summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.mailmap5
-rw-r--r--Documentation/admin-guide/hw-vuln/spectre.rst48
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt12
-rw-r--r--Documentation/devicetree/bindings/clock/keystone-gate.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/keystone-pll.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/adpll.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/apll.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/autoidle.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/clockdomain.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/composite.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/divider.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/dpll.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/fapll.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/gate.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/interface.txt2
-rw-r--r--Documentation/devicetree/bindings/clock/ti/mux.txt2
-rw-r--r--Documentation/devicetree/bindings/dts-coding-style.rst2
-rw-r--r--Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt3
-rw-r--r--Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml2
-rw-r--r--Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml2
-rw-r--r--Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml2
-rw-r--r--Documentation/devicetree/bindings/ufs/qcom,ufs.yaml38
-rw-r--r--Documentation/filesystems/bcachefs/index.rst11
-rw-r--r--Documentation/filesystems/index.rst1
-rw-r--r--MAINTAINERS59
-rw-r--r--Makefile2
-rw-r--r--arch/arm64/kernel/ptrace.c5
-rw-r--r--arch/loongarch/boot/dts/loongson-2k1000.dtsi7
-rw-r--r--arch/loongarch/boot/dts/loongson-2k2000-ref.dts33
-rw-r--r--arch/loongarch/boot/dts/loongson-2k2000.dtsi24
-rw-r--r--arch/loongarch/include/asm/addrspace.h1
-rw-r--r--arch/loongarch/include/asm/io.h20
-rw-r--r--arch/loongarch/include/asm/kfence.h9
-rw-r--r--arch/loongarch/include/asm/page.h26
-rw-r--r--arch/loongarch/mm/mmap.c4
-rw-r--r--arch/loongarch/mm/pgtable.c4
-rw-r--r--arch/nios2/kernel/prom.c6
-rw-r--r--arch/powerpc/include/asm/vdso/gettimeofday.h3
-rw-r--r--arch/riscv/Makefile2
-rw-r--r--arch/riscv/include/asm/pgtable.h6
-rw-r--r--arch/riscv/include/asm/syscall_wrapper.h3
-rw-r--r--arch/riscv/include/asm/uaccess.h4
-rw-r--r--arch/riscv/include/uapi/asm/auxvec.h2
-rw-r--r--arch/riscv/kernel/compat_vdso/Makefile2
-rw-r--r--arch/riscv/kernel/patch.c8
-rw-r--r--arch/riscv/kernel/process.c5
-rw-r--r--arch/riscv/kernel/signal.c15
-rw-r--r--arch/riscv/kernel/traps.c2
-rw-r--r--arch/riscv/kernel/vdso/Makefile1
-rw-r--r--arch/riscv/mm/tlbflush.c4
-rw-r--r--arch/s390/include/asm/atomic.h44
-rw-r--r--arch/s390/include/asm/atomic_ops.h22
-rw-r--r--arch/s390/include/asm/preempt.h36
-rw-r--r--arch/s390/kernel/entry.S1
-rw-r--r--arch/s390/kernel/perf_pai_crypto.c10
-rw-r--r--arch/s390/kernel/perf_pai_ext.c10
-rw-r--r--arch/s390/mm/fault.c2
-rw-r--r--arch/x86/Kconfig26
-rw-r--r--arch/x86/coco/core.c93
-rw-r--r--arch/x86/entry/common.c10
-rw-r--r--arch/x86/entry/entry_64.S61
-rw-r--r--arch/x86/entry/entry_64_compat.S16
-rw-r--r--arch/x86/entry/syscall_32.c21
-rw-r--r--arch/x86/entry/syscall_64.c19
-rw-r--r--arch/x86/entry/syscall_x32.c10
-rw-r--r--arch/x86/events/intel/ds.c8
-rw-r--r--arch/x86/include/asm/coco.h2
-rw-r--r--arch/x86/include/asm/cpufeature.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h7
-rw-r--r--arch/x86/include/asm/msr-index.h9
-rw-r--r--arch/x86/include/asm/nospec-branch.h17
-rw-r--r--arch/x86/include/asm/sev.h4
-rw-r--r--arch/x86/include/asm/syscall.h11
-rw-r--r--arch/x86/kernel/cpu/amd.c38
-rw-r--r--arch/x86/kernel/cpu/bugs.c121
-rw-r--r--arch/x86/kernel/cpu/common.c24
-rw-r--r--arch/x86/kernel/cpu/mce/core.c4
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h3
-rw-r--r--arch/x86/kernel/cpu/scattered.c1
-rw-r--r--arch/x86/kernel/setup.c2
-rw-r--r--arch/x86/kernel/sev.c10
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/reverse_cpuid.h5
-rw-r--r--arch/x86/kvm/svm/sev.c2
-rw-r--r--arch/x86/kvm/vmx/vmenter.S2
-rw-r--r--arch/x86/kvm/x86.c2
-rw-r--r--arch/x86/lib/retpoline.S1
-rw-r--r--arch/x86/mm/numa_32.c1
-rw-r--r--arch/x86/mm/pat/memtype.c49
-rw-r--r--arch/x86/virt/svm/sev.c26
-rw-r--r--block/bdev.c84
-rw-r--r--block/ioctl.c5
-rw-r--r--drivers/acpi/thermal.c22
-rw-r--r--drivers/ata/ahci_st.c1
-rw-r--r--drivers/ata/pata_macio.c3
-rw-r--r--drivers/ata/sata_gemini.c5
-rw-r--r--drivers/ata/sata_mv.c63
-rw-r--r--drivers/ata/sata_sx4.c6
-rw-r--r--drivers/base/core.c26
-rw-r--r--drivers/base/regmap/regcache-maple.c6
-rw-r--r--drivers/block/null_blk/main.c4
-rw-r--r--drivers/crypto/ccp/sev-dev.c2
-rw-r--r--drivers/firewire/ohci.c6
-rw-r--r--drivers/gpio/gpiolib-cdev.c48
-rw-r--r--drivers/gpio/gpiolib.c3
-rw-r--r--drivers/gpu/drm/display/drm_dp_dual_mode_helper.c4
-rw-r--r--drivers/gpu/drm/drm_prime.c7
-rw-r--r--drivers/gpu/drm/i915/Makefile1
-rw-r--r--drivers/gpu/drm/i915/display/intel_display.c9
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_device.h1
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_types.h2
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c11
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp_mst.c2
-rw-r--r--drivers/gpu/drm/i915/display/intel_psr.c78
-rw-r--r--drivers/gpu/drm/i915/gt/gen8_ppgtt.c3
-rw-r--r--drivers/gpu/drm/i915/gt/intel_engine_cs.c17
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt.c6
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt.h9
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c39
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h13
-rw-r--r--drivers/gpu/drm/i915/gt/intel_gt_regs.h6
-rw-r--r--drivers/gpu/drm/i915/gt/intel_workarounds.c30
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_uvmm.c6
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c12
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c1
-rw-r--r--drivers/gpu/drm/panfrost/panfrost_gpu.c6
-rw-r--r--drivers/gpu/drm/xe/xe_device.c11
-rw-r--r--drivers/gpu/drm/xe/xe_device_types.h3
-rw-r--r--drivers/gpu/drm/xe/xe_exec.c79
-rw-r--r--drivers/gpu/drm/xe/xe_exec_queue_types.h5
-rw-r--r--drivers/gpu/drm/xe/xe_gt_pagefault.c3
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c1
-rw-r--r--drivers/gpu/drm/xe/xe_gt_types.h7
-rw-r--r--drivers/gpu/drm/xe/xe_preempt_fence.c2
-rw-r--r--drivers/gpu/drm/xe/xe_pt.c25
-rw-r--r--drivers/gpu/drm/xe/xe_ring_ops.c11
-rw-r--r--drivers/gpu/drm/xe/xe_sched_job.c10
-rw-r--r--drivers/gpu/drm/xe/xe_sched_job_types.h2
-rw-r--r--drivers/gpu/drm/xe/xe_vm.c110
-rw-r--r--drivers/gpu/drm/xe/xe_vm.h8
-rw-r--r--drivers/gpu/drm/xe/xe_vm_types.h8
-rw-r--r--drivers/i2c/busses/i2c-pxa.c2
-rw-r--r--drivers/iommu/amd/init.c4
-rw-r--r--drivers/isdn/mISDN/socket.c10
-rw-r--r--drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c8
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c5
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h2
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c2
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c2
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c11
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c4
-rw-r--r--drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c2
-rw-r--r--drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c5
-rw-r--r--drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h2
-rw-r--r--drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c2
-rw-r--r--drivers/mtd/devices/block2mtd.c2
-rw-r--r--drivers/net/dsa/mt7530.c246
-rw-r--r--drivers/net/dsa/mt7530.h6
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_com.c2
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_netdev.c35
-rw-r--r--drivers/net/ethernet/amazon/ena/ena_xdp.c4
-rw-r--r--drivers/net/ethernet/amd/pds_core/core.c13
-rw-r--r--drivers/net/ethernet/amd/pds_core/core.h2
-rw-r--r--drivers/net/ethernet/amd/pds_core/dev.c3
-rw-r--r--drivers/net/ethernet/amd/pds_core/main.c1
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c2
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c6
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c20
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/qos.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h8
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/qos.c33
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/selq.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c45
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.c9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c11
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_core.c17
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c37
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c82
-rw-r--r--drivers/net/ethernet/micrel/ks8851.h3
-rw-r--r--drivers/net/ethernet/micrel/ks8851_common.c16
-rw-r--r--drivers/net/ethernet/micrel/ks8851_par.c11
-rw-r--r--drivers/net/ethernet/micrel/ks8851_spi.c11
-rw-r--r--drivers/net/ethernet/microchip/sparx5/sparx5_port.c4
-rw-r--r--drivers/net/ethernet/realtek/r8169.h6
-rw-r--r--drivers/net/ethernet/realtek/r8169_leds.c35
-rw-r--r--drivers/net/ethernet/realtek/r8169_main.c9
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/mmc.h2
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/mmc_core.c15
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c2
-rw-r--r--drivers/net/geneve.c4
-rw-r--r--drivers/net/virtio_net.c26
-rw-r--r--drivers/nvme/host/core.c41
-rw-r--r--drivers/nvme/host/fc.c4
-rw-r--r--drivers/nvme/host/nvme.h12
-rw-r--r--drivers/nvme/host/zns.c33
-rw-r--r--drivers/nvme/target/configfs.c47
-rw-r--r--drivers/nvme/target/core.c7
-rw-r--r--drivers/nvme/target/fc.c17
-rw-r--r--drivers/of/dynamic.c12
-rw-r--r--drivers/of/module.c8
-rw-r--r--drivers/perf/riscv_pmu.c4
-rw-r--r--drivers/platform/chrome/cros_ec_uart.c28
-rw-r--r--drivers/platform/x86/acer-wmi.c9
-rw-r--r--drivers/platform/x86/intel/hid.c9
-rw-r--r--drivers/platform/x86/intel/vbtn.c11
-rw-r--r--drivers/platform/x86/lg-laptop.c2
-rw-r--r--drivers/platform/x86/toshiba_acpi.c4
-rw-r--r--drivers/regulator/tps65132-regulator.c7
-rw-r--r--drivers/scsi/hisi_sas/hisi_sas_main.c2
-rw-r--r--drivers/scsi/hisi_sas/hisi_sas_v3_hw.c10
-rw-r--r--drivers/scsi/libsas/sas_expander.c2
-rw-r--r--drivers/scsi/myrb.c20
-rw-r--r--drivers/scsi/myrs.c24
-rw-r--r--drivers/scsi/qla2xxx/qla_edif.c2
-rw-r--r--drivers/scsi/sd.c2
-rw-r--r--drivers/scsi/sg.c18
-rw-r--r--drivers/spi/spi-fsl-lpspi.c14
-rw-r--r--drivers/spi/spi-pci1xxxx.c2
-rw-r--r--drivers/spi/spi-s3c64xx.c5
-rw-r--r--drivers/target/target_core_configfs.c12
-rw-r--r--drivers/thermal/gov_power_allocator.c14
-rw-r--r--drivers/ufs/core/ufshcd.c9
-rw-r--r--fs/aio.c2
-rw-r--r--fs/bcachefs/acl.c30
-rw-r--r--fs/bcachefs/bcachefs_format.h14
-rw-r--r--fs/bcachefs/btree_gc.c13
-rw-r--r--fs/bcachefs/btree_iter.h2
-rw-r--r--fs/bcachefs/btree_journal_iter.c67
-rw-r--r--fs/bcachefs/btree_key_cache.c4
-rw-r--r--fs/bcachefs/btree_locking.c28
-rw-r--r--fs/bcachefs/btree_node_scan.c11
-rw-r--r--fs/bcachefs/btree_types.h14
-rw-r--r--fs/bcachefs/btree_update_interior.c128
-rw-r--r--fs/bcachefs/btree_update_interior.h3
-rw-r--r--fs/bcachefs/chardev.c98
-rw-r--r--fs/bcachefs/data_update.c17
-rw-r--r--fs/bcachefs/debug.c75
-rw-r--r--fs/bcachefs/eytzinger.c8
-rw-r--r--fs/bcachefs/eytzinger.h26
-rw-r--r--fs/bcachefs/journal_reclaim.c2
-rw-r--r--fs/bcachefs/journal_types.h1
-rw-r--r--fs/bcachefs/recovery.c14
-rw-r--r--fs/bcachefs/snapshot.c19
-rw-r--r--fs/bcachefs/super-io.c2
-rw-r--r--fs/bcachefs/super.c5
-rw-r--r--fs/bcachefs/sysfs.c6
-rw-r--r--fs/bcachefs/tests.c2
-rw-r--r--fs/bcachefs/util.h10
-rw-r--r--fs/btrfs/delayed-inode.c3
-rw-r--r--fs/btrfs/inode.c15
-rw-r--r--fs/btrfs/ioctl.c37
-rw-r--r--fs/btrfs/qgroup.c2
-rw-r--r--fs/btrfs/root-tree.c10
-rw-r--r--fs/btrfs/root-tree.h2
-rw-r--r--fs/btrfs/transaction.c19
-rw-r--r--fs/cramfs/inode.c2
-rw-r--r--fs/ext4/super.c8
-rw-r--r--fs/f2fs/super.c2
-rw-r--r--fs/jfs/jfs_logmgr.c4
-rw-r--r--fs/nfsd/nfs4state.c7
-rw-r--r--fs/proc/bootconfig.c12
-rw-r--r--fs/reiserfs/journal.c2
-rw-r--r--fs/romfs/super.c2
-rw-r--r--fs/smb/client/cached_dir.c6
-rw-r--r--fs/smb/client/cifs_debug.c6
-rw-r--r--fs/smb/client/cifsfs.c11
-rw-r--r--fs/smb/client/cifsglob.h19
-rw-r--r--fs/smb/client/cifsproto.h20
-rw-r--r--fs/smb/client/cifssmb.c6
-rw-r--r--fs/smb/client/connect.c153
-rw-r--r--fs/smb/client/dfs.c51
-rw-r--r--fs/smb/client/dfs.h33
-rw-r--r--fs/smb/client/dfs_cache.c53
-rw-r--r--fs/smb/client/dir.c15
-rw-r--r--fs/smb/client/file.c111
-rw-r--r--fs/smb/client/fs_context.c6
-rw-r--r--fs/smb/client/fs_context.h12
-rw-r--r--fs/smb/client/fscache.h6
-rw-r--r--fs/smb/client/ioctl.c6
-rw-r--r--fs/smb/client/misc.c8
-rw-r--r--fs/smb/client/smb1ops.c4
-rw-r--r--fs/smb/client/smb2misc.c4
-rw-r--r--fs/smb/client/smb2ops.c13
-rw-r--r--fs/smb/client/smb2pdu.c2
-rw-r--r--fs/smb/client/smb2transport.c2
-rw-r--r--fs/smb/server/ksmbd_netlink.h3
-rw-r--r--fs/smb/server/mgmt/share_config.c7
-rw-r--r--fs/smb/server/smb2ops.c10
-rw-r--r--fs/smb/server/smb2pdu.c3
-rw-r--r--fs/smb/server/transport_ipc.c37
-rw-r--r--fs/super.c24
-rw-r--r--fs/xfs/xfs_buf.c2
-rw-r--r--fs/xfs/xfs_inode.c15
-rw-r--r--fs/xfs/xfs_super.c6
-rw-r--r--include/linux/blkdev.h11
-rw-r--r--include/linux/bootconfig.h1
-rw-r--r--include/linux/cc_platform.h12
-rw-r--r--include/linux/compiler.h2
-rw-r--r--include/linux/device.h1
-rw-r--r--include/linux/energy_model.h1
-rw-r--r--include/linux/fs.h2
-rw-r--r--include/linux/gfp_types.h2
-rw-r--r--include/linux/io_uring_types.h1
-rw-r--r--include/linux/mm.h10
-rw-r--r--include/linux/randomize_kstack.h2
-rw-r--r--include/linux/secretmem.h4
-rw-r--r--include/linux/sockptr.h25
-rw-r--r--include/linux/stackdepot.h7
-rw-r--r--include/linux/timecounter.h11
-rw-r--r--include/linux/timekeeping.h49
-rw-r--r--include/linux/timer.h12
-rw-r--r--include/linux/u64_stats_sync.h9
-rw-r--r--include/net/addrconf.h4
-rw-r--r--include/net/bluetooth/bluetooth.h9
-rw-r--r--include/net/ip_tunnels.h33
-rw-r--r--include/sound/hdaudio_ext.h3
-rw-r--r--include/sound/tas2781-tlv.h2
-rw-r--r--include/vdso/datapage.h8
-rw-r--r--init/initramfs.c2
-rw-r--r--init/main.c5
-rw-r--r--io_uring/io_uring.c31
-rw-r--r--io_uring/kbuf.c118
-rw-r--r--io_uring/kbuf.h8
-rw-r--r--io_uring/rw.c9
-rw-r--r--kernel/kprobes.c18
-rw-r--r--kernel/time/tick-sched.c18
-rw-r--r--kernel/time/tick-sched.h2
-rw-r--r--kernel/time/timer.c22
-rw-r--r--kernel/time/timer_migration.c32
-rw-r--r--lib/checksum_kunit.c5
-rw-r--r--lib/stackdepot.c4
-rw-r--r--lib/test_ubsan.c2
-rw-r--r--mm/memory.c4
-rw-r--r--mm/vmalloc.c76
-rw-r--r--net/9p/client.c10
-rw-r--r--net/9p/trans_fd.c1
-rw-r--r--net/batman-adv/translation-table.c2
-rw-r--r--net/bluetooth/hci_request.c4
-rw-r--r--net/bluetooth/hci_sock.c21
-rw-r--r--net/bluetooth/hci_sync.c6
-rw-r--r--net/bluetooth/iso.c46
-rw-r--r--net/bluetooth/l2cap_core.c3
-rw-r--r--net/bluetooth/l2cap_sock.c52
-rw-r--r--net/bluetooth/rfcomm/sock.c14
-rw-r--r--net/bluetooth/sco.c23
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv6/addrconf.c7
-rw-r--r--net/ipv6/ip6_fib.c7
-rw-r--r--net/ipv6/netfilter/ip6_tables.c4
-rw-r--r--net/nfc/llcp_sock.c12
-rw-r--r--net/openvswitch/conntrack.c5
-rw-r--r--net/sunrpc/svcsock.c10
-rw-r--r--net/unix/af_unix.c4
-rw-r--r--net/xdp/xsk.c2
-rw-r--r--scripts/gcc-plugins/stackleak_plugin.c2
-rw-r--r--sound/oss/dmasound/dmasound_paula.c8
-rw-r--r--sound/pci/emu10k1/emu10k1_callback.c7
-rw-r--r--sound/pci/hda/cs35l41_hda_property.c6
-rw-r--r--sound/pci/hda/cs35l56_hda_i2c.c13
-rw-r--r--sound/pci/hda/cs35l56_hda_spi.c13
-rw-r--r--sound/pci/hda/patch_realtek.c60
-rw-r--r--sound/soc/amd/acp/acp-pci.c13
-rw-r--r--sound/soc/codecs/cs-amp-lib.c5
-rw-r--r--sound/soc/codecs/cs42l43.c12
-rw-r--r--sound/soc/codecs/es8326.c37
-rw-r--r--sound/soc/codecs/es8326.h2
-rw-r--r--sound/soc/codecs/rt1316-sdw.c8
-rw-r--r--sound/soc/codecs/rt1318-sdw.c8
-rw-r--r--sound/soc/codecs/rt5682-sdw.c16
-rw-r--r--sound/soc/codecs/rt700.c16
-rw-r--r--sound/soc/codecs/rt711-sdca-sdw.c6
-rw-r--r--sound/soc/codecs/rt711-sdca.c18
-rw-r--r--sound/soc/codecs/rt711-sdw.c8
-rw-r--r--sound/soc/codecs/rt711.c16
-rw-r--r--sound/soc/codecs/rt712-sdca-dmic.c24
-rw-r--r--sound/soc/codecs/rt712-sdca-sdw.c7
-rw-r--r--sound/soc/codecs/rt712-sdca.c20
-rw-r--r--sound/soc/codecs/rt715-sdca-sdw.c2
-rw-r--r--sound/soc/codecs/rt715-sdca.c46
-rw-r--r--sound/soc/codecs/rt715-sdw.c4
-rw-r--r--sound/soc/codecs/rt715.c24
-rw-r--r--sound/soc/codecs/rt722-sdca-sdw.c4
-rw-r--r--sound/soc/codecs/rt722-sdca.c21
-rw-r--r--sound/soc/codecs/wm_adsp.c3
-rw-r--r--sound/soc/intel/avs/boards/da7219.c1
-rw-r--r--sound/soc/intel/avs/boards/dmic.c1
-rw-r--r--sound/soc/intel/avs/boards/es8336.c1
-rw-r--r--sound/soc/intel/avs/boards/i2s_test.c1
-rw-r--r--sound/soc/intel/avs/boards/max98357a.c1
-rw-r--r--sound/soc/intel/avs/boards/max98373.c1
-rw-r--r--sound/soc/intel/avs/boards/max98927.c1
-rw-r--r--sound/soc/intel/avs/boards/nau8825.c1
-rw-r--r--sound/soc/intel/avs/boards/probe.c1
-rw-r--r--sound/soc/intel/avs/boards/rt274.c1
-rw-r--r--sound/soc/intel/avs/boards/rt286.c1
-rw-r--r--sound/soc/intel/avs/boards/rt298.c1
-rw-r--r--sound/soc/intel/avs/boards/rt5514.c1
-rw-r--r--sound/soc/intel/avs/boards/rt5663.c1
-rw-r--r--sound/soc/intel/avs/boards/rt5682.c1
-rw-r--r--sound/soc/intel/avs/boards/ssm4567.c1
-rw-r--r--sound/soc/soc-ops.c2
-rw-r--r--sound/soc/sof/amd/acp.c8
-rw-r--r--sound/soc/sof/core.c14
-rw-r--r--sound/soc/sof/intel/hda-common-ops.c3
-rw-r--r--sound/soc/sof/intel/hda-dai-ops.c11
-rw-r--r--sound/soc/sof/intel/hda-dsp.c20
-rw-r--r--sound/soc/sof/intel/hda-pcm.c29
-rw-r--r--sound/soc/sof/intel/hda-stream.c70
-rw-r--r--sound/soc/sof/intel/hda.h6
-rw-r--r--sound/soc/sof/intel/lnl.c34
-rw-r--r--sound/soc/sof/intel/mtl.c14
-rw-r--r--sound/soc/sof/intel/mtl.h10
-rw-r--r--sound/soc/sof/ipc4-mtrace.c11
-rw-r--r--sound/soc/sof/ipc4-pcm.c191
-rw-r--r--sound/soc/sof/ipc4-priv.h14
-rw-r--r--sound/soc/sof/ipc4-topology.c22
-rw-r--r--sound/soc/sof/ops.h24
-rw-r--r--sound/soc/sof/pcm.c8
-rw-r--r--sound/soc/sof/sof-audio.h9
-rw-r--r--sound/soc/sof/sof-priv.h24
-rw-r--r--sound/usb/line6/driver.c6
-rw-r--r--tools/include/linux/kernel.h1
-rw-r--r--tools/include/linux/mm.h5
-rw-r--r--tools/include/linux/panic.h19
-rw-r--r--tools/power/x86/turbostat/turbostat.818
-rw-r--r--tools/power/x86/turbostat/turbostat.c2017
-rw-r--r--tools/testing/selftests/mm/vm_util.h2
-rwxr-xr-xtools/testing/selftests/turbostat/defcolumns.py60
439 files changed, 6069 insertions, 2417 deletions
diff --git a/.mailmap b/.mailmap
index 59c9a841bf71..8284692f9610 100644
--- a/.mailmap
+++ b/.mailmap
@@ -20,6 +20,7 @@ Adam Oldham <oldhamca@gmail.com>
Adam Radford <aradford@gmail.com>
Adriana Reus <adi.reus@gmail.com> <adriana.reus@intel.com>
Adrian Bunk <bunk@stusta.de>
+Ajay Kaher <ajay.kaher@broadcom.com> <akaher@vmware.com>
Akhil P Oommen <quic_akhilpo@quicinc.com> <akhilpo@codeaurora.org>
Alan Cox <alan@lxorguk.ukuu.org.uk>
Alan Cox <root@hraefn.swansea.linux.org.uk>
@@ -36,6 +37,7 @@ Alexei Avshalom Lazar <quic_ailizaro@quicinc.com> <ailizaro@codeaurora.org>
Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alexey Makhalov <alexey.amakhalov@broadcom.com> <amakhalov@vmware.com>
Alex Hung <alexhung@gmail.com> <alex.hung@canonical.com>
Alex Shi <alexs@kernel.org> <alex.shi@intel.com>
Alex Shi <alexs@kernel.org> <alex.shi@linaro.org>
@@ -110,6 +112,7 @@ Brendan Higgins <brendan.higgins@linux.dev> <brendanhiggins@google.com>
Brian Avery <b.avery@hp.com>
Brian King <brking@us.ibm.com>
Brian Silverman <bsilver16384@gmail.com> <brian.silverman@bluerivertech.com>
+Bryan Tan <bryan-bt.tan@broadcom.com> <bryantan@vmware.com>
Cai Huoqing <cai.huoqing@linux.dev> <caihuoqing@baidu.com>
Can Guo <quic_cang@quicinc.com> <cang@codeaurora.org>
Carl Huang <quic_cjhuang@quicinc.com> <cjhuang@codeaurora.org>
@@ -529,6 +532,7 @@ Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org>
Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
+Ronak Doshi <ronak.doshi@broadcom.com> <doshir@vmware.com>
Muchun Song <muchun.song@linux.dev> <songmuchun@bytedance.com>
Muchun Song <muchun.song@linux.dev> <smuchun@gmail.com>
Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
@@ -651,6 +655,7 @@ Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.org>
Viresh Kumar <viresh.kumar@linaro.org> <viresh.kumar@linaro.com>
+Vishnu Dasa <vishnu.dasa@broadcom.com> <vdasa@vmware.com>
Vivek Aknurwar <quic_viveka@quicinc.com> <viveka@codeaurora.org>
Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com>
Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com>
diff --git a/Documentation/admin-guide/hw-vuln/spectre.rst b/Documentation/admin-guide/hw-vuln/spectre.rst
index cce768afec6b..b70b1d8bd8e6 100644
--- a/Documentation/admin-guide/hw-vuln/spectre.rst
+++ b/Documentation/admin-guide/hw-vuln/spectre.rst
@@ -138,11 +138,10 @@ associated with the source address of the indirect branch. Specifically,
the BHB might be shared across privilege levels even in the presence of
Enhanced IBRS.
-Currently the only known real-world BHB attack vector is via
-unprivileged eBPF. Therefore, it's highly recommended to not enable
-unprivileged eBPF, especially when eIBRS is used (without retpolines).
-For a full mitigation against BHB attacks, it's recommended to use
-retpolines (or eIBRS combined with retpolines).
+Previously the only known real-world BHB attack vector was via unprivileged
+eBPF. Further research has found attacks that don't require unprivileged eBPF.
+For a full mitigation against BHB attacks it is recommended to set BHI_DIS_S or
+use the BHB clearing sequence.
Attack scenarios
----------------
@@ -430,6 +429,23 @@ The possible values in this file are:
'PBRSB-eIBRS: Not affected' CPU is not affected by PBRSB
=========================== =======================================================
+ - Branch History Injection (BHI) protection status:
+
+.. list-table::
+
+ * - BHI: Not affected
+ - System is not affected
+ * - BHI: Retpoline
+ - System is protected by retpoline
+ * - BHI: BHI_DIS_S
+ - System is protected by BHI_DIS_S
+ * - BHI: SW loop; KVM SW loop
+ - System is protected by software clearing sequence
+ * - BHI: Syscall hardening
+ - Syscalls are hardened against BHI
+ * - BHI: Syscall hardening; KVM: SW loop
+ - System is protected from userspace attacks by syscall hardening; KVM is protected by software clearing sequence
+
Full mitigation might require a microcode update from the CPU
vendor. When the necessary microcode is not available, the kernel will
report vulnerability.
@@ -484,7 +500,11 @@ Spectre variant 2
Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
boot, by setting the IBRS bit, and they're automatically protected against
- Spectre v2 variant attacks.
+ some Spectre v2 variant attacks. The BHB can still influence the choice of
+ indirect branch predictor entry, and although branch predictor entries are
+ isolated between modes when eIBRS is enabled, the BHB itself is not isolated
+ between modes. Systems which support BHI_DIS_S will set it to protect against
+ BHI attacks.
On Intel's enhanced IBRS systems, this includes cross-thread branch target
injections on SMT systems (STIBP). In other words, Intel eIBRS enables
@@ -638,6 +658,22 @@ kernel command line.
spectre_v2=off. Spectre variant 1 mitigations
cannot be disabled.
+ spectre_bhi=
+
+ [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. Syscalls are hardened against BHI
+ regardless of this setting. This setting affects the deployment
+ of the HW BHI control and the SW BHB clearing sequence.
+
+ on
+ unconditionally enable.
+ off
+ unconditionally disable.
+ auto
+ enable if hardware mitigation
+ control(BHI_DIS_S) is available, otherwise
+ enable alternate mitigation in KVM.
+
For spectre_v2_user see Documentation/admin-guide/kernel-parameters.txt
Mitigation selection guide
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 623fce7d5fcd..70046a019d42 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6063,6 +6063,18 @@
sonypi.*= [HW] Sony Programmable I/O Control Device driver
See Documentation/admin-guide/laptops/sonypi.rst
+ spectre_bhi= [X86] Control mitigation of Branch History Injection
+ (BHI) vulnerability. Syscalls are hardened against BHI
+ reglardless of this setting. This setting affects the
+ deployment of the HW BHI control and the SW BHB
+ clearing sequence.
+
+ on - unconditionally enable.
+ off - unconditionally disable.
+ auto - (default) enable hardware mitigation
+ (BHI_DIS_S) if available, otherwise enable
+ alternate mitigation in KVM.
+
spectre_v2= [X86,EARLY] Control mitigation of Spectre variant 2
(indirect branch speculation) vulnerability.
The default operation protects the kernel from
diff --git a/Documentation/devicetree/bindings/clock/keystone-gate.txt b/Documentation/devicetree/bindings/clock/keystone-gate.txt
index c5aa187026e3..43f6fb6c9392 100644
--- a/Documentation/devicetree/bindings/clock/keystone-gate.txt
+++ b/Documentation/devicetree/bindings/clock/keystone-gate.txt
@@ -1,5 +1,3 @@
-Status: Unstable - ABI compatibility may be broken in the future
-
Binding for Keystone gate control driver which uses PSC controller IP.
This binding uses the common clock binding[1].
diff --git a/Documentation/devicetree/bindings/clock/keystone-pll.txt b/Documentation/devicetree/bindings/clock/keystone-pll.txt
index 9a3fbc665606..69b0eb7c03c9 100644
--- a/Documentation/devicetree/bindings/clock/keystone-pll.txt
+++ b/Documentation/devicetree/bindings/clock/keystone-pll.txt
@@ -1,5 +1,3 @@
-Status: Unstable - ABI compatibility may be broken in the future
-
Binding for keystone PLLs. The main PLL IP typically has a multiplier,
a divider and a post divider. The additional PLL IPs like ARMPLL, DDRPLL
and PAPLL are controlled by the memory mapped register where as the Main
diff --git a/Documentation/devicetree/bindings/clock/ti/adpll.txt b/Documentation/devicetree/bindings/clock/ti/adpll.txt
index 4c8a2ce2cd70..3122360adcf3 100644
--- a/Documentation/devicetree/bindings/clock/ti/adpll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/adpll.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments ADPLL clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped ADPLL with two to three selectable input clocks
and three to four children.
diff --git a/Documentation/devicetree/bindings/clock/ti/apll.txt b/Documentation/devicetree/bindings/clock/ti/apll.txt
index ade4dd4c30f0..bbd505c1199d 100644
--- a/Documentation/devicetree/bindings/clock/ti/apll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/apll.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments APLL clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped APLL with usually two selectable input clocks
(reference clock and bypass clock), with analog phase locked
diff --git a/Documentation/devicetree/bindings/clock/ti/autoidle.txt b/Documentation/devicetree/bindings/clock/ti/autoidle.txt
index 7c735dde9fe9..05645a10a9e3 100644
--- a/Documentation/devicetree/bindings/clock/ti/autoidle.txt
+++ b/Documentation/devicetree/bindings/clock/ti/autoidle.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments autoidle clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a register mapped
clock which can be put to idle automatically by hardware based on the usage
and a configuration bit setting. Autoidle clock is never an individual
diff --git a/Documentation/devicetree/bindings/clock/ti/clockdomain.txt b/Documentation/devicetree/bindings/clock/ti/clockdomain.txt
index 9c6199249ce5..edf0b5d42768 100644
--- a/Documentation/devicetree/bindings/clock/ti/clockdomain.txt
+++ b/Documentation/devicetree/bindings/clock/ti/clockdomain.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments clockdomain.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1] in consumer role.
Every clock on TI SoC belongs to one clockdomain, but software
only needs this information for specific clocks which require
diff --git a/Documentation/devicetree/bindings/clock/ti/composite.txt b/Documentation/devicetree/bindings/clock/ti/composite.txt
index 33ac7c9ad053..6f7e1331b546 100644
--- a/Documentation/devicetree/bindings/clock/ti/composite.txt
+++ b/Documentation/devicetree/bindings/clock/ti/composite.txt
@@ -1,7 +1,5 @@
Binding for TI composite clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped composite clock with multiple different sub-types;
diff --git a/Documentation/devicetree/bindings/clock/ti/divider.txt b/Documentation/devicetree/bindings/clock/ti/divider.txt
index 9b13b32974f9..4d7c76f0b356 100644
--- a/Documentation/devicetree/bindings/clock/ti/divider.txt
+++ b/Documentation/devicetree/bindings/clock/ti/divider.txt
@@ -1,7 +1,5 @@
Binding for TI divider clock
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped adjustable clock rate divider that does not gate and has
only one input clock or parent. By default the value programmed into
diff --git a/Documentation/devicetree/bindings/clock/ti/dpll.txt b/Documentation/devicetree/bindings/clock/ti/dpll.txt
index 37a7cb6ad07d..14a1b72c2e71 100644
--- a/Documentation/devicetree/bindings/clock/ti/dpll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/dpll.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments DPLL clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped DPLL with usually two selectable input clocks
(reference clock and bypass clock), with digital phase locked
diff --git a/Documentation/devicetree/bindings/clock/ti/fapll.txt b/Documentation/devicetree/bindings/clock/ti/fapll.txt
index c19b3f253b8c..88986ef39ddd 100644
--- a/Documentation/devicetree/bindings/clock/ti/fapll.txt
+++ b/Documentation/devicetree/bindings/clock/ti/fapll.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments FAPLL clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped FAPLL with usually two selectable input clocks
(reference clock and bypass clock), and one or more child
diff --git a/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt b/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt
index 518e3c142276..dc69477b6e98 100644
--- a/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt
+++ b/Documentation/devicetree/bindings/clock/ti/fixed-factor-clock.txt
@@ -1,7 +1,5 @@
Binding for TI fixed factor rate clock sources.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1], and also uses the autoidle
support from TI autoidle clock [2].
diff --git a/Documentation/devicetree/bindings/clock/ti/gate.txt b/Documentation/devicetree/bindings/clock/ti/gate.txt
index 4982615c01b9..a8e0335b006a 100644
--- a/Documentation/devicetree/bindings/clock/ti/gate.txt
+++ b/Documentation/devicetree/bindings/clock/ti/gate.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments gate clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. This clock is
quite much similar to the basic gate-clock [2], however,
it supports a number of additional features. If no register
diff --git a/Documentation/devicetree/bindings/clock/ti/interface.txt b/Documentation/devicetree/bindings/clock/ti/interface.txt
index d3eb5ca92a7f..85fb1f2d2d28 100644
--- a/Documentation/devicetree/bindings/clock/ti/interface.txt
+++ b/Documentation/devicetree/bindings/clock/ti/interface.txt
@@ -1,7 +1,5 @@
Binding for Texas Instruments interface clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. This clock is
quite much similar to the basic gate-clock [2], however,
it supports a number of additional features, including
diff --git a/Documentation/devicetree/bindings/clock/ti/mux.txt b/Documentation/devicetree/bindings/clock/ti/mux.txt
index b33f641f1043..cd56d3c1c09f 100644
--- a/Documentation/devicetree/bindings/clock/ti/mux.txt
+++ b/Documentation/devicetree/bindings/clock/ti/mux.txt
@@ -1,7 +1,5 @@
Binding for TI mux clock.
-Binding status: Unstable - ABI compatibility may be broken in the future
-
This binding uses the common clock binding[1]. It assumes a
register-mapped multiplexer with multiple input clock signals or
parents, one of which can be selected as output. This clock does not
diff --git a/Documentation/devicetree/bindings/dts-coding-style.rst b/Documentation/devicetree/bindings/dts-coding-style.rst
index a9bdd2b59dca..8a68331075a0 100644
--- a/Documentation/devicetree/bindings/dts-coding-style.rst
+++ b/Documentation/devicetree/bindings/dts-coding-style.rst
@@ -144,6 +144,8 @@ Example::
#dma-cells = <1>;
clocks = <&clock_controller 0>, <&clock_controller 1>;
clock-names = "bus", "host";
+ #address-cells = <1>;
+ #size-cells = <1>;
vendor,custom-property = <2>;
status = "disabled";
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
index 25f8658e216f..48a49c516b62 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
+++ b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
@@ -1,9 +1,6 @@
TI Davinci DSP devices
=======================
-Binding status: Unstable - Subject to changes for DT representation of clocks
- and resets
-
The TI Davinci family of SoCs usually contains a TI DSP Core sub-system that
is used to offload some of the processor-intensive tasks or algorithms, for
achieving various system level goals.
diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
index 397f75909b20..ce1a6505eb51 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-dcfg.yaml
@@ -51,7 +51,7 @@ properties:
ranges: true
patternProperties:
- "^clock-controller@[0-9a-z]+$":
+ "^clock-controller@[0-9a-f]+$":
$ref: /schemas/clock/fsl,flexspi-clock.yaml#
required:
diff --git a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml
index 8d088b5fe823..a6a511b00a12 100644
--- a/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml
+++ b/Documentation/devicetree/bindings/soc/fsl/fsl,layerscape-scfg.yaml
@@ -41,7 +41,7 @@ properties:
ranges: true
patternProperties:
- "^interrupt-controller@[a-z0-9]+$":
+ "^interrupt-controller@[a-f0-9]+$":
$ref: /schemas/interrupt-controller/fsl,ls-extirq.yaml#
required:
diff --git a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
index 7a4a6ab85970..ab8f28993139 100644
--- a/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
+++ b/Documentation/devicetree/bindings/timer/arm,arch_timer_mmio.yaml
@@ -60,7 +60,7 @@ properties:
be implemented in an always-on power domain."
patternProperties:
- '^frame@[0-9a-z]*$':
+ '^frame@[0-9a-f]+$':
type: object
additionalProperties: false
description: A timer node has up to 8 frame sub-nodes, each with the following properties.
diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
index 10c146424baa..cd3680dc002f 100644
--- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
+++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml
@@ -27,10 +27,13 @@ properties:
- qcom,msm8996-ufshc
- qcom,msm8998-ufshc
- qcom,sa8775p-ufshc
+ - qcom,sc7180-ufshc
- qcom,sc7280-ufshc
+ - qcom,sc8180x-ufshc
- qcom,sc8280xp-ufshc
- qcom,sdm845-ufshc
- qcom,sm6115-ufshc
+ - qcom,sm6125-ufshc
- qcom,sm6350-ufshc
- qcom,sm8150-ufshc
- qcom,sm8250-ufshc
@@ -42,11 +45,11 @@ properties:
- const: jedec,ufs-2.0
clocks:
- minItems: 8
+ minItems: 7
maxItems: 11
clock-names:
- minItems: 8
+ minItems: 7
maxItems: 11
dma-coherent: true
@@ -117,9 +120,35 @@ allOf:
compatible:
contains:
enum:
+ - qcom,sc7180-ufshc
+ then:
+ properties:
+ clocks:
+ minItems: 7
+ maxItems: 7
+ clock-names:
+ items:
+ - const: core_clk
+ - const: bus_aggr_clk
+ - const: iface_clk
+ - const: core_clk_unipro
+ - const: ref_clk
+ - const: tx_lane0_sync_clk
+ - const: rx_lane0_sync_clk
+ reg:
+ maxItems: 1
+ reg-names:
+ maxItems: 1
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ enum:
- qcom,msm8998-ufshc
- qcom,sa8775p-ufshc
- qcom,sc7280-ufshc
+ - qcom,sc8180x-ufshc
- qcom,sc8280xp-ufshc
- qcom,sm8250-ufshc
- qcom,sm8350-ufshc
@@ -215,6 +244,7 @@ allOf:
contains:
enum:
- qcom,sm6115-ufshc
+ - qcom,sm6125-ufshc
then:
properties:
clocks:
@@ -248,7 +278,7 @@ allOf:
reg:
maxItems: 1
clocks:
- minItems: 8
+ minItems: 7
maxItems: 8
else:
properties:
@@ -256,7 +286,7 @@ allOf:
minItems: 1
maxItems: 2
clocks:
- minItems: 8
+ minItems: 7
maxItems: 11
unevaluatedProperties: false
diff --git a/Documentation/filesystems/bcachefs/index.rst b/Documentation/filesystems/bcachefs/index.rst
new file mode 100644
index 000000000000..e2bd61ccd96f
--- /dev/null
+++ b/Documentation/filesystems/bcachefs/index.rst
@@ -0,0 +1,11 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+======================
+bcachefs Documentation
+======================
+
+.. toctree::
+ :maxdepth: 2
+ :numbered:
+
+ errorcodes
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 0ea1e44fa028..1f9b4c905a6a 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -69,6 +69,7 @@ Documentation for filesystem implementations.
afs
autofs
autofs-mount-control
+ bcachefs/index
befs
bfs
btrfs
diff --git a/MAINTAINERS b/MAINTAINERS
index 4745ea94d463..d71eb49aaa06 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2191,7 +2191,6 @@ N: mxs
ARM/FREESCALE LAYERSCAPE ARM ARCHITECTURE
M: Shawn Guo <shawnguo@kernel.org>
-M: Li Yang <leoyang.li@nxp.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
@@ -3573,6 +3572,7 @@ S: Supported
C: irc://irc.oftc.net/bcache
T: git https://evilpiepirate.org/git/bcachefs.git
F: fs/bcachefs/
+F: Documentation/filesystems/bcachefs/
BDISP ST MEDIA DRIVER
M: Fabien Dessenne <fabien.dessenne@foss.st.com>
@@ -8525,7 +8525,6 @@ S: Maintained
F: drivers/video/fbdev/fsl-diu-fb.*
FREESCALE DMA DRIVER
-M: Li Yang <leoyang.li@nxp.com>
M: Zhang Wei <zw@zh-kernel.org>
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
@@ -8690,10 +8689,9 @@ F: drivers/soc/fsl/qe/tsa.h
F: include/dt-bindings/soc/cpm1-fsl,tsa.h
FREESCALE QUICC ENGINE UCC ETHERNET DRIVER
-M: Li Yang <leoyang.li@nxp.com>
L: netdev@vger.kernel.org
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: drivers/net/ethernet/freescale/ucc_geth*
FREESCALE QUICC ENGINE UCC HDLC DRIVER
@@ -8710,10 +8708,9 @@ S: Maintained
F: drivers/tty/serial/ucc_uart.c
FREESCALE SOC DRIVERS
-M: Li Yang <leoyang.li@nxp.com>
L: linuxppc-dev@lists.ozlabs.org
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-S: Maintained
+S: Orphan
F: Documentation/devicetree/bindings/misc/fsl,dpaa2-console.yaml
F: Documentation/devicetree/bindings/soc/fsl/
F: drivers/soc/fsl/
@@ -8747,10 +8744,9 @@ F: Documentation/devicetree/bindings/sound/fsl,qmc-audio.yaml
F: sound/soc/fsl/fsl_qmc_audio.c
FREESCALE USB PERIPHERAL DRIVERS
-M: Li Yang <leoyang.li@nxp.com>
L: linux-usb@vger.kernel.org
L: linuxppc-dev@lists.ozlabs.org
-S: Maintained
+S: Orphan
F: drivers/usb/gadget/udc/fsl*
FREESCALE USB PHY DRIVER
@@ -16735,9 +16731,9 @@ F: include/uapi/linux/ppdev.h
PARAVIRT_OPS INTERFACE
M: Juergen Gross <jgross@suse.com>
-R: Ajay Kaher <akaher@vmware.com>
-R: Alexey Makhalov <amakhalov@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+R: Ajay Kaher <ajay.kaher@broadcom.com>
+R: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: virtualization@lists.linux.dev
L: x86@kernel.org
S: Supported
@@ -22433,6 +22429,7 @@ S: Maintained
W: https://kernsec.org/wiki/index.php/Linux_Kernel_Integrity
Q: https://patchwork.kernel.org/project/linux-integrity/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jarkko/linux-tpmdd.git
+F: Documentation/devicetree/bindings/tpm/
F: drivers/char/tpm/
TPS546D24 DRIVER
@@ -22579,6 +22576,7 @@ Q: https://patchwork.kernel.org/project/linux-pm/list/
B: https://bugzilla.kernel.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat
F: tools/power/x86/turbostat/
+F: tools/testing/selftests/turbostat/
TW5864 VIDEO4LINUX DRIVER
M: Bluecherry Maintainers <maintainers@bluecherrydvr.com>
@@ -23657,9 +23655,9 @@ S: Supported
F: drivers/misc/vmw_balloon.c
VMWARE HYPERVISOR INTERFACE
-M: Ajay Kaher <akaher@vmware.com>
-M: Alexey Makhalov <amakhalov@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Ajay Kaher <ajay.kaher@broadcom.com>
+M: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: virtualization@lists.linux.dev
L: x86@kernel.org
S: Supported
@@ -23668,33 +23666,34 @@ F: arch/x86/include/asm/vmware.h
F: arch/x86/kernel/cpu/vmware.c
VMWARE PVRDMA DRIVER
-M: Bryan Tan <bryantan@vmware.com>
-M: Vishnu Dasa <vdasa@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Bryan Tan <bryan-bt.tan@broadcom.com>
+M: Vishnu Dasa <vishnu.dasa@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/infiniband/hw/vmw_pvrdma/
VMWARE PVSCSI DRIVER
-M: Vishal Bhakta <vbhakta@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Vishal Bhakta <vishal.bhakta@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-scsi@vger.kernel.org
S: Supported
F: drivers/scsi/vmw_pvscsi.c
F: drivers/scsi/vmw_pvscsi.h
VMWARE VIRTUAL PTP CLOCK DRIVER
-R: Ajay Kaher <akaher@vmware.com>
-R: Alexey Makhalov <amakhalov@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Nick Shi <nick.shi@broadcom.com>
+R: Ajay Kaher <ajay.kaher@broadcom.com>
+R: Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/ptp/ptp_vmw.c
VMWARE VMCI DRIVER
-M: Bryan Tan <bryantan@vmware.com>
-M: Vishnu Dasa <vdasa@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Bryan Tan <bryan-bt.tan@broadcom.com>
+M: Vishnu Dasa <vishnu.dasa@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-kernel@vger.kernel.org
S: Supported
F: drivers/misc/vmw_vmci/
@@ -23709,16 +23708,16 @@ F: drivers/input/mouse/vmmouse.c
F: drivers/input/mouse/vmmouse.h
VMWARE VMXNET3 ETHERNET DRIVER
-M: Ronak Doshi <doshir@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Ronak Doshi <ronak.doshi@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: netdev@vger.kernel.org
S: Supported
F: drivers/net/vmxnet3/
VMWARE VSOCK VMCI TRANSPORT DRIVER
-M: Bryan Tan <bryantan@vmware.com>
-M: Vishnu Dasa <vdasa@vmware.com>
-R: VMware PV-Drivers Reviewers <pv-drivers@vmware.com>
+M: Bryan Tan <bryan-bt.tan@broadcom.com>
+M: Vishnu Dasa <vishnu.dasa@broadcom.com>
+R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-kernel@vger.kernel.org
S: Supported
F: net/vmw_vsock/vmci_transport*
diff --git a/Makefile b/Makefile
index 4bef6323c47d..e1bf12891cb0 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 9
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 162b030ab9da..0d022599eb61 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -761,7 +761,6 @@ static void sve_init_header_from_task(struct user_sve_header *header,
{
unsigned int vq;
bool active;
- bool fpsimd_only;
enum vec_type task_type;
memset(header, 0, sizeof(*header));
@@ -777,12 +776,10 @@ static void sve_init_header_from_task(struct user_sve_header *header,
case ARM64_VEC_SVE:
if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = !test_tsk_thread_flag(target, TIF_SVE);
break;
case ARM64_VEC_SME:
if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT))
header->flags |= SVE_PT_VL_INHERIT;
- fpsimd_only = false;
break;
default:
WARN_ON_ONCE(1);
@@ -790,7 +787,7 @@ static void sve_init_header_from_task(struct user_sve_header *header,
}
if (active) {
- if (fpsimd_only) {
+ if (target->thread.fp_type == FP_STATE_FPSIMD) {
header->flags |= SVE_PT_REGS_FPSIMD;
} else {
header->flags |= SVE_PT_REGS_SVE;
diff --git a/arch/loongarch/boot/dts/loongson-2k1000.dtsi b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
index 49a70f8c3cab..b6aeb1f70e2a 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k1000.dtsi
@@ -100,6 +100,13 @@
#size-cells = <2>;
dma-coherent;
+ isa@18000000 {
+ compatible = "isa";
+ #size-cells = <1>;
+ #address-cells = <2>;
+ ranges = <1 0x0 0x0 0x18000000 0x4000>;
+ };
+
liointc0: interrupt-controller@1fe01400 {
compatible = "loongson,liointc-2.0";
reg = <0x0 0x1fe01400 0x0 0x40>,
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
index dca91caf895e..74b99bd234cc 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -61,12 +61,45 @@
&gmac0 {
status = "okay";
+
+ phy-mode = "gmii";
+ phy-handle = <&phy0>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy0: ethernet-phy@0 {
+ reg = <2>;
+ };
+ };
};
&gmac1 {
status = "okay";
+
+ phy-mode = "gmii";
+ phy-handle = <&phy1>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy1: ethernet-phy@1 {
+ reg = <2>;
+ };
+ };
};
&gmac2 {
status = "okay";
+
+ phy-mode = "rgmii";
+ phy-handle = <&phy2>;
+ mdio {
+ compatible = "snps,dwmac-mdio";
+ #address-cells = <1>;
+ #size-cells = <0>;
+ phy2: ethernet-phy@2 {
+ reg = <0>;
+ };
+ };
};
diff --git a/arch/loongarch/boot/dts/loongson-2k2000.dtsi b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
index a231949b5f55..9eab2d02cbe8 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000.dtsi
+++ b/arch/loongarch/boot/dts/loongson-2k2000.dtsi
@@ -51,6 +51,13 @@
#address-cells = <2>;
#size-cells = <2>;
+ isa@18400000 {
+ compatible = "isa";
+ #size-cells = <1>;
+ #address-cells = <2>;
+ ranges = <1 0x0 0x0 0x18400000 0x4000>;
+ };
+
pmc: power-management@100d0000 {
compatible = "loongson,ls2k2000-pmc", "loongson,ls2k0500-pmc", "syscon";
reg = <0x0 0x100d0000 0x0 0x58>;
@@ -109,6 +116,8 @@
msi: msi-controller@1fe01140 {
compatible = "loongson,pch-msi-1.0";
reg = <0x0 0x1fe01140 0x0 0x8>;
+ interrupt-controller;
+ #interrupt-cells = <1>;
msi-controller;
loongson,msi-base-vec = <64>;
loongson,msi-num-vecs = <192>;
@@ -140,27 +149,34 @@
#address-cells = <3>;
#size-cells = <2>;
device_type = "pci";
+ msi-parent = <&msi>;
bus-range = <0x0 0xff>;
- ranges = <0x01000000 0x0 0x00008000 0x0 0x18400000 0x0 0x00008000>,
+ ranges = <0x01000000 0x0 0x00008000 0x0 0x18408000 0x0 0x00008000>,
<0x02000000 0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>;
gmac0: ethernet@3,0 {
reg = <0x1800 0x0 0x0 0x0 0x0>;
- interrupts = <12 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
+ <13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
gmac1: ethernet@3,1 {
reg = <0x1900 0x0 0x0 0x0 0x0>;
- interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
+ <15 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
gmac2: ethernet@3,2 {
reg = <0x1a00 0x0 0x0 0x0 0x0>;
- interrupts = <17 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <17 IRQ_TYPE_LEVEL_HIGH>,
+ <18 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
interrupt-parent = <&pic>;
status = "disabled";
};
diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h
index b24437e28c6e..7bd47d65bf7a 100644
--- a/arch/loongarch/include/asm/addrspace.h
+++ b/arch/loongarch/include/asm/addrspace.h
@@ -11,6 +11,7 @@
#define _ASM_ADDRSPACE_H
#include <linux/const.h>
+#include <linux/sizes.h>
#include <asm/loongarch.h>
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 4a8adcca329b..c2f9979b2979 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -14,11 +14,6 @@
#include <asm/pgtable-bits.h>
#include <asm/string.h>
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page) ((phys_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
extern void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size);
extern void __init early_iounmap(void __iomem *addr, unsigned long size);
@@ -73,6 +68,21 @@ extern void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t
#define __io_aw() mmiowb()
+#ifdef CONFIG_KFENCE
+#define virt_to_phys(kaddr) \
+({ \
+ (likely((unsigned long)kaddr < vm_map_base)) ? __pa((unsigned long)kaddr) : \
+ page_to_phys(tlb_virt_to_page((unsigned long)kaddr)) + offset_in_page((unsigned long)kaddr);\
+})
+
+#define phys_to_virt(paddr) \
+({ \
+ extern char *__kfence_pool; \
+ (unlikely(__kfence_pool == NULL)) ? __va((unsigned long)paddr) : \
+ page_address(phys_to_page((unsigned long)paddr)) + offset_in_page((unsigned long)paddr);\
+})
+#endif
+
#include <asm-generic/io.h>
#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h
index 6c82aea1c993..a6a5760da3a3 100644
--- a/arch/loongarch/include/asm/kfence.h
+++ b/arch/loongarch/include/asm/kfence.h
@@ -16,6 +16,7 @@
static inline bool arch_kfence_init_pool(void)
{
int err;
+ char *kaddr, *vaddr;
char *kfence_pool = __kfence_pool;
struct vm_struct *area;
@@ -35,6 +36,14 @@ static inline bool arch_kfence_init_pool(void)
return false;
}
+ kaddr = kfence_pool;
+ vaddr = __kfence_pool;
+ while (kaddr < kfence_pool + KFENCE_POOL_SIZE) {
+ set_page_address(virt_to_page(kaddr), vaddr);
+ kaddr += PAGE_SIZE;
+ vaddr += PAGE_SIZE;
+ }
+
return true;
}
diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h
index 44027060c54a..e85df33f11c7 100644
--- a/arch/loongarch/include/asm/page.h
+++ b/arch/loongarch/include/asm/page.h
@@ -78,7 +78,26 @@ typedef struct { unsigned long pgprot; } pgprot_t;
struct page *dmw_virt_to_page(unsigned long kaddr);
struct page *tlb_virt_to_page(unsigned long kaddr);
-#define virt_to_pfn(kaddr) PFN_DOWN(PHYSADDR(kaddr))
+#define pfn_to_phys(pfn) __pfn_to_phys(pfn)
+#define phys_to_pfn(paddr) __phys_to_pfn(paddr)
+
+#define page_to_phys(page) pfn_to_phys(page_to_pfn(page))
+#define phys_to_page(paddr) pfn_to_page(phys_to_pfn(paddr))
+
+#ifndef CONFIG_KFENCE
+
+#define page_to_virt(page) __va(page_to_phys(page))
+#define virt_to_page(kaddr) phys_to_page(__pa(kaddr))
+
+#else
+
+#define WANT_PAGE_VIRTUAL
+
+#define page_to_virt(page) \
+({ \
+ extern char *__kfence_pool; \
+ (__kfence_pool == NULL) ? __va(page_to_phys(page)) : page_address(page); \
+})
#define virt_to_page(kaddr) \
({ \
@@ -86,6 +105,11 @@ struct page *tlb_virt_to_page(unsigned long kaddr);
dmw_virt_to_page((unsigned long)kaddr) : tlb_virt_to_page((unsigned long)kaddr);\
})
+#endif
+
+#define pfn_to_virt(pfn) page_to_virt(pfn_to_page(pfn))
+#define virt_to_pfn(kaddr) page_to_pfn(virt_to_page(kaddr))
+
extern int __virt_addr_valid(volatile void *kaddr);
#define virt_addr_valid(kaddr) __virt_addr_valid((volatile void *)(kaddr))
diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index a9630a81b38a..89af7c12e8c0 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -4,6 +4,7 @@
*/
#include <linux/export.h>
#include <linux/io.h>
+#include <linux/kfence.h>
#include <linux/memblock.h>
#include <linux/mm.h>
#include <linux/mman.h>
@@ -111,6 +112,9 @@ int __virt_addr_valid(volatile void *kaddr)
{
unsigned long vaddr = (unsigned long)kaddr;
+ if (is_kfence_address((void *)kaddr))
+ return 1;
+
if ((vaddr < PAGE_OFFSET) || (vaddr >= vm_map_base))
return 0;
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 2aae72e63871..bda018150000 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -11,13 +11,13 @@
struct page *dmw_virt_to_page(unsigned long kaddr)
{
- return pfn_to_page(virt_to_pfn(kaddr));
+ return phys_to_page(__pa(kaddr));
}
EXPORT_SYMBOL(dmw_virt_to_page);
struct page *tlb_virt_to_page(unsigned long kaddr)
{
- return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
+ return phys_to_page(pfn_to_phys(pte_pfn(*virt_to_kpte(kaddr))));
}
EXPORT_SYMBOL(tlb_virt_to_page);
diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c
index 8d98af5c7201..9a8393e6b4a8 100644
--- a/arch/nios2/kernel/prom.c
+++ b/arch/nios2/kernel/prom.c
@@ -21,7 +21,8 @@
void __init early_init_devtree(void *params)
{
- __be32 *dtb = (u32 *)__dtb_start;
+ __be32 __maybe_unused *dtb = (u32 *)__dtb_start;
+
#if defined(CONFIG_NIOS2_DTB_AT_PHYS_ADDR)
if (be32_to_cpup((__be32 *)CONFIG_NIOS2_DTB_PHYS_ADDR) ==
OF_DT_HEADER) {
@@ -30,8 +31,11 @@ void __init early_init_devtree(void *params)
return;
}
#endif
+
+#ifdef CONFIG_NIOS2_DTB_SOURCE_BOOL
if (be32_to_cpu((__be32) *dtb) == OF_DT_HEADER)
params = (void *)__dtb_start;
+#endif
early_init_dt_scan(params);
}
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index f0a4cf01e85c..78302f6c2580 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -4,7 +4,6 @@
#ifndef __ASSEMBLY__
-#include <asm/page.h>
#include <asm/vdso/timebase.h>
#include <asm/barrier.h>
#include <asm/unistd.h>
@@ -95,7 +94,7 @@ const struct vdso_data *__arch_get_vdso_data(void);
static __always_inline
const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd)
{
- return (void *)vd + PAGE_SIZE;
+ return (void *)vd + (1U << CONFIG_PAGE_SHIFT);
}
#endif
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 252d63942f34..5b3115a19852 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -151,7 +151,7 @@ endif
endif
vdso-install-y += arch/riscv/kernel/vdso/vdso.so.dbg
-vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg:../compat_vdso/compat_vdso.so
+vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg
ifneq ($(CONFIG_XIP_KERNEL),y)
ifeq ($(CONFIG_RISCV_M_MODE)$(CONFIG_ARCH_CANAAN),yy)
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 97fcde30e247..9f8ea0e33eb1 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -593,6 +593,12 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
return ptep_test_and_clear_young(vma, address, ptep);
}
+#define pgprot_nx pgprot_nx
+static inline pgprot_t pgprot_nx(pgprot_t _prot)
+{
+ return __pgprot(pgprot_val(_prot) & ~_PAGE_EXEC);
+}
+
#define pgprot_noncached pgprot_noncached
static inline pgprot_t pgprot_noncached(pgprot_t _prot)
{
diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h
index 980094c2e976..ac80216549ff 100644
--- a/arch/riscv/include/asm/syscall_wrapper.h
+++ b/arch/riscv/include/asm/syscall_wrapper.h
@@ -36,7 +36,8 @@ asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *);
ulong) \
__attribute__((alias(__stringify(___se_##prefix##name)))); \
__diag_pop(); \
- static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \
+ static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \
+ __used; \
static long ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__))
#define SC_RISCV_REGS_TO_ARGS(x, ...) \
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index ec0cab9fbddd..72ec1d9bd3f3 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -319,7 +319,7 @@ unsigned long __must_check clear_user(void __user *to, unsigned long n)
#define __get_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__get_user_nocheck(*((type *)(dst)), (type *)(src), __kr_err); \
if (unlikely(__kr_err)) \
@@ -328,7 +328,7 @@ do { \
#define __put_kernel_nofault(dst, src, type, err_label) \
do { \
- long __kr_err; \
+ long __kr_err = 0; \
\
__put_user_nocheck(*((type *)(src)), (type *)(dst), __kr_err); \
if (unlikely(__kr_err)) \
diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h
index 10aaa83db89e..95050ebe9ad0 100644
--- a/arch/riscv/include/uapi/asm/auxvec.h
+++ b/arch/riscv/include/uapi/asm/auxvec.h
@@ -34,7 +34,7 @@
#define AT_L3_CACHEGEOMETRY 47
/* entries in ARCH_DLINFO */
-#define AT_VECTOR_SIZE_ARCH 9
+#define AT_VECTOR_SIZE_ARCH 10
#define AT_MINSIGSTKSZ 51
#endif /* _UAPI_ASM_RISCV_AUXVEC_H */
diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile
index 62fa393b2eb2..3df4cb788c1f 100644
--- a/arch/riscv/kernel/compat_vdso/Makefile
+++ b/arch/riscv/kernel/compat_vdso/Makefile
@@ -74,5 +74,5 @@ quiet_cmd_compat_vdsold = VDSOLD $@
rm $@.tmp
# actual build commands
-quiet_cmd_compat_vdsoas = VDSOAS $@
+quiet_cmd_compat_vdsoas = VDSOAS $@
cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $<
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 37e87fdcf6a0..30e12b310cab 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
*/
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return 0;
}
NOKPROBE_SYMBOL(__patch_insn_set);
@@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (!riscv_patch_in_stop_machine)
lockdep_assert_held(&text_mutex);
+ preempt_disable();
+
if (across_pages)
patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
@@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
if (across_pages)
patch_unmap(FIX_TEXT_POKE1);
+ preempt_enable();
+
return ret;
}
NOKPROBE_SYMBOL(__patch_insn_write);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 92922dbd5b5c..e4bc61c4e58a 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -27,8 +27,6 @@
#include <asm/vector.h>
#include <asm/cpufeature.h>
-register unsigned long gp_in_global __asm__("gp");
-
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
@@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard);
extern asmlinkage void ret_from_fork(void);
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
{
cpu_do_idle();
}
@@ -207,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
if (unlikely(args->fn)) {
/* Kernel thread */
memset(childregs, 0, sizeof(struct pt_regs));
- childregs->gp = gp_in_global;
/* Supervisor/Machine, irqs on: */
childregs->status = SR_PP | SR_PIE;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 501e66debf69..5a2edd7f027e 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -119,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
struct __sc_riscv_v_state __user *state = sc_vec;
void __user *datap;
+ /*
+ * Mark the vstate as clean prior performing the actual copy,
+ * to avoid getting the vstate incorrectly clobbered by the
+ * discarded vector state.
