_write);
+bool set_page_writeback(struct page *page);
-#define test_set_page_writeback(page) \
- __test_set_page_writeback(page, false)
-#define test_set_page_writeback_keepwrite(page) \
- __test_set_page_writeback(page, true)
+#define folio_start_writeback(folio) \
+ __folio_start_writeback(folio, false)
+#define folio_start_writeback_keepwrite(folio) \
+ __folio_start_writeback(folio, true)
-static inline void set_page_writeback(struct page *page)
+static inline void set_page_writeback_keepwrite(struct page *page)
{
- test_set_page_writeback(page);
+ folio_start_writeback_keepwrite(page_folio(page));
}
-static inline void set_page_writeback_keepwrite(struct page *page)
+static inline bool test_set_page_writeback(struct page *page)
{
- test_set_page_writeback_keepwrite(page);
+ return set_page_writeback(page);
}
__PAGEFLAG(Head, head, PF_ANY) CLEARPAGEFLAG(Head, head, PF_ANY)
+/* Whether there are one or multiple pages in a folio */
+static inline bool folio_test_single(struct folio *folio)
+{
+ return !folio_test_head(folio);
+}
+
+static inline bool folio_test_multi(struct folio *folio)
+{
+ return folio_test_head(folio);
+}
+
static __always_inline void set_compound_head(struct page *page, struct page *head)
{
WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
@@ -603,12 +720,15 @@ static inline void ClearPageCompound(struct page *page)
#ifdef CONFIG_HUGETLB_PAGE
int PageHuge(struct page *page);
int PageHeadHuge(struct page *page);
+static inline bool folio_test_hugetlb(struct folio *folio)
+{
+ return PageHeadHuge(&folio->page);
+}
#else
-TESTPAGEFLAG_FALSE(Huge)
-TESTPAGEFLAG_FALSE(HeadHuge)
+TESTPAGEFLAG_FALSE(Huge, hugetlb)
+TESTPAGEFLAG_FALSE(HeadHuge, headhuge)
#endif
-
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/*
* PageHuge() only returns true for hugetlbfs pages, but not for
@@ -624,6 +744,11 @@ static inline int PageTransHuge(struct page *page)
return PageHead(page);
}
+static inline bool folio_test_transhuge(struct folio *folio)
+{
+ return folio_test_head(folio);
+}
+
/*
* PageTransCompound returns true for both transparent huge pages
* and hugetlbfs pages, so it should only be called when it's known
@@ -660,12 +785,26 @@ static inline int PageTransTail(struct page *page)
PAGEFLAG(DoubleMap, double_map, PF_SECOND)
TESTSCFLAG(DoubleMap, double_map, PF_SECOND)
#else
-TESTPAGEFLAG_FALSE(TransHuge)
-TESTPAGEFLAG_FALSE(TransCompound)
-TESTPAGEFLAG_FALSE(TransCompoundMap)
-TESTPAGEFLAG_FALSE(TransTail)
-PAGEFLAG_FALSE(DoubleMap)
- TESTSCFLAG_FALSE(DoubleMap)
+TESTPAGEFLAG_FALSE(TransHuge, transhuge)
+TESTPAGEFLAG_FALSE(TransCompound, transcompound)
+TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap)
+TESTPAGEFLAG_FALSE(TransTail, transtail)
+PAGEFLAG_FALSE(DoubleMap, double_map)
+ TESTSCFLAG_FALSE(DoubleMap, double_map)
+#endif
+
+#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+/*
+ * PageHasHWPoisoned indicates that at least one subpage is hwpoisoned in the
+ * compound page.
+ *
+ * This flag is set by hwpoison handler. Cleared by THP split or free page.
+ */
+PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+ TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+#else
+PAGEFLAG_FALSE(HasHWPoisoned)
+ TESTSCFLAG_FALSE(HasHWPoisoned)
#endif
/*
@@ -849,6 +988,11 @@ static inline int page_has_private(struct page *page)
return !!(page->flags & PAGE_FLAGS_PRIVATE);
}
+static inline bool folio_has_private(struct folio *folio)
+{
+ return page_has_private(&folio->page);
+}
+
#undef PF_ANY
#undef PF_HEAD
#undef PF_ONLY_HEAD
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index d8a6aecf99cb..83abf95e9fa7 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -8,46 +8,16 @@
#ifdef CONFIG_PAGE_IDLE_FLAG
-#ifdef CONFIG_64BIT
-static inline bool page_is_young(struct page *page)
-{
- return PageYoung(page);
-}
-
-static inline void set_page_young(struct page *page)
-{
- SetPageYoung(page);
-}
-
-static inline bool test_and_clear_page_young(struct page *page)
-{
- return TestClearPageYoung(page);
-}
-
-static inline bool page_is_idle(struct page *page)
-{
- return PageIdle(page);
-}
-
-static inline void set_page_idle(struct page *page)
-{
- SetPageIdle(page);
-}
-
-static inline void clear_page_idle(struct page *page)
-{
- ClearPageIdle(page);
-}
-#else /* !CONFIG_64BIT */
+#ifndef CONFIG_64BIT
/*
* If there is not enough space to store Idle and Young bits in page flags, use
* page ext flags instead.
*/
extern struct page_ext_operations page_idle_ops;
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -55,9 +25,9 @@ static inline bool page_is_young(struct page *page)
return test_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
@@ -65,9 +35,9 @@ static inline void set_page_young(struct page *page)
set_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -75,9 +45,9 @@ static inline bool test_and_clear_page_young(struct page *page)
return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags);
}
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return false;
@@ -85,9 +55,9 @@ static inline bool page_is_idle(struct page *page)
return test_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
@@ -95,46 +65,75 @@ static inline void set_page_idle(struct page *page)
set_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
{
- struct page_ext *page_ext = lookup_page_ext(page);
+ struct page_ext *page_ext = lookup_page_ext(&folio->page);
if (unlikely(!page_ext))
return;
clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
}
-#endif /* CONFIG_64BIT */
+#endif /* !CONFIG_64BIT */
#else /* !CONFIG_PAGE_IDLE_FLAG */
-static inline bool page_is_young(struct page *page)
+static inline bool folio_test_young(struct folio *folio)
{
return false;
}
-static inline void set_page_young(struct page *page)
+static inline void folio_set_young(struct folio *folio)
{
}
-static inline bool test_and_clear_page_young(struct page *page)
+static inline bool folio_test_clear_young(struct folio *folio)
{
return false;
}
-static inline bool page_is_idle(struct page *page)
+static inline bool folio_test_idle(struct folio *folio)
{
return false;
}
-static inline void set_page_idle(struct page *page)
+static inline void folio_set_idle(struct folio *folio)
{
}
-static inline void clear_page_idle(struct page *page)
+static inline void folio_clear_idle(struct folio *folio)
{
}
#endif /* CONFIG_PAGE_IDLE_FLAG */
+static inline bool page_is_young(struct page *page)
+{
+ return folio_test_young(page_folio(page));
+}
+
+static inline void set_page_young(struct page *page)
+{
+ folio_set_young(page_folio(page));
+}
+
+static inline bool test_and_clear_page_young(struct page *page)
+{
+ return folio_test_clear_young(page_folio(page));
+}
+
+static inline bool page_is_idle(struct page *page)
+{
+ return folio_test_idle(page_folio(page));
+}
+
+static inline void set_page_idle(struct page *page)
+{
+ folio_set_idle(page_folio(page));
+}
+
+static inline void clear_page_idle(struct page *page)
+{
+ folio_clear_idle(page_folio(page));
+}
#endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 719bfe5108c5..43c638c51c1f 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -12,7 +12,7 @@ extern void __reset_page_owner(struct page *page, unsigned int order);
extern void __set_page_owner(struct page *page,
unsigned int order, gfp_t gfp_mask);
extern void __split_page_owner(struct page *page, unsigned int nr);
-extern void __copy_page_owner(struct page *oldpage, struct page *newpage);
+extern void __folio_copy_owner(struct folio *newfolio, struct folio *old);
extern void __set_page_owner_migrate_reason(struct page *page, int reason);
extern void __dump_page_owner(const struct page *page);
extern void pagetypeinfo_showmixedcount_print(struct seq_file *m,
@@ -36,10 +36,10 @@ static inline void split_page_owner(struct page *page, unsigned int nr)
if (static_branch_unlikely(&page_owner_inited))
__split_page_owner(page, nr);
}
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *old)
{
if (static_branch_unlikely(&page_owner_inited))
- __copy_page_owner(oldpage, newpage);
+ __folio_copy_owner(newfolio, old);
}
static inline void set_page_owner_migrate_reason(struct page *page, int reason)
{
@@ -63,7 +63,7 @@ static inline void split_page_owner(struct page *page,
unsigned int order)
{
}
-static inline void copy_page_owner(struct page *oldpage, struct page *newpage)
+static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio)
{
}
static inline void set_page_owner_migrate_reason(struct page *page, int reason)
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index 7ad46f45df39..2e677e6ad09f 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -67,9 +67,31 @@ static inline int page_ref_count(const struct page *page)
return atomic_read(&page->_refcount);
}
+/**
+ * folio_ref_count - The reference count on this folio.
+ * @folio: The folio.
+ *
+ * The refcount is usually incremented by calls to folio_get() and
+ * decremented by calls to folio_put(). Some typical users of the
+ * folio refcount:
+ *
+ * - Each reference from a page table
+ * - The page cache
+ * - Filesystem private data
+ * - The LRU list
+ * - Pipes
+ * - Direct IO which references this page in the process address space
+ *
+ * Return: The number of references to this folio.
+ */
+static inline int folio_ref_count(const struct folio *folio)
+{
+ return page_ref_count(&folio->page);
+}
+
static inline int page_count(const struct page *page)
{
- return atomic_read(&compound_head(page)->_refcount);
+ return folio_ref_count(page_folio(page));
}
static inline void set_page_count(struct page *page, int v)
@@ -79,6 +101,11 @@ static inline void set_page_count(struct page *page, int v)
__page_ref_set(page, v);
}
+static inline void folio_set_count(struct folio *folio, int v)
+{
+ set_page_count(&folio->page, v);
+}
+
/*
* Setup the page count before being freed into the page allocator for
* the first time (boot or memory hotplug)
@@ -95,6 +122,11 @@ static inline void page_ref_add(struct page *page, int nr)
__page_ref_mod(page, nr);
}
+static inline void folio_ref_add(struct folio *folio, int nr)
+{
+ page_ref_add(&folio->page, nr);
+}
+
static inline void page_ref_sub(struct page *page, int nr)
{
atomic_sub(nr, &page->_refcount);
@@ -102,6 +134,11 @@ static inline void page_ref_sub(struct page *page, int nr)
__page_ref_mod(page, -nr);
}
+static inline void folio_ref_sub(struct folio *folio, int nr)
+{
+ page_ref_sub(&folio->page, nr);
+}
+
static inline int page_ref_sub_return(struct page *page, int nr)
{
int ret = atomic_sub_return(nr, &page->_refcount);
@@ -111,6 +148,11 @@ static inline int page_ref_sub_return(struct page *page, int nr)
return ret;
}
+static inline int folio_ref_sub_return(struct folio *folio, int nr)
+{
+ return page_ref_sub_return(&folio->page, nr);
+}
+
static inline void page_ref_inc(struct page *page)
{
atomic_inc(&page->_refcount);
@@ -118,6 +160,11 @@ static inline void page_ref_inc(struct page *page)
__page_ref_mod(page, 1);
}
+static inline void folio_ref_inc(struct folio *folio)
+{
+ page_ref_inc(&folio->page);
+}
+
static inline void page_ref_dec(struct page *page)
{
atomic_dec(&page->_refcount);
@@ -125,6 +172,11 @@ static inline void page_ref_dec(struct page *page)
__page_ref_mod(page, -1);
}
+static inline void folio_ref_dec(struct folio *folio)
+{
+ page_ref_dec(&folio->page);
+}
+
static inline int page_ref_sub_and_test(struct page *page, int nr)
{
int ret = atomic_sub_and_test(nr, &page->_refcount);
@@ -134,6 +186,11 @@ static inline int page_ref_sub_and_test(struct page *page, int nr)
return ret;
}
+static inline int folio_ref_sub_and_test(struct folio *folio, int nr)
+{
+ return page_ref_sub_and_test(&folio->page, nr);
+}
+
static inline int page_ref_inc_return(struct page *page)
{
int ret = atomic_inc_return(&page->_refcount);
@@ -143,6 +200,11 @@ static inline int page_ref_inc_return(struct page *page)
return ret;
}
+static inline int folio_ref_inc_return(struct folio *folio)
+{
+ return page_ref_inc_return(&folio->page);
+}
+
static inline int page_ref_dec_and_test(struct page *page)
{
int ret = atomic_dec_and_test(&page->_refcount);
@@ -152,6 +214,11 @@ static inline int page_ref_dec_and_test(struct page *page)
return ret;
}
+static inline int folio_ref_dec_and_test(struct folio *folio)
+{
+ return page_ref_dec_and_test(&folio->page);
+}
+
static inline int page_ref_dec_return(struct page *page)
{
int ret = atomic_dec_return(&page->_refcount);
@@ -161,15 +228,91 @@ static inline int page_ref_dec_return(struct page *page)
return ret;
}
-static inline int page_ref_add_unless(struct page *page, int nr, int u)
+static inline int folio_ref_dec_return(struct folio *folio)
+{
+ return page_ref_dec_return(&folio->page);
+}
+
+static inline bool page_ref_add_unless(struct page *page, int nr, int u)
{
- int ret = atomic_add_unless(&page->_refcount, nr, u);
+ bool ret = atomic_add_unless(&page->_refcount, nr, u);
if (page_ref_tracepoint_active(page_ref_mod_unless))
__page_ref_mod_unless(page, nr, ret);
return ret;
}
+static inline bool folio_ref_add_unless(struct folio *folio, int nr, int u)
+{
+ return page_ref_add_unless(&folio->page, nr, u);
+}
+
+/**
+ * folio_try_get - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * If you do not already have a reference to a folio, you can attempt to
+ * get one using this function. It may fail if, for example, the folio
+ * has been freed since you found a pointer to it, or it is frozen for
+ * the purposes of splitting or migration.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get(struct folio *folio)
+{
+ return folio_ref_add_unless(folio, 1, 0);
+}
+
+static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
+{
+#ifdef CONFIG_TINY_RCU
+ /*
+ * The caller guarantees the folio will not be freed from interrupt
+ * context, so (on !SMP) we only need preemption to be disabled
+ * and TINY_RCU does that for us.
+ */
+# ifdef CONFIG_PREEMPT_COUNT
+ VM_BUG_ON(!in_atomic() && !irqs_disabled());
+# endif
+ VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+ folio_ref_add(folio, count);
+#else
+ if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
+ /* Either the folio has been freed, or will be freed. */
+ return false;
+ }
+#endif
+ return true;
+}
+
+/**
+ * folio_try_get_rcu - Attempt to increase the refcount on a folio.
+ * @folio: The folio.
+ *
+ * This is a version of folio_try_get() optimised for non-SMP kernels.
+ * If you are still holding the rcu_read_lock() after looking up the
+ * page and know that the page cannot have its refcount decreased to
+ * zero in interrupt context, you can use this instead of folio_try_get().
+ *
+ * Example users include get_user_pages_fast() (as pages are not unmapped
+ * from interrupt context) and the page cache lookups (as pages are not
+ * truncated from interrupt context). We also know that pages are not
+ * frozen in interrupt context for the purposes of splitting or migration.
+ *
+ * You can also use this function if you're holding a lock that prevents
+ * pages being frozen & removed; eg the i_pages lock for the page cache
+ * or the mmap_sem or page table lock for page tables. In this case,
+ * it will always succeed, and you could have used a plain folio_get(),
+ * but it's sometimes more convenient to have a common function called
+ * from both locked and RCU-protected contexts.
+ *
+ * Return: True if the reference count was successfully incremented.
+ */
+static inline bool folio_try_get_rcu(struct folio *folio)
+{
+ return folio_ref_try_add_rcu(folio, 1);
+}
+
static inline int page_ref_freeze(struct page *page, int count)
{
int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count);
@@ -179,6 +322,11 @@ static inline int page_ref_freeze(struct page *page, int count)
return ret;
}
+static inline int folio_ref_freeze(struct folio *folio, int count)
+{
+ return page_ref_freeze(&folio->page, count);
+}
+
static inline void page_ref_unfreeze(struct page *page, int count)
{
VM_BUG_ON_PAGE(page_count(page) != 0, page);
@@ -189,4 +337,8 @@ static inline void page_ref_unfreeze(struct page *page, int count)
__page_ref_unfreeze(page, count);
}
+static inline void folio_ref_unfreeze(struct folio *folio, int count)
+{
+ page_ref_unfreeze(&folio->page, count);
+}
#endif
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 62db6b0176b9..013cdc90f5fd 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -162,149 +162,119 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping)
void release_pages(struct page **pages, int nr);
-/*
- * For file cache pages, return the address_space, otherwise return NULL
+struct address_space *page_mapping(struct page *);
+struct address_space *folio_mapping(struct folio *);
+struct address_space *swapcache_mapping(struct folio *);
+
+/**
+ * folio_file_mapping - Find the mapping this folio belongs to.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the mapping that this
+ * page belongs to. Folios in the swap cache return the mapping of the
+ * swap file or swap device where the data is stored. This is different
+ * from the mapping returned by folio_mapping(). The only reason to
+ * use it is if, like NFS, you return 0 from ->activate_swapfile.
+ *
+ * Do not call this for folios which aren't in the page cache or swap cache.
*/
-static inline struct address_space *page_mapping_file(struct page *page)
+static inline struct address_space *folio_file_mapping(struct folio *folio)
{
- if (unlikely(PageSwapCache(page)))
- return NULL;
- return page_mapping(page);
+ if (unlikely(folio_test_swapcache(folio)))
+ return swapcache_mapping(folio);
+
+ return folio->mapping;
+}
+
+static inline struct address_space *page_file_mapping(struct page *page)
+{
+ return folio_file_mapping(page_folio(page));
}
/*
- * speculatively take a reference to a page.
- * If the page is free (_refcount == 0), then _refcount is untouched, and 0
- * is returned. Otherwise, _refcount is incremented by 1 and 1 is returned.
- *
- * This function must be called inside the same rcu_read_lock() section as has
- * been used to lookup the page in the pagecache radix-tree (or page table):
- * this allows allocators to use a synchronize_rcu() to stabilize _refcount.
- *
- * Unless an RCU grace period has passed, the count of all pages coming out
- * of the allocator must be considered unstable. page_count may return higher
- * than expected, and put_page must be able to do the right thing when the
- * page has been finished with, no matter what it is subsequently allocated
- * for (because put_page is what is used here to drop an invalid speculative
- * reference).
- *
- * This is the interesting part of the lockless pagecache (and lockless
- * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page)
- * has the following pattern:
- * 1. find page in radix tree
- * 2. conditionally increment refcount
- * 3. check the page is still in pagecache (if no, goto 1)
- *
- * Remove-side that cares about stability of _refcount (eg. reclaim) has the
- * following (with the i_pages lock held):
- * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg)
- * B. remove page from pagecache
- * C. free the page
- *
- * There are 2 critical interleavings that matter:
- * - 2 runs before A: in this case, A sees elevated refcount and bails out
- * - A runs before 2: in this case, 2 sees zero refcount and retries;
- * subsequently, B will complete and 1 will find no page, causing the
- * lookup to return NULL.
- *
- * It is possible that between 1 and 2, the page is removed then the exact same
- * page is inserted into the same position in pagecache. That's OK: the
- * old find_get_page using a lock could equally have run before or after
- * such a re-insertion, depending on order that locks are granted.
- *
- * Lookups racing against pagecache insertion isn't a big problem: either 1
- * will find the page or it will not. Likewise, the old find_get_page could run
- * either before the insertion or afterwards, depending on timing.
+ * For file cache pages, return the address_space, otherwise return NULL
*/
-static inline int __page_cache_add_speculative(struct page *page, int count)
+static inline struct address_space *page_mapping_file(struct page *page)
{
-#ifdef CONFIG_TINY_RCU
-# ifdef CONFIG_PREEMPT_COUNT
- VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
- /*
- * Preempt must be disabled here - we rely on rcu_read_lock doing
- * this for us.
- *
- * Pagecache won't be truncated from interrupt context, so if we have
- * found a page in the radix tree here, we have pinned its refcount by
- * disabling preempt, and hence no need for the "speculative get" that
- * SMP requires.
- */
- VM_BUG_ON_PAGE(page_count(page) == 0, page);
- page_ref_add(page, count);
+ struct folio *folio = page_folio(page);
-#else
- if (unlikely(!page_ref_add_unless(page, count, 0))) {
- /*
- * Either the page has been freed, or will be freed.
- * In either case, retry here and the caller should
- * do the right thing (see comments above).
- */
- return 0;
- }
-#endif
- VM_BUG_ON_PAGE(PageTail(page), page);
-
- return 1;
+ if (unlikely(folio_test_swapcache(folio)))
+ return NULL;
+ return folio_mapping(folio);
}
-static inline int page_cache_get_speculative(struct page *page)
+static inline bool page_cache_add_speculative(struct page *page, int count)
{
- return __page_cache_add_speculative(page, 1);
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ return folio_ref_try_add_rcu((struct folio *)page, count);
}
-static inline int page_cache_add_speculative(struct page *page, int count)
+static inline bool page_cache_get_speculative(struct page *page)
{
- return __page_cache_add_speculative(page, count);
+ return page_cache_add_speculative(page, 1);
}
/**
- * attach_page_private - Attach private data to a page.
- * @page: Page to attach data to.
- * @data: Data to attach to page.
+ * folio_attach_private - Attach private data to a folio.
+ * @folio: Folio to attach data to.
+ * @data: Data to attach to folio.
*
- * Attaching private data to a page increments the page's reference count.
- * The data must be detached before the page will be freed.
+ * Attaching private data to a folio increments the page's reference count.
+ * The data must be detached before the folio will be freed.
*/
-static inline void attach_page_private(struct page *page, void *data)
+static inline void folio_attach_private(struct folio *folio, void *data)
{
- get_page(page);
- set_page_private(page, (unsigned long)data);
- SetPagePrivate(page);
+ folio_get(folio);
+ folio->private = data;
+ folio_set_private(folio);
}
/**
- * detach_page_private - Detach private data from a page.
- * @page: Page to detach data from.
+ * folio_detach_private - Detach private data from a folio.
+ * @folio: Folio to detach data from.
*
- * Removes the data that was previously attached to the page and decrements
+ * Removes the data that was previously attached to the folio and decrements
* the refcount on the page.
*
- * Return: Data that was attached to the page.
+ * Return: Data that was attached to the folio.
*/
-static inline void *detach_page_private(struct page *page)
+static inline void *folio_detach_private(struct folio *folio)
{
- void *data = (void *)page_private(page);
+ void *data = folio_get_private(folio);
- if (!PagePrivate(page))
+ if (!folio_test_private(folio))
return NULL;
- ClearPagePrivate(page);
- set_page_private(page, 0);
- put_page(page);
+ folio_clear_private(folio);
+ folio->private = NULL;
+ folio_put(folio);
return data;
}
+static inline void attach_page_private(struct page *page, void *data)
+{
+ folio_attach_private(page_folio(page), data);
+}
+
+static inline void *detach_page_private(struct page *page)
+{
+ return folio_detach_private(page_folio(page));
+}
+
#ifdef CONFIG_NUMA
-extern struct page *__page_cache_alloc(gfp_t gfp);
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
#else
-static inline struct page *__page_cache_alloc(gfp_t gfp)
+static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
{
- return alloc_pages(gfp, 0);
+ return folio_alloc(gfp, order);
}
#endif
+static inline struct page *__page_cache_alloc(gfp_t gfp)
+{
+ return &filemap_alloc_folio(gfp, 0)->page;
+}
+
static inline struct page *page_cache_alloc(struct address_space *x)
{
return __page_cache_alloc(mapping_gfp_mask(x));
@@ -331,9 +301,28 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
#define FGP_FOR_MMAP 0x00000040
#define FGP_HEAD 0x00000080
#define FGP_ENTRY 0x00000100
+#define FGP_STABLE 0x00000200
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset,
- int fgp_flags, gfp_t cache_gfp_mask);
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp);
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp);
+
+/**
+ * filemap_get_folio - Find and get a folio.
+ * @mapping: The address_space to search.
+ * @index: The page index.
+ *
+ * Looks up the page cache entry at @mapping & @index. If a folio is
+ * present, it is returned with an increased refcount.
+ *
+ * Otherwise, %NULL is returned.
+ */
+static inline struct folio *filemap_get_folio(struct address_space *mapping,
+ pgoff_t index)
+{
+ return __filemap_get_folio(mapping, index, 0, 0);
+}
/**
* find_get_page - find and get a page reference
@@ -377,25 +366,6 @@ static inline struct page *find_lock_page(struct address_space *mapping,
}
/**
- * find_lock_head - Locate, pin and lock a pagecache page.
- * @mapping: The address_space to search.
- * @index: The page index.
- *
- * Looks up the page cache entry at @mapping & @index. If there is a
- * page cache page, its head page is returned locked and with an increased
- * refcount.
- *
- * Context: May sleep.
- * Return: A struct page which is !PageTail, or %NULL if there is no page
- * in the cache for this index.
- */
-static inline struct page *find_lock_head(struct address_space *mapping,
- pgoff_t index)
-{
- return pagecache_get_page(mapping, index, FGP_LOCK | FGP_HEAD, 0);
-}
-
-/**
* find_or_create_page - locate or add a pagecache page
* @mapping: the page's address_space
* @index: the page's index into the mapping
@@ -452,6 +422,73 @@ static inline bool thp_contains(struct page *head, pgoff_t index)
return page_index(head) == (index & ~(thp_nr_pages(head) - 1UL));
}
+#define swapcache_index(folio) __page_file_index(&(folio)->page)
+
+/**
+ * folio_index - File index of a folio.
+ * @folio: The folio.
+ *
+ * For a folio which is either in the page cache or the swap cache,
+ * return its index within the address_space it belongs to. If you know
+ * the page is definitely in the page cache, you can look at the folio's
+ * index directly.
+ *
+ * Return: The index (offset in units of pages) of a folio in its file.
+ */
+static inline pgoff_t folio_index(struct folio *folio)
+{
+ if (unlikely(folio_test_swapcache(folio)))
+ return swapcache_index(folio);
+ return folio->index;
+}
+
+/**
+ * folio_next_index - Get the index of the next folio.
+ * @folio: The current folio.
+ *
+ * Return: The index of the folio which follows this folio in the file.
+ */
+static inline pgoff_t folio_next_index(struct folio *folio)
+{
+ return folio->index + folio_nr_pages(folio);
+}
+
+/**
+ * folio_file_page - The page for a particular index.
+ * @folio: The folio which contains this index.
+ * @index: The index we want to look up.
+ *
+ * Sometimes after looking up a folio in the page cache, we need to
+ * obtain the specific page for an index (eg a page fault).
+ *
+ * Return: The page containing the file data for this index.
+ */
+static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
+{
+ /* HugeTLBfs indexes the page cache in units of hpage_size */
+ if (folio_test_hugetlb(folio))
+ return &folio->page;
+ return folio_page(folio, index & (folio_nr_pages(folio) - 1));
+}
+
+/**
+ * folio_contains - Does this folio contain this index?
+ * @folio: The folio.
+ * @index: The page index within the file.
+ *
+ * Context: The caller should have the page locked in order to prevent
+ * (eg) shmem from moving the page between the page cache and swap cache
+ * and changing its index in the middle of the operation.
+ * Return: true or false.
+ */
+static inline bool folio_contains(struct folio *folio, pgoff_t index)
+{
+ /* HugeTLBfs indexes the page cache in units of hpage_size */
+ if (folio_test_hugetlb(folio))
+ return folio->index == index;
+ return index - folio_index(folio) < folio_nr_pages(folio);
+}
+
/*
* Given the page we found in the page cache, return the page corresponding
* to this index in the file
@@ -560,6 +597,27 @@ static inline loff_t page_file_offset(struct page *page)
return ((loff_t)page_index(page)) << PAGE_SHIFT;
}
+/**
+ * folio_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
+ */
+static inline loff_t folio_pos(struct folio *folio)
+{
+ return page_offset(&folio->page);
+}
+
+/**
+ * folio_file_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
+ *
+ * This differs from folio_pos() for folios which belong to a swap file.
+ * NFS is the only filesystem today which needs to use folio_file_pos().
+ */
+static inline loff_t folio_file_pos(struct folio *folio)
+{
+ return page_file_offset(&folio->page);
+}
+
extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
unsigned long address);
@@ -575,13 +633,13 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
}
struct wait_page_key {
- struct page *page;
+ struct folio *folio;
int bit_nr;
int page_match;
};
struct wait_page_queue {
- struct page *page;
+ struct folio *folio;
int bit_nr;
wait_queue_entry_t wait;
};
@@ -589,7 +647,7 @@ struct wait_page_queue {
static inline bool wake_page_match(struct wait_page_queue *wait_page,
struct wait_page_key *key)
{
- if (wait_page->page != key->page)
+ if (wait_page->folio != key->folio)
return false;
key->page_match = 1;
@@ -599,20 +657,31 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page,
return true;
}
-extern void __lock_page(struct page *page);
-extern int __lock_page_killable(struct page *page);
-extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
-extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+void __folio_lock(struct folio *folio);
+int __folio_lock_killable(struct folio *folio);
+bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
unsigned int flags);
-extern void unlock_page(struct page *page);
+void unlock_page(struct page *page);
+void folio_unlock(struct folio *folio);
+
+static inline bool folio_trylock(struct folio *folio)
+{
+ return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0)));
+}
/*
* Return true if the page was successfully locked
*/
static inline int trylock_page(struct page *page)
{
- page = compound_head(page);
- return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
+ return folio_trylock(page_folio(page));
+}
+
+static inline void folio_lock(struct folio *folio)
+{
+ might_sleep();
+ if (!folio_trylock(folio))
+ __folio_lock(folio);
}
/*
@@ -620,38 +689,30 @@ static inline int trylock_page(struct page *page)
*/
static inline void lock_page(struct page *page)
{
+ struct folio *folio;
might_sleep();
- if (!trylock_page(page))
- __lock_page(page);
+
+ folio = page_folio(page);
+ if (!folio_trylock(folio))
+ __folio_lock(folio);
}
-/*
- * lock_page_killable is like lock_page but can be interrupted by fatal
- * signals. It returns 0 if it locked the page and -EINTR if it was
- * killed while waiting.
- */
-static inline int lock_page_killable(struct page *page)
+static inline int folio_lock_killable(struct folio *folio)
{
might_sleep();
- if (!trylock_page(page))
- return __lock_page_killable(page);
+ if (!folio_trylock(folio))
+ return __folio_lock_killable(folio);
return 0;
}
/*
- * lock_page_async - Lock the page, unless this would block. If the page
- * is already locked, then queue a callback when the page becomes unlocked.
- * This callback can then retry the operation.
- *
- * Returns 0 if the page is locked successfully, or -EIOCBQUEUED if the page
- * was already locked and the callback defined in 'wait' was queued.
+ * lock_page_killable is like lock_page but can be interrupted by fatal
+ * signals. It returns 0 if it locked the page and -EINTR if it was
+ * killed while waiting.
*/
-static inline int lock_page_async(struct page *page,
- struct wait_page_queue *wait)
+static inline int lock_page_killable(struct page *page)
{
- if (!trylock_page(page))
- return __lock_page_async(page, wait);
- return 0;
+ return folio_lock_killable(page_folio(page));
}
/*
@@ -659,78 +720,108 @@ static inline int lock_page_async(struct page *page,
* caller indicated that it can handle a retry.
*
* Return value and mmap_lock implications depend on flags; see
- * __lock_page_or_retry().
+ * __folio_lock_or_retry().
*/
-static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm,
+static inline bool lock_page_or_retry(struct page *page, struct mm_struct *mm,
unsigned int flags)
{
+ struct folio *folio;
might_sleep();
- return trylock_page(page) || __lock_page_or_retry(page, mm, flags);
+
+ folio = page_folio(page);
+ return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags);
}
/*
- * This is exported only for wait_on_page_locked/wait_on_page_writeback, etc.,
+ * This is exported only for folio_wait_locked/folio_wait_writeback, etc.,
* and should not be used directly.
*/
-extern void wait_on_page_bit(struct page *page, int bit_nr);
-extern int wait_on_page_bit_killable(struct page *page, int bit_nr);
+void folio_wait_bit(struct folio *folio, int bit_nr);
+int folio_wait_bit_killable(struct folio *folio, int bit_nr);
/*
- * Wait for a page to be unlocked.
+ * Wait for a folio to be unlocked.
*
- * This must be called with the caller "holding" the page,
- * ie with increased "page->count" so that the page won't
+ * This must be called with the caller "holding" the folio,
+ * ie with increased "page->count" so that the folio won't
* go away during the wait..
*/
+static inline void folio_wait_locked(struct folio *folio)
+{
+ if (folio_test_locked(folio))
+ folio_wait_bit(folio, PG_locked);
+}
+
+static inline int folio_wait_locked_killable(struct folio *folio)
+{
+ if (!folio_test_locked(folio))
+ return 0;
+ return folio_wait_bit_killable(folio, PG_locked);
+}
+
static inline void wait_on_page_locked(struct page *page)
{
- if (PageLocked(page))
- wait_on_page_bit(compound_head(page), PG_locked);
+ folio_wait_locked(page_folio(page));
}
static inline int wait_on_page_locked_killable(struct page *page)
{
- if (!PageLocked(page))
- return 0;
- return wait_on_page_bit_killable(compound_head(page), PG_locked);
+ return folio_wait_locked_killable(page_folio(page));
}
int put_and_wait_on_page_locked(struct page *page, int state);
void wait_on_page_writeback(struct page *page);
-int wait_on_page_writeback_killable(struct page *page);
-extern void end_page_writeback(struct page *page);
+void folio_wait_writeback(struct folio *folio);
+int folio_wait_writeback_killable(struct folio *folio);
+void end_page_writeback(struct page *page);
+void folio_end_writeback(struct folio *folio);
void wait_for_stable_page(struct page *page);
+void folio_wait_stable(struct folio *folio);
+void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
+static inline void __set_page_dirty(struct page *page,
+ struct address_space *mapping, int warn)
+{
+ __folio_mark_dirty(page_folio(page), mapping, warn);
+}
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
+ struct bdi_writeback *wb);
+static inline void account_page_cleaned(struct page *page,
+ struct address_space *mapping, struct bdi_writeback *wb)
+{
+ return folio_account_cleaned(page_folio(page), mapping, wb);
+}
+void __folio_cancel_dirty(struct folio *folio);
+static inline void folio_cancel_dirty(struct folio *folio)
+{
+ /* Avoid atomic ops, locking, etc. when not actually needed. */
+ if (folio_test_dirty(folio))
+ __folio_cancel_dirty(folio);
+}
+static inline void cancel_dirty_page(struct page *page)
+{
+ folio_cancel_dirty(page_folio(page));
+}
+bool folio_clear_dirty_for_io(struct folio *folio);
+bool clear_page_dirty_for_io(struct page *page);
+int __must_check folio_write_one(struct folio *folio);
+static inline int __must_check write_one_page(struct page *page)
+{
+ return folio_write_one(page_folio(page));
+}
-void __set_page_dirty(struct page *, struct address_space *, int warn);
int __set_page_dirty_nobuffers(struct page *page);
int __set_page_dirty_no_writeback(struct page *page);
void page_endio(struct page *page, bool is_write, int err);
-/**
- * set_page_private_2 - Set PG_private_2 on a page and take a ref
- * @page: The page.
- *
- * Set the PG_private_2 flag on a page and take the reference needed for the VM
- * to handle its lifetime correctly. This sets the flag and takes the
- * reference unconditionally, so care must be taken not to set the flag again
- * if it's already set.
- */
-static inline void set_page_private_2(struct page *page)
-{
- page = compound_head(page);
- get_page(page);
- SetPagePrivate2(page);
-}
-
-void end_page_private_2(struct page *page);
-void wait_on_page_private_2(struct page *page);
-int wait_on_page_private_2_killable(struct page *page);
+void folio_end_private_2(struct folio *folio);
+void folio_wait_private_2(struct folio *folio);
+int folio_wait_private_2_killable(struct folio *folio);
/*
* Add an arbitrary waiter to a page's wait queue
*/
-extern void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter);
+void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
/*
* Fault everything in given userspace address range in.
@@ -790,9 +881,11 @@ static inline int fault_in_pages_readable(const char __user *uaddr, size_t size)
}
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp_mask);
+ pgoff_t index, gfp_t gfp);
int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t index, gfp_t gfp_mask);
+ pgoff_t index, gfp_t gfp);
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp);
extern void delete_from_page_cache(struct page *page);
extern void __delete_from_page_cache(struct page *page, void *shadow);
void replace_page_cache_page(struct page *old, struct page *new);
@@ -817,6 +910,10 @@ static inline int add_to_page_cache(struct page *page,
return error;
}
+/* Must be non-static for BPF error injection */
+int __filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp, void **shadowp);
+
/**
* struct readahead_control - Describes a readahead request.
*
@@ -906,33 +1003,57 @@ void page_cache_async_readahead(struct address_space *mapping,
page_cache_async_ra(&ractl, page, req_count);
}
+static inline struct folio *__readahead_folio(struct readahead_control *ractl)
+{
+ struct folio *folio;
+
+ BUG_ON(ractl->_batch_count > ractl->_nr_pages);
+ ractl->_nr_pages -= ractl->_batch_count;
+ ractl->_index += ractl->_batch_count;
+
+ if (!ractl->_nr_pages) {
+ ractl->_batch_count = 0;
+ return NULL;
+ }
+
+ folio = xa_load(&ractl->mapping->i_pages, ractl->_index);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ ractl->_batch_count = folio_nr_pages(folio);
+
+ return folio;
+}
+
/**
* readahead_page - Get the next page to read.
- * @rac: The current readahead request.
+ * @ractl: The current readahead request.
*
* Context: The page is locked and has an elevated refcount. The caller
* should decreases the refcount once the page has been submitted for I/O
* and unlock the page once all I/O to that page has completed.
* Return: A pointer to the next page, or %NULL if we are done.
*/
-static inline struct page *readahead_page(struct readahead_control *rac)
+static inline struct page *readahead_page(struct readahead_control *ractl)
{
- struct page *page;
-
- BUG_ON(rac->_batch_count > rac->_nr_pages);
- rac->_nr_pages -= rac->_batch_count;
- rac->_index += rac->_batch_count;
+ struct folio *folio = __readahead_folio(ractl);
- if (!rac->_nr_pages) {
- rac->_batch_count = 0;
- return NULL;
- }
+ return &folio->page;
+}
- page = xa_load(&rac->mapping->i_pages, rac->_index);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- rac->_batch_count = thp_nr_pages(page);
+/**
+ * readahead_folio - Get the next folio to read.
+ * @ractl: The current readahead request.
+ *
+ * Context: The folio is locked. The caller should unlock the folio once
+ * all I/O to that folio has completed.
+ * Return: A pointer to the next folio, or %NULL if we are done.
+ */
+static inline struct folio *readahead_folio(struct readahead_control *ractl)
+{
+ struct folio *folio = __readahead_folio(ractl);
- return page;
+ if (folio)
+ folio_put(folio);
+ return folio;
}
static inline unsigned int __readahead_batch(struct readahead_control *rac,
@@ -1040,6 +1161,34 @@ static inline unsigned long dir_pages(struct inode *inode)
}
/**
+ * folio_mkwrite_check_truncate - check if folio was truncated
+ * @folio: the folio to check
+ * @inode: the inode to check the folio against
+ *
+ * Return: the number of bytes in the folio up to EOF,
+ * or -EFAULT if the folio was truncated.
+ */
+static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
+ struct inode *inode)
+{
+ loff_t size = i_size_read(inode);
+ pgoff_t index = size >> PAGE_SHIFT;
+ size_t offset = offset_in_folio(folio, size);
+
+ if (!folio->mapping)
+ return -EFAULT;
+
+ /* folio is wholly inside EOF */
+ if (folio_next_index(folio) - 1 < index)
+ return folio_size(folio);
+ /* folio is wholly past EOF */
+ if (folio->index > index || !offset)
+ return -EFAULT;
+ /* folio is partially inside EOF */
+ return offset;
+}
+
+/**
* page_mkwrite_check_truncate - check if page was truncated
* @page: the page to check
* @inode: the inode to check the page against
@@ -1068,19 +1217,25 @@ static inline int page_mkwrite_check_truncate(struct page *page,
}
/**
- * i_blocks_per_page - How many blocks fit in this page.
+ * i_blocks_per_folio - How many blocks fit in this folio.
* @inode: The inode which contains the blocks.
- * @page: The page (head page if the page is a THP).
+ * @folio: The folio.
*
- * If the block size is larger than the size of this page, return zero.
+ * If the block size is larger than the size of this folio, return zero.
*
- * Context: The caller should hold a refcount on the page to prevent it
+ * Context: The caller should hold a refcount on the folio to prevent it
* from being split.
- * Return: The number of filesystem blocks covered by this page.
+ * Return: The number of filesystem blocks covered by this folio.
*/
static inline
+unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio)
+{
+ return folio_size(folio) >> inode->i_blkbits;
+}
+
+static inline
unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
{
- return thp_size(page) >> inode->i_blkbits;
+ return i_blocks_per_folio(inode, page_folio(page));
}
#endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index ae16a9856305..b31d3f3312ce 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -267,6 +267,28 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
}
/**
+ * percpu_ref_tryget_live_rcu - same as percpu_ref_tryget_live() but the
+ * caller is responsible for taking RCU.
+ *
+ * This function is safe to call as long as @ref is between init and exit.
+ */
+static inline bool percpu_ref_tryget_live_rcu(struct percpu_ref *ref)
+{
+ unsigned long __percpu *percpu_count;
+ bool ret = false;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ if (likely(__ref_is_percpu(ref, &percpu_count))) {
+ this_cpu_inc(*percpu_count);
+ ret = true;
+ } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
+ ret = atomic_long_inc_not_zero(&ref->data->count);
+ }
+ return ret;
+}
+
+/**
* percpu_ref_tryget_live - try to increment a live percpu refcount
* @ref: percpu_ref to try-get
*
@@ -283,20 +305,11 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
*/
static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
{
- unsigned long __percpu *percpu_count;
bool ret = false;
rcu_read_lock();
-
- if (__ref_is_percpu(ref, &percpu_count)) {
- this_cpu_inc(*percpu_count);
- ret = true;
- } else if (!(ref->percpu_count_ptr & __PERCPU_REF_DEAD)) {
- ret = atomic_long_inc_not_zero(&ref->data->count);
- }
-
+ ret = percpu_ref_tryget_live_rcu(ref);
rcu_read_unlock();
-
return ret;
}
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c976cc6de257..e704b1a4c06c 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -235,7 +235,7 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
*
* returns the number of cleaned PTEs.
*/
-int page_mkclean(struct page *);
+int folio_mkclean(struct folio *);
/*
* called in munlock()/munmap() path to check for other vmas holding
@@ -295,12 +295,14 @@ static inline void try_to_unmap(struct page *page, enum ttu_flags flags)
{
}
-static inline int page_mkclean(struct page *page)
+static inline int folio_mkclean(struct folio *folio)
{
return 0;
}
-
-
#endif /* CONFIG_MMU */
+static inline int page_mkclean(struct page *page)
+{
+ return folio_mkclean(page_folio(page));
+}
#endif /* _LINUX_RMAP_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c1a927ddec64..e0454e60fe8f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1160,10 +1160,8 @@ struct task_struct {
/* Stacked block device info: */
struct bio_list *bio_list;
-#ifdef CONFIG_BLOCK
/* Stack plugging: */
struct blk_plug *plug;
-#endif
/* VM state: */
struct reclaim_state *reclaim_state;
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
index 21c3771e6a56..988528b5da43 100644
--- a/include/linux/secretmem.h
+++ b/include/linux/secretmem.h
@@ -23,7 +23,7 @@ static inline bool page_is_secretmem(struct page *page)
mapping = (struct address_space *)
((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
- if (mapping != page->mapping)
+ if (!mapping || mapping != page->mapping)
return false;
return mapping->a_ops == &secretmem_aops;
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 14ab0c0bc924..1ce9a9eb223b 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -128,6 +128,7 @@ int sk_msg_memcopy_from_iter(struct sock *sk, struct iov_iter *from,
struct sk_msg *msg, u32 bytes);
int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
int len, int flags);
+bool sk_msg_is_readable(struct sock *sk);
static inline void sk_msg_check_to_free(struct sk_msg *msg, u32 i, u32 bytes)
{
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba52f3a3478e..cdf0957a88a4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -320,11 +320,17 @@ struct vma_swap_readahead {
#endif
};
+static inline swp_entry_t folio_swap_entry(struct folio *folio)
+{
+ swp_entry_t entry = { .val = page_private(&folio->page) };
+ return entry;
+}
+
/* linux/mm/workingset.c */
void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages);
void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg);
-void workingset_refault(struct page *page, void *shadow);
-void workingset_activation(struct page *page);
+void workingset_refault(struct folio *folio, void *shadow);
+void workingset_activation(struct folio *folio);
/* Only track the nodes of mappings with shadow entries */
void workingset_update_node(struct xa_node *node);
@@ -344,9 +350,11 @@ extern unsigned long nr_free_buffer_pages(void);
/* linux/mm/swap.c */
extern void lru_note_cost(struct lruvec *lruvec, bool file,
unsigned int nr_pages);
-extern void lru_note_cost_page(struct page *);
+extern void lru_note_cost_folio(struct folio *);
+extern void folio_add_lru(struct folio *);
extern void lru_cache_add(struct page *);
-extern void mark_page_accessed(struct page *);
+void mark_page_accessed(struct page *);
+void folio_mark_accessed(struct folio *);
extern atomic_t lru_disable_count;
@@ -365,7 +373,6 @@ extern void lru_add_drain(void);
extern void lru_add_drain_cpu(int cpu);
extern void lru_add_drain_cpu_zone(struct zone *zone);
extern void lru_add_drain_all(void);
-extern void rotate_reclaimable_page(struct page *page);
extern void deactivate_file_page(struct page *page);
extern void deactivate_page(struct page *page);
extern void mark_page_lazyfree(struct page *page);
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index aa11fe323c56..12d827734686 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -269,6 +269,7 @@ enum tpm2_cc_attrs {
#define TPM_VID_INTEL 0x8086
#define TPM_VID_WINBOND 0x1050
#define TPM_VID_STM 0x104A
+#define TPM_VID_ATML 0x1114
enum tpm_chip_flags {
TPM_CHIP_FLAG_TPM2 = BIT(1),
diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
index a9f9c5714e65..fe95f0922526 100644
--- a/include/linux/trace_recursion.h
+++ b/include/linux/trace_recursion.h
@@ -16,23 +16,8 @@
* When function tracing occurs, the following steps are made:
* If arch does not support a ftrace feature:
* call internal function (uses INTERNAL bits) which calls...