+ */
+ riscv_v_vstate_set_restore(current, regs);
+
/* Copy everything of __sc_riscv_v_state except datap. */
err = __copy_from_user(&current->thread.vstate, &state->v_state,
offsetof(struct __riscv_v_ext_state, datap));
@@ -133,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
* Copy the whole vector content from user space datap. Use
* copy_from_user to prevent information leak.
*/
- err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
- if (unlikely(err))
- return err;
-
- riscv_v_vstate_set_restore(current, regs);
-
- return err;
+ return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
}
#else
#define save_v_state(task, regs) (0)
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 868d6280cf66..05a16b1f0aee 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -122,7 +122,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
pr_cont("\n");
__show_regs(regs);
- dump_instr(KERN_EMERG, regs);
+ dump_instr(KERN_INFO, regs);
}
force_sig_fault(signo, code, (void __user *)addr);
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9b517fe1b8a8..272c431ac5b9 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -37,6 +37,7 @@ endif
# Disable -pg to prevent insert call site
CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
# Disable profiling and instrumentation for VDSO code
GCOV_PROFILE := n
diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index 893566e004b7..07d743f87b3f 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -99,7 +99,7 @@ static void __ipi_flush_tlb_range_asid(void *info)
local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid);
}
-static void __flush_tlb_range(struct cpumask *cmask, unsigned long asid,
+static void __flush_tlb_range(const struct cpumask *cmask, unsigned long asid,
unsigned long start, unsigned long size,
unsigned long stride)
{
@@ -200,7 +200,7 @@ void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
void flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
- __flush_tlb_range((struct cpumask *)cpu_online_mask, FLUSH_TLB_NO_ASID,
+ __flush_tlb_range(cpu_online_mask, FLUSH_TLB_NO_ASID,
start, end - start, PAGE_SIZE);
}
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 7138d189cc42..0c4cad7d5a5b 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -15,31 +15,31 @@
#include <asm/barrier.h>
#include <asm/cmpxchg.h>
-static inline int arch_atomic_read(const atomic_t *v)
+static __always_inline int arch_atomic_read(const atomic_t *v)
{
return __atomic_read(v);
}
#define arch_atomic_read arch_atomic_read
-static inline void arch_atomic_set(atomic_t *v, int i)
+static __always_inline void arch_atomic_set(atomic_t *v, int i)
{
__atomic_set(v, i);
}
#define arch_atomic_set arch_atomic_set
-static inline int arch_atomic_add_return(int i, atomic_t *v)
+static __always_inline int arch_atomic_add_return(int i, atomic_t *v)
{
return __atomic_add_barrier(i, &v->counter) + i;
}
#define arch_atomic_add_return arch_atomic_add_return
-static inline int arch_atomic_fetch_add(int i, atomic_t *v)
+static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
{
return __atomic_add_barrier(i, &v->counter);
}
#define arch_atomic_fetch_add arch_atomic_fetch_add
-static inline void arch_atomic_add(int i, atomic_t *v)
+static __always_inline void arch_atomic_add(int i, atomic_t *v)
{
__atomic_add(i, &v->counter);
}
@@ -50,11 +50,11 @@ static inline void arch_atomic_add(int i, atomic_t *v)
#define arch_atomic_fetch_sub(_i, _v) arch_atomic_fetch_add(-(int)(_i), _v)
#define ATOMIC_OPS(op) \
-static inline void arch_atomic_##op(int i, atomic_t *v) \
+static __always_inline void arch_atomic_##op(int i, atomic_t *v) \
{ \
__atomic_##op(i, &v->counter); \
} \
-static inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
+static __always_inline int arch_atomic_fetch_##op(int i, atomic_t *v) \
{ \
return __atomic_##op##_barrier(i, &v->counter); \
}
@@ -74,7 +74,7 @@ ATOMIC_OPS(xor)
#define arch_atomic_xchg(v, new) (arch_xchg(&((v)->counter), new))
-static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
+static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
{
return __atomic_cmpxchg(&v->counter, old, new);
}
@@ -82,31 +82,31 @@ static inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new)
#define ATOMIC64_INIT(i) { (i) }
-static inline s64 arch_atomic64_read(const atomic64_t *v)
+static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
{
return __atomic64_read(v);
}
#define arch_atomic64_read arch_atomic64_read
-static inline void arch_atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i)
{
__atomic64_set(v, i);
}
#define arch_atomic64_set arch_atomic64_set
-static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
{
return __atomic64_add_barrier(i, (long *)&v->counter) + i;
}
#define arch_atomic64_add_return arch_atomic64_add_return
-static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
{
return __atomic64_add_barrier(i, (long *)&v->counter);
}
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
-static inline void arch_atomic64_add(s64 i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
{
__atomic64_add(i, (long *)&v->counter);
}
@@ -114,20 +114,20 @@ static inline void arch_atomic64_add(s64 i, atomic64_t *v)
#define arch_atomic64_xchg(v, new) (arch_xchg(&((v)->counter), new))
-static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
return __atomic64_cmpxchg((long *)&v->counter, old, new);
}
#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
-#define ATOMIC64_OPS(op) \
-static inline void arch_atomic64_##op(s64 i, atomic64_t *v) \
-{ \
- __atomic64_##op(i, (long *)&v->counter); \
-} \
-static inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \
-{ \
- return __atomic64_##op##_barrier(i, (long *)&v->counter); \
+#define ATOMIC64_OPS(op) \
+static __always_inline void arch_atomic64_##op(s64 i, atomic64_t *v) \
+{ \
+ __atomic64_##op(i, (long *)&v->counter); \
+} \
+static __always_inline long arch_atomic64_fetch_##op(s64 i, atomic64_t *v) \
+{ \
+ return __atomic64_##op##_barrier(i, (long *)&v->counter); \
}
ATOMIC64_OPS(and)
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index 50510e08b893..7fa5f96a553a 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -8,7 +8,7 @@
#ifndef __ARCH_S390_ATOMIC_OPS__
#define __ARCH_S390_ATOMIC_OPS__
-static inline int __atomic_read(const atomic_t *v)
+static __always_inline int __atomic_read(const atomic_t *v)
{
int c;
@@ -18,14 +18,14 @@ static inline int __atomic_read(const atomic_t *v)
return c;
}
-static inline void __atomic_set(atomic_t *v, int i)
+static __always_inline void __atomic_set(atomic_t *v, int i)
{
asm volatile(
" st %1,%0\n"
: "=R" (v->counter) : "d" (i));
}
-static inline s64 __atomic64_read(const atomic64_t *v)
+static __always_inline s64 __atomic64_read(const atomic64_t *v)
{
s64 c;
@@ -35,7 +35,7 @@ static inline s64 __atomic64_read(const atomic64_t *v)
return c;
}
-static inline void __atomic64_set(atomic64_t *v, s64 i)
+static __always_inline void __atomic64_set(atomic64_t *v, s64 i)
{
asm volatile(
" stg %1,%0\n"
@@ -45,7 +45,7 @@ static inline void __atomic64_set(atomic64_t *v, s64 i)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
#define __ATOMIC_OP(op_name, op_type, op_string, op_barrier) \
-static inline op_type op_name(op_type val, op_type *ptr) \
+static __always_inline op_type op_name(op_type val, op_type *ptr) \
{ \
op_type old; \
\
@@ -96,7 +96,7 @@ __ATOMIC_CONST_OPS(__atomic64_add_const, long, "agsi")
#else /* CONFIG_HAVE_MARCH_Z196_FEATURES */
#define __ATOMIC_OP(op_name, op_string) \
-static inline int op_name(int val, int *ptr) \
+static __always_inline int op_name(int val, int *ptr) \
{ \
int old, new; \
\
@@ -122,7 +122,7 @@ __ATOMIC_OPS(__atomic_xor, "xr")
#undef __ATOMIC_OPS
#define __ATOMIC64_OP(op_name, op_string) \
-static inline long op_name(long val, long *ptr) \
+static __always_inline long op_name(long val, long *ptr) \
{ \
long old, new; \
\
@@ -154,7 +154,7 @@ __ATOMIC64_OPS(__atomic64_xor, "xgr")
#endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
-static inline int __atomic_cmpxchg(int *ptr, int old, int new)
+static __always_inline int __atomic_cmpxchg(int *ptr, int old, int new)
{
asm volatile(
" cs %[old],%[new],%[ptr]"
@@ -164,7 +164,7 @@ static inline int __atomic_cmpxchg(int *ptr, int old, int new)
return old;
}
-static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
+static __always_inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
{
int old_expected = old;
@@ -176,7 +176,7 @@ static inline bool __atomic_cmpxchg_bool(int *ptr, int old, int new)
return old == old_expected;
}
-static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
+static __always_inline long __atomic64_cmpxchg(long *ptr, long old, long new)
{
asm volatile(
" csg %[old],%[new],%[ptr]"
@@ -186,7 +186,7 @@ static inline long __atomic64_cmpxchg(long *ptr, long old, long new)
return old;
}
-static inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new)
+static __always_inline bool __atomic64_cmpxchg_bool(long *ptr, long old, long new)
{
long old_expected = old;
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index bf15da0fedbc..0e3da500e98c 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -12,12 +12,12 @@
#define PREEMPT_NEED_RESCHED 0x80000000
#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED)
-static inline int preempt_count(void)
+static __always_inline int preempt_count(void)
{
return READ_ONCE(S390_lowcore.preempt_count) & ~PREEMPT_NEED_RESCHED;
}
-static inline void preempt_count_set(int pc)
+static __always_inline void preempt_count_set(int pc)
{
int old, new;
@@ -29,22 +29,22 @@ static inline void preempt_count_set(int pc)
old, new) != old);
}
-static inline void set_preempt_need_resched(void)
+static __always_inline void set_preempt_need_resched(void)
{
__atomic_and(~PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
}
-static inline void clear_preempt_need_resched(void)
+static __always_inline void clear_preempt_need_resched(void)
{
__atomic_or(PREEMPT_NEED_RESCHED, &S390_lowcore.preempt_count);
}
-static inline bool test_preempt_need_resched(void)
+static __always_inline bool test_preempt_need_resched(void)
{
return !(READ_ONCE(S390_lowcore.preempt_count) & PREEMPT_NEED_RESCHED);
}
-static inline void __preempt_count_add(int val)
+static __always_inline void __preempt_count_add(int val)
{
/*
* With some obscure config options and CONFIG_PROFILE_ALL_BRANCHES
@@ -59,17 +59,17 @@ static inline void __preempt_count_add(int val)
__atomic_add(val, &S390_lowcore.preempt_count);
}
-static inline void __preempt_count_sub(int val)
+static __always_inline void __preempt_count_sub(int val)
{
__preempt_count_add(-val);
}
-static inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool __preempt_count_dec_and_test(void)
{
return __atomic_add(-1, &S390_lowcore.preempt_count) == 1;
}
-static inline bool should_resched(int preempt_offset)
+static __always_inline bool should_resched(int preempt_offset)
{
return unlikely(READ_ONCE(S390_lowcore.preempt_count) ==
preempt_offset);
@@ -79,45 +79,45 @@ static inline bool should_resched(int preempt_offset)
#define PREEMPT_ENABLED (0)
-static inline int preempt_count(void)
+static __always_inline int preempt_count(void)
{
return READ_ONCE(S390_lowcore.preempt_count);
}
-static inline void preempt_count_set(int pc)
+static __always_inline void preempt_count_set(int pc)
{
S390_lowcore.preempt_count = pc;
}
-static inline void set_preempt_need_resched(void)
+static __always_inline void set_preempt_need_resched(void)
{
}
-static inline void clear_preempt_need_resched(void)
+static __always_inline void clear_preempt_need_resched(void)
{
}
-static inline bool test_preempt_need_resched(void)
+static __always_inline bool test_preempt_need_resched(void)
{
return false;
}
-static inline void __preempt_count_add(int val)
+static __always_inline void __preempt_count_add(int val)
{
S390_lowcore.preempt_count += val;
}
-static inline void __preempt_count_sub(int val)
+static __always_inline void __preempt_count_sub(int val)
{
S390_lowcore.preempt_count -= val;
}
-static inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool __preempt_count_dec_and_test(void)
{
return !--S390_lowcore.preempt_count && tif_need_resched();
}
-static inline bool should_resched(int preempt_offset)
+static __always_inline bool should_resched(int preempt_offset)
{
return unlikely(preempt_count() == preempt_offset &&
tif_need_resched());
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 787394978bc0..3dc85638bc63 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -635,6 +635,7 @@ SYM_DATA_START_LOCAL(daton_psw)
SYM_DATA_END(daton_psw)
.section .rodata, "a"
+ .balign 8
#define SYSCALL(esame,emu) .quad __s390x_ ## esame
SYM_DATA_START(sys_call_table)
#include "asm/syscall_table.h"
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 823d652e3917..4ad472d130a3 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -90,7 +90,6 @@ static void paicrypt_event_destroy(struct perf_event *event)
event->cpu);
struct paicrypt_map *cpump = mp->mapptr;
- cpump->event = NULL;
static_branch_dec(&pai_key);
mutex_lock(&pai_reserve_mutex);
debug_sprintf_event(cfm_dbg, 5, "%s event %#llx cpu %d users %d"
@@ -356,10 +355,15 @@ static int paicrypt_add(struct perf_event *event, int flags)
static void paicrypt_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paicrypt_mapptr *mp = this_cpu_ptr(paicrypt_root.mapptr);
+ struct paicrypt_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paicrypt_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index 616a25606cd6..a6da7e0cc7a6 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -122,7 +122,6 @@ static void paiext_event_destroy(struct perf_event *event)
free_page(PAI_SAVE_AREA(event));
mutex_lock(&paiext_reserve_mutex);
- cpump->event = NULL;
if (refcount_dec_and_test(&cpump->refcnt)) /* Last reference gone */
paiext_free(mp);
paiext_root_free();
@@ -362,10 +361,15 @@ static int paiext_add(struct perf_event *event, int flags)
static void paiext_stop(struct perf_event *event, int flags)
{
- if (!event->attr.sample_period) /* Counting */
+ struct paiext_mapptr *mp = this_cpu_ptr(paiext_root.mapptr);
+ struct paiext_map *cpump = mp->mapptr;
+
+ if (!event->attr.sample_period) { /* Counting */
paiext_read(event);
- else /* Sampling */
+ } else { /* Sampling */
perf_sched_cb_dec(event->pmu);
+ cpump->event = NULL;
+ }
event->hw.state = PERF_HES_STOPPED;
}
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index c421dd44ffbe..0c66b32e0f9f 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -75,7 +75,7 @@ static enum fault_type get_fault_type(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_PGSTE))
return KERNEL_FAULT;
gmap = (struct gmap *)S390_lowcore.gmap;
- if (regs->cr1 == gmap->asce)
+ if (gmap && gmap->asce == regs->cr1)
return GMAP_FAULT;
return KERNEL_FAULT;
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4fff6ed46e90..10a6251f58f3 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2633,6 +2633,32 @@ config MITIGATION_RFDS
stored in floating point, vector and integer registers.
See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
+choice
+ prompt "Clear branch history"
+ depends on CPU_SUP_INTEL
+ default SPECTRE_BHI_ON
+ help
+ Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
+ where the branch history buffer is poisoned to speculatively steer
+ indirect branches.
+ See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
+
+config SPECTRE_BHI_ON
+ bool "on"
+ help
+ Equivalent to setting spectre_bhi=on command line parameter.
+config SPECTRE_BHI_OFF
+ bool "off"
+ help
+ Equivalent to setting spectre_bhi=off command line parameter.
+config SPECTRE_BHI_AUTO
+ bool "auto"
+ depends on BROKEN
+ help
+ Equivalent to setting spectre_bhi=auto command line parameter.
+
+endchoice
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index d07be9d05cd0..b31ef2424d19 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -3,19 +3,28 @@
* Confidential Computing Platform Capability checks
*
* Copyright (C) 2021 Advanced Micro Devices, Inc.
+ * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
*
* Author: Tom Lendacky <thomas.lendacky@amd.com>
*/
#include <linux/export.h>
#include <linux/cc_platform.h>
+#include <linux/string.h>
+#include <linux/random.h>
+#include <asm/archrandom.h>
#include <asm/coco.h>
#include <asm/processor.h>
enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
u64 cc_mask __ro_after_init;
+static struct cc_attr_flags {
+ __u64 host_sev_snp : 1,
+ __resv : 63;
+} cc_flags;
+
static bool noinstr intel_cc_platform_has(enum cc_attr attr)
{
switch (attr) {
@@ -89,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr)
case CC_ATTR_GUEST_SEV_SNP:
return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
+ case CC_ATTR_HOST_SEV_SNP:
+ return cc_flags.host_sev_snp;
+
default:
return false;
}
@@ -148,3 +160,84 @@ u64 cc_mkdec(u64 val)
}
}
EXPORT_SYMBOL_GPL(cc_mkdec);
+
+static void amd_cc_platform_clear(enum cc_attr attr)
+{
+ switch (attr) {
+ case CC_ATTR_HOST_SEV_SNP:
+ cc_flags.host_sev_snp = 0;
+ break;
+ default:
+ break;
+ }
+}
+
+void cc_platform_clear(enum cc_attr attr)
+{
+ switch (cc_vendor) {
+ case CC_VENDOR_AMD:
+ amd_cc_platform_clear(attr);
+ break;
+ default:
+ break;
+ }
+}
+
+static void amd_cc_platform_set(enum cc_attr attr)
+{
+ switch (attr) {
+ case CC_ATTR_HOST_SEV_SNP:
+ cc_flags.host_sev_snp = 1;
+ break;
+ default:
+ break;
+ }
+}
+
+void cc_platform_set(enum cc_attr attr)
+{
+ switch (cc_vendor) {
+ case CC_VENDOR_AMD:
+ amd_cc_platform_set(attr);
+ break;
+ default:
+ break;
+ }
+}
+
+__init void cc_random_init(void)
+{
+ /*
+ * The seed is 32 bytes (in units of longs), which is 256 bits, which
+ * is the security level that the RNG is targeting.
+ */
+ unsigned long rng_seed[32 / sizeof(long)];
+ size_t i, longs;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ return;
+
+ /*
+ * Since the CoCo threat model includes the host, the only reliable
+ * source of entropy that can be neither observed nor manipulated is
+ * RDRAND. Usually, RDRAND failure is considered tolerable, but since
+ * CoCo guests have no other unobservable source of entropy, it's
+ * important to at least ensure the RNG gets some initial random seeds.
+ */
+ for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) {
+ longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i);
+
+ /*
+ * A zero return value means that the guest doesn't have RDRAND
+ * or the CPU is physically broken, and in both cases that
+ * means most crypto inside of the CoCo instance will be
+ * broken, defeating the purpose of CoCo in the first place. So
+ * just panic here because it's absolutely unsafe to continue
+ * executing.
+ */
+ if (longs == 0)
+ panic("RDRAND is defective.");
+ }
+ add_device_randomness(rng_seed, sizeof(rng_seed));
+ memzero_explicit(rng_seed, sizeof(rng_seed));
+}
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6356060caaf3..6de50b80702e 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
if (likely(unr < NR_syscalls)) {
unr = array_index_nospec(unr, NR_syscalls);
- regs->ax = sys_call_table[unr](regs);
+ regs->ax = x64_sys_call(regs, unr);
return true;
}
return false;
@@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
xnr = array_index_nospec(xnr, X32_NR_syscalls);
- regs->ax = x32_sys_call_table[xnr](regs);
+ regs->ax = x32_sys_call(regs, xnr);
return true;
}
return false;
@@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
if (likely(unr < IA32_NR_syscalls)) {
unr = array_index_nospec(unr, IA32_NR_syscalls);
- regs->ax = ia32_sys_call_table[unr](regs);
+ regs->ax = ia32_sys_call(regs, unr);
} else if (nr != -1) {
regs->ax = __ia32_sys_ni_syscall(regs);
}
@@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void)
}
/**
- * int80_emulation - 32-bit legacy syscall entry
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
*
* This entry point can be used by 32-bit and 64-bit programs to perform
* 32-bit system calls. Instances of INT $0x80 can be found inline in
@@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void)
* eax: system call number
* ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6
*/
-DEFINE_IDTENTRY_RAW(int80_emulation)
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
{
int nr;
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8af2a26b24f6..1b5be07f8669 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
/* clobbers %rax, make sure it is after saving the syscall nr */
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
call do_syscall_64 /* returns with IRQs disabled */
@@ -1491,3 +1492,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
call make_task_dead
SYM_CODE_END(rewind_stack_and_make_dead)
.popsection
+
+/*
+ * This sequence executes branches in order to remove user branch information
+ * from the branch history tracker in the Branch Predictor, therefore removing
+ * user influence on subsequent BTB lookups.
+ *
+ * It should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ *
+ * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
+ * and not clearing the branch history. The call tree looks like:
+ *
+ * call 1
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * call 2
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ * ret
+ *
+ * This means that the stack is non-constant and ORC can't unwind it with %rsp
+ * alone. Therefore we unconditionally set up the frame pointer, which allows
+ * ORC to unwind properly.
+ *
+ * The alignment is for performance and not for safety, and may be safely
+ * refactored in the future if needed.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+ push %rbp
+ mov %rsp, %rbp
+ movl $5, %ecx
+ ANNOTATE_INTRA_FUNCTION_CALL
+ call 1f
+ jmp 5f
+ .align 64, 0xcc
+ ANNOTATE_INTRA_FUNCTION_CALL
+1: call 2f
+ RET
+ .align 64, 0xcc
+2: movl $5, %eax
+3: jmp 4f
+ nop
+4: sub $1, %eax
+ jnz 3b
+ sub $1, %ecx
+ jnz 1b
+ RET
+5: lfence
+ pop %rbp
+ RET
+SYM_FUNC_END(clear_bhb_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_loop)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index eabf48c4d4b4..c779046cc3fe 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
/*
* SYSENTER doesn't filter flags, so we need to clear NT and AC
@@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
IBRS_ENTER
UNTRAIN_RET
+ CLEAR_BRANCH_HISTORY
movq %rsp, %rdi
call do_fast_syscall_32
@@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
ANNOTATE_NOENDBR
int3
SYM_CODE_END(entry_SYSCALL_compat)
+
+/*
+ * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries
+ * point to C routines, however since this is a system call interface the branch
+ * history needs to be scrubbed to protect against BHI attacks, and that
+ * scrubbing needs to take place in assembly code prior to entering any C
+ * routines.
+ */
+SYM_CODE_START(int80_emulation)
+ ANNOTATE_NOENDBR
+ UNWIND_HINT_FUNC
+ CLEAR_BRANCH_HISTORY
+ jmp do_int80_emulation
+SYM_CODE_END(int80_emulation)
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cfc9bc73e7f..c2235bae17ef 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
#include <asm/syscalls_32.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
#define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_32.h>
};
+#undef __SYSCALL
+#endif
+
+#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+
+long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_32.h>
+ default: return __ia32_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index be120eec1fc9..33b3f09e6f15 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
#include <asm/syscalls_64.h>
#undef __SYSCALL
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
#define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
#include <asm/syscalls_64.h>
};
+#undef __SYSCALL
+
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+
+long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_64.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
+};
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index bdd0e03a1265..03de4a932131 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
#include <asm/syscalls_x32.h>
#undef __SYSCALL
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+ switch (nr) {
+ #include <asm/syscalls_x32.h>
+ default: return __x64_sys_ni_syscall(regs);
+ }
};
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 2641ba620f12..e010bfed8417 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1237,11 +1237,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
struct pmu *pmu = event->pmu;
/*
- * Make sure we get updated with the first PEBS
- * event. It will trigger also during removal, but
- * that does not hurt:
+ * Make sure we get updated with the first PEBS event.
+ * During removal, ->pebs_data_cfg is still valid for
+ * the last PEBS event. Don't clear it.
*/
- if (cpuc->n_pebs == 1)
+ if ((cpuc->n_pebs == 1) && add)
cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW;
if (needed_cb != pebs_needs_sched_cb(cpuc)) {
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index fb7388bbc212..c086699b0d0c 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -22,6 +22,7 @@ static inline void cc_set_mask(u64 mask)
u64 cc_mkenc(u64 val);
u64 cc_mkdec(u64 val);
+void cc_random_init(void);
#else
#define cc_vendor (CC_VENDOR_NONE)
@@ -34,6 +35,7 @@ static inline u64 cc_mkdec(u64 val)
{
return val;
}
+static inline void cc_random_init(void) { }
#endif
#endif /* _ASM_X86_COCO_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 42157ddcc09d..686e92d2663e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -33,6 +33,8 @@ enum cpuid_leafs
CPUID_7_EDX,
CPUID_8000_001F_EAX,
CPUID_8000_0021_EAX,
+ CPUID_LNX_5,
+ NR_CPUID_WORDS,
};
#define X86_CAP_FMT_NUM "%d:%d"
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index a38f8f9ba657..3c7434329661 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -461,11 +461,15 @@
/*
* Extended auxiliary flags: Linux defined - for features scattered in various
- * CPUID levels like 0x80000022, etc.
+ * CPUID levels like 0x80000022, etc and Linux defined features.
*
* Reuse free bits when adding new feature flags!
*/
#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
/*
* BUG word(s)
@@ -515,4 +519,5 @@
#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 05956bd8bacf..e72c2b872957 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,10 +61,13 @@
#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */
#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */
#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
/* A mask for bits which the kernel toggles when controlling mitigations */
#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
- | SPEC_CTRL_RRSBA_DIS_S)
+ | SPEC_CTRL_RRSBA_DIS_S \
+ | SPEC_CTRL_BHI_DIS_S)
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
@@ -163,6 +166,10 @@
* are restricted to targets in
* kernel.
*/
+#define ARCH_CAP_BHI_NO BIT(20) /*
+ * CPU is not affected by Branch
+ * History Injection.
+ */
#define ARCH_CAP_PBRSB_NO BIT(24) /*
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 170c89ed22fc..ff5f1ecc7d1e 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -326,6 +326,19 @@
ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF
.endm
+#ifdef CONFIG_X86_64
+.macro CLEAR_BRANCH_HISTORY
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
+.endm
+
+.macro CLEAR_BRANCH_HISTORY_VMEXIT
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+.endm
+#else
+#define CLEAR_BRANCH_HISTORY
+#define CLEAR_BRANCH_HISTORY_VMEXIT
+#endif
+
#else /* __ASSEMBLY__ */
#define ANNOTATE_RETPOLINE_SAFE \
@@ -368,6 +381,10 @@ extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
+#ifdef CONFIG_X86_64
+extern void clear_bhb_loop(void);
+#endif
+
extern void (*x86_return_thunk)(void);
extern void __warn_thunk(void);
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 07e125f32528..7f57382afee4 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -228,7 +228,6 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 snp_get_unsupported_features(u64 status);
u64 sev_get_status(void);
-void kdump_sev_callback(void);
void sev_show_status(void);
#else
static inline void sev_es_ist_enter(struct pt_regs *regs) { }
@@ -258,7 +257,6 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
static inline u64 snp_get_unsupported_features(u64 status) { return 0; }
static inline u64 sev_get_status(void) { return 0; }
-static inline void kdump_sev_callback(void) { }
static inline void sev_show_status(void) { }
#endif
@@ -270,6 +268,7 @@ int psmash(u64 pfn);
int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable);
int rmp_make_shared(u64 pfn, enum pg_level level);
void snp_leak_pages(u64 pfn, unsigned int npages);
+void kdump_sev_callback(void);
#else
static inline bool snp_probe_rmptable_info(void) { return false; }
static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
@@ -282,6 +281,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as
}
static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
+static inline void kdump_sev_callback(void) { }
#endif
#endif
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index f44e2f9ab65d..2fc7bc3863ff 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,19 +16,17 @@
#include <asm/thread_info.h> /* for TS_COMPAT */
#include <asm/unistd.h>
+/* This is used purely for kernel/trace/trace_syscalls.c */
typedef long (*sys_call_ptr_t)(const struct pt_regs *);
extern const sys_call_ptr_t sys_call_table[];
-#if defined(CONFIG_X86_32)
-#define ia32_sys_call_table sys_call_table
-#else
/*
* These may not exist, but still put the prototypes in so we
* can use IS_ENABLED().
*/
-extern const sys_call_ptr_t ia32_sys_call_table[];
-extern const sys_call_ptr_t x32_sys_call_table[];
-#endif
+extern long ia32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x32_sys_call(const struct pt_regs *, unsigned int nr);
+extern long x64_sys_call(const struct pt_regs *, unsigned int nr);
/*
* Only the low 32 bits of orig_ax are meaningful, so we return int.
@@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task)
}
bool do_syscall_64(struct pt_regs *regs, int nr);
+void do_int80_emulation(struct pt_regs *regs);
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 6d8677e80ddb..9bf17c9c29da 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -345,6 +345,28 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#endif
}
+static void bsp_determine_snp(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
+ cc_vendor = CC_VENDOR_AMD;
+
+ if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
+ /*
+ * RMP table entry format is not architectural and is defined by the
+ * per-processor PPR. Restrict SNP support on the known CPU models
+ * for which the RMP table entry format is currently defined for.
+ */
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+ c->x86 >= 0x19 && snp_probe_rmptable_info()) {
+ cc_platform_set(CC_ATTR_HOST_SEV_SNP);
+ } else {
+ setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
+ }
+ }
+#endif
+}
+
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -452,21 +474,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
break;
}
- if (cpu_has(c, X86_FEATURE_SEV_SNP)) {
- /*
- * RMP table entry format is not architectural and it can vary by processor
- * and is defined by the per-processor PPR. Restrict SNP support on the
- * known CPU model and family for which the RMP table entry format is
- * currently defined for.
- */
- if (!boot_cpu_has(X86_FEATURE_ZEN3) &&
- !boot_cpu_has(X86_FEATURE_ZEN4) &&
- !boot_cpu_has(X86_FEATURE_ZEN5))
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
- else if (!snp_probe_rmptable_info())
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
- }
-
+ bsp_determine_snp(c);
return;
warn:
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index e7ba936d798b..295463707e68 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -1607,6 +1607,79 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_
dump_stack();
}
+/*
+ * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by
+ * branch history in userspace. Not needed if BHI_NO is set.
+ */
+static bool __init spec_ctrl_bhi_dis(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_BHI_CTRL))
+ return false;
+
+ x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S;
+ update_spec_ctrl(x86_spec_ctrl_base);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW);
+
+ return true;
+}
+
+enum bhi_mitigations {
+ BHI_MITIGATION_OFF,
+ BHI_MITIGATION_ON,
+ BHI_MITIGATION_AUTO,
+};
+
+static enum bhi_mitigations bhi_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_SPECTRE_BHI_ON) ? BHI_MITIGATION_ON :
+ IS_ENABLED(CONFIG_SPECTRE_BHI_OFF) ? BHI_MITIGATION_OFF :
+ BHI_MITIGATION_AUTO;
+
+static int __init spectre_bhi_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ bhi_mitigation = BHI_MITIGATION_OFF;
+ else if (!strcmp(str, "on"))
+ bhi_mitigation = BHI_MITIGATION_ON;
+ else if (!strcmp(str, "auto"))
+ bhi_mitigation = BHI_MITIGATION_AUTO;
+ else
+ pr_err("Ignoring unknown spectre_bhi option (%s)", str);
+
+ return 0;
+}
+early_param("spectre_bhi", spectre_bhi_parse_cmdline);
+
+static void __init bhi_select_mitigation(void)
+{
+ if (bhi_mitigation == BHI_MITIGATION_OFF)
+ return;
+
+ /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
+ if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
+ !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+ return;
+
+ if (spec_ctrl_bhi_dis())
+ return;
+
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ /* Mitigate KVM by default */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n");
+
+ if (bhi_mitigation == BHI_MITIGATION_AUTO)
+ return;
+
+ /* Mitigate syscalls when the mitigation is forced =on */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
+ pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n");
+}
+
static void __init spectre_v2_select_mitigation(void)
{
enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -1718,6 +1791,9 @@ static void __init spectre_v2_select_mitigation(void)
mode == SPECTRE_V2_RETPOLINE)
spec_ctrl_disable_kernel_rrsba();
+ if (boot_cpu_has(X86_BUG_BHI))
+ bhi_select_mitigation();
+
spectre_v2_enabled = mode;
pr_info("%s\n", spectre_v2_strings[mode]);
@@ -2695,15 +2771,15 @@ static char *stibp_state(void)
switch (spectre_v2_user_stibp) {
case SPECTRE_V2_USER_NONE:
- return ", STIBP: disabled";
+ return "; STIBP: disabled";
case SPECTRE_V2_USER_STRICT:
- return ", STIBP: forced";
+ return "; STIBP: forced";
case SPECTRE_V2_USER_STRICT_PREFERRED:
- return ", STIBP: always-on";
+ return "; STIBP: always-on";
case SPECTRE_V2_USER_PRCTL:
case SPECTRE_V2_USER_SECCOMP:
if (static_key_enabled(&switch_to_cond_stibp))
- return ", STIBP: conditional";
+ return "; STIBP: conditional";
}
return "";
}
@@ -2712,10 +2788,10 @@ static char *ibpb_state(void)
{
if (boot_cpu_has(X86_FEATURE_IBPB)) {
if (static_key_enabled(&switch_mm_always_ibpb))
- return ", IBPB: always-on";
+ return "; IBPB: always-on";
if (static_key_enabled(&switch_mm_cond_ibpb))
- return ", IBPB: conditional";
- return ", IBPB: disabled";
+ return "; IBPB: conditional";
+ return "; IBPB: disabled";
}
return "";
}
@@ -2725,14 +2801,31 @@ static char *pbrsb_eibrs_state(void)
if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) {
if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) ||
boot_cpu_has(X86_FEATURE_RSB_VMEXIT))
- return ", PBRSB-eIBRS: SW sequence";
+ return "; PBRSB-eIBRS: SW sequence";
else
- return ", PBRSB-eIBRS: Vulnerable";
+ return "; PBRSB-eIBRS: Vulnerable";
} else {
- return ", PBRSB-eIBRS: Not affected";
+ return "; PBRSB-eIBRS: Not affected";
}
}
+static const char * const spectre_bhi_state(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_BHI))
+ return "; BHI: Not affected";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW))
+ return "; BHI: BHI_DIS_S";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
+ return "; BHI: SW loop, KVM: SW loop";
+ else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
+ !(x86_read_arch_cap_msr() & ARCH_CAP_RRSBA))
+ return "; BHI: Retpoline";
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+ return "; BHI: Syscall hardening, KVM: SW loop";
+
+ return "; BHI: Vulnerable (Syscall hardening enabled)";
+}
+
static ssize_t spectre_v2_show_state(char *buf)
{
if (spectre_v2_enabled == SPECTRE_V2_LFENCE)
@@ -2745,13 +2838,15 @@ static ssize_t spectre_v2_show_state(char *buf)
spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE)
return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n");
- return sysfs_emit(buf, "%s%s%s%s%s%s%s\n",
+ return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n",
spectre_v2_strings[spectre_v2_enabled],
ibpb_state(),
- boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "",
+ boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "",
stibp_state(),
- boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "",
+ boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "",
pbrsb_eibrs_state(),
+ spectre_bhi_state(),
+ /* this should always be at the end */
spectre_v2_module_string());
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5c1e6d6be267..754d91857d63 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1120,6 +1120,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
#define NO_SPECTRE_V2 BIT(8)
#define NO_MMIO BIT(9)
#define NO_EIBRS_PBRSB BIT(10)
+#define NO_BHI BIT(11)
#define VULNWL(vendor, family, model, whitelist) \
X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist)
@@ -1182,18 +1183,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB),
/* AMD Family 0xf - 0x12 */
- VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
- VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
+ VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
+ VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI),
/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
- VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
- VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB),
+ VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
+ VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI),
/* Zhaoxin Family 7 */
- VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
- VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO),
+ VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
+ VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI),
{}
};
@@ -1435,6 +1436,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (vulnerable_to_rfds(ia32_cap))
setup_force_cpu_bug(X86_BUG_RFDS);
+ /* When virtualized, eIBRS could be hidden, assume vulnerable */
+ if (!(ia32_cap & ARCH_CAP_BHI_NO) &&
+ !cpu_matches(cpu_vuln_whitelist, NO_BHI) &&
+ (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) ||
+ boot_cpu_has(X86_FEATURE_HYPERVISOR)))
+ setup_force_cpu_bug(X86_BUG_BHI);
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b5cc557cfc37..84d41be6d06b 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2500,12 +2500,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr,
return -EINVAL;
b = &per_cpu(mce_banks_array, s->id)[bank];
-
if (!b->init)
return -ENODEV;
b->ctl = new;
+
+ mutex_lock(&mce_sysfs_mutex);
mce_restart();
+ mutex_unlock(&mce_sysfs_mutex);
return size;
}
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 422a4ddc2ab7..7b29ebda024f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -108,7 +108,7 @@ static inline void k8_check_syscfg_dram_mod_en(void)
(boot_cpu_data.x86 >= 0x0f)))
return;
- if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return;
rdmsr(MSR_AMD64_SYSCFG, lo, hi);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index c99f26ebe7a6..1a8687f8073a 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -78,7 +78,8 @@ cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
else
cpu = cpumask_any_but(mask, exclude_cpu);
- if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+ /* Only continue if tick_nohz_full_mask has been initialized. */
+ if (!tick_nohz_full_enabled())
return cpu;
/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index a515328d9d7d..af5aa2c754c2 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 },
{ X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 },
+ { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 },
{ X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
{ X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 },
{ X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0109e6c510e0..e125e059e2c4 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -35,6 +35,7 @@
#include <asm/bios_ebda.h>
#include <asm/bugs.h>
#include <asm/cacheinfo.h>
+#include <asm/coco.h>
#include <asm/cpu.h>
#include <asm/efi.h>
#include <asm/gart.h>
@@ -991,6 +992,7 @@ void __init setup_arch(char **cmdline_p)
* memory size.
*/
mem_encrypt_setup_arch();
+ cc_random_init();
efi_fake_memmap();
efi_find_mirror();
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 7e1e63cc48e6..38ad066179d8 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -2284,16 +2284,6 @@ static int __init snp_init_platform_device(void)
}
device_initcall(snp_init_platform_device);
-void kdump_sev_callback(void)
-{
- /*
- * Do wbinvd() on remote CPUs when SNP is enabled in order to
- * safely do SNP_SHUTDOWN on the local CPU.
- */
- if (cpu_feature_enabled(X86_FEATURE_SEV_SNP))
- wbinvd();
-}
-
void sev_show_status(void)
{
int i;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3aaf7e86a859..0ebdd088f28b 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -122,6 +122,7 @@ config KVM_AMD_SEV
default y
depends on KVM_AMD && X86_64
depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
+ select ARCH_HAS_CC_PLATFORM
help
Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
with Encrypted State (SEV-ES) on AMD processors.
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index aadefcaa9561..2f4e155080ba 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs {
#define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1)
#define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2)
#define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3)
-#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
+#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4)
#define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5)
/* CPUID level 0x80000007 (EDX). */
@@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = {
*/
static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
{
+ BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
+ BUILD_BUG_ON(x86_leaf == CPUID_LNX_5);
BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
}
@@ -126,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC);
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index e5a4d9b0e79f..61a7531d41b0 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -3184,7 +3184,7 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu)
unsigned long pfn;
struct page *p;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
/*
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 2bfbf758d061..f6986dee6f8c 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL)
call vmx_spec_ctrl_restore_host
+ CLEAR_BRANCH_HISTORY_VMEXIT
+
/* Put return value in AX */
mov %_ASM_BX, %_ASM_AX
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 47d9f03b7778..984ea2089efc 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1621,7 +1621,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr)
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \
- ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR)
+ ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO)
static u64 kvm_get_arch_capabilities(void)
{
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 0795b3464058..e674ccf720b9 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -229,6 +229,7 @@ SYM_CODE_END(srso_return_thunk)
/* Dummy for the alternative in CALL_UNTRAIN_RET. */
SYM_CODE_START(srso_alias_untrain_ret)
ANNOTATE_UNRET_SAFE
+ ANNOTATE_NOENDBR
ret
int3
SYM_FUNC_END(srso_alias_untrain_ret)
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 104544359d69..025fd7ea5d69 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -24,6 +24,7 @@
#include <linux/memblock.h>
#include <linux/init.h>
+#include <asm/pgtable_areas.h>
#include "numa_internal.h"
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0d72183b5dd0..36b603d0cdde 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -947,6 +947,38 @@ static void free_pfn_range(u64 paddr, unsigned long size)
memtype_free(paddr, paddr + size);
}
+static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
+ pgprot_t *pgprot)
+{
+ unsigned long prot;
+
+ VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
+
+ /*
+ * We need the starting PFN and cachemode used for track_pfn_remap()
+ * that covered the whole VMA. For most mappings, we can obtain that
+ * information from the page tables. For COW mappings, we might now
+ * suddenly have anon folios mapped and follow_phys() will fail.
+ *
+ * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
+ * detect the PFN. If we need the cachemode as well, we're out of luck
+ * for now and have to fail fork().
+ */
+ if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) {
+ if (pgprot)
+ *pgprot = __pgprot(prot);
+ return 0;
+ }
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (pgprot)
+ return -EINVAL;
+ *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+}
+
/*
* track_pfn_copy is called when vma that is covering the pfnmap gets
* copied through copy_page_range().
@@ -957,20 +989,13 @@ static void free_pfn_range(u64 paddr, unsigned long size)
int track_pfn_copy(struct vm_area_struct *vma)
{
resource_size_t paddr;
- unsigned long prot;
unsigned long vma_size = vma->vm_end - vma->vm_start;
pgprot_t pgprot;
if (vma->vm_flags & VM_PAT) {
- /*
- * reserve the whole chunk covered by vma. We need the
- * starting address and protection from pte.
- */
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, &pgprot))
return -EINVAL;
- }
- pgprot = __pgprot(prot);
+ /* reserve the whole chunk covered by vma. */
return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
}
@@ -1045,7 +1070,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size, bool mm_wr_locked)
{
resource_size_t paddr;
- unsigned long prot;
if (vma && !(vma->vm_flags & VM_PAT))
return;
@@ -1053,11 +1077,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
/* free the chunk starting from pfn or the whole chunk */
paddr = (resource_size_t)pfn << PAGE_SHIFT;
if (!paddr && !size) {
- if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
- WARN_ON_ONCE(1);
+ if (get_pat_info(vma, &paddr, NULL))
return;
- }
-
size = vma->vm_end - vma->vm_start;
}
free_pfn_range(paddr, size);
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index cffe1157a90a..ab0e8448bb6e 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -77,7 +77,7 @@ static int __mfd_enable(unsigned int cpu)
{
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
rdmsrl(MSR_AMD64_SYSCFG, val);
@@ -98,7 +98,7 @@ static int __snp_enable(unsigned int cpu)
{
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
rdmsrl(MSR_AMD64_SYSCFG, val);
@@ -174,11 +174,11 @@ static int __init snp_rmptable_init(void)
u64 rmptable_size;
u64 val;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
if (!amd_iommu_snp_en)
- return 0;
+ goto nosnp;
if (!probed_rmp_size)
goto nosnp;
@@ -225,7 +225,7 @@ skip_enable:
return 0;
nosnp:
- setup_clear_cpu_cap(X86_FEATURE_SEV_SNP);
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
return -ENOSYS;
}
@@ -246,7 +246,7 @@ static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level)
{
struct rmpentry *large_entry, *entry;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return ERR_PTR(-ENODEV);
entry = get_rmpentry(pfn);
@@ -363,7 +363,7 @@ int psmash(u64 pfn)
unsigned long paddr = pfn << PAGE_SHIFT;
int ret;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return -ENODEV;
if (!pfn_valid(pfn))
@@ -472,7 +472,7 @@ static int rmpupdate(u64 pfn, struct rmp_state *state)
unsigned long paddr = pfn << PAGE_SHIFT;
int ret, level;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return -ENODEV;
level = RMP_TO_PG_LEVEL(state->pagesize);
@@ -558,3 +558,13 @@ void snp_leak_pages(u64 pfn, unsigned int npages)
spin_unlock(&snp_leaked_pages_list_lock);
}
EXPORT_SYMBOL_GPL(snp_leak_pages);
+
+void kdump_sev_callback(void)
+{
+ /*
+ * Do wbinvd() on remote CPUs when SNP is enabled in order to
+ * safely do SNP_SHUTDOWN on the local CPU.
+ */
+ if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+ wbinvd();
+}
diff --git a/block/bdev.c b/block/bdev.c
index 7a5f611c3d2e..b8e32d933a63 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -583,9 +583,6 @@ static void bd_finish_claiming(struct block_device *bdev, void *holder,
mutex_unlock(&bdev->bd_holder_lock);
bd_clear_claiming(whole, holder);
mutex_unlock(&bdev_lock);
-
- if (hops && hops->get_holder)
- hops->get_holder(holder);
}
/**
@@ -608,7 +605,6 @@ EXPORT_SYMBOL(bd_abort_claiming);
static void bd_end_claim(struct block_device *bdev, void *holder)
{
struct block_device *whole = bdev_whole(bdev);
- const struct blk_holder_ops *hops = bdev->bd_holder_ops;
bool unblock = false;
/*
@@ -631,9 +627,6 @@ static void bd_end_claim(struct block_device *bdev, void *holder)
whole->bd_holder = NULL;
mutex_unlock(&bdev_lock);
- if (hops && hops->put_holder)
- hops->put_holder(holder);
-
/*
* If this was the last claim, remove holder link and unblock evpoll if
* it was a write holder.
@@ -776,17 +769,17 @@ void blkdev_put_no_open(struct block_device *bdev)
static bool bdev_writes_blocked(struct block_device *bdev)
{
- return bdev->bd_writers == -1;
+ return bdev->bd_writers < 0;
}
static void bdev_block_writes(struct block_device *bdev)
{
- bdev->bd_writers = -1;
+ bdev->bd_writers--;
}
static void bdev_unblock_writes(struct block_device *bdev)
{
- bdev->bd_writers = 0;
+ bdev->bd_writers++;
}
static bool bdev_may_open(struct block_device *bdev, blk_mode_t mode)
@@ -813,6 +806,11 @@ static void bdev_claim_write_access(struct block_device *bdev, blk_mode_t mode)
bdev->bd_writers++;
}
+static inline bool bdev_unclaimed(const struct file *bdev_file)
+{
+ return bdev_file->private_data == BDEV_I(bdev_file->f_mapping->host);
+}
+
static void bdev_yield_write_access(struct file *bdev_file)
{
struct block_device *bdev;
@@ -820,14 +818,15 @@ static void bdev_yield_write_access(struct file *bdev_file)
if (bdev_allow_write_mounted)
return;
+ if (bdev_unclaimed(bdev_file))
+ return;
+
bdev = file_bdev(bdev_file);
- /* Yield exclusive or shared write access. */
- if (bdev_file->f_mode & FMODE_WRITE) {
- if (bdev_writes_blocked(bdev))
- bdev_unblock_writes(bdev);
- else
- bdev->bd_writers--;
- }
+
+ if (bdev_file->f_mode & FMODE_WRITE_RESTRICTED)
+ bdev_unblock_writes(bdev);
+ else if (bdev_file->f_mode & FMODE_WRITE)
+ bdev->bd_writers--;
}
/**
@@ -907,6 +906,8 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
bdev_file->f_mode |= FMODE_BUF_RASYNC | FMODE_CAN_ODIRECT;
if (bdev_nowait(bdev))
bdev_file->f_mode |= FMODE_NOWAIT;
+ if (mode & BLK_OPEN_RESTRICT_WRITES)
+ bdev_file->f_mode |= FMODE_WRITE_RESTRICTED;
bdev_file->f_mapping = bdev->bd_inode->i_mapping;
bdev_file->f_wb_err = filemap_sample_wb_err(bdev_file->f_mapping);
bdev_file->private_data = holder;
@@ -1012,6 +1013,20 @@ struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
}
EXPORT_SYMBOL(bdev_file_open_by_path);
+static inline void bd_yield_claim(struct file *bdev_file)
+{
+ struct block_device *bdev = file_bdev(bdev_file);
+ void *holder = bdev_file->private_data;
+
+ lockdep_assert_held(&bdev->bd_disk->open_mutex);
+
+ if (WARN_ON_ONCE(IS_ERR_OR_NULL(holder)))
+ return;
+
+ if (!bdev_unclaimed(bdev_file))
+ bd_end_claim(bdev, holder);
+}
+
void bdev_release(struct file *bdev_file)
{
struct block_device *bdev = file_bdev(bdev_file);
@@ -1036,7 +1051,7 @@ void bdev_release(struct file *bdev_file)
bdev_yield_write_access(bdev_file);
if (holder)
- bd_end_claim(bdev, holder);
+ bd_yield_claim(bdev_file);
/*
* Trigger event checking and tell drivers to flush MEDIA_CHANGE
@@ -1057,6 +1072,39 @@ put_no_open:
}
/**
+ * bdev_fput - yield claim to the block device and put the file
+ * @bdev_file: open block device
+ *
+ * Yield claim on the block device and put the file. Ensure that the
+ * block device can be reclaimed before the file is closed which is a
+ * deferred operation.
+ */
+void bdev_fput(struct file *bdev_file)
+{
+ if (WARN_ON_ONCE(bdev_file->f_op != &def_blk_fops))
+ return;
+
+ if (bdev_file->private_data) {
+ struct block_device *bdev = file_bdev(bdev_file);
+ struct gendisk *disk = bdev->bd_disk;
+
+ mutex_lock(&disk->open_mutex);
+ bdev_yield_write_access(bdev_file);
+ bd_yield_claim(bdev_file);
+ /*
+ * Tell release we already gave up our hold on the
+ * device and if write restrictions are available that
+ * we already gave up write access to the device.
+ */
+ bdev_file->private_data = BDEV_I(bdev_file->f_mapping->host);
+ mutex_unlock(&disk->open_mutex);
+ }
+
+ fput(bdev_file);
+}
+EXPORT_SYMBOL(bdev_fput);
+
+/**
* lookup_bdev() - Look up a struct block_device by name.
* @pathname: Name of the block device in the filesystem.
* @dev: Pointer to the block device's dev_t, if found.
diff --git a/block/ioctl.c b/block/ioctl.c
index 0c76137adcaa..a9028a2c2db5 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -96,7 +96,7 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
unsigned long arg)
{
uint64_t range[2];
- uint64_t start, len;
+ uint64_t start, len, end;
struct inode *inode = bdev->bd_inode;
int err;
@@ -117,7 +117,8 @@ static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode,
if (len & 511)
return -EINVAL;
- if (start + len > bdev_nr_bytes(bdev))
+ if (check_add_overflow(start, len, &end) ||
+ end > bdev_nr_bytes(bdev))
return -EINVAL;
filemap_invalidate_lock(inode->i_mapping);
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 302dce0b2b50..d67881b50bca 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -662,14 +662,15 @@ static int acpi_thermal_register_thermal_zone(struct acpi_thermal *tz,
{
int result;
- tz->thermal_zone = thermal_zone_device_register_with_trips("acpitz",
- trip_table,
- trip_count,
- tz,
- &acpi_thermal_zone_ops,
- NULL,
- passive_delay,
- tz->polling_frequency * 100);
+ if (trip_count)
+ tz->thermal_zone = thermal_zone_device_register_with_trips(
+ "acpitz", trip_table, trip_count, tz,
+ &acpi_thermal_zone_ops, NULL, passive_delay,
+ tz->polling_frequency * 100);
+ else
+ tz->thermal_zone = thermal_tripless_zone_device_register(
+ "acpitz", tz, &acpi_thermal_zone_ops, NULL);
+
if (IS_ERR(tz->thermal_zone))
return PTR_ERR(tz->thermal_zone);
@@ -901,11 +902,8 @@ static int acpi_thermal_add(struct acpi_device *device)
trip++;
}
- if (trip == trip_table) {
+ if (trip == trip_table)
pr_warn(FW_BUG "No valid trip points!\n");
- result = -ENODEV;
- goto free_memory;
- }
result = acpi_thermal_register_thermal_zone(tz, trip_table,
trip - trip_table,
diff --git a/drivers/ata/ahci_st.c b/drivers/ata/ahci_st.c
index d4a626f87963..79a8b0aa37bf 100644
--- a/drivers/ata/ahci_st.c
+++ b/drivers/ata/ahci_st.c
@@ -30,7 +30,6 @@
#define ST_AHCI_OOBR_CIMAX_SHIFT 0
struct st_ahci_drv_data {
- struct platform_device *ahci;
struct reset_control *pwr;
struct reset_control *sw_rst;
struct reset_control *pwr_rst;
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index 4ac854f6b057..88b2e9817f49 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1371,9 +1371,6 @@ static struct pci_driver pata_macio_pci_driver = {
.suspend = pata_macio_pci_suspend,
.resume = pata_macio_pci_resume,
#endif
- .driver = {
- .owner = THIS_MODULE,
- },
};
MODULE_DEVICE_TABLE(pci, pata_macio_pci_match);
diff --git a/drivers/ata/sata_gemini.c b/drivers/ata/sata_gemini.c
index 400b22ee99c3..4c270999ba3c 100644
--- a/drivers/ata/sata_gemini.c
+++ b/drivers/ata/sata_gemini.c
@@ -200,7 +200,10 @@ int gemini_sata_start_bridge(struct sata_gemini *sg, unsigned int bridge)
pclk = sg->sata0_pclk;
else
pclk = sg->sata1_pclk;
- clk_enable(pclk);
+ ret = clk_enable(pclk);
+ if (ret)
+ return ret;
+
msleep(10);
/* Do not keep clocking a bridge that is not online */
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index e82786c63fbd..9bec0aee92e0 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -787,37 +787,6 @@ static const struct ata_port_info mv_port_info[] = {
},
};
-static const struct pci_device_id mv_pci_tbl[] = {
- { PCI_VDEVICE(MARVELL, 0x5040), chip_504x },
- { PCI_VDEVICE(MARVELL, 0x5041), chip_504x },
- { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 },
- { PCI_VDEVICE(MARVELL, 0x5081), chip_508x },
- /* RocketRAID 1720/174x have different identifiers */
- { PCI_VDEVICE(TTI, 0x1720), chip_6042 },
- { PCI_VDEVICE(TTI, 0x1740), chip_6042 },
- { PCI_VDEVICE(TTI, 0x1742), chip_6042 },
-
- { PCI_VDEVICE(MARVELL, 0x6040), chip_604x },
- { PCI_VDEVICE(MARVELL, 0x6041), chip_604x },
- { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 },
- { PCI_VDEVICE(MARVELL, 0x6080), chip_608x },
- { PCI_VDEVICE(MARVELL, 0x6081), chip_608x },
-
- { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x },
-
- /* Adaptec 1430SA */
- { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 },
-
- /* Marvell 7042 support */
- { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 },
-
- /* Highpoint RocketRAID PCIe series */
- { PCI_VDEVICE(TTI, 0x2300), chip_7042 },
- { PCI_VDEVICE(TTI, 0x2310), chip_7042 },
-
- { } /* terminate list */
-};
-
static const struct mv_hw_ops mv5xxx_ops = {
.phy_errata = mv5_phy_errata,
.enable_leds = mv5_enable_leds,
@@ -4303,6 +4272,36 @@ static int mv_pci_init_one(struct pci_dev *pdev,
static int mv_pci_device_resume(struct pci_dev *pdev);
#endif
+static const struct pci_device_id mv_pci_tbl[] = {
+ { PCI_VDEVICE(MARVELL, 0x5040), chip_504x },
+ { PCI_VDEVICE(MARVELL, 0x5041), chip_504x },
+ { PCI_VDEVICE(MARVELL, 0x5080), chip_5080 },
+ { PCI_VDEVICE(MARVELL, 0x5081), chip_508x },
+ /* RocketRAID 1720/174x have different identifiers */
+ { PCI_VDEVICE(TTI, 0x1720), chip_6042 },
+ { PCI_VDEVICE(TTI, 0x1740), chip_6042 },
+ { PCI_VDEVICE(TTI, 0x1742), chip_6042 },
+
+ { PCI_VDEVICE(MARVELL, 0x6040), chip_604x },
+ { PCI_VDEVICE(MARVELL, 0x6041), chip_604x },
+ { PCI_VDEVICE(MARVELL, 0x6042), chip_6042 },
+ { PCI_VDEVICE(MARVELL, 0x6080), chip_608x },
+ { PCI_VDEVICE(MARVELL, 0x6081), chip_608x },
+
+ { PCI_VDEVICE(ADAPTEC2, 0x0241), chip_604x },
+
+ /* Adaptec 1430SA */
+ { PCI_VDEVICE(ADAPTEC2, 0x0243), chip_7042 },
+
+ /* Marvell 7042 support */
+ { PCI_VDEVICE(MARVELL, 0x7042), chip_7042 },
+
+ /* Highpoint RocketRAID PCIe series */
+ { PCI_VDEVICE(TTI, 0x2300), chip_7042 },
+ { PCI_VDEVICE(TTI, 0x2310), chip_7042 },
+
+ { } /* terminate list */
+};
static struct pci_driver mv_pci_driver = {
.name = DRV_NAME,
@@ -4315,6 +4314,7 @@ static struct pci_driver mv_pci_driver = {
#endif
};
+MODULE_DEVICE_TABLE(pci, mv_pci_tbl);
/**
* mv_print_info - Dump key info to kernel log for perusal.
@@ -4487,7 +4487,6 @@ static void __exit mv_exit(void)
MODULE_AUTHOR("Brett Russ");
MODULE_DESCRIPTION("SCSI low-level driver for Marvell SATA controllers");
MODULE_LICENSE("GPL v2");
-MODULE_DEVICE_TABLE(pci, mv_pci_tbl);
MODULE_VERSION(DRV_VERSION);
MODULE_ALIAS("platform:" DRV_NAME);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index b51d7a9d0d90..a482741eb181 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -957,8 +957,7 @@ static void pdc20621_get_from_dimm(struct ata_host *host, void *psource,
offset -= (idx * window_size);
idx++;
- dist = ((long) (window_size - (offset + size))) >= 0 ? size :
- (long) (window_size - offset);
+ dist = min(size, window_size - offset);
memcpy_fromio(psource, dimm_mmio + offset / 4, dist);
psource += dist;
@@ -1005,8 +1004,7 @@ static void pdc20621_put_to_dimm(struct ata_host *host, void *psource,
readl(mmio + PDC_DIMM_WINDOW_CTLR);
offset -= (idx * window_size);
idx++;
- dist = ((long)(s32)(window_size - (offset + size))) >= 0 ? size :
- (long) (window_size - offset);
+ dist = min(size, window_size - offset);
memcpy_toio(dimm_mmio + offset / 4, psource, dist);
writel(0x01, mmio + PDC_GENERAL_CTLR);
readl(mmio + PDC_GENERAL_CTLR);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b93f3c5716ae..5f4e03336e68 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -44,6 +44,7 @@ static bool fw_devlink_is_permissive(void);
static void __fw_devlink_link_to_consumers(struct device *dev);
static bool fw_devlink_drv_reg_done;
static bool fw_devlink_best_effort;
+static struct workqueue_struct *device_link_wq;
/**
* __fwnode_link_add - Create a link between two fwnode_handles.
@@ -533,12 +534,26 @@ static void devlink_dev_release(struct device *dev)
/*
* It may take a while to complete this work because of the SRCU
* synchronization in device_link_release_fn() and if the consumer or
- * supplier devices get deleted when it runs, so put it into the "long"
- * workqueue.
+ * supplier devices get deleted when it runs, so put it into the
+ * dedicated workqueue.
*/
- queue_work(system_long_wq, &link->rm_work);
+ queue_work(device_link_wq, &link->rm_work);
}
+/**
+ * device_link_wait_removal - Wait for ongoing devlink removal jobs to terminate
+ */
+void device_link_wait_removal(void)
+{
+ /*
+ * devlink removal jobs are queued in the dedicated work queue.
+ * To be sure that all removal jobs are terminated, ensure that any
+ * scheduled work has run to completion.
+ */
+ flush_workqueue(device_link_wq);
+}
+EXPORT_SYMBOL_GPL(device_link_wait_removal);
+
static struct class devlink_class = {
.name = "devlink",
.dev_groups = devlink_groups,
@@ -4164,9 +4179,14 @@ int __init devices_init(void)
sysfs_dev_char_kobj = kobject_create_and_add("char", dev_kobj);
if (!sysfs_dev_char_kobj)
goto char_kobj_err;
+ device_link_wq = alloc_workqueue("device_link_wq", 0, 0);
+ if (!device_link_wq)
+ goto wq_err;
return 0;
+ wq_err:
+ kobject_put(sysfs_dev_char_kobj);
char_kobj_err:
kobject_put(sysfs_dev_block_kobj);
block_kobj_err:
diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c
index 41edd6a430eb..55999a50ccc0 100644
--- a/drivers/base/regmap/regcache-maple.c
+++ b/drivers/base/regmap/regcache-maple.c
@@ -112,7 +112,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
unsigned long *entry, *lower, *upper;
unsigned long lower_index, lower_last;
unsigned long upper_index, upper_last;
- int ret;
+ int ret = 0;
lower = NULL;
upper = NULL;
@@ -145,7 +145,7 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
upper_index = max + 1;
upper_last = mas.last;
- upper = kmemdup(&entry[max + 1],
+ upper = kmemdup(&entry[max - mas.index + 1],
((mas.last - max) *
sizeof(unsigned long)),
map->alloc_flags);
@@ -244,7 +244,7 @@ static int regcache_maple_sync(struct regmap *map, unsigned int min,
unsigned long lmin = min;
unsigned long lmax = max;
unsigned int r, v, sync_start;
- int ret;
+ int ret = 0;
bool sync_needed = false;
map->cache_bypass = true;
diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index 71c39bcd872c..ed33cf7192d2 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1965,10 +1965,10 @@ static int null_add_dev(struct nullb_device *dev)
out_ida_free:
ida_free(&nullb_indexes, nullb->index);
-out_cleanup_zone:
- null_free_zoned_dev(dev);
out_cleanup_disk:
put_disk(nullb->disk);
+out_cleanup_zone:
+ null_free_zoned_dev(dev);
out_cleanup_tags:
if (nullb->tag_set == &nullb->__tag_set)
blk_mq_free_tag_set(nullb->tag_set);
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
index f44efbb89c34..2102377f727b 100644
--- a/drivers/crypto/ccp/sev-dev.c
+++ b/drivers/crypto/ccp/sev-dev.c
@@ -1090,7 +1090,7 @@ static int __sev_snp_init_locked(int *error)
void *arg = &data;
int cmd, rc = 0;
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return -ENODEV;
sev = psp->sev_data;
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 7bc71f4be64a..38d19410a2be 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -2060,6 +2060,8 @@ static void bus_reset_work(struct work_struct *work)
ohci->generation = generation;
reg_write(ohci, OHCI1394_IntEventClear, OHCI1394_busReset);
+ if (param_debug & OHCI_PARAM_DEBUG_BUSRESETS)
+ reg_write(ohci, OHCI1394_IntMaskSet, OHCI1394_busReset);
if (ohci->quirks & QUIRK_RESET_PACKET)
ohci->request_generation = generation;
@@ -2125,12 +2127,14 @@ static irqreturn_t irq_handler(int irq, void *data)
return IRQ_NONE;
/*
- * busReset and postedWriteErr must not be cleared yet
+ * busReset and postedWriteErr events must not be cleared yet
* (OHCI 1.1 clauses 7.2.3.2 and 13.2.8.1)
*/
reg_write(ohci, OHCI1394_IntEventClear,
event & ~(OHCI1394_busReset | OHCI1394_postedWriteErr));
log_irqs(ohci, event);
+ if (event & OHCI1394_busReset)
+ reg_write(ohci, OHCI1394_IntMaskClear, OHCI1394_busReset);
if (event & OHCI1394_selfIDComplete)
queue_work(selfid_workqueue, &ohci->bus_reset_work);
diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index fa9635610251..d09c7d728365 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -728,6 +728,25 @@ static u32 line_event_id(int level)
GPIO_V2_LINE_EVENT_FALLING_EDGE;
}
+static inline char *make_irq_label(const char *orig)
+{
+ char *new;
+
+ if (!orig)
+ return NULL;
+
+ new = kstrdup_and_replace(orig, '/', ':', GFP_KERNEL);
+ if (!new)
+ return ERR_PTR(-ENOMEM);
+
+ return new;
+}
+
+static inline void free_irq_label(const char *label)
+{
+ kfree(label);
+}
+
#ifdef CONFIG_HTE
static enum hte_return process_hw_ts_thread(void *p)
@@ -1015,6 +1034,7 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us)
{
unsigned long irqflags;
int ret, level, irq;
+ char *label;
/* try hardware */
ret = gpiod_set_debounce(line->desc, debounce_period_us);
@@ -1037,11 +1057,17 @@ static int debounce_setup(struct line *line, unsigned int debounce_period_us)
if (irq < 0)
return -ENXIO;
+ label = make_irq_label(line->req->label);
+ if (IS_ERR(label))
+ return -ENOMEM;
+
irqflags = IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING;
ret = request_irq(irq, debounce_irq_handler, irqflags,
- line->req->label, line);
- if (ret)
+ label, line);
+ if (ret) {
+ free_irq_label(label);
return ret;
+ }
line->irq = irq;
} else {
ret = hte_edge_setup(line, GPIO_V2_LINE_FLAG_EDGE_BOTH);
@@ -1083,16 +1109,6 @@ static u32 gpio_v2_line_config_debounce_period(struct gpio_v2_line_config *lc,
return 0;
}
-static inline char *make_irq_label(const char *orig)
-{
- return kstrdup_and_replace(orig, '/', ':', GFP_KERNEL);
-}
-
-static inline void free_irq_label(const char *label)
-{
- kfree(label);
-}
-
static void edge_detector_stop(struct line *line)
{
if (line->irq) {
@@ -1158,8 +1174,8 @@ static int edge_detector_setup(struct line *line,
irqflags |= IRQF_ONESHOT;
label = make_irq_label(line->req->label);
- if (!label)
- return -ENOMEM;
+ if (IS_ERR(label))
+ return PTR_ERR(label);
/* Request a thread to read the events */
ret = request_threaded_irq(irq, edge_irq_handler, edge_irq_thread,
@@ -2217,8 +2233,8 @@ static int lineevent_create(struct gpio_device *gdev, void __user *ip)
goto out_free_le;
label = make_irq_label(le->label);
- if (!label) {
- ret = -ENOMEM;
+ if (IS_ERR(label)) {
+ ret = PTR_ERR(label);
goto out_free_le;
}
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 59ccf9a3e153..94903fc1c145 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1175,6 +1175,9 @@ struct gpio_device *gpio_device_find(const void *data,
list_for_each_entry_srcu(gdev, &gpio_devices, list,
srcu_read_lock_held(&gpio_devices_srcu)) {
+ if (!device_is_registered(&gdev->dev))
+ continue;
+
guard(srcu)(&gdev->srcu);
gc = srcu_dereference(gdev->chip, &gdev->srcu);
diff --git a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
index bd61e20770a5..14a2a8473682 100644
--- a/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
+++ b/drivers/gpu/drm/display/drm_dp_dual_mode_helper.c
@@ -52,7 +52,7 @@
* @adapter: I2C adapter for the DDC bus
* @offset: register offset
* @buffer: buffer for return data
- * @size: sizo of the buffer
+ * @size: size of the buffer
*
* Reads @size bytes from the DP dual mode adaptor registers
* starting at @offset.
@@ -116,7 +116,7 @@ EXPORT_SYMBOL(drm_dp_dual_mode_read);
* @adapter: I2C adapter for the DDC bus
* @offset: register offset
* @buffer: buffer for write data
- * @size: sizo of the buffer
+ * @size: size of the buffer
*
* Writes @size bytes to the DP dual mode adaptor registers
* starting at @offset.
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 7352bde299d5..03bd3c7bd0dc 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -582,7 +582,12 @@ int drm_gem_map_attach(struct dma_buf *dma_buf,
{
struct drm_gem_object *obj = dma_buf->priv;
- if (!obj->funcs->get_sg_table)
+ /*
+ * drm_gem_map_dma_buf() requires obj->get_sg_table(), but drivers
+ * that implement their own ->map_dma_buf() do not.
+ */
+ if (dma_buf->ops->map_dma_buf == drm_gem_map_dma_buf &&
+ !obj->funcs->get_sg_table)
return -ENOSYS;
return drm_gem_pin(obj);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4c2f85632391..fba73c38e235 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -118,6 +118,7 @@ gt-y += \
gt/intel_ggtt_fencing.o \
gt/intel_gt.o \
gt/intel_gt_buffer_pool.o \
+ gt/intel_gt_ccs_mode.o \
gt/intel_gt_clock_utils.o \
gt/intel_gt_debugfs.o \
gt/intel_gt_engines_debugfs.o \
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index ab2f52d21bad..8af9e6128277 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -2709,15 +2709,6 @@ static void intel_set_pipe_src_size(const struct intel_crtc_state *crtc_state)
*/
intel_de_write(dev_priv, PIPESRC(pipe),
PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1));
-
- if (!crtc_state->enable_psr2_su_region_et)
- return;
-
- width = drm_rect_width(&crtc_state->psr2_su_area);
- height = drm_rect_height(&crtc_state->psr2_su_area);
-
- intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(pipe),
- PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1));
}
static bool intel_pipe_is_interlaced(const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/display/intel_display_device.h b/drivers/gpu/drm/i915/display/intel_display_device.h
index fe4268813786..9b1bce2624b9 100644
--- a/drivers/gpu/drm/i915/display/intel_display_device.h
+++ b/drivers/gpu/drm/i915/display/intel_display_device.h
@@ -47,6 +47,7 @@ struct drm_printer;
#define HAS_DPT(i915) (DISPLAY_VER(i915) >= 13)
#define HAS_DSB(i915) (DISPLAY_INFO(i915)->has_dsb)
#define HAS_DSC(__i915) (DISPLAY_RUNTIME_INFO(__i915)->has_dsc)
+#define HAS_DSC_MST(__i915) (DISPLAY_VER(__i915) >= 12 && HAS_DSC(__i915))
#define HAS_FBC(i915) (DISPLAY_RUNTIME_INFO(i915)->fbc_mask != 0)
#define HAS_FPGA_DBG_UNCLAIMED(i915) (DISPLAY_INFO(i915)->has_fpga_dbg)
#define HAS_FW_BLC(i915) (DISPLAY_VER(i915) >= 3)
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 9104f18753b4..bf3f942e19c3 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -1423,6 +1423,8 @@ struct intel_crtc_state {
u32 psr2_man_track_ctl;
+ u32 pipe_srcsz_early_tpt;
+
struct drm_rect psr2_su_area;
/* Variable Refresh Rate state */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index f98ef4b42a44..abd62bebc46d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -499,7 +499,7 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
/* The values must be in increasing order */
static const int mtl_rates[] = {
162000, 216000, 243000, 270000, 324000, 432000, 540000, 675000,
- 810000, 1000000, 1350000, 2000000,
+ 810000, 1000000, 2000000,
};
static const int icl_rates[] = {
162000, 216000, 270000, 324000, 432000, 540000, 648000, 810000,
@@ -1422,7 +1422,8 @@ static bool intel_dp_source_supports_fec(struct intel_dp *intel_dp,
if (DISPLAY_VER(dev_priv) >= 12)
return true;
- if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A)
+ if (DISPLAY_VER(dev_priv) == 11 && encoder->port != PORT_A &&
+ !intel_crtc_has_type(pipe_config, INTEL_OUTPUT_DP_MST))
return true;
return false;
@@ -1917,8 +1918,9 @@ icl_dsc_compute_link_config(struct intel_dp *intel_dp,
dsc_max_bpp = min(dsc_max_bpp, pipe_bpp - 1);
for (i = 0; i < ARRAY_SIZE(valid_dsc_bpp); i++) {
- if (valid_dsc_bpp[i] < dsc_min_bpp ||
- valid_dsc_bpp[i] > dsc_max_bpp)
+ if (valid_dsc_bpp[i] < dsc_min_bpp)
+ continue;
+ if (valid_dsc_bpp[i] > dsc_max_bpp)
break;
ret = dsc_compute_link_config(intel_dp,
@@ -6557,6 +6559,7 @@ intel_dp_init_connector(struct intel_digital_port *dig_port,
intel_connector->get_hw_state = intel_ddi_connector_get_hw_state;
else
intel_connector->get_hw_state = intel_connector_get_hw_state;
+ intel_connector->sync_state = intel_dp_connector_sync_state;
if (!intel_edp_init_connector(intel_dp, intel_connector)) {
intel_dp_aux_fini(intel_dp);
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index 53aec023ce92..b651c990af85 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1355,7 +1355,7 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector,
return 0;
}
- if (DISPLAY_VER(dev_priv) >= 10 &&
+ if (HAS_DSC_MST(dev_priv) &&
drm_dp_sink_supports_dsc(intel_connector->dp.dsc_dpcd)) {
/*
* TBD pass the connector BPC,
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 6927785fd6ff..b6e539f1342c 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -1994,6 +1994,7 @@ static void psr_force_hw_tracking_exit(struct intel_dp *intel_dp)
void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_state)
{
+ struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
struct drm_i915_private *dev_priv = to_i915(crtc_state->uapi.crtc->dev);
enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
struct intel_encoder *encoder;
@@ -2013,6 +2014,12 @@ void intel_psr2_program_trans_man_trk_ctl(const struct intel_crtc_state *crtc_st
intel_de_write(dev_priv, PSR2_MAN_TRK_CTL(cpu_transcoder),
crtc_state->psr2_man_track_ctl);
+
+ if (!crtc_state->enable_psr2_su_region_et)
+ return;
+
+ intel_de_write(dev_priv, PIPE_SRCSZ_ERLY_TPT(crtc->pipe),
+ crtc_state->pipe_srcsz_early_tpt);
}
static void psr2_man_trk_ctl_calc(struct intel_crtc_state *crtc_state,
@@ -2051,6 +2058,20 @@ exit:
crtc_state->psr2_man_track_ctl = val;
}
+static u32 psr2_pipe_srcsz_early_tpt_calc(struct intel_crtc_state *crtc_state,
+ bool full_update)
+{
+ int width, height;
+
+ if (!crtc_state->enable_psr2_su_region_et || full_update)
+ return 0;
+
+ width = drm_rect_width(&crtc_state->psr2_su_area);
+ height = drm_rect_height(&crtc_state->psr2_su_area);
+
+ return PIPESRC_WIDTH(width - 1) | PIPESRC_HEIGHT(height - 1);
+}
+
static void clip_area_update(struct drm_rect *overlap_damage_area,
struct drm_rect *damage_area,
struct drm_rect *pipe_src)
@@ -2095,21 +2116,36 @@ static void intel_psr2_sel_fetch_pipe_alignment(struct intel_crtc_state *crtc_st
* cursor fully when cursor is in SU area.
*/
static void
-intel_psr2_sel_fetch_et_alignment(struct intel_crtc_state *crtc_state,
- struct intel_plane_state *cursor_state)
+intel_psr2_sel_fetch_et_alignment(struct intel_atomic_state *state,
+ struct intel_crtc *crtc)
{
- struct drm_rect inter;
+ struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+ struct intel_plane_state *new_plane_state;
+ struct intel_plane *plane;
+ int i;
- if (!crtc_state->enable_psr2_su_region_et ||
- !cursor_state->uapi.visible)
+ if (!crtc_state->enable_psr2_su_region_et)
return;
- inter = crtc_state->psr2_su_area;
- if (!drm_rect_intersect(&inter, &cursor_state->uapi.dst))
- return;
+ for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) {
+ struct drm_rect inter;
- clip_area_update(&crtc_state->psr2_su_area, &cursor_state->uapi.dst,
- &crtc_state->pipe_src);
+ if (new_plane_state->uapi.crtc != crtc_state->uapi.crtc)
+ continue;
+
+ if (plane->id != PLANE_CURSOR)
+ continue;
+
+ if (!new_plane_state->uapi.visible)
+ continue;
+
+ inter = crtc_state->psr2_su_area;
+ if (!drm_rect_intersect(&inter, &new_plane_state->uapi.dst))
+ continue;
+
+ clip_area_update(&crtc_state->psr2_su_area, &new_plane_state->uapi.dst,
+ &crtc_state->pipe_src);
+ }
}
/*
@@ -2152,8 +2188,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
{
struct drm_i915_private *dev_priv = to_i915(state->base.dev);
struct intel_crtc_state *crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
- struct intel_plane_state *new_plane_state, *old_plane_state,
- *cursor_plane_state = NULL;
+ struct intel_plane_state *new_plane_state, *old_plane_state;
struct intel_plane *plane;
bool full_update = false;
int i, ret;
@@ -2238,13 +2273,6 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
damaged_area.x2 += new_plane_state->uapi.dst.x1 - src.x1;
clip_area_update(&crtc_state->psr2_su_area, &damaged_area, &crtc_state->pipe_src);
-
- /*
- * Cursor plane new state is stored to adjust su area to cover
- * cursor are fully.
- */
- if (plane->id == PLANE_CURSOR)
- cursor_plane_state = new_plane_state;
}
/*
@@ -2273,9 +2301,13 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
if (ret)
return ret;
- /* Adjust su area to cover cursor fully as necessary */
- if (cursor_plane_state)
- intel_psr2_sel_fetch_et_alignment(crtc_state, cursor_plane_state);
+ /*
+ * Adjust su area to cover cursor fully as necessary (early
+ * transport). This needs to be done after
+ * drm_atomic_add_affected_planes to ensure visible cursor is added into
+ * affected planes even when cursor is not updated by itself.
+ */
+ intel_psr2_sel_fetch_et_alignment(state, crtc);
intel_psr2_sel_fetch_pipe_alignment(crtc_state);
@@ -2338,6 +2370,8 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
skip_sel_fetch_set_loop:
psr2_man_trk_ctl_calc(crtc_state, full_update);
+ crtc_state->pipe_srcsz_early_tpt =
+ psr2_pipe_srcsz_early_tpt_calc(crtc_state, full_update);
return 0;
}
diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
index fa46d2308b0e..81bf2216371b 100644
--- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c
@@ -961,6 +961,9 @@ static int gen8_init_rsvd(struct i915_address_space *vm)
struct i915_vma *vma;
int ret;
+ if (!intel_gt_needs_wa_16018031267(vm->gt))
+ return 0;
+
/* The memory will be used only by GPU. */
obj = i915_gem_object_create_lmem(i915, PAGE_SIZE,
I915_BO_ALLOC_VOLATILE |
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 1ade568ffbfa..7a6dc371c384 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -908,6 +908,23 @@ static intel_engine_mask_t init_engine_mask(struct intel_gt *gt)
info->engine_mask &= ~BIT(GSC0);
}
+ /*
+ * Do not create the command streamer for CCS slices beyond the first.
+ * All the workload submitted to the first engine will be shared among
+ * all the slices.
+ *
+ * Once the user will be allowed to customize the CCS mode, then this
+ * check needs to be removed.
+ */
+ if (IS_DG2(gt->i915)) {
+ u8 first_ccs = __ffs(CCS_MASK(gt));
+
+ /* Mask off all the CCS engine */
+ info->engine_mask &= ~GENMASK(CCS3, CCS0);
+ /* Put back in the first CCS engine */
+ info->engine_mask |= BIT(_CCS(first_ccs));
+ }
+
return info->engine_mask;
}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index a425db5ed3a2..6a2c2718bcc3 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -1024,6 +1024,12 @@ enum i915_map_type intel_gt_coherent_map_type(struct intel_gt *gt,
return I915_MAP_WC;
}
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt)
+{
+ /* Wa_16018031267, Wa_16018063123 */
+ return IS_GFX_GT_IP_RANGE(gt, IP_VER(12, 55), IP_VER(12, 71));
+}
+
bool intel_gt_needs_wa_22016122933(struct intel_gt *gt)
{
return MEDIA_VER_FULL(gt->i915) == IP_VER(13, 0) && gt->type == GT_MEDIA;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 608f5c872928..003eb93b826f 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -82,17 +82,18 @@ struct drm_printer;
##__VA_ARGS__); \
} while (0)
-#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
- IS_GFX_GT_IP_RANGE(engine->gt, IP_VER(12, 55), IP_VER(12, 71)) && \
- engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
-
static inline bool gt_is_root(struct intel_gt *gt)
{
return !gt->info.id;
}
+bool intel_gt_needs_wa_16018031267(struct intel_gt *gt);
bool intel_gt_needs_wa_22016122933(struct intel_gt *gt);
+#define NEEDS_FASTCOLOR_BLT_WABB(engine) ( \
+ intel_gt_needs_wa_16018031267(engine->gt) && \
+ engine->class == COPY_ENGINE_CLASS && engine->instance == 0)
+
static inline struct intel_gt *uc_to_gt(struct intel_uc *uc)
{
return container_of(uc, struct intel_gt, uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
new file mode 100644
index 000000000000..044219c5960a
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
+#include "intel_gt_regs.h"
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt)
+{
+ int cslice;
+ u32 mode = 0;
+ int first_ccs = __ffs(CCS_MASK(gt));
+
+ if (!IS_DG2(gt->i915))
+ return;
+
+ /* Build the value for the fixed CCS load balancing */
+ for (cslice = 0; cslice < I915_MAX_CCS; cslice++) {
+ if (CCS_MASK(gt) & BIT(cslice))
+ /*
+ * If available, assign the cslice
+ * to the first available engine...
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice, first_ccs);
+
+ else
+ /*
+ * ... otherwise, mark the cslice as
+ * unavailable if no CCS dispatches here
+ */
+ mode |= XEHP_CCS_MODE_CSLICE(cslice,
+ XEHP_CCS_MODE_CSLICE_MASK);
+ }
+
+ intel_uncore_write(gt->uncore, XEHP_CCS_MODE, mode);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
new file mode 100644
index 000000000000..9e5549caeb26
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_gt_ccs_mode.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Intel Corporation
+ */
+
+#ifndef __INTEL_GT_CCS_MODE_H__
+#define __INTEL_GT_CCS_MODE_H__
+
+struct intel_gt;
+
+void intel_gt_apply_ccs_mode(struct intel_gt *gt);
+
+#endif /* __INTEL_GT_CCS_MODE_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_regs.h b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
index 50962cfd1353..743fe3566722 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_regs.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_regs.h
@@ -1477,8 +1477,14 @@
#define ECOBITS_PPGTT_CACHE4B (0 << 8)
#define GEN12_RCU_MODE _MMIO(0x14800)
+#define XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE REG_BIT(1)
#define GEN12_RCU_MODE_CCS_ENABLE REG_BIT(0)
+#define XEHP_CCS_MODE _MMIO(0x14804)
+#define XEHP_CCS_MODE_CSLICE_MASK REG_GENMASK(2, 0) /* CCS0-3 + rsvd */
+#define XEHP_CCS_MODE_CSLICE_WIDTH ilog2(XEHP_CCS_MODE_CSLICE_MASK + 1)
+#define XEHP_CCS_MODE_CSLICE(cslice, ccs) (ccs << (cslice * XEHP_CCS_MODE_CSLICE_WIDTH))
+
#define CHV_FUSE_GT _MMIO(VLV_GUNIT_BASE + 0x2168)
#define CHV_FGT_DISABLE_SS0 (1 << 10)
#define CHV_FGT_DISABLE_SS1 (1 << 11)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 25413809b9dc..6ec3582c9735 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -10,6 +10,7 @@
#include "intel_engine_regs.h"
#include "intel_gpu_commands.h"
#include "intel_gt.h"
+#include "intel_gt_ccs_mode.h"
#include "intel_gt_mcr.h"
#include "intel_gt_print.h"
#include "intel_gt_regs.h"
@@ -51,7 +52,8 @@
* registers belonging to BCS, VCS or VECS should be implemented in
* xcs_engine_wa_init(). Workarounds for registers not belonging to a specific
* engine's MMIO range but that are part of of the common RCS/CCS reset domain
- * should be implemented in general_render_compute_wa_init().
+ * should be implemented in general_render_compute_wa_init(). The settings
+ * about the CCS load balancing should be added in ccs_engine_wa_mode().
*
* - GT workarounds: the list of these WAs is applied whenever these registers
* revert to their default values: on GPU reset, suspend/resume [1]_, etc.
@@ -2854,6 +2856,28 @@ add_render_compute_tuning_settings(struct intel_gt *gt,
wa_write_clr(wal, GEN8_GARBCNTL, GEN12_BUS_HASH_CTL_BIT_EXC);
}
+static void ccs_engine_wa_mode(struct intel_engine_cs *engine, struct i915_wa_list *wal)
+{
+ struct intel_gt *gt = engine->gt;
+
+ if (!IS_DG2(gt->i915))
+ return;
+
+ /*
+ * Wa_14019159160: This workaround, along with others, leads to
+ * significant challenges in utilizing load balancing among the
+ * CCS slices. Consequently, an architectural decision has been
+ * made to completely disable automatic CCS load balancing.
+ */
+ wa_masked_en(wal, GEN12_RCU_MODE, XEHP_RCU_MODE_FIXED_SLICE_CCS_MODE);
+
+ /*
+ * After having disabled automatic load balancing we need to
+ * assign all slices to a single CCS. We will call it CCS mode 1
+ */
+ intel_gt_apply_ccs_mode(gt);
+}
+
/*
* The workarounds in this function apply to shared registers in
* the general render reset domain that aren't tied to a
@@ -3004,8 +3028,10 @@ engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal
* to a single RCS/CCS engine's workaround list since
* they're reset as part of the general render domain reset.
*/
- if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE)
+ if (engine->flags & I915_ENGINE_FIRST_RENDER_COMPUTE) {
general_render_compute_wa_init(engine, wal);
+ ccs_engine_wa_mode(engine, wal);
+ }
if (engine->class == COMPUTE_CLASS)
ccs_engine_wa_init(engine, wal);
diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
index 0a0a11dc9ec0..ee02cd833c5e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
@@ -812,15 +812,15 @@ op_remap(struct drm_gpuva_op_remap *r,
struct drm_gpuva_op_unmap *u = r->unmap;
struct nouveau_uvma *uvma = uvma_from_va(u->va);
u64 addr = uvma->va.va.addr;
- u64 range = uvma->va.va.range;
+ u64 end = uvma->va.va.addr + uvma->va.va.range;
if (r->prev)
addr = r->prev->va.addr + r->prev->va.range;
if (r->next)
- range = r->next->va.addr - addr;
+ end = r->next->va.addr;
- op_unmap_range(u, addr, range);
+ op_unmap_range(u, addr, end - addr);
}
static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 986e8d547c94..060c74a80eb1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -420,7 +420,7 @@ gf100_gr_chan_new(struct nvkm_gr *base, struct nvkm_chan *fifoch,
return ret;
} else {
ret = nvkm_memory_map(gr->attrib_cb, 0, chan->vmm, chan->attrib_cb,
- &args, sizeof(args));;
+ &args, sizeof(args));
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
index 7bcbc4895ec2..271bfa038f5b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm107.c
@@ -25,6 +25,7 @@
#include <subdev/bios.h>
#include <subdev/bios/init.h>
+#include <subdev/gsp.h>
void
gm107_devinit_disable(struct nvkm_devinit *init)
@@ -33,10 +34,13 @@ gm107_devinit_disable(struct nvkm_devinit *init)
u32 r021c00 = nvkm_rd32(device, 0x021c00);
u32 r021c04 = nvkm_rd32(device, 0x021c04);
- if (r021c00 & 0x00000001)
- nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
- if (r021c00 & 0x00000004)
- nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+ /* gsp only wants to enable/disable display */
+ if (!nvkm_gsp_rm(device->gsp)) {
+ if (r021c00 & 0x00000001)
+ nvkm_subdev_disable(device, NVKM_ENGINE_CE, 0);
+ if (r021c00 & 0x00000004)
+ nvkm_subdev_disable(device, NVKM_ENGINE_CE, 2);
+ }
if (r021c04 & 0x00000001)
nvkm_subdev_disable(device, NVKM_ENGINE_DISP, 0);
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
index 11b4c9c274a1..666eb93b1742 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/r535.c
@@ -41,6 +41,7 @@ r535_devinit_new(const struct nvkm_devinit_func *hw,
rm->dtor = r535_devinit_dtor;
rm->post = hw->post;
+ rm->disable = hw->disable;
ret = nv50_devinit_new_(rm, device, type, inst, pdevinit);
if (ret)
diff --git a/drivers/gpu/drm/panfrost/panfrost_gpu.c b/drivers/gpu/drm/panfrost/panfrost_gpu.c
index 9063ce254642..fd8e44992184 100644
--- a/drivers/gpu/drm/panfrost/panfrost_gpu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_gpu.c
@@ -441,19 +441,19 @@ void panfrost_gpu_power_off(struct panfrost_device *pfdev)
gpu_write(pfdev, SHADER_PWROFF_LO, pfdev->features.shader_present);
ret = readl_relaxed_poll_timeout(pfdev->iomem + SHADER_PWRTRANS_LO,
- val, !val, 1, 1000);
+ val, !val, 1, 2000);
if (ret)
dev_err(pfdev->dev, "shader power transition timeout");
gpu_write(pfdev, TILER_PWROFF_LO, pfdev->features.tiler_present);
ret = readl_relaxed_poll_timeout(pfdev->iomem + TILER_PWRTRANS_LO,
- val, !val, 1, 1000);
+ val, !val, 1, 2000);
if (ret)
dev_err(pfdev->dev, "tiler power transition timeout");
gpu_write(pfdev, L2_PWROFF_LO, pfdev->features.l2_present);
ret = readl_poll_timeout(pfdev->iomem + L2_PWRTRANS_LO,
- val, !val, 0, 1000);
+ val, !val, 0, 2000);
if (ret)
dev_err(pfdev->dev, "l2 power transition timeout");
}
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index ca85e81fdb44..d32ff3857e65 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -193,6 +193,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy)
{
struct xe_device *xe = to_xe_device(dev);
+ if (xe->preempt_fence_wq)
+ destroy_workqueue(xe->preempt_fence_wq);
+
if (xe->ordered_wq)
destroy_workqueue(xe->ordered_wq);
@@ -258,9 +261,15 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
INIT_LIST_HEAD(&xe->pinned.external_vram);
INIT_LIST_HEAD(&xe->pinned.evicted);
+ xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0);
xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0);
xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0);
- if (!xe->ordered_wq || !xe->unordered_wq) {
+ if (!xe->ordered_wq || !xe->unordered_wq ||
+ !xe->preempt_fence_wq) {
+ /*
+ * Cleanup done in xe_device_destroy via
+ * drmm_add_action_or_reset register above
+ */
drm_err(&xe->drm, "Failed to allocate xe workqueues\n");
err = -ENOMEM;
goto err;
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 9785eef2e5a4..8e3a222b41cf 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -363,6 +363,9 @@ struct xe_device {
/** @ufence_wq: user fence wait queue */
wait_queue_head_t ufence_wq;
+ /** @preempt_fence_wq: used to serialize preempt fences */
+ struct workqueue_struct *preempt_fence_wq;
+
/** @ordered_wq: used to serialize compute mode resume */
struct workqueue_struct *ordered_wq;
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 826c8b389672..cc5e0f75de3c 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -94,48 +94,16 @@
* Unlock all
*/
+/*
+ * Add validation and rebinding to the drm_exec locking loop, since both can
+ * trigger eviction which may require sleeping dma_resv locks.
+ */
static int xe_exec_fn(struct drm_gpuvm_exec *vm_exec)
{
struct xe_vm *vm = container_of(vm_exec->vm, struct xe_vm, gpuvm);
- struct drm_gem_object *obj;
- unsigned long index;
- int num_fences;
- int ret;
-
- ret = drm_gpuvm_validate(vm_exec->vm, &vm_exec->exec);
- if (ret)
- return ret;
-
- /*
- * 1 fence slot for the final submit, and 1 more for every per-tile for
- * GPU bind and 1 extra for CPU bind. Note that there are potentially
- * many vma per object/dma-resv, however the fence slot will just be
- * re-used, since they are largely the same timeline and the seqno
- * should be in order. In the case of CPU bind there is dummy fence used
- * for all CPU binds, so no need to have a per-tile slot for that.
- */
- num_fences = 1 + 1 + vm->xe->info.tile_count;
- /*
- * We don't know upfront exactly how many fence slots we will need at
- * the start of the exec, since the TTM bo_validate above can consume
- * numerous fence slots. Also due to how the dma_resv_reserve_fences()
- * works it only ensures that at least that many fence slots are
- * available i.e if there are already 10 slots available and we reserve
- * two more, it can just noop without reserving anything. With this it
- * is quite possible that TTM steals some of the fence slots and then
- * when it comes time to do the vma binding and final exec stage we are
- * lacking enough fence slots, leading to some nasty BUG_ON() when
- * adding the fences. Hence just add our own fences here, after the
- * validate stage.
- */
- drm_exec_for_each_locked_object(&vm_exec->exec, index, obj) {
- ret = dma_resv_reserve_fences(obj->resv, num_fences);
- if (ret)
- return ret;
- }
-
- return 0;
+ /* The fence slot added here is intended for the exec sched job. */
+ return xe_vm_validate_rebind(vm, &vm_exec->exec, 1);
}
int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
@@ -152,7 +120,6 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
struct drm_exec *exec = &vm_exec.exec;
u32 i, num_syncs = 0, num_ufence = 0;
struct xe_sched_job *job;
- struct dma_fence *rebind_fence;
struct xe_vm *vm;
bool write_locked, skip_retry = false;
ktime_t end = 0;
@@ -290,39 +257,7 @@ retry:
goto err_exec;
}
- /*
- * Rebind any invalidated userptr or evicted BOs in the VM, non-compute
- * VM mode only.
- */
- rebind_fence = xe_vm_rebind(vm, false);
- if (IS_ERR(rebind_fence)) {
- err = PTR_ERR(rebind_fence);
- goto err_put_job;
- }
-
- /*
- * We store the rebind_fence in the VM so subsequent execs don't get
- * scheduled before the rebinds of userptrs / evicted BOs is complete.
- */
- if (rebind_fence) {
- dma_fence_put(vm->rebind_fence);
- vm->rebind_fence = rebind_fence;
- }
- if (vm->rebind_fence) {
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
- &vm->rebind_fence->flags)) {
- dma_fence_put(vm->rebind_fence);
- vm->rebind_fence = NULL;
- } else {
- dma_fence_get(vm->rebind_fence);
- err = drm_sched_job_add_dependency(&job->drm,
- vm->rebind_fence);
- if (err)
- goto err_put_job;
- }
- }
-
- /* Wait behind munmap style rebinds */
+ /* Wait behind rebinds */
if (!xe_vm_in_lr_mode(vm)) {
err = drm_sched_job_add_resv_dependencies(&job->drm,
xe_vm_resv(vm),
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index 62b3d9d1d7cd..462b33195032 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -148,6 +148,11 @@ struct xe_exec_queue {
const struct xe_ring_ops *ring_ops;
/** @entity: DRM sched entity for this exec queue (1 to 1 relationship) */
struct drm_sched_entity *entity;
+ /**
+ * @tlb_flush_seqno: The seqno of the last rebind tlb flush performed
+ * Protected by @vm's resv. Unused if @vm == NULL.
+ */
+ u64 tlb_flush_seqno;
/** @lrc: logical ring context for this exec queue */
struct xe_lrc lrc[];
};
diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
index 241c294270d9..fa9e9853c53b 100644
--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
+++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
@@ -100,10 +100,9 @@ static int xe_pf_begin(struct drm_exec *exec, struct xe_vma *vma,
{
struct xe_bo *bo = xe_vma_bo(vma);
struct xe_vm *vm = xe_vma_vm(vma);
- unsigned int num_shared = 2; /* slots for bind + move */
int err;
- err = xe_vm_prepare_vma(exec, vma, num_shared);
+ err = xe_vm_lock_vma(exec, vma);
if (err)
return err;
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index f03e077f81a0..e598a4363d01 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -61,7 +61,6 @@ int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);
spin_lock_init(&gt->tlb_invalidation.pending_lock);
spin_lock_init(&gt->tlb_invalidation.lock);
- gt->tlb_invalidation.fence_context = dma_fence_context_alloc(1);
INIT_DELAYED_WORK(&gt->tlb_invalidation.fence_tdr,
xe_gt_tlb_fence_timeout);
diff --git a/drivers/gpu/drm/xe/xe_gt_types.h b/drivers/gpu/drm/xe/xe_gt_types.h
index 70c615dd1498..07b2f724ec45 100644
--- a/drivers/gpu/drm/xe/xe_gt_types.h
+++ b/drivers/gpu/drm/xe/xe_gt_types.h
@@ -177,13 +177,6 @@ struct xe_gt {
* xe_gt_tlb_fence_timeout after the timeut interval is over.
*/
struct delayed_work fence_tdr;
- /** @tlb_invalidation.fence_context: context for TLB invalidation fences */
- u64 fence_context;
- /**
- * @tlb_invalidation.fence_seqno: seqno to TLB invalidation fences, protected by
- * tlb_invalidation.lock
- */
- u32 fence_seqno;
/** @tlb_invalidation.lock: protects TLB invalidation fences */
spinlock_t lock;
} tlb_invalidation;
diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
index 7bce2a332603..7d50c6e89d8e 100644
--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
+++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
@@ -49,7 +49,7 @@ static bool preempt_fence_enable_signaling(struct dma_fence *fence)
struct xe_exec_queue *q = pfence->q;
pfence->error = q->ops->suspend(q);
- queue_work(system_unbound_wq, &pfence->preempt_work);
+ queue_work(q->vm->xe->preempt_fence_wq, &pfence->preempt_work);
return true;
}
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 7f54bc3e389d..4efc8c1a3d7a 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1135,8 +1135,7 @@ static int invalidation_fence_init(struct xe_gt *gt,
spin_lock_irq(&gt->tlb_invalidation.lock);
dma_fence_init(&ifence->base.base, &invalidation_fence_ops,
&gt->tlb_invalidation.lock,
- gt->tlb_invalidation.fence_context,
- ++gt->tlb_invalidation.fence_seqno);
+ dma_fence_context_alloc(1), 1);
spin_unlock_irq(&gt->tlb_invalidation.lock);
INIT_LIST_HEAD(&ifence->base.link);
@@ -1236,6 +1235,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
err = xe_pt_prepare_bind(tile, vma, entries, &num_entries);
if (err)
goto err;
+
+ err = dma_resv_reserve_fences(xe_vm_resv(vm), 1);
+ if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm)
+ err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1);
+ if (err)
+ goto err;
+
xe_tile_assert(tile, num_entries <= ARRAY_SIZE(entries));
xe_vm_dbg_print_entries(tile_to_xe(tile), entries, num_entries);
@@ -1254,11 +1260,13 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
* non-faulting LR, in particular on user-space batch buffer chaining,
* it needs to be done here.
*/
- if ((rebind && !xe_vm_in_lr_mode(vm) && !vm->batch_invalidate_tlb) ||
- (!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
+ if ((!rebind && xe_vm_has_scratch(vm) && xe_vm_in_preempt_fence_mode(vm))) {
ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
if (!ifence)
return ERR_PTR(-ENOMEM);
+ } else if (rebind && !xe_vm_in_lr_mode(vm)) {
+ /* We bump also if batch_invalidate_tlb is true */
+ vm->tlb_flush_seqno++;
}
rfence = kzalloc(sizeof(*rfence), GFP_KERNEL);
@@ -1297,7 +1305,7 @@ __xe_pt_bind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queue
}
/* add shared fence now for pagetable delayed destroy */
- dma_resv_add_fence(xe_vm_resv(vm), fence, !rebind &&
+ dma_resv_add_fence(xe_vm_resv(vm), fence, rebind ||
last_munmap_rebind ?
DMA_RESV_USAGE_KERNEL :
DMA_RESV_USAGE_BOOKKEEP);
@@ -1576,6 +1584,7 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
struct dma_fence *fence = NULL;
struct invalidation_fence *ifence;
struct xe_range_fence *rfence;
+ int err;
LLIST_HEAD(deferred);
@@ -1593,6 +1602,12 @@ __xe_pt_unbind_vma(struct xe_tile *tile, struct xe_vma *vma, struct xe_exec_queu
xe_pt_calc_rfence_interval(vma, &unbind_pt_update, entries,
num_entries);
+ err = dma_resv_reserve_fences(xe_vm_resv(vm), 1);
+ if (!err && !xe_vma_has_no_bo(vma) && !xe_vma_bo(vma)->vm)
+ err = dma_resv_reserve_fences(xe_vma_bo(vma)->ttm.base.resv, 1);
+ if (err)
+ return ERR_PTR(err);
+
ifence = kzalloc(sizeof(*ifence), GFP_KERNEL);
if (!ifence)
return ERR_PTR(-ENOMEM);
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index c4edffcd4a32..5b2b37b59813 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -219,10 +219,9 @@ static void __emit_job_gen12_simple(struct xe_sched_job *job, struct xe_lrc *lrc
{
u32 dw[MAX_JOB_SIZE_DW], i = 0;
u32 ppgtt_flag = get_ppgtt_flag(job);
- struct xe_vm *vm = job->q->vm;
struct xe_gt *gt = job->q->gt;
- if (vm && vm->batch_invalidate_tlb) {
+ if (job->ring_ops_flush_tlb) {
dw[i++] = preparser_disable(true);
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, true, dw, i);
@@ -270,7 +269,6 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
struct xe_gt *gt = job->q->gt;
struct xe_device *xe = gt_to_xe(gt);
bool decode = job->q->class == XE_ENGINE_CLASS_VIDEO_DECODE;
- struct xe_vm *vm = job->q->vm;
dw[i++] = preparser_disable(true);
@@ -282,13 +280,13 @@ static void __emit_job_gen12_video(struct xe_sched_job *job, struct xe_lrc *lrc,
i = emit_aux_table_inv(gt, VE0_AUX_INV, dw, i);
}
- if (vm && vm->batch_invalidate_tlb)
+ if (job->ring_ops_flush_tlb)
i = emit_flush_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, true, dw, i);
dw[i++] = preparser_disable(false);
- if (!vm || !vm->batch_invalidate_tlb)
+ if (!job->ring_ops_flush_tlb)
i = emit_store_imm_ggtt(xe_lrc_start_seqno_ggtt_addr(lrc),
seqno, dw, i);
@@ -317,7 +315,6 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
struct xe_gt *gt = job->q->gt;
struct xe_device *xe = gt_to_xe(gt);
bool lacks_render = !(gt->info.engine_mask & XE_HW_ENGINE_RCS_MASK);
- struct xe_vm *vm = job->q->vm;
u32 mask_flags = 0;
dw[i++] = preparser_disable(true);
@@ -327,7 +324,7 @@ static void __emit_job_gen12_render_compute(struct xe_sched_job *job,
mask_flags = PIPE_CONTROL_3D_ENGINE_FLAGS;
/* See __xe_pt_bind_vma() for a discussion on TLB invalidations. */
- i = emit_pipe_invalidate(mask_flags, vm && vm->batch_invalidate_tlb, dw, i);
+ i = emit_pipe_invalidate(mask_flags, job->ring_ops_flush_tlb, dw, i);
/* hsdes: 1809175790 */
if (has_aux_ccs(xe))
diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
index 8151ddafb940..b0c7fa4693cf 100644
--- a/drivers/gpu/drm/xe/xe_sched_job.c
+++ b/drivers/gpu/drm/xe/xe_sched_job.c
@@ -250,6 +250,16 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
void xe_sched_job_arm(struct xe_sched_job *job)
{
+ struct xe_exec_queue *q = job->q;
+ struct xe_vm *vm = q->vm;
+
+ if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) &&
+ (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) {
+ xe_vm_assert_held(vm);
+ q->tlb_flush_seqno = vm->tlb_flush_seqno;
+ job->ring_ops_flush_tlb = true;
+ }
+
drm_sched_job_arm(&job->drm);
}
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index b1d83da50a53..5e12724219fd 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -39,6 +39,8 @@ struct xe_sched_job {
} user_fence;
/** @migrate_flush_flags: Additional flush flags for migration jobs */
u32 migrate_flush_flags;
+ /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
+ bool ring_ops_flush_tlb;
/** @batch_addr: batch buffer address of job */
u64 batch_addr[];
};
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index f88faef4142b..62d1ef8867a8 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -482,17 +482,53 @@ static int xe_gpuvm_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
return 0;
}
+/**
+ * xe_vm_validate_rebind() - Validate buffer objects and rebind vmas
+ * @vm: The vm for which we are rebinding.