- * If callback is registered to the "global" list, the list
- * function is called and recursion checks the GLOBAL bits.
- * then this function calls...
* The function callback, which can use the FTRACE bits to
* check for recursion.
- *
- * Now if the arch does not support a feature, and it calls
- * the global list function which calls the ftrace callback
- * all three of these steps will do a recursion protection.
- * There's no reason to do one if the previous caller already
- * did. The recursion that we are protecting against will
- * go through the same steps again.
- *
- * To prevent the multiple recursion checks, if a recursion
- * bit is set that is higher than the MAX bit of the current
- * check, then we know that the check was made by the previous
- * caller, and we can skip the current check.
*/
enum {
/* Function recursion bits */
@@ -40,12 +25,14 @@ enum {
TRACE_FTRACE_NMI_BIT,
TRACE_FTRACE_IRQ_BIT,
TRACE_FTRACE_SIRQ_BIT,
+ TRACE_FTRACE_TRANSITION_BIT,
- /* INTERNAL_BITs must be greater than FTRACE_BITs */
+ /* Internal use recursion bits */
TRACE_INTERNAL_BIT,
TRACE_INTERNAL_NMI_BIT,
TRACE_INTERNAL_IRQ_BIT,
TRACE_INTERNAL_SIRQ_BIT,
+ TRACE_INTERNAL_TRANSITION_BIT,
TRACE_BRANCH_BIT,
/*
@@ -86,12 +73,6 @@ enum {
*/
TRACE_GRAPH_NOTRACE_BIT,
- /*
- * When transitioning between context, the preempt_count() may
- * not be correct. Allow for a single recursion to cover this case.
- */
- TRACE_TRANSITION_BIT,
-
/* Used to prevent recursion recording from recursing. */
TRACE_RECORD_RECURSION_BIT,
};
@@ -113,12 +94,10 @@ enum {
#define TRACE_CONTEXT_BITS 4
#define TRACE_FTRACE_START TRACE_FTRACE_BIT
-#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
#define TRACE_LIST_START TRACE_INTERNAL_BIT
-#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
-#define TRACE_CONTEXT_MASK TRACE_LIST_MAX
+#define TRACE_CONTEXT_MASK ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
/*
* Used for setting context
@@ -132,6 +111,7 @@ enum {
TRACE_CTX_IRQ,
TRACE_CTX_SOFTIRQ,
TRACE_CTX_NORMAL,
+ TRACE_CTX_TRANSITION,
};
static __always_inline int trace_get_context_bit(void)
@@ -160,45 +140,34 @@ extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
#endif
static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
- int start, int max)
+ int start)
{
unsigned int val = READ_ONCE(current->trace_recursion);
int bit;
- /* A previous recursion check was made */
- if ((val & TRACE_CONTEXT_MASK) > max)
- return 0;
-
bit = trace_get_context_bit() + start;
if (unlikely(val & (1 << bit))) {
/*
* It could be that preempt_count has not been updated during
* a switch between contexts. Allow for a single recursion.
*/
- bit = TRACE_TRANSITION_BIT;
+ bit = TRACE_CTX_TRANSITION + start;
if (val & (1 << bit)) {
do_ftrace_record_recursion(ip, pip);
return -1;
}
- } else {
- /* Normal check passed, clear the transition to allow it again */
- val &= ~(1 << TRACE_TRANSITION_BIT);
}
val |= 1 << bit;
current->trace_recursion = val;
barrier();
- return bit + 1;
+ return bit;
}
static __always_inline void trace_clear_recursion(int bit)
{
- if (!bit)
- return;
-
barrier();
- bit--;
trace_recursion_clear(bit);
}
@@ -214,7 +183,7 @@ static __always_inline void trace_clear_recursion(int bit)
static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
unsigned long parent_ip)
{
- return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+ return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START);
}
/**
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index eb70cabe6e7f..33a4240e6a6f 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -127,6 +127,8 @@ static inline long get_ucounts_value(struct ucounts *ucounts, enum ucount_type t
long inc_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v);
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type);
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type);
bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max);
static inline void set_rlimit_ucount_max(struct user_namespace *ns,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d6a6cf53b127..bfe38869498d 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -415,6 +415,78 @@ static inline void drain_zonestat(struct zone *zone,
struct per_cpu_zonestat *pzstats) { }
#endif /* CONFIG_SMP */
+static inline void __zone_stat_mod_folio(struct folio *folio,
+ enum zone_stat_item item, long nr)
+{
+ __mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void __zone_stat_add_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ __mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __zone_stat_sub_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ __mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void zone_stat_mod_folio(struct folio *folio,
+ enum zone_stat_item item, long nr)
+{
+ mod_zone_page_state(folio_zone(folio), item, nr);
+}
+
+static inline void zone_stat_add_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ mod_zone_page_state(folio_zone(folio), item, folio_nr_pages(folio));
+}
+
+static inline void zone_stat_sub_folio(struct folio *folio,
+ enum zone_stat_item item)
+{
+ mod_zone_page_state(folio_zone(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void __node_stat_mod_folio(struct folio *folio,
+ enum node_stat_item item, long nr)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void __node_stat_add_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void __node_stat_sub_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ __mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
+}
+
+static inline void node_stat_mod_folio(struct folio *folio,
+ enum node_stat_item item, long nr)
+{
+ mod_node_page_state(folio_pgdat(folio), item, nr);
+}
+
+static inline void node_stat_add_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ mod_node_page_state(folio_pgdat(folio), item, folio_nr_pages(folio));
+}
+
+static inline void node_stat_sub_folio(struct folio *folio,
+ enum node_stat_item item)
+{
+ mod_node_page_state(folio_pgdat(folio), item, -folio_nr_pages(folio));
+}
+
static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
int migratetype)
{
@@ -525,12 +597,6 @@ static inline void mod_lruvec_page_state(struct page *page,
#endif /* CONFIG_MEMCG */
-static inline void inc_lruvec_state(struct lruvec *lruvec,
- enum node_stat_item idx)
-{
- mod_lruvec_state(lruvec, idx, 1);
-}
-
static inline void __inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
@@ -543,6 +609,24 @@ static inline void __dec_lruvec_page_state(struct page *page,
__mod_lruvec_page_state(page, idx, -1);
}
+static inline void __lruvec_stat_mod_folio(struct folio *folio,
+ enum node_stat_item idx, int val)
+{
+ __mod_lruvec_page_state(&folio->page, idx, val);
+}
+
+static inline void __lruvec_stat_add_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ __lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void __lruvec_stat_sub_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ __lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
+
static inline void inc_lruvec_page_state(struct page *page,
enum node_stat_item idx)
{
@@ -555,4 +639,21 @@ static inline void dec_lruvec_page_state(struct page *page,
mod_lruvec_page_state(page, idx, -1);
}
+static inline void lruvec_stat_mod_folio(struct folio *folio,
+ enum node_stat_item idx, int val)
+{
+ mod_lruvec_page_state(&folio->page, idx, val);
+}
+
+static inline void lruvec_stat_add_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ lruvec_stat_mod_folio(folio, idx, folio_nr_pages(folio));
+}
+
+static inline void lruvec_stat_sub_folio(struct folio *folio,
+ enum node_stat_item idx)
+{
+ lruvec_stat_mod_folio(folio, idx, -folio_nr_pages(folio));
+}
#endif /* _LINUX_VMSTAT_H */
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 8eb165760752..3bfd487d1dd2 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -389,7 +389,14 @@ void writeback_set_ratelimit(void);
void tag_pages_for_writeback(struct address_space *mapping,
pgoff_t start, pgoff_t end);
-void account_page_redirty(struct page *page);
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio);
+void folio_account_redirty(struct folio *folio);
+static inline void account_page_redirty(struct page *page)
+{
+ folio_account_redirty(page_folio(page));
+}
+bool folio_redirty_for_writepage(struct writeback_control *, struct folio *);
+bool redirty_page_for_writepage(struct writeback_control *, struct page *);
void sb_mark_inode_writeback(struct inode *inode);
void sb_clear_inode_writeback(struct inode *inode);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 62dd8422e0dc..27336fc70467 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5376,7 +5376,6 @@ static inline void wiphy_unlock(struct wiphy *wiphy)
* netdev and may otherwise be used by driver read-only, will be update
* by cfg80211 on change_interface
* @mgmt_registrations: list of registrations for management frames
- * @mgmt_registrations_lock: lock for the list
* @mgmt_registrations_need_update: mgmt registrations were updated,
* need to propagate the update to the driver
* @mtx: mutex used to lock data in this struct, may be used by drivers
@@ -5423,7 +5422,6 @@ struct wireless_dev {
u32 identifier;
struct list_head mgmt_registrations;
- spinlock_t mgmt_registrations_lock;
u8 mgmt_registrations_need_update:1;
struct mutex mtx;
diff --git a/include/net/mctp.h b/include/net/mctp.h
index a824d47c3c6d..ffd2c23bd76d 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -54,7 +54,7 @@ struct mctp_sock {
struct sock sk;
/* bind() params */
- int bind_net;
+ unsigned int bind_net;
mctp_eid_t bind_addr;
__u8 bind_type;
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 6026bbefbffd..3214848402ec 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -69,6 +69,10 @@ struct mptcp_out_options {
struct {
u64 sndr_key;
u64 rcvr_key;
+ u64 data_seq;
+ u32 subflow_seq;
+ u16 data_len;
+ __sum16 csum;
};
struct {
struct mptcp_addr_info addr;
diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 2eb6d7c2c931..f37c7a558d6d 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -384,11 +384,11 @@ sctp_vtag_verify(const struct sctp_chunk *chunk,
* Verification Tag value does not match the receiver's own
* tag value, the receiver shall silently discard the packet...
*/
- if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag)
- return 1;
+ if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag)
+ return 0;
chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
- return 0;
+ return 1;
}
/* Check VTAG of the packet matches the sender's own tag and the T bit is
diff --git a/include/net/sock.h b/include/net/sock.h
index ea6fbc88c8f9..463f390d90b3 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1208,7 +1208,7 @@ struct proto {
#endif
bool (*stream_memory_free)(const struct sock *sk, int wake);
- bool (*stream_memory_read)(const struct sock *sk);
+ bool (*sock_is_readable)(struct sock *sk);
/* Memory pressure */
void (*enter_memory_pressure)(struct sock *sk);
void (*leave_memory_pressure)(struct sock *sk);
@@ -2820,4 +2820,10 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs);
int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len);
+static inline bool sk_is_readable(struct sock *sk)
+{
+ if (sk->sk_prot->sock_is_readable)
+ return sk->sk_prot->sock_is_readable(sk);
+ return false;
+}
#endif /* _SOCK_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3166dc15d7d6..60c384569e9c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1576,6 +1576,7 @@ struct tcp_md5sig_key {
u8 keylen;
u8 family; /* AF_INET or AF_INET6 */
u8 prefixlen;
+ u8 flags;
union tcp_md5_addr addr;
int l3index; /* set if key added with L3 scope */
u8 key[TCP_MD5SIG_MAXKEYLEN];
@@ -1621,10 +1622,10 @@ struct tcp_md5sig_pool {
int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
const struct sock *sk, const struct sk_buff *skb);
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
- int family, u8 prefixlen, int l3index,
+ int family, u8 prefixlen, int l3index, u8 flags,
const u8 *newkey, u8 newkeylen, gfp_t gfp);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
- int family, u8 prefixlen, int l3index);
+ int family, u8 prefixlen, int l3index, u8 flags);
struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
const struct sock *addr_sk);
diff --git a/include/net/tls.h b/include/net/tls.h
index be4b3e1cac46..1fffb206f09f 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -358,6 +358,7 @@ int tls_sk_query(struct sock *sk, int optname, char __user *optval,
int __user *optlen);
int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
unsigned int optlen);
+void tls_err_abort(struct sock *sk, int err);
int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx);
@@ -375,7 +376,7 @@ void tls_sw_release_resources_rx(struct sock *sk);
void tls_sw_free_ctx_rx(struct tls_context *tls_ctx);
int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int nonblock, int flags, int *addr_len);
-bool tls_sw_stream_read(const struct sock *sk);
+bool tls_sw_sock_is_readable(struct sock *sk);
ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags);
@@ -466,12 +467,6 @@ static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
#endif
}
-static inline void tls_err_abort(struct sock *sk, int err)
-{
- sk->sk_err = err;
- sk_error_report(sk);
-}
-
static inline bool tls_bigint_increment(unsigned char *seq, int len)
{
int i;
@@ -512,7 +507,7 @@ static inline void tls_advance_record_sn(struct sock *sk,
struct cipher_context *ctx)
{
if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size))
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (prot->version != TLS_1_3_VERSION &&
prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
diff --git a/include/net/udp.h b/include/net/udp.h
index 360df454356c..909ecf447e0f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -494,8 +494,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
* CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
* packets in udp_gro_complete_segment. As does UDP GSO, verified by
* udp_send_skb. But when those packets are looped in dev_loopback_xmit
- * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
- * specific case, where PARTIAL is both correct and required.
+ * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
+ * Reset in this specific case, where PARTIAL is both correct and
+ * required.
*/
if (skb->pkt_type == PACKET_LOOPBACK)
skb->ip_summed = CHECKSUM_PARTIAL;
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index cc5ab96a7471..a95daa4d4caa 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -114,7 +114,7 @@ TRACE_EVENT(block_rq_requeue,
*/
TRACE_EVENT(block_rq_complete,
- TP_PROTO(struct request *rq, int error, unsigned int nr_bytes),
+ TP_PROTO(struct request *rq, blk_status_t error, unsigned int nr_bytes),
TP_ARGS(rq, error, nr_bytes),
@@ -122,7 +122,7 @@ TRACE_EVENT(block_rq_complete,
__field( dev_t, dev )
__field( sector_t, sector )
__field( unsigned int, nr_sector )
- __field( int, error )
+ __field( int , error )
__array( char, rwbs, RWBS_LEN )
__dynamic_array( char, cmd, 1 )
),
@@ -131,7 +131,7 @@ TRACE_EVENT(block_rq_complete,
__entry->dev = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
__entry->sector = blk_rq_pos(rq);
__entry->nr_sector = nr_bytes >> 9;
- __entry->error = error;
+ __entry->error = blk_status_to_errno(error);
blk_fill_rwbs(__entry->rwbs, rq->cmd_flags);
__get_str(cmd)[0] = '\0';
diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h
index 0dd30de00e5b..7346f0164cf4 100644
--- a/include/trace/events/io_uring.h
+++ b/include/trace/events/io_uring.h
@@ -6,6 +6,7 @@
#define _TRACE_IO_URING_H
#include <linux/tracepoint.h>
+#include <uapi/linux/io_uring.h>
struct io_wq_work;
@@ -497,6 +498,66 @@ TRACE_EVENT(io_uring_task_run,
(unsigned long long) __entry->user_data)
);
+/*
+ * io_uring_req_failed - called when an sqe is errored dring submission
+ *
+ * @sqe: pointer to the io_uring_sqe that failed
+ * @error: error it failed with
+ *
+ * Allows easier diagnosing of malformed requests in production systems.
+ */
+TRACE_EVENT(io_uring_req_failed,
+
+ TP_PROTO(const struct io_uring_sqe *sqe, int error),
+
+ TP_ARGS(sqe, error),
+
+ TP_STRUCT__entry (
+ __field( u8, opcode )
+ __field( u8, flags )
+ __field( u8, ioprio )
+ __field( u64, off )
+ __field( u64, addr )
+ __field( u32, len )
+ __field( u32, op_flags )
+ __field( u64, user_data )
+ __field( u16, buf_index )
+ __field( u16, personality )
+ __field( u32, file_index )
+ __field( u64, pad1 )
+ __field( u64, pad2 )
+ __field( int, error )
+ ),
+
+ TP_fast_assign(
+ __entry->opcode = sqe->opcode;
+ __entry->flags = sqe->flags;
+ __entry->ioprio = sqe->ioprio;
+ __entry->off = sqe->off;
+ __entry->addr = sqe->addr;
+ __entry->len = sqe->len;
+ __entry->op_flags = sqe->rw_flags;
+ __entry->user_data = sqe->user_data;
+ __entry->buf_index = sqe->buf_index;
+ __entry->personality = sqe->personality;
+ __entry->file_index = sqe->file_index;
+ __entry->pad1 = sqe->__pad2[0];
+ __entry->pad2 = sqe->__pad2[1];
+ __entry->error = error;
+ ),
+
+ TP_printk("op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, "
+ "len=%u, rw_flags=0x%x, user_data=0x%llx, buf_index=%d, "
+ "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d",
+ __entry->opcode, __entry->flags, __entry->ioprio,
+ (unsigned long long)__entry->off,
+ (unsigned long long) __entry->addr, __entry->len,
+ __entry->op_flags, (unsigned long long) __entry->user_data,
+ __entry->buf_index, __entry->personality, __entry->file_index,
+ (unsigned long long) __entry->pad1,
+ (unsigned long long) __entry->pad2, __entry->error)
+);
+
#endif /* _TRACE_IO_URING_H */
/* This part must be outside protection */
diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h
index 1d28431e85bd..171524d3526d 100644
--- a/include/trace/events/pagemap.h
+++ b/include/trace/events/pagemap.h
@@ -16,38 +16,38 @@
#define PAGEMAP_MAPPEDDISK 0x0020u
#define PAGEMAP_BUFFERS 0x0040u
-#define trace_pagemap_flags(page) ( \
- (PageAnon(page) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \
- (page_mapped(page) ? PAGEMAP_MAPPED : 0) | \
- (PageSwapCache(page) ? PAGEMAP_SWAPCACHE : 0) | \
- (PageSwapBacked(page) ? PAGEMAP_SWAPBACKED : 0) | \
- (PageMappedToDisk(page) ? PAGEMAP_MAPPEDDISK : 0) | \
- (page_has_private(page) ? PAGEMAP_BUFFERS : 0) \
+#define trace_pagemap_flags(folio) ( \
+ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \
+ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \
+ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \
+ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \
+ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \
+ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \
)
TRACE_EVENT(mm_lru_insertion,
- TP_PROTO(struct page *page),
+ TP_PROTO(struct folio *folio),
- TP_ARGS(page),
+ TP_ARGS(folio),
TP_STRUCT__entry(
- __field(struct page *, page )
+ __field(struct folio *, folio )
__field(unsigned long, pfn )
__field(enum lru_list, lru )
__field(unsigned long, flags )
),
TP_fast_assign(
- __entry->page = page;
- __entry->pfn = page_to_pfn(page);
- __entry->lru = page_lru(page);
- __entry->flags = trace_pagemap_flags(page);
+ __entry->folio = folio;
+ __entry->pfn = folio_pfn(folio);
+ __entry->lru = folio_lru_list(folio);
+ __entry->flags = trace_pagemap_flags(folio);
),
/* Flag format is based on page-types.c formatting for pagemap */
- TP_printk("page=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
- __entry->page,
+ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s",
+ __entry->folio,
__entry->pfn,
__entry->lru,
__entry->flags & PAGEMAP_MAPPED ? "M" : " ",
@@ -60,23 +60,21 @@ TRACE_EVENT(mm_lru_insertion,
TRACE_EVENT(mm_lru_activate,
- TP_PROTO(struct page *page),
+ TP_PROTO(struct folio *folio),
- TP_ARGS(page),
+ TP_ARGS(folio),
TP_STRUCT__entry(
- __field(struct page *, page )
+ __field(struct folio *, folio )
__field(unsigned long, pfn )
),
TP_fast_assign(
- __entry->page = page;
- __entry->pfn = page_to_pfn(page);
+ __entry->folio = folio;
+ __entry->pfn = folio_pfn(folio);
),
- /* Flag format is based on page-types.c formatting for pagemap */
- TP_printk("page=%p pfn=0x%lx", __entry->page, __entry->pfn)
-
+ TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn)
);
#endif /* _TRACE_PAGEMAP_H */
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 840d1ba84cf5..7dccb66474f7 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -52,11 +52,11 @@ WB_WORK_REASON
struct wb_writeback_work;
-DECLARE_EVENT_CLASS(writeback_page_template,
+DECLARE_EVENT_CLASS(writeback_folio_template,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping),
+ TP_ARGS(folio, mapping),
TP_STRUCT__entry (
__array(char, name, 32)
@@ -69,7 +69,7 @@ DECLARE_EVENT_CLASS(writeback_page_template,
bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
NULL), 32);
__entry->ino = mapping ? mapping->host->i_ino : 0;
- __entry->index = page->index;
+ __entry->index = folio->index;
),
TP_printk("bdi %s: ino=%lu index=%lu",
@@ -79,18 +79,18 @@ DECLARE_EVENT_CLASS(writeback_page_template,
)
);
-DEFINE_EVENT(writeback_page_template, writeback_dirty_page,
+DEFINE_EVENT(writeback_folio_template, writeback_dirty_folio,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping)
+ TP_ARGS(folio, mapping)
);
-DEFINE_EVENT(writeback_page_template, wait_on_page_writeback,
+DEFINE_EVENT(writeback_folio_template, folio_wait_writeback,
- TP_PROTO(struct page *page, struct address_space *mapping),
+ TP_PROTO(struct folio *folio, struct address_space *mapping),
- TP_ARGS(page, mapping)
+ TP_ARGS(folio, mapping)
);
DECLARE_EVENT_CLASS(writeback_dirty_inode_template,
@@ -236,9 +236,9 @@ TRACE_EVENT(inode_switch_wbs,
TRACE_EVENT(track_foreign_dirty,
- TP_PROTO(struct page *page, struct bdi_writeback *wb),
+ TP_PROTO(struct folio *folio, struct bdi_writeback *wb),
- TP_ARGS(page, wb),
+ TP_ARGS(folio, wb),
TP_STRUCT__entry(
__array(char, name, 32)
@@ -250,7 +250,7 @@ TRACE_EVENT(track_foreign_dirty,
),
TP_fast_assign(
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
struct inode *inode = mapping ? mapping->host : NULL;
strscpy_pad(__entry->name, bdi_dev_name(wb->bdi), 32);
@@ -258,7 +258,7 @@ TRACE_EVENT(track_foreign_dirty,
__entry->ino = inode ? inode->i_ino : 0;
__entry->memcg_id = wb->memcg_css->id;
__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
- __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup);
+ __entry->page_cgroup_ino = cgroup_ino(folio_memcg(folio)->css.cgroup);
),
TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu",
diff --git a/include/uapi/asm-generic/fcntl.h b/include/uapi/asm-generic/fcntl.h
index 9dc0bf0c5a6e..ecd0f5bdfc1d 100644
--- a/include/uapi/asm-generic/fcntl.h
+++ b/include/uapi/asm-generic/fcntl.h
@@ -181,6 +181,10 @@ struct f_owner_ex {
blocking */
#define LOCK_UN 8 /* remove lock */
+/*
+ * LOCK_MAND support has been removed from the kernel. We leave the symbols
+ * here to not break legacy builds, but these should not be used in new code.
+ */
#define LOCK_MAND 32 /* This is a mandatory flock ... */
#define LOCK_READ 64 /* which allows concurrent read operations */
#define LOCK_WRITE 128 /* which allows concurrent write operations */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index b270a07b285e..c45b5e9a9387 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -158,6 +158,7 @@ enum {
#define IORING_TIMEOUT_BOOTTIME (1U << 2)
#define IORING_TIMEOUT_REALTIME (1U << 3)
#define IORING_LINK_TIMEOUT_UPDATE (1U << 4)
+#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5)
#define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME)
#define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE)
/*
diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h
index 52b54d13f385..6acd4ccafbf7 100644
--- a/include/uapi/linux/mctp.h
+++ b/include/uapi/linux/mctp.h
@@ -10,6 +10,7 @@
#define __UAPI_MCTP_H
#include <linux/types.h>
+#include <linux/socket.h>
typedef __u8 mctp_eid_t;
@@ -18,11 +19,13 @@ struct mctp_addr {
};
struct sockaddr_mctp {
- unsigned short int smctp_family;
- int smctp_network;
+ __kernel_sa_family_t smctp_family;
+ __u16 __smctp_pad0;
+ unsigned int smctp_network;
struct mctp_addr smctp_addr;
__u8 smctp_type;
__u8 smctp_tag;
+ __u8 __smctp_pad1;
};
#define MCTP_NET_ANY 0x0
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8dd73a64f921..b1cb1dbf7417 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -657,7 +657,7 @@ static int audit_filter_rules(struct task_struct *tsk,
result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val);
break;
case AUDIT_SADDR_FAM:
- if (ctx->sockaddr)
+ if (ctx && ctx->sockaddr)
result = audit_comparator(ctx->sockaddr->ss_family,
f->op, f->val);
break;
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index cebd4fb06d19..447def540544 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -1072,6 +1072,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr)
INIT_WORK(&aux->work, prog_array_map_clear_deferred);
INIT_LIST_HEAD(&aux->poke_progs);
mutex_init(&aux->poke_mutex);
+ spin_lock_init(&aux->owner.lock);
map = array_map_alloc(attr);
if (IS_ERR(map)) {
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index d6b7dfdd8066..6e3ae90ad107 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -524,6 +524,7 @@ int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON);
int bpf_jit_harden __read_mostly;
long bpf_jit_limit __read_mostly;
+long bpf_jit_limit_max __read_mostly;
static void
bpf_prog_ksym_set_addr(struct bpf_prog *prog)
@@ -817,7 +818,8 @@ u64 __weak bpf_jit_alloc_exec_limit(void)
static int __init bpf_jit_charge_init(void)
{
/* Only used as heuristic here to derive limit. */
- bpf_jit_limit = min_t(u64, round_up(bpf_jit_alloc_exec_limit() >> 2,
+ bpf_jit_limit_max = bpf_jit_alloc_exec_limit();
+ bpf_jit_limit = min_t(u64, round_up(bpf_jit_limit_max >> 2,
PAGE_SIZE), LONG_MAX);
return 0;
}
@@ -1821,20 +1823,26 @@ static unsigned int __bpf_prog_ret0_warn(const void *ctx,
bool bpf_prog_array_compatible(struct bpf_array *array,
const struct bpf_prog *fp)
{
+ bool ret;
+
if (fp->kprobe_override)
return false;
- if (!array->aux->type) {
+ spin_lock(&array->aux->owner.lock);
+
+ if (!array->aux->owner.type) {
/* There's no owner yet where we could check for
* compatibility.
*/
- array->aux->type = fp->type;
- array->aux->jited = fp->jited;
- return true;
+ array->aux->owner.type = fp->type;
+ array->aux->owner.jited = fp->jited;
+ ret = true;
+ } else {
+ ret = array->aux->owner.type == fp->type &&
+ array->aux->owner.jited == fp->jited;
}
-
- return array->aux->type == fp->type &&
- array->aux->jited == fp->jited;
+ spin_unlock(&array->aux->owner.lock);
+ return ret;
}
static int bpf_check_tail_call(const struct bpf_prog *fp)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4e50c0bfdb7d..1cad6979a0d0 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -543,8 +543,10 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
array = container_of(map, struct bpf_array, map);
- type = array->aux->type;
- jited = array->aux->jited;
+ spin_lock(&array->aux->owner.lock);
+ type = array->aux->owner.type;
+ jited = array->aux->owner.jited;
+ spin_unlock(&array->aux->owner.lock);
}
seq_printf(m,
@@ -1337,12 +1339,11 @@ int generic_map_update_batch(struct bpf_map *map,
void __user *values = u64_to_user_ptr(attr->batch.values);
void __user *keys = u64_to_user_ptr(attr->batch.keys);
u32 value_size, cp, max_count;
- int ufd = attr->map_fd;
+ int ufd = attr->batch.map_fd;
void *key, *value;
struct fd f;
int err = 0;
- f = fdget(ufd);
if (attr->batch.elem_flags & ~BPF_F_LOCK)
return -EINVAL;
@@ -1367,6 +1368,7 @@ int generic_map_update_batch(struct bpf_map *map,
return -ENOMEM;
}
+ f = fdget(ufd); /* bpf_map_do_batch() guarantees ufd is valid */
for (cp = 0; cp < max_count; cp++) {
err = -EFAULT;
if (copy_from_user(key, keys + cp * map->key_size,
@@ -1386,6 +1388,7 @@ int generic_map_update_batch(struct bpf_map *map,
kvfree(value);
kvfree(key);
+ fdput(f);
return err;
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e76b55917905..de006552be8a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -13319,7 +13319,7 @@ BTF_SET_START(btf_non_sleepable_error_inject)
/* Three functions below can be called from sleepable and non-sleepable context.
* Assume non-sleepable from bpf safety point of view.
*/
-BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, __filemap_add_folio)
BTF_ID(func, should_fail_alloc_page)
BTF_ID(func, should_failslab)
BTF_SET_END(btf_non_sleepable_error_inject)
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 570b0c97392a..ea08f01d0111 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2187,8 +2187,10 @@ static void cgroup_kill_sb(struct super_block *sb)
* And don't kill the default root.
*/
if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root &&
- !percpu_ref_is_dying(&root->cgrp.self.refcnt))
+ !percpu_ref_is_dying(&root->cgrp.self.refcnt)) {
+ cgroup_bpf_offline(&root->cgrp);
percpu_ref_kill(&root->cgrp.self.refcnt);
+ }
cgroup_put(&root->cgrp);
kernfs_kill_sb(sb);
}
diff --git a/kernel/cred.c b/kernel/cred.c
index f784e08c2fbd..1ae0b4948a5a 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -225,8 +225,6 @@ struct cred *cred_alloc_blank(void)
#ifdef CONFIG_DEBUG_CREDENTIALS
new->magic = CRED_MAGIC;
#endif
- new->ucounts = get_ucounts(&init_ucounts);
-
if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
@@ -501,7 +499,7 @@ int commit_creds(struct cred *new)
inc_rlimit_ucounts(new->ucounts, UCOUNT_RLIMIT_NPROC, 1);
rcu_assign_pointer(task->real_cred, new);
rcu_assign_pointer(task->cred, new);
- if (new->user != old->user)
+ if (new->user != old->user || new->user_ns != old->user_ns)
dec_rlimit_ucounts(old->ucounts, UCOUNT_RLIMIT_NPROC, 1);
alter_cred_subscribers(old, -2);
@@ -669,7 +667,7 @@ int set_cred_ucounts(struct cred *new)
{
struct task_struct *task = current;
const struct cred *old = task->real_cred;
- struct ucounts *old_ucounts = new->ucounts;
+ struct ucounts *new_ucounts, *old_ucounts = new->ucounts;
if (new->user == old->user && new->user_ns == old->user_ns)
return 0;
@@ -681,9 +679,10 @@ int set_cred_ucounts(struct cred *new)
if (old_ucounts && old_ucounts->ns == new->user_ns && uid_eq(old_ucounts->uid, new->euid))
return 0;
- if (!(new->ucounts = alloc_ucounts(new->user_ns, new->euid)))
+ if (!(new_ucounts = alloc_ucounts(new->user_ns, new->euid)))
return -EAGAIN;
+ new->ucounts = new_ucounts;
if (old_ucounts)
put_ucounts(old_ucounts);
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
index 95445bd6eb72..7a14ca29c377 100644
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -552,7 +552,7 @@ static void active_cacheline_remove(struct dma_debug_entry *entry)
* Wrapper function for adding an entry to the hash.
* This function takes care of locking itself.
*/
-static void add_dma_entry(struct dma_debug_entry *entry)
+static void add_dma_entry(struct dma_debug_entry *entry, unsigned long attrs)
{
struct hash_bucket *bucket;
unsigned long flags;
@@ -566,7 +566,7 @@ static void add_dma_entry(struct dma_debug_entry *entry)
if (rc == -ENOMEM) {
pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
global_disable = true;
- } else if (rc == -EEXIST) {
+ } else if (rc == -EEXIST && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) {
err_printk(entry->dev, entry,
"cacheline tracking EEXIST, overlapping mappings aren't supported\n");
}
@@ -1191,7 +1191,8 @@ void debug_dma_map_single(struct device *dev, const void *addr,
EXPORT_SYMBOL(debug_dma_map_single);
void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
- size_t size, int direction, dma_addr_t dma_addr)
+ size_t size, int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1222,7 +1223,7 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
check_for_illegal_area(dev, addr, size);
}
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
@@ -1280,7 +1281,8 @@ void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
}
void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction)
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
struct scatterlist *s;
@@ -1289,6 +1291,12 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
if (unlikely(dma_debug_disabled()))
return;
+ for_each_sg(sg, s, nents, i) {
+ check_for_stack(dev, sg_page(s), s->offset);
+ if (!PageHighMem(sg_page(s)))
+ check_for_illegal_area(dev, sg_virt(s), s->length);
+ }
+
for_each_sg(sg, s, mapped_ents, i) {
entry = dma_entry_alloc();
if (!entry)
@@ -1304,15 +1312,9 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
entry->sg_call_ents = nents;
entry->sg_mapped_ents = mapped_ents;
- check_for_stack(dev, sg_page(s), s->offset);
-
- if (!PageHighMem(sg_page(s))) {
- check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
- }
-
check_sg_segment(dev, s);
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
}
@@ -1368,7 +1370,8 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
}
void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt)
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1398,7 +1401,7 @@ void debug_dma_alloc_coherent(struct device *dev, size_t size,
else
entry->pfn = page_to_pfn(virt_to_page(virt));
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_free_coherent(struct device *dev, size_t size,
@@ -1429,7 +1432,8 @@ void debug_dma_free_coherent(struct device *dev, size_t size,
}
void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
- int direction, dma_addr_t dma_addr)
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
struct dma_debug_entry *entry;
@@ -1449,7 +1453,7 @@ void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
entry->direction = direction;
entry->map_err_type = MAP_ERR_NOT_CHECKED;
- add_dma_entry(entry);
+ add_dma_entry(entry, attrs);
}
void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
diff --git a/kernel/dma/debug.h b/kernel/dma/debug.h
index 83643b3010b2..f525197d3cae 100644
--- a/kernel/dma/debug.h
+++ b/kernel/dma/debug.h
@@ -11,26 +11,30 @@
#ifdef CONFIG_DMA_API_DEBUG
extern void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
- int direction, dma_addr_t dma_addr);
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs);
extern void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
size_t size, int direction);
extern void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction);
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs);
extern void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
int nelems, int dir);
extern void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt);
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs);
extern void debug_dma_free_coherent(struct device *dev, size_t size,
void *virt, dma_addr_t addr);
extern void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
size_t size, int direction,
- dma_addr_t dma_addr);
+ dma_addr_t dma_addr,
+ unsigned long attrs);
extern void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
size_t size, int direction);
@@ -53,7 +57,8 @@ extern void debug_dma_sync_sg_for_device(struct device *dev,
#else /* CONFIG_DMA_API_DEBUG */
static inline void debug_dma_map_page(struct device *dev, struct page *page,
size_t offset, size_t size,
- int direction, dma_addr_t dma_addr)
+ int direction, dma_addr_t dma_addr,
+ unsigned long attrs)
{
}
@@ -63,7 +68,8 @@ static inline void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
}
static inline void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
- int nents, int mapped_ents, int direction)
+ int nents, int mapped_ents, int direction,
+ unsigned long attrs)
{
}
@@ -74,7 +80,8 @@ static inline void debug_dma_unmap_sg(struct device *dev,
}
static inline void debug_dma_alloc_coherent(struct device *dev, size_t size,
- dma_addr_t dma_addr, void *virt)
+ dma_addr_t dma_addr, void *virt,
+ unsigned long attrs)
{
}
@@ -85,7 +92,8 @@ static inline void debug_dma_free_coherent(struct device *dev, size_t size,
static inline void debug_dma_map_resource(struct device *dev, phys_addr_t addr,
size_t size, int direction,
- dma_addr_t dma_addr)
+ dma_addr_t dma_addr,
+ unsigned long attrs)
{
}
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
index 06fec5547e7c..8349a9f2c345 100644
--- a/kernel/dma/mapping.c
+++ b/kernel/dma/mapping.c
@@ -156,7 +156,7 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
else
addr = ops->map_page(dev, page, offset, size, dir, attrs);
- debug_dma_map_page(dev, page, offset, size, dir, addr);
+ debug_dma_map_page(dev, page, offset, size, dir, addr, attrs);
return addr;
}
@@ -195,7 +195,7 @@ static int __dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
ents = ops->map_sg(dev, sg, nents, dir, attrs);
if (ents > 0)
- debug_dma_map_sg(dev, sg, nents, ents, dir);
+ debug_dma_map_sg(dev, sg, nents, ents, dir, attrs);
else if (WARN_ON_ONCE(ents != -EINVAL && ents != -ENOMEM &&
ents != -EIO))
return -EIO;
@@ -249,12 +249,12 @@ EXPORT_SYMBOL(dma_map_sg_attrs);
* Returns 0 on success or a negative error code on error. The following
* error codes are supported with the given meaning:
*
- * -EINVAL - An invalid argument, unaligned access or other error
- * in usage. Will not succeed if retried.
- * -ENOMEM - Insufficient resources (like memory or IOVA space) to
- * complete the mapping. Should succeed if retried later.
- * -EIO - Legacy error code with an unknown meaning. eg. this is
- * returned if a lower level call returned DMA_MAPPING_ERROR.
+ * -EINVAL An invalid argument, unaligned access or other error
+ * in usage. Will not succeed if retried.
+ * -ENOMEM Insufficient resources (like memory or IOVA space) to
+ * complete the mapping. Should succeed if retried later.
+ * -EIO Legacy error code with an unknown meaning. eg. this is
+ * returned if a lower level call returned DMA_MAPPING_ERROR.
*/
int dma_map_sgtable(struct device *dev, struct sg_table *sgt,
enum dma_data_direction dir, unsigned long attrs)
@@ -305,7 +305,7 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
else if (ops->map_resource)
addr = ops->map_resource(dev, phys_addr, size, dir, attrs);
- debug_dma_map_resource(dev, phys_addr, size, dir, addr);
+ debug_dma_map_resource(dev, phys_addr, size, dir, addr, attrs);
return addr;
}
EXPORT_SYMBOL(dma_map_resource);
@@ -510,7 +510,7 @@ void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
else
return NULL;
- debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+ debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr, attrs);
return cpu_addr;
}
EXPORT_SYMBOL(dma_alloc_attrs);
@@ -566,7 +566,7 @@ struct page *dma_alloc_pages(struct device *dev, size_t size,
struct page *page = __dma_alloc_pages(dev, size, dma_handle, dir, gfp);
if (page)
- debug_dma_map_page(dev, page, 0, size, dir, *dma_handle);
+ debug_dma_map_page(dev, page, 0, size, dir, *dma_handle, 0);
return page;
}
EXPORT_SYMBOL_GPL(dma_alloc_pages);
@@ -644,7 +644,7 @@ struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
if (sgt) {
sgt->nents = 1;
- debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir);
+ debug_dma_map_sg(dev, sgt->sgl, sgt->orig_nents, 1, dir, attrs);
}
return sgt;
}
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index af24dc3febbe..6357c3580d07 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -167,7 +167,8 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
addr + PAGE_SIZE);
if (new_page) {
- err = mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL);
+ err = mem_cgroup_charge(page_folio(new_page), vma->vm_mm,
+ GFP_KERNEL);
if (err)
return err;
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 92ef7b68198c..59bea523c84b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6343,7 +6343,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
* make sure to submit it to avoid deadlocks.
*/
if (blk_needs_flush_plug(tsk))
- blk_schedule_flush_plug(tsk);
+ blk_flush_plug(tsk->plug, true);
}
static void sched_update_worker(struct task_struct *tsk)
@@ -8354,7 +8354,8 @@ int io_schedule_prepare(void)
int old_iowait = current->in_iowait;
current->in_iowait = 1;
- blk_schedule_flush_plug(current);
+ if (current->plug)
+ blk_flush_plug(current->plug, true);
return old_iowait;
}
@@ -8795,6 +8796,7 @@ void idle_task_exit(void)
finish_arch_post_lock_switch();
}
+ scs_task_reset(current);
/* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}
diff --git a/kernel/signal.c b/kernel/signal.c
index 952741f6d0f9..487bf4f5dadf 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -426,22 +426,10 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
*/
rcu_read_lock();
ucounts = task_ucounts(t);
- sigpending = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
- switch (sigpending) {
- case 1:
- if (likely(get_ucounts(ucounts)))
- break;
- fallthrough;
- case LONG_MAX:
- /*
- * we need to decrease the ucount in the userns tree on any
- * failure to avoid counts leaking.
- */
- dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1);
- rcu_read_unlock();
- return NULL;
- }
+ sigpending = inc_rlimit_get_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
rcu_read_unlock();
+ if (!sigpending)
+ return NULL;
if (override_rlimit || likely(sigpending <= task_rlimit(t, RLIMIT_SIGPENDING))) {
q = kmem_cache_alloc(sigqueue_cachep, gfp_flags);
@@ -450,8 +438,7 @@ __sigqueue_alloc(int sig, struct task_struct *t, gfp_t gfp_flags,
}
if (unlikely(q == NULL)) {
- if (dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING, 1))
- put_ucounts(ucounts);
+ dec_rlimit_put_ucounts(ucounts, UCOUNT_RLIMIT_SIGPENDING);
} else {
INIT_LIST_HEAD(&q->list);
q->flags = sigqueue_flags;
@@ -464,8 +451,8 @@ static void __sigqueue_free(struct sigqueue *q)
{
if (q->flags & SIGQUEUE_PREALLOC)
return;
- if (q->ucounts && dec_rlimit_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING, 1)) {
- put_ucounts(q->ucounts);
+ if (q->ucounts) {
+ dec_rlimit_put_ucounts(q->ucounts, UCOUNT_RLIMIT_SIGPENDING);
q->ucounts = NULL;
}
kmem_cache_free(sigqueue_cachep, q);
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index fa91f398f28b..1183c88634aa 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -816,7 +816,7 @@ blk_trace_request_get_cgid(struct request *rq)
* Records an action against a request. Will log the bio offset + size.
*
**/
-static void blk_add_trace_rq(struct request *rq, int error,
+static void blk_add_trace_rq(struct request *rq, blk_status_t error,
unsigned int nr_bytes, u32 what, u64 cgid)
{
struct blk_trace *bt;
@@ -834,7 +834,8 @@ static void blk_add_trace_rq(struct request *rq, int error,
what |= BLK_TC_ACT(BLK_TC_FS);
__blk_add_trace(bt, blk_rq_trace_sector(rq), nr_bytes, req_op(rq),
- rq->cmd_flags, what, error, 0, NULL, cgid);
+ rq->cmd_flags, what, blk_status_to_errno(error), 0,
+ NULL, cgid);
rcu_read_unlock();
}
@@ -863,7 +864,7 @@ static void blk_add_trace_rq_requeue(void *ignore, struct request *rq)
}
static void blk_add_trace_rq_complete(void *ignore, struct request *rq,
- int error, unsigned int nr_bytes)
+ blk_status_t error, unsigned int nr_bytes)
{
blk_add_trace_rq(rq, error, nr_bytes, BLK_TA_COMPLETE,
blk_trace_request_get_cgid(rq));
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7efbc8aaf7f6..feebf57c6458 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -2208,7 +2208,7 @@ static int ftrace_check_record(struct dyn_ftrace *rec, bool enable, bool update)
}
/**
- * ftrace_update_record, set a record that now is tracing or not
+ * ftrace_update_record - set a record that now is tracing or not
* @rec: the record to update
* @enable: set to true if the record is tracing, false to force disable
*
@@ -2221,7 +2221,7 @@ int ftrace_update_record(struct dyn_ftrace *rec, bool enable)
}
/**
- * ftrace_test_record, check if the record has been enabled or not
+ * ftrace_test_record - check if the record has been enabled or not
* @rec: the record to test
* @enable: set to true to check if enabled, false if it is disabled
*
@@ -2574,7 +2574,7 @@ struct ftrace_rec_iter {
};
/**
- * ftrace_rec_iter_start, start up iterating over traced functions
+ * ftrace_rec_iter_start - start up iterating over traced functions
*
* Returns an iterator handle that is used to iterate over all
* the records that represent address locations where functions
@@ -2605,7 +2605,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_start(void)
}
/**
- * ftrace_rec_iter_next, get the next record to process.