+ * @exec: The struct drm_exec with the locked GEM objects.
+ * @num_fences: The number of fences to reserve for the operation, not
+ * including rebinds and validations.
+ *
+ * Validates all evicted gem objects and rebinds their vmas. Note that
+ * rebindings may cause evictions and hence the validation-rebind
+ * sequence is rerun until there are no more objects to validate.
+ *
+ * Return: 0 on success, negative error code on error. In particular,
+ * may return -EINTR or -ERESTARTSYS if interrupted, and -EDEADLK if
+ * the drm_exec transaction needs to be restarted.
+ */
+int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
+ unsigned int num_fences)
+{
+ struct drm_gem_object *obj;
+ unsigned long index;
+ int ret;
+
+ do {
+ ret = drm_gpuvm_validate(&vm->gpuvm, exec);
+ if (ret)
+ return ret;
+
+ ret = xe_vm_rebind(vm, false);
+ if (ret)
+ return ret;
+ } while (!list_empty(&vm->gpuvm.evict.list));
+
+ drm_exec_for_each_locked_object(exec, index, obj) {
+ ret = dma_resv_reserve_fences(obj->resv, num_fences);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
bool *done)
{
int err;
- /*
- * 1 fence for each preempt fence plus a fence for each tile from a
- * possible rebind
- */
- err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, vm->preempt.num_exec_queues +
- vm->xe->info.tile_count);
+ err = drm_gpuvm_prepare_vm(&vm->gpuvm, exec, 0);
if (err)
return err;
@@ -507,7 +543,7 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
return 0;
}
- err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, vm->preempt.num_exec_queues);
+ err = drm_gpuvm_prepare_objects(&vm->gpuvm, exec, 0);
if (err)
return err;
@@ -515,14 +551,19 @@ static int xe_preempt_work_begin(struct drm_exec *exec, struct xe_vm *vm,
if (err)
return err;
- return drm_gpuvm_validate(&vm->gpuvm, exec);
+ /*
+ * Add validation and rebinding to the locking loop since both can
+ * cause evictions which may require blocing dma_resv locks.
+ * The fence reservation here is intended for the new preempt fences
+ * we attach at the end of the rebind work.
+ */
+ return xe_vm_validate_rebind(vm, exec, vm->preempt.num_exec_queues);
}
static void preempt_rebind_work_func(struct work_struct *w)
{
struct xe_vm *vm = container_of(w, struct xe_vm, preempt.rebind_work);
struct drm_exec exec;
- struct dma_fence *rebind_fence;
unsigned int fence_count = 0;
LIST_HEAD(preempt_fences);
ktime_t end = 0;
@@ -568,18 +609,11 @@ retry:
if (err)
goto out_unlock;
- rebind_fence = xe_vm_rebind(vm, true);
- if (IS_ERR(rebind_fence)) {
- err = PTR_ERR(rebind_fence);
+ err = xe_vm_rebind(vm, true);
+ if (err)
goto out_unlock;
- }
- if (rebind_fence) {
- dma_fence_wait(rebind_fence, false);
- dma_fence_put(rebind_fence);
- }
-
- /* Wait on munmap style VM unbinds */
+ /* Wait on rebinds and munmap style VM unbinds */
wait = dma_resv_wait_timeout(xe_vm_resv(vm),
DMA_RESV_USAGE_KERNEL,
false, MAX_SCHEDULE_TIMEOUT);
@@ -773,14 +807,14 @@ xe_vm_bind_vma(struct xe_vma *vma, struct xe_exec_queue *q,
struct xe_sync_entry *syncs, u32 num_syncs,
bool first_op, bool last_op);
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
{
- struct dma_fence *fence = NULL;
+ struct dma_fence *fence;
struct xe_vma *vma, *next;
lockdep_assert_held(&vm->lock);
if (xe_vm_in_lr_mode(vm) && !rebind_worker)
- return NULL;
+ return 0;
xe_vm_assert_held(vm);
list_for_each_entry_safe(vma, next, &vm->rebind_list,
@@ -788,17 +822,17 @@ struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker)
xe_assert(vm->xe, vma->tile_present);
list_del_init(&vma->combined_links.rebind);
- dma_fence_put(fence);
if (rebind_worker)
trace_xe_vma_rebind_worker(vma);
else
trace_xe_vma_rebind_exec(vma);
fence = xe_vm_bind_vma(vma, NULL, NULL, 0, false, false);
if (IS_ERR(fence))
- return fence;
+ return PTR_ERR(fence);
+ dma_fence_put(fence);
}
- return fence;
+ return 0;
}
static void xe_vma_free(struct xe_vma *vma)
@@ -1004,35 +1038,26 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
}
/**
- * xe_vm_prepare_vma() - drm_exec utility to lock a vma
+ * xe_vm_lock_vma() - drm_exec utility to lock a vma
* @exec: The drm_exec object we're currently locking for.
* @vma: The vma for witch we want to lock the vm resv and any attached
* object's resv.
- * @num_shared: The number of dma-fence slots to pre-allocate in the
- * objects' reservation objects.
*
* Return: 0 on success, negative error code on error. In particular
* may return -EDEADLK on WW transaction contention and -EINTR if
* an interruptible wait is terminated by a signal.
*/
-int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
- unsigned int num_shared)
+int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma)
{
struct xe_vm *vm = xe_vma_vm(vma);
struct xe_bo *bo = xe_vma_bo(vma);
int err;
XE_WARN_ON(!vm);
- if (num_shared)
- err = drm_exec_prepare_obj(exec, xe_vm_obj(vm), num_shared);
- else
- err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
- if (!err && bo && !bo->vm) {
- if (num_shared)
- err = drm_exec_prepare_obj(exec, &bo->ttm.base, num_shared);
- else
- err = drm_exec_lock_obj(exec, &bo->ttm.base);
- }
+
+ err = drm_exec_lock_obj(exec, xe_vm_obj(vm));
+ if (!err && bo && !bo->vm)
+ err = drm_exec_lock_obj(exec, &bo->ttm.base);
return err;
}
@@ -1044,7 +1069,7 @@ static void xe_vma_destroy_unlocked(struct xe_vma *vma)
drm_exec_init(&exec, 0, 0);
drm_exec_until_all_locked(&exec) {
- err = xe_vm_prepare_vma(&exec, vma, 0);
+ err = xe_vm_lock_vma(&exec, vma);
drm_exec_retry_on_contention(&exec);
if (XE_WARN_ON(err))
break;
@@ -1589,7 +1614,6 @@ static void vm_destroy_work_func(struct work_struct *w)
XE_WARN_ON(vm->pt_root[id]);
trace_xe_vm_free(vm);
- dma_fence_put(vm->rebind_fence);
kfree(vm);
}
@@ -2512,7 +2536,7 @@ static int op_execute(struct drm_exec *exec, struct xe_vm *vm,
lockdep_assert_held_write(&vm->lock);
- err = xe_vm_prepare_vma(exec, vma, 1);
+ err = xe_vm_lock_vma(exec, vma);
if (err)
return err;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 6df1f1c7f85d..306cd0934a19 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -207,7 +207,7 @@ int __xe_vm_userptr_needs_repin(struct xe_vm *vm);
int xe_vm_userptr_check_repin(struct xe_vm *vm);
-struct dma_fence *xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
+int xe_vm_rebind(struct xe_vm *vm, bool rebind_worker);
int xe_vm_invalidate_vma(struct xe_vma *vma);
@@ -242,8 +242,10 @@ bool xe_vm_validate_should_retry(struct drm_exec *exec, int err, ktime_t *end);
int xe_analyze_vm(struct drm_printer *p, struct xe_vm *vm, int gt_id);
-int xe_vm_prepare_vma(struct drm_exec *exec, struct xe_vma *vma,
- unsigned int num_shared);
+int xe_vm_lock_vma(struct drm_exec *exec, struct xe_vma *vma);
+
+int xe_vm_validate_rebind(struct xe_vm *vm, struct drm_exec *exec,
+ unsigned int num_fences);
/**
* xe_vm_resv() - Return's the vm's reservation object
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index ae5fb565f6bf..badf3945083d 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -177,9 +177,6 @@ struct xe_vm {
*/
struct list_head rebind_list;
- /** @rebind_fence: rebind fence from execbuf */
- struct dma_fence *rebind_fence;
-
/**
* @destroy_work: worker to destroy VM, needed as a dma_fence signaling
* from an irq context can be last put and the destroy needs to be able
@@ -264,6 +261,11 @@ struct xe_vm {
bool capture_once;
} error_capture;
+ /**
+ * @tlb_flush_seqno: Required TLB flush seqno for the next exec.
+ * protected by the vm resv.
+ */
+ u64 tlb_flush_seqno;
/** @batch_invalidate_tlb: Always invalidate TLB before batch start */
bool batch_invalidate_tlb;
/** @xef: XE file handle for tracking this VM's drm client */
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 76f79b68cef8..888ca636f3f3 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -324,6 +324,7 @@ static void decode_ISR(unsigned int val)
decode_bits(KERN_DEBUG "ISR", isr_bits, ARRAY_SIZE(isr_bits), val);
}
+#ifdef CONFIG_I2C_PXA_SLAVE
static const struct bits icr_bits[] = {
PXA_BIT(ICR_START, "START", NULL),
PXA_BIT(ICR_STOP, "STOP", NULL),
@@ -342,7 +343,6 @@ static const struct bits icr_bits[] = {
PXA_BIT(ICR_UR, "UR", "ur"),
};
-#ifdef CONFIG_I2C_PXA_SLAVE
static void decode_ICR(unsigned int val)
{
decode_bits(KERN_DEBUG "ICR", icr_bits, ARRAY_SIZE(icr_bits), val);
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index e7a44929f0da..33228c1c8980 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -3228,7 +3228,7 @@ out:
static void iommu_snp_enable(void)
{
#ifdef CONFIG_KVM_AMD_SEV
- if (!cpu_feature_enabled(X86_FEATURE_SEV_SNP))
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return;
/*
* The SNP support requires that IOMMU must be enabled, and is
@@ -3236,12 +3236,14 @@ static void iommu_snp_enable(void)
*/
if (no_iommu || iommu_default_passthrough()) {
pr_err("SNP: IOMMU disabled or configured in passthrough mode, SNP cannot be supported.\n");
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
return;
}
amd_iommu_snp_en = check_feature(FEATURE_SNP);
if (!amd_iommu_snp_en) {
pr_err("SNP: IOMMU SNP feature not enabled, SNP cannot be supported.\n");
+ cc_platform_clear(CC_ATTR_HOST_SEV_SNP);
return;
}
diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index 2776ca5fc33f..b215b28cad7b 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -401,23 +401,23 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
}
static int data_sock_setsockopt(struct socket *sock, int level, int optname,
- sockptr_t optval, unsigned int len)
+ sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
int err = 0, opt = 0;
if (*debug & DEBUG_SOCKET)
printk(KERN_DEBUG "%s(%p, %d, %x, optval, %d)\n", __func__, sock,
- level, optname, len);
+ level, optname, optlen);
lock_sock(sk);
switch (optname) {
case MISDN_TIME_STAMP:
- if (copy_from_sockptr(&opt, optval, sizeof(int))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt)
_pms(sk)->cmask |= MISDN_TIME_STAMP;
diff --git a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
index 4c34344dc7dc..d7027d600208 100644
--- a/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
+++ b/drivers/media/platform/mediatek/vcodec/common/mtk_vcodec_fw_vpu.c
@@ -50,12 +50,12 @@ static void mtk_vcodec_vpu_reset_dec_handler(void *priv)
dev_err(&dev->plat_dev->dev, "Watchdog timeout!!");
- mutex_lock(&dev->dev_mutex);
+ mutex_lock(&dev->dev_ctx_lock);
list_for_each_entry(ctx, &dev->ctx_list, list) {
ctx->state = MTK_STATE_ABORT;
mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id);
}
- mutex_unlock(&dev->dev_mutex);
+ mutex_unlock(&dev->dev_ctx_lock);
}
static void mtk_vcodec_vpu_reset_enc_handler(void *priv)
@@ -65,12 +65,12 @@ static void mtk_vcodec_vpu_reset_enc_handler(void *priv)
dev_err(&dev->plat_dev->dev, "Watchdog timeout!!");
- mutex_lock(&dev->dev_mutex);
+ mutex_lock(&dev->dev_ctx_lock);
list_for_each_entry(ctx, &dev->ctx_list, list) {
ctx->state = MTK_STATE_ABORT;
mtk_v4l2_vdec_dbg(0, ctx, "[%d] Change to state MTK_STATE_ABORT", ctx->id);
}
- mutex_unlock(&dev->dev_mutex);
+ mutex_unlock(&dev->dev_ctx_lock);
}
static const struct mtk_vcodec_fw_ops mtk_vcodec_vpu_msg = {
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
index f47c98faf068..2073781ccadb 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.c
@@ -268,7 +268,9 @@ static int fops_vcodec_open(struct file *file)
ctx->dev->vdec_pdata->init_vdec_params(ctx);
+ mutex_lock(&dev->dev_ctx_lock);
list_add(&ctx->list, &dev->ctx_list);
+ mutex_unlock(&dev->dev_ctx_lock);
mtk_vcodec_dbgfs_create(ctx);
mutex_unlock(&dev->dev_mutex);
@@ -311,7 +313,9 @@ static int fops_vcodec_release(struct file *file)
v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
mtk_vcodec_dbgfs_remove(dev, ctx->id);
+ mutex_lock(&dev->dev_ctx_lock);
list_del_init(&ctx->list);
+ mutex_unlock(&dev->dev_ctx_lock);
kfree(ctx);
mutex_unlock(&dev->dev_mutex);
return 0;
@@ -404,6 +408,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
for (i = 0; i < MTK_VDEC_HW_MAX; i++)
mutex_init(&dev->dec_mutex[i]);
mutex_init(&dev->dev_mutex);
+ mutex_init(&dev->dev_ctx_lock);
spin_lock_init(&dev->irqlock);
snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s",
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
index 849b89dd205c..85b2c0d3d8bc 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
+++ b/drivers/media/platform/mediatek/vcodec/decoder/mtk_vcodec_dec_drv.h
@@ -241,6 +241,7 @@ struct mtk_vcodec_dec_ctx {
*
* @dec_mutex: decoder hardware lock
* @dev_mutex: video_device lock
+ * @dev_ctx_lock: the lock of context list
* @decode_workqueue: decode work queue
*
* @irqlock: protect data access by irq handler and work thread
@@ -282,6 +283,7 @@ struct mtk_vcodec_dec_dev {
/* decoder hardware mutex lock */
struct mutex dec_mutex[MTK_VDEC_HW_MAX];
struct mutex dev_mutex;
+ struct mutex dev_ctx_lock;
struct workqueue_struct *decode_workqueue;
spinlock_t irqlock;
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
index 06ed47df693b..21836dd6ef85 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_hevc_req_multi_if.c
@@ -869,7 +869,6 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx)
inst->vpu.codec_type = ctx->current_codec;
inst->vpu.capture_type = ctx->capture_fourcc;
- ctx->drv_handle = inst;
err = vpu_dec_init(&inst->vpu);
if (err) {
mtk_vdec_err(ctx, "vdec_hevc init err=%d", err);
@@ -898,6 +897,7 @@ static int vdec_hevc_slice_init(struct mtk_vcodec_dec_ctx *ctx)
mtk_vdec_debug(ctx, "lat hevc instance >> %p, codec_type = 0x%x",
inst, inst->vpu.codec_type);
+ ctx->drv_handle = inst;
return 0;
error_free_inst:
kfree(inst);
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
index 19407f9bc773..987b3d71b662 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
@@ -449,7 +449,7 @@ static int vdec_vp8_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
inst->frm_cnt, y_fb_dma, c_fb_dma, fb);
inst->cur_fb = fb;
- dec->bs_dma = (unsigned long)bs->dma_addr;
+ dec->bs_dma = (uint64_t)bs->dma_addr;
dec->bs_sz = bs->size;
dec->cur_y_fb_dma = y_fb_dma;
dec->cur_c_fb_dma = c_fb_dma;
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
index 55355fa70090..039082f600c8 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_if.c
@@ -16,6 +16,7 @@
#include "../vdec_drv_base.h"
#include "../vdec_vpu_if.h"
+#define VP9_MAX_SUPER_FRAMES_NUM 8
#define VP9_SUPER_FRAME_BS_SZ 64
#define MAX_VP9_DPB_SIZE 9
@@ -133,11 +134,11 @@ struct vp9_sf_ref_fb {
*/
struct vdec_vp9_vsi {
unsigned char sf_bs_buf[VP9_SUPER_FRAME_BS_SZ];
- struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_FRM_BUF_NUM-1];
+ struct vp9_sf_ref_fb sf_ref_fb[VP9_MAX_SUPER_FRAMES_NUM];
int sf_next_ref_fb_idx;
unsigned int sf_frm_cnt;
- unsigned int sf_frm_offset[VP9_MAX_FRM_BUF_NUM-1];
- unsigned int sf_frm_sz[VP9_MAX_FRM_BUF_NUM-1];
+ unsigned int sf_frm_offset[VP9_MAX_SUPER_FRAMES_NUM];
+ unsigned int sf_frm_sz[VP9_MAX_SUPER_FRAMES_NUM];
unsigned int sf_frm_idx;
unsigned int sf_init;
struct vdec_fb fb;
@@ -526,7 +527,7 @@ static void vp9_swap_frm_bufs(struct vdec_vp9_inst *inst)
/* if this super frame and it is not last sub-frame, get next fb for
* sub-frame decode
*/
- if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt - 1)
+ if (vsi->sf_frm_cnt > 0 && vsi->sf_frm_idx != vsi->sf_frm_cnt)
vsi->sf_next_ref_fb_idx = vp9_get_sf_ref_fb(inst);
}
@@ -735,7 +736,7 @@ static void get_free_fb(struct vdec_vp9_inst *inst, struct vdec_fb **out_fb)
static int validate_vsi_array_indexes(struct vdec_vp9_inst *inst,
struct vdec_vp9_vsi *vsi) {
- if (vsi->sf_frm_idx >= VP9_MAX_FRM_BUF_NUM - 1) {
+ if (vsi->sf_frm_idx > VP9_MAX_SUPER_FRAMES_NUM) {
mtk_vdec_err(inst->ctx, "Invalid vsi->sf_frm_idx=%u.", vsi->sf_frm_idx);
return -EIO;
}
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
index cf48d09b78d7..eea709d93820 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp9_req_lat_if.c
@@ -1074,7 +1074,7 @@ static int vdec_vp9_slice_setup_tile_buffer(struct vdec_vp9_slice_instance *inst
unsigned int mi_row;
unsigned int mi_col;
unsigned int offset;
- unsigned int pa;
+ dma_addr_t pa;
unsigned int size;
struct vdec_vp9_slice_tiles *tiles;
unsigned char *pos;
@@ -1109,7 +1109,7 @@ static int vdec_vp9_slice_setup_tile_buffer(struct vdec_vp9_slice_instance *inst
pos = va + offset;
end = va + bs->size;
/* truncated */
- pa = (unsigned int)bs->dma_addr + offset;
+ pa = bs->dma_addr + offset;
tb = instance->tile.va;
for (i = 0; i < rows; i++) {
for (j = 0; j < cols; j++) {
diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
index 82e57ae983d5..da6be556727b 100644
--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
+++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
@@ -77,12 +77,14 @@ static bool vpu_dec_check_ap_inst(struct mtk_vcodec_dec_dev *dec_dev, struct vde
struct mtk_vcodec_dec_ctx *ctx;
int ret = false;
+ mutex_lock(&dec_dev->dev_ctx_lock);
list_for_each_entry(ctx, &dec_dev->ctx_list, list) {
if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) {
ret = true;
break;
}
}
+ mutex_unlock(&dec_dev->dev_ctx_lock);
return ret;
}
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
index 6319f24bc714..3cb8a1622222 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.c
@@ -177,7 +177,9 @@ static int fops_vcodec_open(struct file *file)
mtk_v4l2_venc_dbg(2, ctx, "Create instance [%d]@%p m2m_ctx=%p ",
ctx->id, ctx, ctx->m2m_ctx);
+ mutex_lock(&dev->dev_ctx_lock);
list_add(&ctx->list, &dev->ctx_list);
+ mutex_unlock(&dev->dev_ctx_lock);
mutex_unlock(&dev->dev_mutex);
mtk_v4l2_venc_dbg(0, ctx, "%s encoder [%d]", dev_name(&dev->plat_dev->dev),
@@ -212,7 +214,9 @@ static int fops_vcodec_release(struct file *file)
v4l2_fh_exit(&ctx->fh);
v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
+ mutex_lock(&dev->dev_ctx_lock);
list_del_init(&ctx->list);
+ mutex_unlock(&dev->dev_ctx_lock);
kfree(ctx);
mutex_unlock(&dev->dev_mutex);
return 0;
@@ -294,6 +298,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
mutex_init(&dev->enc_mutex);
mutex_init(&dev->dev_mutex);
+ mutex_init(&dev->dev_ctx_lock);
spin_lock_init(&dev->irqlock);
snprintf(dev->v4l2_dev.name, sizeof(dev->v4l2_dev.name), "%s",
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
index a042f607ed8d..0bd85d0fb379 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
+++ b/drivers/media/platform/mediatek/vcodec/encoder/mtk_vcodec_enc_drv.h
@@ -178,6 +178,7 @@ struct mtk_vcodec_enc_ctx {
*
* @enc_mutex: encoder hardware lock.
* @dev_mutex: video_device lock
+ * @dev_ctx_lock: the lock of context list
* @encode_workqueue: encode work queue
*
* @enc_irq: h264 encoder irq resource
@@ -205,6 +206,7 @@ struct mtk_vcodec_enc_dev {
/* encoder hardware mutex lock */
struct mutex enc_mutex;
struct mutex dev_mutex;
+ struct mutex dev_ctx_lock;
struct workqueue_struct *encode_workqueue;
int enc_irq;
diff --git a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
index 84ad1cc6ad17..51bb7ee141b9 100644
--- a/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
+++ b/drivers/media/platform/mediatek/vcodec/encoder/venc_vpu_if.c
@@ -47,12 +47,14 @@ static bool vpu_enc_check_ap_inst(struct mtk_vcodec_enc_dev *enc_dev, struct ven
struct mtk_vcodec_enc_ctx *ctx;
int ret = false;
+ mutex_lock(&enc_dev->dev_ctx_lock);
list_for_each_entry(ctx, &enc_dev->ctx_list, list) {
if (!IS_ERR_OR_NULL(ctx) && ctx->vpu_inst == vpu) {
ret = true;
break;
}
}
+ mutex_unlock(&enc_dev->dev_ctx_lock);
return ret;
}
diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 97a00ec9a4d4..caacdc0a3819 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -209,7 +209,7 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
if (dev->bdev_file) {
invalidate_mapping_pages(dev->bdev_file->f_mapping, 0, -1);
- fput(dev->bdev_file);
+ bdev_fput(dev->bdev_file);
}
kfree(dev);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1035820c2377..c0d0bce0b594 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -950,20 +950,173 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface)
mutex_unlock(&priv->reg_mutex);
}
-/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std
- * 802.1Qâ„¢-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA
- * must only be propagated to C-VLAN and MAC Bridge components. That means
- * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports,
- * these frames are supposed to be processed by the CPU (software). So we make
- * the switch only forward them to the CPU port. And if received from a CPU
- * port, forward to a single port. The software is responsible of making the
- * switch conform to the latter by setting a single port as destination port on
- * the special tag.
+/* In Clause 5 of IEEE Std 802-2014, two sublayers of the data link layer (DLL)
+ * of the Open Systems Interconnection basic reference model (OSI/RM) are
+ * described; the medium access control (MAC) and logical link control (LLC)
+ * sublayers. The MAC sublayer is the one facing the physical layer.
*
- * This switch intellectual property cannot conform to this part of the standard
- * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC
- * DAs, it also includes :22-FF which the scope of propagation is not supposed
- * to be restricted for these MAC DAs.
+ * In 8.2 of IEEE Std 802.1Q-2022, the Bridge architecture is described. A
+ * Bridge component comprises a MAC Relay Entity for interconnecting the Ports
+ * of the Bridge, at least two Ports, and higher layer entities with at least a
+ * Spanning Tree Protocol Entity included.
+ *
+ * Each Bridge Port also functions as an end station and shall provide the MAC
+ * Service to an LLC Entity. Each instance of the MAC Service is provided to a
+ * distinct LLC Entity that supports protocol identification, multiplexing, and
+ * demultiplexing, for protocol data unit (PDU) transmission and reception by
+ * one or more higher layer entities.
+ *
+ * It is described in 8.13.9 of IEEE Std 802.1Q-2022 that in a Bridge, the LLC
+ * Entity associated with each Bridge Port is modeled as being directly
+ * connected to the attached Local Area Network (LAN).
+ *
+ * On the switch with CPU port architecture, CPU port functions as Management
+ * Port, and the Management Port functionality is provided by software which
+ * functions as an end station. Software is connected to an IEEE 802 LAN that is
+ * wholly contained within the system that incorporates the Bridge. Software
+ * provides access to the LLC Entity associated with each Bridge Port by the
+ * value of the source port field on the special tag on the frame received by
+ * software.
+ *
+ * We call frames that carry control information to determine the active
+ * topology and current extent of each Virtual Local Area Network (VLAN), i.e.,
+ * spanning tree or Shortest Path Bridging (SPB) and Multiple VLAN Registration
+ * Protocol Data Units (MVRPDUs), and frames from other link constrained
+ * protocols, such as Extensible Authentication Protocol over LAN (EAPOL) and
+ * Link Layer Discovery Protocol (LLDP), link-local frames. They are not
+ * forwarded by a Bridge. Permanently configured entries in the filtering
+ * database (FDB) ensure that such frames are discarded by the Forwarding
+ * Process. In 8.6.3 of IEEE Std 802.1Q-2022, this is described in detail:
+ *
+ * Each of the reserved MAC addresses specified in Table 8-1
+ * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]) shall be
+ * permanently configured in the FDB in C-VLAN components and ERs.
+ *
+ * Each of the reserved MAC addresses specified in Table 8-2
+ * (01-80-C2-00-00-[01,02,03,04,05,06,07,08,09,0A,0E]) shall be permanently
+ * configured in the FDB in S-VLAN components.
+ *
+ * Each of the reserved MAC addresses specified in Table 8-3
+ * (01-80-C2-00-00-[01,02,04,0E]) shall be permanently configured in the FDB in
+ * TPMR components.
+ *
+ * The FDB entries for reserved MAC addresses shall specify filtering for all
+ * Bridge Ports and all VIDs. Management shall not provide the capability to
+ * modify or remove entries for reserved MAC addresses.
+ *
+ * The addresses in Table 8-1, Table 8-2, and Table 8-3 determine the scope of
+ * propagation of PDUs within a Bridged Network, as follows:
+ *
+ * The Nearest Bridge group address (01-80-C2-00-00-0E) is an address that no
+ * conformant Two-Port MAC Relay (TPMR) component, Service VLAN (S-VLAN)
+ * component, Customer VLAN (C-VLAN) component, or MAC Bridge can forward.
+ * PDUs transmitted using this destination address, or any other addresses
+ * that appear in Table 8-1, Table 8-2, and Table 8-3
+ * (01-80-C2-00-00-[00,01,02,03,04,05,06,07,08,09,0A,0B,0C,0D,0E,0F]), can
+ * therefore travel no further than those stations that can be reached via a
+ * single individual LAN from the originating station.
+ *
+ * The Nearest non-TPMR Bridge group address (01-80-C2-00-00-03), is an
+ * address that no conformant S-VLAN component, C-VLAN component, or MAC
+ * Bridge can forward; however, this address is relayed by a TPMR component.
+ * PDUs using this destination address, or any of the other addresses that
+ * appear in both Table 8-1 and Table 8-2 but not in Table 8-3
+ * (01-80-C2-00-00-[00,03,05,06,07,08,09,0A,0B,0C,0D,0F]), will be relayed by
+ * any TPMRs but will propagate no further than the nearest S-VLAN component,
+ * C-VLAN component, or MAC Bridge.
+ *
+ * The Nearest Customer Bridge group address (01-80-C2-00-00-00) is an address
+ * that no conformant C-VLAN component, MAC Bridge can forward; however, it is
+ * relayed by TPMR components and S-VLAN components. PDUs using this
+ * destination address, or any of the other addresses that appear in Table 8-1
+ * but not in either Table 8-2 or Table 8-3 (01-80-C2-00-00-[00,0B,0C,0D,0F]),
+ * will be relayed by TPMR components and S-VLAN components but will propagate
+ * no further than the nearest C-VLAN component or MAC Bridge.
+ *
+ * Because the LLC Entity associated with each Bridge Port is provided via CPU
+ * port, we must not filter these frames but forward them to CPU port.
+ *
+ * In a Bridge, the transmission Port is majorly decided by ingress and egress
+ * rules, FDB, and spanning tree Port State functions of the Forwarding Process.
+ * For link-local frames, only CPU port should be designated as destination port
+ * in the FDB, and the other functions of the Forwarding Process must not
+ * interfere with the decision of the transmission Port. We call this process
+ * trapping frames to CPU port.
+ *
+ * Therefore, on the switch with CPU port architecture, link-local frames must
+ * be trapped to CPU port, and certain link-local frames received by a Port of a
+ * Bridge comprising a TPMR component or an S-VLAN component must be excluded
+ * from it.
+ *
+ * A Bridge of the switch with CPU port architecture cannot comprise a Two-Port
+ * MAC Relay (TPMR) component as a TPMR component supports only a subset of the
+ * functionality of a MAC Bridge. A Bridge comprising two Ports (Management Port
+ * doesn't count) of this architecture will either function as a standard MAC
+ * Bridge or a standard VLAN Bridge.
+ *
+ * Therefore, a Bridge of this architecture can only comprise S-VLAN components,
+ * C-VLAN components, or MAC Bridge components. Since there's no TPMR component,
+ * we don't need to relay PDUs using the destination addresses specified on the
+ * Nearest non-TPMR section, and the proportion of the Nearest Customer Bridge
+ * section where they must be relayed by TPMR components.
+ *
+ * One option to trap link-local frames to CPU port is to add static FDB entries
+ * with CPU port designated as destination port. However, because that
+ * Independent VLAN Learning (IVL) is being used on every VID, each entry only
+ * applies to a single VLAN Identifier (VID). For a Bridge comprising a MAC
+ * Bridge component or a C-VLAN component, there would have to be 16 times 4096
+ * entries. This switch intellectual property can only hold a maximum of 2048
+ * entries. Using this option, there also isn't a mechanism to prevent
+ * link-local frames from being discarded when the spanning tree Port State of
+ * the reception Port is discarding.
+ *
+ * The remaining option is to utilise the BPC, RGAC1, RGAC2, RGAC3, and RGAC4
+ * registers. Whilst this applies to every VID, it doesn't contain all of the
+ * reserved MAC addresses without affecting the remaining Standard Group MAC
+ * Addresses. The REV_UN frame tag utilised using the RGAC4 register covers the
+ * remaining 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F] destination
+ * addresses. It also includes the 01-80-C2-00-00-22 to 01-80-C2-00-00-FF
+ * destination addresses which may be relayed by MAC Bridges or VLAN Bridges.
+ * The latter option provides better but not complete conformance.
+ *
+ * This switch intellectual property also does not provide a mechanism to trap
+ * link-local frames with specific destination addresses to CPU port by Bridge,
+ * to conform to the filtering rules for the distinct Bridge components.
+ *
+ * Therefore, regardless of the type of the Bridge component, link-local frames
+ * with these destination addresses will be trapped to CPU port:
+ *
+ * 01-80-C2-00-00-[00,01,02,03,0E]
+ *
+ * In a Bridge comprising a MAC Bridge component or a C-VLAN component:
+ *
+ * Link-local frames with these destination addresses won't be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-[04,05,06,07,08,09,0A,0B,0C,0D,0F]
+ *
+ * In a Bridge comprising an S-VLAN component:
+ *
+ * Link-local frames with these destination addresses will be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-00
+ *
+ * Link-local frames with these destination addresses won't be trapped to CPU
+ * port which won't conform to IEEE Std 802.1Q-2022:
+ *
+ * 01-80-C2-00-00-[04,05,06,07,08,09,0A]
+ *
+ * To trap link-local frames to CPU port as conformant as this switch
+ * intellectual property can allow, link-local frames are made to be regarded as
+ * Bridge Protocol Data Units (BPDUs). This is because this switch intellectual
+ * property only lets the frames regarded as BPDUs bypass the spanning tree Port
+ * State function of the Forwarding Process.
+ *
+ * The only remaining interference is the ingress rules. When the reception Port
+ * has no PVID assigned on software, VLAN-untagged frames won't be allowed in.
+ * There doesn't seem to be a mechanism on the switch intellectual property to
+ * have link-local frames bypass this function of the Forwarding Process.
*/
static void
mt753x_trap_frames(struct mt7530_priv *priv)
@@ -971,35 +1124,43 @@ mt753x_trap_frames(struct mt7530_priv *priv)
/* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them
* VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK |
- MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
- MT753X_BPDU_PORT_FW_MASK,
- MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_BPC,
+ MT753X_PAE_BPDU_FR | MT753X_PAE_EG_TAG_MASK |
+ MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
+ MT753X_BPDU_PORT_FW_MASK,
+ MT753X_PAE_BPDU_FR |
+ MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
/* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK |
- MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK |
- MT753X_R01_PORT_FW_MASK,
- MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_RGAC1,
+ MT753X_R02_BPDU_FR | MT753X_R02_EG_TAG_MASK |
+ MT753X_R02_PORT_FW_MASK | MT753X_R01_BPDU_FR |
+ MT753X_R01_EG_TAG_MASK | MT753X_R01_PORT_FW_MASK,
+ MT753X_R02_BPDU_FR |
+ MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_R01_BPDU_FR |
+ MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
/* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress
* them VLAN-untagged.
*/
- mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK |
- MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK |
- MT753X_R03_PORT_FW_MASK,
- MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
- MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
- MT753X_BPDU_CPU_ONLY);
+ mt7530_rmw(priv, MT753X_RGAC2,
+ MT753X_R0E_BPDU_FR | MT753X_R0E_EG_TAG_MASK |
+ MT753X_R0E_PORT_FW_MASK | MT753X_R03_BPDU_FR |
+ MT753X_R03_EG_TAG_MASK | MT753X_R03_PORT_FW_MASK,
+ MT753X_R0E_BPDU_FR |
+ MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+ MT753X_R03_BPDU_FR |
+ MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+ MT753X_BPDU_CPU_ONLY);
}
static void
@@ -2505,18 +2666,25 @@ mt7531_setup(struct dsa_switch *ds)
mt7530_rmw(priv, MT7531_GPIO_MODE0, MT7531_GPIO0_MASK,
MT7531_GPIO0_INTERRUPT);
- /* Enable PHY core PLL, since phy_device has not yet been created
- * provided for phy_[read,write]_mmd_indirect is called, we provide
- * our own mt7531_ind_mmd_phy_[read,write] to complete this
- * function.
+ /* Enable Energy-Efficient Ethernet (EEE) and PHY core PLL, since
+ * phy_device has not yet been created provided for
+ * phy_[read,write]_mmd_indirect is called, we provide our own
+ * mt7531_ind_mmd_phy_[read,write] to complete this function.
*/
val = mt7531_ind_c45_phy_read(priv, MT753X_CTRL_PHY_ADDR,
MDIO_MMD_VEND2, CORE_PLL_GROUP4);
- val |= MT7531_PHY_PLL_BYPASS_MODE;
+ val |= MT7531_RG_SYSPLL_DMY2 | MT7531_PHY_PLL_BYPASS_MODE;
val &= ~MT7531_PHY_PLL_OFF;
mt7531_ind_c45_phy_write(priv, MT753X_CTRL_PHY_ADDR, MDIO_MMD_VEND2,
CORE_PLL_GROUP4, val);
+ /* Disable EEE advertisement on the switch PHYs. */
+ for (i = MT753X_CTRL_PHY_ADDR;
+ i < MT753X_CTRL_PHY_ADDR + MT7530_NUM_PHYS; i++) {
+ mt7531_ind_c45_phy_write(priv, i, MDIO_MMD_AN, MDIO_AN_EEE_ADV,
+ 0);
+ }
+
mt7531_setup_common(ds);
/* Setup VLAN ID 0 for VLAN-unaware bridges */
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index d17b318e6ee4..585db03c0548 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -65,6 +65,7 @@ enum mt753x_id {
/* Registers for BPDU and PAE frame control*/
#define MT753X_BPC 0x24
+#define MT753X_PAE_BPDU_FR BIT(25)
#define MT753X_PAE_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_PAE_EG_TAG(x) FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x)
#define MT753X_PAE_PORT_FW_MASK GENMASK(18, 16)
@@ -75,20 +76,24 @@ enum mt753x_id {
/* Register for :01 and :02 MAC DA frame control */
#define MT753X_RGAC1 0x28
+#define MT753X_R02_BPDU_FR BIT(25)
#define MT753X_R02_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_R02_EG_TAG(x) FIELD_PREP(MT753X_R02_EG_TAG_MASK, x)
#define MT753X_R02_PORT_FW_MASK GENMASK(18, 16)
#define MT753X_R02_PORT_FW(x) FIELD_PREP(MT753X_R02_PORT_FW_MASK, x)
+#define MT753X_R01_BPDU_FR BIT(9)
#define MT753X_R01_EG_TAG_MASK GENMASK(8, 6)
#define MT753X_R01_EG_TAG(x) FIELD_PREP(MT753X_R01_EG_TAG_MASK, x)
#define MT753X_R01_PORT_FW_MASK GENMASK(2, 0)
/* Register for :03 and :0E MAC DA frame control */
#define MT753X_RGAC2 0x2c
+#define MT753X_R0E_BPDU_FR BIT(25)
#define MT753X_R0E_EG_TAG_MASK GENMASK(24, 22)
#define MT753X_R0E_EG_TAG(x) FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x)
#define MT753X_R0E_PORT_FW_MASK GENMASK(18, 16)
#define MT753X_R0E_PORT_FW(x) FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x)
+#define MT753X_R03_BPDU_FR BIT(9)
#define MT753X_R03_EG_TAG_MASK GENMASK(8, 6)
#define MT753X_R03_EG_TAG(x) FIELD_PREP(MT753X_R03_EG_TAG_MASK, x)
#define MT753X_R03_PORT_FW_MASK GENMASK(2, 0)
@@ -616,6 +621,7 @@ enum mt7531_clk_skew {
#define RG_SYSPLL_DDSFBK_EN BIT(12)
#define RG_SYSPLL_BIAS_EN BIT(11)
#define RG_SYSPLL_BIAS_LPF_EN BIT(10)
+#define MT7531_RG_SYSPLL_DMY2 BIT(6)
#define MT7531_PHY_PLL_OFF BIT(5)
#define MT7531_PHY_PLL_BYPASS_MODE BIT(4)
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 9e9e4a03f1a8..2d8a66ea82fa 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -351,7 +351,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
ENA_COM_BOUNCE_BUFFER_CNTRL_CNT;
io_sq->bounce_buf_ctrl.next_to_use = 0;
- size = io_sq->bounce_buf_ctrl.buffer_size *
+ size = (size_t)io_sq->bounce_buf_ctrl.buffer_size *
io_sq->bounce_buf_ctrl.buffers_num;
dev_node = dev_to_node(ena_dev->dmadev);
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 09e7da1a69c9..be5acfa41ee0 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -718,8 +718,11 @@ void ena_unmap_tx_buff(struct ena_ring *tx_ring,
static void ena_free_tx_bufs(struct ena_ring *tx_ring)
{
bool print_once = true;
+ bool is_xdp_ring;
u32 i;
+ is_xdp_ring = ENA_IS_XDP_INDEX(tx_ring->adapter, tx_ring->qid);
+
for (i = 0; i < tx_ring->ring_size; i++) {
struct ena_tx_buffer *tx_info = &tx_ring->tx_buffer_info[i];
@@ -739,10 +742,15 @@ static void ena_free_tx_bufs(struct ena_ring *tx_ring)
ena_unmap_tx_buff(tx_ring, tx_info);
- dev_kfree_skb_any(tx_info->skb);
+ if (is_xdp_ring)
+ xdp_return_frame(tx_info->xdpf);
+ else
+ dev_kfree_skb_any(tx_info->skb);
}
- netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
- tx_ring->qid));
+
+ if (!is_xdp_ring)
+ netdev_tx_reset_queue(netdev_get_tx_queue(tx_ring->netdev,
+ tx_ring->qid));
}
static void ena_free_all_tx_bufs(struct ena_adapter *adapter)
@@ -3481,10 +3489,11 @@ static void check_for_missing_completions(struct ena_adapter *adapter)
{
struct ena_ring *tx_ring;
struct ena_ring *rx_ring;
- int i, budget, rc;
+ int qid, budget, rc;
int io_queue_count;
io_queue_count = adapter->xdp_num_queues + adapter->num_io_queues;
+
/* Make sure the driver doesn't turn the device in other process */
smp_rmb();
@@ -3497,27 +3506,29 @@ static void check_for_missing_completions(struct ena_adapter *adapter)
if (adapter->missing_tx_completion_to == ENA_HW_HINTS_NO_TIMEOUT)
return;
- budget = ENA_MONITORED_TX_QUEUES;
+ budget = min_t(u32, io_queue_count, ENA_MONITORED_TX_QUEUES);
- for (i = adapter->last_monitored_tx_qid; i < io_queue_count; i++) {
- tx_ring = &adapter->tx_ring[i];
- rx_ring = &adapter->rx_ring[i];
+ qid = adapter->last_monitored_tx_qid;
+
+ while (budget) {
+ qid = (qid + 1) % io_queue_count;
+
+ tx_ring = &adapter->tx_ring[qid];
+ rx_ring = &adapter->rx_ring[qid];
rc = check_missing_comp_in_tx_queue(adapter, tx_ring);
if (unlikely(rc))
return;
- rc = !ENA_IS_XDP_INDEX(adapter, i) ?
+ rc = !ENA_IS_XDP_INDEX(adapter, qid) ?
check_for_rx_interrupt_queue(adapter, rx_ring) : 0;
if (unlikely(rc))
return;
budget--;
- if (!budget)
- break;
}
- adapter->last_monitored_tx_qid = i % io_queue_count;
+ adapter->last_monitored_tx_qid = qid;
}
/* trigger napi schedule after 2 consecutive detections */
diff --git a/drivers/net/ethernet/amazon/ena/ena_xdp.c b/drivers/net/ethernet/amazon/ena/ena_xdp.c
index 337c435d3ce9..5b175e7e92a1 100644
--- a/drivers/net/ethernet/amazon/ena/ena_xdp.c
+++ b/drivers/net/ethernet/amazon/ena/ena_xdp.c
@@ -89,7 +89,7 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring,
rc = ena_xdp_tx_map_frame(tx_ring, tx_info, xdpf, &ena_tx_ctx);
if (unlikely(rc))
- return rc;
+ goto err;
ena_tx_ctx.req_id = req_id;
@@ -112,7 +112,9 @@ int ena_xdp_xmit_frame(struct ena_ring *tx_ring,
error_unmap_dma:
ena_unmap_tx_buff(tx_ring, tx_info);
+err:
tx_info->xdpf = NULL;
+
return rc;
}
diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c
index 9662ee72814c..536635e57727 100644
--- a/drivers/net/ethernet/amd/pds_core/core.c
+++ b/drivers/net/ethernet/amd/pds_core/core.c
@@ -593,6 +593,16 @@ err_out:
pdsc_teardown(pdsc, PDSC_TEARDOWN_RECOVERY);
}
+void pdsc_pci_reset_thread(struct work_struct *work)
+{
+ struct pdsc *pdsc = container_of(work, struct pdsc, pci_reset_work);
+ struct pci_dev *pdev = pdsc->pdev;
+
+ pci_dev_get(pdev);
+ pci_reset_function(pdev);
+ pci_dev_put(pdev);
+}
+
static void pdsc_check_pci_health(struct pdsc *pdsc)
{
u8 fw_status;
@@ -607,7 +617,8 @@ static void pdsc_check_pci_health(struct pdsc *pdsc)
if (fw_status != PDS_RC_BAD_PCI)
return;
- pci_reset_function(pdsc->pdev);
+ /* prevent deadlock between pdsc_reset_prepare and pdsc_health_thread */
+ queue_work(pdsc->wq, &pdsc->pci_reset_work);
}
void pdsc_health_thread(struct work_struct *work)
diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h
index 92d7657dd614..a3e17a0c187a 100644
--- a/drivers/net/ethernet/amd/pds_core/core.h
+++ b/drivers/net/ethernet/amd/pds_core/core.h
@@ -197,6 +197,7 @@ struct pdsc {
struct pdsc_qcq notifyqcq;
u64 last_eid;
struct pdsc_viftype *viftype_status;
+ struct work_struct pci_reset_work;
};
/** enum pds_core_dbell_bits - bitwise composition of dbell values.
@@ -313,5 +314,6 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
void pdsc_fw_down(struct pdsc *pdsc);
void pdsc_fw_up(struct pdsc *pdsc);
+void pdsc_pci_reset_thread(struct work_struct *work);
#endif /* _PDSC_H_ */
diff --git a/drivers/net/ethernet/amd/pds_core/dev.c b/drivers/net/ethernet/amd/pds_core/dev.c
index e494e1298dc9..495ef4ef8c10 100644
--- a/drivers/net/ethernet/amd/pds_core/dev.c
+++ b/drivers/net/ethernet/amd/pds_core/dev.c
@@ -229,6 +229,9 @@ int pdsc_devcmd_reset(struct pdsc *pdsc)
.reset.opcode = PDS_CORE_CMD_RESET,
};
+ if (!pdsc_is_fw_running(pdsc))
+ return 0;
+
return pdsc_devcmd(pdsc, &cmd, &comp, pdsc->devcmd_timeout);
}
diff --git a/drivers/net/ethernet/amd/pds_core/main.c b/drivers/net/ethernet/amd/pds_core/main.c
index ab6133e7db42..660268ff9562 100644
--- a/drivers/net/ethernet/amd/pds_core/main.c
+++ b/drivers/net/ethernet/amd/pds_core/main.c
@@ -239,6 +239,7 @@ static int pdsc_init_pf(struct pdsc *pdsc)
snprintf(wq_name, sizeof(wq_name), "%s.%d", PDS_CORE_DRV_NAME, pdsc->uid);
pdsc->wq = create_singlethread_workqueue(wq_name);
INIT_WORK(&pdsc->health_work, pdsc_health_thread);
+ INIT_WORK(&pdsc->pci_reset_work, pdsc_pci_reset_thread);
timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
pdsc->wdtimer_period = PDSC_WATCHDOG_SECS * HZ;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d728df139c9c..a30df865be7b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11991,6 +11991,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
/* VF-reps may need to be re-opened after the PF is re-opened */
if (BNXT_PF(bp))
bnxt_vf_reps_open(bp);
+ if (bp->ptp_cfg)
+ atomic_set(&bp->ptp_cfg->tx_avail, BNXT_MAX_TX_TS);
bnxt_ptp_init_rtc(bp, true);
bnxt_ptp_cfg_tstamp_filters(bp);
if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index edb10aebd095..d8927838f1cf 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -252,6 +252,9 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
if (err)
return;
+ if (edev->ulp_tbl->msix_requested)
+ bnxt_fill_msix_vecs(bp, edev->msix_entries);
+
if (aux_priv) {
struct auxiliary_device *adev;
@@ -457,12 +460,13 @@ void bnxt_rdma_aux_device_init(struct bnxt *bp)
if (!edev)
goto aux_dev_uninit;
+ aux_priv->edev = edev;
+
ulp = kzalloc(sizeof(*ulp), GFP_KERNEL);
if (!ulp)
goto aux_dev_uninit;
edev->ulp_tbl = ulp;
- aux_priv->edev = edev;
bp->edev = edev;
bnxt_set_edev_info(edev, bp);
bp->ulp_num_msix_want = bnxt_set_dflt_ulp_msix(bp);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index d39001cdc707..00af8888e329 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -4819,18 +4819,18 @@ static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw)
*/
rvu_write64(rvu, blkaddr, NIX_AF_CFG,
rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x40ULL);
+ }
- /* Set chan/link to backpressure TL3 instead of TL2 */
- rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01);
+ /* Set chan/link to backpressure TL3 instead of TL2 */
+ rvu_write64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL, 0x01);
- /* Disable SQ manager's sticky mode operation (set TM6 = 0)
- * This sticky mode is known to cause SQ stalls when multiple
- * SQs are mapped to same SMQ and transmitting pkts at a time.
- */
- cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS);
- cfg &= ~BIT_ULL(15);
- rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg);
- }
+ /* Disable SQ manager's sticky mode operation (set TM6 = 0)
+ * This sticky mode is known to cause SQ stalls when multiple
+ * SQs are mapped to same SMQ and transmitting pkts at a time.
+ */
+ cfg = rvu_read64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS);
+ cfg &= ~BIT_ULL(15);
+ rvu_write64(rvu, blkaddr, NIX_AF_SQM_DBG_CTL_STATUS, cfg);
ltdefs = rvu->kpu.lt_def;
/* Calibrate X2P bus to check if CGX/LBK links are fine */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
index 1e77bbf5d22a..1723e9912ae0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos.c
@@ -382,6 +382,7 @@ static void otx2_qos_read_txschq_cfg_tl(struct otx2_qos_node *parent,
otx2_qos_read_txschq_cfg_tl(node, cfg);
cnt = cfg->static_node_pos[node->level];
cfg->schq_contig_list[node->level][cnt] = node->schq;
+ cfg->schq_index_used[node->level][cnt] = true;
cfg->schq_contig[node->level]++;
cfg->static_node_pos[node->level]++;
otx2_qos_read_txschq_cfg_schq(node, cfg);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 86f1854698b4..883c044852f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -95,9 +95,15 @@ static inline void mlx5e_ptp_metadata_fifo_push(struct mlx5e_ptp_metadata_fifo *
}
static inline u8
+mlx5e_ptp_metadata_fifo_peek(struct mlx5e_ptp_metadata_fifo *fifo)
+{
+ return fifo->data[fifo->mask & fifo->cc];
+}
+
+static inline void
mlx5e_ptp_metadata_fifo_pop(struct mlx5e_ptp_metadata_fifo *fifo)
{
- return fifo->data[fifo->mask & fifo->cc++];
+ fifo->cc++;
}
static inline void
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
index e87e26f2c669..6743806b8480 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/qos.c
@@ -83,24 +83,25 @@ int mlx5e_open_qos_sq(struct mlx5e_priv *priv, struct mlx5e_channels *chs,
txq_ix = mlx5e_qid_from_qos(chs, node_qid);
- WARN_ON(node_qid > priv->htb_max_qos_sqs);
- if (node_qid == priv->htb_max_qos_sqs) {
- struct mlx5e_sq_stats *stats, **stats_list = NULL;
-
- if (priv->htb_max_qos_sqs == 0) {
- stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev),
- sizeof(*stats_list),
- GFP_KERNEL);
- if (!stats_list)
- return -ENOMEM;
- }
+ WARN_ON(node_qid >= mlx5e_htb_cur_leaf_nodes(priv->htb));
+ if (!priv->htb_qos_sq_stats) {
+ struct mlx5e_sq_stats **stats_list;
+
+ stats_list = kvcalloc(mlx5e_qos_max_leaf_nodes(priv->mdev),
+ sizeof(*stats_list), GFP_KERNEL);
+ if (!stats_list)
+ return -ENOMEM;
+
+ WRITE_ONCE(priv->htb_qos_sq_stats, stats_list);
+ }
+
+ if (!priv->htb_qos_sq_stats[node_qid]) {
+ struct mlx5e_sq_stats *stats;
+
stats = kzalloc(sizeof(*stats), GFP_KERNEL);
- if (!stats) {
- kvfree(stats_list);
+ if (!stats)
return -ENOMEM;
- }
- if (stats_list)
- WRITE_ONCE(priv->htb_qos_sq_stats, stats_list);
+
WRITE_ONCE(priv->htb_qos_sq_stats[node_qid], stats);
/* Order htb_max_qos_sqs increment after writing the array pointer.
* Pairs with smp_load_acquire in en_stats.c.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
index bcafb4bf9415..8d9a3b5ec973 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.c
@@ -179,6 +179,13 @@ u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels)
return min_t(u32, rqt_size, max_cap_rqt_size);
}
+#define MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH 256
+
+unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void)
+{
+ return MLX5E_MAX_RQT_SIZE_ALLOWED_WITH_XOR8_HASH / MLX5E_UNIFORM_SPREAD_RQT_FACTOR;
+}
+
void mlx5e_rqt_destroy(struct mlx5e_rqt *rqt)
{
mlx5_core_destroy_rqt(rqt->mdev, rqt->rqtn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
index e0bc30308c77..2f9e04a8418f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rqt.h
@@ -38,6 +38,7 @@ static inline u32 mlx5e_rqt_get_rqtn(struct mlx5e_rqt *rqt)
}
u32 mlx5e_rqt_size(struct mlx5_core_dev *mdev, unsigned int num_channels);
+unsigned int mlx5e_rqt_max_num_channels_allowed_for_xor8(void);
int mlx5e_rqt_redirect_direct(struct mlx5e_rqt *rqt, u32 rqn, u32 *vhca_id);
int mlx5e_rqt_redirect_indir(struct mlx5e_rqt *rqt, u32 *rqns, u32 *vhca_ids,
unsigned int num_rqns,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
index f675b1926340..f66bbc846464 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/selq.c
@@ -57,6 +57,7 @@ int mlx5e_selq_init(struct mlx5e_selq *selq, struct mutex *state_lock)
void mlx5e_selq_cleanup(struct mlx5e_selq *selq)
{
+ mutex_lock(selq->state_lock);
WARN_ON_ONCE(selq->is_prepared);
kvfree(selq->standby);
@@ -67,6 +68,7 @@ void mlx5e_selq_cleanup(struct mlx5e_selq *selq)
kvfree(selq->standby);
selq->standby = NULL;
+ mutex_unlock(selq->state_lock);
}
void mlx5e_selq_prepare_params(struct mlx5e_selq *selq, struct mlx5e_params *params)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a4fe164a1c4c..2261a2b854dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -457,6 +457,34 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
mutex_lock(&priv->state_lock);
+ if (mlx5e_rx_res_get_current_hash(priv->rx_res).hfunc == ETH_RSS_HASH_XOR) {
+ unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8();
+
+ if (count > xor8_max_channels) {
+ err = -EINVAL;
+ netdev_err(priv->netdev, "%s: Requested number of channels (%d) exceeds the maximum allowed by the XOR8 RSS hfunc (%d)\n",
+ __func__, count, xor8_max_channels);
+ goto out;
+ }
+ }
+
+ /* If RXFH is configured, changing the channels number is allowed only if
+ * it does not require resizing the RSS table. This is because the previous
+ * configuration may no longer be compatible with the new RSS table.
+ */
+ if (netif_is_rxfh_configured(priv->netdev)) {
+ int cur_rqt_size = mlx5e_rqt_size(priv->mdev, cur_params->num_channels);
+ int new_rqt_size = mlx5e_rqt_size(priv->mdev, count);
+
+ if (new_rqt_size != cur_rqt_size) {
+ err = -EINVAL;
+ netdev_err(priv->netdev,
+ "%s: RXFH is configured, block changing channels number that affects RSS table size (new: %d, current: %d)\n",
+ __func__, new_rqt_size, cur_rqt_size);
+ goto out;
+ }
+ }
+
/* Don't allow changing the number of channels if HTB offload is active,
* because the numeration of the QoS SQs will change, while per-queue
* qdiscs are attached.
@@ -1287,17 +1315,30 @@ static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxf
struct mlx5e_priv *priv = netdev_priv(dev);
u32 *rss_context = &rxfh->rss_context;
u8 hfunc = rxfh->hfunc;
+ unsigned int count;
int err;
mutex_lock(&priv->state_lock);
+
+ count = priv->channels.params.num_channels;
+
+ if (hfunc == ETH_RSS_HASH_XOR) {
+ unsigned int xor8_max_channels = mlx5e_rqt_max_num_channels_allowed_for_xor8();
+
+ if (count > xor8_max_channels) {
+ err = -EINVAL;
+ netdev_err(priv->netdev, "%s: Cannot set RSS hash function to XOR, current number of channels (%d) exceeds the maximum allowed for XOR8 RSS hfunc (%d)\n",
+ __func__, count, xor8_max_channels);
+ goto unlock;
+ }
+ }
+
if (*rss_context && rxfh->rss_delete) {
err = mlx5e_rx_res_rss_destroy(priv->rx_res, *rss_context);
goto unlock;
}
if (*rss_context == ETH_RXFH_CONTEXT_ALLOC) {
- unsigned int count = priv->channels.params.num_channels;
-
err = mlx5e_rx_res_rss_init(priv->rx_res, rss_context, count);
if (err)
goto unlock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a0d3af96dcb1..dec60a6836db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5723,9 +5723,7 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
kfree(priv->tx_rates);
kfree(priv->txq2sq);
destroy_workqueue(priv->wq);
- mutex_lock(&priv->state_lock);
mlx5e_selq_cleanup(&priv->selq);
- mutex_unlock(&priv->state_lock);
free_cpumask_var(priv->scratchpad.cpumask);
for (i = 0; i < priv->htb_max_qos_sqs; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 09a592909101..099bf1078889 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -398,6 +398,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) {
u8 metadata_index = be32_to_cpu(eseg->flow_table_metadata);
+ mlx5e_ptp_metadata_fifo_pop(&sq->ptpsq->metadata_freelist);
+
mlx5e_skb_cb_hwtstamp_init(skb);
mlx5e_ptp_metadata_map_put(&sq->ptpsq->metadata_map, skb,
metadata_index);
@@ -496,9 +498,6 @@ mlx5e_sq_xmit_wqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
err_drop:
stats->dropped++;
- if (unlikely(sq->ptpsq && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
- mlx5e_ptp_metadata_fifo_push(&sq->ptpsq->metadata_freelist,
- be32_to_cpu(eseg->flow_table_metadata));
dev_kfree_skb_any(skb);
mlx5e_tx_flush(sq);
}
@@ -657,7 +656,7 @@ static void mlx5e_cqe_ts_id_eseg(struct mlx5e_ptpsq *ptpsq, struct sk_buff *skb,
{
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
eseg->flow_table_metadata =
- cpu_to_be32(mlx5e_ptp_metadata_fifo_pop(&ptpsq->metadata_freelist));
+ cpu_to_be32(mlx5e_ptp_metadata_fifo_peek(&ptpsq->metadata_freelist));
}
static void mlx5e_txwqe_build_eseg(struct mlx5e_priv *priv, struct mlx5e_txqsq *sq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 3047d7015c52..1789800faaeb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1868,6 +1868,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
if (err)
goto abort;
+ dev->priv.eswitch = esw;
err = esw_offloads_init(esw);
if (err)
goto reps_err;
@@ -1892,11 +1893,6 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_BASIC;
else
esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
- if (MLX5_ESWITCH_MANAGER(dev) &&
- mlx5_esw_vport_match_metadata_supported(esw))
- esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
-
- dev->priv.eswitch = esw;
BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
esw_info(dev,
@@ -1908,6 +1904,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
reps_err:
mlx5_esw_vports_cleanup(esw);
+ dev->priv.eswitch = NULL;
abort:
if (esw->work_queue)
destroy_workqueue(esw->work_queue);
@@ -1926,7 +1923,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
esw_info(esw->dev, "cleanup\n");
- esw->dev->priv.eswitch = NULL;
destroy_workqueue(esw->work_queue);
WARN_ON(refcount_read(&esw->qos.refcnt));
mutex_destroy(&esw->state_lock);
@@ -1937,6 +1933,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
mutex_destroy(&esw->offloads.encap_tbl_lock);
mutex_destroy(&esw->offloads.decap_tbl_lock);
esw_offloads_cleanup(esw);
+ esw->dev->priv.eswitch = NULL;
mlx5_esw_vports_cleanup(esw);
debugfs_remove_recursive(esw->debugfs_root);
devl_params_unregister(priv_to_devlink(esw->dev), mlx5_eswitch_params,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 20927f65ac2c..8a359d283bb2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -43,6 +43,7 @@
#include "rdma.h"
#include "en.h"
#include "fs_core.h"
+#include "lib/mlx5.h"
#include "lib/devcom.h"
#include "lib/eq.h"
#include "lib/fs_chains.h"
@@ -2478,6 +2479,10 @@ int esw_offloads_init(struct mlx5_eswitch *esw)
if (err)
return err;
+ if (MLX5_ESWITCH_MANAGER(esw->dev) &&
+ mlx5_esw_vport_match_metadata_supported(esw))
+ esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
+
err = devl_params_register(priv_to_devlink(esw->dev),
esw_devlink_params,
ARRAY_SIZE(esw_devlink_params));
@@ -3709,6 +3714,12 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
if (esw_mode_from_devlink(mode, &mlx5_mode))
return -EINVAL;
+ if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && mlx5_get_sd(esw->dev)) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured.");
+ return -EPERM;
+ }
+
mlx5_lag_disable_change(esw->dev);
err = mlx5_esw_try_lock(esw);
if (err < 0) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index e6bfa7e4f146..cf085a478e3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1664,6 +1664,16 @@ static int create_auto_flow_group(struct mlx5_flow_table *ft,
return err;
}
+static bool mlx5_pkt_reformat_cmp(struct mlx5_pkt_reformat *p1,
+ struct mlx5_pkt_reformat *p2)
+{
+ return p1->owner == p2->owner &&
+ (p1->owner == MLX5_FLOW_RESOURCE_OWNER_FW ?
+ p1->id == p2->id :
+ mlx5_fs_dr_action_get_pkt_reformat_id(p1) ==
+ mlx5_fs_dr_action_get_pkt_reformat_id(p2));
+}
+
static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
struct mlx5_flow_destination *d2)
{
@@ -1675,8 +1685,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ?
(d1->vport.vhca_id == d2->vport.vhca_id) : true) &&
((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
- (d1->vport.pkt_reformat->id ==
- d2->vport.pkt_reformat->id) : true)) ||
+ mlx5_pkt_reformat_cmp(d1->vport.pkt_reformat,
+ d2->vport.pkt_reformat) : true)) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
d1->ft == d2->ft) ||
(d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
@@ -1808,8 +1818,9 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
}
trace_mlx5_fs_set_fte(fte, false);
+ /* Link newly added rules into the tree. */
for (i = 0; i < handle->num_rules; i++) {
- if (refcount_read(&handle->rule[i]->node.refcount) == 1) {
+ if (!handle->rule[i]->node.parent) {
tree_add_node(&handle->rule[i]->node, &fte->node);
trace_mlx5_fs_add_rule(handle->rule[i]);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index c2593625c09a..59806553889e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1480,6 +1480,14 @@ int mlx5_init_one_devl_locked(struct mlx5_core_dev *dev)
if (err)
goto err_register;
+ err = mlx5_crdump_enable(dev);
+ if (err)
+ mlx5_core_err(dev, "mlx5_crdump_enable failed with error code %d\n", err);
+
+ err = mlx5_hwmon_dev_register(dev);
+ if (err)
+ mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
+
mutex_unlock(&dev->intf_state_mutex);
return 0;
@@ -1505,7 +1513,10 @@ int mlx5_init_one(struct mlx5_core_dev *dev)
int err;
devl_lock(devlink);
+ devl_register(devlink);
err = mlx5_init_one_devl_locked(dev);
+ if (err)
+ devl_unregister(devlink);
devl_unlock(devlink);
return err;
}
@@ -1517,6 +1528,8 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev)
devl_lock(devlink);
mutex_lock(&dev->intf_state_mutex);
+ mlx5_hwmon_dev_unregister(dev);
+ mlx5_crdump_disable(dev);
mlx5_unregister_device(dev);
if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
@@ -1534,6 +1547,7 @@ void mlx5_uninit_one(struct mlx5_core_dev *dev)
mlx5_function_teardown(dev, true);
out:
mutex_unlock(&dev->intf_state_mutex);
+ devl_unregister(devlink);
devl_unlock(devlink);
}
@@ -1680,16 +1694,20 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev)
}
devl_lock(devlink);
+ devl_register(devlink);
+
err = mlx5_devlink_params_register(priv_to_devlink(dev));
- devl_unlock(devlink);
if (err) {
mlx5_core_warn(dev, "mlx5_devlink_param_reg err = %d\n", err);
goto query_hca_caps_err;
}
+ devl_unlock(devlink);
return 0;
query_hca_caps_err:
+ devl_unregister(devlink);
+ devl_unlock(devlink);
mlx5_function_disable(dev, true);
out:
dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
@@ -1702,6 +1720,7 @@ void mlx5_uninit_one_light(struct mlx5_core_dev *dev)
devl_lock(devlink);
mlx5_devlink_params_unregister(priv_to_devlink(dev));
+ devl_unregister(devlink);
devl_unlock(devlink);
if (dev->state != MLX5_DEVICE_STATE_UP)
return;
@@ -1943,16 +1962,7 @@ static int probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
goto err_init_one;
}
- err = mlx5_crdump_enable(dev);
- if (err)
- dev_err(&pdev->dev, "mlx5_crdump_enable failed with error code %d\n", err);
-
- err = mlx5_hwmon_dev_register(dev);
- if (err)
- mlx5_core_err(dev, "mlx5_hwmon_dev_register failed with error code %d\n", err);
-
pci_save_state(pdev);
- devlink_register(devlink);
return 0;
err_init_one:
@@ -1973,16 +1983,9 @@ static void remove_one(struct pci_dev *pdev)
struct devlink *devlink = priv_to_devlink(dev);
set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
- /* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using
- * devlink notify APIs.
- * Hence, we must drain them before unregistering the devlink.
- */
mlx5_drain_fw_reset(dev);
mlx5_drain_health_wq(dev);
- devlink_unregister(devlink);
mlx5_sriov_disable(pdev, false);
- mlx5_hwmon_dev_unregister(dev);
- mlx5_crdump_disable(dev);
mlx5_uninit_one(dev);
mlx5_pci_close(dev);
mlx5_mdev_uninit(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 4dcf995cb1a2..6bac8ad70ba6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -19,6 +19,7 @@
#define MLX5_IRQ_CTRL_SF_MAX 8
/* min num of vectors for SFs to be enabled */
#define MLX5_IRQ_VEC_COMP_BASE_SF 2
+#define MLX5_IRQ_VEC_COMP_BASE 1
#define MLX5_EQ_SHARE_IRQ_MAX_COMP (8)
#define MLX5_EQ_SHARE_IRQ_MAX_CTRL (UINT_MAX)
@@ -246,6 +247,7 @@ static void irq_set_name(struct mlx5_irq_pool *pool, char *name, int vecidx)
return;
}
+ vecidx -= MLX5_IRQ_VEC_COMP_BASE;
snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", vecidx);
}
@@ -585,7 +587,7 @@ struct mlx5_irq *mlx5_irq_request_vector(struct mlx5_core_dev *dev, u16 cpu,
struct mlx5_irq_table *table = mlx5_irq_table_get(dev);
struct mlx5_irq_pool *pool = table->pcif_pool;
struct irq_affinity_desc af_desc;
- int offset = 1;
+ int offset = MLX5_IRQ_VEC_COMP_BASE;
if (!pool->xa_num_irqs.max)
offset = 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
index bc863e1f062e..e3bf8c7e4baa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
@@ -101,7 +101,6 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
devlink = priv_to_devlink(mdev);
set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
mlx5_drain_health_wq(mdev);
- devlink_unregister(devlink);
if (mlx5_dev_is_lightweight(mdev))
mlx5_uninit_one_light(mdev);
else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
index 64f4cc284aea..030a5776c937 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.c
@@ -205,12 +205,11 @@ dr_dump_hex_print(char hex[DR_HEX_SIZE], char *src, u32 size)
}
static int
-dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id,
+dr_dump_rule_action_mem(struct seq_file *file, char *buff, const u64 rule_id,
struct mlx5dr_rule_action_member *action_mem)
{
struct mlx5dr_action *action = action_mem->action;
const u64 action_id = DR_DBG_PTR_TO_ID(action);
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
u64 hit_tbl_ptr, miss_tbl_ptr;
u32 hit_tbl_id, miss_tbl_id;
int ret;
@@ -488,10 +487,9 @@ dr_dump_rule_action_mem(struct seq_file *file, const u64 rule_id,
}
static int
-dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste,
+dr_dump_rule_mem(struct seq_file *file, char *buff, struct mlx5dr_ste *ste,
bool is_rx, const u64 rule_id, u8 format_ver)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
char hw_ste_dump[DR_HEX_SIZE];
u32 mem_rec_type;
int ret;
@@ -522,7 +520,8 @@ dr_dump_rule_mem(struct seq_file *file, struct mlx5dr_ste *ste,
}
static int
-dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx,
+dr_dump_rule_rx_tx(struct seq_file *file, char *buff,
+ struct mlx5dr_rule_rx_tx *rule_rx_tx,
bool is_rx, const u64 rule_id, u8 format_ver)
{
struct mlx5dr_ste *ste_arr[DR_RULE_MAX_STES + DR_ACTION_MAX_STES];
@@ -533,7 +532,7 @@ dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx,
return 0;
while (i--) {
- ret = dr_dump_rule_mem(file, ste_arr[i], is_rx, rule_id,
+ ret = dr_dump_rule_mem(file, buff, ste_arr[i], is_rx, rule_id,
format_ver);
if (ret < 0)
return ret;
@@ -542,7 +541,8 @@ dr_dump_rule_rx_tx(struct seq_file *file, struct mlx5dr_rule_rx_tx *rule_rx_tx,
return 0;
}
-static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
+static noinline_for_stack int
+dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
{
struct mlx5dr_rule_action_member *action_mem;
const u64 rule_id = DR_DBG_PTR_TO_ID(rule);
@@ -565,19 +565,19 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
return ret;
if (rx->nic_matcher) {
- ret = dr_dump_rule_rx_tx(file, rx, true, rule_id, format_ver);
+ ret = dr_dump_rule_rx_tx(file, buff, rx, true, rule_id, format_ver);
if (ret < 0)
return ret;
}
if (tx->nic_matcher) {
- ret = dr_dump_rule_rx_tx(file, tx, false, rule_id, format_ver);
+ ret = dr_dump_rule_rx_tx(file, buff, tx, false, rule_id, format_ver);
if (ret < 0)
return ret;
}
list_for_each_entry(action_mem, &rule->rule_actions_list, list) {
- ret = dr_dump_rule_action_mem(file, rule_id, action_mem);
+ ret = dr_dump_rule_action_mem(file, buff, rule_id, action_mem);
if (ret < 0)
return ret;
}
@@ -586,10 +586,10 @@ static int dr_dump_rule(struct seq_file *file, struct mlx5dr_rule *rule)
}
static int
-dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask,
+dr_dump_matcher_mask(struct seq_file *file, char *buff,
+ struct mlx5dr_match_param *mask,
u8 criteria, const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
char dump[DR_HEX_SIZE];
int ret;
@@ -681,10 +681,10 @@ dr_dump_matcher_mask(struct seq_file *file, struct mlx5dr_match_param *mask,
}
static int
-dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder,
+dr_dump_matcher_builder(struct seq_file *file, char *buff,
+ struct mlx5dr_ste_build *builder,
u32 index, bool is_rx, const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -702,11 +702,10 @@ dr_dump_matcher_builder(struct seq_file *file, struct mlx5dr_ste_build *builder,
}
static int
-dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx,
+dr_dump_matcher_rx_tx(struct seq_file *file, char *buff, bool is_rx,
struct mlx5dr_matcher_rx_tx *matcher_rx_tx,
const u64 matcher_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
enum dr_dump_rec_type rec_type;
u64 s_icm_addr, e_icm_addr;
int i, ret;
@@ -731,7 +730,7 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx,
return ret;
for (i = 0; i < matcher_rx_tx->num_of_builders; i++) {
- ret = dr_dump_matcher_builder(file,
+ ret = dr_dump_matcher_builder(file, buff,
&matcher_rx_tx->ste_builder[i],
i, is_rx, matcher_id);
if (ret < 0)
@@ -741,7 +740,7 @@ dr_dump_matcher_rx_tx(struct seq_file *file, bool is_rx,
return 0;
}
-static int
+static noinline_for_stack int
dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher)
{
struct mlx5dr_matcher_rx_tx *rx = &matcher->rx;
@@ -763,19 +762,19 @@ dr_dump_matcher(struct seq_file *file, struct mlx5dr_matcher *matcher)
if (ret)
return ret;
- ret = dr_dump_matcher_mask(file, &matcher->mask,
+ ret = dr_dump_matcher_mask(file, buff, &matcher->mask,
matcher->match_criteria, matcher_id);
if (ret < 0)
return ret;
if (rx->nic_tbl) {
- ret = dr_dump_matcher_rx_tx(file, true, rx, matcher_id);
+ ret = dr_dump_matcher_rx_tx(file, buff, true, rx, matcher_id);
if (ret < 0)
return ret;
}
if (tx->nic_tbl) {
- ret = dr_dump_matcher_rx_tx(file, false, tx, matcher_id);
+ ret = dr_dump_matcher_rx_tx(file, buff, false, tx, matcher_id);
if (ret < 0)
return ret;
}
@@ -803,11 +802,10 @@ dr_dump_matcher_all(struct seq_file *file, struct mlx5dr_matcher *matcher)
}
static int
-dr_dump_table_rx_tx(struct seq_file *file, bool is_rx,
+dr_dump_table_rx_tx(struct seq_file *file, char *buff, bool is_rx,
struct mlx5dr_table_rx_tx *table_rx_tx,
const u64 table_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
enum dr_dump_rec_type rec_type;
u64 s_icm_addr;
int ret;
@@ -829,7 +827,8 @@ dr_dump_table_rx_tx(struct seq_file *file, bool is_rx,
return 0;
}
-static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table)
+static noinline_for_stack int
+dr_dump_table(struct seq_file *file, struct mlx5dr_table *table)
{
struct mlx5dr_table_rx_tx *rx = &table->rx;
struct mlx5dr_table_rx_tx *tx = &table->tx;
@@ -848,14 +847,14 @@ static int dr_dump_table(struct seq_file *file, struct mlx5dr_table *table)
return ret;
if (rx->nic_dmn) {
- ret = dr_dump_table_rx_tx(file, true, rx,
+ ret = dr_dump_table_rx_tx(file, buff, true, rx,
DR_DBG_PTR_TO_ID(table));
if (ret < 0)
return ret;
}
if (tx->nic_dmn) {
- ret = dr_dump_table_rx_tx(file, false, tx,
+ ret = dr_dump_table_rx_tx(file, buff, false, tx,
DR_DBG_PTR_TO_ID(table));
if (ret < 0)
return ret;
@@ -881,10 +880,10 @@ static int dr_dump_table_all(struct seq_file *file, struct mlx5dr_table *tbl)
}
static int
-dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring,
+dr_dump_send_ring(struct seq_file *file, char *buff,
+ struct mlx5dr_send_ring *ring,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -902,13 +901,13 @@ dr_dump_send_ring(struct seq_file *file, struct mlx5dr_send_ring *ring,
return 0;
}
-static noinline_for_stack int
+static int
dr_dump_domain_info_flex_parser(struct seq_file *file,
+ char *buff,
const char *flex_parser_name,
const u8 flex_parser_value,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
int ret;
ret = snprintf(buff, MLX5DR_DEBUG_DUMP_BUFF_LENGTH,
@@ -925,11 +924,11 @@ dr_dump_domain_info_flex_parser(struct seq_file *file,
return 0;
}
-static noinline_for_stack int
-dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps,
+static int
+dr_dump_domain_info_caps(struct seq_file *file, char *buff,
+ struct mlx5dr_cmd_caps *caps,
const u64 domain_id)
{
- char buff[MLX5DR_DEBUG_DUMP_BUFF_LENGTH];
struct mlx5dr_cmd_vport_cap *vport_caps;
unsigned long i, vports_num;
int ret;
@@ -969,34 +968,35 @@ dr_dump_domain_info_caps(struct seq_file *file, struct mlx5dr_cmd_caps *caps,
}
static int
-dr_dump_domain_info(struct seq_file *file, struct mlx5dr_domain_info *info,
+dr_dump_domain_info(struct seq_file *file, char *buff,
+ struct mlx5dr_domain_info *info,
const u64 domain_id)
{
int ret;
- ret = dr_dump_domain_info_caps(file, &info->caps, domain_id);
+ ret = dr_dump_domain_info_caps(file, buff, &info->caps, domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmp_dw0",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw0",
info->caps.flex_parser_id_icmp_dw0,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmp_dw1",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmp_dw1",
info->caps.flex_parser_id_icmp_dw1,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw0",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw0",
info->caps.flex_parser_id_icmpv6_dw0,
domain_id);
if (ret < 0)
return ret;
- ret = dr_dump_domain_info_flex_parser(file, "icmpv6_dw1",
+ ret = dr_dump_domain_info_flex_parser(file, buff, "icmpv6_dw1",
info->caps.flex_parser_id_icmpv6_dw1,
domain_id);
if (ret < 0)
@@ -1032,12 +1032,12 @@ dr_dump_domain(struct seq_file *file, struct mlx5dr_domain *dmn)
if (ret)
return ret;
- ret = dr_dump_domain_info(file, &dmn->info, domain_id);
+ ret = dr_dump_domain_info(file, buff, &dmn->info, domain_id);
if (ret < 0)
return ret;
if (dmn->info.supp_sw_steering) {
- ret = dr_dump_send_ring(file, dmn->send_ring, domain_id);
+ ret = dr_dump_send_ring(file, buff, dmn->send_ring, domain_id);
if (ret < 0)
return ret;
}
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index e5ec0a363aff..31f75b4a67fd 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -368,7 +368,6 @@ union ks8851_tx_hdr {
* @rdfifo: FIFO read callback
* @wrfifo: FIFO write callback
* @start_xmit: start_xmit() implementation callback
- * @rx_skb: rx_skb() implementation callback
* @flush_tx_work: flush_tx_work() implementation callback
*
* The @statelock is used to protect information in the structure which may
@@ -423,8 +422,6 @@ struct ks8851_net {
struct sk_buff *txp, bool irq);
netdev_tx_t (*start_xmit)(struct sk_buff *skb,
struct net_device *dev);
- void (*rx_skb)(struct ks8851_net *ks,
- struct sk_buff *skb);
void (*flush_tx_work)(struct ks8851_net *ks);
};
diff --git a/drivers/net/ethernet/micrel/ks8851_common.c b/drivers/net/ethernet/micrel/ks8851_common.c
index 0bf13b38b8f5..d4cdf3d4f552 100644
--- a/drivers/net/ethernet/micrel/ks8851_common.c
+++ b/drivers/net/ethernet/micrel/ks8851_common.c
@@ -232,16 +232,6 @@ static void ks8851_dbg_dumpkkt(struct ks8851_net *ks, u8 *rxpkt)
}
/**
- * ks8851_rx_skb - receive skbuff
- * @ks: The device state.
- * @skb: The skbuff
- */
-static void ks8851_rx_skb(struct ks8851_net *ks, struct sk_buff *skb)
-{
- ks->rx_skb(ks, skb);
-}
-
-/**
* ks8851_rx_pkts - receive packets from the host
* @ks: The device information.
*
@@ -309,7 +299,7 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
ks8851_dbg_dumpkkt(ks, rxpkt);
skb->protocol = eth_type_trans(skb, ks->netdev);
- ks8851_rx_skb(ks, skb);
+ __netif_rx(skb);
ks->netdev->stats.rx_packets++;
ks->netdev->stats.rx_bytes += rxlen;
@@ -340,6 +330,8 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
unsigned long flags;
unsigned int status;
+ local_bh_disable();
+
ks8851_lock(ks, &flags);
status = ks8851_rdreg16(ks, KS_ISR);
@@ -416,6 +408,8 @@ static irqreturn_t ks8851_irq(int irq, void *_ks)
if (status & IRQ_LCI)
mii_check_link(&ks->mii);
+ local_bh_enable();
+
return IRQ_HANDLED;
}
diff --git a/drivers/net/ethernet/micrel/ks8851_par.c b/drivers/net/ethernet/micrel/ks8851_par.c
index 2a7f29854267..381b9cd285eb 100644
--- a/drivers/net/ethernet/micrel/ks8851_par.c
+++ b/drivers/net/ethernet/micrel/ks8851_par.c
@@ -210,16 +210,6 @@ static void ks8851_wrfifo_par(struct ks8851_net *ks, struct sk_buff *txp,
iowrite16_rep(ksp->hw_addr, txp->data, len / 2);
}
-/**
- * ks8851_rx_skb_par - receive skbuff
- * @ks: The device state.
- * @skb: The skbuff
- */
-static void ks8851_rx_skb_par(struct ks8851_net *ks, struct sk_buff *skb)
-{
- netif_rx(skb);
-}
-
static unsigned int ks8851_rdreg16_par_txqcr(struct ks8851_net *ks)
{
return ks8851_rdreg16_par(ks, KS_TXQCR);
@@ -298,7 +288,6 @@ static int ks8851_probe_par(struct platform_device *pdev)
ks->rdfifo = ks8851_rdfifo_par;
ks->wrfifo = ks8851_wrfifo_par;
ks->start_xmit = ks8851_start_xmit_par;
- ks->rx_skb = ks8851_rx_skb_par;
#define STD_IRQ (IRQ_LCI | /* Link Change */ \
IRQ_RXI | /* RX done */ \
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 2f803377c9f9..670c1de966db 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -299,16 +299,6 @@ static unsigned int calc_txlen(unsigned int len)
}
/**
- * ks8851_rx_skb_spi - receive skbuff
- * @ks: The device state
- * @skb: The skbuff
- */
-static void ks8851_rx_skb_spi(struct ks8851_net *ks, struct sk_buff *skb)
-{
- netif_rx(skb);
-}
-
-/**
* ks8851_tx_work - process tx packet(s)
* @work: The work strucutre what was scheduled.
*
@@ -435,7 +425,6 @@ static int ks8851_probe_spi(struct spi_device *spi)
ks->rdfifo = ks8851_rdfifo_spi;
ks->wrfifo = ks8851_wrfifo_spi;
ks->start_xmit = ks8851_start_xmit_spi;
- ks->rx_skb = ks8851_rx_skb_spi;
ks->flush_tx_work = ks8851_flush_tx_work_spi;
#define STD_IRQ (IRQ_LCI | /* Link Change */ \
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
index 3a1b1a1f5a19..60dd2fd603a8 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_port.c
@@ -731,7 +731,7 @@ static int sparx5_port_pcs_low_set(struct sparx5 *sparx5,
bool sgmii = false, inband_aneg = false;
int err;
- if (port->conf.inband) {
+ if (conf->inband) {
if (conf->portmode == PHY_INTERFACE_MODE_SGMII ||
conf->portmode == PHY_INTERFACE_MODE_QSGMII)
inband_aneg = true; /* Cisco-SGMII in-band-aneg */
@@ -948,7 +948,7 @@ int sparx5_port_pcs_set(struct sparx5 *sparx5,
if (err)
return -EINVAL;
- if (port->conf.inband) {
+ if (conf->inband) {
/* Enable/disable 1G counters in ASM */
spx5_rmw(ASM_PORT_CFG_CSC_STAT_DIS_SET(high_speed_dev),
ASM_PORT_CFG_CSC_STAT_DIS,
diff --git a/drivers/net/ethernet/realtek/r8169.h b/drivers/net/ethernet/realtek/r8169.h
index 4c043052198d..00882ffc7a02 100644
--- a/drivers/net/ethernet/realtek/r8169.h
+++ b/drivers/net/ethernet/realtek/r8169.h
@@ -73,6 +73,7 @@ enum mac_version {
};
struct rtl8169_private;
+struct r8169_led_classdev;
void r8169_apply_firmware(struct rtl8169_private *tp);
u16 rtl8168h_2_get_adc_bias_ioffset(struct rtl8169_private *tp);
@@ -84,7 +85,8 @@ void r8169_get_led_name(struct rtl8169_private *tp, int idx,
char *buf, int buf_len);
int rtl8168_get_led_mode(struct rtl8169_private *tp);
int rtl8168_led_mod_ctrl(struct rtl8169_private *tp, u16 mask, u16 val);
-void rtl8168_init_leds(struct net_device *ndev);
+struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev);
int rtl8125_get_led_mode(struct rtl8169_private *tp, int index);
int rtl8125_set_led_mode(struct rtl8169_private *tp, int index, u16 mode);
-void rtl8125_init_leds(struct net_device *ndev);
+struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev);
+void r8169_remove_leds(struct r8169_led_classdev *leds);
diff --git a/drivers/net/ethernet/realtek/r8169_leds.c b/drivers/net/ethernet/realtek/r8169_leds.c
index 7c5dc9d0df85..e10bee706bc6 100644
--- a/drivers/net/ethernet/realtek/r8169_leds.c
+++ b/drivers/net/ethernet/realtek/r8169_leds.c
@@ -146,22 +146,22 @@ static void rtl8168_setup_ldev(struct r8169_led_classdev *ldev,
led_cdev->hw_control_get_device = r8169_led_hw_control_get_device;
/* ignore errors */
- devm_led_classdev_register(&ndev->dev, led_cdev);
+ led_classdev_register(&ndev->dev, led_cdev);
}
-void rtl8168_init_leds(struct net_device *ndev)
+struct r8169_led_classdev *rtl8168_init_leds(struct net_device *ndev)
{
- /* bind resource mgmt to netdev */
- struct device *dev = &ndev->dev;
struct r8169_led_classdev *leds;
int i;
- leds = devm_kcalloc(dev, RTL8168_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+ leds = kcalloc(RTL8168_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL);
if (!leds)
- return;
+ return NULL;
for (i = 0; i < RTL8168_NUM_LEDS; i++)
rtl8168_setup_ldev(leds + i, ndev, i);
+
+ return leds;
}
static int rtl8125_led_hw_control_is_supported(struct led_classdev *led_cdev,
@@ -245,20 +245,31 @@ static void rtl8125_setup_led_ldev(struct r8169_led_classdev *ldev,
led_cdev->hw_control_get_device = r8169_led_hw_control_get_device;
/* ignore errors */
- devm_led_classdev_register(&ndev->dev, led_cdev);
+ led_classdev_register(&ndev->dev, led_cdev);
}
-void rtl8125_init_leds(struct net_device *ndev)
+struct r8169_led_classdev *rtl8125_init_leds(struct net_device *ndev)
{
- /* bind resource mgmt to netdev */
- struct device *dev = &ndev->dev;
struct r8169_led_classdev *leds;
int i;
- leds = devm_kcalloc(dev, RTL8125_NUM_LEDS, sizeof(*leds), GFP_KERNEL);
+ leds = kcalloc(RTL8125_NUM_LEDS + 1, sizeof(*leds), GFP_KERNEL);
if (!leds)
- return;
+ return NULL;
for (i = 0; i < RTL8125_NUM_LEDS; i++)
rtl8125_setup_led_ldev(leds + i, ndev, i);
+
+ return leds;
+}
+
+void r8169_remove_leds(struct r8169_led_classdev *leds)
+{
+ if (!leds)
+ return;
+
+ for (struct r8169_led_classdev *l = leds; l->ndev; l++)
+ led_classdev_unregister(&l->led);
+
+ kfree(leds);
}
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 60540ca63464..fab21d2bc4ff 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -647,6 +647,8 @@ struct rtl8169_private {
const char *fw_name;
struct rtl_fw *rtl_fw;
+ struct r8169_led_classdev *leds;
+
u32 ocp_base;
};
@@ -5046,6 +5048,9 @@ static void rtl_remove_one(struct pci_dev *pdev)
cancel_work_sync(&tp->wk.work);
+ if (IS_ENABLED(CONFIG_R8169_LEDS))
+ r8169_remove_leds(tp->leds);
+
unregister_netdev(tp->dev);
if (tp->dash_type != RTL_DASH_NONE)
@@ -5503,9 +5508,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
if (IS_ENABLED(CONFIG_R8169_LEDS)) {
if (rtl_is_8125(tp))
- rtl8125_init_leds(dev);
+ tp->leds = rtl8125_init_leds(dev);
else if (tp->mac_version > RTL_GIGA_MAC_VER_06)
- rtl8168_init_leds(dev);
+ tp->leds = rtl8168_init_leds(dev);
}
netdev_info(dev, "%s, %pM, XID %03x, IRQ %d\n",
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h
index dff02d75d519..5d1ea3e07459 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc.h
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h
@@ -52,6 +52,7 @@ struct stmmac_counters {
unsigned int mmc_tx_excessdef;
unsigned int mmc_tx_pause_frame;
unsigned int mmc_tx_vlan_frame_g;
+ unsigned int mmc_tx_oversize_g;
unsigned int mmc_tx_lpi_usec;
unsigned int mmc_tx_lpi_tran;
@@ -80,6 +81,7 @@ struct stmmac_counters {
unsigned int mmc_rx_fifo_overflow;
unsigned int mmc_rx_vlan_frames_gb;
unsigned int mmc_rx_watchdog_error;
+ unsigned int mmc_rx_error;
unsigned int mmc_rx_lpi_usec;
unsigned int mmc_rx_lpi_tran;
unsigned int mmc_rx_discard_frames_gb;
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index 7eb477faa75a..0fab842902a8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -53,6 +53,7 @@
#define MMC_TX_EXCESSDEF 0x6c
#define MMC_TX_PAUSE_FRAME 0x70
#define MMC_TX_VLAN_FRAME_G 0x74
+#define MMC_TX_OVERSIZE_G 0x78
/* MMC RX counter registers */
#define MMC_RX_FRAMECOUNT_GB 0x80
@@ -79,6 +80,13 @@
#define MMC_RX_FIFO_OVERFLOW 0xd4
#define MMC_RX_VLAN_FRAMES_GB 0xd8
#define MMC_RX_WATCHDOG_ERROR 0xdc
+#define MMC_RX_ERROR 0xe0
+
+#define MMC_TX_LPI_USEC 0xec
+#define MMC_TX_LPI_TRAN 0xf0
+#define MMC_RX_LPI_USEC 0xf4
+#define MMC_RX_LPI_TRAN 0xf8
+
/* IPC*/
#define MMC_RX_IPC_INTR_MASK 0x100
#define MMC_RX_IPC_INTR 0x108
@@ -283,6 +291,9 @@ static void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
mmc->mmc_tx_excessdef += readl(mmcaddr + MMC_TX_EXCESSDEF);
mmc->mmc_tx_pause_frame += readl(mmcaddr + MMC_TX_PAUSE_FRAME);
mmc->mmc_tx_vlan_frame_g += readl(mmcaddr + MMC_TX_VLAN_FRAME_G);
+ mmc->mmc_tx_oversize_g += readl(mmcaddr + MMC_TX_OVERSIZE_G);
+ mmc->mmc_tx_lpi_usec += readl(mmcaddr + MMC_TX_LPI_USEC);
+ mmc->mmc_tx_lpi_tran += readl(mmcaddr + MMC_TX_LPI_TRAN);
/* MMC RX counter registers */
mmc->mmc_rx_framecount_gb += readl(mmcaddr + MMC_RX_FRAMECOUNT_GB);
@@ -316,6 +327,10 @@ static void dwmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc)
mmc->mmc_rx_fifo_overflow += readl(mmcaddr + MMC_RX_FIFO_OVERFLOW);
mmc->mmc_rx_vlan_frames_gb += readl(mmcaddr + MMC_RX_VLAN_FRAMES_GB);
mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_RX_WATCHDOG_ERROR);
+ mmc->mmc_rx_error += readl(mmcaddr + MMC_RX_ERROR);
+ mmc->mmc_rx_lpi_usec += readl(mmcaddr + MMC_RX_LPI_USEC);
+ mmc->mmc_rx_lpi_tran += readl(mmcaddr + MMC_RX_LPI_TRAN);
+
/* IPv4 */
mmc->mmc_rx_ipv4_gd += readl(mmcaddr + MMC_RX_IPV4_GD);
mmc->mmc_rx_ipv4_hderr += readl(mmcaddr + MMC_RX_IPV4_HDERR);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index e1537a57815f..542e2633a6f5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -212,6 +212,7 @@ static const struct stmmac_stats stmmac_mmc[] = {
STMMAC_MMC_STAT(mmc_tx_excessdef),
STMMAC_MMC_STAT(mmc_tx_pause_frame),
STMMAC_MMC_STAT(mmc_tx_vlan_frame_g),
+ STMMAC_MMC_STAT(mmc_tx_oversize_g),
STMMAC_MMC_STAT(mmc_tx_lpi_usec),
STMMAC_MMC_STAT(mmc_tx_lpi_tran),
STMMAC_MMC_STAT(mmc_rx_framecount_gb),
@@ -238,6 +239,7 @@ static const struct stmmac_stats stmmac_mmc[] = {
STMMAC_MMC_STAT(mmc_rx_fifo_overflow),
STMMAC_MMC_STAT(mmc_rx_vlan_frames_gb),
STMMAC_MMC_STAT(mmc_rx_watchdog_error),
+ STMMAC_MMC_STAT(mmc_rx_error),
STMMAC_MMC_STAT(mmc_rx_lpi_usec),
STMMAC_MMC_STAT(mmc_rx_lpi_tran),
STMMAC_MMC_STAT(mmc_rx_discard_frames_gb),
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 163f94a5a58f..f918ca6146c8 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -826,7 +826,7 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
__be16 sport;
int err;
- if (!pskb_inet_may_pull(skb))
+ if (!skb_vlan_inet_prepare(skb))
return -EINVAL;
if (!gs4)
@@ -935,7 +935,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
__be16 sport;
int err;
- if (!pskb_inet_may_pull(skb))
+ if (!skb_vlan_inet_prepare(skb))
return -EINVAL;
if (!gs6)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index c22d1118a133..115c3c5414f2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3807,6 +3807,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
struct netlink_ext_ack *extack)
{
struct virtnet_info *vi = netdev_priv(dev);
+ bool update = false;
int i;
if (rxfh->hfunc != ETH_RSS_HASH_NO_CHANGE &&
@@ -3814,13 +3815,28 @@ static int virtnet_set_rxfh(struct net_device *dev,
return -EOPNOTSUPP;
if (rxfh->indir) {
+ if (!vi->has_rss)
+ return -EOPNOTSUPP;
+
for (i = 0; i < vi->rss_indir_table_size; ++i)
vi->ctrl->rss.indirection_table[i] = rxfh->indir[i];
+ update = true;
}
- if (rxfh->key)
+
+ if (rxfh->key) {
+ /* If either _F_HASH_REPORT or _F_RSS are negotiated, the
+ * device provides hash calculation capabilities, that is,
+ * hash_key is configured.
+ */
+ if (!vi->has_rss && !vi->has_rss_hash_report)
+ return -EOPNOTSUPP;
+
memcpy(vi->ctrl->rss.key, rxfh->key, vi->rss_key_size);
+ update = true;
+ }
- virtnet_commit_rss_command(vi);
+ if (update)
+ virtnet_commit_rss_command(vi);
return 0;
}
@@ -4729,13 +4745,15 @@ static int virtnet_probe(struct virtio_device *vdev)
if (virtio_has_feature(vdev, VIRTIO_NET_F_HASH_REPORT))
vi->has_rss_hash_report = true;
- if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS))
+ if (virtio_has_feature(vdev, VIRTIO_NET_F_RSS)) {
vi->has_rss = true;
- if (vi->has_rss || vi->has_rss_hash_report) {
vi->rss_indir_table_size =
virtio_cread16(vdev, offsetof(struct virtio_net_config,
rss_max_indirection_table_length));
+ }
+
+ if (vi->has_rss || vi->has_rss_hash_report) {
vi->rss_key_size =
virtio_cread8(vdev, offsetof(struct virtio_net_config, rss_max_key_size));
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 943d72bdd794..27281a9a8951 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2076,6 +2076,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
bool vwc = ns->ctrl->vwc & NVME_CTRL_VWC_PRESENT;
struct queue_limits lim;
struct nvme_id_ns_nvm *nvm = NULL;
+ struct nvme_zone_info zi = {};
struct nvme_id_ns *id;
sector_t capacity;
unsigned lbaf;
@@ -2088,9 +2089,10 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
if (id->ncap == 0) {
/* namespace not allocated or attached */
info->is_removed = true;
- ret = -ENODEV;
+ ret = -ENXIO;
goto out;
}
+ lbaf = nvme_lbaf_index(id->flbas);
if (ns->ctrl->ctratt & NVME_CTRL_ATTR_ELBAS) {
ret = nvme_identify_ns_nvm(ns->ctrl, info->nsid, &nvm);
@@ -2098,8 +2100,14 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
goto out;
}
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+ ns->head->ids.csi == NVME_CSI_ZNS) {
+ ret = nvme_query_zone_info(ns, lbaf, &zi);
+ if (ret < 0)
+ goto out;
+ }
+
blk_mq_freeze_queue(ns->disk->queue);
- lbaf = nvme_lbaf_index(id->flbas);
ns->head->lba_shift = id->lbaf[lbaf].ds;
ns->head->nuse = le64_to_cpu(id->nuse);
capacity = nvme_lba_to_sect(ns->head, le64_to_cpu(id->nsze));
@@ -2112,13 +2120,8 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
capacity = 0;
nvme_config_discard(ns, &lim);
if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
- ns->head->ids.csi == NVME_CSI_ZNS) {
- ret = nvme_update_zone_info(ns, lbaf, &lim);
- if (ret) {
- blk_mq_unfreeze_queue(ns->disk->queue);
- goto out;
- }
- }
+ ns->head->ids.csi == NVME_CSI_ZNS)
+ nvme_update_zone_info(ns, &lim, &zi);
ret = queue_limits_commit_update(ns->disk->queue, &lim);
if (ret) {
blk_mq_unfreeze_queue(ns->disk->queue);
@@ -2201,6 +2204,7 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
}
if (!ret && nvme_ns_head_multipath(ns->head)) {
+ struct queue_limits *ns_lim = &ns->disk->queue->limits;
struct queue_limits lim;
blk_mq_freeze_queue(ns->head->disk->queue);
@@ -2212,7 +2216,26 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
nvme_mpath_revalidate_paths(ns);
+ /*
+ * queue_limits mixes values that are the hardware limitations
+ * for bio splitting with what is the device configuration.
+ *
+ * For NVMe the device configuration can change after e.g. a
+ * Format command, and we really want to pick up the new format
+ * value here. But we must still stack the queue limits to the
+ * least common denominator for multipathing to split the bios
+ * properly.
+ *
+ * To work around this, we explicitly set the device
+ * configuration to those that we just queried, but only stack
+ * the splitting limits in to make sure we still obey possibly
+ * lower limitations of other controllers.
+ */
lim = queue_limits_start_update(ns->head->disk->queue);
+ lim.logical_block_size = ns_lim->logical_block_size;
+ lim.physical_block_size = ns_lim->physical_block_size;
+ lim.io_min = ns_lim->io_min;
+ lim.io_opt = ns_lim->io_opt;
queue_limits_stack_bdev(&lim, ns->disk->part0, 0,
ns->head->disk->disk_name);
ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 68a5d971657b..a5b29e9ad342 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2428,7 +2428,7 @@ nvme_fc_ctrl_get(struct nvme_fc_ctrl *ctrl)
* controller. Called after last nvme_put_ctrl() call
*/
static void
-nvme_fc_nvme_ctrl_freed(struct nvme_ctrl *nctrl)
+nvme_fc_free_ctrl(struct nvme_ctrl *nctrl)
{
struct nvme_fc_ctrl *ctrl = to_fc_ctrl(nctrl);
@@ -3384,7 +3384,7 @@ static const struct nvme_ctrl_ops nvme_fc_ctrl_ops = {
.reg_read32 = nvmf_reg_read32,
.reg_read64 = nvmf_reg_read64,
.reg_write32 = nvmf_reg_write32,
- .free_ctrl = nvme_fc_nvme_ctrl_freed,
+ .free_ctrl = nvme_fc_free_ctrl,
.submit_async_event = nvme_fc_submit_async_event,
.delete_ctrl = nvme_fc_delete_ctrl,
.get_address = nvmf_get_address,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 24193fcb8bd5..d0ed64dc7380 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -1036,10 +1036,18 @@ static inline bool nvme_disk_is_ns_head(struct gendisk *disk)
}
#endif /* CONFIG_NVME_MULTIPATH */
+struct nvme_zone_info {
+ u64 zone_size;
+ unsigned int max_open_zones;
+ unsigned int max_active_zones;
+};
+
int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
unsigned int nr_zones, report_zones_cb cb, void *data);
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
- struct queue_limits *lim);
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi);
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi);
#ifdef CONFIG_BLK_DEV_ZONED
blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmnd,
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index 722384bcc765..77aa0f440a6d 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -35,8 +35,8 @@ static int nvme_set_max_append(struct nvme_ctrl *ctrl)
return 0;
}
-int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
- struct queue_limits *lim)
+int nvme_query_zone_info(struct nvme_ns *ns, unsigned lbaf,
+ struct nvme_zone_info *zi)
{
struct nvme_effects_log *log = ns->head->effects;
struct nvme_command c = { };
@@ -89,27 +89,34 @@ int nvme_update_zone_info(struct nvme_ns *ns, unsigned lbaf,
goto free_data;
}
- ns->head->zsze =
- nvme_lba_to_sect(ns->head, le64_to_cpu(id->lbafe[lbaf].zsze));
- if (!is_power_of_2(ns->head->zsze)) {
+ zi->zone_size = le64_to_cpu(id->lbafe[lbaf].zsze);
+ if (!is_power_of_2(zi->zone_size)) {
dev_warn(ns->ctrl->device,
- "invalid zone size:%llu for namespace:%u\n",
- ns->head->zsze, ns->head->ns_id);
+ "invalid zone size: %llu for namespace: %u\n",
+ zi->zone_size, ns->head->ns_id);
status = -ENODEV;
goto free_data;
}
+ zi->max_open_zones = le32_to_cpu(id->mor) + 1;
+ zi->max_active_zones = le32_to_cpu(id->mar) + 1;
- blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
- lim->zoned = 1;
- lim->max_open_zones = le32_to_cpu(id->mor) + 1;
- lim->max_active_zones = le32_to_cpu(id->mar) + 1;
- lim->chunk_sectors = ns->head->zsze;
- lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
free_data:
kfree(id);
return status;
}
+void nvme_update_zone_info(struct nvme_ns *ns, struct queue_limits *lim,
+ struct nvme_zone_info *zi)
+{
+ lim->zoned = 1;
+ lim->max_open_zones = zi->max_open_zones;
+ lim->max_active_zones = zi->max_active_zones;
+ lim->max_zone_append_sectors = ns->ctrl->max_zone_append;
+ lim->chunk_sectors = ns->head->zsze =
+ nvme_lba_to_sect(ns->head, zi->zone_size);
+ blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, ns->queue);
+}
+
static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
unsigned int nr_zones, size_t *buflen)
{
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 77a6e817b315..a2325330bf22 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1613,6 +1613,11 @@ static struct config_group *nvmet_subsys_make(struct config_group *group,
return ERR_PTR(-EINVAL);
}
+ if (sysfs_streq(name, nvmet_disc_subsys->subsysnqn)) {
+ pr_err("can't create subsystem using unique discovery NQN\n");
+ return ERR_PTR(-EINVAL);
+ }
+
subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME);
if (IS_ERR(subsys))
return ERR_CAST(subsys);
@@ -2159,7 +2164,49 @@ static const struct config_item_type nvmet_hosts_type = {
static struct config_group nvmet_hosts_group;
+static ssize_t nvmet_root_discovery_nqn_show(struct config_item *item,
+ char *page)
+{
+ return snprintf(page, PAGE_SIZE, "%s\n", nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_root_discovery_nqn_store(struct config_item *item,
+ const char *page, size_t count)
+{
+ struct list_head *entry;
+ size_t len;
+
+ len = strcspn(page, "\n");
+ if (!len || len > NVMF_NQN_FIELD_LEN - 1)
+ return -EINVAL;
+
+ down_write(&nvmet_config_sem);
+ list_for_each(entry, &nvmet_subsystems_group.cg_children) {
+ struct config_item *item =
+ container_of(entry, struct config_item, ci_entry);
+
+ if (!strncmp(config_item_name(item), page, len)) {
+ pr_err("duplicate NQN %s\n", config_item_name(item));
+ up_write(&nvmet_config_sem);
+ return -EINVAL;
+ }
+ }
+ memset(nvmet_disc_subsys->subsysnqn, 0, NVMF_NQN_FIELD_LEN);
+ memcpy(nvmet_disc_subsys->subsysnqn, page, len);
+ up_write(&nvmet_config_sem);
+
+ return len;
+}
+
+CONFIGFS_ATTR(nvmet_root_, discovery_nqn);
+
+static struct configfs_attribute *nvmet_root_attrs[] = {
+ &nvmet_root_attr_discovery_nqn,
+ NULL,
+};
+
static const struct config_item_type nvmet_root_type = {
+ .ct_attrs = nvmet_root_attrs,
.ct_owner = THIS_MODULE,
};
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 6bbe4df0166c..8860a3eb71ec 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1541,6 +1541,13 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
}
down_read(&nvmet_config_sem);
+ if (!strncmp(nvmet_disc_subsys->subsysnqn, subsysnqn,
+ NVMF_NQN_SIZE)) {
+ if (kref_get_unless_zero(&nvmet_disc_subsys->ref)) {
+ up_read(&nvmet_config_sem);
+ return nvmet_disc_subsys;
+ }
+ }
list_for_each_entry(p, &port->subsystems, entry) {
if (!strncmp(p->subsys->subsysnqn, subsysnqn,
NVMF_NQN_SIZE)) {
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index fd229f310c93..337ee1cb09ae 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -1115,16 +1115,21 @@ nvmet_fc_schedule_delete_assoc(struct nvmet_fc_tgt_assoc *assoc)
}
static bool
-nvmet_fc_assoc_exits(struct nvmet_fc_tgtport *tgtport, u64 association_id)
+nvmet_fc_assoc_exists(struct nvmet_fc_tgtport *tgtport, u64 association_id)
{
struct nvmet_fc_tgt_assoc *a;
+ bool found = false;
+ rcu_read_lock();
list_for_each_entry_rcu(a, &tgtport->assoc_list, a_list) {
- if (association_id == a->association_id)
- return true;
+ if (association_id == a->association_id) {
+ found = true;
+ break;
+ }
}
+ rcu_read_unlock();
- return false;
+ return found;
}
static struct nvmet_fc_tgt_assoc *
@@ -1164,13 +1169,11 @@ nvmet_fc_alloc_target_assoc(struct nvmet_fc_tgtport *tgtport, void *hosthandle)
ran = ran << BYTES_FOR_QID_SHIFT;
spin_lock_irqsave(&tgtport->lock, flags);
- rcu_read_lock();
- if (!nvmet_fc_assoc_exits(tgtport, ran)) {
+ if (!nvmet_fc_assoc_exists(tgtport, ran)) {
assoc->association_id = ran;
list_add_tail_rcu(&assoc->a_list, &tgtport->assoc_list);
done = true;
}
- rcu_read_unlock();
spin_unlock_irqrestore(&tgtport->lock, flags);
} while (!done);
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 3bf27052832f..4d57a4e34105 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -9,6 +9,7 @@
#define pr_fmt(fmt) "OF: " fmt
+#include <linux/device.h>
#include <linux/of.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
@@ -667,6 +668,17 @@ void of_changeset_destroy(struct of_changeset *ocs)
{
struct of_changeset_entry *ce, *cen;
+ /*
+ * When a device is deleted, the device links to/from it are also queued
+ * for deletion. Until these device links are freed, the devices
+ * themselves aren't freed. If the device being deleted is due to an
+ * overlay change, this device might be holding a reference to a device
+ * node that will be freed. So, wait until all already pending device
+ * links are deleted before freeing a device node. This ensures we don't
+ * free any device node that has a non-zero reference count.
+ */
+ device_link_wait_removal();
+
list_for_each_entry_safe_reverse(ce, cen, &ocs->entries, node)
__of_changeset_entry_destroy(ce);
}
diff --git a/drivers/of/module.c b/drivers/of/module.c
index 0e8aa974f0f2..f58e624953a2 100644
--- a/drivers/of/module.c
+++ b/drivers/of/module.c
@@ -16,6 +16,14 @@ ssize_t of_modalias(const struct device_node *np, char *str, ssize_t len)
ssize_t csize;
ssize_t tsize;
+ /*
+ * Prevent a kernel oops in vsnprintf() -- it only allows passing a
+ * NULL ptr when the length is also 0. Also filter out the negative
+ * lengths...