+ * ftrace_rec_iter_next - get the next record to process.
* @iter: The handle to the iterator.
*
* Returns the next iterator after the given iterator @iter.
@@ -2630,7 +2630,7 @@ struct ftrace_rec_iter *ftrace_rec_iter_next(struct ftrace_rec_iter *iter)
}
/**
- * ftrace_rec_iter_record, get the record at the iterator location
+ * ftrace_rec_iter_record - get the record at the iterator location
* @iter: The current iterator location
*
* Returns the record that the current @iter is at.
@@ -2733,7 +2733,7 @@ static int __ftrace_modify_code(void *data)
}
/**
- * ftrace_run_stop_machine, go back to the stop machine method
+ * ftrace_run_stop_machine - go back to the stop machine method
* @command: The command to tell ftrace what to do
*
* If an arch needs to fall back to the stop machine method, the
@@ -2745,7 +2745,7 @@ void ftrace_run_stop_machine(int command)
}
/**
- * arch_ftrace_update_code, modify the code to trace or not trace
+ * arch_ftrace_update_code - modify the code to trace or not trace
* @command: The command that needs to be done
*
* Archs can override this function if it does not need to
@@ -6977,7 +6977,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
struct ftrace_ops *op;
int bit;
- bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
+ bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START);
if (bit < 0)
return;
@@ -7052,7 +7052,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
{
int bit;
- bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
+ bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START);
if (bit < 0)
return;
@@ -7525,7 +7525,9 @@ void ftrace_kill(void)
}
/**
- * Test if ftrace is dead or not.
+ * ftrace_is_dead - Test if ftrace is dead or not.
+ *
+ * Returns 1 if ftrace is "dead", zero otherwise.
*/
int ftrace_is_dead(void)
{
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index c4a15aef36af..928867f527e7 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -904,8 +904,8 @@ static int __trace_eprobe_create(int argc, const char *argv[])
if (IS_ERR(ep)) {
ret = PTR_ERR(ep);
- /* This must return -ENOMEM, else there is a bug */
- WARN_ON_ONCE(ret != -ENOMEM);
+ /* This must return -ENOMEM or missing event, else there is a bug */
+ WARN_ON_ONCE(ret != -ENOMEM && ret != -ENODEV);
ep = NULL;
goto error;
}
diff --git a/kernel/ucount.c b/kernel/ucount.c
index bb51849e6375..eb03f3c68375 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -284,6 +284,55 @@ bool dec_rlimit_ucounts(struct ucounts *ucounts, enum ucount_type type, long v)
return (new == 0);
}
+static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts,
+ struct ucounts *last, enum ucount_type type)
+{
+ struct ucounts *iter, *next;
+ for (iter = ucounts; iter != last; iter = next) {
+ long dec = atomic_long_add_return(-1, &iter->ucount[type]);
+ WARN_ON_ONCE(dec < 0);
+ next = iter->ns->ucounts;
+ if (dec == 0)
+ put_ucounts(iter);
+ }
+}
+
+void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum ucount_type type)
+{
+ do_dec_rlimit_put_ucounts(ucounts, NULL, type);
+}
+
+long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum ucount_type type)
+{
+ /* Caller must hold a reference to ucounts */
+ struct ucounts *iter;
+ long dec, ret = 0;
+
+ for (iter = ucounts; iter; iter = iter->ns->ucounts) {
+ long max = READ_ONCE(iter->ns->ucount_max[type]);
+ long new = atomic_long_add_return(1, &iter->ucount[type]);
+ if (new < 0 || new > max)
+ goto unwind;
+ if (iter == ucounts)
+ ret = new;
+ /*
+ * Grab an extra ucount reference for the caller when
+ * the rlimit count was previously 0.
+ */
+ if (new != 1)
+ continue;
+ if (!get_ucounts(iter))
+ goto dec_unwind;
+ }
+ return ret;
+dec_unwind:
+ dec = atomic_long_add_return(-1, &iter->ucount[type]);
+ WARN_ON_ONCE(dec < 0);
+unwind:
+ do_dec_rlimit_put_ucounts(ucounts, iter, type);
+ return 0;
+}
+
bool is_ucounts_overlimit(struct ucounts *ucounts, enum ucount_type type, unsigned long max)
{
struct ucounts *iter;
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
index 451543937524..53e7eb1dd76c 100644
--- a/lib/flex_proportions.c
+++ b/lib/flex_proportions.c
@@ -217,11 +217,12 @@ static void fprop_reflect_period_percpu(struct fprop_global *p,
}
/* Event of type pl happened */
-void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
+void __fprop_add_percpu(struct fprop_global *p, struct fprop_local_percpu *pl,
+ long nr)
{
fprop_reflect_period_percpu(p, pl);
- percpu_counter_add_batch(&pl->events, 1, PROP_BATCH);
- percpu_counter_add(&p->events, 1);
+ percpu_counter_add_batch(&pl->events, nr, PROP_BATCH);
+ percpu_counter_add(&p->events, nr);
}
void fprop_fraction_percpu(struct fprop_global *p,
@@ -253,20 +254,29 @@ void fprop_fraction_percpu(struct fprop_global *p,
}
/*
- * Like __fprop_inc_percpu() except that event is counted only if the given
+ * Like __fprop_add_percpu() except that event is counted only if the given
* type has fraction smaller than @max_frac/FPROP_FRAC_BASE
*/
-void __fprop_inc_percpu_max(struct fprop_global *p,
- struct fprop_local_percpu *pl, int max_frac)
+void __fprop_add_percpu_max(struct fprop_global *p,
+ struct fprop_local_percpu *pl, int max_frac, long nr)
{
if (unlikely(max_frac < FPROP_FRAC_BASE)) {
unsigned long numerator, denominator;
+ s64 tmp;
fprop_fraction_percpu(p, pl, &numerator, &denominator);
- if (numerator >
- (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
+ /* Adding 'nr' to fraction exceeds max_frac/FPROP_FRAC_BASE? */
+ tmp = (u64)denominator * max_frac -
+ ((u64)numerator << FPROP_FRAC_SHIFT);
+ if (tmp < 0) {
+ /* Maximum fraction already exceeded? */
return;
+ } else if (tmp < nr * (FPROP_FRAC_BASE - max_frac)) {
+ /* Add just enough for the fraction to saturate */
+ nr = div_u64(tmp + FPROP_FRAC_BASE - max_frac - 1,
+ FPROP_FRAC_BASE - max_frac);
+ }
}
- __fprop_inc_percpu(p, pl);
+ __fprop_add_percpu(p, pl, nr);
}
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index c6e2f1f2c4d2..2709ab825499 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -631,7 +631,7 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_wake_up);
static inline void sbitmap_update_cpu_hint(struct sbitmap *sb, int cpu, int tag)
{
if (likely(!sb->round_robin && tag < sb->depth))
- *per_cpu_ptr(sb->alloc_hint, cpu) = tag;
+ data_race(*per_cpu_ptr(sb->alloc_hint, cpu) = tag);
}
void sbitmap_queue_clear_batch(struct sbitmap_queue *sbq, int offset,
diff --git a/mm/Makefile b/mm/Makefile
index fc60a40ce954..d6c0042e3aa0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -46,7 +46,7 @@ mmu-$(CONFIG_MMU) += process_vm_access.o
endif
obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
- maccess.o page-writeback.o \
+ maccess.o page-writeback.o folio-compat.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o percpu.o slab_common.o \
diff --git a/mm/compaction.c b/mm/compaction.c
index bfc93da1c2c7..fbc60f964c38 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1022,7 +1022,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
if (!TestClearPageLRU(page))
goto isolate_fail_put;
- lruvec = mem_cgroup_page_lruvec(page);
+ lruvec = folio_lruvec(page_folio(page));
/* If we already hold the lock, we can skip some rechecking */
if (lruvec != locked) {
@@ -1032,7 +1032,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
compact_lock_irqsave(&lruvec->lru_lock, &flags, cc);
locked = lruvec;
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, page_folio(page));
/* Try get exclusive access under lock */
if (!skip_updated) {
diff --git a/mm/damon/core-test.h b/mm/damon/core-test.h
index c938a9c34e6c..7008c3735e99 100644
--- a/mm/damon/core-test.h
+++ b/mm/damon/core-test.h
@@ -219,14 +219,14 @@ static void damon_test_split_regions_of(struct kunit *test)
r = damon_new_region(0, 22);
damon_add_region(r, t);
damon_split_regions_of(c, t, 2);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 2u);
+ KUNIT_EXPECT_LE(test, damon_nr_regions(t), 2u);
damon_free_target(t);
t = damon_new_target(42);
r = damon_new_region(0, 220);
damon_add_region(r, t);
damon_split_regions_of(c, t, 4);
- KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 4u);
+ KUNIT_EXPECT_LE(test, damon_nr_regions(t), 4u);
damon_free_target(t);
damon_destroy_ctx(c);
}
diff --git a/mm/filemap.c b/mm/filemap.c
index 44b4b551e430..5e206a429b57 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -834,6 +834,8 @@ EXPORT_SYMBOL(file_write_and_wait_range);
*/
void replace_page_cache_page(struct page *old, struct page *new)
{
+ struct folio *fold = page_folio(old);
+ struct folio *fnew = page_folio(new);
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *) = mapping->a_ops->freepage;
pgoff_t offset = old->index;
@@ -847,7 +849,7 @@ void replace_page_cache_page(struct page *old, struct page *new)
new->mapping = mapping;
new->index = offset;
- mem_cgroup_migrate(old, new);
+ mem_cgroup_migrate(fold, fnew);
xas_lock_irq(&xas);
xas_store(&xas, new);
@@ -869,26 +871,25 @@ void replace_page_cache_page(struct page *old, struct page *new)
}
EXPORT_SYMBOL_GPL(replace_page_cache_page);
-noinline int __add_to_page_cache_locked(struct page *page,
- struct address_space *mapping,
- pgoff_t offset, gfp_t gfp,
- void **shadowp)
+noinline int __filemap_add_folio(struct address_space *mapping,
+ struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp)
{
- XA_STATE(xas, &mapping->i_pages, offset);
- int huge = PageHuge(page);
+ XA_STATE(xas, &mapping->i_pages, index);
+ int huge = folio_test_hugetlb(folio);
int error;
bool charged = false;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(PageSwapBacked(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ VM_BUG_ON_FOLIO(folio_test_swapbacked(folio), folio);
mapping_set_update(&xas, mapping);
- get_page(page);
- page->mapping = mapping;
- page->index = offset;
+ folio_get(folio);
+ folio->mapping = mapping;
+ folio->index = index;
if (!huge) {
- error = mem_cgroup_charge(page, NULL, gfp);
+ error = mem_cgroup_charge(folio, NULL, gfp);
+ VM_BUG_ON_FOLIO(index & (folio_nr_pages(folio) - 1), folio);
if (error)
goto error;
charged = true;
@@ -900,7 +901,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
unsigned int order = xa_get_order(xas.xa, xas.xa_index);
void *entry, *old = NULL;
- if (order > thp_order(page))
+ if (order > folio_order(folio))
xas_split_alloc(&xas, xa_load(xas.xa, xas.xa_index),
order, gfp);
xas_lock_irq(&xas);
@@ -917,13 +918,13 @@ noinline int __add_to_page_cache_locked(struct page *page,
*shadowp = old;
/* entry may have been split before we acquired lock */
order = xa_get_order(xas.xa, xas.xa_index);
- if (order > thp_order(page)) {
+ if (order > folio_order(folio)) {
xas_split(&xas, old, order);
xas_reset(&xas);
}
}
- xas_store(&xas, page);
+ xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
@@ -931,7 +932,7 @@ noinline int __add_to_page_cache_locked(struct page *page,
/* hugetlb pages do not participate in page cache accounting */
if (!huge)
- __inc_lruvec_page_state(page, NR_FILE_PAGES);
+ __lruvec_stat_add_folio(folio, NR_FILE_PAGES);
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
@@ -939,19 +940,19 @@ unlock:
if (xas_error(&xas)) {
error = xas_error(&xas);
if (charged)
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(folio);
goto error;
}
- trace_mm_filemap_add_to_page_cache(page);
+ trace_mm_filemap_add_to_page_cache(&folio->page);
return 0;
error:
- page->mapping = NULL;
+ folio->mapping = NULL;
/* Leave page->index set: truncation relies upon it */
- put_page(page);
+ folio_put(folio);
return error;
}
-ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
+ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
/**
* add_to_page_cache_locked - add a locked page to the pagecache
@@ -968,59 +969,58 @@ ALLOW_ERROR_INJECTION(__add_to_page_cache_locked, ERRNO);
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
pgoff_t offset, gfp_t gfp_mask)
{
- return __add_to_page_cache_locked(page, mapping, offset,
+ return __filemap_add_folio(mapping, page_folio(page), offset,
gfp_mask, NULL);
}
EXPORT_SYMBOL(add_to_page_cache_locked);
-int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
+int filemap_add_folio(struct address_space *mapping, struct folio *folio,
+ pgoff_t index, gfp_t gfp)
{
void *shadow = NULL;
int ret;
- __SetPageLocked(page);
- ret = __add_to_page_cache_locked(page, mapping, offset,
- gfp_mask, &shadow);
+ __folio_set_locked(folio);
+ ret = __filemap_add_folio(mapping, folio, index, gfp, &shadow);
if (unlikely(ret))
- __ClearPageLocked(page);
+ __folio_clear_locked(folio);
else {
/*
- * The page might have been evicted from cache only
+ * The folio might have been evicted from cache only
* recently, in which case it should be activated like
- * any other repeatedly accessed page.
- * The exception is pages getting rewritten; evicting other
+ * any other repeatedly accessed folio.
+ * The exception is folios getting rewritten; evicting other
* data from the working set, only to cache data that will
* get overwritten with something else, is a waste of memory.
*/
- WARN_ON_ONCE(PageActive(page));
- if (!(gfp_mask & __GFP_WRITE) && shadow)
- workingset_refault(page, shadow);
- lru_cache_add(page);
+ WARN_ON_ONCE(folio_test_active(folio));
+ if (!(gfp & __GFP_WRITE) && shadow)
+ workingset_refault(folio, shadow);
+ folio_add_lru(folio);
}
return ret;
}
-EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
+EXPORT_SYMBOL_GPL(filemap_add_folio);
#ifdef CONFIG_NUMA
-struct page *__page_cache_alloc(gfp_t gfp)
+struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
{
int n;
- struct page *page;
+ struct folio *folio;
if (cpuset_do_page_mem_spread()) {
unsigned int cpuset_mems_cookie;
do {
cpuset_mems_cookie = read_mems_allowed_begin();
n = cpuset_mem_spread_node();
- page = __alloc_pages_node(n, gfp, 0);
- } while (!page && read_mems_allowed_retry(cpuset_mems_cookie));
+ folio = __folio_alloc_node(gfp, order, n);
+ } while (!folio && read_mems_allowed_retry(cpuset_mems_cookie));
- return page;
+ return folio;
}
- return alloc_pages(gfp, 0);
+ return folio_alloc(gfp, order);
}
-EXPORT_SYMBOL(__page_cache_alloc);
+EXPORT_SYMBOL(filemap_alloc_folio);
#endif
/*
@@ -1073,11 +1073,11 @@ EXPORT_SYMBOL(filemap_invalidate_unlock_two);
*/
#define PAGE_WAIT_TABLE_BITS 8
#define PAGE_WAIT_TABLE_SIZE (1 << PAGE_WAIT_TABLE_BITS)
-static wait_queue_head_t page_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
+static wait_queue_head_t folio_wait_table[PAGE_WAIT_TABLE_SIZE] __cacheline_aligned;
-static wait_queue_head_t *page_waitqueue(struct page *page)
+static wait_queue_head_t *folio_waitqueue(struct folio *folio)
{
- return &page_wait_table[hash_ptr(page, PAGE_WAIT_TABLE_BITS)];
+ return &folio_wait_table[hash_ptr(folio, PAGE_WAIT_TABLE_BITS)];
}
void __init pagecache_init(void)
@@ -1085,7 +1085,7 @@ void __init pagecache_init(void)
int i;
for (i = 0; i < PAGE_WAIT_TABLE_SIZE; i++)
- init_waitqueue_head(&page_wait_table[i]);
+ init_waitqueue_head(&folio_wait_table[i]);
page_writeback_init();
}
@@ -1140,10 +1140,10 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
*/
flags = wait->flags;
if (flags & WQ_FLAG_EXCLUSIVE) {
- if (test_bit(key->bit_nr, &key->page->flags))
+ if (test_bit(key->bit_nr, &key->folio->flags))
return -1;
if (flags & WQ_FLAG_CUSTOM) {
- if (test_and_set_bit(key->bit_nr, &key->page->flags))
+ if (test_and_set_bit(key->bit_nr, &key->folio->flags))
return -1;
flags |= WQ_FLAG_DONE;
}
@@ -1156,7 +1156,7 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
*
* So update the flags atomically, and wake up the waiter
* afterwards to avoid any races. This store-release pairs
- * with the load-acquire in wait_on_page_bit_common().
+ * with the load-acquire in folio_wait_bit_common().
*/
smp_store_release(&wait->flags, flags | WQ_FLAG_WOKEN);
wake_up_state(wait->private, mode);
@@ -1175,14 +1175,14 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
return (flags & WQ_FLAG_EXCLUSIVE) != 0;
}
-static void wake_up_page_bit(struct page *page, int bit_nr)
+static void folio_wake_bit(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
+ wait_queue_head_t *q = folio_waitqueue(folio);
struct wait_page_key key;
unsigned long flags;
wait_queue_entry_t bookmark;
- key.page = page;
+ key.folio = folio;
key.bit_nr = bit_nr;
key.page_match = 0;
@@ -1217,7 +1217,7 @@ static void wake_up_page_bit(struct page *page, int bit_nr)
* page waiters.
*/
if (!waitqueue_active(q) || !key.page_match) {
- ClearPageWaiters(page);
+ folio_clear_waiters(folio);
/*
* It's possible to miss clearing Waiters here, when we woke
* our page waiters, but the hashed waitqueue has waiters for
@@ -1229,19 +1229,19 @@ static void wake_up_page_bit(struct page *page, int bit_nr)
spin_unlock_irqrestore(&q->lock, flags);
}
-static void wake_up_page(struct page *page, int bit)
+static void folio_wake(struct folio *folio, int bit)
{
- if (!PageWaiters(page))
+ if (!folio_test_waiters(folio))
return;
- wake_up_page_bit(page, bit);
+ folio_wake_bit(folio, bit);
}
/*
- * A choice of three behaviors for wait_on_page_bit_common():
+ * A choice of three behaviors for folio_wait_bit_common():
*/
enum behavior {
EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
- * __lock_page() waiting on then setting PG_locked.
+ * __folio_lock() waiting on then setting PG_locked.
*/
SHARED, /* Hold ref to page and check the bit when woken, like
* wait_on_page_writeback() waiting on PG_writeback.
@@ -1252,16 +1252,16 @@ enum behavior {
};
/*
- * Attempt to check (or get) the page bit, and mark us done
+ * Attempt to check (or get) the folio flag, and mark us done
* if successful.
*/
-static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
+static inline bool folio_trylock_flag(struct folio *folio, int bit_nr,
struct wait_queue_entry *wait)
{
if (wait->flags & WQ_FLAG_EXCLUSIVE) {
- if (test_and_set_bit(bit_nr, &page->flags))
+ if (test_and_set_bit(bit_nr, &folio->flags))
return false;
- } else if (test_bit(bit_nr, &page->flags))
+ } else if (test_bit(bit_nr, &folio->flags))
return false;
wait->flags |= WQ_FLAG_WOKEN | WQ_FLAG_DONE;
@@ -1271,9 +1271,10 @@ static inline bool trylock_page_bit_common(struct page *page, int bit_nr,
/* How many times do we accept lock stealing from under a waiter? */
int sysctl_page_lock_unfairness = 5;
-static inline int wait_on_page_bit_common(wait_queue_head_t *q,
- struct page *page, int bit_nr, int state, enum behavior behavior)
+static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
+ int state, enum behavior behavior)
{
+ wait_queue_head_t *q = folio_waitqueue(folio);
int unfairness = sysctl_page_lock_unfairness;
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
@@ -1282,8 +1283,8 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
unsigned long pflags;
if (bit_nr == PG_locked &&
- !PageUptodate(page) && PageWorkingset(page)) {
- if (!PageSwapBacked(page)) {
+ !folio_test_uptodate(folio) && folio_test_workingset(folio)) {
+ if (!folio_test_swapbacked(folio)) {
delayacct_thrashing_start();
delayacct = true;
}
@@ -1293,7 +1294,7 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
init_wait(wait);
wait->func = wake_page_function;
- wait_page.page = page;
+ wait_page.folio = folio;
wait_page.bit_nr = bit_nr;
repeat:
@@ -1308,7 +1309,7 @@ repeat:
* Do one last check whether we can get the
* page bit synchronously.
*
- * Do the SetPageWaiters() marking before that
+ * Do the folio_set_waiters() marking before that
* to let any waker we _just_ missed know they
* need to wake us up (otherwise they'll never
* even go to the slow case that looks at the
@@ -1319,8 +1320,8 @@ repeat:
* lock to avoid races.
*/
spin_lock_irq(&q->lock);
- SetPageWaiters(page);
- if (!trylock_page_bit_common(page, bit_nr, wait))
+ folio_set_waiters(folio);
+ if (!folio_trylock_flag(folio, bit_nr, wait))
__add_wait_queue_entry_tail(q, wait);
spin_unlock_irq(&q->lock);
@@ -1330,10 +1331,10 @@ repeat:
* see whether the page bit testing has already
* been done by the wake function.
*
- * We can drop our reference to the page.
+ * We can drop our reference to the folio.
*/
if (behavior == DROP)
- put_page(page);
+ folio_put(folio);
/*
* Note that until the "finish_wait()", or until
@@ -1370,7 +1371,7 @@ repeat:
*
* And if that fails, we'll have to retry this all.
*/
- if (unlikely(test_and_set_bit(bit_nr, &page->flags)))
+ if (unlikely(test_and_set_bit(bit_nr, folio_flags(folio, 0))))
goto repeat;
wait->flags |= WQ_FLAG_DONE;
@@ -1379,7 +1380,7 @@ repeat:
/*
* If a signal happened, this 'finish_wait()' may remove the last
- * waiter from the wait-queues, but the PageWaiters bit will remain
+ * waiter from the wait-queues, but the folio waiters bit will remain
* set. That's ok. The next wakeup will take care of it, and trying
* to do it here would be difficult and prone to races.
*/
@@ -1410,19 +1411,17 @@ repeat:
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
-void wait_on_page_bit(struct page *page, int bit_nr)
+void folio_wait_bit(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
+ folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
-EXPORT_SYMBOL(wait_on_page_bit);
+EXPORT_SYMBOL(folio_wait_bit);
-int wait_on_page_bit_killable(struct page *page, int bit_nr)
+int folio_wait_bit_killable(struct folio *folio, int bit_nr)
{
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
+ return folio_wait_bit_common(folio, bit_nr, TASK_KILLABLE, SHARED);
}
-EXPORT_SYMBOL(wait_on_page_bit_killable);
+EXPORT_SYMBOL(folio_wait_bit_killable);
/**
* put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
@@ -1439,31 +1438,28 @@ EXPORT_SYMBOL(wait_on_page_bit_killable);
*/
int put_and_wait_on_page_locked(struct page *page, int state)
{
- wait_queue_head_t *q;
-
- page = compound_head(page);
- q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, state, DROP);
+ return folio_wait_bit_common(page_folio(page), PG_locked, state,
+ DROP);
}
/**
- * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
- * @page: Page defining the wait queue of interest
+ * folio_add_wait_queue - Add an arbitrary waiter to a folio's wait queue
+ * @folio: Folio defining the wait queue of interest
* @waiter: Waiter to add to the queue
*
- * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ * Add an arbitrary @waiter to the wait queue for the nominated @folio.
*/
-void add_page_wait_queue(struct page *page, wait_queue_entry_t *waiter)
+void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter)
{
- wait_queue_head_t *q = page_waitqueue(page);
+ wait_queue_head_t *q = folio_waitqueue(folio);
unsigned long flags;
spin_lock_irqsave(&q->lock, flags);
__add_wait_queue_entry_tail(q, waiter);
- SetPageWaiters(page);
+ folio_set_waiters(folio);
spin_unlock_irqrestore(&q->lock, flags);
}
-EXPORT_SYMBOL_GPL(add_page_wait_queue);
+EXPORT_SYMBOL_GPL(folio_add_wait_queue);
#ifndef clear_bit_unlock_is_negative_byte
@@ -1489,124 +1485,116 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem
#endif
/**
- * unlock_page - unlock a locked page
- * @page: the page
+ * folio_unlock - Unlock a locked folio.
+ * @folio: The folio.
*
- * Unlocks the page and wakes up sleepers in wait_on_page_locked().
- * Also wakes sleepers in wait_on_page_writeback() because the wakeup
- * mechanism between PageLocked pages and PageWriteback pages is shared.
- * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
+ * Unlocks the folio and wakes up any thread sleeping on the page lock.
*
- * Note that this depends on PG_waiters being the sign bit in the byte
- * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
- * clear the PG_locked bit and test PG_waiters at the same time fairly
- * portably (architectures that do LL/SC can test any bit, while x86 can
- * test the sign bit).
+ * Context: May be called from interrupt or process context. May not be
+ * called from NMI context.
*/
-void unlock_page(struct page *page)
+void folio_unlock(struct folio *folio)
{
+ /* Bit 7 allows x86 to check the byte's sign bit */
BUILD_BUG_ON(PG_waiters != 7);
- page = compound_head(page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
- wake_up_page_bit(page, PG_locked);
+ BUILD_BUG_ON(PG_locked > 7);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0)))
+ folio_wake_bit(folio, PG_locked);
}
-EXPORT_SYMBOL(unlock_page);
+EXPORT_SYMBOL(folio_unlock);
/**
- * end_page_private_2 - Clear PG_private_2 and release any waiters
- * @page: The page
+ * folio_end_private_2 - Clear PG_private_2 and wake any waiters.
+ * @folio: The folio.
*
- * Clear the PG_private_2 bit on a page and wake up any sleepers waiting for
- * this. The page ref held for PG_private_2 being set is released.
+ * Clear the PG_private_2 bit on a folio and wake up any sleepers waiting for
+ * it. The folio reference held for PG_private_2 being set is released.
*
- * This is, for example, used when a netfs page is being written to a local
- * disk cache, thereby allowing writes to the cache for the same page to be
+ * This is, for example, used when a netfs folio is being written to a local
+ * disk cache, thereby allowing writes to the cache for the same folio to be
* serialised.
*/
-void end_page_private_2(struct page *page)
+void folio_end_private_2(struct folio *folio)
{
- page = compound_head(page);
- VM_BUG_ON_PAGE(!PagePrivate2(page), page);
- clear_bit_unlock(PG_private_2, &page->flags);
- wake_up_page_bit(page, PG_private_2);
- put_page(page);
+ VM_BUG_ON_FOLIO(!folio_test_private_2(folio), folio);
+ clear_bit_unlock(PG_private_2, folio_flags(folio, 0));
+ folio_wake_bit(folio, PG_private_2);
+ folio_put(folio);
}
-EXPORT_SYMBOL(end_page_private_2);
+EXPORT_SYMBOL(folio_end_private_2);
/**
- * wait_on_page_private_2 - Wait for PG_private_2 to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_private_2 - Wait for PG_private_2 to be cleared on a folio.
+ * @folio: The folio to wait on.
*
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page.
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio.
*/
-void wait_on_page_private_2(struct page *page)
+void folio_wait_private_2(struct folio *folio)
{
- page = compound_head(page);
- while (PagePrivate2(page))
- wait_on_page_bit(page, PG_private_2);
+ while (folio_test_private_2(folio))
+ folio_wait_bit(folio, PG_private_2);
}
-EXPORT_SYMBOL(wait_on_page_private_2);
+EXPORT_SYMBOL(folio_wait_private_2);
/**
- * wait_on_page_private_2_killable - Wait for PG_private_2 to be cleared on a page
- * @page: The page to wait on
+ * folio_wait_private_2_killable - Wait for PG_private_2 to be cleared on a folio.
+ * @folio: The folio to wait on.
*
- * Wait for PG_private_2 (aka PG_fscache) to be cleared on a page or until a
+ * Wait for PG_private_2 (aka PG_fscache) to be cleared on a folio or until a
* fatal signal is received by the calling task.
*
* Return:
* - 0 if successful.
* - -EINTR if a fatal signal was encountered.
*/
-int wait_on_page_private_2_killable(struct page *page)
+int folio_wait_private_2_killable(struct folio *folio)
{
int ret = 0;
- page = compound_head(page);
- while (PagePrivate2(page)) {
- ret = wait_on_page_bit_killable(page, PG_private_2);
+ while (folio_test_private_2(folio)) {
+ ret = folio_wait_bit_killable(folio, PG_private_2);
if (ret < 0)
break;
}
return ret;
}
-EXPORT_SYMBOL(wait_on_page_private_2_killable);
+EXPORT_SYMBOL(folio_wait_private_2_killable);
/**
- * end_page_writeback - end writeback against a page
- * @page: the page
+ * folio_end_writeback - End writeback against a folio.
+ * @folio: The folio.
*/
-void end_page_writeback(struct page *page)
+void folio_end_writeback(struct folio *folio)
{
/*
- * TestClearPageReclaim could be used here but it is an atomic
- * operation and overkill in this particular case. Failing to
- * shuffle a page marked for immediate reclaim is too mild to
- * justify taking an atomic operation penalty at the end of
- * ever page writeback.
+ * folio_test_clear_reclaim() could be used here but it is an
+ * atomic operation and overkill in this particular case. Failing
+ * to shuffle a folio marked for immediate reclaim is too mild
+ * a gain to justify taking an atomic operation penalty at the
+ * end of every folio writeback.
*/
- if (PageReclaim(page)) {
- ClearPageReclaim(page);
- rotate_reclaimable_page(page);
+ if (folio_test_reclaim(folio)) {
+ folio_clear_reclaim(folio);
+ folio_rotate_reclaimable(folio);
}
/*
- * Writeback does not hold a page reference of its own, relying
+ * Writeback does not hold a folio reference of its own, relying
* on truncation to wait for the clearing of PG_writeback.
- * But here we must make sure that the page is not freed and
- * reused before the wake_up_page().
+ * But here we must make sure that the folio is not freed and
+ * reused before the folio_wake().
*/
- get_page(page);
- if (!test_clear_page_writeback(page))
+ folio_get(folio);
+ if (!__folio_end_writeback(folio))
BUG();
smp_mb__after_atomic();
- wake_up_page(page, PG_writeback);
- put_page(page);
+ folio_wake(folio, PG_writeback);
+ folio_put(folio);
}
-EXPORT_SYMBOL(end_page_writeback);
+EXPORT_SYMBOL(folio_end_writeback);
/*
* After completing I/O on a page, call this routine to update the page
@@ -1637,39 +1625,35 @@ void page_endio(struct page *page, bool is_write, int err)
EXPORT_SYMBOL_GPL(page_endio);
/**
- * __lock_page - get a lock on the page, assuming we need to sleep to get it
- * @__page: the page to lock
+ * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it.
+ * @folio: The folio to lock
*/
-void __lock_page(struct page *__page)
+void __folio_lock(struct folio *folio)
{
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+ folio_wait_bit_common(folio, PG_locked, TASK_UNINTERRUPTIBLE,
EXCLUSIVE);
}
-EXPORT_SYMBOL(__lock_page);
+EXPORT_SYMBOL(__folio_lock);
-int __lock_page_killable(struct page *__page)
+int __folio_lock_killable(struct folio *folio)
{
- struct page *page = compound_head(__page);
- wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
+ return folio_wait_bit_common(folio, PG_locked, TASK_KILLABLE,
EXCLUSIVE);
}
-EXPORT_SYMBOL_GPL(__lock_page_killable);
+EXPORT_SYMBOL_GPL(__folio_lock_killable);
-int __lock_page_async(struct page *page, struct wait_page_queue *wait)
+static int __folio_lock_async(struct folio *folio, struct wait_page_queue *wait)
{
- struct wait_queue_head *q = page_waitqueue(page);
+ struct wait_queue_head *q = folio_waitqueue(folio);
int ret = 0;
- wait->page = page;
+ wait->folio = folio;
wait->bit_nr = PG_locked;
spin_lock_irq(&q->lock);
__add_wait_queue_entry_tail(q, &wait->wait);
- SetPageWaiters(page);
- ret = !trylock_page(page);
+ folio_set_waiters(folio);
+ ret = !folio_trylock(folio);
/*
* If we were successful now, we know we're still on the
* waitqueue as we're still under the lock. This means it's
@@ -1686,16 +1670,16 @@ int __lock_page_async(struct page *page, struct wait_page_queue *wait)
/*
* Return values:
- * 1 - page is locked; mmap_lock is still held.
- * 0 - page is not locked.
+ * true - folio is locked; mmap_lock is still held.
+ * false - folio is not locked.
* mmap_lock has been released (mmap_read_unlock(), unless flags had both
* FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_RETRY_NOWAIT set, in
* which case mmap_lock is still held.
*
- * If neither ALLOW_RETRY nor KILLABLE are set, will always return 1
- * with the page locked and the mmap_lock unperturbed.
+ * If neither ALLOW_RETRY nor KILLABLE are set, will always return true
+ * with the folio locked and the mmap_lock unperturbed.
*/
-int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
unsigned int flags)
{
if (fault_flag_allow_retry_first(flags)) {
@@ -1704,28 +1688,28 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
* even though return 0.
*/
if (flags & FAULT_FLAG_RETRY_NOWAIT)
- return 0;
+ return false;
mmap_read_unlock(mm);
if (flags & FAULT_FLAG_KILLABLE)
- wait_on_page_locked_killable(page);
+ folio_wait_locked_killable(folio);
else
- wait_on_page_locked(page);
- return 0;
+ folio_wait_locked(folio);
+ return false;
}
if (flags & FAULT_FLAG_KILLABLE) {
- int ret;
+ bool ret;
- ret = __lock_page_killable(page);
+ ret = __folio_lock_killable(folio);
if (ret) {
mmap_read_unlock(mm);
- return 0;
+ return false;
}
} else {
- __lock_page(page);
+ __folio_lock(folio);
}
- return 1;
+ return true;
}
/**
@@ -1801,143 +1785,155 @@ pgoff_t page_cache_prev_miss(struct address_space *mapping,
EXPORT_SYMBOL(page_cache_prev_miss);
/*
+ * Lockless page cache protocol:
+ * On the lookup side:
+ * 1. Load the folio from i_pages
+ * 2. Increment the refcount if it's not zero
+ * 3. If the folio is not found by xas_reload(), put the refcount and retry
+ *
+ * On the removal side:
+ * A. Freeze the page (by zeroing the refcount if nobody else has a reference)
+ * B. Remove the page from i_pages
+ * C. Return the page to the page allocator
+ *
+ * This means that any page may have its reference count temporarily
+ * increased by a speculative page cache (or fast GUP) lookup as it can
+ * be allocated by another user before the RCU grace period expires.
+ * Because the refcount temporarily acquired here may end up being the
+ * last refcount on the page, any page allocation must be freeable by
+ * folio_put().
+ */
+
+/*
* mapping_get_entry - Get a page cache entry.
* @mapping: the address_space to search
* @index: The page cache index.
*
- * Looks up the page cache slot at @mapping & @index. If there is a
- * page cache page, the head page is returned with an increased refcount.
+ * Looks up the page cache entry at @mapping & @index. If it is a folio,
+ * it is returned with an increased refcount. If it is a shadow entry
+ * of a previously evicted folio, or a swap entry from shmem/tmpfs,
+ * it is returned without further action.
*
- * If the slot holds a shadow entry of a previously evicted page, or a
- * swap entry from shmem/tmpfs, it is returned.
- *
- * Return: The head page or shadow entry, %NULL if nothing is found.
+ * Return: The folio, swap or shadow entry, %NULL if nothing is found.
*/
-static struct page *mapping_get_entry(struct address_space *mapping,
- pgoff_t index)
+static void *mapping_get_entry(struct address_space *mapping, pgoff_t index)
{
XA_STATE(xas, &mapping->i_pages, index);
- struct page *page;
+ struct folio *folio;
rcu_read_lock();
repeat:
xas_reset(&xas);
- page = xas_load(&xas);
- if (xas_retry(&xas, page))
+ folio = xas_load(&xas);
+ if (xas_retry(&xas, folio))
goto repeat;
/*
* A shadow entry of a recently evicted page, or a swap entry from
* shmem/tmpfs. Return it without attempting to raise page count.
*/
- if (!page || xa_is_value(page))
+ if (!folio || xa_is_value(folio))
goto out;
- if (!page_cache_get_speculative(page))
+ if (!folio_try_get_rcu(folio))
goto repeat;
- /*
- * Has the page moved or been split?
- * This is part of the lockless pagecache protocol. See
- * include/linux/pagemap.h for details.
- */
- if (unlikely(page != xas_reload(&xas))) {
- put_page(page);
+ if (unlikely(folio != xas_reload(&xas))) {
+ folio_put(folio);
goto repeat;
}
out:
rcu_read_unlock();
- return page;
+ return folio;
}
/**
- * pagecache_get_page - Find and get a reference to a page.
+ * __filemap_get_folio - Find and get a reference to a folio.
* @mapping: The address_space to search.
* @index: The page index.
- * @fgp_flags: %FGP flags modify how the page is returned.
- * @gfp_mask: Memory allocation flags to use if %FGP_CREAT is specified.
+ * @fgp_flags: %FGP flags modify how the folio is returned.
+ * @gfp: Memory allocation flags to use if %FGP_CREAT is specified.
*
* Looks up the page cache entry at @mapping & @index.
*
* @fgp_flags can be zero or more of these flags:
*
- * * %FGP_ACCESSED - The page will be marked accessed.
- * * %FGP_LOCK - The page is returned locked.
- * * %FGP_HEAD - If the page is present and a THP, return the head page
- * rather than the exact page specified by the index.
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
* * %FGP_ENTRY - If there is a shadow / swap / DAX entry, return it
- * instead of allocating a new page to replace it.
+ * instead of allocating a new folio to replace it.
* * %FGP_CREAT - If no page is present then a new page is allocated using
- * @gfp_mask and added to the page cache and the VM's LRU list.
+ * @gfp and added to the page cache and the VM's LRU list.
* The page is returned locked and with an increased refcount.
* * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
* page is already in cache. If the page was allocated, unlock it before
* returning so the caller can do the same dance.
- * * %FGP_WRITE - The page will be written
- * * %FGP_NOFS - __GFP_FS will get cleared in gfp mask
- * * %FGP_NOWAIT - Don't get blocked by page lock
+ * * %FGP_WRITE - The page will be written to by the caller.
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
+ * * %FGP_NOWAIT - Don't get blocked by page lock.
+ * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
*
* If %FGP_LOCK or %FGP_CREAT are specified then the function may sleep even
* if the %GFP flags specified for %FGP_CREAT are atomic.
*
* If there is a page cache page, it is returned with an increased refcount.
*
- * Return: The found page or %NULL otherwise.
+ * Return: The found folio or %NULL otherwise.
*/
-struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
- int fgp_flags, gfp_t gfp_mask)
+struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp)
{
- struct page *page;
+ struct folio *folio;
repeat:
- page = mapping_get_entry(mapping, index);
- if (xa_is_value(page)) {
+ folio = mapping_get_entry(mapping, index);
+ if (xa_is_value(folio)) {
if (fgp_flags & FGP_ENTRY)
- return page;
- page = NULL;
+ return folio;
+ folio = NULL;
}
- if (!page)
+ if (!folio)
goto no_page;
if (fgp_flags & FGP_LOCK) {
if (fgp_flags & FGP_NOWAIT) {
- if (!trylock_page(page)) {
- put_page(page);
+ if (!folio_trylock(folio)) {
+ folio_put(folio);
return NULL;
}
} else {
- lock_page(page);
+ folio_lock(folio);
}
/* Has the page been truncated? */
- if (unlikely(page->mapping != mapping)) {
- unlock_page(page);
- put_page(page);
+ if (unlikely(folio->mapping != mapping)) {
+ folio_unlock(folio);
+ folio_put(folio);
goto repeat;
}
- VM_BUG_ON_PAGE(!thp_contains(page, index), page);
+ VM_BUG_ON_FOLIO(!folio_contains(folio, index), folio);
}
if (fgp_flags & FGP_ACCESSED)
- mark_page_accessed(page);
+ folio_mark_accessed(folio);
else if (fgp_flags & FGP_WRITE) {
/* Clear idle flag for buffer write */
- if (page_is_idle(page))
- clear_page_idle(page);
+ if (folio_test_idle(folio))
+ folio_clear_idle(folio);
}
- if (!(fgp_flags & FGP_HEAD))
- page = find_subpage(page, index);
+ if (fgp_flags & FGP_STABLE)
+ folio_wait_stable(folio);
no_page:
- if (!page && (fgp_flags & FGP_CREAT)) {
+ if (!folio && (fgp_flags & FGP_CREAT)) {
int err;
if ((fgp_flags & FGP_WRITE) && mapping_can_writeback(mapping))
- gfp_mask |= __GFP_WRITE;
+ gfp |= __GFP_WRITE;
if (fgp_flags & FGP_NOFS)
- gfp_mask &= ~__GFP_FS;
+ gfp &= ~__GFP_FS;
- page = __page_cache_alloc(gfp_mask);
- if (!page)
+ folio = filemap_alloc_folio(gfp, 0);
+ if (!folio)
return NULL;
if (WARN_ON_ONCE(!(fgp_flags & (FGP_LOCK | FGP_FOR_MMAP))))
@@ -1945,27 +1941,27 @@ no_page:
/* Init accessed so avoid atomic mark_page_accessed later */
if (fgp_flags & FGP_ACCESSED)
- __SetPageReferenced(page);
+ __folio_set_referenced(folio);
- err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+ err = filemap_add_folio(mapping, folio, index, gfp);
if (unlikely(err)) {
- put_page(page);
- page = NULL;
+ folio_put(folio);
+ folio = NULL;
if (err == -EEXIST)
goto repeat;
}
/*
- * add_to_page_cache_lru locks the page, and for mmap we expect
- * an unlocked page.
+ * filemap_add_folio locks the page, and for mmap
+ * we expect an unlocked page.
*/
- if (page && (fgp_flags & FGP_FOR_MMAP))
- unlock_page(page);
+ if (folio && (fgp_flags & FGP_FOR_MMAP))
+ folio_unlock(folio);
}
- return page;
+ return folio;
}
-EXPORT_SYMBOL(pagecache_get_page);
+EXPORT_SYMBOL(__filemap_get_folio);
static inline struct page *find_get_entry(struct xa_state *xas, pgoff_t max,
xa_mark_t mark)
@@ -2420,6 +2416,7 @@ static int filemap_update_page(struct kiocb *iocb,
struct address_space *mapping, struct iov_iter *iter,
struct page *page)
{
+ struct folio *folio = page_folio(page);
int error;
if (iocb->ki_flags & IOCB_NOWAIT) {
@@ -2429,40 +2426,40 @@ static int filemap_update_page(struct kiocb *iocb,
filemap_invalidate_lock_shared(mapping);
}
- if (!trylock_page(page)) {
+ if (!folio_trylock(folio)) {
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOWAIT | IOCB_NOIO))
goto unlock_mapping;
if (!(iocb->ki_flags & IOCB_WAITQ)) {
filemap_invalidate_unlock_shared(mapping);
- put_and_wait_on_page_locked(page, TASK_KILLABLE);
+ put_and_wait_on_page_locked(&folio->page, TASK_KILLABLE);
return AOP_TRUNCATED_PAGE;
}
- error = __lock_page_async(page, iocb->ki_waitq);
+ error = __folio_lock_async(folio, iocb->ki_waitq);
if (error)
goto unlock_mapping;
}
error = AOP_TRUNCATED_PAGE;
- if (!page->mapping)
+ if (!folio->mapping)
goto unlock;
error = 0;
- if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, page))
+ if (filemap_range_uptodate(mapping, iocb->ki_pos, iter, &folio->page))
goto unlock;
error = -EAGAIN;
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
- error = filemap_read_page(iocb->ki_filp, mapping, page);
+ error = filemap_read_page(iocb->ki_filp, mapping, &folio->page);
goto unlock_mapping;
unlock:
- unlock_page(page);
+ folio_unlock(folio);
unlock_mapping:
filemap_invalidate_unlock_shared(mapping);
if (error == AOP_TRUNCATED_PAGE)
- put_page(page);
+ folio_put(folio);
return error;
}
@@ -2899,7 +2896,9 @@ unlock:
static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
struct file **fpin)
{
- if (trylock_page(page))
+ struct folio *folio = page_folio(page);
+
+ if (folio_trylock(folio))
return 1;
/*
@@ -2912,7 +2911,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
if (vmf->flags & FAULT_FLAG_KILLABLE) {
- if (__lock_page_killable(page)) {
+ if (__folio_lock_killable(folio)) {
/*
* We didn't have the right flags to drop the mmap_lock,
* but all fault_handlers only check for fatal signals
@@ -2924,11 +2923,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
return 0;
}
} else
- __lock_page(page);
+ __folio_lock(folio);
+
return 1;
}
-
/*
* Synchronous readahead happens when we don't even find a page in the page
* cache at all. We don't want to perform IO under the mmap sem, so if we have
@@ -3707,28 +3706,6 @@ out:
}
EXPORT_SYMBOL(generic_file_direct_write);
-/*
- * Find or create a page at the given pagecache position. Return the locked
- * page. This function is specifically for buffered writes.