+ */
+ if ((len > 0 && !str) || len < 0)
+ return -EINVAL;
+
/* Name & Type */
/* %p eats all alphanum characters, so %c must be used here */
csize = snprintf(str, len, "of:N%pOFn%c%s", np, 'T',
diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c
index c78a6fd6c57f..b4efdddb2ad9 100644
--- a/drivers/perf/riscv_pmu.c
+++ b/drivers/perf/riscv_pmu.c
@@ -313,6 +313,10 @@ static int riscv_pmu_event_init(struct perf_event *event)
u64 event_config = 0;
uint64_t cmask;
+ /* driver does not support branch stack sampling */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
hwc->flags = 0;
mapped_event = rvpmu->event_map(event, &event_config);
if (mapped_event < 0) {
diff --git a/drivers/platform/chrome/cros_ec_uart.c b/drivers/platform/chrome/cros_ec_uart.c
index 8ea867c2a01a..62bc24f6dcc7 100644
--- a/drivers/platform/chrome/cros_ec_uart.c
+++ b/drivers/platform/chrome/cros_ec_uart.c
@@ -263,12 +263,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev)
if (!ec_dev)
return -ENOMEM;
- ret = devm_serdev_device_open(dev, serdev);
- if (ret) {
- dev_err(dev, "Unable to open UART device");
- return ret;
- }
-
serdev_device_set_drvdata(serdev, ec_dev);
init_waitqueue_head(&ec_uart->response.wait_queue);
@@ -280,14 +274,6 @@ static int cros_ec_uart_probe(struct serdev_device *serdev)
return ret;
}
- ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate);
- if (ret < 0) {
- dev_err(dev, "Failed to set up host baud rate (%d)", ret);
- return ret;
- }
-
- serdev_device_set_flow_control(serdev, ec_uart->flowcontrol);
-
/* Initialize ec_dev for cros_ec */
ec_dev->phys_name = dev_name(dev);
ec_dev->dev = dev;
@@ -301,6 +287,20 @@ static int cros_ec_uart_probe(struct serdev_device *serdev)
serdev_device_set_client_ops(serdev, &cros_ec_uart_client_ops);
+ ret = devm_serdev_device_open(dev, serdev);
+ if (ret) {
+ dev_err(dev, "Unable to open UART device");
+ return ret;
+ }
+
+ ret = serdev_device_set_baudrate(serdev, ec_uart->baudrate);
+ if (ret < 0) {
+ dev_err(dev, "Failed to set up host baud rate (%d)", ret);
+ return ret;
+ }
+
+ serdev_device_set_flow_control(serdev, ec_uart->flowcontrol);
+
return cros_ec_register(ec_dev);
}
diff --git a/drivers/platform/x86/acer-wmi.c b/drivers/platform/x86/acer-wmi.c
index ee2e164f86b9..38c932df6446 100644
--- a/drivers/platform/x86/acer-wmi.c
+++ b/drivers/platform/x86/acer-wmi.c
@@ -598,6 +598,15 @@ static const struct dmi_system_id acer_quirks[] __initconst = {
.driver_data = &quirk_acer_predator_v4,
},
{
+ .callback = dmi_matched,
+ .ident = "Acer Predator PH18-71",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Predator PH18-71"),
+ },
+ .driver_data = &quirk_acer_predator_v4,
+ },
+ {
.callback = set_force_caps,
.ident = "Acer Aspire Switch 10E SW3-016",
.matches = {
diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 7457ca2b27a6..c7a827645864 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -49,6 +49,8 @@ static const struct acpi_device_id intel_hid_ids[] = {
{"INTC1076", 0},
{"INTC1077", 0},
{"INTC1078", 0},
+ {"INTC107B", 0},
+ {"INTC10CB", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
@@ -504,6 +506,7 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
struct platform_device *device = context;
struct intel_hid_priv *priv = dev_get_drvdata(&device->dev);
unsigned long long ev_index;
+ struct key_entry *ke;
int err;
/*
@@ -545,11 +548,15 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
if (event == 0xc0 || !priv->array)
return;
- if (!sparse_keymap_entry_from_scancode(priv->array, event)) {
+ ke = sparse_keymap_entry_from_scancode(priv->array, event);
+ if (!ke) {
dev_info(&device->dev, "unknown event 0x%x\n", event);
return;
}
+ if (ke->type == KE_IGNORE)
+ return;
+
wakeup:
pm_wakeup_hard_event(&device->dev);
diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
index 084c355c86f5..79bb2c801daa 100644
--- a/drivers/platform/x86/intel/vbtn.c
+++ b/drivers/platform/x86/intel/vbtn.c
@@ -136,8 +136,6 @@ static int intel_vbtn_input_setup(struct platform_device *device)
priv->switches_dev->id.bustype = BUS_HOST;
if (priv->has_switches) {
- detect_tablet_mode(&device->dev);
-
ret = input_register_device(priv->switches_dev);
if (ret)
return ret;
@@ -258,9 +256,6 @@ static const struct dmi_system_id dmi_switches_allow_list[] = {
static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel)
{
- unsigned long long vgbs;
- acpi_status status;
-
/* See dual_accel_detect.h for more info */
if (dual_accel)
return false;
@@ -268,8 +263,7 @@ static bool intel_vbtn_has_switches(acpi_handle handle, bool dual_accel)
if (!dmi_check_system(dmi_switches_allow_list))
return false;
- status = acpi_evaluate_integer(handle, "VGBS", NULL, &vgbs);
- return ACPI_SUCCESS(status);
+ return acpi_has_method(handle, "VGBS");
}
static int intel_vbtn_probe(struct platform_device *device)
@@ -316,6 +310,9 @@ static int intel_vbtn_probe(struct platform_device *device)
if (ACPI_FAILURE(status))
dev_err(&device->dev, "Error VBDL failed with ACPI status %d\n", status);
}
+ // Check switches after buttons since VBDL may have side effects.
+ if (has_switches)
+ detect_tablet_mode(&device->dev);
device_init_wakeup(&device->dev, true);
/*
diff --git a/drivers/platform/x86/lg-laptop.c b/drivers/platform/x86/lg-laptop.c
index ad3c39e9e9f5..e714ee6298dd 100644
--- a/drivers/platform/x86/lg-laptop.c
+++ b/drivers/platform/x86/lg-laptop.c
@@ -736,7 +736,7 @@ static int acpi_add(struct acpi_device *device)
default:
year = 2019;
}
- pr_info("product: %s year: %d\n", product, year);
+ pr_info("product: %s year: %d\n", product ?: "unknown", year);
if (year >= 2019)
battery_limit_use_wmbb = 1;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 291f14ef6702..77244c9aa60d 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -264,6 +264,7 @@ static const struct key_entry toshiba_acpi_keymap[] = {
{ KE_KEY, 0xb32, { KEY_NEXTSONG } },
{ KE_KEY, 0xb33, { KEY_PLAYPAUSE } },
{ KE_KEY, 0xb5a, { KEY_MEDIA } },
+ { KE_IGNORE, 0x0e00, { KEY_RESERVED } }, /* Wake from sleep */
{ KE_IGNORE, 0x1430, { KEY_RESERVED } }, /* Wake from sleep */
{ KE_IGNORE, 0x1501, { KEY_RESERVED } }, /* Output changed */
{ KE_IGNORE, 0x1502, { KEY_RESERVED } }, /* HDMI plugged/unplugged */
@@ -3523,9 +3524,10 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event)
(dev->kbd_mode == SCI_KBD_MODE_ON) ?
LED_FULL : LED_OFF);
break;
+ case 0x8e: /* Power button pressed */
+ break;
case 0x85: /* Unknown */
case 0x8d: /* Unknown */
- case 0x8e: /* Unknown */
case 0x94: /* Unknown */
case 0x95: /* Unknown */
default:
diff --git a/drivers/regulator/tps65132-regulator.c b/drivers/regulator/tps65132-regulator.c
index a06f5f2d7932..9c2f0dd42613 100644
--- a/drivers/regulator/tps65132-regulator.c
+++ b/drivers/regulator/tps65132-regulator.c
@@ -267,10 +267,17 @@ static const struct i2c_device_id tps65132_id[] = {
};
MODULE_DEVICE_TABLE(i2c, tps65132_id);
+static const struct of_device_id __maybe_unused tps65132_of_match[] = {
+ { .compatible = "ti,tps65132" },
+ {},
+};
+MODULE_DEVICE_TABLE(of, tps65132_of_match);
+
static struct i2c_driver tps65132_i2c_driver = {
.driver = {
.name = "tps65132",
.probe_type = PROBE_PREFER_ASYNCHRONOUS,
+ .of_match_table = of_match_ptr(tps65132_of_match),
},
.probe = tps65132_probe,
.id_table = tps65132_id,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 097dfe4b620d..35f8e00850d6 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1797,7 +1797,7 @@ static int hisi_sas_debug_I_T_nexus_reset(struct domain_device *device)
if (dev_is_sata(device)) {
struct ata_link *link = &device->sata_dev.ap->link;
- rc = ata_wait_after_reset(link, HISI_SAS_WAIT_PHYUP_TIMEOUT,
+ rc = ata_wait_after_reset(link, jiffies + HISI_SAS_WAIT_PHYUP_TIMEOUT,
smp_ata_check_ready_type);
} else {
msleep(2000);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 7d2a33514538..34f96cc35342 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2244,7 +2244,15 @@ slot_err_v3_hw(struct hisi_hba *hisi_hba, struct sas_task *task,
case SAS_PROTOCOL_SATA | SAS_PROTOCOL_STP:
if ((dw0 & CMPLT_HDR_RSPNS_XFRD_MSK) &&
(sipc_rx_err_type & RX_FIS_STATUS_ERR_MSK)) {
- ts->stat = SAS_PROTO_RESPONSE;
+ if (task->ata_task.use_ncq) {
+ struct domain_device *device = task->dev;
+ struct hisi_sas_device *sas_dev = device->lldd_dev;
+
+ sas_dev->dev_status = HISI_SAS_DEV_NCQ_ERR;
+ slot->abort = 1;
+ } else {
+ ts->stat = SAS_PROTO_RESPONSE;
+ }
} else if (dma_rx_err_type & RX_DATA_LEN_UNDERFLOW_MSK) {
ts->residual = trans_tx_fail_type;
ts->stat = SAS_DATA_UNDERRUN;
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 5c261005b74e..f6e6db8b8aba 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -135,7 +135,7 @@ static int smp_execute_task(struct domain_device *dev, void *req, int req_size,
static inline void *alloc_smp_req(int size)
{
- u8 *p = kzalloc(size, GFP_KERNEL);
+ u8 *p = kzalloc(ALIGN(size, ARCH_DMA_MINALIGN), GFP_KERNEL);
if (p)
p[0] = SMP_REQUEST;
return p;
diff --git a/drivers/scsi/myrb.c b/drivers/scsi/myrb.c
index ca2e932dd9b7..f684eb5e0489 100644
--- a/drivers/scsi/myrb.c
+++ b/drivers/scsi/myrb.c
@@ -1775,9 +1775,9 @@ static ssize_t raid_state_show(struct device *dev,
name = myrb_devstate_name(ldev_info->state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->state);
} else {
struct myrb_pdev_state *pdev_info = sdev->hostdata;
@@ -1796,9 +1796,9 @@ static ssize_t raid_state_show(struct device *dev,
else
name = myrb_devstate_name(pdev_info->state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
pdev_info->state);
}
return ret;
@@ -1886,11 +1886,11 @@ static ssize_t raid_level_show(struct device *dev,
name = myrb_raidlevel_name(ldev_info->raid_level);
if (!name)
- return snprintf(buf, 32, "Invalid (%02X)\n",
+ return snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->state);
- return snprintf(buf, 32, "%s\n", name);
+ return snprintf(buf, 64, "%s\n", name);
}
- return snprintf(buf, 32, "Physical Drive\n");
+ return snprintf(buf, 64, "Physical Drive\n");
}
static DEVICE_ATTR_RO(raid_level);
@@ -1903,15 +1903,15 @@ static ssize_t rebuild_show(struct device *dev,
unsigned char status;
if (sdev->channel < myrb_logical_channel(sdev->host))
- return snprintf(buf, 32, "physical device - not rebuilding\n");
+ return snprintf(buf, 64, "physical device - not rebuilding\n");
status = myrb_get_rbld_progress(cb, &rbld_buf);
if (rbld_buf.ldev_num != sdev->id ||
status != MYRB_STATUS_SUCCESS)
- return snprintf(buf, 32, "not rebuilding\n");
+ return snprintf(buf, 64, "not rebuilding\n");
- return snprintf(buf, 32, "rebuilding block %u of %u\n",
+ return snprintf(buf, 64, "rebuilding block %u of %u\n",
rbld_buf.ldev_size - rbld_buf.blocks_left,
rbld_buf.ldev_size);
}
diff --git a/drivers/scsi/myrs.c b/drivers/scsi/myrs.c
index a1eec65a9713..e824be9d9bbb 100644
--- a/drivers/scsi/myrs.c
+++ b/drivers/scsi/myrs.c
@@ -947,9 +947,9 @@ static ssize_t raid_state_show(struct device *dev,
name = myrs_devstate_name(ldev_info->dev_state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->dev_state);
} else {
struct myrs_pdev_info *pdev_info;
@@ -958,9 +958,9 @@ static ssize_t raid_state_show(struct device *dev,
pdev_info = sdev->hostdata;
name = myrs_devstate_name(pdev_info->dev_state);
if (name)
- ret = snprintf(buf, 32, "%s\n", name);
+ ret = snprintf(buf, 64, "%s\n", name);
else
- ret = snprintf(buf, 32, "Invalid (%02X)\n",
+ ret = snprintf(buf, 64, "Invalid (%02X)\n",
pdev_info->dev_state);
}
return ret;
@@ -1066,13 +1066,13 @@ static ssize_t raid_level_show(struct device *dev,
ldev_info = sdev->hostdata;
name = myrs_raid_level_name(ldev_info->raid_level);
if (!name)
- return snprintf(buf, 32, "Invalid (%02X)\n",
+ return snprintf(buf, 64, "Invalid (%02X)\n",
ldev_info->dev_state);
} else
name = myrs_raid_level_name(MYRS_RAID_PHYSICAL);
- return snprintf(buf, 32, "%s\n", name);
+ return snprintf(buf, 64, "%s\n", name);
}
static DEVICE_ATTR_RO(raid_level);
@@ -1086,7 +1086,7 @@ static ssize_t rebuild_show(struct device *dev,
unsigned char status;
if (sdev->channel < cs->ctlr_info->physchan_present)
- return snprintf(buf, 32, "physical device - not rebuilding\n");
+ return snprintf(buf, 64, "physical device - not rebuilding\n");
ldev_info = sdev->hostdata;
ldev_num = ldev_info->ldev_num;
@@ -1098,11 +1098,11 @@ static ssize_t rebuild_show(struct device *dev,
return -EIO;
}
if (ldev_info->rbld_active) {
- return snprintf(buf, 32, "rebuilding block %zu of %zu\n",
+ return snprintf(buf, 64, "rebuilding block %zu of %zu\n",
(size_t)ldev_info->rbld_lba,
(size_t)ldev_info->cfg_devsize);
} else
- return snprintf(buf, 32, "not rebuilding\n");
+ return snprintf(buf, 64, "not rebuilding\n");
}
static ssize_t rebuild_store(struct device *dev,
@@ -1190,7 +1190,7 @@ static ssize_t consistency_check_show(struct device *dev,
unsigned short ldev_num;
if (sdev->channel < cs->ctlr_info->physchan_present)
- return snprintf(buf, 32, "physical device - not checking\n");
+ return snprintf(buf, 64, "physical device - not checking\n");
ldev_info = sdev->hostdata;
if (!ldev_info)
@@ -1198,11 +1198,11 @@ static ssize_t consistency_check_show(struct device *dev,
ldev_num = ldev_info->ldev_num;
myrs_get_ldev_info(cs, ldev_num, ldev_info);
if (ldev_info->cc_active)
- return snprintf(buf, 32, "checking block %zu of %zu\n",
+ return snprintf(buf, 64, "checking block %zu of %zu\n",
(size_t)ldev_info->cc_lba,
(size_t)ldev_info->cfg_devsize);
else
- return snprintf(buf, 32, "not checking\n");
+ return snprintf(buf, 64, "not checking\n");
}
static ssize_t consistency_check_store(struct device *dev,
diff --git a/drivers/scsi/qla2xxx/qla_edif.c b/drivers/scsi/qla2xxx/qla_edif.c
index 26e6b3e3af43..dcde55c8ee5d 100644
--- a/drivers/scsi/qla2xxx/qla_edif.c
+++ b/drivers/scsi/qla2xxx/qla_edif.c
@@ -1100,7 +1100,7 @@ qla_edif_app_getstats(scsi_qla_host_t *vha, struct bsg_job *bsg_job)
list_for_each_entry_safe(fcport, tf, &vha->vp_fcports, list) {
if (fcport->edif.enable) {
- if (pcnt > app_req.num_ports)
+ if (pcnt >= app_req.num_ports)
break;
app_reply->elem[pcnt].rekey_count =
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3cf898670290..58fdf679341d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -3920,7 +3920,7 @@ static int sd_probe(struct device *dev)
error = device_add_disk(dev, gd, NULL);
if (error) {
- put_device(&sdkp->disk_dev);
+ device_unregister(&sdkp->disk_dev);
put_disk(gd);
goto out;
}
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 386981c6976a..baf870a03ecf 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -285,6 +285,7 @@ sg_open(struct inode *inode, struct file *filp)
int dev = iminor(inode);
int flags = filp->f_flags;
struct request_queue *q;
+ struct scsi_device *device;
Sg_device *sdp;
Sg_fd *sfp;
int retval;
@@ -301,11 +302,12 @@ sg_open(struct inode *inode, struct file *filp)
/* This driver's module count bumped by fops_get in <linux/fs.h> */
/* Prevent the device driver from vanishing while we sleep */
- retval = scsi_device_get(sdp->device);
+ device = sdp->device;
+ retval = scsi_device_get(device);
if (retval)
goto sg_put;
- retval = scsi_autopm_get_device(sdp->device);
+ retval = scsi_autopm_get_device(device);
if (retval)
goto sdp_put;
@@ -313,7 +315,7 @@ sg_open(struct inode *inode, struct file *filp)
* check if O_NONBLOCK. Permits SCSI commands to be issued
* during error recovery. Tread carefully. */
if (!((flags & O_NONBLOCK) ||
- scsi_block_when_processing_errors(sdp->device))) {
+ scsi_block_when_processing_errors(device))) {
retval = -ENXIO;
/* we are in error recovery for this device */
goto error_out;
@@ -344,7 +346,7 @@ sg_open(struct inode *inode, struct file *filp)
if (sdp->open_cnt < 1) { /* no existing opens */
sdp->sgdebug = 0;
- q = sdp->device->request_queue;
+ q = device->request_queue;
sdp->sg_tablesize = queue_max_segments(q);
}
sfp = sg_add_sfp(sdp);
@@ -370,10 +372,11 @@ out_undo:
error_mutex_locked:
mutex_unlock(&sdp->open_rel_lock);
error_out:
- scsi_autopm_put_device(sdp->device);
+ scsi_autopm_put_device(device);
sdp_put:
- scsi_device_put(sdp->device);
- goto sg_put;
+ kref_put(&sdp->d_ref, sg_device_destroy);
+ scsi_device_put(device);
+ return retval;
}
/* Release resources associated with a successful sg_open()
@@ -2233,7 +2236,6 @@ sg_remove_sfp_usercontext(struct work_struct *work)
"sg_remove_sfp: sfp=0x%p\n", sfp));
kfree(sfp);
- WARN_ON_ONCE(kref_read(&sdp->d_ref) != 1);
kref_put(&sdp->d_ref, sg_device_destroy);
scsi_device_put(device);
module_put(THIS_MODULE);
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 079035db7dd8..92a662d1b55c 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -852,39 +852,39 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
fsl_lpspi->base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
if (IS_ERR(fsl_lpspi->base)) {
ret = PTR_ERR(fsl_lpspi->base);
- goto out_controller_put;
+ return ret;
}
fsl_lpspi->base_phys = res->start;
irq = platform_get_irq(pdev, 0);
if (irq < 0) {
ret = irq;
- goto out_controller_put;
+ return ret;
}
ret = devm_request_irq(&pdev->dev, irq, fsl_lpspi_isr, 0,
dev_name(&pdev->dev), fsl_lpspi);
if (ret) {
dev_err(&pdev->dev, "can't get irq%d: %d\n", irq, ret);
- goto out_controller_put;
+ return ret;
}
fsl_lpspi->clk_per = devm_clk_get(&pdev->dev, "per");
if (IS_ERR(fsl_lpspi->clk_per)) {
ret = PTR_ERR(fsl_lpspi->clk_per);
- goto out_controller_put;
+ return ret;
}
fsl_lpspi->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
if (IS_ERR(fsl_lpspi->clk_ipg)) {
ret = PTR_ERR(fsl_lpspi->clk_ipg);
- goto out_controller_put;
+ return ret;
}
/* enable the clock */
ret = fsl_lpspi_init_rpm(fsl_lpspi);
if (ret)
- goto out_controller_put;
+ return ret;
ret = pm_runtime_get_sync(fsl_lpspi->dev);
if (ret < 0) {
@@ -945,8 +945,6 @@ out_pm_get:
pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);
pm_runtime_put_sync(fsl_lpspi->dev);
pm_runtime_disable(fsl_lpspi->dev);
-out_controller_put:
- spi_controller_put(controller);
return ret;
}
diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c
index 969965d7bc98..cc18d320370f 100644
--- a/drivers/spi/spi-pci1xxxx.c
+++ b/drivers/spi/spi-pci1xxxx.c
@@ -725,6 +725,8 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id *
spi_bus->spi_int[iter] = devm_kzalloc(&pdev->dev,
sizeof(struct pci1xxxx_spi_internal),
GFP_KERNEL);
+ if (!spi_bus->spi_int[iter])
+ return -ENOMEM;
spi_sub_ptr = spi_bus->spi_int[iter];
spi_sub_ptr->spi_host = devm_spi_alloc_host(dev, sizeof(struct spi_controller));
if (!spi_sub_ptr->spi_host)
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 9fcbe040cb2f..f726d8670428 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -430,7 +430,7 @@ static bool s3c64xx_spi_can_dma(struct spi_controller *host,
struct s3c64xx_spi_driver_data *sdd = spi_controller_get_devdata(host);
if (sdd->rx_dma.ch && sdd->tx_dma.ch)
- return xfer->len > sdd->fifo_depth;
+ return xfer->len >= sdd->fifo_depth;
return false;
}
@@ -826,10 +826,9 @@ static int s3c64xx_spi_transfer_one(struct spi_controller *host,
return status;
}
- if (!is_polling(sdd) && (xfer->len > fifo_len) &&
+ if (!is_polling(sdd) && xfer->len >= fifo_len &&
sdd->rx_dma.ch && sdd->tx_dma.ch) {
use_dma = 1;
-
} else if (xfer->len >= fifo_len) {
tx_buf = xfer->tx_buf;
rx_buf = xfer->rx_buf;
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index c1fbcdd16182..c40217f44b1b 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -3672,6 +3672,8 @@ static int __init target_core_init_configfs(void)
{
struct configfs_subsystem *subsys = &target_core_fabrics;
struct t10_alua_lu_gp *lu_gp;
+ struct cred *kern_cred;
+ const struct cred *old_cred;
int ret;
pr_debug("TARGET_CORE[0]: Loading Generic Kernel Storage"
@@ -3748,11 +3750,21 @@ static int __init target_core_init_configfs(void)
if (ret < 0)
goto out;
+ /* We use the kernel credentials to access the target directory */
+ kern_cred = prepare_kernel_cred(&init_task);
+ if (!kern_cred) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ old_cred = override_creds(kern_cred);
target_init_dbroot();
+ revert_creds(old_cred);
+ put_cred(kern_cred);
return 0;
out:
+ target_xcopy_release_pt();
configfs_unregister_subsystem(subsys);
core_dev_release_virtual_lun0();
rd_module_exit();
diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 1b17dc4c219c..e25e48d76aa7 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -606,7 +606,7 @@ static int allocate_actors_buffer(struct power_allocator_params *params,
/* There might be no cooling devices yet. */
if (!num_actors) {
- ret = -EINVAL;
+ ret = 0;
goto clean_state;
}
@@ -679,11 +679,6 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
return -ENOMEM;
get_governor_trips(tz, params);
- if (!params->trip_max) {
- dev_warn(&tz->device, "power_allocator: missing trip_max\n");
- kfree(params);
- return -EINVAL;
- }
ret = check_power_actors(tz, params);
if (ret < 0) {
@@ -714,9 +709,10 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
else
params->sustainable_power = tz->tzp->sustainable_power;
- estimate_pid_constants(tz, tz->tzp->sustainable_power,
- params->trip_switch_on,
- params->trip_max->temperature);
+ if (params->trip_max)
+ estimate_pid_constants(tz, tz->tzp->sustainable_power,
+ params->trip_switch_on,
+ params->trip_max->temperature);
reset_pid_controller(params);
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index e30fd125988d..a0f8e930167d 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -3217,7 +3217,9 @@ retry:
/* MCQ mode */
if (is_mcq_enabled(hba)) {
- err = ufshcd_clear_cmd(hba, lrbp->task_tag);
+ /* successfully cleared the command, retry if needed */
+ if (ufshcd_clear_cmd(hba, lrbp->task_tag) == 0)
+ err = -EAGAIN;
hba->dev_cmd.complete = NULL;
return err;
}
@@ -9791,7 +9793,10 @@ static int __ufshcd_wl_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
/* UFS device & link must be active before we enter in this function */
if (!ufshcd_is_ufs_dev_active(hba) || !ufshcd_is_link_active(hba)) {
- ret = -EINVAL;
+ /* Wait err handler finish or trigger err recovery */
+ if (!ufshcd_eh_in_progress(hba))
+ ufshcd_force_error_recovery(hba);
+ ret = -EBUSY;
goto enable_scaling;
}
diff --git a/fs/aio.c b/fs/aio.c
index 9cdaa2faa536..0f4f531c9780 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1202,8 +1202,8 @@ static void aio_complete(struct aio_kiocb *iocb)
spin_lock_irqsave(&ctx->wait.lock, flags);
list_for_each_entry_safe(curr, next, &ctx->wait.head, w.entry)
if (avail >= curr->min_nr) {
- list_del_init_careful(&curr->w.entry);
wake_up_process(curr->w.private);
+ list_del_init_careful(&curr->w.entry);
}
spin_unlock_irqrestore(&ctx->wait.lock, flags);
}
diff --git a/fs/bcachefs/acl.c b/fs/bcachefs/acl.c
index 3640f417cce1..5c180fdc3efb 100644
--- a/fs/bcachefs/acl.c
+++ b/fs/bcachefs/acl.c
@@ -281,7 +281,6 @@ struct posix_acl *bch2_get_acl(struct mnt_idmap *idmap,
struct xattr_search_key search = X_SEARCH(acl_to_xattr_type(type), "", 0);
struct btree_trans *trans = bch2_trans_get(c);
struct btree_iter iter = { NULL };
- struct bkey_s_c_xattr xattr;
struct posix_acl *acl = NULL;
struct bkey_s_c k;
int ret;
@@ -290,28 +289,27 @@ retry:
ret = bch2_hash_lookup(trans, &iter, bch2_xattr_hash_desc,
&hash, inode_inum(inode), &search, 0);
- if (ret) {
- if (!bch2_err_matches(ret, ENOENT))
- acl = ERR_PTR(ret);
- goto out;
- }
+ if (ret)
+ goto err;
k = bch2_btree_iter_peek_slot(&iter);
ret = bkey_err(k);
- if (ret) {
- acl = ERR_PTR(ret);
- goto out;
- }
+ if (ret)
+ goto err;
- xattr = bkey_s_c_to_xattr(k);
+ struct bkey_s_c_xattr xattr = bkey_s_c_to_xattr(k);
acl = bch2_acl_from_disk(trans, xattr_val(xattr.v),
- le16_to_cpu(xattr.v->x_val_len));
+ le16_to_cpu(xattr.v->x_val_len));
+ ret = PTR_ERR_OR_ZERO(acl);
+err:
+ if (bch2_err_matches(ret, BCH_ERR_transaction_restart))
+ goto retry;
- if (!IS_ERR(acl))
+ if (ret)
+ acl = !bch2_err_matches(ret, ENOENT) ? ERR_PTR(ret) : NULL;
+
+ if (!IS_ERR_OR_NULL(acl))
set_cached_acl(&inode->v, type, acl);
-out:
- if (bch2_err_matches(PTR_ERR_OR_ZERO(acl), BCH_ERR_transaction_restart))
- goto retry;
bch2_trans_iter_exit(trans, &iter);
bch2_trans_put(trans);
diff --git a/fs/bcachefs/bcachefs_format.h b/fs/bcachefs/bcachefs_format.h
index 63102992d955..364ae42022af 100644
--- a/fs/bcachefs/bcachefs_format.h
+++ b/fs/bcachefs/bcachefs_format.h
@@ -1535,6 +1535,20 @@ enum btree_id {
BTREE_ID_NR
};
+static inline bool btree_id_is_alloc(enum btree_id id)
+{
+ switch (id) {
+ case BTREE_ID_alloc:
+ case BTREE_ID_backpointers:
+ case BTREE_ID_need_discard:
+ case BTREE_ID_freespace:
+ case BTREE_ID_bucket_gens:
+ return true;
+ default:
+ return false;
+ }
+}
+
#define BTREE_MAX_DEPTH 4U
/* Btree nodes */
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 6280da1244b5..d2555da55c6d 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -368,11 +368,16 @@ again:
buf.buf)) {
bch2_btree_node_evict(trans, cur_k.k);
cur = NULL;
- ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes) ?:
- bch2_journal_key_delete(c, b->c.btree_id,
- b->c.level, cur_k.k->k.p);
+ ret = bch2_journal_key_delete(c, b->c.btree_id,
+ b->c.level, cur_k.k->k.p);
if (ret)
break;
+
+ if (!btree_id_is_alloc(b->c.btree_id)) {
+ ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
+ if (ret)
+ break;
+ }
continue;
}
@@ -544,12 +549,12 @@ reconstruct_root:
bch2_btree_root_alloc_fake(c, i, 0);
} else {
bch2_btree_root_alloc_fake(c, i, 1);
+ bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
if (ret)
break;
}
- bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
reconstructed_root = true;
}
diff --git a/fs/bcachefs/btree_iter.h b/fs/bcachefs/btree_iter.h
index 24772538e4cc..1d58d447b386 100644
--- a/fs/bcachefs/btree_iter.h
+++ b/fs/bcachefs/btree_iter.h
@@ -642,7 +642,7 @@ int __bch2_btree_trans_too_many_iters(struct btree_trans *);
static inline int btree_trans_too_many_iters(struct btree_trans *trans)
{
- if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_INITIAL - 8)
+ if (bitmap_weight(trans->paths_allocated, trans->nr_paths) > BTREE_ITER_NORMAL_LIMIT - 8)
return __bch2_btree_trans_too_many_iters(trans);
return 0;
diff --git a/fs/bcachefs/btree_journal_iter.c b/fs/bcachefs/btree_journal_iter.c
index 5cbcbfe85235..1e8cf49a6935 100644
--- a/fs/bcachefs/btree_journal_iter.c
+++ b/fs/bcachefs/btree_journal_iter.c
@@ -130,12 +130,30 @@ struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *c, enum btree_id btree
return bch2_journal_keys_peek_upto(c, btree_id, level, pos, pos, &idx);
}
+static void journal_iter_verify(struct journal_iter *iter)
+{
+ struct journal_keys *keys = iter->keys;
+ size_t gap_size = keys->size - keys->nr;
+
+ BUG_ON(iter->idx >= keys->gap &&
+ iter->idx < keys->gap + gap_size);
+
+ if (iter->idx < keys->size) {
+ struct journal_key *k = keys->data + iter->idx;
+
+ int cmp = cmp_int(k->btree_id, iter->btree_id) ?:
+ cmp_int(k->level, iter->level);
+ BUG_ON(cmp < 0);
+ }
+}
+
static void journal_iters_fix(struct bch_fs *c)
{
struct journal_keys *keys = &c->journal_keys;
/* The key we just inserted is immediately before the gap: */
size_t gap_end = keys->gap + (keys->size - keys->nr);
- struct btree_and_journal_iter *iter;
+ struct journal_key *new_key = &keys->data[keys->gap - 1];
+ struct journal_iter *iter;
/*
* If an iterator points one after the key we just inserted, decrement
@@ -143,9 +161,14 @@ static void journal_iters_fix(struct bch_fs *c)
* decrement was unnecessary, bch2_btree_and_journal_iter_peek() will
* handle that:
*/
- list_for_each_entry(iter, &c->journal_iters, journal.list)
- if (iter->journal.idx == gap_end)
- iter->journal.idx = keys->gap - 1;
+ list_for_each_entry(iter, &c->journal_iters, list) {
+ journal_iter_verify(iter);
+ if (iter->idx == gap_end &&
+ new_key->btree_id == iter->btree_id &&
+ new_key->level == iter->level)
+ iter->idx = keys->gap - 1;
+ journal_iter_verify(iter);
+ }
}
static void journal_iters_move_gap(struct bch_fs *c, size_t old_gap, size_t new_gap)
@@ -192,7 +215,12 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
if (idx > keys->gap)
idx -= keys->size - keys->nr;
+ size_t old_gap = keys->gap;
+
if (keys->nr == keys->size) {
+ journal_iters_move_gap(c, old_gap, keys->size);
+ old_gap = keys->size;
+
struct journal_keys new_keys = {
.nr = keys->nr,
.size = max_t(size_t, keys->size, 8) * 2,
@@ -216,7 +244,7 @@ int bch2_journal_key_insert_take(struct bch_fs *c, enum btree_id id,
keys->gap = keys->nr;
}
- journal_iters_move_gap(c, keys->gap, idx);
+ journal_iters_move_gap(c, old_gap, idx);
move_gap(keys, idx);
@@ -301,16 +329,21 @@ static void bch2_journal_iter_advance(struct journal_iter *iter)
static struct bkey_s_c bch2_journal_iter_peek(struct journal_iter *iter)
{
- struct journal_key *k = iter->keys->data + iter->idx;
+ journal_iter_verify(iter);
+
+ while (iter->idx < iter->keys->size) {
+ struct journal_key *k = iter->keys->data + iter->idx;
+
+ int cmp = cmp_int(k->btree_id, iter->btree_id) ?:
+ cmp_int(k->level, iter->level);
+ if (cmp > 0)
+ break;
+ BUG_ON(cmp);
- while (k < iter->keys->data + iter->keys->size &&
- k->btree_id == iter->btree_id &&
- k->level == iter->level) {
if (!k->overwritten)
return bkey_i_to_s_c(k->k);
bch2_journal_iter_advance(iter);
- k = iter->keys->data + iter->idx;
}
return bkey_s_c_null;
@@ -330,6 +363,8 @@ static void bch2_journal_iter_init(struct bch_fs *c,
iter->level = level;
iter->keys = &c->journal_keys;
iter->idx = bch2_journal_key_search(&c->journal_keys, id, level, pos);
+
+ journal_iter_verify(iter);
}
static struct bkey_s_c bch2_journal_iter_peek_btree(struct btree_and_journal_iter *iter)
@@ -434,10 +469,15 @@ void __bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans,
iter->trans = trans;
iter->b = b;
iter->node_iter = node_iter;
- bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos);
- INIT_LIST_HEAD(&iter->journal.list);
iter->pos = b->data->min_key;
iter->at_end = false;
+ INIT_LIST_HEAD(&iter->journal.list);
+
+ if (trans->journal_replay_not_finished) {
+ bch2_journal_iter_init(trans->c, &iter->journal, b->c.btree_id, b->c.level, pos);
+ if (!test_bit(BCH_FS_may_go_rw, &trans->c->flags))
+ list_add(&iter->journal.list, &trans->c->journal_iters);
+ }
}
/*
@@ -452,9 +492,6 @@ void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *trans,
bch2_btree_node_iter_init_from_start(&node_iter, b);
__bch2_btree_and_journal_iter_init_node_iter(trans, iter, b, node_iter, b->data->min_key);
- if (trans->journal_replay_not_finished &&
- !test_bit(BCH_FS_may_go_rw, &trans->c->flags))
- list_add(&iter->journal.list, &trans->c->journal_iters);
}
/* sort and dedup all keys in the journal: */
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 581edcb0911b..88a3582a3275 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -169,6 +169,7 @@ static void bkey_cached_move_to_freelist(struct btree_key_cache *bc,
} else {
mutex_lock(&bc->lock);
list_move_tail(&ck->list, &bc->freed_pcpu);
+ bc->nr_freed_pcpu++;
mutex_unlock(&bc->lock);
}
}
@@ -245,6 +246,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path,
if (!list_empty(&bc->freed_pcpu)) {
ck = list_last_entry(&bc->freed_pcpu, struct bkey_cached, list);
list_del_init(&ck->list);
+ bc->nr_freed_pcpu--;
}
mutex_unlock(&bc->lock);
}
@@ -659,7 +661,7 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans,
commit_flags |= BCH_WATERMARK_reclaim;
if (ck->journal.seq != journal_last_seq(j) ||
- j->watermark == BCH_WATERMARK_stripe)
+ !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags))
commit_flags |= BCH_TRANS_COMMIT_no_journal_res;
ret = bch2_btree_iter_traverse(&b_iter) ?:
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index b9b151e693ed..f2caf491957e 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -440,33 +440,7 @@ void bch2_btree_node_lock_write_nofail(struct btree_trans *trans,
struct btree_path *path,
struct btree_bkey_cached_common *b)
{
- struct btree_path *linked;
- unsigned i, iter;
- int ret;
-
- /*
- * XXX BIG FAT NOTICE
- *
- * Drop all read locks before taking a write lock:
- *
- * This is a hack, because bch2_btree_node_lock_write_nofail() is a
- * hack - but by dropping read locks first, this should never fail, and
- * we only use this in code paths where whatever read locks we've
- * already taken are no longer needed:
- */
-
- trans_for_each_path(trans, linked, iter) {
- if (!linked->nodes_locked)
- continue;
-
- for (i = 0; i < BTREE_MAX_DEPTH; i++)
- if (btree_node_read_locked(linked, i)) {
- btree_node_unlock(trans, linked, i);
- btree_path_set_dirty(linked, BTREE_ITER_NEED_RELOCK);
- }
- }
-
- ret = __btree_node_lock_write(trans, path, b, true);
+ int ret = __btree_node_lock_write(trans, path, b, true);
BUG_ON(ret);
}
diff --git a/fs/bcachefs/btree_node_scan.c b/fs/bcachefs/btree_node_scan.c
index 3f33be7e5e5c..556f76f5c84e 100644
--- a/fs/bcachefs/btree_node_scan.c
+++ b/fs/bcachefs/btree_node_scan.c
@@ -133,6 +133,9 @@ static void try_read_btree_node(struct find_btree_nodes *f, struct bch_dev *ca,
if (le64_to_cpu(bn->magic) != bset_magic(c))
return;
+ if (btree_id_is_alloc(BTREE_NODE_ID(bn)))
+ return;
+
rcu_read_lock();
struct found_btree_node n = {
.btree_id = BTREE_NODE_ID(bn),
@@ -213,6 +216,9 @@ static int read_btree_nodes(struct find_btree_nodes *f)
closure_init_stack(&cl);
for_each_online_member(c, ca) {
+ if (!(ca->mi.data_allowed & BIT(BCH_DATA_btree)))
+ continue;
+
struct find_btree_nodes_worker *w = kmalloc(sizeof(*w), GFP_KERNEL);
struct task_struct *t;
@@ -290,7 +296,7 @@ again:
found_btree_node_to_text(&buf, c, n);
bch_err(c, "%s", buf.buf);
printbuf_exit(&buf);
- return -1;
+ return -BCH_ERR_fsck_repair_unimplemented;
}
}
@@ -436,6 +442,9 @@ bool bch2_btree_has_scanned_nodes(struct bch_fs *c, enum btree_id btree)
int bch2_get_scanned_nodes(struct bch_fs *c, enum btree_id btree,
unsigned level, struct bpos node_min, struct bpos node_max)
{
+ if (btree_id_is_alloc(btree))
+ return 0;
+
struct find_btree_nodes *f = &c->found_btree_nodes;
int ret = bch2_run_explicit_recovery_pass(c, BCH_RECOVERY_PASS_scan_for_btree_nodes);
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index 9404d96c38f3..e0c982a4195c 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -364,7 +364,21 @@ struct btree_insert_entry {
unsigned long ip_allocated;
};
+/* Number of btree paths we preallocate, usually enough */
#define BTREE_ITER_INITIAL 64
+/*
+ * Lmiit for btree_trans_too_many_iters(); this is enough that almost all code
+ * paths should run inside this limit, and if they don't it usually indicates a
+ * bug (leaking/duplicated btree paths).
+ *
+ * exception: some fsck paths
+ *
+ * bugs with excessive path usage seem to have possibly been eliminated now, so
+ * we might consider eliminating this (and btree_trans_too_many_iter()) at some
+ * point.
+ */
+#define BTREE_ITER_NORMAL_LIMIT 256
+/* never exceed limit */
#define BTREE_ITER_MAX (1U << 10)
struct btree_trans_commit_hook;
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index 32397b99752f..c4a5e83a56a4 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -26,9 +26,9 @@
#include <linux/random.h>
-const char * const bch2_btree_update_modes[] = {
+static const char * const bch2_btree_update_modes[] = {
#define x(t) #t,
- BCH_WATERMARKS()
+ BTREE_UPDATE_MODES()
#undef x
NULL
};
@@ -704,9 +704,13 @@ static void btree_update_nodes_written(struct btree_update *as)
bch2_fs_fatal_err_on(ret && !bch2_journal_error(&c->journal), c,
"%s", bch2_err_str(ret));
err:
- if (as->b) {
-
- b = as->b;
+ /*
+ * We have to be careful because another thread might be getting ready
+ * to free as->b and calling btree_update_reparent() on us - we'll
+ * recheck under btree_update_lock below:
+ */
+ b = READ_ONCE(as->b);
+ if (b) {
btree_path_idx_t path_idx = get_unlocked_mut_path(trans,
as->btree_id, b->c.level, b->key.k.p);
struct btree_path *path = trans->paths + path_idx;
@@ -850,15 +854,17 @@ static void btree_update_updated_node(struct btree_update *as, struct btree *b)
{
struct bch_fs *c = as->c;
- mutex_lock(&c->btree_interior_update_lock);
- list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
-
BUG_ON(as->mode != BTREE_UPDATE_none);
+ BUG_ON(as->update_level_end < b->c.level);
BUG_ON(!btree_node_dirty(b));
BUG_ON(!b->c.level);
+ mutex_lock(&c->btree_interior_update_lock);
+ list_add_tail(&as->unwritten_list, &c->btree_interior_updates_unwritten);
+
as->mode = BTREE_UPDATE_node;
as->b = b;
+ as->update_level_end = b->c.level;
set_btree_node_write_blocked(b);
list_add(&as->write_blocked_list, &b->write_blocked);
@@ -1100,7 +1106,7 @@ static void bch2_btree_update_done(struct btree_update *as, struct btree_trans *
static struct btree_update *
bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
- unsigned level, bool split, unsigned flags)
+ unsigned level_start, bool split, unsigned flags)
{
struct bch_fs *c = trans->c;
struct btree_update *as;
@@ -1108,7 +1114,7 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
int disk_res_flags = (flags & BCH_TRANS_COMMIT_no_enospc)
? BCH_DISK_RESERVATION_NOFAIL : 0;
unsigned nr_nodes[2] = { 0, 0 };
- unsigned update_level = level;
+ unsigned level_end = level_start;
enum bch_watermark watermark = flags & BCH_WATERMARK_MASK;
int ret = 0;
u32 restart_count = trans->restart_count;
@@ -1123,34 +1129,30 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
flags &= ~BCH_WATERMARK_MASK;
flags |= watermark;
- if (watermark < c->journal.watermark) {
- struct journal_res res = { 0 };
- unsigned journal_flags = watermark|JOURNAL_RES_GET_CHECK;
+ if (watermark < BCH_WATERMARK_reclaim &&
+ test_bit(JOURNAL_SPACE_LOW, &c->journal.flags)) {
+ if (flags & BCH_TRANS_COMMIT_journal_reclaim)
+ return ERR_PTR(-BCH_ERR_journal_reclaim_would_deadlock);
- if ((flags & BCH_TRANS_COMMIT_journal_reclaim) &&
- watermark < BCH_WATERMARK_reclaim)
- journal_flags |= JOURNAL_RES_GET_NONBLOCK;
-
- ret = drop_locks_do(trans,
- bch2_journal_res_get(&c->journal, &res, 1, journal_flags));
- if (bch2_err_matches(ret, BCH_ERR_operation_blocked))
- ret = -BCH_ERR_journal_reclaim_would_deadlock;
+ bch2_trans_unlock(trans);
+ wait_event(c->journal.wait, !test_bit(JOURNAL_SPACE_LOW, &c->journal.flags));
+ ret = bch2_trans_relock(trans);
if (ret)
return ERR_PTR(ret);
}
while (1) {
- nr_nodes[!!update_level] += 1 + split;
- update_level++;
+ nr_nodes[!!level_end] += 1 + split;
+ level_end++;
- ret = bch2_btree_path_upgrade(trans, path, update_level + 1);
+ ret = bch2_btree_path_upgrade(trans, path, level_end + 1);
if (ret)
return ERR_PTR(ret);
- if (!btree_path_node(path, update_level)) {
+ if (!btree_path_node(path, level_end)) {
/* Allocating new root? */
nr_nodes[1] += split;
- update_level = BTREE_MAX_DEPTH;
+ level_end = BTREE_MAX_DEPTH;
break;
}
@@ -1158,11 +1160,11 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
* Always check for space for two keys, even if we won't have to
* split at prior level - it might have been a merge instead:
*/
- if (bch2_btree_node_insert_fits(path->l[update_level].b,
+ if (bch2_btree_node_insert_fits(path->l[level_end].b,
BKEY_BTREE_PTR_U64s_MAX * 2))
break;
- split = path->l[update_level].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
+ split = path->l[level_end].b->nr.live_u64s > BTREE_SPLIT_THRESHOLD(c);
}
if (!down_read_trylock(&c->gc_lock)) {
@@ -1176,14 +1178,15 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
as = mempool_alloc(&c->btree_interior_update_pool, GFP_NOFS);
memset(as, 0, sizeof(*as));
closure_init(&as->cl, NULL);
- as->c = c;
- as->start_time = start_time;
- as->ip_started = _RET_IP_;
- as->mode = BTREE_UPDATE_none;
- as->watermark = watermark;
- as->took_gc_lock = true;
- as->btree_id = path->btree_id;
- as->update_level = update_level;
+ as->c = c;
+ as->start_time = start_time;
+ as->ip_started = _RET_IP_;
+ as->mode = BTREE_UPDATE_none;
+ as->watermark = watermark;
+ as->took_gc_lock = true;
+ as->btree_id = path->btree_id;
+ as->update_level_start = level_start;
+ as->update_level_end = level_end;
INIT_LIST_HEAD(&as->list);
INIT_LIST_HEAD(&as->unwritten_list);
INIT_LIST_HEAD(&as->write_blocked_list);
@@ -1373,12 +1376,12 @@ static void bch2_insert_fixup_btree_ptr(struct btree_update *as,
}
static void
-__bch2_btree_insert_keys_interior(struct btree_update *as,
- struct btree_trans *trans,
- struct btree_path *path,
- struct btree *b,
- struct btree_node_iter node_iter,
- struct keylist *keys)
+bch2_btree_insert_keys_interior(struct btree_update *as,
+ struct btree_trans *trans,
+ struct btree_path *path,
+ struct btree *b,
+ struct btree_node_iter node_iter,
+ struct keylist *keys)
{
struct bkey_i *insert = bch2_keylist_front(keys);
struct bkey_packed *k;
@@ -1534,7 +1537,7 @@ static void btree_split_insert_keys(struct btree_update *as,
bch2_btree_node_iter_init(&node_iter, b, &bch2_keylist_front(keys)->k.p);
- __bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
+ bch2_btree_insert_keys_interior(as, trans, path, b, node_iter, keys);
BUG_ON(bch2_btree_node_check_topology(trans, b));
}
@@ -1714,27 +1717,6 @@ err:
goto out;
}
-static void
-bch2_btree_insert_keys_interior(struct btree_update *as,
- struct btree_trans *trans,
- struct btree_path *path,
- struct btree *b,
- struct keylist *keys)
-{
- struct btree_path *linked;
- unsigned i;
-
- __bch2_btree_insert_keys_interior(as, trans, path, b,
- path->l[b->c.level].iter, keys);
-
- btree_update_updated_node(as, b);
-
- trans_for_each_path_with_node(trans, b, linked, i)
- bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
-
- bch2_trans_verify_paths(trans);
-}
-
/**
* bch2_btree_insert_node - insert bkeys into a given btree node
*
@@ -1755,7 +1737,8 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
struct keylist *keys)
{
struct bch_fs *c = as->c;
- struct btree_path *path = trans->paths + path_idx;
+ struct btree_path *path = trans->paths + path_idx, *linked;
+ unsigned i;
int old_u64s = le16_to_cpu(btree_bset_last(b)->u64s);
int old_live_u64s = b->nr.live_u64s;
int live_u64s_added, u64s_added;
@@ -1784,7 +1767,13 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
return ret;
}
- bch2_btree_insert_keys_interior(as, trans, path, b, keys);
+ bch2_btree_insert_keys_interior(as, trans, path, b,
+ path->l[b->c.level].iter, keys);
+
+ trans_for_each_path_with_node(trans, b, linked, i)
+ bch2_btree_node_iter_peek(&linked->l[b->c.level].iter, b);
+
+ bch2_trans_verify_paths(trans);
live_u64s_added = (int) b->nr.live_u64s - old_live_u64s;
u64s_added = (int) le16_to_cpu(btree_bset_last(b)->u64s) - old_u64s;
@@ -1798,6 +1787,7 @@ static int bch2_btree_insert_node(struct btree_update *as, struct btree_trans *t
bch2_maybe_compact_whiteouts(c, b))
bch2_trans_node_reinit_iter(trans, b);
+ btree_update_updated_node(as, b);
bch2_btree_node_unlock_write(trans, path, b);
BUG_ON(bch2_btree_node_check_topology(trans, b));
@@ -1807,7 +1797,7 @@ split:
* We could attempt to avoid the transaction restart, by calling
* bch2_btree_path_upgrade() and allocating more nodes:
*/
- if (b->c.level >= as->update_level) {
+ if (b->c.level >= as->update_level_end) {
trace_and_count(c, trans_restart_split_race, trans, _THIS_IP_, b);
return btree_trans_restart(trans, BCH_ERR_transaction_restart_split_race);
}
@@ -2519,9 +2509,11 @@ void bch2_btree_root_alloc_fake(struct bch_fs *c, enum btree_id id, unsigned lev
static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update *as)
{
- prt_printf(out, "%ps: btree=%s watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+ prt_printf(out, "%ps: btree=%s l=%u-%u watermark=%s mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
(void *) as->ip_started,
bch2_btree_id_str(as->btree_id),
+ as->update_level_start,
+ as->update_level_end,
bch2_watermarks[as->watermark],
bch2_btree_update_modes[as->mode],
as->nodes_written,
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 88dcf5a22a3b..c1a479ebaad1 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -57,7 +57,8 @@ struct btree_update {
unsigned took_gc_lock:1;
enum btree_id btree_id;
- unsigned update_level;
+ unsigned update_level_start;
+ unsigned update_level_end;
struct disk_reservation disk_res;
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index cbfa6459bdbc..72781aad6ba7 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -134,42 +134,38 @@ static long bch2_ioctl_incremental(struct bch_ioctl_incremental __user *user_arg
struct fsck_thread {
struct thread_with_stdio thr;
struct bch_fs *c;
- char **devs;
- size_t nr_devs;
struct bch_opts opts;
};
static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr)
{
struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr);
- if (thr->devs)
- for (size_t i = 0; i < thr->nr_devs; i++)
- kfree(thr->devs[i]);
- kfree(thr->devs);
kfree(thr);
}
static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio)
{
struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr);
- struct bch_fs *c = bch2_fs_open(thr->devs, thr->nr_devs, thr->opts);
-
- if (IS_ERR(c))
- return PTR_ERR(c);
+ struct bch_fs *c = thr->c;
- int ret = 0;
- if (test_bit(BCH_FS_errors_fixed, &c->flags))
- ret |= 1;
- if (test_bit(BCH_FS_error, &c->flags))
- ret |= 4;
+ int ret = PTR_ERR_OR_ZERO(c);
+ if (ret)
+ return ret;
- bch2_fs_stop(c);
+ ret = bch2_fs_start(thr->c);
+ if (ret)
+ goto err;
- if (ret & 1)
+ if (test_bit(BCH_FS_errors_fixed, &c->flags)) {
bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name);
- if (ret & 4)
+ ret |= 1;
+ }
+ if (test_bit(BCH_FS_error, &c->flags)) {
bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name);
-
+ ret |= 4;
+ }
+err:
+ bch2_fs_stop(c);
return ret;
}
@@ -182,7 +178,7 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
{
struct bch_ioctl_fsck_offline arg;
struct fsck_thread *thr = NULL;
- u64 *devs = NULL;
+ darray_str(devs) = {};
long ret = 0;
if (copy_from_user(&arg, user_arg, sizeof(arg)))
@@ -194,29 +190,32 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!(devs = kcalloc(arg.nr_devs, sizeof(*devs), GFP_KERNEL)) ||
- !(thr = kzalloc(sizeof(*thr), GFP_KERNEL)) ||
- !(thr->devs = kcalloc(arg.nr_devs, sizeof(*thr->devs), GFP_KERNEL))) {
- ret = -ENOMEM;
- goto err;
- }
+ for (size_t i = 0; i < arg.nr_devs; i++) {
+ u64 dev_u64;
+ ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64));
+ if (ret)
+ goto err;
- thr->opts = bch2_opts_empty();
- thr->nr_devs = arg.nr_devs;
+ char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX);
+ ret = PTR_ERR_OR_ZERO(dev_str);
+ if (ret)
+ goto err;
- if (copy_from_user(devs, &user_arg->devs[0],
- array_size(sizeof(user_arg->devs[0]), arg.nr_devs))) {
- ret = -EINVAL;
- goto err;
+ ret = darray_push(&devs, dev_str);
+ if (ret) {
+ kfree(dev_str);
+ goto err;
+ }
}
- for (size_t i = 0; i < arg.nr_devs; i++) {
- thr->devs[i] = strndup_user((char __user *)(unsigned long) devs[i], PATH_MAX);
- ret = PTR_ERR_OR_ZERO(thr->devs[i]);
- if (ret)
- goto err;
+ thr = kzalloc(sizeof(*thr), GFP_KERNEL);
+ if (!thr) {
+ ret = -ENOMEM;
+ goto err;
}
+ thr->opts = bch2_opts_empty();
+
if (arg.opts) {
char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16);
@@ -230,15 +229,26 @@ static long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_a
opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio);
+ /* We need request_key() to be called before we punt to kthread: */
+ opt_set(thr->opts, nostart, true);
+
+ thr->c = bch2_fs_open(devs.data, arg.nr_devs, thr->opts);
+
+ if (!IS_ERR(thr->c) &&
+ thr->c->opts.errors == BCH_ON_ERROR_panic)
+ thr->c->opts.errors = BCH_ON_ERROR_ro;
+
ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_offline_fsck_ops);
-err:
- if (ret < 0) {
- if (thr)
- bch2_fsck_thread_exit(&thr->thr);
- pr_err("ret %s", bch2_err_str(ret));
- }
- kfree(devs);
+out:
+ darray_for_each(devs, i)
+ kfree(*i);
+ darray_exit(&devs);
return ret;
+err:
+ if (thr)
+ bch2_fsck_thread_exit(&thr->thr);
+ pr_err("ret %s", bch2_err_str(ret));
+ goto out;
}
static long bch2_global_ioctl(unsigned cmd, void __user *arg)
diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 34731ee0217f..0022b51ce3c0 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -598,6 +598,8 @@ int bch2_data_update_init(struct btree_trans *trans,
i++;
}
+ unsigned durability_required = max(0, (int) (io_opts.data_replicas - durability_have));
+
/*
* If current extent durability is less than io_opts.data_replicas,
* we're not trying to rereplicate the extent up to data_replicas here -
@@ -607,7 +609,7 @@ int bch2_data_update_init(struct btree_trans *trans,
* rereplicate, currently, so that users don't get an unexpected -ENOSPC
*/
if (!(m->data_opts.write_flags & BCH_WRITE_CACHED) &&
- durability_have >= io_opts.data_replicas) {
+ !durability_required) {
m->data_opts.kill_ptrs |= m->data_opts.rewrite_ptrs;
m->data_opts.rewrite_ptrs = 0;
/* if iter == NULL, it's just a promote */
@@ -616,11 +618,18 @@ int bch2_data_update_init(struct btree_trans *trans,
goto done;
}
- m->op.nr_replicas = min(durability_removing, io_opts.data_replicas - durability_have) +
+ m->op.nr_replicas = min(durability_removing, durability_required) +
m->data_opts.extra_replicas;
- m->op.nr_replicas_required = m->op.nr_replicas;
- BUG_ON(!m->op.nr_replicas);
+ /*
+ * If device(s) were set to durability=0 after data was written to them
+ * we can end up with a duribilty=0 extent, and the normal algorithm
+ * that tries not to increase durability doesn't work:
+ */
+ if (!(durability_have + durability_removing))
+ m->op.nr_replicas = max((unsigned) m->op.nr_replicas, 1);
+
+ m->op.nr_replicas_required = m->op.nr_replicas;
if (reserve_sectors) {
ret = bch2_disk_reservation_add(c, &m->op.res, reserve_sectors,
diff --git a/fs/bcachefs/debug.c b/fs/bcachefs/debug.c
index 208ce6f0fc43..cd99b7399414 100644
--- a/fs/bcachefs/debug.c
+++ b/fs/bcachefs/debug.c
@@ -13,6 +13,7 @@
#include "btree_iter.h"
#include "btree_locking.h"
#include "btree_update.h"
+#include "btree_update_interior.h"
#include "buckets.h"
#include "debug.h"
#include "error.h"
@@ -668,7 +669,7 @@ static ssize_t bch2_journal_pins_read(struct file *file, char __user *buf,
i->size = size;
i->ret = 0;
- do {
+ while (1) {
err = flush_buf(i);
if (err)
return err;
@@ -676,9 +677,12 @@ static ssize_t bch2_journal_pins_read(struct file *file, char __user *buf,
if (!i->size)
break;
+ if (done)
+ break;
+
done = bch2_journal_seq_pins_to_text(&i->buf, &c->journal, &i->iter);
i->iter++;
- } while (!done);
+ }
if (i->buf.allocation_failure)
return -ENOMEM;
@@ -693,13 +697,45 @@ static const struct file_operations journal_pins_ops = {
.read = bch2_journal_pins_read,
};
+static ssize_t bch2_btree_updates_read(struct file *file, char __user *buf,
+ size_t size, loff_t *ppos)
+{
+ struct dump_iter *i = file->private_data;
+ struct bch_fs *c = i->c;
+ int err;
+
+ i->ubuf = buf;
+ i->size = size;
+ i->ret = 0;
+
+ if (!i->iter) {
+ bch2_btree_updates_to_text(&i->buf, c);
+ i->iter++;
+ }
+
+ err = flush_buf(i);
+ if (err)
+ return err;
+
+ if (i->buf.allocation_failure)
+ return -ENOMEM;
+
+ return i->ret;
+}
+
+static const struct file_operations btree_updates_ops = {
+ .owner = THIS_MODULE,
+ .open = bch2_dump_open,
+ .release = bch2_dump_release,
+ .read = bch2_btree_updates_read,
+};
+
static int btree_transaction_stats_open(struct inode *inode, struct file *file)
{
struct bch_fs *c = inode->i_private;
struct dump_iter *i;
i = kzalloc(sizeof(struct dump_iter), GFP_KERNEL);
-
if (!i)
return -ENOMEM;
@@ -866,6 +902,20 @@ void bch2_fs_debug_exit(struct bch_fs *c)
debugfs_remove_recursive(c->fs_debug_dir);
}
+static void bch2_fs_debug_btree_init(struct bch_fs *c, struct btree_debug *bd)
+{
+ struct dentry *d;
+
+ d = debugfs_create_dir(bch2_btree_id_str(bd->id), c->btree_debug_dir);
+
+ debugfs_create_file("keys", 0400, d, bd, &btree_debug_ops);
+
+ debugfs_create_file("formats", 0400, d, bd, &btree_format_debug_ops);
+
+ debugfs_create_file("bfloat-failed", 0400, d, bd,
+ &bfloat_failed_debug_ops);
+}
+
void bch2_fs_debug_init(struct bch_fs *c)
{
struct btree_debug *bd;
@@ -888,6 +938,9 @@ void bch2_fs_debug_init(struct bch_fs *c)
debugfs_create_file("journal_pins", 0400, c->fs_debug_dir,
c->btree_debug, &journal_pins_ops);
+ debugfs_create_file("btree_updates", 0400, c->fs_debug_dir,
+ c->btree_debug, &btree_updates_ops);
+
debugfs_create_file("btree_transaction_stats", 0400, c->fs_debug_dir,
c, &btree_transaction_stats_op);
@@ -902,21 +955,7 @@ void bch2_fs_debug_init(struct bch_fs *c)
bd < c->btree_debug + ARRAY_SIZE(c->btree_debug);
bd++) {
bd->id = bd - c->btree_debug;
- debugfs_create_file(bch2_btree_id_str(bd->id),
- 0400, c->btree_debug_dir, bd,
- &btree_debug_ops);
-
- snprintf(name, sizeof(name), "%s-formats",
- bch2_btree_id_str(bd->id));
-
- debugfs_create_file(name, 0400, c->btree_debug_dir, bd,
- &btree_format_debug_ops);
-
- snprintf(name, sizeof(name), "%s-bfloat-failed",
- bch2_btree_id_str(bd->id));
-
- debugfs_create_file(name, 0400, c->btree_debug_dir, bd,
- &bfloat_failed_debug_ops);
+ bch2_fs_debug_btree_init(c, bd);
}
}
diff --git a/fs/bcachefs/eytzinger.c b/fs/bcachefs/eytzinger.c
index 4ce5e957a6e9..0f955c3c76a7 100644
--- a/fs/bcachefs/eytzinger.c
+++ b/fs/bcachefs/eytzinger.c
@@ -115,7 +115,7 @@ static void swap_bytes(void *a, void *b, size_t n)
struct wrapper {
cmp_func_t cmp;
- swap_func_t swap;
+ swap_func_t swap_func;
};
/*
@@ -125,7 +125,7 @@ struct wrapper {
static void do_swap(void *a, void *b, size_t size, swap_r_func_t swap_func, const void *priv)
{
if (swap_func == SWAP_WRAPPER) {
- ((const struct wrapper *)priv)->swap(a, b, (int)size);
+ ((const struct wrapper *)priv)->swap_func(a, b, (int)size);
return;
}
@@ -174,7 +174,7 @@ void eytzinger0_sort_r(void *base, size_t n, size_t size,
int i, c, r;
/* called from 'sort' without swap function, let's pick the default */
- if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap)
+ if (swap_func == SWAP_WRAPPER && !((struct wrapper *)priv)->swap_func)
swap_func = NULL;
if (!swap_func) {
@@ -227,7 +227,7 @@ void eytzinger0_sort(void *base, size_t n, size_t size,
{
struct wrapper w = {
.cmp = cmp_func,
- .swap = swap_func,
+ .swap_func = swap_func,
};
return eytzinger0_sort_r(base, n, size, _CMP_WRAPPER, SWAP_WRAPPER, &w);
diff --git a/fs/bcachefs/eytzinger.h b/fs/bcachefs/eytzinger.h
index ee0e2df33322..24840aee335c 100644
--- a/fs/bcachefs/eytzinger.h
+++ b/fs/bcachefs/eytzinger.h
@@ -242,8 +242,8 @@ static inline unsigned inorder_to_eytzinger0(unsigned i, unsigned size)
(_i) = eytzinger0_next((_i), (_size)))
/* return greatest node <= @search, or -1 if not found */
-static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size,
- cmp_func_t cmp, const void *search)
+static inline int eytzinger0_find_le(void *base, size_t nr, size_t size,
+ cmp_func_t cmp, const void *search)
{
unsigned i, n = 0;
@@ -256,18 +256,32 @@ static inline ssize_t eytzinger0_find_le(void *base, size_t nr, size_t size,
} while (n < nr);
if (n & 1) {
- /* @i was greater than @search, return previous node: */
+ /*
+ * @i was greater than @search, return previous node:
+ *
+ * if @i was leftmost/smallest element,
+ * eytzinger0_prev(eytzinger0_first())) returns -1, as expected
+ */
return eytzinger0_prev(i, nr);
} else {
return i;
}
}
-static inline ssize_t eytzinger0_find_gt(void *base, size_t nr, size_t size,
- cmp_func_t cmp, const void *search)
+static inline int eytzinger0_find_gt(void *base, size_t nr, size_t size,
+ cmp_func_t cmp, const void *search)
{
ssize_t idx = eytzinger0_find_le(base, nr, size, cmp, search);
- return eytzinger0_next(idx, size);
+
+ /*
+ * if eytitzinger0_find_le() returned -1 - no element was <= search - we
+ * want to return the first element; next/prev identities mean this work
+ * as expected
+ *
+ * similarly if find_le() returns last element, we should return -1;
+ * identities mean this all works out:
+ */
+ return eytzinger0_next(idx, nr);
}
#define eytzinger0_find(base, nr, size, _cmp, search) \
diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c
index ab811c0dad26..04a577848b01 100644
--- a/fs/bcachefs/journal_reclaim.c
+++ b/fs/bcachefs/journal_reclaim.c
@@ -67,6 +67,8 @@ void bch2_journal_set_watermark(struct journal *j)
track_event_change(&c->times[BCH_TIME_blocked_write_buffer_full], low_on_wb))
trace_and_count(c, journal_full, c);
+ mod_bit(JOURNAL_SPACE_LOW, &j->flags, low_on_space || low_on_pin);
+
swap(watermark, j->watermark);
if (watermark > j->watermark)
journal_wake(j);
diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h
index 8c053cb64ca5..b5161b5d76a0 100644
--- a/fs/bcachefs/journal_types.h
+++ b/fs/bcachefs/journal_types.h
@@ -134,6 +134,7 @@ enum journal_flags {
JOURNAL_STARTED,
JOURNAL_MAY_SKIP_FLUSH,
JOURNAL_NEED_FLUSH_WRITE,
+ JOURNAL_SPACE_LOW,
};
/* Reasons we may fail to get a journal reservation: */
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index b76c16152579..0f328aba9760 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -47,20 +47,6 @@ void bch2_btree_lost_data(struct bch_fs *c, enum btree_id btree)
}
}
-static bool btree_id_is_alloc(enum btree_id id)
-{
- switch (id) {
- case BTREE_ID_alloc:
- case BTREE_ID_backpointers:
- case BTREE_ID_need_discard:
- case BTREE_ID_freespace:
- case BTREE_ID_bucket_gens:
- return true;
- default:
- return false;
- }
-}
-
/* for -o reconstruct_alloc: */
static void bch2_reconstruct_alloc(struct bch_fs *c)
{
diff --git a/fs/bcachefs/snapshot.c b/fs/bcachefs/snapshot.c
index 0e806f04f3d7..544322d5c251 100644
--- a/fs/bcachefs/snapshot.c
+++ b/fs/bcachefs/snapshot.c
@@ -125,6 +125,15 @@ static inline u32 get_ancestor_below(struct snapshot_table *t, u32 id, u32 ances
return s->parent;
}
+static bool test_ancestor_bitmap(struct snapshot_table *t, u32 id, u32 ancestor)
+{
+ const struct snapshot_t *s = __snapshot_t(t, id);
+ if (!s)
+ return false;
+
+ return test_bit(ancestor - id - 1, s->is_ancestor);
+}
+
bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
{
bool ret;
@@ -140,13 +149,11 @@ bool __bch2_snapshot_is_ancestor(struct bch_fs *c, u32 id, u32 ancestor)
while (id && id < ancestor - IS_ANCESTOR_BITMAP)
id = get_ancestor_below(t, id, ancestor);
- if (id && id < ancestor) {
- ret = test_bit(ancestor - id - 1, __snapshot_t(t, id)->is_ancestor);
+ ret = id && id < ancestor
+ ? test_ancestor_bitmap(t, id, ancestor)
+ : id == ancestor;
- EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
- } else {
- ret = id == ancestor;
- }
+ EBUG_ON(ret != __bch2_snapshot_is_ancestor_early(t, id, ancestor));
out:
rcu_read_unlock();
diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index e0aa3655b63b..5eee055ee272 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -143,7 +143,7 @@ void bch2_free_super(struct bch_sb_handle *sb)
{
kfree(sb->bio);
if (!IS_ERR_OR_NULL(sb->s_bdev_file))
- fput(sb->s_bdev_file);
+ bdev_fput(sb->s_bdev_file);
kfree(sb->holder);
kfree(sb->sb_name);
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index ed63018f21be..8daf80a38d60 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -288,8 +288,13 @@ static void __bch2_fs_read_only(struct bch_fs *c)
if (test_bit(JOURNAL_REPLAY_DONE, &c->journal.flags) &&
!test_bit(BCH_FS_emergency_ro, &c->flags))
set_bit(BCH_FS_clean_shutdown, &c->flags);
+
bch2_fs_journal_stop(&c->journal);
+ bch_info(c, "%sshutdown complete, journal seq %llu",
+ test_bit(BCH_FS_clean_shutdown, &c->flags) ? "" : "un",
+ c->journal.seq_ondisk);
+
/*
* After stopping journal:
*/
diff --git a/fs/bcachefs/sysfs.c b/fs/bcachefs/sysfs.c
index c86a93a8d8fc..b18b0cc81b59 100644
--- a/fs/bcachefs/sysfs.c
+++ b/fs/bcachefs/sysfs.c
@@ -17,7 +17,6 @@
#include "btree_iter.h"
#include "btree_key_cache.h"
#include "btree_update.h"
-#include "btree_update_interior.h"
#include "btree_gc.h"
#include "buckets.h"
#include "clock.h"
@@ -166,7 +165,6 @@ read_attribute(btree_write_stats);
read_attribute(btree_cache_size);
read_attribute(compression_stats);
read_attribute(journal_debug);
-read_attribute(btree_updates);
read_attribute(btree_cache);
read_attribute(btree_key_cache);
read_attribute(stripes_heap);
@@ -415,9 +413,6 @@ SHOW(bch2_fs)
if (attr == &sysfs_journal_debug)
bch2_journal_debug_to_text(out, &c->journal);
- if (attr == &sysfs_btree_updates)
- bch2_btree_updates_to_text(out, c);
-
if (attr == &sysfs_btree_cache)
bch2_btree_cache_to_text(out, c);
@@ -639,7 +634,6 @@ SYSFS_OPS(bch2_fs_internal);
struct attribute *bch2_fs_internal_files[] = {
&sysfs_flags,
&sysfs_journal_debug,
- &sysfs_btree_updates,
&sysfs_btree_cache,
&sysfs_btree_key_cache,
&sysfs_new_stripes,
diff --git a/fs/bcachefs/tests.c b/fs/bcachefs/tests.c
index b3fe9fc57747..bfec656f94c0 100644
--- a/fs/bcachefs/tests.c
+++ b/fs/bcachefs/tests.c
@@ -672,7 +672,7 @@ static int __do_delete(struct btree_trans *trans, struct bpos pos)
bch2_trans_iter_init(trans, &iter, BTREE_ID_xattrs, pos,
BTREE_ITER_INTENT);
- k = bch2_btree_iter_peek(&iter);
+ k = bch2_btree_iter_peek_upto(&iter, POS(0, U64_MAX));
ret = bkey_err(k);
if (ret)
goto err;
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index b7e7c29278fc..5cf885b09986 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -788,6 +788,14 @@ static inline int copy_from_user_errcode(void *to, const void __user *from, unsi
#endif
+static inline void mod_bit(long nr, volatile unsigned long *addr, bool v)
+{
+ if (v)
+ set_bit(nr, addr);
+ else
+ clear_bit(nr, addr);
+}
+
static inline void __set_bit_le64(size_t bit, __le64 *addr)
{
addr[bit / 64] |= cpu_to_le64(BIT_ULL(bit % 64));
@@ -795,7 +803,7 @@ static inline void __set_bit_le64(size_t bit, __le64 *addr)
static inline void __clear_bit_le64(size_t bit, __le64 *addr)
{
- addr[bit / 64] &= !cpu_to_le64(BIT_ULL(bit % 64));
+ addr[bit / 64] &= ~cpu_to_le64(BIT_ULL(bit % 64));
}
static inline bool test_bit_le64(size_t bit, __le64 *addr)
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index dd6f566a383f..121ab890bd05 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1133,6 +1133,9 @@ __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
if (ret)
return ret;
+ ret = btrfs_record_root_in_trans(trans, node->root);
+ if (ret)
+ return ret;
ret = btrfs_update_delayed_inode(trans, node->root, path, node);
return ret;
}
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 37701531eeb1..c65fe5de4022 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2533,7 +2533,7 @@ void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
*/
if (bits & EXTENT_CLEAR_META_RESV &&
root != fs_info->tree_root)
- btrfs_delalloc_release_metadata(inode, len, false);
+ btrfs_delalloc_release_metadata(inode, len, true);
/* For sanity tests. */
if (btrfs_is_testing(fs_info))
@@ -4503,6 +4503,7 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
struct btrfs_trans_handle *trans;
struct btrfs_block_rsv block_rsv;
u64 root_flags;
+ u64 qgroup_reserved = 0;
int ret;
down_write(&fs_info->subvol_sem);
@@ -4547,12 +4548,20 @@ int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
if (ret)
goto out_undead;
+ qgroup_reserved = block_rsv.qgroup_rsv_reserved;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
goto out_release;
}
+ ret = btrfs_record_root_in_trans(trans, root);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_end_trans;
+ }
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
@@ -4611,7 +4620,9 @@ out_end_trans:
ret = btrfs_end_transaction(trans);
inode->i_flags |= S_DEAD;
out_release:
- btrfs_subvolume_release_metadata(root, &block_rsv);
+ btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
out_undead:
if (ret) {
spin_lock(&dest->root_item_lock);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 294e31edec9d..55f3ba6a831c 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -613,6 +613,7 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
int ret;
dev_t anon_dev;
u64 objectid;
+ u64 qgroup_reserved = 0;
root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
if (!root_item)
@@ -650,13 +651,18 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
trans_num_items, false);
if (ret)
goto out_new_inode_args;
+ qgroup_reserved = block_rsv.qgroup_rsv_reserved;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
- btrfs_subvolume_release_metadata(root, &block_rsv);
- goto out_new_inode_args;
+ goto out_release_rsv;
}
+ ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+ if (ret)
+ goto out;
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
/* Tree log can't currently deal with an inode which is a new root. */
@@ -767,9 +773,11 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
out:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
- btrfs_subvolume_release_metadata(root, &block_rsv);
-
btrfs_end_transaction(trans);
+out_release_rsv:
+ btrfs_block_rsv_release(fs_info, &block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
out_new_inode_args:
btrfs_new_inode_args_destroy(&new_inode_args);
out_inode:
@@ -791,6 +799,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
struct btrfs_pending_snapshot *pending_snapshot;
unsigned int trans_num_items;
struct btrfs_trans_handle *trans;
+ struct btrfs_block_rsv *block_rsv;
+ u64 qgroup_reserved = 0;
int ret;
/* We do not support snapshotting right now. */
@@ -827,19 +837,19 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
goto free_pending;
}
- btrfs_init_block_rsv(&pending_snapshot->block_rsv,
- BTRFS_BLOCK_RSV_TEMP);
+ block_rsv = &pending_snapshot->block_rsv;
+ btrfs_init_block_rsv(block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
* 1 to add dir item
* 1 to add dir index
* 1 to update parent inode item
*/
trans_num_items = create_subvol_num_items(inherit) + 3;
- ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
- &pending_snapshot->block_rsv,
+ ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, block_rsv,
trans_num_items, false);
if (ret)
goto free_pending;
+ qgroup_reserved = block_rsv->qgroup_rsv_reserved;
pending_snapshot->dentry = dentry;
pending_snapshot->root = root;
@@ -852,6 +862,13 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
ret = PTR_ERR(trans);
goto fail;
}
+ ret = btrfs_record_root_in_trans(trans, BTRFS_I(dir)->root);
+ if (ret) {
+ btrfs_end_transaction(trans);
+ goto fail;
+ }
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
+ qgroup_reserved = 0;
trans->pending_snapshot = pending_snapshot;
@@ -881,7 +898,9 @@ fail:
if (ret && pending_snapshot->snap)
pending_snapshot->snap->anon_dev = 0;
btrfs_put_root(pending_snapshot->snap);
- btrfs_subvolume_release_metadata(root, &pending_snapshot->block_rsv);
+ btrfs_block_rsv_release(fs_info, block_rsv, (u64)-1, NULL);
+ if (qgroup_reserved)
+ btrfs_qgroup_free_meta_prealloc(root, qgroup_reserved);
free_pending:
if (pending_snapshot->anon_dev)
free_anon_bdev(pending_snapshot->anon_dev);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5f90f0605b12..cf8820ce7aa2 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -4495,6 +4495,8 @@ void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
BTRFS_QGROUP_RSV_META_PREALLOC);
trace_qgroup_meta_convert(root, num_bytes);
qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
+ if (!sb_rdonly(fs_info->sb))
+ add_root_meta_rsv(root, num_bytes, BTRFS_QGROUP_RSV_META_PERTRANS);
}
/*
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 4bb538a372ce..7007f9e0c972 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -548,13 +548,3 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
}
return ret;
}
-
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
- struct btrfs_block_rsv *rsv)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- u64 qgroup_to_release;
-
- btrfs_block_rsv_release(fs_info, rsv, (u64)-1, &qgroup_to_release);
- btrfs_qgroup_convert_reserved_meta(root, qgroup_to_release);
-}
diff --git a/fs/btrfs/root-tree.h b/fs/btrfs/root-tree.h
index 6f929cf3bd49..8f5739e732b9 100644
--- a/fs/btrfs/root-tree.h
+++ b/fs/btrfs/root-tree.h
@@ -18,8 +18,6 @@ struct btrfs_trans_handle;
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems, bool use_global_rsv);
-void btrfs_subvolume_release_metadata(struct btrfs_root *root,
- struct btrfs_block_rsv *rsv);
int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
u64 ref_id, u64 dirid, u64 sequence,
const struct fscrypt_str *name);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 46e8426adf4f..85f359e0e0a7 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -745,14 +745,6 @@ again:
h->reloc_reserved = reloc_reserved;
}
- /*
- * Now that we have found a transaction to be a part of, convert the
- * qgroup reservation from prealloc to pertrans. A different transaction
- * can't race in and free our pertrans out from under us.
- */
- if (qgroup_reserved)
- btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
-
got_it:
if (!current->journal_info)
current->journal_info = h;
@@ -786,8 +778,15 @@ got_it:
* not just freed.
*/
btrfs_end_transaction(h);
- return ERR_PTR(ret);
+ goto reserve_fail;
}
+ /*
+ * Now that we have found a transaction to be a part of, convert the
+ * qgroup reservation from prealloc to pertrans. A different transaction
+ * can't race in and free our pertrans out from under us.
+ */
+ if (qgroup_reserved)
+ btrfs_qgroup_convert_reserved_meta(root, qgroup_reserved);
return h;
@@ -1495,6 +1494,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
radix_tree_tag_clear(&fs_info->fs_roots_radix,
(unsigned long)root->root_key.objectid,
BTRFS_ROOT_TRANS_TAG);
+ btrfs_qgroup_free_meta_all_pertrans(root);
spin_unlock(&fs_info->fs_roots_radix_lock);
btrfs_free_log(trans, root);
@@ -1519,7 +1519,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
if (ret2)
return ret2;
spin_lock(&fs_info->fs_roots_radix_lock);
- btrfs_qgroup_free_meta_all_pertrans(root);
}
}
spin_unlock(&fs_info->fs_roots_radix_lock);
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 39e75131fd5a..9901057a15ba 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -495,7 +495,7 @@ static void cramfs_kill_sb(struct super_block *sb)
sb->s_mtd = NULL;
} else if (IS_ENABLED(CONFIG_CRAMFS_BLOCKDEV) && sb->s_bdev) {
sync_blockdev(sb->s_bdev);
- fput(sb->s_bdev_file);
+ bdev_fput(sb->s_bdev_file);
}
kfree(sbi);
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index cfb8449c731f..044135796f2b 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5668,7 +5668,7 @@ failed_mount:
brelse(sbi->s_sbh);
if (sbi->s_journal_bdev_file) {
invalidate_bdev(file_bdev(sbi->s_journal_bdev_file));
- fput(sbi->s_journal_bdev_file);
+ bdev_fput(sbi->s_journal_bdev_file);
}
out_fail:
invalidate_bdev(sb->s_bdev);
@@ -5913,7 +5913,7 @@ static struct file *ext4_get_journal_blkdev(struct super_block *sb,
out_bh:
brelse(bh);
out_bdev:
- fput(bdev_file);
+ bdev_fput(bdev_file);
return ERR_PTR(errno);
}
@@ -5952,7 +5952,7 @@ static journal_t *ext4_open_dev_journal(struct super_block *sb,
out_journal:
jbd2_journal_destroy(journal);
out_bdev:
- fput(bdev_file);
+ bdev_fput(bdev_file);
return ERR_PTR(errno);
}
@@ -7327,7 +7327,7 @@ static void ext4_kill_sb(struct super_block *sb)
kill_block_super(sb);
if (bdev_file)
- fput(bdev_file);
+ bdev_fput(bdev_file);
}
static struct file_system_type ext4_fs_type = {
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index a6867f26f141..a4bc26dfdb1a 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -1558,7 +1558,7 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
for (i = 0; i < sbi->s_ndevs; i++) {
if (i > 0)
- fput(FDEV(i).bdev_file);
+ bdev_fput(FDEV(i).bdev_file);
#ifdef CONFIG_BLK_DEV_ZONED
kvfree(FDEV(i).blkz_seq);
#endif
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 73389c68e251..9609349e92e5 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1141,7 +1141,7 @@ journal_found:
lbmLogShutdown(log);
close: /* close external log device */
- fput(bdev_file);
+ bdev_fput(bdev_file);
free: /* free log descriptor */
mutex_unlock(&jfs_log_mutex);
@@ -1485,7 +1485,7 @@ int lmLogClose(struct super_block *sb)
bdev_file = log->bdev_file;
rc = lmLogShutdown(log);
- fput(bdev_file);
+ bdev_fput(bdev_file);
kfree(log);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2391ab3c3231..84d4093ca713 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3042,12 +3042,9 @@ static void
nfsd4_cb_recall_any_release(struct nfsd4_callback *cb)
{
struct nfs4_client *clp = cb->cb_clp;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- spin_lock(&nn->client_lock);
clear_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
- put_client_renew_locked(clp);
- spin_unlock(&nn->client_lock);
+ drop_client(clp);
}
static int
@@ -6616,7 +6613,7 @@ deleg_reaper(struct nfsd_net *nn)
list_add(&clp->cl_ra_cblist, &cblist);
/* release in nfsd4_cb_recall_any_release */
- atomic_inc(&clp->cl_rpc_users);
+ kref_get(&clp->cl_nfsdfs.cl_ref);
set_bit(NFSD4_CLIENT_CB_RECALL_ANY, &clp->cl_flags);
clp->cl_ra_time = ktime_get_boottime_seconds();
}
diff --git a/fs/proc/bootconfig.c b/fs/proc/bootconfig.c
index 902b326e1e56..87dcaae32ff8 100644
--- a/fs/proc/bootconfig.c
+++ b/fs/proc/bootconfig.c
@@ -62,12 +62,12 @@ static int __init copy_xbc_key_value_list(char *dst, size_t size)
break;
dst += ret;
}
- if (ret >= 0 && boot_command_line[0]) {
- ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
- boot_command_line);
- if (ret > 0)
- dst += ret;
- }
+ }
+ if (cmdline_has_extra_options() && ret >= 0 && boot_command_line[0]) {
+ ret = snprintf(dst, rest(dst, end), "# Parameters from bootloader:\n# %s\n",
+ boot_command_line);
+ if (ret > 0)
+ dst += ret;
}
out:
kfree(key);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 6474529c4253..e539ccd39e1e 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2589,7 +2589,7 @@ static void journal_list_init(struct super_block *sb)
static void release_journal_dev(struct reiserfs_journal *journal)
{
if (journal->j_bdev_file) {
- fput(journal->j_bdev_file);
+ bdev_fput(journal->j_bdev_file);
journal->j_bdev_file = NULL;
}
}
diff --git a/fs/romfs/super.c b/fs/romfs/super.c
index 2be227532f39..2cbb92462074 100644
--- a/fs/romfs/super.c
+++ b/fs/romfs/super.c
@@ -594,7 +594,7 @@ static void romfs_kill_sb(struct super_block *sb)
#ifdef CONFIG_ROMFS_ON_BLOCK
if (sb->s_bdev) {
sync_blockdev(sb->s_bdev);
- fput(sb->s_bdev_file);
+ bdev_fput(sb->s_bdev_file);
}
#endif
}
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index a0017724d523..13a9d7acf8f8 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -417,6 +417,7 @@ smb2_close_cached_fid(struct kref *ref)
{
struct cached_fid *cfid = container_of(ref, struct cached_fid,
refcount);
+ int rc;
spin_lock(&cfid->cfids->cfid_list_lock);
if (cfid->on_list) {
@@ -430,9 +431,10 @@ smb2_close_cached_fid(struct kref *ref)
cfid->dentry = NULL;
if (cfid->is_open) {
- SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
+ rc = SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid,
cfid->fid.volatile_fid);
- atomic_dec(&cfid->tcon->num_remote_opens);
+ if (rc != -EBUSY && rc != -EAGAIN)
+ atomic_dec(&cfid->tcon->num_remote_opens);
}
free_cached_dir(cfid);
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index 226d4835c92d..c71ae5c04306 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -250,6 +250,8 @@ static int cifs_debug_files_proc_show(struct seq_file *m, void *v)
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
list_for_each_entry(cfile, &tcon->openFileList, tlist) {
@@ -676,6 +678,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
}
#endif /* CONFIG_CIFS_STATS2 */
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
atomic_set(&tcon->num_smbs_sent, 0);
spin_lock(&tcon->stat_lock);
@@ -755,6 +759,8 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
}
#endif /* STATS2 */
list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
i++;
seq_printf(m, "\n%d) %s", i, tcon->tree_name);
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index aa6f1ecb7c0e..d41eedbff674 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -156,6 +156,7 @@ struct workqueue_struct *decrypt_wq;
struct workqueue_struct *fileinfo_put_wq;
struct workqueue_struct *cifsoplockd_wq;
struct workqueue_struct *deferredclose_wq;
+struct workqueue_struct *serverclose_wq;
__u32 cifs_lock_secret;
/*
@@ -1888,6 +1889,13 @@ init_cifs(void)
goto out_destroy_cifsoplockd_wq;
}
+ serverclose_wq = alloc_workqueue("serverclose",
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+ if (!serverclose_wq) {
+ rc = -ENOMEM;
+ goto out_destroy_serverclose_wq;
+ }
+
rc = cifs_init_inodecache();
if (rc)
goto out_destroy_deferredclose_wq;
@@ -1962,6 +1970,8 @@ out_destroy_decrypt_wq:
destroy_workqueue(decrypt_wq);
out_destroy_cifsiod_wq:
destroy_workqueue(cifsiod_wq);
+out_destroy_serverclose_wq:
+ destroy_workqueue(serverclose_wq);
out_clean_proc:
cifs_proc_clean();
return rc;
@@ -1991,6 +2001,7 @@ exit_cifs(void)
destroy_workqueue(cifsoplockd_wq);
destroy_workqueue(decrypt_wq);
destroy_workqueue(fileinfo_put_wq);
+ destroy_workqueue(serverclose_wq);
destroy_workqueue(cifsiod_wq);
cifs_proc_clean();
}
diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
index 7ed9d05f6890..f6a302205f89 100644
--- a/fs/smb/client/cifsglob.h
+++ b/fs/smb/client/cifsglob.h
@@ -442,10 +442,10 @@ struct smb_version_operations {
/* set fid protocol-specific info */
void (*set_fid)(struct cifsFileInfo *, struct cifs_fid *, __u32);
/* close a file */
- void (*close)(const unsigned int, struct cifs_tcon *,
+ int (*close)(const unsigned int, struct cifs_tcon *,
struct cifs_fid *);
/* close a file, returning file attributes and timestamps */
- void (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon,
+ int (*close_getattr)(const unsigned int xid, struct cifs_tcon *tcon,
struct cifsFileInfo *pfile_info);
/* send a flush request to the server */
int (*flush)(const unsigned int, struct cifs_tcon *, struct cifs_fid *);
@@ -1281,7 +1281,6 @@ struct cifs_tcon {
struct cached_fids *cfids;
/* BB add field for back pointer to sb struct(s)? */
#ifdef CONFIG_CIFS_DFS_UPCALL
- struct list_head dfs_ses_list;
struct delayed_work dfs_cache_work;
#endif
struct delayed_work query_interfaces; /* query interfaces workqueue job */
@@ -1440,6 +1439,7 @@ struct cifsFileInfo {
bool swapfile:1;
bool oplock_break_cancelled:1;
bool status_file_deleted:1; /* file has been deleted */
+ bool offload:1; /* offload final part of _put to a wq */
unsigned int oplock_epoch; /* epoch from the lease break */
__u32 oplock_level; /* oplock/lease level from the lease break */
int count;
@@ -1448,6 +1448,7 @@ struct cifsFileInfo {
struct cifs_search_info srch_inf;
struct work_struct oplock_break; /* work for oplock breaks */
struct work_struct put; /* work for the final part of _put */
+ struct work_struct serverclose; /* work for serverclose */
struct delayed_work deferred;
bool deferred_close_scheduled; /* Flag to indicate close is scheduled */
char *symlink_target;
@@ -1804,7 +1805,6 @@ struct cifs_mount_ctx {
struct TCP_Server_Info *server;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
- struct list_head dfs_ses_list;
};
static inline void __free_dfs_info_param(struct dfs_info3_param *param)
@@ -2105,6 +2105,7 @@ extern struct workqueue_struct *decrypt_wq;
extern struct workqueue_struct *fileinfo_put_wq;
extern struct workqueue_struct *cifsoplockd_wq;
extern struct workqueue_struct *deferredclose_wq;
+extern struct workqueue_struct *serverclose_wq;
extern __u32 cifs_lock_secret;
extern mempool_t *cifs_sm_req_poolp;
@@ -2324,4 +2325,14 @@ struct smb2_compound_vars {
struct kvec ea_iov;
};
+static inline bool cifs_ses_exiting(struct cifs_ses *ses)
+{
+ bool ret;
+
+ spin_lock(&ses->ses_lock);
+ ret = ses->ses_status == SES_EXITING;
+ spin_unlock(&ses->ses_lock);
+ return ret;
+}
+
#endif /* _CIFS_GLOB_H */
diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h
index 0723e1b57256..8e0a348f1f66 100644
--- a/fs/smb/client/cifsproto.h
+++ b/fs/smb/client/cifsproto.h
@@ -725,31 +725,31 @@ struct super_block *cifs_get_tcon_super(struct cifs_tcon *tcon);
void cifs_put_tcon_super(struct super_block *sb);
int cifs_wait_for_server_reconnect(struct TCP_Server_Info *server, bool retry);
-/* Put references of @ses and @ses->dfs_root_ses */
+/* Put references of @ses and its children */
static inline void cifs_put_smb_ses(struct cifs_ses *ses)
{
- struct cifs_ses *rses = ses->dfs_root_ses;
+ struct cifs_ses *next;
- __cifs_put_smb_ses(ses);
- if (rses)
- __cifs_put_smb_ses(rses);
+ do {
+ next = ses->dfs_root_ses;
+ __cifs_put_smb_ses(ses);
+ } while ((ses = next));
}
-/* Get an active reference of @ses and @ses->dfs_root_ses.
+/* Get an active reference of @ses and its children.
*
* NOTE: make sure to call this function when incrementing reference count of
* @ses to ensure that any DFS root session attached to it (@ses->dfs_root_ses)
* will also get its reference count incremented.
*
- * cifs_put_smb_ses() will put both references, so call it when you're done.
+ * cifs_put_smb_ses() will put all references, so call it when you're done.
*/
static inline void cifs_smb_ses_inc_refcount(struct cifs_ses *ses)
{
lockdep_assert_held(&cifs_tcp_ses_lock);
- ses->ses_count++;
- if (ses->dfs_root_ses)
- ses->dfs_root_ses->ses_count++;
+ for (; ses; ses = ses->dfs_root_ses)
+ ses->ses_count++;
}
static inline bool dfs_src_pathname_equal(const char *s1, const char *s2)
diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 5aee55551573..23b5709ddc31 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -5854,10 +5854,8 @@ SetEARetry:
parm_data->list.EA_flags = 0;
/* we checked above that name len is less than 255 */
parm_data->list.name_len = (__u8)name_len;
- /* EA names are always ASCII */
- if (ea_name)
- strncpy(parm_data->list.name, ea_name, name_len);
- parm_data->list.name[name_len] = '\0';
+ /* EA names are always ASCII and NUL-terminated */
+ strscpy(parm_data->list.name, ea_name ?: "", name_len + 1);
parm_data->list.value_len = cpu_to_le16(ea_value_len);
/* caller ensures that ea_value_len is less than 64K but
we need to ensure that it fits within the smb */
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 9b85b5341822..85679ae106fd 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -175,6 +175,8 @@ cifs_signal_cifsd_for_reconnect(struct TCP_Server_Info *server,
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
spin_lock(&ses->chan_lock);
for (i = 0; i < ses->chan_count; i++) {
if (!ses->chans[i].server)
@@ -232,7 +234,13 @@ cifs_mark_tcp_ses_conns_for_reconnect(struct TCP_Server_Info *server,
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(ses, nses, &pserver->smb_ses_list, smb_ses_list) {
- /* check if iface is still active */
+ spin_lock(&ses->ses_lock);
+ if (ses->ses_status == SES_EXITING) {
+ spin_unlock(&ses->ses_lock);
+ continue;
+ }
+ spin_unlock(&ses->ses_lock);
+
spin_lock(&ses->chan_lock);
if (cifs_ses_get_chan_index(ses, server) ==
CIFS_INVAL_CHAN_INDEX) {
@@ -1860,6 +1868,9 @@ static int match_session(struct cifs_ses *ses, struct smb3_fs_context *ctx)
ctx->sectype != ses->sectype)
return 0;
+ if (ctx->dfs_root_ses != ses->dfs_root_ses)
+ return 0;
+
/*
* If an existing session is limited to less channels than
* requested, it should not be reused
@@ -1963,31 +1974,6 @@ out:
return rc;
}
-/**
- * cifs_free_ipc - helper to release the session IPC tcon
- * @ses: smb session to unmount the IPC from
- *
- * Needs to be called everytime a session is destroyed.
- *
- * On session close, the IPC is closed and the server must release all tcons of the session.
- * No need to send a tree disconnect here.
- *
- * Besides, it will make the server to not close durable and resilient files on session close, as
- * specified in MS-SMB2 3.3.5.6 Receiving an SMB2 LOGOFF Request.
- */
-static int
-cifs_free_ipc(struct cifs_ses *ses)
-{
- struct cifs_tcon *tcon = ses->tcon_ipc;
-
- if (tcon == NULL)
- return 0;
-
- tconInfoFree(tcon);
- ses->tcon_ipc = NULL;
- return 0;
-}
-
static struct cifs_ses *
cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
{
@@ -2019,48 +2005,52 @@ cifs_find_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
void __cifs_put_smb_ses(struct cifs_ses *ses)
{
struct TCP_Server_Info *server = ses->server;
+ struct cifs_tcon *tcon;
unsigned int xid;
size_t i;
+ bool do_logoff;
int rc;
+ spin_lock(&cifs_tcp_ses_lock);
spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_EXITING) {
+ cifs_dbg(FYI, "%s: id=0x%llx ses_count=%d ses_status=%u ipc=%s\n",
+ __func__, ses->Suid, ses->ses_count, ses->ses_status,
+ ses->tcon_ipc ? ses->tcon_ipc->tree_name : "none");
+ if (ses->ses_status == SES_EXITING || --ses->ses_count > 0) {
spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
return;
}
- spin_unlock(&ses->ses_lock);
+ /* ses_count can never go negative */
+ WARN_ON(ses->ses_count < 0);
- cifs_dbg(FYI, "%s: ses_count=%d\n", __func__, ses->ses_count);
- cifs_dbg(FYI,
- "%s: ses ipc: %s\n", __func__, ses->tcon_ipc ? ses->tcon_ipc->tree_name : "NONE");
+ spin_lock(&ses->chan_lock);
+ cifs_chan_clear_need_reconnect(ses, server);
+ spin_unlock(&ses->chan_lock);
- spin_lock(&cifs_tcp_ses_lock);
- if (--ses->ses_count > 0) {
- spin_unlock(&cifs_tcp_ses_lock);
- return;
- }
- spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_GOOD)
- ses->ses_status = SES_EXITING;
+ do_logoff = ses->ses_status == SES_GOOD && server->ops->logoff;
+ ses->ses_status = SES_EXITING;
+ tcon = ses->tcon_ipc;
+ ses->tcon_ipc = NULL;
spin_unlock(&ses->ses_lock);
spin_unlock(&cifs_tcp_ses_lock);
- /* ses_count can never go negative */
- WARN_ON(ses->ses_count < 0);
-
- spin_lock(&ses->ses_lock);
- if (ses->ses_status == SES_EXITING && server->ops->logoff) {
- spin_unlock(&ses->ses_lock);
- cifs_free_ipc(ses);
+ /*
+ * On session close, the IPC is closed and the server must release all
+ * tcons of the session. No need to send a tree disconnect here.
+ *
+ * Besides, it will make the server to not close durable and resilient
+ * files on session close, as specified in MS-SMB2 3.3.5.6 Receiving an
+ * SMB2 LOGOFF Request.
+ */
+ tconInfoFree(tcon);
+ if (do_logoff) {
xid = get_xid();
rc = server->ops->logoff(xid, ses);
if (rc)
cifs_server_dbg(VFS, "%s: Session Logoff failure rc=%d\n",
__func__, rc);
_free_xid(xid);
- } else {
- spin_unlock(&ses->ses_lock);
- cifs_free_ipc(ses);
}
spin_lock(&cifs_tcp_ses_lock);
@@ -2373,9 +2363,9 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx)
* need to lock before changing something in the session.
*/
spin_lock(&cifs_tcp_ses_lock);
+ if (ctx->dfs_root_ses)
+ cifs_smb_ses_inc_refcount(ctx->dfs_root_ses);
ses->dfs_root_ses = ctx->dfs_root_ses;
- if (ses->dfs_root_ses)
- ses->dfs_root_ses->ses_count++;
list_add(&ses->smb_ses_list, &server->smb_ses_list);
spin_unlock(&cifs_tcp_ses_lock);
@@ -3326,6 +3316,9 @@ void cifs_mount_put_conns(struct cifs_mount_ctx *mnt_ctx)
cifs_put_smb_ses(mnt_ctx->ses);
else if (mnt_ctx->server)
cifs_put_tcp_session(mnt_ctx->server, 0);
+ mnt_ctx->ses = NULL;
+ mnt_ctx->tcon = NULL;
+ mnt_ctx->server = NULL;
mnt_ctx->cifs_sb->mnt_cifs_flags &= ~CIFS_MOUNT_POSIX_PATHS;
free_xid(mnt_ctx->xid);
}
@@ -3604,8 +3597,6 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
bool isdfs;
int rc;
- INIT_LIST_HEAD(&mnt_ctx.dfs_ses_list);
-
rc = dfs_mount_share(&mnt_ctx, &isdfs);
if (rc)
goto error;
@@ -3636,7 +3627,6 @@ out:
return rc;
error:
- dfs_put_root_smb_sessions(&mnt_ctx.dfs_ses_list);
cifs_mount_put_conns(&mnt_ctx);
return rc;
}
@@ -3651,6 +3641,18 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
goto error;
rc = cifs_mount_get_tcon(&mnt_ctx);
+ if (!rc) {
+ /*
+ * Prevent superblock from being created with any missing
+ * connections.
+ */
+ if (WARN_ON(!mnt_ctx.server))
+ rc = -EHOSTDOWN;
+ else if (WARN_ON(!mnt_ctx.ses))
+ rc = -EACCES;
+ else if (WARN_ON(!mnt_ctx.tcon))
+ rc = -ENOENT;
+ }
if (rc)
goto error;
@@ -3988,13 +3990,14 @@ cifs_set_vol_auth(struct smb3_fs_context *ctx, struct cifs_ses *ses)
}
static struct cifs_tcon *
-cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
+__cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
{
int rc;
struct cifs_tcon *master_tcon = cifs_sb_master_tcon(cifs_sb);
struct cifs_ses *ses;
struct cifs_tcon *tcon = NULL;
struct smb3_fs_context *ctx;
+ char *origin_fullpath = NULL;
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (ctx == NULL)
@@ -4018,6 +4021,7 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
ctx->sign = master_tcon->ses->sign;
ctx->seal = master_tcon->seal;
ctx->witness = master_tcon->use_witness;
+ ctx->dfs_root_ses = master_tcon->ses->dfs_root_ses;
rc = cifs_set_vol_auth(ctx, master_tcon->ses);
if (rc) {
@@ -4037,12 +4041,39 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
goto out;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ spin_lock(&master_tcon->tc_lock);
+ if (master_tcon->origin_fullpath) {
+ spin_unlock(&master_tcon->tc_lock);
+ origin_fullpath = dfs_get_path(cifs_sb, cifs_sb->ctx->source);
+ if (IS_ERR(origin_fullpath)) {
+ tcon = ERR_CAST(origin_fullpath);
+ origin_fullpath = NULL;
+ cifs_put_smb_ses(ses);
+ goto out;
+ }
+ } else {
+ spin_unlock(&master_tcon->tc_lock);
+ }
+#endif
+
tcon = cifs_get_tcon(ses, ctx);
if (IS_ERR(tcon)) {
cifs_put_smb_ses(ses);
goto out;
}
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (origin_fullpath) {
+ spin_lock(&tcon->tc_lock);
+ tcon->origin_fullpath = origin_fullpath;
+ spin_unlock(&tcon->tc_lock);
+ origin_fullpath = NULL;
+ queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
+ dfs_cache_get_ttl() * HZ);
+ }
+#endif
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (cap_unix(ses))
reset_cifs_unix_caps(0, tcon, NULL, ctx);
@@ -4051,11 +4082,23 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
out:
kfree(ctx->username);
kfree_sensitive(ctx->password);
+ kfree(origin_fullpath);
kfree(ctx);
return tcon;
}
+static struct cifs_tcon *
+cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
+{
+ struct cifs_tcon *ret;
+
+ cifs_mount_lock();
+ ret = __cifs_construct_tcon(cifs_sb, fsuid);
+ cifs_mount_unlock();
+ return ret;
+}
+
struct cifs_tcon *
cifs_sb_master_tcon(struct cifs_sb_info *cifs_sb)
{
diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c
index 449c59830039..3ec965547e3d 100644
--- a/fs/smb/client/dfs.c
+++ b/fs/smb/client/dfs.c
@@ -66,33 +66,20 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path)
}
/*
- * Track individual DFS referral servers used by new DFS mount.
- *
- * On success, their lifetime will be shared by final tcon (dfs_ses_list).
- * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount().
+ * Get an active reference of @ses so that next call to cifs_put_tcon() won't
+ * release it as any new DFS referrals must go through its IPC tcon.
*/
-static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx)
+static void add_root_smb_session(struct cifs_mount_ctx *mnt_ctx)
{
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
- struct dfs_root_ses *root_ses;
struct cifs_ses *ses = mnt_ctx->ses;
if (ses) {
- root_ses = kmalloc(sizeof(*root_ses), GFP_KERNEL);
- if (!root_ses)
- return -ENOMEM;
-
- INIT_LIST_HEAD(&root_ses->list);
-
spin_lock(&cifs_tcp_ses_lock);
cifs_smb_ses_inc_refcount(ses);
spin_unlock(&cifs_tcp_ses_lock);
- root_ses->ses = ses;
- list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list);
}
- /* Select new DFS referral server so that new referrals go through it */
ctx->dfs_root_ses = ses;
- return 0;
}
static inline int parse_dfs_target(struct smb3_fs_context *ctx,
@@ -185,11 +172,8 @@ again:
continue;
}
- if (is_refsrv) {
- rc = add_root_smb_session(mnt_ctx);
- if (rc)
- goto out;
- }
+ if (is_refsrv)
+ add_root_smb_session(mnt_ctx);
rc = ref_walk_advance(rw);
if (!rc) {
@@ -232,6 +216,7 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
struct cifs_tcon *tcon;
char *origin_fullpath;
+ bool new_tcon = true;
int rc;
origin_fullpath = dfs_get_path(cifs_sb, ctx->source);
@@ -239,6 +224,18 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
return PTR_ERR(origin_fullpath);
rc = dfs_referral_walk(mnt_ctx);
+ if (!rc) {
+ /*
+ * Prevent superblock from being created with any missing
+ * connections.
+ */
+ if (WARN_ON(!mnt_ctx->server))
+ rc = -EHOSTDOWN;
+ else if (WARN_ON(!mnt_ctx->ses))
+ rc = -EACCES;
+ else if (WARN_ON(!mnt_ctx->tcon))
+ rc = -ENOENT;
+ }
if (rc)
goto out;
@@ -247,15 +244,14 @@ static int __dfs_mount_share(struct cifs_mount_ctx *mnt_ctx)
if (!tcon->origin_fullpath) {
tcon->origin_fullpath = origin_fullpath;
origin_fullpath = NULL;
+ } else {
+ new_tcon = false;
}
spin_unlock(&tcon->tc_lock);
- if (list_empty(&tcon->dfs_ses_list)) {
- list_replace_init(&mnt_ctx->dfs_ses_list, &tcon->dfs_ses_list);
+ if (new_tcon) {
queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
dfs_cache_get_ttl() * HZ);
- } else {
- dfs_put_root_smb_sessions(&mnt_ctx->dfs_ses_list);
}
out:
@@ -298,7 +294,6 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs)
if (rc)
return rc;
- ctx->dfs_root_ses = mnt_ctx->ses;
/*
* If called with 'nodfs' mount option, then skip DFS resolving. Otherwise unconditionally
* try to get an DFS referral (even cached) to determine whether it is an DFS mount.
@@ -324,7 +319,9 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs)
*isdfs = true;
add_root_smb_session(mnt_ctx);
- return __dfs_mount_share(mnt_ctx);
+ rc = __dfs_mount_share(mnt_ctx);
+ dfs_put_root_smb_sessions(mnt_ctx);
+ return rc;
}
/* Update dfs referral path of superblock */
diff --git a/fs/smb/client/dfs.h b/fs/smb/client/dfs.h
index 875ab7ae57fc..e5c4dcf83750 100644
--- a/fs/smb/client/dfs.h
+++ b/fs/smb/client/dfs.h
@@ -7,7 +7,9 @@
#define _CIFS_DFS_H
#include "cifsglob.h"
+#include "cifsproto.h"
#include "fs_context.h"
+#include "dfs_cache.h"
#include "cifs_unicode.h"
#include <linux/namei.h>
@@ -114,11 +116,6 @@ static inline void ref_walk_set_tgt_hint(struct dfs_ref_walk *rw)
ref_walk_tit(rw));
}
-struct dfs_root_ses {
- struct list_head list;
- struct cifs_ses *ses;
-};
-
int dfs_parse_target_referral(const char *full_path, const struct dfs_info3_param *ref,
struct smb3_fs_context *ctx);
int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs);
@@ -133,20 +130,32 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p
{
struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
struct cifs_sb_info *cifs_sb = mnt_ctx->cifs_sb;
+ struct cifs_ses *rses = ctx->dfs_root_ses ?: mnt_ctx->ses;
- return dfs_cache_find(mnt_ctx->xid, ctx->dfs_root_ses, cifs_sb->local_nls,
+ return dfs_cache_find(mnt_ctx->xid, rses, cifs_sb->local_nls,
cifs_remap(cifs_sb), path, ref, tl);
}
-static inline void dfs_put_root_smb_sessions(struct list_head *head)
+/*
+ * cifs_get_smb_ses() already guarantees an active reference of
+ * @ses->dfs_root_ses when a new session is created, so we need to put extra
+ * references of all DFS root sessions that were used across the mount process
+ * in dfs_mount_share().