- */
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
- pgoff_t index, unsigned flags)
-{
- struct page *page;
- int fgp_flags = FGP_LOCK|FGP_WRITE|FGP_CREAT;
-
- if (flags & AOP_FLAG_NOFS)
- fgp_flags |= FGP_NOFS;
-
- page = pagecache_get_page(mapping, index, fgp_flags,
- mapping_gfp_mask(mapping));
- if (page)
- wait_for_stable_page(page);
-
- return page;
-}
-EXPORT_SYMBOL(grab_cache_page_write_begin);
-
ssize_t generic_perform_write(struct file *file,
struct iov_iter *i, loff_t pos)
{
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
new file mode 100644
index 000000000000..5b6ae1da314e
--- /dev/null
+++ b/mm/folio-compat.c
@@ -0,0 +1,142 @@
+/*
+ * Compatibility functions which bloat the callers too much to make inline.
+ * All of the callers of these functions should be converted to use folios
+ * eventually.
+ */
+
+#include <linux/migrate.h>
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+
+struct address_space *page_mapping(struct page *page)
+{
+ return folio_mapping(page_folio(page));
+}
+EXPORT_SYMBOL(page_mapping);
+
+void unlock_page(struct page *page)
+{
+ return folio_unlock(page_folio(page));
+}
+EXPORT_SYMBOL(unlock_page);
+
+void end_page_writeback(struct page *page)
+{
+ return folio_end_writeback(page_folio(page));
+}
+EXPORT_SYMBOL(end_page_writeback);
+
+void wait_on_page_writeback(struct page *page)
+{
+ return folio_wait_writeback(page_folio(page));
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+
+void wait_for_stable_page(struct page *page)
+{
+ return folio_wait_stable(page_folio(page));
+}
+EXPORT_SYMBOL_GPL(wait_for_stable_page);
+
+bool page_mapped(struct page *page)
+{
+ return folio_mapped(page_folio(page));
+}
+EXPORT_SYMBOL(page_mapped);
+
+void mark_page_accessed(struct page *page)
+{
+ folio_mark_accessed(page_folio(page));
+}
+EXPORT_SYMBOL(mark_page_accessed);
+
+#ifdef CONFIG_MIGRATION
+int migrate_page_move_mapping(struct address_space *mapping,
+ struct page *newpage, struct page *page, int extra_count)
+{
+ return folio_migrate_mapping(mapping, page_folio(newpage),
+ page_folio(page), extra_count);
+}
+EXPORT_SYMBOL(migrate_page_move_mapping);
+
+void migrate_page_states(struct page *newpage, struct page *page)
+{
+ folio_migrate_flags(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_states);
+
+void migrate_page_copy(struct page *newpage, struct page *page)
+{
+ folio_migrate_copy(page_folio(newpage), page_folio(page));
+}
+EXPORT_SYMBOL(migrate_page_copy);
+#endif
+
+bool set_page_writeback(struct page *page)
+{
+ return folio_start_writeback(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_writeback);
+
+bool set_page_dirty(struct page *page)
+{
+ return folio_mark_dirty(page_folio(page));
+}
+EXPORT_SYMBOL(set_page_dirty);
+
+int __set_page_dirty_nobuffers(struct page *page)
+{
+ return filemap_dirty_folio(page_mapping(page), page_folio(page));
+}
+EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+
+bool clear_page_dirty_for_io(struct page *page)
+{
+ return folio_clear_dirty_for_io(page_folio(page));
+}
+EXPORT_SYMBOL(clear_page_dirty_for_io);
+
+bool redirty_page_for_writepage(struct writeback_control *wbc,
+ struct page *page)
+{
+ return folio_redirty_for_writepage(wbc, page_folio(page));
+}
+EXPORT_SYMBOL(redirty_page_for_writepage);
+
+void lru_cache_add(struct page *page)
+{
+ folio_add_lru(page_folio(page));
+}
+EXPORT_SYMBOL(lru_cache_add);
+
+int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
+ pgoff_t index, gfp_t gfp)
+{
+ return filemap_add_folio(mapping, page_folio(page), index, gfp);
+}
+EXPORT_SYMBOL(add_to_page_cache_lru);
+
+noinline
+struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
+ int fgp_flags, gfp_t gfp)
+{
+ struct folio *folio;
+
+ folio = __filemap_get_folio(mapping, index, fgp_flags, gfp);
+ if ((fgp_flags & FGP_HEAD) || !folio || xa_is_value(folio))
+ return &folio->page;
+ return folio_file_page(folio, index);
+}
+EXPORT_SYMBOL(pagecache_get_page);
+
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+ pgoff_t index, unsigned flags)
+{
+ unsigned fgp_flags = FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE;
+
+ if (flags & AOP_FLAG_NOFS)
+ fgp_flags |= FGP_NOFS;
+ return pagecache_get_page(mapping, index, fgp_flags,
+ mapping_gfp_mask(mapping));
+}
+EXPORT_SYMBOL(grab_cache_page_write_begin);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 5e9ef0fc261e..e5483347291c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -603,7 +603,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
VM_BUG_ON_PAGE(!PageCompound(page), page);
- if (mem_cgroup_charge(page, vma->vm_mm, gfp)) {
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, gfp)) {
put_page(page);
count_vm_event(THP_FAULT_FALLBACK);
count_vm_event(THP_FAULT_FALLBACK_CHARGE);
@@ -2405,7 +2405,8 @@ static void __split_huge_page_tail(struct page *head, int tail,
static void __split_huge_page(struct page *page, struct list_head *list,
pgoff_t end)
{
- struct page *head = compound_head(page);
+ struct folio *folio = page_folio(page);
+ struct page *head = &folio->page;
struct lruvec *lruvec;
struct address_space *swap_cache = NULL;
unsigned long offset = 0;
@@ -2424,7 +2425,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
}
/* lock lru list/PageCompound, ref frozen by page_ref_freeze */
- lruvec = lock_page_lruvec(head);
+ lruvec = folio_lruvec_lock(folio);
+
+ ClearPageHasHWPoisoned(head);
for (i = nr - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
@@ -2700,12 +2703,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
if (mapping) {
int nr = thp_nr_pages(head);
- if (PageSwapBacked(head))
+ if (PageSwapBacked(head)) {
__mod_lruvec_page_state(head, NR_SHMEM_THPS,
-nr);
- else
+ } else {
__mod_lruvec_page_state(head, NR_FILE_THPS,
-nr);
+ filemap_nr_thps_dec(mapping);
+ }
}
__split_huge_page(page, list, end);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 95dc7b83381f..6378c1066459 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5302,7 +5302,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
*pagep = NULL;
goto out;
}
- copy_huge_page(page, *pagep);
+ folio_copy(page_folio(page), page_folio(*pagep));
put_page(*pagep);
*pagep = NULL;
}
diff --git a/mm/internal.h b/mm/internal.h
index cf3cb933eba3..b1001ebeb286 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -34,7 +34,16 @@
void page_writeback_init(void);
+static inline void *folio_raw_mapping(struct folio *folio)
+{
+ unsigned long mapping = (unsigned long)folio->mapping;
+
+ return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
+}
+
vm_fault_t do_swap_page(struct vm_fault *vmf);
+void folio_rotate_reclaimable(struct folio *folio);
+bool __folio_end_writeback(struct folio *folio);
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
unsigned long floor, unsigned long ceiling);
@@ -63,17 +72,28 @@ unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
/**
- * page_evictable - test whether a page is evictable
- * @page: the page to test
+ * folio_evictable - Test whether a folio is evictable.
+ * @folio: The folio to test.
*
- * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
- *
- * Reasons page might not be evictable:
- * (1) page's mapping marked unevictable
- * (2) page is part of an mlocked VMA
+ * Test whether @folio is evictable -- i.e., should be placed on
+ * active/inactive lists vs unevictable list.
*
+ * Reasons folio might not be evictable:
+ * 1. folio's mapping marked unevictable
+ * 2. One of the pages in the folio is part of an mlocked VMA
*/
+static inline bool folio_evictable(struct folio *folio)
+{
+ bool ret;
+
+ /* Prevent address_space of inode and swap cache from being freed */
+ rcu_read_lock();
+ ret = !mapping_unevictable(folio_mapping(folio)) &&
+ !folio_test_mlocked(folio);
+ rcu_read_unlock();
+ return ret;
+}
+
static inline bool page_evictable(struct page *page)
{
bool ret;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 045cc579f724..5f02fda6f265 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -445,22 +445,25 @@ static bool hugepage_vma_check(struct vm_area_struct *vma,
if (!transhuge_vma_enabled(vma, vm_flags))
return false;
+ if (vma->vm_file && !IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) -
+ vma->vm_pgoff, HPAGE_PMD_NR))
+ return false;
+
/* Enabled via shmem mount options or sysfs settings. */
- if (shmem_file(vma->vm_file) && shmem_huge_enabled(vma)) {
- return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR);
- }
+ if (shmem_file(vma->vm_file))
+ return shmem_huge_enabled(vma);
/* THP settings require madvise. */
if (!(vm_flags & VM_HUGEPAGE) && !khugepaged_always())
return false;
- /* Read-only file mappings need to be aligned for THP to work. */
+ /* Only regular file is valid */
if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && vma->vm_file &&
- !inode_is_open_for_write(vma->vm_file->f_inode) &&
(vm_flags & VM_EXEC)) {
- return IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
- HPAGE_PMD_NR);
+ struct inode *inode = vma->vm_file->f_inode;
+
+ return !inode_is_open_for_write(inode) &&
+ S_ISREG(inode->i_mode);
}
if (!vma->anon_vma || vma->vm_ops)
@@ -1087,7 +1090,7 @@ static void collapse_huge_page(struct mm_struct *mm,
goto out_nolock;
}
- if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) {
+ if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out_nolock;
}
@@ -1211,7 +1214,7 @@ out_up_write:
mmap_write_unlock(mm);
out_nolock:
if (!IS_ERR_OR_NULL(*hpage))
- mem_cgroup_uncharge(*hpage);
+ mem_cgroup_uncharge(page_folio(*hpage));
trace_mm_collapse_huge_page(mm, isolated, result);
return;
}
@@ -1658,7 +1661,7 @@ static void collapse_file(struct mm_struct *mm,
goto out;
}
- if (unlikely(mem_cgroup_charge(new_page, mm, gfp))) {
+ if (unlikely(mem_cgroup_charge(page_folio(new_page), mm, gfp))) {
result = SCAN_CGROUP_CHARGE_FAIL;
goto out;
}
@@ -1763,6 +1766,10 @@ static void collapse_file(struct mm_struct *mm,
filemap_flush(mapping);
result = SCAN_FAIL;
goto xa_unlocked;
+ } else if (PageWriteback(page)) {
+ xas_unlock_irq(&xas);
+ result = SCAN_FAIL;
+ goto xa_unlocked;
} else if (trylock_page(page)) {
get_page(page);
xas_unlock_irq(&xas);
@@ -1798,7 +1805,8 @@ static void collapse_file(struct mm_struct *mm,
goto out_unlock;
}
- if (!is_shmem && PageDirty(page)) {
+ if (!is_shmem && (PageDirty(page) ||
+ PageWriteback(page))) {
/*
* khugepaged only works on read-only fd, so this
* page is dirty because it hasn't been flushed
@@ -1975,7 +1983,7 @@ xa_unlocked:
out:
VM_BUG_ON(!list_empty(&pagelist));
if (!IS_ERR_OR_NULL(*hpage))
- mem_cgroup_uncharge(*hpage);
+ mem_cgroup_uncharge(page_folio(*hpage));
/* TODO: tracepoints */
}
diff --git a/mm/ksm.c b/mm/ksm.c
index a5716fdec1aa..0662093237e4 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -751,7 +751,7 @@ stale:
/*
* We come here from above when page->mapping or !PageSwapCache
* suggests that the node is stale; but it might be under migration.
- * We need smp_rmb(), matching the smp_wmb() in ksm_migrate_page(),
+ * We need smp_rmb(), matching the smp_wmb() in folio_migrate_ksm(),
* before checking whether node->kpfn has been changed.
*/
smp_rmb();
@@ -852,9 +852,14 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma,
return err;
}
+static inline struct stable_node *folio_stable_node(struct folio *folio)
+{
+ return folio_test_ksm(folio) ? folio_raw_mapping(folio) : NULL;
+}
+
static inline struct stable_node *page_stable_node(struct page *page)
{
- return PageKsm(page) ? page_rmapping(page) : NULL;
+ return folio_stable_node(page_folio(page));
}
static inline void set_page_stable_node(struct page *page,
@@ -2578,7 +2583,8 @@ struct page *ksm_might_need_to_copy(struct page *page,
return page; /* let do_swap_page report the error */
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
- if (new_page && mem_cgroup_charge(new_page, vma->vm_mm, GFP_KERNEL)) {
+ if (new_page &&
+ mem_cgroup_charge(page_folio(new_page), vma->vm_mm, GFP_KERNEL)) {
put_page(new_page);
new_page = NULL;
}
@@ -2658,26 +2664,26 @@ again:
}
#ifdef CONFIG_MIGRATION
-void ksm_migrate_page(struct page *newpage, struct page *oldpage)
+void folio_migrate_ksm(struct folio *newfolio, struct folio *folio)
{
struct stable_node *stable_node;
- VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
- VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- VM_BUG_ON_PAGE(newpage->mapping != oldpage->mapping, newpage);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+ VM_BUG_ON_FOLIO(!folio_test_locked(newfolio), newfolio);
+ VM_BUG_ON_FOLIO(newfolio->mapping != folio->mapping, newfolio);
- stable_node = page_stable_node(newpage);
+ stable_node = folio_stable_node(folio);
if (stable_node) {
- VM_BUG_ON_PAGE(stable_node->kpfn != page_to_pfn(oldpage), oldpage);
- stable_node->kpfn = page_to_pfn(newpage);
+ VM_BUG_ON_FOLIO(stable_node->kpfn != folio_pfn(folio), folio);
+ stable_node->kpfn = folio_pfn(newfolio);
/*
- * newpage->mapping was set in advance; now we need smp_wmb()
+ * newfolio->mapping was set in advance; now we need smp_wmb()
* to make sure that the new stable_node->kpfn is visible
- * to get_ksm_page() before it can see that oldpage->mapping
- * has gone stale (or that PageSwapCache has been cleared).
+ * to get_ksm_page() before it can see that folio->mapping
+ * has gone stale (or that folio_test_swapcache has been cleared).
*/
smp_wmb();
- set_page_stable_node(oldpage, NULL);
+ set_page_stable_node(&folio->page, NULL);
}
}
#endif /* CONFIG_MIGRATION */
diff --git a/mm/memblock.c b/mm/memblock.c
index 5c3503c98b2f..5096500b2647 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -932,16 +932,14 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
* covered by the memory map. The struct page representing NOMAP memory
* frames in the memory map will be PageReserved()
*
+ * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from
+ * memblock, the caller must inform kmemleak to ignore that memory
+ *
* Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
{
- int ret = memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
-
- if (!ret)
- kmemleak_free_part_phys(base, size);
-
- return ret;
+ return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
}
/**
@@ -1692,7 +1690,7 @@ void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
if (!size)
return;
- if (memblock.memory.cnt <= 1) {
+ if (!memblock_memory->total_size) {
pr_warn("%s: No memory registered yet\n", __func__);
return;
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6da5020a8656..8dab23a71fc4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -456,28 +456,6 @@ ino_t page_cgroup_ino(struct page *page)
return ino;
}
-static struct mem_cgroup_per_node *
-mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
-{
- int nid = page_to_nid(page);
-
- return memcg->nodeinfo[nid];
-}
-
-static struct mem_cgroup_tree_per_node *
-soft_limit_tree_node(int nid)
-{
- return soft_limit_tree.rb_tree_per_node[nid];
-}
-
-static struct mem_cgroup_tree_per_node *
-soft_limit_tree_from_page(struct page *page)
-{
- int nid = page_to_nid(page);
-
- return soft_limit_tree.rb_tree_per_node[nid];
-}
-
static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
struct mem_cgroup_tree_per_node *mctz,
unsigned long new_usage_in_excess)
@@ -548,13 +526,13 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
return excess;
}
-static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
+static void mem_cgroup_update_tree(struct mem_cgroup *memcg, int nid)
{
unsigned long excess;
struct mem_cgroup_per_node *mz;
struct mem_cgroup_tree_per_node *mctz;
- mctz = soft_limit_tree_from_page(page);
+ mctz = soft_limit_tree.rb_tree_per_node[nid];
if (!mctz)
return;
/*
@@ -562,7 +540,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
* because their event counter is not touched.
*/
for (; memcg; memcg = parent_mem_cgroup(memcg)) {
- mz = mem_cgroup_page_nodeinfo(memcg, page);
+ mz = memcg->nodeinfo[nid];
excess = soft_limit_excess(memcg);
/*
* We have to update the tree if mz is on RB-tree or
@@ -593,7 +571,7 @@ static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
for_each_node(nid) {
mz = memcg->nodeinfo[nid];
- mctz = soft_limit_tree_node(nid);
+ mctz = soft_limit_tree.rb_tree_per_node[nid];
if (mctz)
mem_cgroup_remove_exceeded(mz, mctz);
}
@@ -799,7 +777,6 @@ static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
}
static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
- struct page *page,
int nr_pages)
{
/* pagein of a big page is an event. So, ignore page size */
@@ -842,7 +819,7 @@ static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
* Check events in order.
*
*/
-static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
+static void memcg_check_events(struct mem_cgroup *memcg, int nid)
{
/* threshold event is triggered in finer grain than soft limit */
if (unlikely(mem_cgroup_event_ratelimit(memcg,
@@ -853,7 +830,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
MEM_CGROUP_TARGET_SOFTLIMIT);
mem_cgroup_threshold(memcg);
if (unlikely(do_softlimit))
- mem_cgroup_update_tree(memcg, page);
+ mem_cgroup_update_tree(memcg, nid);
}
}
@@ -1149,64 +1126,88 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
}
#ifdef CONFIG_DEBUG_VM
-void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
+void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
{
struct mem_cgroup *memcg;
if (mem_cgroup_disabled())
return;
- memcg = page_memcg(page);
+ memcg = folio_memcg(folio);
if (!memcg)
- VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != root_mem_cgroup, page);
+ VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio);
else
- VM_BUG_ON_PAGE(lruvec_memcg(lruvec) != memcg, page);
+ VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
}
#endif
/**
- * lock_page_lruvec - lock and return lruvec for a given page.
- * @page: the page
+ * folio_lruvec_lock - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
*
* These functions are safe to use under any of the following conditions:
- * - page locked
- * - PageLRU cleared
- * - lock_page_memcg()
- * - page->_refcount is zero
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held.
*/
-struct lruvec *lock_page_lruvec(struct page *page)
+struct lruvec *folio_lruvec_lock(struct folio *folio)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock(&lruvec->lru_lock);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
-struct lruvec *lock_page_lruvec_irq(struct page *page)
+/**
+ * folio_lruvec_lock_irq - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
+ *
+ * These functions are safe to use under any of the following conditions:
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held and interrupts
+ * disabled.
+ */
+struct lruvec *folio_lruvec_lock_irq(struct folio *folio)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock_irq(&lruvec->lru_lock);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
-struct lruvec *lock_page_lruvec_irqsave(struct page *page, unsigned long *flags)
+/**
+ * folio_lruvec_lock_irqsave - Lock the lruvec for a folio.
+ * @folio: Pointer to the folio.
+ * @flags: Pointer to irqsave flags.
+ *
+ * These functions are safe to use under any of the following conditions:
+ * - folio locked
+ * - folio_test_lru false
+ * - folio_memcg_lock()
+ * - folio frozen (refcount of 0)
+ *
+ * Return: The lruvec this folio is on with its lock held and interrupts
+ * disabled.
+ */
+struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
+ unsigned long *flags)
{
- struct lruvec *lruvec;
+ struct lruvec *lruvec = folio_lruvec(folio);
- lruvec = mem_cgroup_page_lruvec(page);
spin_lock_irqsave(&lruvec->lru_lock, *flags);
-
- lruvec_memcg_debug(lruvec, page);
+ lruvec_memcg_debug(lruvec, folio);
return lruvec;
}
@@ -1956,18 +1957,17 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
}
/**
- * lock_page_memcg - lock a page and memcg binding
- * @page: the page
+ * folio_memcg_lock - Bind a folio to its memcg.
+ * @folio: The folio.
*
- * This function protects unlocked LRU pages from being moved to
+ * This function prevents unlocked LRU folios from being moved to
* another cgroup.
*
- * It ensures lifetime of the locked memcg. Caller is responsible
- * for the lifetime of the page.
+ * It ensures lifetime of the bound memcg. The caller is responsible
+ * for the lifetime of the folio.
*/
-void lock_page_memcg(struct page *page)
+void folio_memcg_lock(struct folio *folio)
{
- struct page *head = compound_head(page); /* rmap on tail pages */
struct mem_cgroup *memcg;
unsigned long flags;
@@ -1981,7 +1981,7 @@ void lock_page_memcg(struct page *page)
if (mem_cgroup_disabled())
return;
again:
- memcg = page_memcg(head);
+ memcg = folio_memcg(folio);
if (unlikely(!memcg))
return;
@@ -1995,7 +1995,7 @@ again:
return;
spin_lock_irqsave(&memcg->move_lock, flags);
- if (memcg != page_memcg(head)) {
+ if (memcg != folio_memcg(folio)) {
spin_unlock_irqrestore(&memcg->move_lock, flags);
goto again;
}
@@ -2009,9 +2009,15 @@ again:
memcg->move_lock_task = current;
memcg->move_lock_flags = flags;
}
+EXPORT_SYMBOL(folio_memcg_lock);
+
+void lock_page_memcg(struct page *page)
+{
+ folio_memcg_lock(page_folio(page));
+}
EXPORT_SYMBOL(lock_page_memcg);
-static void __unlock_page_memcg(struct mem_cgroup *memcg)
+static void __folio_memcg_unlock(struct mem_cgroup *memcg)
{
if (memcg && memcg->move_lock_task == current) {
unsigned long flags = memcg->move_lock_flags;
@@ -2026,14 +2032,22 @@ static void __unlock_page_memcg(struct mem_cgroup *memcg)
}
/**
- * unlock_page_memcg - unlock a page and memcg binding
- * @page: the page
+ * folio_memcg_unlock - Release the binding between a folio and its memcg.
+ * @folio: The folio.
+ *
+ * This releases the binding created by folio_memcg_lock(). This does
+ * not change the accounting of this folio to its memcg, but it does
+ * permit others to change it.
*/
-void unlock_page_memcg(struct page *page)
+void folio_memcg_unlock(struct folio *folio)
{
- struct page *head = compound_head(page);
+ __folio_memcg_unlock(folio_memcg(folio));
+}
+EXPORT_SYMBOL(folio_memcg_unlock);
- __unlock_page_memcg(page_memcg(head));
+void unlock_page_memcg(struct page *page)
+{
+ folio_memcg_unlock(page_folio(page));
}
EXPORT_SYMBOL(unlock_page_memcg);
@@ -2734,9 +2748,9 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
}
#endif
-static void commit_charge(struct page *page, struct mem_cgroup *memcg)
+static void commit_charge(struct folio *folio, struct mem_cgroup *memcg)
{
- VM_BUG_ON_PAGE(page_memcg(page), page);
+ VM_BUG_ON_FOLIO(folio_memcg(folio), folio);
/*
* Any of the following ensures page's memcg stability:
*
@@ -2745,7 +2759,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg)
* - lock_page_memcg()
* - exclusive reference
*/
- page->memcg_data = (unsigned long)memcg;
+ folio->memcg_data = (unsigned long)memcg;
}
static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
@@ -3015,15 +3029,16 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order)
*/
void __memcg_kmem_uncharge_page(struct page *page, int order)
{
+ struct folio *folio = page_folio(page);
struct obj_cgroup *objcg;
unsigned int nr_pages = 1 << order;
- if (!PageMemcgKmem(page))
+ if (!folio_memcg_kmem(folio))
return;
- objcg = __page_objcg(page);
+ objcg = __folio_objcg(folio);
obj_cgroup_uncharge_pages(objcg, nr_pages);
- page->memcg_data = 0;
+ folio->memcg_data = 0;
obj_cgroup_put(objcg);
}
@@ -3257,17 +3272,18 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
*/
void split_page_memcg(struct page *head, unsigned int nr)
{
- struct mem_cgroup *memcg = page_memcg(head);
+ struct folio *folio = page_folio(head);
+ struct mem_cgroup *memcg = folio_memcg(folio);
int i;
if (mem_cgroup_disabled() || !memcg)
return;
for (i = 1; i < nr; i++)
- head[i].memcg_data = head->memcg_data;
+ folio_page(folio, i)->memcg_data = folio->memcg_data;
- if (PageMemcgKmem(head))
- obj_cgroup_get_many(__page_objcg(head), nr - 1);
+ if (folio_memcg_kmem(folio))
+ obj_cgroup_get_many(__folio_objcg(folio), nr - 1);
else
css_get_many(&memcg->css, nr - 1);
}
@@ -3381,7 +3397,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
if (order > 0)
return 0;
- mctz = soft_limit_tree_node(pgdat->node_id);
+ mctz = soft_limit_tree.rb_tree_per_node[pgdat->node_id];
/*
* Do not even bother to check the largest node if the root
@@ -4537,17 +4553,17 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
* As being wrong occasionally doesn't matter, updates and accesses to the
* records are lockless and racy.
*/
-void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio,
struct bdi_writeback *wb)
{
- struct mem_cgroup *memcg = page_memcg(page);
+ struct mem_cgroup *memcg = folio_memcg(folio);
struct memcg_cgwb_frn *frn;
u64 now = get_jiffies_64();
u64 oldest_at = now;
int oldest = -1;
int i;
- trace_track_foreign_dirty(page, wb);
+ trace_track_foreign_dirty(folio, wb);
/*
* Pick the slot to use. If there is already a slot for @wb, keep
@@ -5575,38 +5591,39 @@ static int mem_cgroup_move_account(struct page *page,
struct mem_cgroup *from,
struct mem_cgroup *to)
{
+ struct folio *folio = page_folio(page);
struct lruvec *from_vec, *to_vec;
struct pglist_data *pgdat;
- unsigned int nr_pages = compound ? thp_nr_pages(page) : 1;
- int ret;
+ unsigned int nr_pages = compound ? folio_nr_pages(folio) : 1;
+ int nid, ret;
VM_BUG_ON(from == to);
- VM_BUG_ON_PAGE(PageLRU(page), page);
- VM_BUG_ON(compound && !PageTransHuge(page));
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
+ VM_BUG_ON(compound && !folio_test_multi(folio));
/*
* Prevent mem_cgroup_migrate() from looking at
* page's memory cgroup of its source page while we change it.
*/
ret = -EBUSY;
- if (!trylock_page(page))
+ if (!folio_trylock(folio))
goto out;
ret = -EINVAL;
- if (page_memcg(page) != from)
+ if (folio_memcg(folio) != from)
goto out_unlock;
- pgdat = page_pgdat(page);
+ pgdat = folio_pgdat(folio);
from_vec = mem_cgroup_lruvec(from, pgdat);
to_vec = mem_cgroup_lruvec(to, pgdat);
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
- if (PageAnon(page)) {
- if (page_mapped(page)) {
+ if (folio_test_anon(folio)) {
+ if (folio_mapped(folio)) {
__mod_lruvec_state(from_vec, NR_ANON_MAPPED, -nr_pages);
__mod_lruvec_state(to_vec, NR_ANON_MAPPED, nr_pages);
- if (PageTransHuge(page)) {
+ if (folio_test_transhuge(folio)) {
__mod_lruvec_state(from_vec, NR_ANON_THPS,
-nr_pages);
__mod_lruvec_state(to_vec, NR_ANON_THPS,
@@ -5617,18 +5634,18 @@ static int mem_cgroup_move_account(struct page *page,
__mod_lruvec_state(from_vec, NR_FILE_PAGES, -nr_pages);
__mod_lruvec_state(to_vec, NR_FILE_PAGES, nr_pages);
- if (PageSwapBacked(page)) {
+ if (folio_test_swapbacked(folio)) {
__mod_lruvec_state(from_vec, NR_SHMEM, -nr_pages);
__mod_lruvec_state(to_vec, NR_SHMEM, nr_pages);
}
- if (page_mapped(page)) {
+ if (folio_mapped(folio)) {
__mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages);
__mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages);
}
- if (PageDirty(page)) {
- struct address_space *mapping = page_mapping(page);
+ if (folio_test_dirty(folio)) {
+ struct address_space *mapping = folio_mapping(folio);
if (mapping_can_writeback(mapping)) {
__mod_lruvec_state(from_vec, NR_FILE_DIRTY,
@@ -5639,7 +5656,7 @@ static int mem_cgroup_move_account(struct page *page,
}
}
- if (PageWriteback(page)) {
+ if (folio_test_writeback(folio)) {
__mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages);
__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
}
@@ -5662,20 +5679,21 @@ static int mem_cgroup_move_account(struct page *page,
css_get(&to->css);
css_put(&from->css);
- page->memcg_data = (unsigned long)to;
+ folio->memcg_data = (unsigned long)to;
- __unlock_page_memcg(from);
+ __folio_memcg_unlock(from);
ret = 0;
+ nid = folio_nid(folio);
local_irq_disable();
- mem_cgroup_charge_statistics(to, page, nr_pages);
- memcg_check_events(to, page);
- mem_cgroup_charge_statistics(from, page, -nr_pages);
- memcg_check_events(from, page);
+ mem_cgroup_charge_statistics(to, nr_pages);
+ memcg_check_events(to, nid);
+ mem_cgroup_charge_statistics(from, -nr_pages);
+ memcg_check_events(from, nid);
local_irq_enable();
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
out:
return ret;
}
@@ -6680,9 +6698,10 @@ void mem_cgroup_calculate_protection(struct mem_cgroup *root,
atomic_long_read(&parent->memory.children_low_usage)));
}
-static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
+static int charge_memcg(struct folio *folio, struct mem_cgroup *memcg,
+ gfp_t gfp)
{
- unsigned int nr_pages = thp_nr_pages(page);
+ long nr_pages = folio_nr_pages(folio);
int ret;
ret = try_charge(memcg, gfp, nr_pages);
@@ -6690,38 +6709,23 @@ static int charge_memcg(struct page *page, struct mem_cgroup *memcg, gfp_t gfp)
goto out;
css_get(&memcg->css);
- commit_charge(page, memcg);
+ commit_charge(folio, memcg);
local_irq_disable();
- mem_cgroup_charge_statistics(memcg, page, nr_pages);
- memcg_check_events(memcg, page);
+ mem_cgroup_charge_statistics(memcg, nr_pages);
+ memcg_check_events(memcg, folio_nid(folio));
local_irq_enable();
out:
return ret;
}
-/**
- * __mem_cgroup_charge - charge a newly allocated page to a cgroup
- * @page: page to charge
- * @mm: mm context of the victim
- * @gfp_mask: reclaim mode
- *
- * Try to charge @page to the memcg that @mm belongs to, reclaiming
- * pages according to @gfp_mask if necessary. if @mm is NULL, try to
- * charge to the active memcg.
- *
- * Do not use this for pages allocated for swapin.
- *
- * Returns 0 on success. Otherwise, an error code is returned.
- */
-int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
- gfp_t gfp_mask)
+int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp)
{
struct mem_cgroup *memcg;
int ret;
memcg = get_mem_cgroup_from_mm(mm);
- ret = charge_memcg(page, memcg, gfp_mask);
+ ret = charge_memcg(folio, memcg, gfp);
css_put(&memcg->css);
return ret;
@@ -6742,6 +6746,7 @@ int __mem_cgroup_charge(struct page *page, struct mm_struct *mm,
int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
gfp_t gfp, swp_entry_t entry)
{
+ struct folio *folio = page_folio(page);
struct mem_cgroup *memcg;
unsigned short id;
int ret;
@@ -6756,7 +6761,7 @@ int mem_cgroup_swapin_charge_page(struct page *page, struct mm_struct *mm,
memcg = get_mem_cgroup_from_mm(mm);
rcu_read_unlock();
- ret = charge_memcg(page, memcg, gfp);
+ ret = charge_memcg(folio, memcg, gfp);
css_put(&memcg->css);
return ret;
@@ -6800,7 +6805,7 @@ struct uncharge_gather {
unsigned long nr_memory;
unsigned long pgpgout;
unsigned long nr_kmem;
- struct page *dummy_page;
+ int nid;
};
static inline void uncharge_gather_clear(struct uncharge_gather *ug)
@@ -6824,36 +6829,36 @@ static void uncharge_batch(const struct uncharge_gather *ug)
local_irq_save(flags);
__count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout);
__this_cpu_add(ug->memcg->vmstats_percpu->nr_page_events, ug->nr_memory);
- memcg_check_events(ug->memcg, ug->dummy_page);
+ memcg_check_events(ug->memcg, ug->nid);
local_irq_restore(flags);
- /* drop reference from uncharge_page */
+ /* drop reference from uncharge_folio */
css_put(&ug->memcg->css);
}
-static void uncharge_page(struct page *page, struct uncharge_gather *ug)
+static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug)
{
- unsigned long nr_pages;
+ long nr_pages;
struct mem_cgroup *memcg;
struct obj_cgroup *objcg;
- bool use_objcg = PageMemcgKmem(page);
+ bool use_objcg = folio_memcg_kmem(folio);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/*
* Nobody should be changing or seriously looking at
- * page memcg or objcg at this point, we have fully
- * exclusive access to the page.
+ * folio memcg or objcg at this point, we have fully
+ * exclusive access to the folio.
*/
if (use_objcg) {
- objcg = __page_objcg(page);
+ objcg = __folio_objcg(folio);
/*
* This get matches the put at the end of the function and
* kmem pages do not hold memcg references anymore.
*/
memcg = get_mem_cgroup_from_objcg(objcg);
} else {
- memcg = __page_memcg(page);
+ memcg = __folio_memcg(folio);
}
if (!memcg)
@@ -6865,19 +6870,19 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
uncharge_gather_clear(ug);
}
ug->memcg = memcg;
- ug->dummy_page = page;
+ ug->nid = folio_nid(folio);
/* pairs with css_put in uncharge_batch */
css_get(&memcg->css);
}
- nr_pages = compound_nr(page);
+ nr_pages = folio_nr_pages(folio);
if (use_objcg) {
ug->nr_memory += nr_pages;
ug->nr_kmem += nr_pages;
- page->memcg_data = 0;
+ folio->memcg_data = 0;
obj_cgroup_put(objcg);
} else {
/* LRU pages aren't accounted at the root level */
@@ -6885,28 +6890,22 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
ug->nr_memory += nr_pages;
ug->pgpgout++;
- page->memcg_data = 0;
+ folio->memcg_data = 0;
}
css_put(&memcg->css);
}
-/**
- * __mem_cgroup_uncharge - uncharge a page
- * @page: page to uncharge
- *
- * Uncharge a page previously charged with __mem_cgroup_charge().
- */
-void __mem_cgroup_uncharge(struct page *page)
+void __mem_cgroup_uncharge(struct folio *folio)
{
struct uncharge_gather ug;
- /* Don't touch page->lru of any random page, pre-check: */
- if (!page_memcg(page))
+ /* Don't touch folio->lru of any random page, pre-check: */
+ if (!folio_memcg(folio))
return;
uncharge_gather_clear(&ug);
- uncharge_page(page, &ug);
+ uncharge_folio(folio, &ug);
uncharge_batch(&ug);
}
@@ -6920,52 +6919,49 @@ void __mem_cgroup_uncharge(struct page *page)
void __mem_cgroup_uncharge_list(struct list_head *page_list)
{
struct uncharge_gather ug;
- struct page *page;
+ struct folio *folio;
uncharge_gather_clear(&ug);
- list_for_each_entry(page, page_list, lru)
- uncharge_page(page, &ug);
+ list_for_each_entry(folio, page_list, lru)
+ uncharge_folio(folio, &ug);
if (ug.memcg)
uncharge_batch(&ug);
}
/**
- * mem_cgroup_migrate - charge a page's replacement
- * @oldpage: currently circulating page
- * @newpage: replacement page
+ * mem_cgroup_migrate - Charge a folio's replacement.
+ * @old: Currently circulating folio.
+ * @new: Replacement folio.
*
- * Charge @newpage as a replacement page for @oldpage. @oldpage will
+ * Charge @new as a replacement folio for @old. @old will
* be uncharged upon free.
*
- * Both pages must be locked, @newpage->mapping must be set up.
+ * Both folios must be locked, @new->mapping must be set up.
*/
-void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
+void mem_cgroup_migrate(struct folio *old, struct folio *new)
{
struct mem_cgroup *memcg;
- unsigned int nr_pages;
+ long nr_pages = folio_nr_pages(new);
unsigned long flags;
- VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
- VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
- VM_BUG_ON_PAGE(PageTransHuge(oldpage) != PageTransHuge(newpage),
- newpage);
+ VM_BUG_ON_FOLIO(!folio_test_locked(old), old);
+ VM_BUG_ON_FOLIO(!folio_test_locked(new), new);
+ VM_BUG_ON_FOLIO(folio_test_anon(old) != folio_test_anon(new), new);
+ VM_BUG_ON_FOLIO(folio_nr_pages(old) != nr_pages, new);
if (mem_cgroup_disabled())
return;
- /* Page cache replacement: new page already charged? */
- if (page_memcg(newpage))
+ /* Page cache replacement: new folio already charged? */
+ if (folio_memcg(new))
return;
- memcg = page_memcg(oldpage);
- VM_WARN_ON_ONCE_PAGE(!memcg, oldpage);
+ memcg = folio_memcg(old);
+ VM_WARN_ON_ONCE_FOLIO(!memcg, old);
if (!memcg)
return;
/* Force-charge the new page. The old one will be freed soon */
- nr_pages = thp_nr_pages(newpage);
-
if (!mem_cgroup_is_root(memcg)) {
page_counter_charge(&memcg->memory, nr_pages);
if (do_memsw_account())
@@ -6973,11 +6969,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
}
css_get(&memcg->css);
- commit_charge(newpage, memcg);
+ commit_charge(new, memcg);
local_irq_save(flags);
- mem_cgroup_charge_statistics(memcg, newpage, nr_pages);
- memcg_check_events(memcg, newpage);
+ mem_cgroup_charge_statistics(memcg, nr_pages);
+ memcg_check_events(memcg, folio_nid(new));
local_irq_restore(flags);
}
@@ -7204,8 +7200,8 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
* only synchronisation we have for updating the per-CPU variables.
*/
VM_BUG_ON(!irqs_disabled());
- mem_cgroup_charge_statistics(memcg, page, -nr_entries);
- memcg_check_events(memcg, page);
+ mem_cgroup_charge_statistics(memcg, -nr_entries);
+ memcg_check_events(memcg, page_to_nid(page));
css_put(&memcg->css);
}
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 3e6449f2102a..93078a2859a7 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -762,7 +762,7 @@ static int delete_from_lru_cache(struct page *p)
* Poisoned page might never drop its ref count to 0 so we have
* to uncharge it manually from its memcg.
*/
- mem_cgroup_uncharge(p);
+ mem_cgroup_uncharge(page_folio(p));
/*
* drop the page count elevated by isolate_lru_page()
@@ -1147,20 +1147,6 @@ static int __get_hwpoison_page(struct page *page)
if (!HWPoisonHandlable(head))
return -EBUSY;
- if (PageTransHuge(head)) {
- /*
- * Non anonymous thp exists only in allocation/free time. We
- * can't handle such a case correctly, so let's give it up.
- * This should be better than triggering BUG_ON when kernel
- * tries to touch the "partially handled" page.
- */
- if (!PageAnon(head)) {
- pr_err("Memory failure: %#lx: non anonymous thp\n",
- page_to_pfn(page));
- return 0;
- }
- }
-
if (get_page_unless_zero(head)) {
if (head == compound_head(page))
return 1;
@@ -1708,6 +1694,20 @@ try_again:
}
if (PageTransHuge(hpage)) {
+ /*
+ * The flag must be set after the refcount is bumped
+ * otherwise it may race with THP split.
+ * And the flag can't be set in get_hwpoison_page() since
+ * it is called by soft offline too and it is just called
+ * for !MF_COUNT_INCREASE. So here seems to be the best
+ * place.
+ *
+ * Don't need care about the above error handling paths for
+ * get_hwpoison_page() since they handle either free page
+ * or unhandlable page. The refcount is bumped iff the
+ * page is a valid handlable page.
+ */
+ SetPageHasHWPoisoned(hpage);
if (try_to_split_thp_page(p, "Memory Failure") < 0) {
action_result(pfn, MF_MSG_UNSPLIT_THP, MF_IGNORED);
res = -EBUSY;
diff --git a/mm/memory.c b/mm/memory.c
index adf9b9ef8277..4b1de80c2a9c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -990,7 +990,7 @@ page_copy_prealloc(struct mm_struct *src_mm, struct vm_area_struct *vma,
if (!new_page)
return NULL;
- if (mem_cgroup_charge(new_page, src_mm, GFP_KERNEL)) {
+ if (mem_cgroup_charge(page_folio(new_page), src_mm, GFP_KERNEL)) {
put_page(new_page);
return NULL;
}
@@ -3019,7 +3019,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
}
}
- if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(new_page), mm, GFP_KERNEL))
goto oom_free_new;
cgroup_throttle_swaprate(new_page, GFP_KERNEL);
@@ -3539,7 +3539,8 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
shadow = get_shadow_from_swap_cache(entry);
if (shadow)
- workingset_refault(page, shadow);
+ workingset_refault(page_folio(page),
+ shadow);
lru_cache_add(page);
@@ -3769,7 +3770,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
if (!page)
goto oom;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
goto oom_free_page;
cgroup_throttle_swaprate(page, GFP_KERNEL);
@@ -3907,6 +3908,15 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
return ret;
/*
+ * Just backoff if any subpage of a THP is corrupted otherwise
+ * the corrupted page may mapped by PMD silently to escape the
+ * check. This kind of THP just can be PTE mapped. Access to
+ * the corrupted subpage should trigger SIGBUS as expected.
+ */
+ if (unlikely(PageHasHWPoisoned(page)))
+ return ret;
+
+ /*
* Archs like ppc64 need additional space to store information
* related to pte entry. Use the preallocated table for that.
*/
@@ -4193,7 +4203,8 @@ static vm_fault_t do_cow_fault(struct vm_fault *vmf)
if (!vmf->cow_page)
return VM_FAULT_OOM;
- if (mem_cgroup_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL)) {
+ if (mem_cgroup_charge(page_folio(vmf->cow_page), vma->vm_mm,
+ GFP_KERNEL)) {
put_page(vmf->cow_page);
return VM_FAULT_OOM;
}
@@ -4258,7 +4269,7 @@ static vm_fault_t do_shared_fault(struct vm_fault *vmf)
* We enter with non-exclusive mmap_lock (to exclude vma changes,
* but allow concurrent faults).
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
* If mmap_lock is released, vma may become invalid (for example
* by other thread calling munmap()).
*/
@@ -4499,7 +4510,7 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
* concurrent faults).
*
* The mmap_lock may have been released depending on flags and our return value.
- * See filemap_fault() and __lock_page_or_retry().
+ * See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t handle_pte_fault(struct vm_fault *vmf)
{
@@ -4603,7 +4614,7 @@ unlock:
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
*/
static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
@@ -4759,7 +4770,7 @@ static inline void mm_account_fault(struct pt_regs *regs,
* By the time we get here, we already hold the mm semaphore
*
* The mmap_lock may have been released depending on flags and our
- * return value. See filemap_fault() and __lock_page_or_retry().
+ * return value. See filemap_fault() and __folio_lock_or_retry().
*/
vm_fault_t handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
unsigned int flags, struct pt_regs *regs)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 1592b081c58e..f4b4be7af4d3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -856,16 +856,6 @@ static long do_set_mempolicy(unsigned short mode, unsigned short flags,
goto out;
}
- if (flags & MPOL_F_NUMA_BALANCING) {
- if (new && new->mode == MPOL_BIND) {
- new->flags |= (MPOL_F_MOF | MPOL_F_MORON);
- } else {
- ret = -EINVAL;
- mpol_put(new);
- goto out;
- }
- }
-
ret = mpol_set_nodemask(new, nodes, scratch);
if (ret) {
mpol_put(new);
@@ -1458,7 +1448,11 @@ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags)
return -EINVAL;
if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES))
return -EINVAL;
-
+ if (*flags & MPOL_F_NUMA_BALANCING) {
+ if (*mode != MPOL_BIND)
+ return -EINVAL;
+ *flags |= (MPOL_F_MOF | MPOL_F_MORON);
+ }
return 0;
}
@@ -2202,6 +2196,16 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
}
EXPORT_SYMBOL(alloc_pages);
+struct folio *folio_alloc(gfp_t gfp, unsigned order)
+{
+ struct page *page = alloc_pages(gfp | __GFP_COMP, order);
+
+ if (page && order > 1)
+ prep_transhuge_page(page);
+ return (struct folio *)page;
+}
+EXPORT_SYMBOL(folio_alloc);
+
int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
{
struct mempolicy *pol = mpol_dup(vma_policy(src));
diff --git a/mm/memremap.c b/mm/memremap.c
index ed593bf87109..5a66a71ab591 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -505,7 +505,7 @@ void free_devmap_managed_page(struct page *page)
__ClearPageWaiters(page);
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
/*
* When a device_private page is freed, the page->mapping field
diff --git a/mm/migrate.c b/mm/migrate.c
index a6a7743ee98f..efa9941ebe03 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -364,7 +364,7 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
*/
expected_count += is_device_private_page(page);
if (mapping)
- expected_count += thp_nr_pages(page) + page_has_private(page);
+ expected_count += compound_nr(page) + page_has_private(page);
return expected_count;
}
@@ -377,74 +377,75 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
* 2 for pages with a mapping
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
-int migrate_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page, int extra_count)
+int folio_migrate_mapping(struct address_space *mapping,
+ struct folio *newfolio, struct folio *folio, int extra_count)
{
- XA_STATE(xas, &mapping->i_pages, page_index(page));
+ XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct zone *oldzone, *newzone;
int dirty;
- int expected_count = expected_page_refs(mapping, page) + extra_count;
- int nr = thp_nr_pages(page);
+ int expected_count = expected_page_refs(mapping, &folio->page) + extra_count;
+ long nr = folio_nr_pages(folio);
if (!mapping) {
/* Anonymous page without mapping */
- if (page_count(page) != expected_count)
+ if (folio_ref_count(folio) != expected_count)
return -EAGAIN;
/* No turning back from here */
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- if (PageSwapBacked(page))
- __SetPageSwapBacked(newpage);
+ newfolio->index = folio->index;
+ newfolio->mapping = folio->mapping;
+ if (folio_test_swapbacked(folio))
+ __folio_set_swapbacked(newfolio);
return MIGRATEPAGE_SUCCESS;
}
- oldzone = page_zone(page);
- newzone = page_zone(newpage);
+ oldzone = folio_zone(folio);
+ newzone = folio_zone(newfolio);
xas_lock_irq(&xas);
- if (page_count(page) != expected_count || xas_load(&xas) != page) {
+ if (folio_ref_count(folio) != expected_count ||
+ xas_load(&xas) != folio) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
- if (!page_ref_freeze(page, expected_count)) {
+ if (!folio_ref_freeze(folio, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
/*
- * Now we know that no one else is looking at the page:
+ * Now we know that no one else is looking at the folio:
* no turning back from here.
*/
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- page_ref_add(newpage, nr); /* add cache reference */
- if (PageSwapBacked(page)) {
- __SetPageSwapBacked(newpage);
- if (PageSwapCache(page)) {
- SetPageSwapCache(newpage);
- set_page_private(newpage, page_private(page));
+ newfolio->index = folio->index;
+ newfolio->mapping = folio->mapping;
+ folio_ref_add(newfolio, nr); /* add cache reference */
+ if (folio_test_swapbacked(folio)) {
+ __folio_set_swapbacked(newfolio);
+ if (folio_test_swapcache(folio)) {
+ folio_set_swapcache(newfolio);
+ newfolio->private = folio_get_private(folio);
}
} else {
- VM_BUG_ON_PAGE(PageSwapCache(page), page);
+ VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
}
/* Move dirty while page refs frozen and newpage not yet exposed */
- dirty = PageDirty(page);
+ dirty = folio_test_dirty(folio);
if (dirty) {
- ClearPageDirty(page);
- SetPageDirty(newpage);
+ folio_clear_dirty(folio);
+ folio_set_dirty(newfolio);
}
- xas_store(&xas, newpage);
- if (PageTransHuge(page)) {
+ xas_store(&xas, newfolio);
+ if (nr > 1) {
int i;
for (i = 1; i < nr; i++) {
xas_next(&xas);
- xas_store(&xas, newpage);
+ xas_store(&xas, newfolio);
}
}
@@ -453,7 +454,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
* to one less reference.
* We know this isn't the last reference.
*/
- page_ref_unfreeze(page, expected_count - nr);
+ folio_ref_unfreeze(folio, expected_count - nr);
xas_unlock(&xas);
/* Leave irq disabled to prevent preemption while updating stats */
@@ -472,18 +473,18 @@ int migrate_page_move_mapping(struct address_space *mapping,
struct lruvec *old_lruvec, *new_lruvec;
struct mem_cgroup *memcg;
- memcg = page_memcg(page);
+ memcg = folio_memcg(folio);
old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
__mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
__mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
- if (PageSwapBacked(page) && !PageSwapCache(page)) {
+ if (folio_test_swapbacked(folio) && !folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
__mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
}
#ifdef CONFIG_SWAP
- if (PageSwapCache(page)) {
+ if (folio_test_swapcache(folio)) {
__mod_lruvec_state(old_lruvec, NR_SWAPCACHE, -nr);
__mod_lruvec_state(new_lruvec, NR_SWAPCACHE, nr);
}
@@ -499,11 +500,11 @@ int migrate_page_move_mapping(struct address_space *mapping,
return MIGRATEPAGE_SUCCESS;
}
-EXPORT_SYMBOL(migrate_page_move_mapping);
+EXPORT_SYMBOL(folio_migrate_mapping);
/*
* The expected number of remaining references is the same as that
- * of migrate_page_move_mapping().
+ * of folio_migrate_mapping().
*/
int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page)
@@ -538,91 +539,87 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
}
/*
- * Copy the page to its new location
+ * Copy the flags and some other ancillary information
*/
-void migrate_page_states(struct page *newpage, struct page *page)
+void folio_migrate_flags(struct folio *newfolio, struct folio *folio)
{
int cpupid;
- if (PageError(page))
- SetPageError(newpage);
- if (PageReferenced(page))
- SetPageReferenced(newpage);
- if (PageUptodate(page))
- SetPageUptodate(newpage);
- if (TestClearPageActive(page)) {
- VM_BUG_ON_PAGE(PageUnevictable(page), page);
- SetPageActive(newpage);
- } else if (TestClearPageUnevictable(page))
- SetPageUnevictable(newpage);
- if (PageWorkingset(page))
- SetPageWorkingset(newpage);
- if (PageChecked(page))
- SetPageChecked(newpage);
- if (PageMappedToDisk(page))
- SetPageMappedToDisk(newpage);
-
- /* Move dirty on pages not done by migrate_page_move_mapping() */
- if (PageDirty(page))
- SetPageDirty(newpage);
-
- if (page_is_young(page))
- set_page_young(newpage);
- if (page_is_idle(page))
- set_page_idle(newpage);
+ if (folio_test_error(folio))
+ folio_set_error(newfolio);
+ if (folio_test_referenced(folio))
+ folio_set_referenced(newfolio);
+ if (folio_test_uptodate(folio))
+ folio_mark_uptodate(newfolio);
+ if (folio_test_clear_active(folio)) {
+ VM_BUG_ON_FOLIO(folio_test_unevictable(folio), folio);
+ folio_set_active(newfolio);
+ } else if (folio_test_clear_unevictable(folio))
+ folio_set_unevictable(newfolio);
+ if (folio_test_workingset(folio))
+ folio_set_workingset(newfolio);
+ if (folio_test_checked(folio))
+ folio_set_checked(newfolio);
+ if (folio_test_mappedtodisk(folio))
+ folio_set_mappedtodisk(newfolio);
+
+ /* Move dirty on pages not done by folio_migrate_mapping() */
+ if (folio_test_dirty(folio))
+ folio_set_dirty(newfolio);
+
+ if (folio_test_young(folio))
+ folio_set_young(newfolio);
+ if (folio_test_idle(folio))
+ folio_set_idle(newfolio);
/*
* Copy NUMA information to the new page, to prevent over-eager
* future migrations of this same page.
*/
- cpupid = page_cpupid_xchg_last(page, -1);
- page_cpupid_xchg_last(newpage, cpupid);
+ cpupid = page_cpupid_xchg_last(&folio->page, -1);
+ page_cpupid_xchg_last(&newfolio->page, cpupid);
- ksm_migrate_page(newpage, page);
+ folio_migrate_ksm(newfolio, folio);
/*
* Please do not reorder this without considering how mm/ksm.c's
* get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
*/
- if (PageSwapCache(page))
- ClearPageSwapCache(page);
- ClearPagePrivate(page);
+ if (folio_test_swapcache(folio))
+ folio_clear_swapcache(folio);
+ folio_clear_private(folio);
/* page->private contains hugetlb specific flags */
- if (!PageHuge(page))
- set_page_private(page, 0);
+ if (!folio_test_hugetlb(folio))
+ folio->private = NULL;
/*
* If any waiters have accumulated on the new page then
* wake them up.
*/
- if (PageWriteback(newpage))
- end_page_writeback(newpage);
+ if (folio_test_writeback(newfolio))
+ folio_end_writeback(newfolio);
/*
* PG_readahead shares the same bit with PG_reclaim. The above
* end_page_writeback() may clear PG_readahead mistakenly, so set the
* bit after that.
*/
- if (PageReadahead(page))
- SetPageReadahead(newpage);
+ if (folio_test_readahead(folio))
+ folio_set_readahead(newfolio);
- copy_page_owner(page, newpage);
+ folio_copy_owner(newfolio, folio);
- if (!PageHuge(page))
- mem_cgroup_migrate(page, newpage);
+ if (!folio_test_hugetlb(folio))
+ mem_cgroup_migrate(folio, newfolio);
}
-EXPORT_SYMBOL(migrate_page_states);
+EXPORT_SYMBOL(folio_migrate_flags);
-void migrate_page_copy(struct page *newpage, struct page *page)
+void folio_migrate_copy(struct folio *newfolio, struct folio *folio)
{
- if (PageHuge(page) || PageTransHuge(page))
- copy_huge_page(newpage, page);
- else
- copy_highpage(newpage, page);
-
- migrate_page_states(newpage, page);
+ folio_copy(newfolio, folio);
+ folio_migrate_flags(newfolio, folio);
}
-EXPORT_SYMBOL(migrate_page_copy);
+EXPORT_SYMBOL(folio_migrate_copy);
/************************************************************
* Migration functions
@@ -638,19 +635,21 @@ int migrate_page(struct address_space *mapping,
struct page *newpage, struct page *page,
enum migrate_mode mode)
{
+ struct folio *newfolio = page_folio(newpage);
+ struct folio *folio = page_folio(page);
int rc;
- BUG_ON(PageWriteback(page)); /* Writeback must be complete */
+ BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page, 0);
+ rc = folio_migrate_mapping(mapping, newfolio, folio, 0);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
+ folio_migrate_copy(newfolio, folio);
else
- migrate_page_states(newpage, page);
+ folio_migrate_flags(newfolio, folio);
return MIGRATEPAGE_SUCCESS;
}
EXPORT_SYMBOL(migrate_page);
@@ -2468,7 +2467,7 @@ static void migrate_vma_collect(struct migrate_vma *migrate)
* @page: struct page to check
*
* Pinned pages cannot be migrated. This is the same test as in
- * migrate_page_move_mapping(), except that here we allow migration of a
+ * folio_migrate_mapping(), except that here we allow migration of a
* ZONE_DEVICE page.
*/
static bool migrate_vma_check_page(struct page *page)
@@ -2846,7 +2845,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
if (unlikely(anon_vma_prepare(vma)))
goto abort;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), vma->vm_mm, GFP_KERNEL))
goto abort;
/*
@@ -3066,7 +3065,7 @@ void migrate_vma_finalize(struct migrate_vma *migrate)
EXPORT_SYMBOL(migrate_vma_finalize);
#endif /* CONFIG_DEVICE_PRIVATE */
-#if defined(CONFIG_MEMORY_HOTPLUG)
+#if defined(CONFIG_HOTPLUG_CPU)
/* Disable reclaim-based migration. */
static void __disable_all_migrate_targets(void)
{
@@ -3209,25 +3208,6 @@ static void set_migration_target_nodes(void)
}
/*
- * React to hotplug events that might affect the migration targets
- * like events that online or offline NUMA nodes.
- *
- * The ordering is also currently dependent on which nodes have
- * CPUs. That means we need CPU on/offline notification too.
- */
-static int migration_online_cpu(unsigned int cpu)
-{
- set_migration_target_nodes();
- return 0;
-}
-
-static int migration_offline_cpu(unsigned int cpu)
-{
- set_migration_target_nodes();
- return 0;
-}
-
-/*
* This leaves migrate-on-reclaim transiently disabled between
* the MEM_GOING_OFFLINE and MEM_OFFLINE events. This runs
* whether reclaim-based migration is enabled or not, which
@@ -3239,8 +3219,18 @@ static int migration_offline_cpu(unsigned int cpu)
* set_migration_target_nodes().
*/
static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
- unsigned long action, void *arg)
+ unsigned long action, void *_arg)
{
+ struct memory_notify *arg = _arg;
+
+ /*
+ * Only update the node migration order when a node is
+ * changing status, like online->offline. This avoids
+ * the overhead of synchronize_rcu() in most cases.
+ */
+ if (arg->status_change_nid < 0)
+ return notifier_from_errno(0);
+
switch (action) {
case MEM_GOING_OFFLINE:
/*
@@ -3274,13 +3264,31 @@ static int __meminit migrate_on_reclaim_callback(struct notifier_block *self,
return notifier_from_errno(0);
}
+/*
+ * React to hotplug events that might affect the migration targets
+ * like events that online or offline NUMA nodes.
+ *
+ * The ordering is also currently dependent on which nodes have
+ * CPUs. That means we need CPU on/offline notification too.
+ */
+static int migration_online_cpu(unsigned int cpu)
+{
+ set_migration_target_nodes();
+ return 0;
+}
+
+static int migration_offline_cpu(unsigned int cpu)
+{
+ set_migration_target_nodes();
+ return 0;
+}
+
static int __init migrate_on_reclaim_init(void)
{
int ret;
- ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "migrate on reclaim",
- migration_online_cpu,
- migration_offline_cpu);
+ ret = cpuhp_setup_state_nocalls(CPUHP_MM_DEMOTION_DEAD, "mm/demotion:offline",
+ NULL, migration_offline_cpu);
/*
* In the unlikely case that this fails, the automatic
* migration targets may become suboptimal for nodes
@@ -3288,9 +3296,12 @@ static int __init migrate_on_reclaim_init(void)
* rare case, do not bother trying to do anything special.
*/
WARN_ON(ret < 0);
+ ret = cpuhp_setup_state(CPUHP_AP_MM_DEMOTION_ONLINE, "mm/demotion:online",
+ migration_online_cpu, NULL);
+ WARN_ON(ret < 0);
hotplug_memory_notifier(migrate_on_reclaim_callback, 100);
return 0;
}
late_initcall(migrate_on_reclaim_init);
-#endif /* CONFIG_MEMORY_HOTPLUG */
+#endif /* CONFIG_HOTPLUG_CPU */
diff --git a/mm/mlock.c b/mm/mlock.c
index 16d2ee160d43..e263d62ae2d0 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -271,6 +271,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
/* Phase 1: page isolation */
for (i = 0; i < nr; i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
if (TestClearPageMlocked(page)) {
/*
@@ -278,7 +279,7 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
* so we can spare the get_page() here.
*/
if (TestClearPageLRU(page)) {
- lruvec = relock_page_lruvec_irq(page, lruvec);
+ lruvec = folio_lruvec_relock_irq(folio, lruvec);
del_page_from_lru_list(page, lruvec);
continue;
} else
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 831340e7ad8b..989f35a2bbb1 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -1150,7 +1150,7 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
struct task_struct *task;
struct task_struct *p;
unsigned int f_flags;
- bool reap = true;
+ bool reap = false;
struct pid *pid;
long ret = 0;
@@ -1177,15 +1177,15 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
goto put_task;
}
- mm = p->mm;
- mmgrab(mm);
-
- /* If the work has been done already, just exit with success */
- if (test_bit(MMF_OOM_SKIP, &mm->flags))
- reap = false;
- else if (!task_will_free_mem(p)) {
- reap = false;
- ret = -EINVAL;
+ if (mmget_not_zero(p->mm)) {
+ mm = p->mm;
+ if (task_will_free_mem(p))
+ reap = true;
+ else {
+ /* Error only if the work has not been done already */
+ if (!test_bit(MMF_OOM_SKIP, &mm->flags))
+ ret = -EINVAL;
+ }
}
task_unlock(p);
@@ -1201,7 +1201,8 @@ SYSCALL_DEFINE2(process_mrelease, int, pidfd, unsigned int, flags)
mmap_read_unlock(mm);
drop_mm:
- mmdrop(mm);
+ if (mm)
+ mmput(mm);
put_task:
put_task_struct(task);
put_pid:
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 4812a17b288c..9c64490171e0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -562,12 +562,12 @@ static unsigned long wp_next_time(unsigned long cur_time)
return cur_time;
}
-static void wb_domain_writeout_inc(struct wb_domain *dom,
+static void wb_domain_writeout_add(struct wb_domain *dom,
struct fprop_local_percpu *completions,
- unsigned int max_prop_frac)
+ unsigned int max_prop_frac, long nr)
{
- __fprop_inc_percpu_max(&dom->completions, completions,
- max_prop_frac);
+ __fprop_add_percpu_max(&dom->completions, completions,
+ max_prop_frac, nr);
/* First event after period switching was turned off? */
if (unlikely(!dom->period_time)) {
/*
@@ -583,20 +583,20 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
/*
* Increment @wb's writeout completion count and the global writeout
- * completion count. Called from test_clear_page_writeback().
+ * completion count. Called from __folio_end_writeback().
*/
-static inline void __wb_writeout_inc(struct bdi_writeback *wb)
+static inline void __wb_writeout_add(struct bdi_writeback *wb, long nr)
{
struct wb_domain *cgdom;
- inc_wb_stat(wb, WB_WRITTEN);
- wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
- wb->bdi->max_prop_frac);
+ wb_stat_mod(wb, WB_WRITTEN, nr);
+ wb_domain_writeout_add(&global_wb_domain, &wb->completions,
+ wb->bdi->max_prop_frac, nr);
cgdom = mem_cgroup_wb_domain(wb);
if (cgdom)
- wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb),
- wb->bdi->max_prop_frac);
+ wb_domain_writeout_add(cgdom, wb_memcg_completions(wb),
+ wb->bdi->max_prop_frac, nr);
}
void wb_writeout_inc(struct bdi_writeback *wb)
@@ -604,7 +604,7 @@ void wb_writeout_inc(struct bdi_writeback *wb)
unsigned long flags;
local_irq_save(flags);
- __wb_writeout_inc(wb);
+ __wb_writeout_add(wb, 1);
local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(wb_writeout_inc);
@@ -1084,7 +1084,7 @@ static void wb_update_write_bandwidth(struct bdi_writeback *wb,
* write_bandwidth = ---------------------------------------------------
* period
*
- * @written may have decreased due to account_page_redirty().
+ * @written may have decreased due to folio_account_redirty().
* Avoid underflowing @bw calculation.
*/
bw = written - min(written, wb->written_stamp);
@@ -2381,44 +2381,44 @@ int do_writepages(struct address_space *mapping, struct writeback_control *wbc)
}
/**
- * write_one_page - write out a single page and wait on I/O
- * @page: the page to write
+ * folio_write_one - write out a single folio and wait on I/O.
+ * @folio: The folio to write.
*
- * The page must be locked by the caller and will be unlocked upon return.
+ * The folio must be locked by the caller and will be unlocked upon return.
*
* Note that the mapping's AS_EIO/AS_ENOSPC flags will be cleared when this
* function returns.
*
* Return: %0 on success, negative error code otherwise
*/
-int write_one_page(struct page *page)
+int folio_write_one(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
int ret = 0;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
- .nr_to_write = 1,
+ .nr_to_write = folio_nr_pages(folio),
};
- BUG_ON(!PageLocked(page));
+ BUG_ON(!folio_test_locked(folio));
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
- if (clear_page_dirty_for_io(page)) {
- get_page(page);
- ret = mapping->a_ops->writepage(page, &wbc);
+ if (folio_clear_dirty_for_io(folio)) {
+ folio_get(folio);
+ ret = mapping->a_ops->writepage(&folio->page, &wbc);
if (ret == 0)
- wait_on_page_writeback(page);
- put_page(page);
+ folio_wait_writeback(folio);
+ folio_put(folio);
} else {
- unlock_page(page);
+ folio_unlock(folio);
}
if (!ret)
ret = filemap_check_errors(mapping);
return ret;
}
-EXPORT_SYMBOL(write_one_page);
+EXPORT_SYMBOL(folio_write_one);
/*
* For address_spaces which do not use buffers nor write back.
@@ -2438,29 +2438,30 @@ EXPORT_SYMBOL(__set_page_dirty_no_writeback);
*
* NOTE: This relies on being atomic wrt interrupts.
*/
-static void account_page_dirtied(struct page *page,
+static void folio_account_dirtied(struct folio *folio,
struct address_space *mapping)
{
struct inode *inode = mapping->host;
- trace_writeback_dirty_page(page, mapping);
+ trace_writeback_dirty_folio(folio, mapping);
if (mapping_can_writeback(mapping)) {
struct bdi_writeback *wb;
+ long nr = folio_nr_pages(folio);
- inode_attach_wb(inode, page);
+ inode_attach_wb(inode, &folio->page);
wb = inode_to_wb(inode);
- __inc_lruvec_page_state(page, NR_FILE_DIRTY);
- __inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- __inc_node_page_state(page, NR_DIRTIED);
- inc_wb_stat(wb, WB_RECLAIMABLE);
- inc_wb_stat(wb, WB_DIRTIED);
- task_io_account_write(PAGE_SIZE);
- current->nr_dirtied++;
- __this_cpu_inc(bdp_ratelimits);
+ __lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, nr);
+ __zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
+ __node_stat_mod_folio(folio, NR_DIRTIED, nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, nr);
+ wb_stat_mod(wb, WB_DIRTIED, nr);
+ task_io_account_write(nr * PAGE_SIZE);
+ current->nr_dirtied += nr;
+ __this_cpu_add(bdp_ratelimits, nr);
- mem_cgroup_track_foreign_dirty(page, wb);
+ mem_cgroup_track_foreign_dirty(folio, wb);
}
}
@@ -2469,130 +2470,152 @@ static void account_page_dirtied(struct page *page,
*
* Caller must hold lock_page_memcg().
*/
-void account_page_cleaned(struct page *page, struct address_space *mapping,
+void folio_account_cleaned(struct folio *folio, struct address_space *mapping,
struct bdi_writeback *wb)
{
if (mapping_can_writeback(mapping)) {
- dec_lruvec_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- dec_wb_stat(wb, WB_RECLAIMABLE);
- task_io_account_cancelled_write(PAGE_SIZE);
+ long nr = folio_nr_pages(folio);
+ lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+ task_io_account_cancelled_write(nr * PAGE_SIZE);
}
}
/*
- * Mark the page dirty, and set it dirty in the page cache, and mark the inode
- * dirty.
+ * Mark the folio dirty, and set it dirty in the page cache, and mark
+ * the inode dirty.
*
- * If warn is true, then emit a warning if the page is not uptodate and has
+ * If warn is true, then emit a warning if the folio is not uptodate and has
* not been truncated.
*
* The caller must hold lock_page_memcg().
*/
-void __set_page_dirty(struct page *page, struct address_space *mapping,
+void __folio_mark_dirty(struct folio *folio, struct address_space *mapping,
int warn)
{
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
- if (page->mapping) { /* Race with truncate? */
- WARN_ON_ONCE(warn && !PageUptodate(page));
- account_page_dirtied(page, mapping);
- __xa_set_mark(&mapping->i_pages, page_index(page),
+ if (folio->mapping) { /* Race with truncate? */
+ WARN_ON_ONCE(warn && !folio_test_uptodate(folio));
+ folio_account_dirtied(folio, mapping);
+ __xa_set_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_DIRTY);
}
xa_unlock_irqrestore(&mapping->i_pages, flags);
}
-/*
- * For address_spaces which do not use buffers. Just tag the page as dirty in
- * the xarray.
+/**
+ * filemap_dirty_folio - Mark a folio dirty for filesystems which do not use buffer_heads.
+ * @mapping: Address space this folio belongs to.
+ * @folio: Folio to be marked as dirty.
+ *
+ * Filesystems which do not use buffer heads should call this function
+ * from their set_page_dirty address space operation. It ignores the
+ * contents of folio_get_private(), so if the filesystem marks individual
+ * blocks as dirty, the filesystem should handle that itself.
*
- * This is also used when a single buffer is being dirtied: we want to set the
- * page dirty in that case, but not all the buffers. This is a "bottom-up"
- * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying.
+ * This is also sometimes used by filesystems which use buffer_heads when
+ * a single buffer is being dirtied: we want to set the folio dirty in
+ * that case, but not all the buffers. This is a "bottom-up" dirtying,
+ * whereas __set_page_dirty_buffers() is a "top-down" dirtying.
*
- * The caller must ensure this doesn't race with truncation. Most will simply
- * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and
- * the pte lock held, which also locks out truncation.
+ * The caller must ensure this doesn't race with truncation. Most will
+ * simply hold the folio lock, but e.g. zap_pte_range() calls with the
+ * folio mapped and the pte lock held, which also locks out truncation.
*/
-int __set_page_dirty_nobuffers(struct page *page)
+bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio)
{
- lock_page_memcg(page);
- if (!TestSetPageDirty(page)) {
- struct address_space *mapping = page_mapping(page);
+ folio_memcg_lock(folio);
+ if (folio_test_set_dirty(folio)) {
+ folio_memcg_unlock(folio);
+ return false;
+ }
- if (!mapping) {
- unlock_page_memcg(page);
- return 1;
- }
- __set_page_dirty(page, mapping, !PagePrivate(page));
- unlock_page_memcg(page);
+ __folio_mark_dirty(folio, mapping, !folio_test_private(folio));
+ folio_memcg_unlock(folio);
- if (mapping->host) {
- /* !PageAnon && !swapper_space */
- __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
- }
- return 1;
+ if (mapping->host) {
+ /* !PageAnon && !swapper_space */
+ __mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
}
- unlock_page_memcg(page);
- return 0;
+ return true;
}
-EXPORT_SYMBOL(__set_page_dirty_nobuffers);
+EXPORT_SYMBOL(filemap_dirty_folio);
-/*
- * Call this whenever redirtying a page, to de-account the dirty counters
- * (NR_DIRTIED, WB_DIRTIED, tsk->nr_dirtied), so that they match the written
- * counters (NR_WRITTEN, WB_WRITTEN) in long term. The mismatches will lead to
- * systematic errors in balanced_dirty_ratelimit and the dirty pages position
- * control.
+/**
+ * folio_account_redirty - Manually account for redirtying a page.
+ * @folio: The folio which is being redirtied.
+ *
+ * Most filesystems should call folio_redirty_for_writepage() instead
+ * of this fuction. If your filesystem is doing writeback outside the
+ * context of a writeback_control(), it can call this when redirtying
+ * a folio, to de-account the dirty counters (NR_DIRTIED, WB_DIRTIED,
+ * tsk->nr_dirtied), so that they match the written counters (NR_WRITTEN,
+ * WB_WRITTEN) in long term. The mismatches will lead to systematic errors
+ * in balanced_dirty_ratelimit and the dirty pages position control.
*/
-void account_page_redirty(struct page *page)
+void folio_account_redirty(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
+ long nr = folio_nr_pages(folio);
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- current->nr_dirtied--;
- dec_node_page_state(page, NR_DIRTIED);
- dec_wb_stat(wb, WB_DIRTIED);
+ current->nr_dirtied -= nr;
+ node_stat_mod_folio(folio, NR_DIRTIED, -nr);
+ wb_stat_mod(wb, WB_DIRTIED, -nr);
unlocked_inode_to_wb_end(inode, &cookie);
}
}
-EXPORT_SYMBOL(account_page_redirty);
+EXPORT_SYMBOL(folio_account_redirty);
-/*
- * When a writepage implementation decides that it doesn't want to write this
- * page for some reason, it should redirty the locked page via
- * redirty_page_for_writepage() and it should then unlock the page and return 0
+/**
+ * folio_redirty_for_writepage - Decline to write a dirty folio.
+ * @wbc: The writeback control.
+ * @folio: The folio.
+ *
+ * When a writepage implementation decides that it doesn't want to write
+ * @folio for some reason, it should call this function, unlock @folio and
+ * return 0.
+ *
+ * Return: True if we redirtied the folio. False if someone else dirtied
+ * it first.
*/
-int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page)
+bool folio_redirty_for_writepage(struct writeback_control *wbc,
+ struct folio *folio)
{
- int ret;
+ bool ret;
+ long nr = folio_nr_pages(folio);
+
+ wbc->pages_skipped += nr;
+ ret = filemap_dirty_folio(folio->mapping, folio);
+ folio_account_redirty(folio);
- wbc->pages_skipped++;
- ret = __set_page_dirty_nobuffers(page);
- account_page_redirty(page);
return ret;
}
-EXPORT_SYMBOL(redirty_page_for_writepage);
+EXPORT_SYMBOL(folio_redirty_for_writepage);
-/*
- * Dirty a page.
+/**
+ * folio_mark_dirty - Mark a folio as being modified.
+ * @folio: The folio.
*
- * For pages with a mapping this should be done under the page lock for the
- * benefit of asynchronous memory errors who prefer a consistent dirty state.
- * This rule can be broken in some special cases, but should be better not to.
+ * For folios with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
+ *
+ * Return: True if the folio was newly dirtied, false if it was already dirty.
*/
-int set_page_dirty(struct page *page)
+bool folio_mark_dirty(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
- page = compound_head(page);
if (likely(mapping)) {
/*
* readahead/lru_deactivate_page could remain
@@ -2604,17 +2627,17 @@ int set_page_dirty(struct page *page)
* it will confuse readahead and make it restart the size rampup
* process. But it's a trivial problem.
*/
- if (PageReclaim(page))
- ClearPageReclaim(page);
- return mapping->a_ops->set_page_dirty(page);
+ if (folio_test_reclaim(folio))
+ folio_clear_reclaim(folio);
+ return mapping->a_ops->set_page_dirty(&folio->page);
}
- if (!PageDirty(page)) {
- if (!TestSetPageDirty(page))
- return 1;
+ if (!folio_test_dirty(folio)) {
+ if (!folio_test_set_dirty(folio))
+ return true;
}
- return 0;
+ return false;
}
-EXPORT_SYMBOL(set_page_dirty);
+EXPORT_SYMBOL(folio_mark_dirty);
/*
* set_page_dirty() is racy if the caller has no reference against
@@ -2650,49 +2673,49 @@ EXPORT_SYMBOL(set_page_dirty_lock);
* page without actually doing it through the VM. Can you say "ext3 is
* horribly ugly"? Thought you could.
*/
-void __cancel_dirty_page(struct page *page)
+void __folio_cancel_dirty(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
+ struct address_space *mapping = folio_mapping(folio);
if (mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct wb_lock_cookie cookie = {};
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- if (TestClearPageDirty(page))
- account_page_cleaned(page, mapping, wb);
+ if (folio_test_clear_dirty(folio))
+ folio_account_cleaned(folio, mapping, wb);
unlocked_inode_to_wb_end(inode, &cookie);
- unlock_page_memcg(page);
+ folio_memcg_unlock(folio);
} else {
- ClearPageDirty(page);
+ folio_clear_dirty(folio);
}
}
-EXPORT_SYMBOL(__cancel_dirty_page);
+EXPORT_SYMBOL(__folio_cancel_dirty);
/*
- * Clear a page's dirty flag, while caring for dirty memory accounting.
- * Returns true if the page was previously dirty.
- *
- * This is for preparing to put the page under writeout. We leave the page
- * tagged as dirty in the xarray so that a concurrent write-for-sync
- * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage
- * implementation will run either set_page_writeback() or set_page_dirty(),
- * at which stage we bring the page's dirty flag and xarray dirty tag
- * back into sync.
- *
- * This incoherency between the page's dirty flag and xarray tag is
- * unfortunate, but it only exists while the page is locked.
+ * Clear a folio's dirty flag, while caring for dirty memory accounting.
+ * Returns true if the folio was previously dirty.
+ *
+ * This is for preparing to put the folio under writeout. We leave
+ * the folio tagged as dirty in the xarray so that a concurrent
+ * write-for-sync can discover it via a PAGECACHE_TAG_DIRTY walk.
+ * The ->writepage implementation will run either folio_start_writeback()
+ * or folio_mark_dirty(), at which stage we bring the folio's dirty flag
+ * and xarray dirty tag back into sync.
+ *
+ * This incoherency between the folio's dirty flag and xarray tag is
+ * unfortunate, but it only exists while the folio is locked.
*/
-int clear_page_dirty_for_io(struct page *page)
+bool folio_clear_dirty_for_io(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
- int ret = 0;
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret = false;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
+ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
if (mapping && mapping_can_writeback(mapping)) {
struct inode *inode = mapping->host;
@@ -2705,48 +2728,49 @@ int clear_page_dirty_for_io(struct page *page)
* We use this sequence to make sure that
* (a) we account for dirty stats properly
* (b) we tell the low-level filesystem to
- * mark the whole page dirty if it was
+ * mark the whole folio dirty if it was
* dirty in a pagetable. Only to then
- * (c) clean the page again and return 1 to
+ * (c) clean the folio again and return 1 to
* cause the writeback.
*
* This way we avoid all nasty races with the
* dirty bit in multiple places and clearing
* them concurrently from different threads.
*
- * Note! Normally the "set_page_dirty(page)"
+ * Note! Normally the "folio_mark_dirty(folio)"
* has no effect on the actual dirty bit - since
* that will already usually be set. But we
* need the side effects, and it can help us
* avoid races.
*
- * We basically use the page "master dirty bit"
+ * We basically use the folio "master dirty bit"
* as a serialization point for all the different
* threads doing their things.
*/
- if (page_mkclean(page))
- set_page_dirty(page);
+ if (folio_mkclean(folio))
+ folio_mark_dirty(folio);
/*
* We carefully synchronise fault handlers against
- * installing a dirty pte and marking the page dirty
+ * installing a dirty pte and marking the folio dirty
* at this point. We do this by having them hold the
- * page lock while dirtying the page, and pages are
+ * page lock while dirtying the folio, and folios are
* always locked coming in here, so we get the desired
* exclusion.
*/
wb = unlocked_inode_to_wb_begin(inode, &cookie);
- if (TestClearPageDirty(page)) {
- dec_lruvec_page_state(page, NR_FILE_DIRTY);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- dec_wb_stat(wb, WB_RECLAIMABLE);
- ret = 1;
+ if (folio_test_clear_dirty(folio)) {
+ long nr = folio_nr_pages(folio);
+ lruvec_stat_mod_folio(folio, NR_FILE_DIRTY, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ wb_stat_mod(wb, WB_RECLAIMABLE, -nr);
+ ret = true;
}
unlocked_inode_to_wb_end(inode, &cookie);
return ret;
}
- return TestClearPageDirty(page);
+ return folio_test_clear_dirty(folio);
}
-EXPORT_SYMBOL(clear_page_dirty_for_io);
+EXPORT_SYMBOL(folio_clear_dirty_for_io);
static void wb_inode_writeback_start(struct bdi_writeback *wb)
{
@@ -2766,27 +2790,28 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
queue_delayed_work(bdi_wq, &wb->bw_dwork, BANDWIDTH_INTERVAL);
}
-int test_clear_page_writeback(struct page *page)
+bool __folio_end_writeback(struct folio *folio)
{
- struct address_space *mapping = page_mapping(page);
- int ret;
+ long nr = folio_nr_pages(folio);
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret;
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
if (mapping && mapping_use_writeback_tags(mapping)) {
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
xa_lock_irqsave(&mapping->i_pages, flags);
- ret = TestClearPageWriteback(page);
+ ret = folio_test_clear_writeback(folio);
if (ret) {
- __xa_clear_mark(&mapping->i_pages, page_index(page),
+ __xa_clear_mark(&mapping->i_pages, folio_index(folio),
PAGECACHE_TAG_WRITEBACK);
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
- dec_wb_stat(wb, WB_WRITEBACK);
- __wb_writeout_inc(wb);
+ wb_stat_mod(wb, WB_WRITEBACK, -nr);
+ __wb_writeout_add(wb, nr);
if (!mapping_tagged(mapping,
PAGECACHE_TAG_WRITEBACK))
wb_inode_writeback_end(wb);
@@ -2799,32 +2824,34 @@ int test_clear_page_writeback(struct page *page)
xa_unlock_irqrestore(&mapping->i_pages, flags);
} else {
- ret = TestClearPageWriteback(page);
+ ret = folio_test_clear_writeback(folio);
}
if (ret) {
- dec_lruvec_page_state(page, NR_WRITEBACK);
- dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);
- inc_node_page_state(page, NR_WRITTEN);
+ lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+ node_stat_mod_folio(folio, NR_WRITTEN, nr);
}
- unlock_page_memcg(page);
+ folio_memcg_unlock(folio);
return ret;
}
-int __test_set_page_writeback(struct page *page, bool keep_write)
+bool __folio_start_writeback(struct folio *folio, bool keep_write)
{
- struct address_space *mapping = page_mapping(page);
- int ret, access_ret;
+ long nr = folio_nr_pages(folio);
+ struct address_space *mapping = folio_mapping(folio);
+ bool ret;
+ int access_ret;
- lock_page_memcg(page);
+ folio_memcg_lock(folio);
if (mapping && mapping_use_writeback_tags(mapping)) {
- XA_STATE(xas, &mapping->i_pages, page_index(page));
+ XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct inode *inode = mapping->host;
struct backing_dev_info *bdi = inode_to_bdi(inode);
unsigned long flags;
xas_lock_irqsave(&xas, flags);
xas_load(&xas);
- ret = TestSetPageWriteback(page);
+ ret = folio_test_set_writeback(folio);
if (!ret) {
bool on_wblist;
@@ -2835,84 +2862,105 @@ int __test_set_page_writeback(struct page *page, bool keep_write)
if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
struct bdi_writeback *wb = inode_to_wb(inode);
- inc_wb_stat(wb, WB_WRITEBACK);
+ wb_stat_mod(wb, WB_WRITEBACK, nr);
if (!on_wblist)
wb_inode_writeback_start(wb);
}
/*
- * We can come through here when swapping anonymous
- * pages, so we don't necessarily have an inode to track
- * for sync.
+ * We can come through here when swapping
+ * anonymous folios, so we don't necessarily
+ * have an inode to track for sync.
*/
if (mapping->host && !on_wblist)
sb_mark_inode_writeback(mapping->host);
}
- if (!PageDirty(page))
+ if (!folio_test_dirty(folio))
xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY);
if (!keep_write)
xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE);
xas_unlock_irqrestore(&xas, flags);
} else {
- ret = TestSetPageWriteback(page);
+ ret = folio_test_set_writeback(folio);
}
if (!ret) {
- inc_lruvec_page_state(page, NR_WRITEBACK);
- inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);
+ lruvec_stat_mod_folio(folio, NR_WRITEBACK, nr);
+ zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, nr);
}
- unlock_page_memcg(page);
- access_ret = arch_make_page_accessible(page);
+ folio_memcg_unlock(folio);
+ access_ret = arch_make_folio_accessible(folio);
/*
* If writeback has been triggered on a page that cannot be made
* accessible, it is too late to recover here.
*/
- VM_BUG_ON_PAGE(access_ret != 0, page);
+ VM_BUG_ON_FOLIO(access_ret != 0, folio);
return ret;
-
}
-EXPORT_SYMBOL(__test_set_page_writeback);
+EXPORT_SYMBOL(__folio_start_writeback);
-/*
- * Wait for a page to complete writeback
+/**
+ * folio_wait_writeback - Wait for a folio to finish writeback.
+ * @folio: The folio to wait for.
+ *
+ * If the folio is currently being written back to storage, wait for the
+ * I/O to complete.
+ *
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
*/
-void wait_on_page_writeback(struct page *page)
+void folio_wait_writeback(struct folio *folio)
{
- while (PageWriteback(page)) {
- trace_wait_on_page_writeback(page, page_mapping(page));
- wait_on_page_bit(page, PG_writeback);
+ while (folio_test_writeback(folio)) {
+ trace_folio_wait_writeback(folio, folio_mapping(folio));
+ folio_wait_bit(folio, PG_writeback);
}
}
-EXPORT_SYMBOL_GPL(wait_on_page_writeback);
+EXPORT_SYMBOL_GPL(folio_wait_writeback);
-/*
- * Wait for a page to complete writeback. Returns -EINTR if we get a
- * fatal signal while waiting.
+/**
+ * folio_wait_writeback_killable - Wait for a folio to finish writeback.
+ * @folio: The folio to wait for.
+ *
+ * If the folio is currently being written back to storage, wait for the
+ * I/O to complete or a fatal signal to arrive.
+ *
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
+ * Return: 0 on success, -EINTR if we get a fatal signal while waiting.
*/
-int wait_on_page_writeback_killable(struct page *page)
+int folio_wait_writeback_killable(struct folio *folio)
{
- while (PageWriteback(page)) {
- trace_wait_on_page_writeback(page, page_mapping(page));
- if (wait_on_page_bit_killable(page, PG_writeback))
+ while (folio_test_writeback(folio)) {
+ trace_folio_wait_writeback(folio, folio_mapping(folio));
+ if (folio_wait_bit_killable(folio, PG_writeback))
return -EINTR;
}
return 0;
}
-EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+EXPORT_SYMBOL_GPL(folio_wait_writeback_killable);
/**
- * wait_for_stable_page() - wait for writeback to finish, if necessary.
- * @page: The page to wait on.
+ * folio_wait_stable() - wait for writeback to finish, if necessary.
+ * @folio: The folio to wait on.
+ *
+ * This function determines if the given folio is related to a backing
+ * device that requires folio contents to be held stable during writeback.
+ * If so, then it will wait for any pending writeback to complete.
*
- * This function determines if the given page is related to a backing device
- * that requires page contents to be held stable during writeback. If so, then
- * it will wait for any pending writeback to complete.
+ * Context: Sleeps. Must be called in process context and with
+ * no spinlocks held. Caller should hold a reference on the folio.
+ * If the folio is not locked, writeback may start again after writeback
+ * has finished.
*/
-void wait_for_stable_page(struct page *page)
+void folio_wait_stable(struct folio *folio)
{
- page = thp_head(page);
- if (page->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
- wait_on_page_writeback(page);
+ if (folio->mapping->host->i_sb->s_iflags & SB_I_STABLE_WRITES)
+ folio_wait_writeback(folio);
}
-EXPORT_SYMBOL_GPL(wait_for_stable_page);
+EXPORT_SYMBOL_GPL(folio_wait_stable);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b37435c274cf..fee18ada46a2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -724,7 +724,7 @@ static inline void free_the_page(struct page *page, unsigned int order)
void free_compound_page(struct page *page)
{
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
free_the_page(page, compound_order(page));
}
@@ -1312,8 +1312,10 @@ static __always_inline bool free_pages_prepare(struct page *page,
VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
- if (compound)
+ if (compound) {
ClearPageDoubleMap(page);
+ ClearPageHasHWPoisoned(page);
+ }
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
@@ -5223,6 +5225,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
if (unlikely(page_array && nr_pages - nr_populated == 0))
goto out;
+ /* Bulk allocator does not support memcg accounting. */
+ if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
+ goto failed;
+
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
@@ -5400,6 +5406,18 @@ out:
}
EXPORT_SYMBOL(__alloc_pages);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+ nodemask_t *nodemask)
+{
+ struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
+ preferred_nid, nodemask);
+
+ if (page && order > 1)
+ prep_transhuge_page(page);
+ return (struct folio *)page;
+}
+EXPORT_SYMBOL(__folio_alloc);
+
/*
* Common helper functions. Never use with __GFP_HIGHMEM because the returned
* address cannot represent highmem pages. Use alloc_pages and then kmap if
diff --git a/mm/page_ext.c b/mm/page_ext.c
index dfb91653d359..2a52fd9ed464 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -269,7 +269,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid)
total_usage += table_size;
return 0;
}
-#ifdef CONFIG_MEMORY_HOTPLUG
+
static void free_page_ext(void *addr)
{
if (is_vmalloc_addr(addr)) {
@@ -374,8 +374,6 @@ static int __meminit page_ext_callback(struct notifier_block *self,
return notifier_from_errno(ret);
}
-#endif
-
void __init page_ext_init(void)
{
unsigned long pfn;
diff --git a/mm/page_io.c b/mm/page_io.c
index 6010fb07f231..9725c7e1eeea 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -38,7 +38,7 @@ void end_swap_bio_write(struct bio *bio)
* Also print a dire warning that things will go BAD (tm)
* very quickly.
*
- * Also clear PG_reclaim to avoid rotate_reclaimable_page()
+ * Also clear PG_reclaim to avoid folio_rotate_reclaimable()
*/
set_page_dirty(page);
pr_alert_ratelimited("Write-error on swap-device (%u:%u:%llu)\n",
@@ -317,7 +317,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
* temporary failure if the system has limited
* memory for allocating transmit buffers.
* Mark the page dirty and avoid
- * rotate_reclaimable_page but rate-limit the
+ * folio_rotate_reclaimable but rate-limit the
* messages but do not flag PageError like
* the normal direct-to-bio case as it could
* be temporary.
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 62402d22539b..d24ed221357c 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -210,10 +210,10 @@ void __split_page_owner(struct page *page, unsigned int nr)
}
}
-void __copy_page_owner(struct page *oldpage, struct page *newpage)
+void __folio_copy_owner(struct folio *newfolio, struct folio *old)
{
- struct page_ext *old_ext = lookup_page_ext(oldpage);
- struct page_ext *new_ext = lookup_page_ext(newpage);
+ struct page_ext *old_ext = lookup_page_ext(&old->page);
+ struct page_ext *new_ext = lookup_page_ext(&newfolio->page);
struct page_owner *old_page_owner, *new_page_owner;
if (unlikely(!old_ext || !new_ext))
@@ -231,11 +231,11 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage)
new_page_owner->free_ts_nsec = old_page_owner->ts_nsec;
/*
- * We don't clear the bit on the oldpage as it's going to be freed
+ * We don't clear the bit on the old folio as it's going to be freed
* after migration. Until then, the info can be useful in case of
* a bug, and the overall stats will be off a bit only temporarily.
* Also, migrate_misplaced_transhuge_page() can still fail the
- * migration and then we want the oldpage to retain the info. But
+ * migration and then we want the old folio to retain the info. But
* in that case we also don't need to explicitly clear the info from
* the new page, which will be freed.
*/
diff --git a/mm/rmap.c b/mm/rmap.c
index 6aebd1747251..3a1059c284c3 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -34,7 +34,7 @@
* mapping->private_lock (in __set_page_dirty_buffers)
* lock_page_memcg move_lock (in __set_page_dirty_buffers)
* i_pages lock (widely used)
- * lruvec->lru_lock (in lock_page_lruvec_irq)
+ * lruvec->lru_lock (in folio_lruvec_lock_irq)
* inode->i_lock (in set_page_dirty's __mark_inode_dirty)
* bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty)
* sb_lock (within inode_lock in fs/fs-writeback.c)
@@ -981,7 +981,7 @@ static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg)
return true;
}
-int page_mkclean(struct page *page)
+int folio_mkclean(struct folio *folio)
{
int cleaned = 0;
struct address_space *mapping;
@@ -991,20 +991,20 @@ int page_mkclean(struct page *page)
.invalid_vma = invalid_mkclean_vma,
};
- BUG_ON(!PageLocked(page));
+ BUG_ON(!folio_test_locked(folio));
- if (!page_mapped(page))
+ if (!folio_mapped(folio))
return 0;
- mapping = page_mapping(page);
+ mapping = folio_mapping(folio);
if (!mapping)
return 0;
- rmap_walk(page, &rwc);
+ rmap_walk(&folio->page, &rwc);
return cleaned;
}
-EXPORT_SYMBOL_GPL(page_mkclean);
+EXPORT_SYMBOL_GPL(folio_mkclean);
/**
* page_move_anon_rmap - move a page to our anon_vma
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 1fea68b8d5a6..22b310adb53d 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -18,7 +18,6 @@
#include <linux/secretmem.h>
#include <linux/set_memory.h>
#include <linux/sched/signal.h>
-#include <linux/refcount.h>
#include <uapi/linux/magic.h>
@@ -41,11 +40,11 @@ module_param_named(enable, secretmem_enable, bool, 0400);
MODULE_PARM_DESC(secretmem_enable,
"Enable secretmem and memfd_secret(2) system call");
-static refcount_t secretmem_users;
+static atomic_t secretmem_users;
bool secretmem_active(void)
{
- return !!refcount_read(&secretmem_users);
+ return !!atomic_read(&secretmem_users);
}
static vm_fault_t secretmem_fault(struct vm_fault *vmf)
@@ -104,7 +103,7 @@ static const struct vm_operations_struct secretmem_vm_ops = {
static int secretmem_release(struct inode *inode, struct file *file)
{
- refcount_dec(&secretmem_users);
+ atomic_dec(&secretmem_users);
return 0;
}
@@ -204,6 +203,8 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
if (flags & ~(SECRETMEM_FLAGS_MASK | O_CLOEXEC))
return -EINVAL;
+ if (atomic_read(&secretmem_users) < 0)
+ return -ENFILE;
fd = get_unused_fd_flags(flags & O_CLOEXEC);
if (fd < 0)
@@ -217,8 +218,8 @@ SYSCALL_DEFINE1(memfd_secret, unsigned int, flags)
file->f_flags |= O_LARGEFILE;
+ atomic_inc(&secretmem_users);
fd_install(fd, file);
- refcount_inc(&secretmem_users);
return fd;
err_put_fd:
diff --git a/mm/shmem.c b/mm/shmem.c
index 2ca4a341652c..17e344e26e73 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -709,7 +709,7 @@ static int shmem_add_to_page_cache(struct page *page,
page->index = index;
if (!PageSwapCache(page)) {
- error = mem_cgroup_charge(page, charge_mm, gfp);
+ error = mem_cgroup_charge(page_folio(page), charge_mm, gfp);
if (error) {
if (PageTransHuge(page)) {
count_vm_event(THP_FILE_FALLBACK);
@@ -1636,6 +1636,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct page *oldpage, *newpage;
+ struct folio *old, *new;
struct address_space *swap_mapping;
swp_entry_t entry;
pgoff_t swap_index;
@@ -1672,7 +1673,9 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp,
xa_lock_irq(&swap_mapping->i_pages);
error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage);
if (!error) {
- mem_cgroup_migrate(oldpage, newpage);
+ old = page_folio(oldpage);
+ new = page_folio(newpage);
+ mem_cgroup_migrate(old, new);
__inc_lruvec_page_state(newpage, NR_FILE_PAGES);
__dec_lruvec_page_state(oldpage, NR_FILE_PAGES);
}
diff --git a/mm/slab.c b/mm/slab.c
index d0f725637663..874b3f8fe80d 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1095,7 +1095,7 @@ static int slab_offline_cpu(unsigned int cpu)
return 0;
}
-#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+#if defined(CONFIG_NUMA)
/*
* Drains freelist for a node on each slab cache, used for memory hot-remove.
* Returns -EBUSY if all objects cannot be drained so that the node is not
@@ -1157,7 +1157,7 @@ static int __meminit slab_memory_callback(struct notifier_block *self,
out:
return notifier_from_errno(ret);
}
-#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
+#endif /* CONFIG_NUMA */
/*
* swap the static kmem_cache_node with kmalloced memory
diff --git a/mm/slub.c b/mm/slub.c
index 3d2025f7163b..d8f77346376d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1701,7 +1701,8 @@ static __always_inline bool slab_free_hook(struct kmem_cache *s,
}
static inline bool slab_free_freelist_hook(struct kmem_cache *s,
- void **head, void **tail)
+ void **head, void **tail,
+ int *cnt)
{
void *object;
@@ -1728,6 +1729,12 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
*head = object;
if (!*tail)
*tail = object;
+ } else {
+ /*
+ * Adjust the reconstructed freelist depth
+ * accordingly if object's reuse is delayed.
+ */
+ --(*cnt);
}
} while (object != old_tail);
@@ -3413,7 +3420,9 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
struct kmem_cache_cpu *c;
unsigned long tid;
- memcg_slab_free_hook(s, &head, 1);
+ /* memcg_slab_free_hook() is already called for bulk free. */
+ if (!tail)
+ memcg_slab_free_hook(s, &head, 1);
redo:
/*
* Determine the currently cpus per cpu slab.
@@ -3480,7 +3489,7 @@ static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
* With KASAN enabled slab_free_freelist_hook modifies the freelist
* to remove objects, whose reuse must be delayed.
*/
- if (slab_free_freelist_hook(s, &head, &tail))
+ if (slab_free_freelist_hook(s, &head, &tail, &cnt))
do_slab_free(s, page, head, tail, cnt, addr);
}
@@ -4203,8 +4212,8 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags)
if (alloc_kmem_cache_cpus(s))
return 0;
- free_kmem_cache_nodes(s);
error:
+ __kmem_cache_release(s);
return -EINVAL;
}
@@ -4880,13 +4889,15 @@ int __kmem_cache_create(struct kmem_cache *s, slab_flags_t flags)
return 0;
err = sysfs_slab_add(s);
- if (err)
+ if (err) {
__kmem_cache_release(s);
+ return err;
+ }
if (s->flags & SLAB_STORE_USER)
debugfs_slab_add(s);
- return err;
+ return 0;
}
void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
@@ -6108,9 +6119,14 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
struct kmem_cache *s = file_inode(filep)->i_private;
unsigned long *obj_map;
+ if (!t)
+ return -ENOMEM;
+
obj_map = bitmap_alloc(oo_objects(s->oo), GFP_KERNEL);
- if (!obj_map)
+ if (!obj_map) {
+ seq_release_private(inode, filep);
return -ENOMEM;
+ }
if (strcmp(filep->f_path.dentry->d_name.name, "alloc_traces") == 0)
alloc = TRACK_ALLOC;
@@ -6119,6 +6135,7 @@ static int slab_debug_trace_open(struct inode *inode, struct file *filep)
if (!alloc_loc_track(t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) {
bitmap_free(obj_map);
+ seq_release_private(inode, filep);
return -ENOMEM;
}
diff --git a/mm/swap.c b/mm/swap.c
index af3cad4e5378..8ff9ba7cf2de 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -80,10 +80,11 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
static void __page_cache_release(struct page *page)
{
if (PageLRU(page)) {
+ struct folio *folio = page_folio(page);
struct lruvec *lruvec;
unsigned long flags;
- lruvec = lock_page_lruvec_irqsave(page, &flags);
+ lruvec = folio_lruvec_lock_irqsave(folio, &flags);
del_page_from_lru_list(page, lruvec);
__clear_page_lru_flags(page);
unlock_page_lruvec_irqrestore(lruvec, flags);
@@ -94,7 +95,7 @@ static void __page_cache_release(struct page *page)
static void __put_single_page(struct page *page)
{
__page_cache_release(page);
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
free_unref_page(page, 0);
}
@@ -188,12 +189,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
for (i = 0; i < pagevec_count(pvec); i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
/* block memcg migration during page moving between lru */
if (!TestClearPageLRU(page))
continue;
- lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags);
(*move_fn)(page, lruvec);
SetPageLRU(page);
@@ -206,11 +208,13 @@ static void pagevec_lru_move_fn(struct pagevec *pvec,
static void pagevec_move_tail_fn(struct page *page, struct lruvec *lruvec)
{
- if (!PageUnevictable(page)) {
- del_page_from_lru_list(page, lruvec);
- ClearPageActive(page);
- add_page_to_lru_list_tail(page, lruvec);
- __count_vm_events(PGROTATED, thp_nr_pages(page));
+ struct folio *folio = page_folio(page);
+
+ if (!folio_test_unevictable(folio)) {
+ lruvec_del_folio(lruvec, folio);
+ folio_clear_active(folio);
+ lruvec_add_folio_tail(lruvec, folio);
+ __count_vm_events(PGROTATED, folio_nr_pages(folio));
}
}
@@ -227,23 +231,23 @@ static bool pagevec_add_and_need_flush(struct pagevec *pvec, struct page *page)
}
/*
- * Writeback is about to end against a page which has been marked for immediate
- * reclaim. If it still appears to be reclaimable, move it to the tail of the
- * inactive list.
+ * Writeback is about to end against a folio which has been marked for
+ * immediate reclaim. If it still appears to be reclaimable, move it
+ * to the tail of the inactive list.
*
- * rotate_reclaimable_page() must disable IRQs, to prevent nasty races.
+ * folio_rotate_reclaimable() must disable IRQs, to prevent nasty races.
*/
-void rotate_reclaimable_page(struct page *page)
+void folio_rotate_reclaimable(struct folio *folio)
{
- if (!PageLocked(page) && !PageDirty(page) &&
- !PageUnevictable(page) && PageLRU(page)) {
+ if (!folio_test_locked(folio) && !folio_test_dirty(folio) &&
+ !folio_test_unevictable(folio) && folio_test_lru(folio)) {
struct pagevec *pvec;
unsigned long flags;
- get_page(page);
+ folio_get(folio);
local_lock_irqsave(&lru_rotate.lock, flags);
pvec = this_cpu_ptr(&lru_rotate.pvec);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
pagevec_lru_move_fn(pvec, pagevec_move_tail_fn);
local_unlock_irqrestore(&lru_rotate.lock, flags);
}
@@ -289,21 +293,21 @@ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_pages)
} while ((lruvec = parent_lruvec(lruvec)));
}
-void lru_note_cost_page(struct page *page)
+void lru_note_cost_folio(struct folio *folio)
{
- lru_note_cost(mem_cgroup_page_lruvec(page),
- page_is_file_lru(page), thp_nr_pages(page));
+ lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
+ folio_nr_pages(folio));
}
-static void __activate_page(struct page *page, struct lruvec *lruvec)
+static void __folio_activate(struct folio *folio, struct lruvec *lruvec)
{
- if (!PageActive(page) && !PageUnevictable(page)) {
- int nr_pages = thp_nr_pages(page);
+ if (!folio_test_active(folio) && !folio_test_unevictable(folio)) {
+ long nr_pages = folio_nr_pages(folio);
- del_page_from_lru_list(page, lruvec);
- SetPageActive(page);
- add_page_to_lru_list(page, lruvec);
- trace_mm_lru_activate(page);
+ lruvec_del_folio(lruvec, folio);
+ folio_set_active(folio);
+ lruvec_add_folio(lruvec, folio);
+ trace_mm_lru_activate(folio);
__count_vm_events(PGACTIVATE, nr_pages);
__count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE,
@@ -312,6 +316,11 @@ static void __activate_page(struct page *page, struct lruvec *lruvec)
}
#ifdef CONFIG_SMP
+static void __activate_page(struct page *page, struct lruvec *lruvec)
+{
+ return __folio_activate(page_folio(page), lruvec);
+}
+
static void activate_page_drain(int cpu)
{
struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page, cpu);
@@ -325,16 +334,16 @@ static bool need_activate_page_drain(int cpu)
return pagevec_count(&per_cpu(lru_pvecs.activate_page, cpu)) != 0;
}
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
{
- page = compound_head(page);
- if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
+ if (folio_test_lru(folio) && !folio_test_active(folio) &&
+ !folio_test_unevictable(folio)) {
struct pagevec *pvec;
+ folio_get(folio);
local_lock(&lru_pvecs.lock);
pvec = this_cpu_ptr(&lru_pvecs.activate_page);
- get_page(page);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
pagevec_lru_move_fn(pvec, __activate_page);
local_unlock(&lru_pvecs.lock);
}
@@ -345,21 +354,20 @@ static inline void activate_page_drain(int cpu)
{
}
-static void activate_page(struct page *page)
+static void folio_activate(struct folio *folio)
{
struct lruvec *lruvec;
- page = compound_head(page);
- if (TestClearPageLRU(page)) {
- lruvec = lock_page_lruvec_irq(page);
- __activate_page(page, lruvec);
+ if (folio_test_clear_lru(folio)) {
+ lruvec = folio_lruvec_lock_irq(folio);
+ __folio_activate(folio, lruvec);
unlock_page_lruvec_irq(lruvec);
- SetPageLRU(page);
+ folio_set_lru(folio);
}
}
#endif
-static void __lru_cache_activate_page(struct page *page)
+static void __lru_cache_activate_folio(struct folio *folio)
{
struct pagevec *pvec;
int i;
@@ -380,8 +388,8 @@ static void __lru_cache_activate_page(struct page *page)
for (i = pagevec_count(pvec) - 1; i >= 0; i--) {
struct page *pagevec_page = pvec->pages[i];
- if (pagevec_page == page) {
- SetPageActive(page);
+ if (pagevec_page == &folio->page) {
+ folio_set_active(folio);
break;
}
}
@@ -399,61 +407,59 @@ static void __lru_cache_activate_page(struct page *page)
* When a newly allocated page is not yet visible, so safe for non-atomic ops,
* __SetPageReferenced(page) may be substituted for mark_page_accessed(page).
*/
-void mark_page_accessed(struct page *page)
+void folio_mark_accessed(struct folio *folio)
{
- page = compound_head(page);
-
- if (!PageReferenced(page)) {
- SetPageReferenced(page);
- } else if (PageUnevictable(page)) {
+ if (!folio_test_referenced(folio)) {
+ folio_set_referenced(folio);
+ } else if (folio_test_unevictable(folio)) {
/*
* Unevictable pages are on the "LRU_UNEVICTABLE" list. But,
* this list is never rotated or maintained, so marking an
* evictable page accessed has no effect.
*/
- } else if (!PageActive(page)) {
+ } else if (!folio_test_active(folio)) {
/*
* If the page is on the LRU, queue it for activation via
* lru_pvecs.activate_page. Otherwise, assume the page is on a
* pagevec, mark it active and it'll be moved to the active
* LRU on the next drain.
*/
- if (PageLRU(page))
- activate_page(page);
+ if (folio_test_lru(folio))
+ folio_activate(folio);
else
- __lru_cache_activate_page(page);
- ClearPageReferenced(page);
- workingset_activation(page);
+ __lru_cache_activate_folio(folio);
+ folio_clear_referenced(folio);
+ workingset_activation(folio);
}
- if (page_is_idle(page))
- clear_page_idle(page);
+ if (folio_test_idle(folio))
+ folio_clear_idle(folio);
}
-EXPORT_SYMBOL(mark_page_accessed);
+EXPORT_SYMBOL(folio_mark_accessed);
/**
- * lru_cache_add - add a page to a page list
- * @page: the page to be added to the LRU.
+ * folio_add_lru - Add a folio to an LRU list.
+ * @folio: The folio to be added to the LRU.
*
- * Queue the page for addition to the LRU via pagevec. The decision on whether
+ * Queue the folio for addition to the LRU. The decision on whether
* to add the page to the [in]active [file|anon] list is deferred until the
- * pagevec is drained. This gives a chance for the caller of lru_cache_add()
- * have the page added to the active list using mark_page_accessed().
+ * pagevec is drained. This gives a chance for the caller of folio_add_lru()
+ * have the folio added to the active list using folio_mark_accessed().
*/
-void lru_cache_add(struct page *page)
+void folio_add_lru(struct folio *folio)
{
struct pagevec *pvec;
- VM_BUG_ON_PAGE(PageActive(page) && PageUnevictable(page), page);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_active(folio) && folio_test_unevictable(folio), folio);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
- get_page(page);
+ folio_get(folio);
local_lock(&lru_pvecs.lock);
pvec = this_cpu_ptr(&lru_pvecs.lru_add);
- if (pagevec_add_and_need_flush(pvec, page))
+ if (pagevec_add_and_need_flush(pvec, &folio->page))
__pagevec_lru_add(pvec);
local_unlock(&lru_pvecs.lock);
}
-EXPORT_SYMBOL(lru_cache_add);
+EXPORT_SYMBOL(folio_add_lru);
/**
* lru_cache_add_inactive_or_unevictable
@@ -888,11 +894,12 @@ void release_pages(struct page **pages, int nr)
int i;
LIST_HEAD(pages_to_free);
struct lruvec *lruvec = NULL;
- unsigned long flags;
+ unsigned long flags = 0;
unsigned int lock_batch;
for (i = 0; i < nr; i++) {
struct page *page = pages[i];
+ struct folio *folio = page_folio(page);
/*
* Make sure the IRQ-safe lock-holding time does not get
@@ -904,7 +911,7 @@ void release_pages(struct page **pages, int nr)
lruvec = NULL;
}
- page = compound_head(page);
+ page = &folio->page;
if (is_huge_zero_page(page))
continue;
@@ -943,7 +950,7 @@ void release_pages(struct page **pages, int nr)
if (PageLRU(page)) {
struct lruvec *prev_lruvec = lruvec;
- lruvec = relock_page_lruvec_irqsave(page, lruvec,
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec,
&flags);
if (prev_lruvec != lruvec)
lock_batch = 0;
@@ -985,17 +992,18 @@ void __pagevec_release(struct pagevec *pvec)
}
EXPORT_SYMBOL(__pagevec_release);
-static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
+static void __pagevec_lru_add_fn(struct folio *folio, struct lruvec *lruvec)
{
- int was_unevictable = TestClearPageUnevictable(page);
- int nr_pages = thp_nr_pages(page);
+ int was_unevictable = folio_test_clear_unevictable(folio);
+ long nr_pages = folio_nr_pages(folio);
- VM_BUG_ON_PAGE(PageLRU(page), page);
+ VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
/*
- * Page becomes evictable in two ways:
+ * A folio becomes evictable in two ways:
* 1) Within LRU lock [munlock_vma_page() and __munlock_pagevec()].
- * 2) Before acquiring LRU lock to put the page to correct LRU and then
+ * 2) Before acquiring LRU lock to put the folio on the correct LRU
+ * and then
* a) do PageLRU check with lock [check_move_unevictable_pages]
* b) do PageLRU check before lock [clear_page_mlock]
*
@@ -1004,35 +1012,36 @@ static void __pagevec_lru_add_fn(struct page *page, struct lruvec *lruvec)
*
* #0: __pagevec_lru_add_fn #1: clear_page_mlock
*
- * SetPageLRU() TestClearPageMlocked()
+ * folio_set_lru() folio_test_clear_mlocked()
* smp_mb() // explicit ordering // above provides strict
* // ordering
- * PageMlocked() PageLRU()
+ * folio_test_mlocked() folio_test_lru()
*
*
- * if '#1' does not observe setting of PG_lru by '#0' and fails
- * isolation, the explicit barrier will make sure that page_evictable
- * check will put the page in correct LRU. Without smp_mb(), SetPageLRU
- * can be reordered after PageMlocked check and can make '#1' to fail
- * the isolation of the page whose Mlocked bit is cleared (#0 is also
- * looking at the same page) and the evictable page will be stranded
- * in an unevictable LRU.
+ * if '#1' does not observe setting of PG_lru by '#0' and
+ * fails isolation, the explicit barrier will make sure that
+ * folio_evictable check will put the folio on the correct
+ * LRU. Without smp_mb(), folio_set_lru() can be reordered
+ * after folio_test_mlocked() check and can make '#1' fail the
+ * isolation of the folio whose mlocked bit is cleared (#0 is
+ * also looking at the same folio) and the evictable folio will
+ * be stranded on an unevictable LRU.
*/
- SetPageLRU(page);
+ folio_set_lru(folio);
smp_mb__after_atomic();
- if (page_evictable(page)) {
+ if (folio_evictable(folio)) {
if (was_unevictable)
__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
} else {
- ClearPageActive(page);
- SetPageUnevictable(page);
+ folio_clear_active(folio);
+ folio_set_unevictable(folio);
if (!was_unevictable)
__count_vm_events(UNEVICTABLE_PGCULLED, nr_pages);
}
- add_page_to_lru_list(page, lruvec);
- trace_mm_lru_insertion(page);
+ lruvec_add_folio(lruvec, folio);
+ trace_mm_lru_insertion(folio);
}
/*
@@ -1046,10 +1055,10 @@ void __pagevec_lru_add(struct pagevec *pvec)
unsigned long flags = 0;
for (i = 0; i < pagevec_count(pvec); i++) {
- struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(pvec->pages[i]);
- lruvec = relock_page_lruvec_irqsave(page, lruvec, &flags);
- __pagevec_lru_add_fn(page, lruvec);
+ lruvec = folio_lruvec_relock_irqsave(folio, lruvec, &flags);
+ __pagevec_lru_add_fn(folio, lruvec);
}
if (lruvec)
unlock_page_lruvec_irqrestore(lruvec, flags);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index bc7cee6b2ec5..8d4104242100 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -498,7 +498,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
mem_cgroup_swapin_uncharge_swap(entry);
if (shadow)
- workingset_refault(page, shadow);
+ workingset_refault(page_folio(page), shadow);
/* Caller will initiate read into locked page */
lru_cache_add(page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 30db362749c0..41c9e92f1f00 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3534,13 +3534,13 @@ struct swap_info_struct *page_swap_info(struct page *page)
}
/*
- * out-of-line __page_file_ methods to avoid include hell.
+ * out-of-line methods to avoid include hell.
*/
-struct address_space *__page_file_mapping(struct page *page)
+struct address_space *swapcache_mapping(struct folio *folio)
{
- return page_swap_info(page)->swap_file->f_mapping;
+ return page_swap_info(&folio->page)->swap_file->f_mapping;
}
-EXPORT_SYMBOL_GPL(__page_file_mapping);
+EXPORT_SYMBOL_GPL(swapcache_mapping);
pgoff_t __page_file_index(struct page *page)
{
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7a9008415534..36e5f6ab976f 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -164,7 +164,7 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
__SetPageUptodate(page);
ret = -ENOMEM;
- if (mem_cgroup_charge(page, dst_mm, GFP_KERNEL))
+ if (mem_cgroup_charge(page_folio(page), dst_mm, GFP_KERNEL))
goto out_release;
ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
diff --git a/mm/util.c b/mm/util.c
index bacabe446906..e58151a61255 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -654,81 +654,78 @@ void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
}
EXPORT_SYMBOL(kvrealloc);
-static inline void *__page_rmapping(struct page *page)
-{
- unsigned long mapping;
-
- mapping = (unsigned long)page->mapping;
- mapping &= ~PAGE_MAPPING_FLAGS;
-
- return (void *)mapping;
-}
-
/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
- page = compound_head(page);
- return __page_rmapping(page);
+ return folio_raw_mapping(page_folio(page));
}
-/*
- * Return true if this page is mapped into pagetables.
- * For compound page it returns true if any subpage of compound page is mapped.
+/**
+ * folio_mapped - Is this folio mapped into userspace?
+ * @folio: The folio.
+ *
+ * Return: True if any page in this folio is referenced by user page tables.
*/
-bool page_mapped(struct page *page)
+bool folio_mapped(struct folio *folio)
{
- int i;
+ long i, nr;
- if (likely(!PageCompound(page)))
- return atomic_read(&page->_mapcount) >= 0;
- page = compound_head(page);
- if (atomic_read(compound_mapcount_ptr(page)) >= 0)
+ if (folio_test_single(folio))
+ return atomic_read(&folio->_mapcount) >= 0;
+ if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
return true;
- if (PageHuge(page))
+ if (folio_test_hugetlb(folio))
return false;
- for (i = 0; i < compound_nr(page); i++) {
- if (atomic_read(&page[i]._mapcount) >= 0)
+
+ nr = folio_nr_pages(folio);
+ for (i = 0; i < nr; i++) {
+ if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0)
return true;
}
return false;
}
-EXPORT_SYMBOL(page_mapped);
+EXPORT_SYMBOL(folio_mapped);
struct anon_vma *page_anon_vma(struct page *page)
{
- unsigned long mapping;
+ struct folio *folio = page_folio(page);
+ unsigned long mapping = (unsigned long)folio->mapping;
- page = compound_head(page);
- mapping = (unsigned long)page->mapping;
if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
return NULL;
- return __page_rmapping(page);
+ return (void *)(mapping - PAGE_MAPPING_ANON);
}
-struct address_space *page_mapping(struct page *page)
+/**
+ * folio_mapping - Find the mapping where this folio is stored.
+ * @folio: The folio.
+ *
+ * For folios which are in the page cache, return the mapping that this
+ * page belongs to. Folios in the swap cache return the swap mapping
+ * this page is stored in (which is different from the mapping for the
+ * swap file or swap device where the data is stored).
+ *
+ * You can call this for folios which aren't in the swap cache or page
+ * cache and it will return NULL.
+ */
+struct address_space *folio_mapping(struct folio *folio)
{
struct address_space *mapping;
- page = compound_head(page);
-
/* This happens if someone calls flush_dcache_page on slab page */
- if (unlikely(PageSlab(page)))
+ if (unlikely(folio_test_slab(folio)))
return NULL;
- if (unlikely(PageSwapCache(page))) {
- swp_entry_t entry;
+ if (unlikely(folio_test_swapcache(folio)))
+ return swap_address_space(folio_swap_entry(folio));
- entry.val = page_private(page);
- return swap_address_space(entry);
- }
-
- mapping = page->mapping;
+ mapping = folio->mapping;
if ((unsigned long)mapping & PAGE_MAPPING_ANON)
return NULL;
return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
}
-EXPORT_SYMBOL(page_mapping);
+EXPORT_SYMBOL(folio_mapping);
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
@@ -750,13 +747,26 @@ int __page_mapcount(struct page *page)
}
EXPORT_SYMBOL_GPL(__page_mapcount);
-void copy_huge_page(struct page *dst, struct page *src)
+/**
+ * folio_copy - Copy the contents of one folio to another.
+ * @dst: Folio to copy to.
+ * @src: Folio to copy from.
+ *
+ * The bytes in the folio represented by @src are copied to @dst.
+ * Assumes the caller has validated that @dst is at least as large as @src.
+ * Can be called in atomic context for order-0 folios, but if the folio is
+ * larger, it may sleep.
+ */
+void folio_copy(struct folio *dst, struct folio *src)
{
- unsigned i, nr = compound_nr(src);
+ long i = 0;
+ long nr = folio_nr_pages(src);
- for (i = 0; i < nr; i++) {
+ for (;;) {
+ copy_highpage(folio_page(dst, i), folio_page(src, i));
+ if (++i == nr)
+ break;
cond_resched();
- copy_highpage(nth_page(dst, i), nth_page(src, i));
}
}
@@ -1079,3 +1089,14 @@ void page_offline_end(void)
up_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_end);
+
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+void flush_dcache_folio(struct folio *folio)
+{
+ long i, nr = folio_nr_pages(folio);
+
+ for (i = 0; i < nr; i++)
+ flush_dcache_page(folio_page(folio, i));
+}
+EXPORT_SYMBOL(flush_dcache_folio);
+#endif
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d77830ff604c..e8a807c78110 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2816,6 +2816,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
unsigned int order, unsigned int nr_pages, struct page **pages)
{
unsigned int nr_allocated = 0;
+ struct page *page;
+ int i;
/*
* For order-0 pages we make use of bulk allocator, if
@@ -2823,7 +2825,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
* to fails, fallback to a single page allocator that is
* more permissive.
*/
- if (!order) {
+ if (!order && nid != NUMA_NO_NODE) {
while (nr_allocated < nr_pages) {
unsigned int nr, nr_pages_request;
@@ -2848,7 +2850,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
if (nr != nr_pages_request)
break;
}
- } else
+ } else if (order)
/*
* Compound pages required for remap_vmalloc_page if
* high-order pages.
@@ -2856,11 +2858,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
gfp |= __GFP_COMP;
/* High-order pages or fallback path if "bulk" fails. */
- while (nr_allocated < nr_pages) {
- struct page *page;
- int i;
- page = alloc_pages_node(nid, gfp, order);
+ while (nr_allocated < nr_pages) {
+ if (nid == NUMA_NO_NODE)
+ page = alloc_pages(gfp, order);
+ else
+ page = alloc_pages_node(nid, gfp, order);
if (unlikely(!page))
break;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 74296c2d1fed..306229c4313f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2090,6 +2090,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
*/
int isolate_lru_page(struct page *page)
{
+ struct folio *folio = page_folio(page);
int ret = -EBUSY;
VM_BUG_ON_PAGE(!page_count(page), page);
@@ -2099,7 +2100,7 @@ int isolate_lru_page(struct page *page)
struct lruvec *lruvec;
get_page(page);
- lruvec = lock_page_lruvec_irq(page);
+ lruvec = folio_lruvec_lock_irq(folio);
del_page_from_lru_list(page, lruvec);
unlock_page_lruvec_irq(lruvec);
ret = 0;
@@ -2199,7 +2200,7 @@ static unsigned int move_pages_to_lru(struct lruvec *lruvec,
* All pages were isolated from the same lruvec (and isolation
* inhibits memcg migration).
*/
- VM_BUG_ON_PAGE(!page_matches_lruvec(page, lruvec), page);
+ VM_BUG_ON_PAGE(!folio_matches_lruvec(page_folio(page), lruvec), page);
add_page_to_lru_list(page, lruvec);
nr_pages = thp_nr_pages(page);
nr_moved += nr_pages;
@@ -4665,6 +4666,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
for (i = 0; i < pvec->nr; i++) {
struct page *page = pvec->pages[i];
+ struct folio *folio = page_folio(page);
int nr_pages;
if (PageTransTail(page))
@@ -4677,7 +4679,7 @@ void check_move_unevictable_pages(struct pagevec *pvec)
if (!TestClearPageLRU(page))
continue;
- lruvec = relock_page_lruvec_irq(page, lruvec);
+ lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (page_evictable(page) && PageUnevictable(page)) {
del_page_from_lru_list(page, lruvec);
ClearPageUnevictable(page);
diff --git a/mm/workingset.c b/mm/workingset.c
index d5b81e4f4cbe..109ab978251a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -273,17 +273,17 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg)
}
/**
- * workingset_refault - evaluate the refault of a previously evicted page
- * @page: the freshly allocated replacement page
- * @shadow: shadow entry of the evicted page
+ * workingset_refault - Evaluate the refault of a previously evicted folio.
+ * @folio: The freshly allocated replacement folio.
+ * @shadow: Shadow entry of the evicted folio.
*
* Calculates and evaluates the refault distance of the previously
- * evicted page in the context of the node and the memcg whose memory
+ * evicted folio in the context of the node and the memcg whose memory
* pressure caused the eviction.
*/
-void workingset_refault(struct page *page, void *shadow)
+void workingset_refault(struct folio *folio, void *shadow)
{
- bool file = page_is_file_lru(page);
+ bool file = folio_is_file_lru(folio);
struct mem_cgroup *eviction_memcg;
struct lruvec *eviction_lruvec;
unsigned long refault_distance;
@@ -295,16 +295,17 @@ void workingset_refault(struct page *page, void *shadow)
unsigned long refault;
bool workingset;
int memcgid;
+ long nr;
unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset);
rcu_read_lock();
/*
* Look up the memcg associated with the stored ID. It might
- * have been deleted since the page's eviction.
+ * have been deleted since the folio's eviction.
*
* Note that in rare events the ID could have been recycled
- * for a new cgroup that refaults a shared page. This is
+ * for a new cgroup that refaults a shared folio. This is
* impossible to tell from the available data. However, this
* should be a rare and limited disturbance, and activations
* are always speculative anyway. Ultimately, it's the aging
@@ -340,17 +341,18 @@ void workingset_refault(struct page *page, void *shadow)
refault_distance = (refault - eviction) & EVICTION_MASK;
/*
- * The activation decision for this page is made at the level
+ * The activation decision for this folio is made at the level
* where the eviction occurred, as that is where the LRU order
- * during page reclaim is being determined.
+ * during folio reclaim is being determined.
*
- * However, the cgroup that will own the page is the one that
+ * However, the cgroup that will own the folio is the one that
* is actually experiencing the refault event.
*/
- memcg = page_memcg(page);
+ nr = folio_nr_pages(folio);
+ memcg = folio_memcg(folio);
lruvec = mem_cgroup_lruvec(memcg, pgdat);
- inc_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file);
+ mod_lruvec_state(lruvec, WORKINGSET_REFAULT_BASE + file, nr);
mem_cgroup_flush_stats();
/*
@@ -376,16 +378,16 @@ void workingset_refault(struct page *page, void *shadow)
if (refault_distance > workingset_size)
goto out;
- SetPageActive(page);
- workingset_age_nonresident(lruvec, thp_nr_pages(page));
- inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file);
+ folio_set_active(folio);
+ workingset_age_nonresident(lruvec, nr);
+ mod_lruvec_state(lruvec, WORKINGSET_ACTIVATE_BASE + file, nr);
- /* Page was active prior to eviction */
+ /* Folio was active prior to eviction */
if (workingset) {
- SetPageWorkingset(page);
+ folio_set_workingset(folio);
/* XXX: Move to lru_cache_add() when it supports new vs putback */
- lru_note_cost_page(page);
- inc_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file);
+ lru_note_cost_folio(folio);
+ mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + file, nr);
}
out:
rcu_read_unlock();
@@ -393,12 +395,11 @@ out:
/**
* workingset_activation - note a page activation
- * @page: page that is being activated
+ * @folio: Folio that is being activated.
*/
-void workingset_activation(struct page *page)
+void workingset_activation(struct folio *folio)
{
struct mem_cgroup *memcg;
- struct lruvec *lruvec;
rcu_read_lock();
/*
@@ -408,11 +409,10 @@ void workingset_activation(struct page *page)
* XXX: See workingset_refault() - this should return
* root_mem_cgroup even for !CONFIG_MEMCG.
*/
- memcg = page_memcg_rcu(page);
+ memcg = folio_memcg_rcu(folio);
if (!mem_cgroup_disabled() && !memcg)
goto out;
- lruvec = mem_cgroup_page_lruvec(page);
- workingset_age_nonresident(lruvec, thp_nr_pages(page));
+ workingset_age_nonresident(folio_lruvec(folio), folio_nr_pages(folio));
out:
rcu_read_unlock();
}
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 1669744304c5..17687848daec 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1560,10 +1560,14 @@ int batadv_bla_init(struct batadv_priv *bat_priv)
return 0;
bat_priv->bla.claim_hash = batadv_hash_new(128);
- bat_priv->bla.backbone_hash = batadv_hash_new(32);
+ if (!bat_priv->bla.claim_hash)
+ return -ENOMEM;
- if (!bat_priv->bla.claim_hash || !bat_priv->bla.backbone_hash)
+ bat_priv->bla.backbone_hash = batadv_hash_new(32);
+ if (!bat_priv->bla.backbone_hash) {
+ batadv_hash_destroy(bat_priv->bla.claim_hash);
return -ENOMEM;
+ }
batadv_hash_set_lock_class(bat_priv->bla.claim_hash,
&batadv_claim_hash_lock_class_key);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 3ddd66e4c29e..5207cd8d6ad8 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -190,29 +190,41 @@ int batadv_mesh_init(struct net_device *soft_iface)
bat_priv->gw.generation = 0;
- ret = batadv_v_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
-
ret = batadv_originator_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_orig;
+ }
ret = batadv_tt_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_tt;
+ }
+
+ ret = batadv_v_mesh_init(bat_priv);
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_v;
+ }
ret = batadv_bla_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_bla;
+ }
ret = batadv_dat_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_dat;
+ }
ret = batadv_nc_mesh_init(bat_priv);
- if (ret < 0)
- goto err;
+ if (ret < 0) {
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
+ goto err_nc;
+ }
batadv_gw_init(bat_priv);
batadv_mcast_init(bat_priv);
@@ -222,8 +234,20 @@ int batadv_mesh_init(struct net_device *soft_iface)
return 0;
-err:
- batadv_mesh_free(soft_iface);
+err_nc:
+ batadv_dat_free(bat_priv);
+err_dat:
+ batadv_bla_free(bat_priv);
+err_bla:
+ batadv_v_mesh_free(bat_priv);
+err_v:
+ batadv_tt_free(bat_priv);
+err_tt:
+ batadv_originator_free(bat_priv);
+err_orig:
+ batadv_purge_outstanding_packets(bat_priv, NULL);
+ atomic_set(&bat_priv->mesh_state, BATADV_MESH_INACTIVE);
+
return ret;
}
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 9f06132e007d..0a7f1d36a6a8 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -152,8 +152,10 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
&batadv_nc_coding_hash_lock_class_key);
bat_priv->nc.decoding_hash = batadv_hash_new(128);
- if (!bat_priv->nc.decoding_hash)
+ if (!bat_priv->nc.decoding_hash) {
+ batadv_hash_destroy(bat_priv->nc.coding_hash);
goto err;
+ }
batadv_hash_set_lock_class(bat_priv->nc.decoding_hash,
&batadv_nc_decoding_hash_lock_class_key);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index e0b3dace2020..4b7ad6684bc4 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -4162,8 +4162,10 @@ int batadv_tt_init(struct batadv_priv *bat_priv)
return ret;
ret = batadv_tt_global_init(bat_priv);
- if (ret < 0)
+ if (ret < 0) {
+ batadv_tt_local_table_free(bat_priv);
return ret;
+ }
batadv_tvlv_handler_register(bat_priv, batadv_tt_tvlv_ogm_handler_v1,
batadv_tt_tvlv_unicast_handler_v1,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e8136db44462..37ca76406f1e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1125,9 +1125,7 @@ static inline unsigned long br_multicast_lmqt(const struct net_bridge_mcast *brm
static inline unsigned long br_multicast_gmi(const struct net_bridge_mcast *brmctx)
{
- /* use the RFC default of 2 for QRV */
- return 2 * brmctx->multicast_query_interval +
- brmctx->multicast_query_response_interval;
+ return brmctx->multicast_membership_interval;
}
static inline bool
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 83d1798dfbb4..ba045f35114d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -926,7 +926,9 @@ static int translate_table(struct net *net, const char *name,
return -ENOMEM;
for_each_possible_cpu(i) {
newinfo->chainstack[i] =
- vmalloc(array_size(udc_cnt, sizeof(*(newinfo->chainstack[0]))));
+ vmalloc_node(array_size(udc_cnt,
+ sizeof(*(newinfo->chainstack[0]))),
+ cpu_to_node(i));
if (!newinfo->chainstack[i]) {
while (i)
vfree(newinfo->chainstack[--i]);
diff --git a/net/can/isotp.c b/net/can/isotp.c
index caaa532ece94..df6968b28bf4 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -121,7 +121,7 @@ enum {
struct tpcon {
int idx;
int len;
- u8 state;
+ u32 state;
u8 bs;
u8 sn;
u8 ll_dl;
@@ -848,6 +848,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
{
struct sock *sk = sock->sk;
struct isotp_sock *so = isotp_sk(sk);
+ u32 old_state = so->tx.state;
struct sk_buff *skb;
struct net_device *dev;
struct canfd_frame *cf;
@@ -860,45 +861,55 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
return -EADDRNOTAVAIL;
/* we do not support multiple buffers - for now */
- if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) {
- if (msg->msg_flags & MSG_DONTWAIT)
- return -EAGAIN;
+ if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE ||
+ wq_has_sleeper(&so->wait)) {
+ if (msg->msg_flags & MSG_DONTWAIT) {
+ err = -EAGAIN;
+ goto err_out;
+ }
/* wait for complete transmission of current pdu */
- wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+ err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+ if (err)
+ goto err_out;
}
- if (!size || size > MAX_MSG_LENGTH)
- return -EINVAL;
+ if (!size || size > MAX_MSG_LENGTH) {
+ err = -EINVAL;
+ goto err_out;
+ }
/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
/* does the given data fit into a single frame for SF_BROADCAST? */
if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) &&
- (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off))
- return -EINVAL;
+ (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) {
+ err = -EINVAL;
+ goto err_out;
+ }
err = memcpy_from_msg(so->tx.buf, msg, size);
if (err < 0)
- return err;
+ goto err_out;
dev = dev_get_by_index(sock_net(sk), so->ifindex);
- if (!dev)
- return -ENXIO;
+ if (!dev) {
+ err = -ENXIO;
+ goto err_out;
+ }
skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv),
msg->msg_flags & MSG_DONTWAIT, &err);
if (!skb) {
dev_put(dev);
- return err;
+ goto err_out;
}
can_skb_reserve(skb);
can_skb_prv(skb)->ifindex = dev->ifindex;
can_skb_prv(skb)->skbcnt = 0;
- so->tx.state = ISOTP_SENDING;
so->tx.len = size;
so->tx.idx = 0;
@@ -954,15 +965,25 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
if (err) {
pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
__func__, ERR_PTR(err));
- return err;
+ goto err_out;
}
if (wait_tx_done) {
/* wait for complete transmission of current pdu */
wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+
+ if (sk->sk_err)
+ return -sk->sk_err;
}
return size;
+
+err_out:
+ so->tx.state = old_state;
+ if (so->tx.state == ISOTP_IDLE)
+ wake_up_interruptible(&so->wait);
+
+ return err;
}
static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index f6df20808f5e..16af1a7f80f6 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -330,6 +330,7 @@ int j1939_session_activate(struct j1939_session *session);
void j1939_tp_schedule_txtimer(struct j1939_session *session, int msec);
void j1939_session_timers_cancel(struct j1939_session *session);
+#define J1939_MIN_TP_PACKET_SIZE 9
#define J1939_MAX_TP_PACKET_SIZE (7 * 0xff)
#define J1939_MAX_ETP_PACKET_SIZE (7 * 0x00ffffff)
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 08c8606cfd9c..9bc55ecb37f9 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -249,11 +249,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
struct j1939_priv *priv, *priv_new;
int ret;
- priv = j1939_priv_get_by_ndev(ndev);
+ spin_lock(&j1939_netdev_lock);
+ priv = j1939_priv_get_by_ndev_locked(ndev);
if (priv) {
kref_get(&priv->rx_kref);
+ spin_unlock(&j1939_netdev_lock);
return priv;
}
+ spin_unlock(&j1939_netdev_lock);
priv = j1939_priv_create(ndev);
if (!priv)
@@ -269,10 +272,10 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
/* Someone was faster than us, use their priv and roll
* back our's.
*/
+ kref_get(&priv_new->rx_kref);
spin_unlock(&j1939_netdev_lock);
dev_put(ndev);
kfree(priv);
- kref_get(&priv_new->rx_kref);
return priv_new;
}
j1939_priv_set(ndev, priv);
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index bb5c4b8979be..6c0a0ebdd024 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1237,12 +1237,11 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer)
session->err = -ETIME;
j1939_session_deactivate(session);
} else {
- netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n",
- __func__, session);
-
j1939_session_list_lock(session->priv);
if (session->state >= J1939_SESSION_ACTIVE &&
session->state < J1939_SESSION_ACTIVE_MAX) {
+ netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n",
+ __func__, session);
j1939_session_get(session);
hrtimer_start(&session->rxtimer,
ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS),
@@ -1609,6 +1608,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
abort = J1939_XTP_ABORT_FAULT;
else if (len > priv->tp_max_packet_size)
abort = J1939_XTP_ABORT_RESOURCE;
+ else if (len < J1939_MIN_TP_PACKET_SIZE)
+ abort = J1939_XTP_ABORT_FAULT;
}
if (abort != J1939_XTP_NO_ABORT) {
@@ -1789,6 +1790,7 @@ static void j1939_xtp_rx_dpo(struct j1939_priv *priv, struct sk_buff *skb,
static void j1939_xtp_rx_dat_one(struct j1939_session *session,
struct sk_buff *skb)
{
+ enum j1939_xtp_abort abort = J1939_XTP_ABORT_FAULT;
struct j1939_priv *priv = session->priv;
struct j1939_sk_buff_cb *skcb, *se_skcb;
struct sk_buff *se_skb = NULL;
@@ -1803,9 +1805,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
skcb = j1939_skb_to_cb(skb);
dat = skb->data;
- if (skb->len <= 1)
+ if (skb->len != 8) {
/* makes no sense */
+ abort = J1939_XTP_ABORT_UNEXPECTED_DATA;
goto out_session_cancel;
+ }
switch (session->last_cmd) {
case 0xff:
@@ -1904,7 +1908,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
out_session_cancel:
kfree_skb(se_skb);
j1939_session_timers_cancel(session);
- j1939_session_cancel(session, J1939_XTP_ABORT_FAULT);
+ j1939_session_cancel(session, abort);
j1939_session_put(session);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ee9fecd3aff..eb3a366bf212 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3163,6 +3163,12 @@ static u16 skb_tx_hash(const struct net_device *dev,
qoffset = sb_dev->tc_to_txq[tc].offset;
qcount = sb_dev->tc_to_txq[tc].count;
+ if (unlikely(!qcount)) {
+ net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n",
+ sb_dev->name, qoffset, tc);
+ qoffset = 0;
+ qcount = dev->real_num_tx_queues;
+ }
}
if (skb_rx_queue_recorded(skb)) {
@@ -3906,7 +3912,8 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
skb_reset_mac_header(skb);
__skb_pull(skb, skb_network_offset(skb));
skb->pkt_type = PACKET_LOOPBACK;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ if (skb->ip_summed == CHECKSUM_NONE)
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
WARN_ON(!skb_dst(skb));
skb_dst_force(skb);
netif_rx_ni(skb);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f6197774048b..b2e49eb7001d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1973,9 +1973,9 @@ int netdev_register_kobject(struct net_device *ndev)
int netdev_change_owner(struct net_device *ndev, const struct net *net_old,
const struct net *net_new)
{
+ kuid_t old_uid = GLOBAL_ROOT_UID, new_uid = GLOBAL_ROOT_UID;
+ kgid_t old_gid = GLOBAL_ROOT_GID, new_gid = GLOBAL_ROOT_GID;
struct device *dev = &ndev->dev;
- kuid_t old_uid, new_uid;
- kgid_t old_gid, new_gid;
int error;
net_ns_get_ownership(net_old, &old_uid, &old_gid);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2170bea2c7de..fe9358437380 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -80,6 +80,7 @@
#include <linux/indirect_call_wrapper.h>
#include "datagram.h"
+#include "sock_destructor.h"
struct kmem_cache *skbuff_head_cache __ro_after_init;
static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
@@ -1804,30 +1805,39 @@ EXPORT_SYMBOL(skb_realloc_headroom);
struct sk_buff *skb_expand_head(struct sk_buff *skb, unsigned int headroom)
{
int delta = headroom - skb_headroom(skb);
+ int osize = skb_end_offset(skb);
+ struct sock *sk = skb->sk;
if (WARN_ONCE(delta <= 0,
"%s is expecting an increase in the headroom", __func__))
return skb;
- /* pskb_expand_head() might crash, if skb is shared */
- if (skb_shared(skb)) {
+ delta = SKB_DATA_ALIGN(delta);
+ /* pskb_expand_head() might crash, if skb is shared. */
+ if (skb_shared(skb) || !is_skb_wmem(skb)) {
struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
- if (likely(nskb)) {
- if (skb->sk)
- skb_set_owner_w(nskb, skb->sk);
- consume_skb(skb);
- } else {
- kfree_skb(skb);
- }
+ if (unlikely(!nskb))
+ goto fail;
+
+ if (sk)
+ skb_set_owner_w(nskb, sk);
+ consume_skb(skb);
skb = nskb;
}
- if (skb &&
- pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
- kfree_skb(skb);
- skb = NULL;
+ if (pskb_expand_head(skb, delta, 0, GFP_ATOMIC))
+ goto fail;
+
+ if (sk && is_skb_wmem(skb)) {
+ delta = skb_end_offset(skb) - osize;
+ refcount_add(delta, &sk->sk_wmem_alloc);
+ skb->truesize += delta;
}
return skb;
+
+fail:
+ kfree_skb(skb);
+ return NULL;
}
EXPORT_SYMBOL(skb_expand_head);
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..a86ef7e844f8 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -474,6 +474,20 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
}
EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
+bool sk_msg_is_readable(struct sock *sk)
+{
+ struct sk_psock *psock;
+ bool empty = true;
+
+ rcu_read_lock();
+ psock = sk_psock(sk);
+ if (likely(psock))
+ empty = list_empty(&psock->ingress_msg);
+ rcu_read_unlock();
+ return !empty;
+}
+EXPORT_SYMBOL_GPL(sk_msg_is_readable);
+
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
struct sk_buff *skb)
{
diff --git a/net/core/sock_destructor.h b/net/core/sock_destructor.h
new file mode 100644
index 000000000000..2f396e6bfba5
--- /dev/null
+++ b/net/core/sock_destructor.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _NET_CORE_SOCK_DESTRUCTOR_H
+#define _NET_CORE_SOCK_DESTRUCTOR_H
+#include <net/tcp.h>
+
+static inline bool is_skb_wmem(const struct sk_buff *skb)
+{
+ return skb->destructor == sock_wfree ||
+ skb->destructor == __sock_wfree ||
+ (IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree);
+}
+#endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c8496c1142c9..5f88526ad61c 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -419,7 +419,7 @@ static struct ctl_table net_core_table[] = {
.mode = 0600,
.proc_handler = proc_dolongvec_minmax_bpf_restricted,
.extra1 = &long_one,
- .extra2 = &long_max,
+ .extra2 = &bpf_jit_limit_max,
},
#endif
{
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index da18094b5a04..e9911b18bdbf 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1374,12 +1374,15 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
for_each_available_child_of_node(ports, port) {
err = of_property_read_u32(port, "reg", &reg);
- if (err)
+ if (err) {
+ of_node_put(port);
goto out_put_node;
+ }
if (reg >= ds->num_ports) {
dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%zu)\n",
port, reg, ds->num_ports);
+ of_node_put(port);
err = -EINVAL;
goto out_put_node;
}
@@ -1387,8 +1390,10 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
dp = dsa_to_port(ds, reg);
err = dsa_port_parse_of(dp, port);
- if (err)
+ if (err) {
+ of_node_put(port);
goto out_put_node;
+ }
}
out_put_node:
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e8b48df73c85..f5c336f8b0c8 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -486,10 +486,7 @@ static bool tcp_stream_is_readable(struct sock *sk, int target)
{
if (tcp_epollin_ready(sk, target))
return true;
-
- if (sk->sk_prot->stream_memory_read)
- return sk->sk_prot->stream_memory_read(sk);
- return false;
+ return sk_is_readable(sk);
}
/*
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index d3e9386b493e..5f4d6f45d87f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -150,19 +150,6 @@ int tcp_bpf_sendmsg_redir(struct sock *sk, struct sk_msg *msg,
EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir);
#ifdef CONFIG_BPF_SYSCALL
-static bool tcp_bpf_stream_read(const struct sock *sk)
-{
- struct sk_psock *psock;
- bool empty = true;
-
- rcu_read_lock();
- psock = sk_psock(sk);
- if (likely(psock))
- empty = list_empty(&psock->ingress_msg);
- rcu_read_unlock();
- return !empty;
-}
-
static int tcp_msg_wait_data(struct sock *sk, struct sk_psock *psock,
long timeo)
{
@@ -232,6 +219,7 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock,
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
u32 tosend, delta = 0;
+ u32 eval = __SK_NONE;
int ret;
more_data:
@@ -275,13 +263,24 @@ more_data:
case __SK_REDIRECT:
sk_redir = psock->sk_redir;
sk_msg_apply_bytes(psock, tosend);
+ if (!psock->apply_bytes) {
+ /* Clean up before releasing the sock lock. */
+ eval = psock->eval;
+ psock->eval = __SK_NONE;
+ psock->sk_redir = NULL;
+ }
if (psock->cork) {
cork = true;
psock->cork = NULL;
}
sk_msg_return(sk, msg, tosend);
release_sock(sk);
+
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+
+ if (eval == __SK_REDIRECT)
+ sock_put(sk_redir);
+
lock_sock(sk);
if (unlikely(ret < 0)) {
int free = sk_msg_free_nocharge(sk, msg);
@@ -479,7 +478,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
prot[TCP_BPF_BASE].unhash = sock_map_unhash;
prot[TCP_BPF_BASE].close = sock_map_close;
prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg;
- prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read;
+ prot[TCP_BPF_BASE].sock_is_readable = sk_msg_is_readable;
prot[TCP_BPF_TX] = prot[TCP_BPF_BASE];
prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2e62e0d6373a..5b8ce65dfc06 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1037,6 +1037,20 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
DEFINE_STATIC_KEY_FALSE(tcp_md5_needed);
EXPORT_SYMBOL(tcp_md5_needed);
+static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new)
+{
+ if (!old)
+ return true;
+
+ /* l3index always overrides non-l3index */
+ if (old->l3index && new->l3index == 0)
+ return false;
+ if (old->l3index == 0 && new->l3index)
+ return true;
+
+ return old->prefixlen < new->prefixlen;
+}
+
/* Find the Key structure for an address. */
struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
const union tcp_md5_addr *addr,
@@ -1059,7 +1073,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
lockdep_sock_is_held(sk)) {
if (key->family != family)
continue;
- if (key->l3index && key->l3index != l3index)
+ if (key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index)
continue;
if (family == AF_INET) {
mask = inet_make_mask(key->prefixlen);
@@ -1074,8 +1088,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
match = false;
}
- if (match && (!best_match ||
- key->prefixlen > best_match->prefixlen))
+ if (match && better_md5_match(best_match, key))
best_match = key;
}
return best_match;
@@ -1085,7 +1098,7 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup);
static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
const union tcp_md5_addr *addr,
int family, u8 prefixlen,
- int l3index)
+ int l3index, u8 flags)
{
const struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *key;
@@ -1105,7 +1118,9 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
lockdep_sock_is_held(sk)) {
if (key->family != family)
continue;
- if (key->l3index && key->l3index != l3index)
+ if ((key->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX))
+ continue;
+ if (key->l3index != l3index)
continue;
if (!memcmp(&key->addr, addr, size) &&
key->prefixlen == prefixlen)
@@ -1129,7 +1144,7 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup);
/* This can be called on a newly created socket, from other files */
int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
- int family, u8 prefixlen, int l3index,
+ int family, u8 prefixlen, int l3index, u8 flags,
const u8 *newkey, u8 newkeylen, gfp_t gfp)
{
/* Add Key to the list */
@@ -1137,7 +1152,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_info *md5sig;
- key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
+ key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags);
if (key) {
/* Pre-existing entry - just update that one.
* Note that the key might be used concurrently.
@@ -1182,6 +1197,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
key->family = family;
key->prefixlen = prefixlen;
key->l3index = l3index;
+ key->flags = flags;
memcpy(&key->addr, addr,
(family == AF_INET6) ? sizeof(struct in6_addr) :
sizeof(struct in_addr));
@@ -1191,11 +1207,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
EXPORT_SYMBOL(tcp_md5_do_add);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
- u8 prefixlen, int l3index)
+ u8 prefixlen, int l3index, u8 flags)
{
struct tcp_md5sig_key *key;
- key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
+ key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags);
if (!key)
return -ENOENT;
hlist_del_rcu(&key->node);
@@ -1229,6 +1245,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
const union tcp_md5_addr *addr;
u8 prefixlen = 32;
int l3index = 0;
+ u8 flags;
if (optlen < sizeof(cmd))
return -EINVAL;
@@ -1239,6 +1256,8 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
if (sin->sin_family != AF_INET)
return -EINVAL;
+ flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
+
if (optname == TCP_MD5SIG_EXT &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
prefixlen = cmd.tcpm_prefixlen;
@@ -1246,7 +1265,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
return -EINVAL;
}
- if (optname == TCP_MD5SIG_EXT &&
+ if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
struct net_device *dev;
@@ -1267,12 +1286,12 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr;
if (!cmd.tcpm_keylen)
- return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index);
+ return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index, flags);
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
return -EINVAL;
- return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index,
+ return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags,
cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
@@ -1596,7 +1615,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
* memory, then we end up not copying the key
* across. Shucks.
*/
- tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index,
+ tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags,
key->key, key->keylen, GFP_ATOMIC);
sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 8536b2a7210b..2fffcf2b54f3 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2867,6 +2867,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
!(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1)
mask &= ~(EPOLLIN | EPOLLRDNORM);
+ /* psock ingress_msg queue should not contain any bad checksum frames */
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
return mask;
}
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 7a1d5f473878..bbe6569c9ad3 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -114,6 +114,7 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = udp_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 12f985f43bcc..2f044a49afa8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -464,13 +464,14 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
int ip6_forward(struct sk_buff *skb)
{
- struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
+ struct inet6_dev *idev;
u32 mtu;
+ idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index 733c83d38b30..4ad8b2032f1f 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -25,12 +25,7 @@ MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
static inline bool
segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
{
- bool r;
- pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n",
- invert ? '!' : ' ', min, id, max);
- r = (id >= min && id <= max) ^ invert;
- pr_debug(" result %s\n", r ? "PASS" : "FAILED");
- return r;
+ return (id >= min && id <= max) ^ invert;
}
static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
@@ -65,30 +60,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
return false;
}
- pr_debug("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen);
- pr_debug("TYPE %04X ", rh->type);
- pr_debug("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left);
-
- pr_debug("IPv6 RT segsleft %02X ",
- segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
- rh->segments_left,
- !!(rtinfo->invflags & IP6T_RT_INV_SGS)));
- pr_debug("type %02X %02X %02X ",
- rtinfo->rt_type, rh->type,
- (!(rtinfo->flags & IP6T_RT_TYP) ||
- ((rtinfo->rt_type == rh->type) ^
- !!(rtinfo->invflags & IP6T_RT_INV_TYP))));
- pr_debug("len %02X %04X %02X ",
- rtinfo->hdrlen, hdrlen,
- !(rtinfo->flags & IP6T_RT_LEN) ||
- ((rtinfo->hdrlen == hdrlen) ^
- !!(rtinfo->invflags & IP6T_RT_INV_LEN)));
- pr_debug("res %02X %02X %02X ",
- rtinfo->flags & IP6T_RT_RES,
- ((const struct rt0_hdr *)rh)->reserved,
- !((rtinfo->flags & IP6T_RT_RES) &&
- (((const struct rt0_hdr *)rh)->reserved)));
-
ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
rh->segments_left,
!!(rtinfo->invflags & IP6T_RT_INV_SGS))) &&
@@ -107,22 +78,22 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
reserved),
sizeof(_reserved),
&_reserved);
+ if (!rp) {
+ par->hotdrop = true;
+ return false;
+ }
ret = (*rp == 0);
}
- pr_debug("#%d ", rtinfo->addrnr);
if (!(rtinfo->flags & IP6T_RT_FST)) {
return ret;
} else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) {
- pr_debug("Not strict ");
if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
- pr_debug("There isn't enough space\n");
return false;
} else {
unsigned int i = 0;
- pr_debug("#%d ", rtinfo->addrnr);
for (temp = 0;
temp < (unsigned int)((hdrlen - 8) / 16);
temp++) {
@@ -138,26 +109,20 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
return false;
}
- if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) {
- pr_debug("i=%d temp=%d;\n", i, temp);
+ if (ipv6_addr_equal(ap, &rtinfo->addrs[i]))
i++;
- }
if (i == rtinfo->addrnr)
break;
}
- pr_debug("i=%d #%d\n", i, rtinfo->addrnr);
if (i == rtinfo->addrnr)
return ret;
else
return false;
}
} else {
- pr_debug("Strict ");
if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
- pr_debug("There isn't enough space\n");
return false;
} else {
- pr_debug("#%d ", rtinfo->addrnr);
for (temp = 0; temp < rtinfo->addrnr; temp++) {
ap = skb_header_pointer(skb,
ptr
@@ -173,7 +138,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp]))
break;
}
- pr_debug("temp=%d #%d\n", temp, rtinfo->addrnr);
if (temp == rtinfo->addrnr &&
temp == (unsigned int)((hdrlen - 8) / 16))
return ret;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0ce52d46e4f8..b03dd02c9f13 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -599,6 +599,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
int l3index = 0;
u8 prefixlen;
+ u8 flags;
if (optlen < sizeof(cmd))
return -EINVAL;
@@ -609,6 +610,8 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
if (sin6->sin6_family != AF_INET6)
return -EINVAL;
+ flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
+
if (optname == TCP_MD5SIG_EXT &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
prefixlen = cmd.tcpm_prefixlen;
@@ -619,7 +622,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
}
- if (optname == TCP_MD5SIG_EXT &&
+ if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
struct net_device *dev;
@@ -640,9 +643,9 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
AF_INET, prefixlen,
- l3index);
+ l3index, flags);
return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
- AF_INET6, prefixlen, l3index);
+ AF_INET6, prefixlen, l3index, flags);
}
if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
@@ -650,12 +653,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
if (ipv6_addr_v4mapped(&sin6->sin6_addr))
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
- AF_INET, prefixlen, l3index,
+ AF_INET, prefixlen, l3index, flags,
cmd.tcpm_key, cmd.tcpm_keylen,
GFP_KERNEL);
return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
- AF_INET6, prefixlen, l3index,
+ AF_INET6, prefixlen, l3index, flags,
cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
}
@@ -1404,7 +1407,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
* across. Shucks.
*/
tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
- AF_INET6, 128, l3index, key->key, key->keylen,
+ AF_INET6, 128, l3index, key->flags, key->key, key->keylen,
sk_gfp_mask(sk, GFP_ATOMIC));
}
#endif
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 97095b7c9c64..5dcfd53a4ab6 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -672,7 +672,7 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
u8 *ie, u8 ie_len)
{
struct ieee80211_supported_band *sband;
- const u8 *cap;
+ const struct element *cap;
const struct ieee80211_he_operation *he_oper = NULL;
sband = ieee80211_get_sband(sdata);
@@ -687,9 +687,10 @@ ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
sdata->vif.bss_conf.he_support = true;
- cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
- if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
- he_oper = (void *)(cap + 3);
+ cap = cfg80211_find_ext_elem(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+ if (cap && cap->datalen >= 1 + sizeof(*he_oper) &&
+ cap->datalen >= 1 + ieee80211_he_oper_size(cap->data + 1))
+ he_oper = (void *)(cap->data + 1);
if (he_oper)
sdata->vif.bss_conf.he_oper.params =
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index c41273cefc51..f0f22eb4fd5f 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -485,11 +485,11 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
mpext = mptcp_get_ext(skb);
data_len = mpext ? mpext->data_len : 0;
- /* we will check ext_copy.data_len in mptcp_write_options() to
+ /* we will check ops->data_len in mptcp_write_options() to
* discriminate between TCPOLEN_MPTCP_MPC_ACK_DATA and
* TCPOLEN_MPTCP_MPC_ACK
*/
- opts->ext_copy.data_len = data_len;
+ opts->data_len = data_len;
opts->suboptions = OPTION_MPTCP_MPC_ACK;
opts->sndr_key = subflow->local_key;
opts->rcvr_key = subflow->remote_key;
@@ -505,9 +505,9 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd) {
/* we need to propagate more info to csum the pseudo hdr */
- opts->ext_copy.data_seq = mpext->data_seq;
- opts->ext_copy.subflow_seq = mpext->subflow_seq;
- opts->ext_copy.csum = mpext->csum;
+ opts->data_seq = mpext->data_seq;
+ opts->subflow_seq = mpext->subflow_seq;
+ opts->csum = mpext->csum;
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
}
*size = ALIGN(len, 4);
@@ -1227,7 +1227,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
}
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __sum16 sum)
{
struct csum_pseudo_header header;
__wsum csum;
@@ -1237,15 +1237,21 @@ static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
* always the 64-bit value, irrespective of what length is used in the
* DSS option itself.
*/
- header.data_seq = cpu_to_be64(mpext->data_seq);
- header.subflow_seq = htonl(mpext->subflow_seq);
- header.data_len = htons(mpext->data_len);
+ header.data_seq = cpu_to_be64(data_seq);
+ header.subflow_seq = htonl(subflow_seq);
+ header.data_len = htons(data_len);
header.csum = 0;
- csum = csum_partial(&header, sizeof(header), ~csum_unfold(mpext->csum));
+ csum = csum_partial(&header, sizeof(header), ~csum_unfold(sum));
return (__force u16)csum_fold(csum);
}
+static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+{
+ return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
+ mpext->csum);
+}
+
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts)
{
@@ -1337,7 +1343,7 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
len = TCPOLEN_MPTCP_MPC_SYN;
} else if (OPTION_MPTCP_MPC_SYNACK & opts->suboptions) {
len = TCPOLEN_MPTCP_MPC_SYNACK;
- } else if (opts->ext_copy.data_len) {
+ } else if (opts->data_len) {
len = TCPOLEN_MPTCP_MPC_ACK_DATA;
if (opts->csum_reqd)
len += TCPOLEN_MPTCP_DSS_CHECKSUM;
@@ -1366,14 +1372,17 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
put_unaligned_be64(opts->rcvr_key, ptr);
ptr += 2;
- if (!opts->ext_copy.data_len)
+ if (!opts->data_len)
goto mp_capable_done;
if (opts->csum_reqd) {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
- mptcp_make_csum(&opts->ext_copy), ptr);
+ put_unaligned_be32(opts->data_len << 16 |
+ __mptcp_make_csum(opts->data_seq,
+ opts->subflow_seq,
+ opts->data_len,
+ opts->csum), ptr);
} else {
- put_unaligned_be32(opts->ext_copy.data_len << 16 |
+ put_unaligned_be32(opts->data_len << 16 |
TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
}
ptr += 1;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 54395266339d..92a747896f80 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -109,7 +109,7 @@ config NF_CONNTRACK_MARK
config NF_CONNTRACK_SECMARK
bool 'Connection tracking security mark support'
depends on NETWORK_SECMARK
- default m if NETFILTER_ADVANCED=n
+ default y if NETFILTER_ADVANCED=n
help
This option enables security markings to be applied to
connections. Typically they are copied to connections from
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c25097092a06..29ec3ef63edc 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -4090,6 +4090,11 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
+#ifdef CONFIG_IP_VS_DEBUG
+ /* Global sysctls must be ro in non-init netns */
+ if (!net_eq(net, &init_net))
+ tbl[idx++].mode = 0444;
+#endif
ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
if (ipvs->sysctl_hdr == NULL) {
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 5b02408a920b..3ced0eb6b7c3 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -342,12 +342,6 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
return;
}
- /* UNREGISTER events are also happening on netns exit.
- *
- * Although nf_tables core releases all tables/chains, only this event
- * handler provides guarantee that hook->ops.dev is still accessible,
- * so we cannot skip exiting net namespaces.
- */
__nft_release_basechain(ctx);
}
@@ -366,6 +360,9 @@ static int nf_tables_netdev_event(struct notifier_block *this,
event != NETDEV_CHANGENAME)
return NOTIFY_DONE;
+ if (!check_net(ctx.net))
+ return NOTIFY_DONE;
+
nft_net = nft_pernet(ctx.net);
mutex_lock(&nft_net->commit_mutex);
list_for_each_entry(table, &nft_net->tables, list) {
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 7b2f359bfce4..2f7cf5ecebf4 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -137,7 +137,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
{
int ret;
- info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL);
+ info->timer = kzalloc(sizeof(*info->timer), GFP_KERNEL);
if (!info->timer) {
ret = -ENOMEM;
goto out;
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index ad9df0cb4b98..90866ae45573 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -960,6 +960,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
tmpl = p->tmpl;
tcf_lastuse_update(&c->tcf_tm);
+ tcf_action_update_bstats(&c->common, skb);
if (clear) {
qdisc_skb_cb(skb)->post_ct = false;
@@ -1049,7 +1050,6 @@ out_push:
qdisc_skb_cb(skb)->post_ct = true;
out_clear:
- tcf_action_update_bstats(&c->common, skb);
if (defrag)
qdisc_skb_cb(skb)->pkt_len = skb->len;
return retval;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 32df65f68c12..fb3da4d8f4a3 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -156,6 +156,12 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort(
void *arg,
struct sctp_cmd_seq *commands);
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands);
+
/* Small helper function that checks if the chunk length
* is of the appropriate length. The 'required_length' argument
* is set to be the size of a specific chunk we are testing.
@@ -337,6 +343,14 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length.
+ * Normally, this would cause an ABORT with a Protocol Violation
+ * error, but since we don't have an association, we'll
+ * just discard the packet.
+ */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -351,14 +365,6 @@ enum sctp_disposition sctp_sf_do_5_1B_init(struct net *net,
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * Normally, this would cause an ABORT with a Protocol Violation
- * error, but since we don't have an association, we'll
- * just discard the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* If the INIT is coming toward a closing socket, we'll send back
* and ABORT. Essentially, this catches the race of INIT being
* backloged to the socket at the same time as the user issues close().
@@ -704,6 +710,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
struct sock *sk;
int error = 0;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* If the packet is an OOTB packet which is temporarily on the
* control endpoint, respond with an ABORT.
*/
@@ -718,7 +727,8 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net,
* in sctp_unpack_cookie().
*/
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
/* If the endpoint is not listening or if the number of associations
* on the TCP-style socket exceed the max backlog, respond with an
@@ -1524,20 +1534,16 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
if (!chunk->singleton)
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+ /* Make sure that the INIT chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* 3.1 A packet containing an INIT chunk MUST have a zero Verification
* Tag.
*/
if (chunk->sctp_hdr->vtag != 0)
return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
- /* Make sure that the INIT chunk has a valid length.
- * In this case, we generate a protocol violation since we have
- * an association established.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
-
if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
@@ -1882,9 +1888,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_a(
* its peer.
*/
if (sctp_state(asoc, SHUTDOWN_ACK_SENT)) {
- disposition = sctp_sf_do_9_2_reshutack(net, ep, asoc,
- SCTP_ST_CHUNK(chunk->chunk_hdr->type),
- chunk, commands);
+ disposition = __sctp_sf_do_9_2_reshutack(net, ep, asoc,
+ SCTP_ST_CHUNK(chunk->chunk_hdr->type),
+ chunk, commands);
if (SCTP_DISPOSITION_NOMEM == disposition)
goto nomem;
@@ -2202,9 +2208,11 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
* enough for the chunk header. Cookie length verification is
* done later.
*/
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr))) {
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands);
+ }
/* "Decode" the chunk. We have no optional parameters so we
* are in good shape.
@@ -2341,7 +2349,7 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2387,7 +2395,7 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2657,7 +2665,7 @@ enum sctp_disposition sctp_sf_do_9_1_abort(
*/
if (SCTP_ADDR_DEL ==
sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
if (!sctp_err_chunk_valid(chunk))
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
@@ -2970,13 +2978,11 @@ enum sctp_disposition sctp_sf_do_9_2_shut_ctsn(
* that belong to this association, it should discard the INIT chunk and
* retransmit the SHUTDOWN ACK chunk.
*/
-enum sctp_disposition sctp_sf_do_9_2_reshutack(
- struct net *net,
- const struct sctp_endpoint *ep,
- const struct sctp_association *asoc,
- const union sctp_subtype type,
- void *arg,
- struct sctp_cmd_seq *commands)
+static enum sctp_disposition
+__sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
{
struct sctp_chunk *chunk = arg;
struct sctp_chunk *reply;
@@ -3010,6 +3016,26 @@ nomem:
return SCTP_DISPOSITION_NOMEM;
}
+enum sctp_disposition
+sctp_sf_do_9_2_reshutack(struct net *net, const struct sctp_endpoint *ep,
+ const struct sctp_association *asoc,
+ const union sctp_subtype type, void *arg,
+ struct sctp_cmd_seq *commands)
+{
+ struct sctp_chunk *chunk = arg;
+
+ if (!chunk->singleton)
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
+ if (chunk->sctp_hdr->vtag != 0)
+ return sctp_sf_tabort_8_4_8(net, ep, asoc, type, arg, commands);
+
+ return __sctp_sf_do_9_2_reshutack(net, ep, asoc, type, arg, commands);
+}
+
/*
* sctp_sf_do_ecn_cwr
*
@@ -3662,6 +3688,9 @@ enum sctp_disposition sctp_sf_ootb(struct net *net,
SCTP_INC_STATS(net, SCTP_MIB_OUTOFBLUES);
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
ch = (struct sctp_chunkhdr *)chunk->chunk_hdr;
do {
/* Report violation if the chunk is less then minimal */
@@ -3777,12 +3806,6 @@ static enum sctp_disposition sctp_sf_shut_8_4_5(
SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
- /* If the chunk length is invalid, we don't want to process
- * the reset of the packet.
- */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
-
/* We need to discard the rest of the packet to prevent
* potential boomming attacks from additional bundled chunks.
* This is documented in SCTP Threats ID.
@@ -3810,6 +3833,9 @@ enum sctp_disposition sctp_sf_do_8_5_1_E_sa(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ asoc = NULL;
+
/* Make sure that the SHUTDOWN_ACK chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -3845,6 +3871,11 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ASCONF ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP: Section 4.1.1
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3853,13 +3884,7 @@ enum sctp_disposition sctp_sf_do_asconf(struct net *net,
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !chunk->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ASCONF ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
hdr = (struct sctp_addiphdr *)chunk->skb->data;
serial = ntohl(hdr->serial);
@@ -3988,6 +4013,12 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
}
+ /* Make sure that the ADDIP chunk has a valid length. */
+ if (!sctp_chunk_length_valid(asconf_ack,
+ sizeof(struct sctp_addip_chunk)))
+ return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
+ commands);
+
/* ADD-IP, Section 4.1.2:
* This chunk MUST be sent in an authenticated way by using
* the mechanism defined in [I-D.ietf-tsvwg-sctp-auth]. If this chunk
@@ -3996,14 +4027,7 @@ enum sctp_disposition sctp_sf_do_asconf_ack(struct net *net,
*/
if (!asoc->peer.asconf_capable ||
(!net->sctp.addip_noauth && !asconf_ack->auth))
- return sctp_sf_discard_chunk(net, ep, asoc, type, arg,
- commands);
-
- /* Make sure that the ADDIP chunk has a valid length. */
- if (!sctp_chunk_length_valid(asconf_ack,
- sizeof(struct sctp_addip_chunk)))
- return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
- commands);
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
addip_hdr = (struct sctp_addiphdr *)asconf_ack->skb->data;
rcvd_serial = ntohl(addip_hdr->serial);
@@ -4575,6 +4599,9 @@ enum sctp_disposition sctp_sf_discard_chunk(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (asoc && !sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length.
* Since we don't know the chunk type, we use a general
* chunkhdr structure to make a comparison.
@@ -4642,6 +4669,9 @@ enum sctp_disposition sctp_sf_violation(struct net *net,
{
struct sctp_chunk *chunk = arg;
+ if (!sctp_vtag_verify(chunk, asoc))
+ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+
/* Make sure that the chunk has a valid length. */
if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_chunkhdr)))
return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
@@ -6348,6 +6378,7 @@ static struct sctp_packet *sctp_ootb_pkt_new(
* yet.
*/
switch (chunk->chunk_hdr->type) {
+ case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
{
struct sctp_initack_chunk *initack;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c038efc23ce3..78b663dbfa1f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1057,7 +1057,7 @@ static void smc_connect_work(struct work_struct *work)
if (smc->clcsock->sk->sk_err) {
smc->sk.sk_err = smc->clcsock->sk->sk_err;
} else if ((1 << smc->clcsock->sk->sk_state) &
- (TCPF_SYN_SENT | TCP_SYN_RECV)) {
+ (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
rc = sk_stream_wait_connect(smc->clcsock->sk, &timeo);
if ((rc == -EPIPE) &&
((1 << smc->clcsock->sk->sk_state) &
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 72f4b72eb175..f1d323439a2a 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1822,7 +1822,7 @@ void smc_llc_link_active(struct smc_link *link)
link->smcibdev->ibdev->name, link->ibport);
link->state = SMC_LNK_ACTIVE;
if (link->lgr->llc_testlink_time) {
- link->llc_testlink_time = link->lgr->llc_testlink_time * HZ;
+ link->llc_testlink_time = link->lgr->llc_testlink_time;
schedule_delayed_work(&link->llc_testlink_wrk,
link->llc_testlink_time);
}
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index c9391d38de85..dc60c32bb70d 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -2285,43 +2285,53 @@ static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr)
u16 key_gen = msg_key_gen(hdr);
u16 size = msg_data_sz(hdr);
u8 *data = msg_data(hdr);
+ unsigned int keylen;
+
+ /* Verify whether the size can exist in the packet */
+ if (unlikely(size < sizeof(struct tipc_aead_key) + TIPC_AEAD_KEYLEN_MIN)) {
+ pr_debug("%s: message data size is too small\n", rx->name);
+ goto exit;
+ }
+
+ keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+
+ /* Verify the supplied size values */
+ if (unlikely(size != keylen + sizeof(struct tipc_aead_key) ||
+ keylen > TIPC_AEAD_KEY_SIZE_MAX)) {
+ pr_debug("%s: invalid MSG_CRYPTO key size\n", rx->name);
+ goto exit;
+ }
spin_lock(&rx->lock);
if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) {
pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name,
rx->skey, key_gen, rx->key_gen);
- goto exit;
+ goto exit_unlock;
}
/* Allocate memory for the key */
skey = kmalloc(size, GFP_ATOMIC);
if (unlikely(!skey)) {
pr_err("%s: unable to allocate memory for skey\n", rx->name);
- goto exit;
+ goto exit_unlock;
}
/* Copy key from msg data */
- skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+ skey->keylen = keylen;
memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME);
memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32),
skey->keylen);
- /* Sanity check */
- if (unlikely(size != tipc_aead_key_size(skey))) {
- kfree(skey);
- skey = NULL;
- goto exit;
- }
-
rx->key_gen = key_gen;
rx->skey_mode = msg_key_mode(hdr);
rx->skey = skey;
rx->nokey = 0;
mb(); /* for nokey flag */
-exit:
+exit_unlock:
spin_unlock(&rx->lock);
+exit:
/* Schedule the key attaching on this crypto */
if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0)))
return true;
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index fde56ff49163..9ab81db8a654 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -681,12 +681,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE];
prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_BASE][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_BASE][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close;
prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE];
prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg;
- prot[TLS_SW][TLS_SW].stream_memory_read = tls_sw_stream_read;
+ prot[TLS_SW][TLS_SW].sock_is_readable = tls_sw_sock_is_readable;
prot[TLS_SW][TLS_SW].close = tls_sk_proto_close;
#ifdef CONFIG_TLS_DEVICE
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 4feb95e34b64..1b08b877a890 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -35,6 +35,7 @@
* SOFTWARE.
*/
+#include <linux/bug.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
#include <linux/splice.h>
@@ -43,6 +44,14 @@
#include <net/strparser.h>
#include <net/tls.h>
+noinline void tls_err_abort(struct sock *sk, int err)
+{
+ WARN_ON_ONCE(err >= 0);
+ /* sk->sk_err should contain a positive error code. */
+ sk->sk_err = -err;
+ sk_error_report(sk);
+}
+
static int __skb_nsg(struct sk_buff *skb, int offset, int len,
unsigned int recursion_level)
{
@@ -419,7 +428,7 @@ int tls_tx_records(struct sock *sk, int flags)
tx_err:
if (rc < 0 && rc != -EAGAIN)
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
return rc;
}
@@ -450,7 +459,7 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err)
/* If err is already set on socket, return the same code */
if (sk->sk_err) {
- ctx->async_wait.err = sk->sk_err;
+ ctx->async_wait.err = -sk->sk_err;
} else {
ctx->async_wait.err = err;
tls_err_abort(sk, err);
@@ -763,7 +772,7 @@ static int tls_push_record(struct sock *sk, int flags,
msg_pl->sg.size + prot->tail_size, i);
if (rc < 0) {
if (rc != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
if (split) {
tls_ctx->pending_open_record_frags = true;
tls_merge_open_record(sk, rec, tmp, orig_end);
@@ -1827,7 +1836,7 @@ int tls_sw_recvmsg(struct sock *sk,
err = decrypt_skb_update(sk, skb, &msg->msg_iter,
&chunk, &zc, async_capable);
if (err < 0 && err != -EINPROGRESS) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto recv_end;
}
@@ -2007,7 +2016,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos,
}
if (err < 0) {
- tls_err_abort(sk, EBADMSG);
+ tls_err_abort(sk, -EBADMSG);
goto splice_read_end;
}
ctx->decrypted = 1;
@@ -2026,7 +2035,7 @@ splice_read_end:
return copied ? : err;
}
-bool tls_sw_stream_read(const struct sock *sk)
+bool tls_sw_sock_is_readable(struct sock *sk)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 89f9e85ae970..78e08e82c08c 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -3052,6 +3052,8 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if ((sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) &&
@@ -3091,6 +3093,8 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
/* readable? */
if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
mask |= EPOLLIN | EPOLLRDNORM;
+ if (sk_is_readable(sk))
+ mask |= EPOLLIN | EPOLLRDNORM;
/* Connection-based need to check for termination and startup */
if (sk->sk_type == SOCK_SEQPACKET) {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index b927e2baae50..452376c6f419 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -102,6 +102,7 @@ static void unix_dgram_bpf_rebuild_protos(struct proto *prot, const struct proto
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
}
static void unix_stream_bpf_rebuild_protos(struct proto *prot,
@@ -110,6 +111,7 @@ static void unix_stream_bpf_rebuild_protos(struct proto *prot,
*prot = *base;
prot->close = sock_map_close;
prot->recvmsg = unix_bpf_recvmsg;
+ prot->sock_is_readable = sk_msg_is_readable;
prot->unhash = sock_map_unhash;
}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 03323121ca50..aaba847d79eb 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -524,6 +524,7 @@ use_default_name:
INIT_WORK(&rdev->propagate_cac_done_wk, cfg80211_propagate_cac_done_wk);
INIT_WORK(&rdev->mgmt_registrations_update_wk,
cfg80211_mgmt_registrations_update_wk);
+ spin_lock_init(&rdev->mgmt_registrations_lock);
#ifdef CONFIG_CFG80211_DEFAULT_PS
rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -1279,7 +1280,6 @@ void cfg80211_init_wdev(struct wireless_dev *wdev)
INIT_LIST_HEAD(&wdev->event_list);
spin_lock_init(&wdev->event_lock);
INIT_LIST_HEAD(&wdev->mgmt_registrations);
- spin_lock_init(&wdev->mgmt_registrations_lock);
INIT_LIST_HEAD(&wdev->pmsr_list);
spin_lock_init(&wdev->pmsr_lock);
INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b35d0db12f1d..1720abf36f92 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -100,6 +100,8 @@ struct cfg80211_registered_device {
struct work_struct propagate_cac_done_wk;
struct work_struct mgmt_registrations_update_wk;
+ /* lock for all wdev lists */
+ spinlock_t mgmt_registrations_lock;
/* must be last because of the way we do wiphy_priv(),
* and it should at least be aligned to NETDEV_ALIGN */
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 3aa69b375a10..783acd2c4211 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -452,9 +452,9 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
lockdep_assert_held(&rdev->wiphy.mtx);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
if (!wdev->mgmt_registrations_need_update) {
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return;
}
@@ -479,7 +479,7 @@ static void cfg80211_mgmt_registrations_update(struct wireless_dev *wdev)
rcu_read_unlock();
wdev->mgmt_registrations_need_update = 0;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
rdev_update_mgmt_frame_registrations(rdev, wdev, &upd);
}
@@ -503,6 +503,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
int match_len, bool multicast_rx,
struct netlink_ext_ack *extack)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *nreg;
int err = 0;
u16 mgmt_type;
@@ -548,7 +549,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
if (!nreg)
return -ENOMEM;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
int mlen = min(match_len, reg->match_len);
@@ -583,7 +584,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
list_add(&nreg->list, &wdev->mgmt_registrations);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
@@ -591,7 +592,7 @@ int cfg80211_mlme_register_mgmt(struct wireless_dev *wdev, u32 snd_portid,
out:
kfree(nreg);
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
return err;
}
@@ -602,7 +603,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
if (reg->nlportid != nlportid)
@@ -615,7 +616,7 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
schedule_work(&rdev->mgmt_registrations_update_wk);
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
if (nlportid && rdev->crit_proto_nlportid == nlportid) {
rdev->crit_proto_nlportid = 0;
@@ -628,15 +629,16 @@ void cfg80211_mlme_unregister_socket(struct wireless_dev *wdev, u32 nlportid)
void cfg80211_mlme_purge_registrations(struct wireless_dev *wdev)
{
+ struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
struct cfg80211_mgmt_registration *reg, *tmp;
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry_safe(reg, tmp, &wdev->mgmt_registrations, list) {
list_del(&reg->list);
kfree(reg);
}
wdev->mgmt_registrations_need_update = 1;
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
cfg80211_mgmt_registrations_update(wdev);
}
@@ -784,7 +786,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm,
data = buf + ieee80211_hdrlen(mgmt->frame_control);
data_len = len - ieee80211_hdrlen(mgmt->frame_control);
- spin_lock_bh(&wdev->mgmt_registrations_lock);
+ spin_lock_bh(&rdev->mgmt_registrations_lock);
list_for_each_entry(reg, &wdev->mgmt_registrations, list) {
if (reg->frame_type != ftype)
@@ -808,7 +810,7 @@ bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm,
break;
}
- spin_unlock_bh(&wdev->mgmt_registrations_lock);
+ spin_unlock_bh(&rdev->mgmt_registrations_lock);
trace_cfg80211_return_bool(result);
return result;
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 11c68b159324..adc0d14cfd86 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -418,14 +418,17 @@ cfg80211_add_nontrans_list(struct cfg80211_bss *trans_bss,
}
ssid_len = ssid[1];
ssid = ssid + 2;
- rcu_read_unlock();
/* check if nontrans_bss is in the list */
list_for_each_entry(bss, &trans_bss->nontrans_list, nontrans_list) {
- if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len))
+ if (is_bss(bss, nontrans_bss->bssid, ssid, ssid_len)) {
+ rcu_read_unlock();
return 0;
+ }
}
+ rcu_read_unlock();
+
/* add to the list */
list_add_tail(&nontrans_bss->nontrans_list, &trans_bss->nontrans_list);
return 0;
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 18dba3d7c638..a1a99a574984 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1028,14 +1028,14 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
!(rdev->wiphy.interface_modes & (1 << ntype)))
return -EOPNOTSUPP;
- /* if it's part of a bridge, reject changing type to station/ibss */
- if (netif_is_bridge_port(dev) &&
- (ntype == NL80211_IFTYPE_ADHOC ||
- ntype == NL80211_IFTYPE_STATION ||
- ntype == NL80211_IFTYPE_P2P_CLIENT))
- return -EBUSY;
-
if (ntype != otype) {
+ /* if it's part of a bridge, reject changing type to station/ibss */
+ if (netif_is_bridge_port(dev) &&
+ (ntype == NL80211_IFTYPE_ADHOC ||
+ ntype == NL80211_IFTYPE_STATION ||
+ ntype == NL80211_IFTYPE_P2P_CLIENT))
+ return -EBUSY;
+
dev->ieee80211_ptr->use_4addr = false;
dev->ieee80211_ptr->mesh_id_up_len = 0;
wdev_lock(dev->ieee80211_ptr);
diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c
index e3d79a7b6db6..b5d5333ab330 100644
--- a/security/keys/process_keys.c
+++ b/security/keys/process_keys.c
@@ -918,6 +918,13 @@ void key_change_session_keyring(struct callback_head *twork)
return;
}
+ /* If get_ucounts fails more bits are needed in the refcount */
+ if (unlikely(!get_ucounts(old->ucounts))) {
+ WARN_ONCE(1, "In %s get_ucounts failed\n", __func__);
+ put_cred(new);
+ return;
+ }
+
new-> uid = old-> uid;
new-> euid = old-> euid;
new-> suid = old-> suid;
@@ -927,6 +934,7 @@ void key_change_session_keyring(struct callback_head *twork)
new-> sgid = old-> sgid;
new->fsgid = old->fsgid;
new->user = get_uid(old->user);
+ new->ucounts = old->ucounts;
new->user_ns = get_user_ns(old->user_ns);
new->group_info = get_group_info(old->group_info);
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 22d27b12c4e7..965b096f416f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2535,6 +2535,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
SND_PCI_QUIRK(0x1558, 0x65d2, "Clevo PB51R[CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x65e1, "Clevo PB51[ED][DF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x65e5, "Clevo PC50D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
+ SND_PCI_QUIRK(0x1558, 0x65f1, "Clevo PC50HS", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x67d1, "Clevo PB71[ER][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x67e1, "Clevo PB71[DE][CDF]", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
SND_PCI_QUIRK(0x1558, 0x67e5, "Clevo PC70D[PRS](?:-D|-G)?", ALC1220_FIXUP_CLEVO_PB51ED_PINS),
@@ -6405,6 +6406,44 @@ static void alc_fixup_no_int_mic(struct hda_codec *codec,
}
}
+/* GPIO1 = amplifier on/off
+ * GPIO3 = mic mute LED
+ */
+static void alc285_fixup_hp_spectre_x360_eb1(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ static const hda_nid_t conn[] = { 0x02 };
+
+ struct alc_spec *spec = codec->spec;
+ static const struct hda_pintbl pincfgs[] = {
+ { 0x14, 0x90170110 }, /* front/high speakers */
+ { 0x17, 0x90170130 }, /* back/bass speakers */
+ { }
+ };
+
+ //enable micmute led
+ alc_fixup_hp_gpio_led(codec, action, 0x00, 0x04);
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ spec->micmute_led_polarity = 1;
+ /* needed for amp of back speakers */
+ spec->gpio_mask |= 0x01;
+ spec->gpio_dir |= 0x01;
+ snd_hda_apply_pincfgs(codec, pincfgs);
+ /* share DAC to have unified volume control */
+ snd_hda_override_conn_list(codec, 0x14, ARRAY_SIZE(conn), conn);
+ snd_hda_override_conn_list(codec, 0x17, ARRAY_SIZE(conn), conn);
+ break;
+ case HDA_FIXUP_ACT_INIT:
+ /* need to toggle GPIO to enable the amp of back speakers */
+ alc_update_gpio_data(codec, 0x01, true);
+ msleep(100);
+ alc_update_gpio_data(codec, 0x01, false);
+ break;
+ }
+}
+
static void alc285_fixup_hp_spectre_x360(struct hda_codec *codec,
const struct hda_fixup *fix, int action)
{
@@ -6557,6 +6596,7 @@ enum {
ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED,
ALC280_FIXUP_HP_9480M,
ALC245_FIXUP_HP_X360_AMP,
+ ALC285_FIXUP_HP_SPECTRE_X360_EB1,
ALC288_FIXUP_DELL_HEADSET_MODE,
ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
ALC288_FIXUP_DELL_XPS_13,
@@ -8250,6 +8290,10 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_hp_spectre_x360,
},
+ [ALC285_FIXUP_HP_SPECTRE_X360_EB1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_hp_spectre_x360_eb1
+ },
[ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc285_fixup_ideapad_s740_coef,
@@ -8584,6 +8628,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8811, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
+ SND_PCI_QUIRK(0x103c, 0x8812, "HP Spectre x360 15-eb1xxx", ALC285_FIXUP_HP_SPECTRE_X360_EB1),
SND_PCI_QUIRK(0x103c, 0x8846, "HP EliteBook 850 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8847, "HP EliteBook x360 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x884b, "HP EliteBook 840 Aero G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
@@ -9005,6 +9051,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
{.id = ALC245_FIXUP_HP_X360_AMP, .name = "alc245-hp-x360-amp"},
{.id = ALC295_FIXUP_HP_OMEN, .name = "alc295-hp-omen"},
{.id = ALC285_FIXUP_HP_SPECTRE_X360, .name = "alc285-hp-spectre-x360"},
+ {.id = ALC285_FIXUP_HP_SPECTRE_X360_EB1, .name = "alc285-hp-spectre-x360-eb1"},
{.id = ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP, .name = "alc287-ideapad-bass-spk-amp"},
{.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"},
{.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"},
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 82ee233a269d..216cea04ad70 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1583,6 +1583,7 @@ config SND_SOC_WCD938X_SDW
tristate "WCD9380/WCD9385 Codec - SDW"
select SND_SOC_WCD938X
select SND_SOC_WCD_MBHC
+ select REGMAP_IRQ
depends on SOUNDWIRE
select REGMAP_SOUNDWIRE
help
diff --git a/sound/soc/codecs/cs42l42.c b/sound/soc/codecs/cs42l42.c
index fb1e4c33e27d..9a463ab54bdd 100644
--- a/sound/soc/codecs/cs42l42.c
+++ b/sound/soc/codecs/cs42l42.c
@@ -922,7 +922,6 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream)
struct snd_soc_component *component = dai->component;
struct cs42l42_private *cs42l42 = snd_soc_component_get_drvdata(component);
unsigned int regval;
- u8 fullScaleVol;
int ret;
if (mute) {
@@ -993,20 +992,11 @@ static int cs42l42_mute_stream(struct snd_soc_dai *dai, int mute, int stream)
cs42l42->stream_use |= 1 << stream;
if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
- /* Read the headphone load */
- regval = snd_soc_component_read(component, CS42L42_LOAD_DET_RCSTAT);
- if (((regval & CS42L42_RLA_STAT_MASK) >> CS42L42_RLA_STAT_SHIFT) ==
- CS42L42_RLA_STAT_15_OHM) {
- fullScaleVol = CS42L42_HP_FULL_SCALE_VOL_MASK;
- } else {
- fullScaleVol = 0;
- }
-
- /* Un-mute the headphone, set the full scale volume flag */
+ /* Un-mute the headphone */
snd_soc_component_update_bits(component, CS42L42_HP_CTL,
CS42L42_HP_ANA_AMUTE_MASK |
- CS42L42_HP_ANA_BMUTE_MASK |
- CS42L42_HP_FULL_SCALE_VOL_MASK, fullScaleVol);
+ CS42L42_HP_ANA_BMUTE_MASK,
+ 0);
}
}
diff --git a/sound/soc/codecs/cs4341.c b/sound/soc/codecs/cs4341.c
index 7d3e54d8eef3..29d05e32d341 100644
--- a/sound/soc/codecs/cs4341.c
+++ b/sound/soc/codecs/cs4341.c
@@ -305,12 +305,19 @@ static int cs4341_spi_probe(struct spi_device *spi)
return cs4341_probe(&spi->dev);
}
+static const struct spi_device_id cs4341_spi_ids[] = {
+ { "cs4341a" },
+ { }
+};
+MODULE_DEVICE_TABLE(spi, cs4341_spi_ids);
+
static struct spi_driver cs4341_spi_driver = {
.driver = {
.name = "cs4341-spi",
.of_match_table = of_match_ptr(cs4341_dt_ids),
},
.probe = cs4341_spi_probe,
+ .id_table = cs4341_spi_ids,
};
#endif
diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index db88be48c998..f946ef65a4c1 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -867,8 +867,8 @@ static void nau8824_jdet_work(struct work_struct *work)
struct regmap *regmap = nau8824->regmap;
int adc_value, event = 0, event_mask = 0;
- snd_soc_dapm_enable_pin(dapm, "MICBIAS");
- snd_soc_dapm_enable_pin(dapm, "SAR");
+ snd_soc_dapm_force_enable_pin(dapm, "MICBIAS");
+ snd_soc_dapm_force_enable_pin(dapm, "SAR");
snd_soc_dapm_sync(dapm);
msleep(100);
diff --git a/sound/soc/codecs/pcm179x-spi.c b/sound/soc/codecs/pcm179x-spi.c
index 0a542924ec5f..ebf63ea90a1c 100644
--- a/sound/soc/codecs/pcm179x-spi.c
+++ b/sound/soc/codecs/pcm179x-spi.c
@@ -36,6 +36,7 @@ static const struct of_device_id pcm179x_of_match[] = {
MODULE_DEVICE_TABLE(of, pcm179x_of_match);
static const struct spi_device_id pcm179x_spi_ids[] = {
+ { "pcm1792a", 0 },
{ "pcm179x", 0 },
{ },
};
diff --git a/sound/soc/codecs/pcm512x.c b/sound/soc/codecs/pcm512x.c
index 4dc844f3c1fc..60dee41816dc 100644
--- a/sound/soc/codecs/pcm512x.c
+++ b/sound/soc/codecs/pcm512x.c
@@ -116,6 +116,8 @@ static const struct reg_default pcm512x_reg_defaults[] = {
{ PCM512x_FS_SPEED_MODE, 0x00 },
{ PCM512x_IDAC_1, 0x01 },
{ PCM512x_IDAC_2, 0x00 },
+ { PCM512x_I2S_1, 0x02 },
+ { PCM512x_I2S_2, 0x00 },
};
static bool pcm512x_readable(struct device *dev, unsigned int reg)
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index f0daf8defcf1..52de7d14b139 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -4144,10 +4144,10 @@ static int wcd938x_codec_set_jack(struct snd_soc_component *comp,
{
struct wcd938x_priv *wcd = dev_get_drvdata(comp->dev);
- if (!jack)
+ if (jack)
return wcd_mbhc_start(wcd->wcd_mbhc, &wcd->mbhc_cfg, jack);
-
- wcd_mbhc_stop(wcd->wcd_mbhc);
+ else
+ wcd_mbhc_stop(wcd->wcd_mbhc);
return 0;
}
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 9e621a254392..499604f1e178 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -742,9 +742,16 @@ static int wm8960_configure_clocking(struct snd_soc_component *component)
int i, j, k;
int ret;
- if (!(iface1 & (1<<6))) {
- dev_dbg(component->dev,
- "Codec is slave mode, no need to configure clock\n");
+ /*
+ * For Slave mode clocking should still be configured,
+ * so this if statement should be removed, but some platform
+ * may not work if the sysclk is not configured, to avoid such
+ * compatible issue, just add '!wm8960->sysclk' condition in
+ * this if statement.
+ */
+ if (!(iface1 & (1 << 6)) && !wm8960->sysclk) {
+ dev_warn(component->dev,
+ "slave mode, but proceeding with no clock configuration\n");
return 0;
}
diff --git a/sound/soc/fsl/fsl_xcvr.c b/sound/soc/fsl/fsl_xcvr.c
index 7ba2fd15132d..d0556c79fdb1 100644
--- a/sound/soc/fsl/fsl_xcvr.c
+++ b/sound/soc/fsl/fsl_xcvr.c
@@ -487,8 +487,9 @@ static int fsl_xcvr_prepare(struct snd_pcm_substream *substream,
return ret;
}
- /* clear DPATH RESET */
+ /* set DPATH RESET */
m_ctl |= FSL_XCVR_EXT_CTRL_DPTH_RESET(tx);
+ v_ctl |= FSL_XCVR_EXT_CTRL_DPTH_RESET(tx);
ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL, m_ctl, v_ctl);
if (ret < 0) {
dev_err(dai->dev, "Error while setting EXT_CTRL: %d\n", ret);
@@ -590,10 +591,6 @@ static void fsl_xcvr_shutdown(struct snd_pcm_substream *substream,
val |= FSL_XCVR_EXT_CTRL_CMDC_RESET(tx);
}
- /* set DPATH RESET */
- mask |= FSL_XCVR_EXT_CTRL_DPTH_RESET(tx);
- val |= FSL_XCVR_EXT_CTRL_DPTH_RESET(tx);
-
ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL, mask, val);
if (ret < 0) {
dev_err(dai->dev, "Err setting DPATH RESET: %d\n", ret);
@@ -643,6 +640,16 @@ static int fsl_xcvr_trigger(struct snd_pcm_substream *substream, int cmd,
dev_err(dai->dev, "Failed to enable DMA: %d\n", ret);
return ret;
}
+
+ /* clear DPATH RESET */
+ ret = regmap_update_bits(xcvr->regmap, FSL_XCVR_EXT_CTRL,
+ FSL_XCVR_EXT_CTRL_DPTH_RESET(tx),
+ 0);
+ if (ret < 0) {
+ dev_err(dai->dev, "Failed to clear DPATH RESET: %d\n", ret);
+ return ret;
+ }
+
break;
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
index 055248f104b2..4d313d0d0f23 100644
--- a/sound/soc/intel/boards/bytcht_es8316.c
+++ b/sound/soc/intel/boards/bytcht_es8316.c
@@ -456,12 +456,12 @@ static const struct dmi_system_id byt_cht_es8316_quirk_table[] = {
static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
{
+ struct device *dev = &pdev->dev;
static const char * const mic_name[] = { "in1", "in2" };
+ struct snd_soc_acpi_mach *mach = dev_get_platdata(dev);
struct property_entry props[MAX_NO_PROPS] = {};
struct byt_cht_es8316_private *priv;
const struct dmi_system_id *dmi_id;
- struct device *dev = &pdev->dev;
- struct snd_soc_acpi_mach *mach;
struct fwnode_handle *fwnode;
const char *platform_name;
struct acpi_device *adev;
@@ -476,7 +476,6 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
if (!priv)
return -ENOMEM;
- mach = dev->platform_data;
/* fix index of codec dai */
for (i = 0; i < ARRAY_SIZE(byt_cht_es8316_dais); i++) {
if (!strcmp(byt_cht_es8316_dais[i].codecs->name,
@@ -494,7 +493,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
put_device(&adev->dev);
byt_cht_es8316_dais[dai_index].codecs->name = codec_name;
} else {
- dev_err(&pdev->dev, "Error cannot find '%s' dev\n", mach->id);
+ dev_err(dev, "Error cannot find '%s' dev\n", mach->id);
return -ENXIO;
}
@@ -533,11 +532,8 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
/* get the clock */
priv->mclk = devm_clk_get(dev, "pmc_plt_clk_3");
- if (IS_ERR(priv->mclk)) {
- ret = PTR_ERR(priv->mclk);
- dev_err(dev, "clk_get pmc_plt_clk_3 failed: %d\n", ret);
- return ret;
- }
+ if (IS_ERR(priv->mclk))
+ return dev_err_probe(dev, PTR_ERR(priv->mclk), "clk_get pmc_plt_clk_3 failed\n");
/* get speaker enable GPIO */
codec_dev = acpi_get_first_physical_node(adev);
@@ -567,22 +563,13 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
devm_acpi_dev_add_driver_gpios(codec_dev, byt_cht_es8316_gpios);
priv->speaker_en_gpio =
- gpiod_get_index(codec_dev, "speaker-enable", 0,
- /* see comment in byt_cht_es8316_resume */
- GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_NONEXCLUSIVE);
-
+ gpiod_get_optional(codec_dev, "speaker-enable",
+ /* see comment in byt_cht_es8316_resume() */
+ GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_NONEXCLUSIVE);
if (IS_ERR(priv->speaker_en_gpio)) {
- ret = PTR_ERR(priv->speaker_en_gpio);
- switch (ret) {
- case -ENOENT:
- priv->speaker_en_gpio = NULL;
- break;
- default:
- dev_err(dev, "get speaker GPIO failed: %d\n", ret);
- fallthrough;
- case -EPROBE_DEFER:
- goto err_put_codec;
- }
+ ret = dev_err_probe(dev, PTR_ERR(priv->speaker_en_gpio),
+ "get speaker GPIO failed\n");
+ goto err_put_codec;
}
snprintf(components_string, sizeof(components_string),
@@ -597,7 +584,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
byt_cht_es8316_card.long_name = long_name;
#endif
- sof_parent = snd_soc_acpi_sof_parent(&pdev->dev);
+ sof_parent = snd_soc_acpi_sof_parent(dev);
/* set card and driver name */
if (sof_parent) {
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index c830e96afba2..80ca260595fd 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2599,6 +2599,7 @@ int snd_soc_component_initialize(struct snd_soc_component *component,
INIT_LIST_HEAD(&component->dai_list);
INIT_LIST_HEAD(&component->dobj_list);
INIT_LIST_HEAD(&component->card_list);
+ INIT_LIST_HEAD(&component->list);
mutex_init(&component->io_mutex);
component->name = fmt_single_name(dev, &component->id);
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 7b67f1e19ae9..59d07648a7e7 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -2561,6 +2561,7 @@ static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
const char *pin, int status)
{
struct snd_soc_dapm_widget *w = dapm_find_widget(dapm, pin, true);
+ int ret = 0;
dapm_assert_locked(dapm);
@@ -2573,13 +2574,14 @@ static int snd_soc_dapm_set_pin(struct snd_soc_dapm_context *dapm,
dapm_mark_dirty(w, "pin configuration");
dapm_widget_invalidate_input_paths(w);
dapm_widget_invalidate_output_paths(w);
+ ret = 1;
}
w->connected = status;
if (status == 0)
w->force = 0;
- return 0;
+ return ret;
}
/**
@@ -3583,14 +3585,15 @@ int snd_soc_dapm_put_pin_switch(struct snd_kcontrol *kcontrol,
{
struct snd_soc_card *card = snd_kcontrol_chip(kcontrol);
const char *pin = (const char *)kcontrol->private_value;
+ int ret;
if (ucontrol->value.integer.value[0])
- snd_soc_dapm_enable_pin(&card->dapm, pin);
+ ret = snd_soc_dapm_enable_pin(&card->dapm, pin);
else
- snd_soc_dapm_disable_pin(&card->dapm, pin);
+ ret = snd_soc_dapm_disable_pin(&card->dapm, pin);
snd_soc_dapm_sync(&card->dapm);
- return 0;
+ return ret;
}
EXPORT_SYMBOL_GPL(snd_soc_dapm_put_pin_switch);
@@ -4023,7 +4026,7 @@ static int snd_soc_dapm_dai_link_put(struct snd_kcontrol *kcontrol,
rtd->params_select = ucontrol->value.enumerated.item[0];
- return 0;
+ return 1;
}
static void
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index a2ce535df14b..8e030b1c061a 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -1198,6 +1198,13 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
cval->res = 1;
}
break;
+ case USB_ID(0x1224, 0x2a25): /* Jieli Technology USB PHY 2.0 */
+ if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
+ usb_audio_info(chip,
+ "set resolution quirk: cval->res = 16\n");
+ cval->res = 16;
+ }
+ break;
}
}
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index de18fff69280..2af8c68fac27 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -4012,6 +4012,38 @@ YAMAHA_DEVICE(0x7010, "UB99"),
}
}
},
+{
+ /*
+ * Sennheiser GSP670
+ * Change order of interfaces loaded
+ */
+ USB_DEVICE(0x1395, 0x0300),
+ .bInterfaceClass = USB_CLASS_PER_INTERFACE,
+ .driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+ .ifnum = QUIRK_ANY_INTERFACE,
+ .type = QUIRK_COMPOSITE,
+ .data = &(const struct snd_usb_audio_quirk[]) {
+ // Communication
+ {
+ .ifnum = 3,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ // Recording
+ {
+ .ifnum = 4,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ // Main
+ {
+ .ifnum = 1,
+ .type = QUIRK_AUDIO_STANDARD_INTERFACE
+ },
+ {
+ .ifnum = -1
+ }
+ }
+ }
+},
#undef USB_DEVICE_VENDOR_SPEC
#undef USB_AUDIO_DEVICE
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 889c855addfc..8929d9abe8aa 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1719,6 +1719,11 @@ void snd_usb_audioformat_attributes_quirk(struct snd_usb_audio *chip,
*/
fp->attributes &= ~UAC_EP_CS_ATTR_FILL_MAX;
break;
+ case USB_ID(0x1224, 0x2a25): /* Jieli Technology USB PHY 2.0 */
+ /* mic works only when ep packet size is set to wMaxPacketSize */
+ fp->attributes |= UAC_EP_CS_ATTR_FILL_MAX;
+ break;
+
}
}
@@ -1884,10 +1889,14 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
QUIRK_FLAG_GET_SAMPLE_RATE),
DEVICE_FLG(0x2912, 0x30c8, /* Audioengine D1 */
QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
+ QUIRK_FLAG_IGNORE_CTL_ERROR),
DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
QUIRK_FLAG_GET_SAMPLE_RATE),
DEVICE_FLG(0x534d, 0x2109, /* MacroSilicon MS2109 */
QUIRK_FLAG_ALIGN_TRANSFER),
+ DEVICE_FLG(0x1224, 0x2a25, /* Jieli Technology USB PHY 2.0 */
+ QUIRK_FLAG_GET_SAMPLE_RATE),
/* Vendor matches */
VENDOR_FLG(0x045e, /* MS Lifecam */
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index b0bf56c5f120..5a5bd74f55bd 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -742,7 +742,7 @@ class DebugfsProvider(Provider):
The fields are all available KVM debugfs files
"""
- exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns']
+ exempt_list = ['halt_poll_fail_ns', 'halt_poll_success_ns', 'halt_wait_ns']
fields = [field for field in self.walkdir(PATH_DEBUGFS_KVM)[2]
if field not in exempt_list]
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 5cd702062a04..b856afa6eb52 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -787,6 +787,8 @@ $(OUTPUT)dlfilters/%.o: dlfilters/%.c include/perf/perf_dlfilter.h
$(Q)$(MKDIR) -p $(OUTPUT)dlfilters
$(QUIET_CC)$(CC) -c -Iinclude $(EXTRA_CFLAGS) -o $@ -fpic $<
+.SECONDARY: $(DLFILTERS:.so=.o)
+
$(OUTPUT)dlfilters/%.so: $(OUTPUT)dlfilters/%.o
$(QUIET_LINK)$(CC) $(EXTRA_CFLAGS) -shared -o $@ $<
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 3018a054526a..20cd6244863b 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -45,7 +45,7 @@ static const Dwfl_Callbacks offline_callbacks = {
*/
static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
{
- Dwarf_Op ops_mem[2];
+ Dwarf_Op ops_mem[3];
Dwarf_Op dummy;
Dwarf_Op *ops = &dummy;
size_t nops;
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 6211d0b84b7a..c32c2eb16d7d 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -459,7 +459,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(WEIGHT) &&
- evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT, "WEIGHT", PERF_OUTPUT_WEIGHT))
+ evsel__check_stype(evsel, PERF_SAMPLE_WEIGHT_TYPE, "WEIGHT", PERF_OUTPUT_WEIGHT))
return -EINVAL;
if (PRINT_FIELD(SYM) &&
@@ -4039,11 +4039,15 @@ script_found:
goto out_delete;
uname(&uts);
- if (data.is_pipe || /* assume pipe_mode indicates native_arch */
- !strcmp(uts.machine, session->header.env.arch) ||
- (!strcmp(uts.machine, "x86_64") &&
- !strcmp(session->header.env.arch, "i386")))
+ if (data.is_pipe) { /* Assume pipe_mode indicates native_arch */
native_arch = true;
+ } else if (session->header.env.arch) {
+ if (!strcmp(uts.machine, session->header.env.arch))
+ native_arch = true;
+ else if (!strcmp(uts.machine, "x86_64") &&
+ !strcmp(session->header.env.arch, "i386"))
+ native_arch = true;
+ }
script.session = session;
script__setup_sample_type(&script);
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5c5979046523..d88bb65b74cc 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -949,7 +949,6 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
int err, n;
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1002,17 +1001,11 @@ static void redir_to_connected(int family, int sotype, int sock_mapfd,
goto close_peer1;
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_peer1:
xclose(p1);
@@ -1571,7 +1564,6 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1606,17 +1598,11 @@ static void unix_redir_to_connected(int sotype, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
@@ -1748,7 +1734,6 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
u32 key;
char b;
@@ -1781,17 +1766,11 @@ static void udp_redir_to_connected(int family, int sock_mapfd, int verd_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1841,7 +1820,6 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
const char *log_prefix = redir_mode_str(mode);
int c0, c1, p0, p1;
unsigned int pass;
- int retries = 100;
int err, n;
int sfd[2];
u32 key;
@@ -1876,17 +1854,11 @@ static void inet_unix_redir_to_connected(int family, int type, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close_cli1:
xclose(c1);
@@ -1932,7 +1904,6 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
int sfd[2];
u32 key;
char b;
- int retries = 100;
zero_verdict_count(verd_mapfd);
@@ -1963,17 +1934,11 @@ static void unix_inet_redir_to_connected(int family, int type, int sock_mapfd,
if (pass != 1)
FAIL("%s: want pass count 1, have %d", log_prefix, pass);
-again:
- n = read(mode == REDIR_INGRESS ? p0 : c0, &b, 1);
- if (n < 0) {
- if (errno == EAGAIN && retries--) {
- usleep(1000);
- goto again;
- }
- FAIL_ERRNO("%s: read", log_prefix);
- }
+ n = recv_timeout(mode == REDIR_INGRESS ? p0 : c0, &b, 1, 0, IO_TIMEOUT_SEC);
+ if (n < 0)
+ FAIL_ERRNO("%s: recv_timeout", log_prefix);
if (n == 0)
- FAIL("%s: incomplete read", log_prefix);
+ FAIL("%s: incomplete recv", log_prefix);
close:
xclose(c1);
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 21b646d10b88..86ab429fe7f3 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -43,3 +43,4 @@ CONFIG_NET_ACT_TUNNEL_KEY=m
CONFIG_NET_ACT_MIRRED=m
CONFIG_BAREUDP=m
CONFIG_IPV6_IOAM6_LWTUNNEL=y
+CONFIG_CRYPTO_SM4=y
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 13350cd5c8ac..3313566ce906 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -289,6 +289,12 @@ set_sysctl()
run_cmd sysctl -q -w $*
}
+# get sysctl values in NS-A
+get_sysctl()
+{
+ ${NSA_CMD} sysctl -n $*
+}
+
################################################################################
# Setup for tests
@@ -439,10 +445,13 @@ cleanup()
ip -netns ${NSA} link set dev ${NSA_DEV} down
ip -netns ${NSA} link del dev ${NSA_DEV}
+ ip netns pids ${NSA} | xargs kill 2>/dev/null
ip netns del ${NSA}
fi
+ ip netns pids ${NSB} | xargs kill 2>/dev/null
ip netns del ${NSB}
+ ip netns pids ${NSC} | xargs kill 2>/dev/null
ip netns del ${NSC} >/dev/null 2>&1
}
@@ -1003,6 +1012,60 @@ ipv4_tcp_md5()
run_cmd nettest -s -I ${NSA_DEV} -M ${MD5_PW} -m ${NS_NET}
log_test $? 1 "MD5: VRF: Device must be a VRF - prefix"
+ test_ipv4_md5_vrf__vrf_server__no_bind_ifindex
+ test_ipv4_md5_vrf__global_server__bind_ifindex0
+}
+
+test_ipv4_md5_vrf__vrf_server__no_bind_ifindex()
+{
+ log_start
+ show_hint "Simulates applications using VRF without TCP_MD5SIG_FLAG_IFINDEX"
+ run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 0 "MD5: VRF: VRF-bound server, unbound key accepts connection"
+
+ log_start
+ show_hint "Binding both the socket and the key is not required but it works"
+ run_cmd nettest -s -I ${VRF} -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 0 "MD5: VRF: VRF-bound server, bound key accepts connection"
+}
+
+test_ipv4_md5_vrf__global_server__bind_ifindex0()
+{
+ # This particular test needs tcp_l3mdev_accept=1 for Global server to accept VRF connections
+ local old_tcp_l3mdev_accept
+ old_tcp_l3mdev_accept=$(get_sysctl net.ipv4.tcp_l3mdev_accept)
+ set_sysctl net.ipv4.tcp_l3mdev_accept=1
+
+ log_start
+ run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 2 "MD5: VRF: Global server, Key bound to ifindex=0 rejects VRF connection"
+
+ log_start
+ run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --force-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 0 "MD5: VRF: Global server, key bound to ifindex=0 accepts non-VRF connection"
+ log_start
+
+ run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsb nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts VRF connection"
+
+ log_start
+ run_cmd nettest -s -M ${MD5_PW} -m ${NS_NET} --no-bind-key-ifindex &
+ sleep 1
+ run_cmd_nsc nettest -r ${NSA_IP} -X ${MD5_PW}
+ log_test $? 0 "MD5: VRF: Global server, key not bound to ifindex accepts non-VRF connection"
+
+ # restore value
+ set_sysctl net.ipv4.tcp_l3mdev_accept="$old_tcp_l3mdev_accept"
}
ipv4_tcp_novrf()
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index d97bd6889446..72ee644d47bf 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \
gre_inner_v4_multipath.sh \
gre_inner_v6_multipath.sh \
gre_multipath.sh \
+ ip6_forward_instats_vrf.sh \
ip6gre_inner_v4_multipath.sh \
ip6gre_inner_v6_multipath.sh \
ipip_flat_gre_key.sh \
diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample
index b802c14d2950..e5e2fbeca22e 100644
--- a/tools/testing/selftests/net/forwarding/forwarding.config.sample
+++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample
@@ -39,3 +39,5 @@ NETIF_CREATE=yes
# Timeout (in seconds) before ping exits regardless of how many packets have
# been sent or received
PING_TIMEOUT=5
+# IPv6 traceroute utility name.
+TROUTE6=traceroute6
diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
new file mode 100755
index 000000000000..9f5b3e2e5e95
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
@@ -0,0 +1,172 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test ipv6 stats on the incoming if when forwarding with VRF
+
+ALL_TESTS="
+ ipv6_ping
+ ipv6_in_too_big_err
+ ipv6_in_hdr_err
+ ipv6_in_addr_err
+ ipv6_in_discard
+"
+
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 2001:1:1::2/64
+ ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+}
+
+h1_destroy()
+{
+ ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+ simple_if_fini $h1 2001:1:1::2/64
+}
+
+router_create()
+{
+ vrf_create router
+ __simple_if_init $rtr1 router 2001:1:1::1/64
+ __simple_if_init $rtr2 router 2001:1:2::1/64
+ mtu_set $rtr2 1280
+}
+
+router_destroy()
+{
+ mtu_restore $rtr2
+ __simple_if_fini $rtr2 2001:1:2::1/64
+ __simple_if_fini $rtr1 2001:1:1::1/64
+ vrf_destroy router
+}
+
+h2_create()
+{
+ simple_if_init $h2 2001:1:2::2/64
+ ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+ mtu_set $h2 1280
+}
+
+h2_destroy()
+{
+ mtu_restore $h2
+ ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+ simple_if_fini $h2 2001:1:2::2/64
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rtr1=${NETIFS[p2]}
+
+ rtr2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+ h1_create
+ router_create
+ h2_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ h2_destroy
+ router_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+ipv6_in_too_big_err()
+{
+ RET=0
+
+ local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+ local vrf_name=$(master_name_get $h1)
+
+ # Send too big packets
+ ip vrf exec $vrf_name \
+ $PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+
+ local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+ test "$((t1 - t0))" -ne 0
+ check_err $?
+ log_test "Ip6InTooBigErrors"
+}
+
+ipv6_in_hdr_err()
+{
+ RET=0
+
+ local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+ local vrf_name=$(master_name_get $h1)
+
+ # Send packets with hop limit 1, easiest with traceroute6 as some ping6
+ # doesn't allow hop limit to be specified
+ ip vrf exec $vrf_name \
+ $TROUTE6 2001:1:2::2 &> /dev/null
+
+ local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+ test "$((t1 - t0))" -ne 0
+ check_err $?
+ log_test "Ip6InHdrErrors"
+}
+
+ipv6_in_addr_err()
+{
+ RET=0
+
+ local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+ local vrf_name=$(master_name_get $h1)
+
+ # Disable forwarding temporary while sending the packet
+ sysctl -qw net.ipv6.conf.all.forwarding=0
+ ip vrf exec $vrf_name \
+ $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+ sysctl -qw net.ipv6.conf.all.forwarding=1
+
+ local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+ test "$((t1 - t0))" -ne 0
+ check_err $?
+ log_test "Ip6InAddrErrors"
+}
+
+ipv6_in_discard()
+{
+ RET=0
+
+ local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+ local vrf_name=$(master_name_get $h1)
+
+ # Add a policy to discard
+ ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block
+ ip vrf exec $vrf_name \
+ $PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+ ip xfrm policy del dst 2001:1:2::2/128 dir fwd
+
+ local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+ test "$((t1 - t0))" -ne 0
+ check_err $?
+ log_test "Ip6InDiscards"
+}
+ipv6_ping()
+{
+ RET=0
+
+ ping6_test $h1 2001:1:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e7fc5c35b569..92087d423bcf 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -751,6 +751,14 @@ qdisc_parent_stats_get()
| jq '.[] | select(.parent == "'"$parent"'") | '"$selector"
}
+ipv6_stats_get()
+{
+ local dev=$1; shift
+ local stat=$1; shift
+
+ cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2
+}
+
humanize()
{
local speed=$1; shift
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index bd6288302094..b599003eb5ba 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -28,6 +28,7 @@
#include <unistd.h>
#include <time.h>
#include <errno.h>
+#include <getopt.h>
#include <linux/xfrm.h>
#include <linux/ipsec.h>
@@ -101,6 +102,8 @@ struct sock_args {
struct sockaddr_in6 v6;
} md5_prefix;
unsigned int prefix_len;
+ /* 0: default, -1: force off, +1: force on */
+ int bind_key_ifindex;
/* expected addresses and device index for connection */
const char *expected_dev;
@@ -271,11 +274,14 @@ static int tcp_md5sig(int sd, void *addr, socklen_t alen, struct sock_args *args
}
memcpy(&md5sig.tcpm_addr, addr, alen);
- if (args->ifindex) {
+ if ((args->ifindex && args->bind_key_ifindex >= 0) || args->bind_key_ifindex >= 1) {
opt = TCP_MD5SIG_EXT;
md5sig.tcpm_flags |= TCP_MD5SIG_FLAG_IFINDEX;
md5sig.tcpm_ifindex = args->ifindex;
+ log_msg("TCP_MD5SIG_FLAG_IFINDEX set tcpm_ifindex=%d\n", md5sig.tcpm_ifindex);
+ } else {
+ log_msg("TCP_MD5SIG_FLAG_IFINDEX off\n", md5sig.tcpm_ifindex);
}
rc = setsockopt(sd, IPPROTO_TCP, opt, &md5sig, sizeof(md5sig));
@@ -1822,6 +1828,14 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
}
#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
+#define OPT_FORCE_BIND_KEY_IFINDEX 1001
+#define OPT_NO_BIND_KEY_IFINDEX 1002
+
+static struct option long_opts[] = {
+ {"force-bind-key-ifindex", 0, 0, OPT_FORCE_BIND_KEY_IFINDEX},
+ {"no-bind-key-ifindex", 0, 0, OPT_NO_BIND_KEY_IFINDEX},
+ {0, 0, 0, 0}
+};
static void print_usage(char *prog)
{
@@ -1858,6 +1872,10 @@ static void print_usage(char *prog)
" -M password use MD5 sum protection\n"
" -X password MD5 password for client mode\n"
" -m prefix/len prefix and length to use for MD5 key\n"
+ " --no-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX off\n"
+ " --force-bind-key-ifindex: Force TCP_MD5SIG_FLAG_IFINDEX on\n"
+ " (default: only if -I is passed)\n"
+ "\n"
" -g grp multicast group (e.g., 239.1.1.1)\n"
" -i interactive mode (default is echo and terminate)\n"
"\n"
@@ -1893,7 +1911,7 @@ int main(int argc, char *argv[])
* process input args
*/
- while ((rc = getopt(argc, argv, GETOPT_STR)) != -1) {
+ while ((rc = getopt_long(argc, argv, GETOPT_STR, long_opts, NULL)) != -1) {
switch (rc) {
case 'B':
both_mode = 1;
@@ -1966,6 +1984,12 @@ int main(int argc, char *argv[])
case 'M':
args.password = optarg;
break;
+ case OPT_FORCE_BIND_KEY_IFINDEX:
+ args.bind_key_ifindex = 1;
+ break;
+ case OPT_NO_BIND_KEY_IFINDEX:
+ args.bind_key_ifindex = -1;
+ break;
case 'X':
args.client_pw = optarg;
break;
diff --git a/tools/testing/selftests/netfilter/nft_flowtable.sh b/tools/testing/selftests/netfilter/nft_flowtable.sh
index 427d94816f2d..d4ffebb989f8 100755
--- a/tools/testing/selftests/netfilter/nft_flowtable.sh
+++ b/tools/testing/selftests/netfilter/nft_flowtable.sh
@@ -199,7 +199,6 @@ fi
# test basic connectivity
if ! ip netns exec ns1 ping -c 1 -q 10.0.2.99 > /dev/null; then
echo "ERROR: ns1 cannot reach ns2" 1>&2
- bash
exit 1
fi
diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh
index d7e07f4c3d7f..da1c1e4b6c86 100755
--- a/tools/testing/selftests/netfilter/nft_nat.sh
+++ b/tools/testing/selftests/netfilter/nft_nat.sh
@@ -741,6 +741,149 @@ EOF
return $lret
}
+# test port shadowing.
+# create two listening services, one on router (ns0), one
+# on client (ns2), which is masqueraded from ns1 point of view.
+# ns2 sends udp packet coming from service port to ns1, on a highport.
+# Later, if n1 uses same highport to connect to ns0:service, packet
+# might be port-forwarded to ns2 instead.
+
+# second argument tells if we expect the 'fake-entry' to take effect
+# (CLIENT) or not (ROUTER).
+test_port_shadow()
+{
+ local test=$1
+ local expect=$2
+ local daddrc="10.0.1.99"
+ local daddrs="10.0.1.1"
+ local result=""
+ local logmsg=""
+
+ echo ROUTER | ip netns exec "$ns0" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
+ nc_r=$!
+
+ echo CLIENT | ip netns exec "$ns2" nc -w 5 -u -l -p 1405 >/dev/null 2>&1 &
+ nc_c=$!
+
+ # make shadow entry, from client (ns2), going to (ns1), port 41404, sport 1405.
+ echo "fake-entry" | ip netns exec "$ns2" nc -w 1 -p 1405 -u "$daddrc" 41404 > /dev/null
+
+ # ns1 tries to connect to ns0:1405. With default settings this should connect
+ # to client, it matches the conntrack entry created above.
+
+ result=$(echo "" | ip netns exec "$ns1" nc -w 1 -p 41404 -u "$daddrs" 1405)
+
+ if [ "$result" = "$expect" ] ;then
+ echo "PASS: portshadow test $test: got reply from ${expect}${logmsg}"
+ else
+ echo "ERROR: portshadow test $test: got reply from \"$result\", not $expect as intended"
+ ret=1
+ fi
+
+ kill $nc_r $nc_c 2>/dev/null
+
+ # flush udp entries for next test round, if any
+ ip netns exec "$ns0" conntrack -F >/dev/null 2>&1
+}
+
+# This prevents port shadow of router service via packet filter,
+# packets claiming to originate from service port from internal
+# network are dropped.
+test_port_shadow_filter()
+{
+ local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family filter {
+ chain forward {
+ type filter hook forward priority 0; policy accept;
+ meta iif veth1 udp sport 1405 drop
+ }
+}
+EOF
+ test_port_shadow "port-filter" "ROUTER"
+
+ ip netns exec "$ns0" nft delete table $family filter
+}
+
+# This prevents port shadow of router service via notrack.
+test_port_shadow_notrack()
+{
+ local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family raw {
+ chain prerouting {
+ type filter hook prerouting priority -300; policy accept;
+ meta iif veth0 udp dport 1405 notrack
+ udp dport 1405 notrack
+ }
+ chain output {
+ type filter hook output priority -300; policy accept;
+ udp sport 1405 notrack
+ }
+}
+EOF
+ test_port_shadow "port-notrack" "ROUTER"
+
+ ip netns exec "$ns0" nft delete table $family raw
+}
+
+# This prevents port shadow of router service via sport remap.
+test_port_shadow_pat()
+{
+ local family=$1
+
+ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family pat {
+ chain postrouting {
+ type nat hook postrouting priority -1; policy accept;
+ meta iif veth1 udp sport <= 1405 masquerade to : 1406-65535 random
+ }
+}
+EOF
+ test_port_shadow "pat" "ROUTER"
+
+ ip netns exec "$ns0" nft delete table $family pat
+}
+
+test_port_shadowing()
+{
+ local family="ip"
+
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null
+ ip netns exec "$ns0" sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null
+
+ ip netns exec "$ns0" nft -f /dev/stdin <<EOF
+table $family nat {
+ chain postrouting {
+ type nat hook postrouting priority 0; policy accept;
+ meta oif veth0 masquerade
+ }
+}
+EOF
+ if [ $? -ne 0 ]; then
+ echo "SKIP: Could not add add $family masquerade hook"
+ return $ksft_skip
+ fi
+
+ # test default behaviour. Packet from ns1 to ns0 is redirected to ns2.
+ test_port_shadow "default" "CLIENT"
+
+ # test packet filter based mitigation: prevent forwarding of
+ # packets claiming to come from the service port.
+ test_port_shadow_filter "$family"
+
+ # test conntrack based mitigation: connections going or coming
+ # from router:service bypass connection tracking.
+ test_port_shadow_notrack "$family"
+
+ # test nat based mitigation: fowarded packets coming from service port
+ # are masqueraded with random highport.
+ test_port_shadow_pat "$family"
+
+ ip netns exec "$ns0" nft delete table $family nat
+}
# ip netns exec "$ns0" ping -c 1 -q 10.0.$i.99
for i in 0 1 2; do
@@ -861,6 +1004,8 @@ reset_counters
$test_inet_nat && test_redirect inet
$test_inet_nat && test_redirect6 inet
+test_port_shadowing
+
if [ $ret -ne 0 ];then
echo -n "FAIL: "
nft --version
diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
index 1af16d2c2a0a..52497b7b9f1d 100644
--- a/tools/testing/selftests/vm/split_huge_page_test.c
+++ b/tools/testing/selftests/vm/split_huge_page_test.c
@@ -341,7 +341,7 @@ void split_file_backed_thp(void)
}
/* write something to the file, so a file-backed THP can be allocated */
- num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc));
+ num_written = write(fd, tmpfs_loc, strlen(tmpfs_loc) + 1);
close(fd);
if (num_written < 1) {
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 10ab56c2484a..60aa1a4fc69b 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -414,9 +414,6 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
uffd_test_ops->allocate_area((void **)&area_src);
uffd_test_ops->allocate_area((void **)&area_dst);
- uffd_test_ops->release_pages(area_src);
- uffd_test_ops->release_pages(area_dst);
-
userfaultfd_open(features);
count_verify = malloc(nr_pages * sizeof(unsigned long long));
@@ -437,6 +434,26 @@ static void uffd_test_ctx_init_ext(uint64_t *features)
*(area_count(area_src, nr) + 1) = 1;
}
+ /*
+ * After initialization of area_src, we must explicitly release pages
+ * for area_dst to make sure it's fully empty. Otherwise we could have
+ * some area_dst pages be errornously initialized with zero pages,
+ * hence we could hit memory corruption later in the test.
+ *
+ * One example is when THP is globally enabled, above allocate_area()
+ * calls could have the two areas merged into a single VMA (as they
+ * will have the same VMA flags so they're mergeable). When we
+ * initialize the area_src above, it's possible that some part of
+ * area_dst could have been faulted in via one huge THP that will be
+ * shared between area_src and area_dst. It could cause some of the
+ * area_dst won't be trapped by missing userfaults.
+ *
+ * This release_pages() will guarantee even if that happened, we'll
+ * proactively split the thp and drop any accidentally initialized
+ * pages within area_dst.
+ */
+ uffd_test_ops->release_pages(area_dst);
+
pipefd = malloc(sizeof(int) * nr_cpus * 2);
if (!pipefd)
err("pipefd");
diff --git a/tools/testing/vsock/vsock_diag_test.c b/tools/testing/vsock/vsock_diag_test.c
index cec6f5a738e1..fa927ad16f8a 100644
--- a/tools/testing/vsock/vsock_diag_test.c
+++ b/tools/testing/vsock/vsock_diag_test.c
@@ -332,8 +332,6 @@ static void test_no_sockets(const struct test_opts *opts)
read_vsock_stat(&sockets);
check_no_sockets(&sockets);
-
- free_sock_stat(&sockets);
}
static void test_listen_socket_server(const struct test_opts *opts)