+ */
+static inline void dfs_put_root_smb_sessions(struct cifs_mount_ctx *mnt_ctx)
{
- struct dfs_root_ses *root, *tmp;
+ const struct smb3_fs_context *ctx = mnt_ctx->fs_ctx;
+ struct cifs_ses *ses = ctx->dfs_root_ses;
+ struct cifs_ses *cur;
+
+ if (!ses)
+ return;
- list_for_each_entry_safe(root, tmp, head, list) {
- list_del_init(&root->list);
- cifs_put_smb_ses(root->ses);
- kfree(root);
+ for (cur = ses; cur; cur = cur->dfs_root_ses) {
+ if (cur->dfs_root_ses)
+ cifs_put_smb_ses(cur->dfs_root_ses);
}
+ cifs_put_smb_ses(ses);
}
#endif /* _CIFS_DFS_H */
diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c
index 508d831fabe3..11c8efecf7aa 100644
--- a/fs/smb/client/dfs_cache.c
+++ b/fs/smb/client/dfs_cache.c
@@ -1172,8 +1172,8 @@ static bool is_ses_good(struct cifs_ses *ses)
return ret;
}
-/* Refresh dfs referral of tcon and mark it for reconnect if needed */
-static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_refresh)
+/* Refresh dfs referral of @ses and mark it for reconnect if needed */
+static void __refresh_ses_referral(struct cifs_ses *ses, bool force_refresh)
{
struct TCP_Server_Info *server = ses->server;
DFS_CACHE_TGT_LIST(old_tl);
@@ -1181,10 +1181,21 @@ static int __refresh_tcon(const char *path, struct cifs_ses *ses, bool force_ref
bool needs_refresh = false;
struct cache_entry *ce;
unsigned int xid;
+ char *path = NULL;
int rc = 0;
xid = get_xid();
+ mutex_lock(&server->refpath_lock);
+ if (server->leaf_fullpath) {
+ path = kstrdup(server->leaf_fullpath + 1, GFP_ATOMIC);
+ if (!path)
+ rc = -ENOMEM;
+ }
+ mutex_unlock(&server->refpath_lock);
+ if (!path)
+ goto out;
+
down_read(&htable_rw_lock);
ce = lookup_cache_entry(path);
needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
@@ -1218,19 +1229,17 @@ out:
free_xid(xid);
dfs_cache_free_tgts(&old_tl);
dfs_cache_free_tgts(&new_tl);
- return rc;
+ kfree(path);
}
-static int refresh_tcon(struct cifs_tcon *tcon, bool force_refresh)
+static inline void refresh_ses_referral(struct cifs_ses *ses)
{
- struct TCP_Server_Info *server = tcon->ses->server;
- struct cifs_ses *ses = tcon->ses;
+ __refresh_ses_referral(ses, false);
+}
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, force_refresh);
- mutex_unlock(&server->refpath_lock);
- return 0;
+static inline void force_refresh_ses_referral(struct cifs_ses *ses)
+{
+ __refresh_ses_referral(ses, true);
}
/**
@@ -1271,34 +1280,20 @@ int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
*/
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
- return refresh_tcon(tcon, true);
+ force_refresh_ses_referral(tcon->ses);
+ return 0;
}
/* Refresh all DFS referrals related to DFS tcon */
void dfs_cache_refresh(struct work_struct *work)
{
- struct TCP_Server_Info *server;
- struct dfs_root_ses *rses;
struct cifs_tcon *tcon;
struct cifs_ses *ses;
tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work);
- ses = tcon->ses;
- server = ses->server;
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, false);
- mutex_unlock(&server->refpath_lock);
-
- list_for_each_entry(rses, &tcon->dfs_ses_list, list) {
- ses = rses->ses;
- server = ses->server;
- mutex_lock(&server->refpath_lock);
- if (server->leaf_fullpath)
- __refresh_tcon(server->leaf_fullpath + 1, ses, false);
- mutex_unlock(&server->refpath_lock);
- }
+ for (ses = tcon->ses; ses; ses = ses->dfs_root_ses)
+ refresh_ses_referral(ses);
queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work,
atomic_read(&dfs_cache_ttl) * HZ);
diff --git a/fs/smb/client/dir.c b/fs/smb/client/dir.c
index d11dc3aa458b..864b194dbaa0 100644
--- a/fs/smb/client/dir.c
+++ b/fs/smb/client/dir.c
@@ -189,6 +189,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
int disposition;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
*oplock = 0;
if (tcon->ses->server->oplocks)
@@ -200,6 +201,10 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
return PTR_ERR(full_path);
}
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (oflags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
if (tcon->unix_ext && cap_unix(tcon->ses) && !tcon->broken_posix_open &&
(CIFS_UNIX_POSIX_PATH_OPS_CAP &
@@ -276,6 +281,8 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
desired_access |= GENERIC_READ; /* is this too little? */
if (OPEN_FMODE(oflags) & FMODE_WRITE)
desired_access |= GENERIC_WRITE;
+ if (rdwr_for_fscache == 1)
+ desired_access |= GENERIC_READ;
disposition = FILE_OVERWRITE_IF;
if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
@@ -304,6 +311,7 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
if (!tcon->unix_ext && (mode & S_IWUGO) == 0)
create_options |= CREATE_OPTION_READONLY;
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -317,8 +325,15 @@ static int cifs_do_create(struct inode *inode, struct dentry *direntry, unsigned
rc = server->ops->open(xid, &oparms, oplock, buf);
if (rc) {
cifs_dbg(FYI, "cifs_create returned 0x%x\n", rc);
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access &= ~GENERIC_READ;
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
goto out;
}
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
/*
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index 16aadce492b2..9be37d0fe724 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -206,12 +206,12 @@ cifs_mark_open_files_invalid(struct cifs_tcon *tcon)
*/
}
-static inline int cifs_convert_flags(unsigned int flags)
+static inline int cifs_convert_flags(unsigned int flags, int rdwr_for_fscache)
{
if ((flags & O_ACCMODE) == O_RDONLY)
return GENERIC_READ;
else if ((flags & O_ACCMODE) == O_WRONLY)
- return GENERIC_WRITE;
+ return rdwr_for_fscache == 1 ? (GENERIC_READ | GENERIC_WRITE) : GENERIC_WRITE;
else if ((flags & O_ACCMODE) == O_RDWR) {
/* GENERIC_ALL is too much permission to request
can cause unnecessary access denied on create */
@@ -348,11 +348,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
int create_options = CREATE_NOT_DIR;
struct TCP_Server_Info *server = tcon->ses->server;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
if (!server->ops->open)
return -ENOSYS;
- desired_access = cifs_convert_flags(f_flags);
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (f_flags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
+ desired_access = cifs_convert_flags(f_flags, rdwr_for_fscache);
/*********************************************************************
* open flag mapping table:
@@ -389,6 +394,7 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
if (f_flags & O_DIRECT)
create_options |= CREATE_NO_BUFFER;
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -400,8 +406,16 @@ static int cifs_nt_open(const char *full_path, struct inode *inode, struct cifs_
};
rc = server->ops->open(xid, &oparms, oplock, buf);
- if (rc)
+ if (rc) {
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access = cifs_convert_flags(f_flags, 0);
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
return rc;
+ }
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
/* TODO: Add support for calling posix query info but with passing in fid */
if (tcon->unix_ext)
@@ -445,6 +459,7 @@ cifs_down_write(struct rw_semaphore *sem)
}
static void cifsFileInfo_put_work(struct work_struct *work);
+void serverclose_work(struct work_struct *work);
struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
struct tcon_link *tlink, __u32 oplock,
@@ -491,6 +506,7 @@ struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
cfile->tlink = cifs_get_tlink(tlink);
INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
INIT_WORK(&cfile->put, cifsFileInfo_put_work);
+ INIT_WORK(&cfile->serverclose, serverclose_work);
INIT_DELAYED_WORK(&cfile->deferred, smb2_deferred_work_close);
mutex_init(&cfile->fh_mutex);
spin_lock_init(&cfile->file_info_lock);
@@ -582,6 +598,40 @@ static void cifsFileInfo_put_work(struct work_struct *work)
cifsFileInfo_put_final(cifs_file);
}
+void serverclose_work(struct work_struct *work)
+{
+ struct cifsFileInfo *cifs_file = container_of(work,
+ struct cifsFileInfo, serverclose);
+
+ struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
+
+ struct TCP_Server_Info *server = tcon->ses->server;
+ int rc = 0;
+ int retries = 0;
+ int MAX_RETRIES = 4;
+
+ do {
+ if (server->ops->close_getattr)
+ rc = server->ops->close_getattr(0, tcon, cifs_file);
+ else if (server->ops->close)
+ rc = server->ops->close(0, tcon, &cifs_file->fid);
+
+ if (rc == -EBUSY || rc == -EAGAIN) {
+ retries++;
+ msleep(250);
+ }
+ } while ((rc == -EBUSY || rc == -EAGAIN) && (retries < MAX_RETRIES)
+ );
+
+ if (retries == MAX_RETRIES)
+ pr_warn("Serverclose failed %d times, giving up\n", MAX_RETRIES);
+
+ if (cifs_file->offload)
+ queue_work(fileinfo_put_wq, &cifs_file->put);
+ else
+ cifsFileInfo_put_final(cifs_file);
+}
+
/**
* cifsFileInfo_put - release a reference of file priv data
*
@@ -622,10 +672,13 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
struct cifs_fid fid = {};
struct cifs_pending_open open;
bool oplock_break_cancelled;
+ bool serverclose_offloaded = false;
spin_lock(&tcon->open_file_lock);
spin_lock(&cifsi->open_file_lock);
spin_lock(&cifs_file->file_info_lock);
+
+ cifs_file->offload = offload;
if (--cifs_file->count > 0) {
spin_unlock(&cifs_file->file_info_lock);
spin_unlock(&cifsi->open_file_lock);
@@ -667,13 +720,20 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
struct TCP_Server_Info *server = tcon->ses->server;
unsigned int xid;
+ int rc = 0;
xid = get_xid();
if (server->ops->close_getattr)
- server->ops->close_getattr(xid, tcon, cifs_file);
+ rc = server->ops->close_getattr(xid, tcon, cifs_file);
else if (server->ops->close)
- server->ops->close(xid, tcon, &cifs_file->fid);
+ rc = server->ops->close(xid, tcon, &cifs_file->fid);
_free_xid(xid);
+
+ if (rc == -EBUSY || rc == -EAGAIN) {
+ // Server close failed, hence offloading it as an async op
+ queue_work(serverclose_wq, &cifs_file->serverclose);
+ serverclose_offloaded = true;
+ }
}
if (oplock_break_cancelled)
@@ -681,10 +741,15 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file,
cifs_del_pending_open(&open);
- if (offload)
- queue_work(fileinfo_put_wq, &cifs_file->put);
- else
- cifsFileInfo_put_final(cifs_file);
+ // if serverclose has been offloaded to wq (on failure), it will
+ // handle offloading put as well. If serverclose not offloaded,
+ // we need to handle offloading put here.
+ if (!serverclose_offloaded) {
+ if (offload)
+ queue_work(fileinfo_put_wq, &cifs_file->put);
+ else
+ cifsFileInfo_put_final(cifs_file);
+ }
}
int cifs_open(struct inode *inode, struct file *file)
@@ -834,11 +899,11 @@ int cifs_open(struct inode *inode, struct file *file)
use_cache:
fscache_use_cookie(cifs_inode_cookie(file_inode(file)),
file->f_mode & FMODE_WRITE);
- if (file->f_flags & O_DIRECT &&
- (!((file->f_flags & O_ACCMODE) != O_RDONLY) ||
- file->f_flags & O_APPEND))
- cifs_invalidate_cache(file_inode(file),
- FSCACHE_INVAL_DIO_WRITE);
+ if (!(file->f_flags & O_DIRECT))
+ goto out;
+ if ((file->f_flags & (O_ACCMODE | O_APPEND)) == O_RDONLY)
+ goto out;
+ cifs_invalidate_cache(file_inode(file), FSCACHE_INVAL_DIO_WRITE);
out:
free_dentry_path(page);
@@ -903,6 +968,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
int disposition = FILE_OPEN;
int create_options = CREATE_NOT_DIR;
struct cifs_open_parms oparms;
+ int rdwr_for_fscache = 0;
xid = get_xid();
mutex_lock(&cfile->fh_mutex);
@@ -966,7 +1032,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
}
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
- desired_access = cifs_convert_flags(cfile->f_flags);
+ /* If we're caching, we need to be able to fill in around partial writes. */
+ if (cifs_fscache_enabled(inode) && (cfile->f_flags & O_ACCMODE) == O_WRONLY)
+ rdwr_for_fscache = 1;
+
+ desired_access = cifs_convert_flags(cfile->f_flags, rdwr_for_fscache);
/* O_SYNC also has bit for O_DSYNC so following check picks up either */
if (cfile->f_flags & O_SYNC)
@@ -978,6 +1048,7 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
if (server->ops->get_lease_key)
server->ops->get_lease_key(inode, &cfile->fid);
+retry_open:
oparms = (struct cifs_open_parms) {
.tcon = tcon,
.cifs_sb = cifs_sb,
@@ -1003,6 +1074,11 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
/* indicate that we need to relock the file */
oparms.reconnect = true;
}
+ if (rc == -EACCES && rdwr_for_fscache == 1) {
+ desired_access = cifs_convert_flags(cfile->f_flags, 0);
+ rdwr_for_fscache = 2;
+ goto retry_open;
+ }
if (rc) {
mutex_unlock(&cfile->fh_mutex);
@@ -1011,6 +1087,9 @@ cifs_reopen_file(struct cifsFileInfo *cfile, bool can_flush)
goto reopen_error_exit;
}
+ if (rdwr_for_fscache == 2)
+ cifs_invalidate_cache(inode, FSCACHE_INVAL_DIO_WRITE);
+
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
reopen_success:
#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index bdcbe6ff2739..b7bfe705b2c4 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -37,7 +37,7 @@
#include "rfc1002pdu.h"
#include "fs_context.h"
-static DEFINE_MUTEX(cifs_mount_mutex);
+DEFINE_MUTEX(cifs_mount_mutex);
static const match_table_t cifs_smb_version_tokens = {
{ Smb_1, SMB1_VERSION_STRING },
@@ -783,9 +783,9 @@ static int smb3_get_tree(struct fs_context *fc)
if (err)
return err;
- mutex_lock(&cifs_mount_mutex);
+ cifs_mount_lock();
ret = smb3_get_tree_common(fc);
- mutex_unlock(&cifs_mount_mutex);
+ cifs_mount_unlock();
return ret;
}
diff --git a/fs/smb/client/fs_context.h b/fs/smb/client/fs_context.h
index 7863f2248c4d..8a35645e0b65 100644
--- a/fs/smb/client/fs_context.h
+++ b/fs/smb/client/fs_context.h
@@ -304,4 +304,16 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb);
#define MAX_CACHED_FIDS 16
extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp);
+extern struct mutex cifs_mount_mutex;
+
+static inline void cifs_mount_lock(void)
+{
+ mutex_lock(&cifs_mount_mutex);
+}
+
+static inline void cifs_mount_unlock(void)
+{
+ mutex_unlock(&cifs_mount_mutex);
+}
+
#endif
diff --git a/fs/smb/client/fscache.h b/fs/smb/client/fscache.h
index a3d73720914f..1f2ea9f5cc9a 100644
--- a/fs/smb/client/fscache.h
+++ b/fs/smb/client/fscache.h
@@ -109,6 +109,11 @@ static inline void cifs_readahead_to_fscache(struct inode *inode,
__cifs_readahead_to_fscache(inode, pos, len);
}
+static inline bool cifs_fscache_enabled(struct inode *inode)
+{
+ return fscache_cookie_enabled(cifs_inode_cookie(inode));
+}
+
#else /* CONFIG_CIFS_FSCACHE */
static inline
void cifs_fscache_fill_coherency(struct inode *inode,
@@ -124,6 +129,7 @@ static inline void cifs_fscache_release_inode_cookie(struct inode *inode) {}
static inline void cifs_fscache_unuse_inode_cookie(struct inode *inode, bool update) {}
static inline struct fscache_cookie *cifs_inode_cookie(struct inode *inode) { return NULL; }
static inline void cifs_invalidate_cache(struct inode *inode, unsigned int flags) {}
+static inline bool cifs_fscache_enabled(struct inode *inode) { return false; }
static inline int cifs_fscache_query_occupancy(struct inode *inode,
pgoff_t first, unsigned int nr_pages,
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index c012dfdba80d..855ac5a62edf 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -247,7 +247,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) {
list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) {
- if (ses_it->Suid == out.session_id) {
+ spin_lock(&ses_it->ses_lock);
+ if (ses_it->ses_status != SES_EXITING &&
+ ses_it->Suid == out.session_id) {
ses = ses_it;
/*
* since we are using the session outside the crit
@@ -255,9 +257,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug
* so increment its refcount
*/
cifs_smb_ses_inc_refcount(ses);
+ spin_unlock(&ses_it->ses_lock);
found = true;
goto search_end;
}
+ spin_unlock(&ses_it->ses_lock);
}
}
search_end:
diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
index c3771fc81328..33ac4f8f5050 100644
--- a/fs/smb/client/misc.c
+++ b/fs/smb/client/misc.c
@@ -138,9 +138,6 @@ tcon_info_alloc(bool dir_leases_enabled)
atomic_set(&ret_buf->num_local_opens, 0);
atomic_set(&ret_buf->num_remote_opens, 0);
ret_buf->stats_from_time = ktime_get_real_seconds();
-#ifdef CONFIG_CIFS_DFS_UPCALL
- INIT_LIST_HEAD(&ret_buf->dfs_ses_list);
-#endif
return ret_buf;
}
@@ -156,9 +153,6 @@ tconInfoFree(struct cifs_tcon *tcon)
atomic_dec(&tconInfoAllocCount);
kfree(tcon->nativeFileSystem);
kfree_sensitive(tcon->password);
-#ifdef CONFIG_CIFS_DFS_UPCALL
- dfs_put_root_smb_sessions(&tcon->dfs_ses_list);
-#endif
kfree(tcon->origin_fullpath);
kfree(tcon);
}
@@ -487,6 +481,8 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid != buf->Tid)
continue;
diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
index a9eaba8083b0..212ec6f66ec6 100644
--- a/fs/smb/client/smb1ops.c
+++ b/fs/smb/client/smb1ops.c
@@ -753,11 +753,11 @@ cifs_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
cinode->can_cache_brlcks = CIFS_CACHE_WRITE(cinode);
}
-static void
+static int
cifs_close_file(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid *fid)
{
- CIFSSMBClose(xid, tcon, fid->netfid);
+ return CIFSSMBClose(xid, tcon, fid->netfid);
}
static int
diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c
index 82b84a4941dd..cc72be5a93a9 100644
--- a/fs/smb/client/smb2misc.c
+++ b/fs/smb/client/smb2misc.c
@@ -622,6 +622,8 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
cifs_stats_inc(
@@ -697,6 +699,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 2ed456948f34..b156eefa75d7 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -1412,14 +1412,14 @@ smb2_set_fid(struct cifsFileInfo *cfile, struct cifs_fid *fid, __u32 oplock)
memcpy(cfile->fid.create_guid, fid->create_guid, 16);
}
-static void
+static int
smb2_close_file(const unsigned int xid, struct cifs_tcon *tcon,
struct cifs_fid *fid)
{
- SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
+ return SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
}
-static void
+static int
smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
struct cifsFileInfo *cfile)
{
@@ -1430,7 +1430,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
rc = __SMB2_close(xid, tcon, cfile->fid.persistent_fid,
cfile->fid.volatile_fid, &file_inf);
if (rc)
- return;
+ return rc;
inode = d_inode(cfile->dentry);
@@ -1459,6 +1459,7 @@ smb2_close_getattr(const unsigned int xid, struct cifs_tcon *tcon,
/* End of file and Attributes should not have to be updated on close */
spin_unlock(&inode->i_lock);
+ return rc;
}
static int
@@ -2480,6 +2481,8 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server)
spin_lock(&cifs_tcp_ses_lock);
list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (cifs_ses_exiting(ses))
+ continue;
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) {
spin_lock(&tcon->tc_lock);
@@ -3913,7 +3916,7 @@ smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock,
strcat(message, "W");
}
if (!new_oplock)
- strncpy(message, "None", sizeof(message));
+ strscpy(message, "None");
cinode->oplock = new_oplock;
cifs_dbg(FYI, "%s Lease granted on inode %p\n", message,
diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
index 3ea688558e6c..c0c4933af5fc 100644
--- a/fs/smb/client/smb2pdu.c
+++ b/fs/smb/client/smb2pdu.c
@@ -3628,9 +3628,9 @@ replay_again:
memcpy(&pbuf->network_open_info,
&rsp->network_open_info,
sizeof(pbuf->network_open_info));
+ atomic_dec(&tcon->num_remote_opens);
}
- atomic_dec(&tcon->num_remote_opens);
close_exit:
SMB2_close_free(&rqst);
free_rsp_buf(resp_buftype, rsp);
diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c
index 5a3ca62d2f07..1d6e54f7879e 100644
--- a/fs/smb/client/smb2transport.c
+++ b/fs/smb/client/smb2transport.c
@@ -659,7 +659,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server)
}
spin_unlock(&server->srv_lock);
if (!is_binding && !server->session_estab) {
- strncpy(shdr->Signature, "BSRSPYL", 8);
+ strscpy(shdr->Signature, "BSRSPYL");
return 0;
}
diff --git a/fs/smb/server/ksmbd_netlink.h b/fs/smb/server/ksmbd_netlink.h
index 8ca8a45c4c62..686b321c5a8b 100644
--- a/fs/smb/server/ksmbd_netlink.h
+++ b/fs/smb/server/ksmbd_netlink.h
@@ -167,7 +167,8 @@ struct ksmbd_share_config_response {
__u16 force_uid;
__u16 force_gid;
__s8 share_name[KSMBD_REQ_MAX_SHARE_NAME];
- __u32 reserved[112]; /* Reserved room */
+ __u32 reserved[111]; /* Reserved room */
+ __u32 payload_sz;
__u32 veto_list_sz;
__s8 ____payload[];
};
diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
index 328a412259dc..a2f0a2edceb8 100644
--- a/fs/smb/server/mgmt/share_config.c
+++ b/fs/smb/server/mgmt/share_config.c
@@ -158,7 +158,12 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
share->name = kstrdup(name, GFP_KERNEL);
if (!test_share_config_flag(share, KSMBD_SHARE_FLAG_PIPE)) {
- share->path = kstrdup(ksmbd_share_config_path(resp),
+ int path_len = PATH_MAX;
+
+ if (resp->payload_sz)
+ path_len = resp->payload_sz - resp->veto_list_sz;
+
+ share->path = kstrndup(ksmbd_share_config_path(resp), path_len,
GFP_KERNEL);
if (share->path)
share->path_sz = strlen(share->path);
diff --git a/fs/smb/server/smb2ops.c b/fs/smb/server/smb2ops.c
index a45f7dca482e..606aa3c5189a 100644
--- a/fs/smb/server/smb2ops.c
+++ b/fs/smb/server/smb2ops.c
@@ -228,6 +228,11 @@ void init_smb3_0_server(struct ksmbd_conn *conn)
conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
+ if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
+ (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
+ conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION))
+ conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
+
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL;
}
@@ -278,11 +283,6 @@ int init_smb3_11_server(struct ksmbd_conn *conn)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_LEASING |
SMB2_GLOBAL_CAP_DIRECTORY_LEASING;
- if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION ||
- (!(server_conf.flags & KSMBD_GLOBAL_FLAG_SMB2_ENCRYPTION_OFF) &&
- conn->cli_cap & SMB2_GLOBAL_CAP_ENCRYPTION))
- conn->vals->capabilities |= SMB2_GLOBAL_CAP_ENCRYPTION;
-
if (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL)
conn->vals->capabilities |= SMB2_GLOBAL_CAP_MULTI_CHANNEL;
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index d478fa0c57ab..5723bbf372d7 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -5857,8 +5857,9 @@ static int smb2_rename(struct ksmbd_work *work,
if (!file_info->ReplaceIfExists)
flags = RENAME_NOREPLACE;
- smb_break_all_levII_oplock(work, fp, 0);
rc = ksmbd_vfs_rename(work, &fp->filp->f_path, new_name, flags);
+ if (!rc)
+ smb_break_all_levII_oplock(work, fp, 0);
out:
kfree(new_name);
return rc;
diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index f29bb03f0dc4..8752ac82c557 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -65,6 +65,7 @@ struct ipc_msg_table_entry {
struct hlist_node ipc_table_hlist;
void *response;
+ unsigned int msg_sz;
};
static struct delayed_work ipc_timer_work;
@@ -275,6 +276,7 @@ static int handle_response(int type, void *payload, size_t sz)
}
memcpy(entry->response, payload, sz);
+ entry->msg_sz = sz;
wake_up_interruptible(&entry->wait);
ret = 0;
break;
@@ -453,6 +455,34 @@ out:
return ret;
}
+static int ipc_validate_msg(struct ipc_msg_table_entry *entry)
+{
+ unsigned int msg_sz = entry->msg_sz;
+
+ if (entry->type == KSMBD_EVENT_RPC_REQUEST) {
+ struct ksmbd_rpc_command *resp = entry->response;
+
+ msg_sz = sizeof(struct ksmbd_rpc_command) + resp->payload_sz;
+ } else if (entry->type == KSMBD_EVENT_SPNEGO_AUTHEN_REQUEST) {
+ struct ksmbd_spnego_authen_response *resp = entry->response;
+
+ msg_sz = sizeof(struct ksmbd_spnego_authen_response) +
+ resp->session_key_len + resp->spnego_blob_len;
+ } else if (entry->type == KSMBD_EVENT_SHARE_CONFIG_REQUEST) {
+ struct ksmbd_share_config_response *resp = entry->response;
+
+ if (resp->payload_sz) {
+ if (resp->payload_sz < resp->veto_list_sz)
+ return -EINVAL;
+
+ msg_sz = sizeof(struct ksmbd_share_config_response) +
+ resp->payload_sz;
+ }
+ }
+
+ return entry->msg_sz != msg_sz ? -EINVAL : 0;
+}
+
static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle)
{
struct ipc_msg_table_entry entry;
@@ -477,6 +507,13 @@ static void *ipc_msg_send_request(struct ksmbd_ipc_msg *msg, unsigned int handle
ret = wait_event_interruptible_timeout(entry.wait,
entry.response != NULL,
IPC_WAIT_TIMEOUT);
+ if (entry.response) {
+ ret = ipc_validate_msg(&entry);
+ if (ret) {
+ kvfree(entry.response);
+ entry.response = NULL;
+ }
+ }
out:
down_write(&ipc_msg_table_lock);
hash_del(&entry.ipc_table_hlist);
diff --git a/fs/super.c b/fs/super.c
index 71d9779c42b1..69ce6c600968 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1515,29 +1515,11 @@ static int fs_bdev_thaw(struct block_device *bdev)
return error;
}
-static void fs_bdev_super_get(void *data)
-{
- struct super_block *sb = data;
-
- spin_lock(&sb_lock);
- sb->s_count++;
- spin_unlock(&sb_lock);
-}
-
-static void fs_bdev_super_put(void *data)
-{
- struct super_block *sb = data;
-
- put_super(sb);
-}
-
const struct blk_holder_ops fs_holder_ops = {
.mark_dead = fs_bdev_mark_dead,
.sync = fs_bdev_sync,
.freeze = fs_bdev_freeze,
.thaw = fs_bdev_thaw,
- .get_holder = fs_bdev_super_get,
- .put_holder = fs_bdev_super_put,
};
EXPORT_SYMBOL_GPL(fs_holder_ops);
@@ -1562,7 +1544,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
* writable from userspace even for a read-only block device.
*/
if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) {
- fput(bdev_file);
+ bdev_fput(bdev_file);
return -EACCES;
}
@@ -1573,7 +1555,7 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
if (atomic_read(&bdev->bd_fsfreeze_count) > 0) {
if (fc)
warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev);
- fput(bdev_file);
+ bdev_fput(bdev_file);
return -EBUSY;
}
spin_lock(&sb_lock);
@@ -1693,7 +1675,7 @@ void kill_block_super(struct super_block *sb)
generic_shutdown_super(sb);
if (bdev) {
sync_blockdev(bdev);
- fput(sb->s_bdev_file);
+ bdev_fput(sb->s_bdev_file);
}
}
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 1a18c381127e..f0fa02264eda 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2030,7 +2030,7 @@ xfs_free_buftarg(
fs_put_dax(btp->bt_daxdev, btp->bt_mount);
/* the main block device is closed by kill_block_super */
if (btp->bt_bdev != btp->bt_mount->m_super->s_bdev)
- fput(btp->bt_bdev_file);
+ bdev_fput(btp->bt_bdev_file);
kfree(btp);
}
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ea48774f6b76..d55b42b2480d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1301,8 +1301,19 @@ xfs_link(
*/
if (unlikely((tdp->i_diflags & XFS_DIFLAG_PROJINHERIT) &&
tdp->i_projid != sip->i_projid)) {
- error = -EXDEV;
- goto error_return;
+ /*
+ * Project quota setup skips special files which can
+ * leave inodes in a PROJINHERIT directory without a
+ * project ID set. We need to allow links to be made
+ * to these "project-less" inodes because userspace
+ * expects them to succeed after project ID setup,
+ * but everything else should be rejected.
+ */
+ if (!special_file(VFS_I(sip)->i_mode) ||
+ sip->i_projid != 0) {
+ error = -EXDEV;
+ goto error_return;
+ }
}
if (!resblks) {
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index c21f10ab0f5d..bce020374c5e 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -485,7 +485,7 @@ xfs_open_devices(
mp->m_logdev_targp = mp->m_ddev_targp;
/* Handle won't be used, drop it */
if (logdev_file)
- fput(logdev_file);
+ bdev_fput(logdev_file);
}
return 0;
@@ -497,10 +497,10 @@ xfs_open_devices(
xfs_free_buftarg(mp->m_ddev_targp);
out_close_rtdev:
if (rtdev_file)
- fput(rtdev_file);
+ bdev_fput(rtdev_file);
out_close_logdev:
if (logdev_file)
- fput(logdev_file);
+ bdev_fput(logdev_file);
return error;
}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c3e8f7cf96be..172c91879999 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1505,16 +1505,6 @@ struct blk_holder_ops {
* Thaw the file system mounted on the block device.
*/
int (*thaw)(struct block_device *bdev);
-
- /*
- * If needed, get a reference to the holder.
- */
- void (*get_holder)(void *holder);
-
- /*
- * Release the holder.
- */
- void (*put_holder)(void *holder);
};
/*
@@ -1585,6 +1575,7 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
int bdev_freeze(struct block_device *bdev);
int bdev_thaw(struct block_device *bdev);
+void bdev_fput(struct file *bdev_file);
struct io_comp_batch {
struct request *req_list;
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index ca73940e26df..e5ee2c694401 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -10,6 +10,7 @@
#ifdef __KERNEL__
#include <linux/kernel.h>
#include <linux/types.h>
+bool __init cmdline_has_extra_options(void);
#else /* !__KERNEL__ */
/*
* NOTE: This is only for tools/bootconfig, because tools/bootconfig will
diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h
index cb0d6cd1c12f..60693a145894 100644
--- a/include/linux/cc_platform.h
+++ b/include/linux/cc_platform.h
@@ -90,6 +90,14 @@ enum cc_attr {
* Examples include TDX Guest.
*/
CC_ATTR_HOTPLUG_DISABLED,
+
+ /**
+ * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host.
+ *
+ * The host kernel is running with the necessary features
+ * enabled to run SEV-SNP guests.
+ */
+ CC_ATTR_HOST_SEV_SNP,
};
#ifdef CONFIG_ARCH_HAS_CC_PLATFORM
@@ -107,10 +115,14 @@ enum cc_attr {
* * FALSE - Specified Confidential Computing attribute is not active
*/
bool cc_platform_has(enum cc_attr attr);
+void cc_platform_set(enum cc_attr attr);
+void cc_platform_clear(enum cc_attr attr);
#else /* !CONFIG_ARCH_HAS_CC_PLATFORM */
static inline bool cc_platform_has(enum cc_attr attr) { return false; }
+static inline void cc_platform_set(enum cc_attr attr) { }
+static inline void cc_platform_clear(enum cc_attr attr) { }
#endif /* CONFIG_ARCH_HAS_CC_PLATFORM */
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index c00cc6c0878a..8c252e073bd8 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -268,7 +268,7 @@ static inline void *offset_to_ptr(const int *off)
* - When one operand is a null pointer constant (i.e. when x is an integer
* constant expression) and the other is an object pointer (i.e. our
* third operand), the conditional operator returns the type of the
- * object pointer operand (i.e. "int *). Here, within the sizeof(), we
+ * object pointer operand (i.e. "int *"). Here, within the sizeof(), we
* would then get:
* sizeof(*((int *)(...)) == sizeof(int) == 4
* - When one operand is a void pointer (i.e. when x is not an integer
diff --git a/include/linux/device.h b/include/linux/device.h
index 97c4b046c09d..b9f5464f44ed 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1247,6 +1247,7 @@ void device_link_del(struct device_link *link);
void device_link_remove(void *consumer, struct device *supplier);
void device_links_supplier_sync_state_pause(void);
void device_links_supplier_sync_state_resume(void);
+void device_link_wait_removal(void);
/* Create alias, so I can be autoloaded. */
#define MODULE_ALIAS_CHARDEV(major,minor) \
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 770755df852f..70cd7258cd29 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -245,7 +245,6 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
* max utilization to the allowed CPU capacity before calculating
* effective performance.
*/
- max_util = map_util_perf(max_util);
max_util = min(max_util, allowed_cpu_cap);
/*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 00fc429b0af0..8dfd53b52744 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -121,6 +121,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
#define FMODE_PWRITE ((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC ((__force fmode_t)0x20)
+/* File writes are restricted (block device specific) */
+#define FMODE_WRITE_RESTRICTED ((__force fmode_t)0x40)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 868c8fb1bbc1..13becafe41df 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -2,6 +2,8 @@
#ifndef __LINUX_GFP_TYPES_H
#define __LINUX_GFP_TYPES_H
+#include <linux/bits.h>
+
/* The typedef is in types.h but we want the documentation here */
#if 0
/**
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index e24893625085..05df0e399d7c 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -294,7 +294,6 @@ struct io_ring_ctx {
struct io_submit_state submit_state;
- struct io_buffer_list *io_bl;
struct xarray io_bl_xa;
struct io_hash_table cancel_table_locked;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0436b919f1c7..7b0ee64225de 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2207,11 +2207,6 @@ static inline int arch_make_folio_accessible(struct folio *folio)
*/
#include <linux/vmstat.h>
-static __always_inline void *lowmem_page_address(const struct page *page)
-{
- return page_to_virt(page);
-}
-
#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#define HASHED_PAGE_VIRTUAL
#endif
@@ -2234,6 +2229,11 @@ void set_page_address(struct page *page, void *virtual);
void page_address_init(void);
#endif
+static __always_inline void *lowmem_page_address(const struct page *page)
+{
+ return page_to_virt(page);
+}
+
#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
#define page_address(page) lowmem_page_address(page)
#define set_page_address(page, address) do { } while(0)
diff --git a/include/linux/randomize_kstack.h b/include/linux/randomize_kstack.h
index 5d868505a94e..6d92b68efbf6 100644
--- a/include/linux/randomize_kstack.h
+++ b/include/linux/randomize_kstack.h
@@ -80,7 +80,7 @@ DECLARE_PER_CPU(u32, kstack_offset);
if (static_branch_maybe(CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT, \
&randomize_kstack_offset)) { \
u32 offset = raw_cpu_read(kstack_offset); \
- offset ^= (rand); \
+ offset = ror32(offset, 5) ^ (rand); \
raw_cpu_write(kstack_offset, offset); \
} \
} while (0)
diff --git a/include/linux/secretmem.h b/include/linux/secretmem.h
index 35f3a4a8ceb1..acf7e1a3f3de 100644
--- a/include/linux/secretmem.h
+++ b/include/linux/secretmem.h
@@ -13,10 +13,10 @@ static inline bool folio_is_secretmem(struct folio *folio)
/*
* Using folio_mapping() is quite slow because of the actual call
* instruction.
- * We know that secretmem pages are not compound and LRU so we can
+ * We know that secretmem pages are not compound, so we can
* save a couple of cycles here.
*/
- if (folio_test_large(folio) || !folio_test_lru(folio))
+ if (folio_test_large(folio))
return false;
mapping = (struct address_space *)
diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h
index 307961b41541..317200cd3a60 100644
--- a/include/linux/sockptr.h
+++ b/include/linux/sockptr.h
@@ -50,11 +50,36 @@ static inline int copy_from_sockptr_offset(void *dst, sockptr_t src,
return 0;
}
+/* Deprecated.
+ * This is unsafe, unless caller checked user provided optlen.
+ * Prefer copy_safe_from_sockptr() instead.
+ */
static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size)
{
return copy_from_sockptr_offset(dst, src, 0, size);
}
+/**
+ * copy_safe_from_sockptr: copy a struct from sockptr
+ * @dst: Destination address, in kernel space. This buffer must be @ksize
+ * bytes long.
+ * @ksize: Size of @dst struct.
+ * @optval: Source address. (in user or kernel space)
+ * @optlen: Size of @optval data.
+ *
+ * Returns:
+ * * -EINVAL: @optlen < @ksize
+ * * -EFAULT: access to userspace failed.
+ * * 0 : @ksize bytes were copied
+ */
+static inline int copy_safe_from_sockptr(void *dst, size_t ksize,
+ sockptr_t optval, unsigned int optlen)
+{
+ if (optlen < ksize)
+ return -EINVAL;
+ return copy_from_sockptr(dst, optval, ksize);
+}
+
static inline int copy_struct_from_sockptr(void *dst, size_t ksize,
sockptr_t src, size_t usize)
{
diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h
index 3c6caa5abc7c..e9ec32fb97d4 100644
--- a/include/linux/stackdepot.h
+++ b/include/linux/stackdepot.h
@@ -44,10 +44,9 @@ typedef u32 depot_stack_handle_t;
union handle_parts {
depot_stack_handle_t handle;
struct {
- /* pool_index is offset by 1 */
- u32 pool_index : DEPOT_POOL_INDEX_BITS;
- u32 offset : DEPOT_OFFSET_BITS;
- u32 extra : STACK_DEPOT_EXTRA_BITS;
+ u32 pool_index_plus_1 : DEPOT_POOL_INDEX_BITS;
+ u32 offset : DEPOT_OFFSET_BITS;
+ u32 extra : STACK_DEPOT_EXTRA_BITS;
};
};
diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index c6540ceea143..0982d1d52b24 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -22,7 +22,7 @@
*
* @read: returns the current cycle value
* @mask: bitmask for two's complement
- * subtraction of non 64 bit counters,
+ * subtraction of non-64-bit counters,
* see CYCLECOUNTER_MASK() helper macro
* @mult: cycle to nanosecond multiplier
* @shift: cycle to nanosecond divisor (power of two)
@@ -35,7 +35,7 @@ struct cyclecounter {
};
/**
- * struct timecounter - layer above a %struct cyclecounter which counts nanoseconds
+ * struct timecounter - layer above a &struct cyclecounter which counts nanoseconds
* Contains the state needed by timecounter_read() to detect
* cycle counter wrap around. Initialize with
* timecounter_init(). Also used to convert cycle counts into the
@@ -66,6 +66,8 @@ struct timecounter {
* @cycles: Cycles
* @mask: bit mask for maintaining the 'frac' field
* @frac: pointer to storage for the fractional nanoseconds.
+ *
+ * Returns: cycle counter cycles converted to nanoseconds
*/
static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
u64 cycles, u64 mask, u64 *frac)
@@ -79,6 +81,7 @@ static inline u64 cyclecounter_cyc2ns(const struct cyclecounter *cc,
/**
* timecounter_adjtime - Shifts the time of the clock.
+ * @tc: The &struct timecounter to adjust
* @delta: Desired change in nanoseconds.
*/
static inline void timecounter_adjtime(struct timecounter *tc, s64 delta)
@@ -107,6 +110,8 @@ extern void timecounter_init(struct timecounter *tc,
*
* In other words, keeps track of time since the same epoch as
* the function which generated the initial time stamp.
+ *
+ * Returns: nanoseconds since the initial time stamp
*/
extern u64 timecounter_read(struct timecounter *tc);
@@ -123,6 +128,8 @@ extern u64 timecounter_read(struct timecounter *tc);
*
* This allows conversion of cycle counter values which were generated
* in the past.
+ *
+ * Returns: cycle counter converted to nanoseconds since the initial time stamp
*/
extern u64 timecounter_cyc2time(const struct timecounter *tc,
u64 cycle_tstamp);
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 7e50cbd97f86..0ea7823b7f31 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -22,14 +22,14 @@ extern int do_sys_settimeofday64(const struct timespec64 *tv,
const struct timezone *tz);
/*
- * ktime_get() family: read the current time in a multitude of ways,
+ * ktime_get() family - read the current time in a multitude of ways.
*
* The default time reference is CLOCK_MONOTONIC, starting at
* boot time but not counting the time spent in suspend.
* For other references, use the functions with "real", "clocktai",
* "boottime" and "raw" suffixes.
*
- * To get the time in a different format, use the ones wit
+ * To get the time in a different format, use the ones with
* "ns", "ts64" and "seconds" suffix.
*
* See Documentation/core-api/timekeeping.rst for more details.
@@ -74,6 +74,8 @@ extern u32 ktime_get_resolution_ns(void);
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
+ *
+ * Returns: real (wall) time in ktime_t format
*/
static inline ktime_t ktime_get_real(void)
{
@@ -86,10 +88,12 @@ static inline ktime_t ktime_get_coarse_real(void)
}
/**
- * ktime_get_boottime - Returns monotonic time since boot in ktime_t format
+ * ktime_get_boottime - Get monotonic time since boot in ktime_t format
*
* This is similar to CLOCK_MONTONIC/ktime_get, but also includes the
* time spent in suspend.
+ *
+ * Returns: monotonic time since boot in ktime_t format
*/
static inline ktime_t ktime_get_boottime(void)
{
@@ -102,7 +106,9 @@ static inline ktime_t ktime_get_coarse_boottime(void)
}
/**
- * ktime_get_clocktai - Returns the TAI time of day in ktime_t format
+ * ktime_get_clocktai - Get the TAI time of day in ktime_t format
+ *
+ * Returns: the TAI time of day in ktime_t format
*/
static inline ktime_t ktime_get_clocktai(void)
{
@@ -144,32 +150,60 @@ static inline u64 ktime_get_coarse_clocktai_ns(void)
/**
* ktime_mono_to_real - Convert monotonic time to clock realtime
+ * @mono: monotonic time to convert
+ *
+ * Returns: time converted to realtime clock
*/
static inline ktime_t ktime_mono_to_real(ktime_t mono)
{
return ktime_mono_to_any(mono, TK_OFFS_REAL);
}
+/**
+ * ktime_get_ns - Get the current time in nanoseconds
+ *
+ * Returns: current time converted to nanoseconds
+ */
static inline u64 ktime_get_ns(void)
{
return ktime_to_ns(ktime_get());
}
+/**
+ * ktime_get_real_ns - Get the current real/wall time in nanoseconds
+ *
+ * Returns: current real time converted to nanoseconds
+ */
static inline u64 ktime_get_real_ns(void)
{
return ktime_to_ns(ktime_get_real());
}
+/**
+ * ktime_get_boottime_ns - Get the monotonic time since boot in nanoseconds
+ *
+ * Returns: current boottime converted to nanoseconds
+ */
static inline u64 ktime_get_boottime_ns(void)
{
return ktime_to_ns(ktime_get_boottime());
}
+/**
+ * ktime_get_clocktai_ns - Get the current TAI time of day in nanoseconds
+ *
+ * Returns: current TAI time converted to nanoseconds
+ */
static inline u64 ktime_get_clocktai_ns(void)
{
return ktime_to_ns(ktime_get_clocktai());
}
+/**
+ * ktime_get_raw_ns - Get the raw monotonic time in nanoseconds
+ *
+ * Returns: current raw monotonic time converted to nanoseconds
+ */
static inline u64 ktime_get_raw_ns(void)
{
return ktime_to_ns(ktime_get_raw());
@@ -224,8 +258,8 @@ extern bool timekeeping_rtc_skipresume(void);
extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
-/*
- * struct ktime_timestanps - Simultaneous mono/boot/real timestamps
+/**
+ * struct ktime_timestamps - Simultaneous mono/boot/real timestamps
* @mono: Monotonic timestamp
* @boot: Boottime timestamp
* @real: Realtime timestamp
@@ -242,7 +276,8 @@ struct ktime_timestamps {
* @cycles: Clocksource counter value to produce the system times
* @real: Realtime system time
* @raw: Monotonic raw system time
- * @clock_was_set_seq: The sequence number of clock was set events
+ * @cs_id: Clocksource ID
+ * @clock_was_set_seq: The sequence number of clock-was-set events
* @cs_was_changed_seq: The sequence number of clocksource change events
*/
struct system_time_snapshot {
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 14a633ba61d6..e67ecd1cbc97 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -22,7 +22,7 @@
#define __TIMER_LOCKDEP_MAP_INITIALIZER(_kn)
#endif
-/**
+/*
* @TIMER_DEFERRABLE: A deferrable timer will work normally when the
* system is busy, but will not cause a CPU to come out of idle just
* to service it; instead, the timer will be serviced when the CPU
@@ -140,7 +140,7 @@ static inline void destroy_timer_on_stack(struct timer_list *timer) { }
* or not. Callers must ensure serialization wrt. other operations done
* to this timer, eg. interrupt contexts, or other CPUs on SMP.
*
- * return value: 1 if the timer is pending, 0 if not.
+ * Returns: 1 if the timer is pending, 0 if not.
*/
static inline int timer_pending(const struct timer_list * timer)
{
@@ -175,6 +175,10 @@ extern int timer_shutdown(struct timer_list *timer);
* See timer_delete_sync() for detailed explanation.
*
* Do not use in new code. Use timer_delete_sync() instead.
+ *
+ * Returns:
+ * * %0 - The timer was not pending
+ * * %1 - The timer was pending and deactivated
*/
static inline int del_timer_sync(struct timer_list *timer)
{
@@ -188,6 +192,10 @@ static inline int del_timer_sync(struct timer_list *timer)
* See timer_delete() for detailed explanation.
*
* Do not use in new code. Use timer_delete() instead.
+ *
+ * Returns:
+ * * %0 - The timer was not pending
+ * * %1 - The timer was pending and deactivated
*/
static inline int del_timer(struct timer_list *timer)
{
diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index ffe48e69b3f3..457879938fc1 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -135,10 +135,11 @@ static inline void u64_stats_inc(u64_stats_t *p)
p->v++;
}
-static inline void u64_stats_init(struct u64_stats_sync *syncp)
-{
- seqcount_init(&syncp->seq);
-}
+#define u64_stats_init(syncp) \
+ do { \
+ struct u64_stats_sync *__s = (syncp); \
+ seqcount_init(&__s->seq); \
+ } while (0)
static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp)
{
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 9d06eb945509..62a407db1bf5 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -438,6 +438,10 @@ static inline void in6_ifa_hold(struct inet6_ifaddr *ifp)
refcount_inc(&ifp->refcnt);
}
+static inline bool in6_ifa_hold_safe(struct inet6_ifaddr *ifp)
+{
+ return refcount_inc_not_zero(&ifp->refcnt);
+}
/*
* compute link-local solicited-node multicast address
diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 9fe95a22abeb..eaec5d6caa29 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -585,6 +585,15 @@ static inline struct sk_buff *bt_skb_sendmmsg(struct sock *sk,
return skb;
}
+static inline int bt_copy_from_sockptr(void *dst, size_t dst_size,
+ sockptr_t src, size_t src_size)
+{
+ if (dst_size > src_size)
+ return -EINVAL;
+
+ return copy_from_sockptr(dst, src, dst_size);
+}
+
int bt_to_errno(u16 code);
__u8 bt_status(int err);
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index d8f574fbb11e..9a6a08ec7713 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -459,6 +459,39 @@ static inline bool pskb_inet_may_pull(struct sk_buff *skb)
return pskb_network_may_pull(skb, nhlen);
}
+/* Variant of pskb_inet_may_pull().
+ */
+static inline bool skb_vlan_inet_prepare(struct sk_buff *skb)
+{
+ int nhlen = 0, maclen = ETH_HLEN;
+ __be16 type = skb->protocol;
+
+ /* Essentially this is skb_protocol(skb, true)
+ * And we get MAC len.
+ */
+ if (eth_type_vlan(type))
+ type = __vlan_get_protocol(skb, type, &maclen);
+
+ switch (type) {
+#if IS_ENABLED(CONFIG_IPV6)
+ case htons(ETH_P_IPV6):
+ nhlen = sizeof(struct ipv6hdr);
+ break;
+#endif
+ case htons(ETH_P_IP):
+ nhlen = sizeof(struct iphdr);
+ break;
+ }
+ /* For ETH_P_IPV6/ETH_P_IP we make sure to pull
+ * a base network header in skb->head.
+ */
+ if (!pskb_may_pull(skb, maclen + nhlen))
+ return false;
+
+ skb_set_network_header(skb, maclen);
+ return true;
+}
+
static inline int ip_encap_hlen(struct ip_tunnel_encap *e)
{
const struct ip_tunnel_encap_ops *ops;
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index a8bebac1e4b2..957295364a5e 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -56,6 +56,9 @@ struct hdac_ext_stream {
u32 pphcldpl;
u32 pphcldpu;
+ u32 pplcllpl;
+ u32 pplcllpu;
+
bool decoupled:1;
bool link_locked:1;
bool link_prepared;
diff --git a/include/sound/tas2781-tlv.h b/include/sound/tas2781-tlv.h
index 4038dd421150..1dc59005d241 100644
--- a/include/sound/tas2781-tlv.h
+++ b/include/sound/tas2781-tlv.h
@@ -15,7 +15,7 @@
#ifndef __TAS2781_TLV_H__
#define __TAS2781_TLV_H__
-static const DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0);
+static const __maybe_unused DECLARE_TLV_DB_SCALE(dvc_tlv, -10000, 100, 0);
static const DECLARE_TLV_DB_SCALE(amp_vol_tlv, 1100, 50, 0);
#endif
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 5d5c0b8efff2..c71ddb6d4691 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -19,12 +19,6 @@
#include <vdso/time32.h>
#include <vdso/time64.h>
-#ifdef CONFIG_ARM64
-#include <asm/page-def.h>
-#else
-#include <asm/page.h>
-#endif
-
#ifdef CONFIG_ARCH_HAS_VDSO_DATA
#include <asm/vdso/data.h>
#else
@@ -132,7 +126,7 @@ extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden
*/
union vdso_data_store {
struct vdso_data data[CS_BASES];
- u8 page[PAGE_SIZE];
+ u8 page[1U << CONFIG_PAGE_SHIFT];
};
/*
diff --git a/init/initramfs.c b/init/initramfs.c
index 3127e0bf7bbd..a298a3854a80 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -367,7 +367,7 @@ static int __init do_name(void)
if (S_ISREG(mode)) {
int ml = maybe_link();
if (ml >= 0) {
- int openflags = O_WRONLY|O_CREAT;
+ int openflags = O_WRONLY|O_CREAT|O_LARGEFILE;
if (ml != 1)
openflags |= O_TRUNC;
wfile = filp_open(collected, openflags, mode);
diff --git a/init/main.c b/init/main.c
index 2ca52474d0c3..881f6230ee59 100644
--- a/init/main.c
+++ b/init/main.c
@@ -487,6 +487,11 @@ static int __init warn_bootconfig(char *str)
early_param("bootconfig", warn_bootconfig);
+bool __init cmdline_has_extra_options(void)
+{
+ return extra_command_line || extra_init_args;
+}
+
/* Change NUL term back to "=", to make "param" the whole string. */
static void __init repair_env_string(char *param, char *val)
{
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 5d4b448fdc50..4521c2b66b98 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -147,6 +147,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
static void io_queue_sqe(struct io_kiocb *req);
struct kmem_cache *req_cachep;
+static struct workqueue_struct *iou_wq __ro_after_init;
static int __read_mostly sysctl_io_uring_disabled;
static int __read_mostly sysctl_io_uring_group = -1;
@@ -350,7 +351,6 @@ static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
err:
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
- kfree(ctx->io_bl);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
return NULL;
@@ -1982,10 +1982,15 @@ fail:
err = -EBADFD;
if (!io_file_can_poll(req))
goto fail;
- err = -ECANCELED;
- if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
- goto fail;
- return;
+ if (req->file->f_flags & O_NONBLOCK ||
+ req->file->f_mode & FMODE_NOWAIT) {
+ err = -ECANCELED;
+ if (io_arm_poll_handler(req, issue_flags) != IO_APOLL_OK)
+ goto fail;
+ return;
+ } else {
+ req->flags &= ~REQ_F_APOLL_MULTISHOT;
+ }
}
if (req->flags & REQ_F_FORCE_ASYNC) {
@@ -2926,7 +2931,6 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
io_napi_free(ctx);
kfree(ctx->cancel_table.hbs);
kfree(ctx->cancel_table_locked.hbs);
- kfree(ctx->io_bl);
xa_destroy(&ctx->io_bl_xa);
kfree(ctx);
}
@@ -3161,7 +3165,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
* noise and overhead, there's no discernable change in runtime
* over using system_wq.
*/
- queue_work(system_unbound_wq, &ctx->exit_work);
+ queue_work(iou_wq, &ctx->exit_work);
}
static int io_uring_release(struct inode *inode, struct file *file)
@@ -3443,14 +3447,15 @@ static void *io_uring_validate_mmap_request(struct file *file,
ptr = ctx->sq_sqes;
break;
case IORING_OFF_PBUF_RING: {
+ struct io_buffer_list *bl;
unsigned int bgid;
bgid = (offset & ~IORING_OFF_MMAP_MASK) >> IORING_OFF_PBUF_SHIFT;
- rcu_read_lock();
- ptr = io_pbuf_get_address(ctx, bgid);
- rcu_read_unlock();
- if (!ptr)
- return ERR_PTR(-EINVAL);
+ bl = io_pbuf_get_bl(ctx, bgid);
+ if (IS_ERR(bl))
+ return bl;
+ ptr = bl->buf_ring;
+ io_put_bl(ctx, bl);
break;
}
default:
@@ -4185,6 +4190,8 @@ static int __init io_uring_init(void)
io_buf_cachep = KMEM_CACHE(io_buffer,
SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT);
+ iou_wq = alloc_workqueue("iou_exit", WQ_UNBOUND, 64);
+
#ifdef CONFIG_SYSCTL
register_sysctl_init("kernel", kernel_io_uring_disabled_table);
#endif
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 693c26da4ee1..3aa16e27f509 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -17,8 +17,6 @@
#define IO_BUFFER_LIST_BUF_PER_PAGE (PAGE_SIZE / sizeof(struct io_uring_buf))
-#define BGID_ARRAY 64
-
/* BIDs are addressed by a 16-bit field in a CQE */
#define MAX_BIDS_PER_BGID (1 << 16)
@@ -40,13 +38,9 @@ struct io_buf_free {
int inuse;
};
-static struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
- struct io_buffer_list *bl,
- unsigned int bgid)
+static inline struct io_buffer_list *__io_buffer_get_list(struct io_ring_ctx *ctx,
+ unsigned int bgid)
{
- if (bl && bgid < BGID_ARRAY)
- return &bl[bgid];
-
return xa_load(&ctx->io_bl_xa, bgid);
}
@@ -55,7 +49,7 @@ static inline struct io_buffer_list *io_buffer_get_list(struct io_ring_ctx *ctx,
{
lockdep_assert_held(&ctx->uring_lock);
- return __io_buffer_get_list(ctx, ctx->io_bl, bgid);
+ return __io_buffer_get_list(ctx, bgid);
}
static int io_buffer_add_list(struct io_ring_ctx *ctx,
@@ -67,11 +61,7 @@ static int io_buffer_add_list(struct io_ring_ctx *ctx,
* always under the ->uring_lock, but the RCU lookup from mmap does.
*/
bl->bgid = bgid;
- smp_store_release(&bl->is_ready, 1);
-
- if (bgid < BGID_ARRAY)
- return 0;
-
+ atomic_set(&bl->refs, 1);
return xa_err(xa_store(&ctx->io_bl_xa, bgid, bl, GFP_KERNEL));
}
@@ -208,24 +198,6 @@ void __user *io_buffer_select(struct io_kiocb *req, size_t *len,
return ret;
}
-static __cold int io_init_bl_list(struct io_ring_ctx *ctx)
-{
- struct io_buffer_list *bl;
- int i;
-
- bl = kcalloc(BGID_ARRAY, sizeof(struct io_buffer_list), GFP_KERNEL);
- if (!bl)
- return -ENOMEM;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- INIT_LIST_HEAD(&bl[i].buf_list);
- bl[i].bgid = i;
- }
-
- smp_store_release(&ctx->io_bl, bl);
- return 0;
-}
-
/*
* Mark the given mapped range as free for reuse
*/
@@ -294,24 +266,24 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
return i;
}
+void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl)
+{
+ if (atomic_dec_and_test(&bl->refs)) {
+ __io_remove_buffers(ctx, bl, -1U);
+ kfree_rcu(bl, rcu);
+ }
+}
+
void io_destroy_buffers(struct io_ring_ctx *ctx)
{
struct io_buffer_list *bl;
struct list_head *item, *tmp;
struct io_buffer *buf;
unsigned long index;
- int i;
-
- for (i = 0; i < BGID_ARRAY; i++) {
- if (!ctx->io_bl)
- break;
- __io_remove_buffers(ctx, &ctx->io_bl[i], -1U);
- }
xa_for_each(&ctx->io_bl_xa, index, bl) {
xa_erase(&ctx->io_bl_xa, bl->bgid);
- __io_remove_buffers(ctx, bl, -1U);
- kfree_rcu(bl, rcu);
+ io_put_bl(ctx, bl);
}
/*
@@ -489,12 +461,6 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
io_ring_submit_lock(ctx, issue_flags);
- if (unlikely(p->bgid < BGID_ARRAY && !ctx->io_bl)) {
- ret = io_init_bl_list(ctx);
- if (ret)
- goto err;
- }
-
bl = io_buffer_get_list(ctx, p->bgid);
if (unlikely(!bl)) {
bl = kzalloc(sizeof(*bl), GFP_KERNEL_ACCOUNT);
@@ -507,14 +473,9 @@ int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags)
if (ret) {
/*
* Doesn't need rcu free as it was never visible, but
- * let's keep it consistent throughout. Also can't
- * be a lower indexed array group, as adding one
- * where lookup failed cannot happen.
+ * let's keep it consistent throughout.
*/
- if (p->bgid >= BGID_ARRAY)
- kfree_rcu(bl, rcu);
- else
- WARN_ON_ONCE(1);
+ kfree_rcu(bl, rcu);
goto err;
}
}
@@ -679,12 +640,6 @@ int io_register_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
if (reg.ring_entries >= 65536)
return -EINVAL;
- if (unlikely(reg.bgid < BGID_ARRAY && !ctx->io_bl)) {
- int ret = io_init_bl_list(ctx);
- if (ret)
- return ret;
- }
-
bl = io_buffer_get_list(ctx, reg.bgid);
if (bl) {
/* if mapped buffer ring OR classic exists, don't allow */
@@ -733,11 +688,8 @@ int io_unregister_pbuf_ring(struct io_ring_ctx *ctx, void __user *arg)
if (!bl->is_buf_ring)
return -EINVAL;
- __io_remove_buffers(ctx, bl, -1U);
- if (bl->bgid >= BGID_ARRAY) {
- xa_erase(&ctx->io_bl_xa, bl->bgid);
- kfree_rcu(bl, rcu);
- }
+ xa_erase(&ctx->io_bl_xa, bl->bgid);
+ io_put_bl(ctx, bl);
return 0;
}
@@ -767,23 +719,35 @@ int io_register_pbuf_status(struct io_ring_ctx *ctx, void __user *arg)
return 0;
}
-void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid)
+struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
+ unsigned long bgid)
{
struct io_buffer_list *bl;
+ bool ret;
- bl = __io_buffer_get_list(ctx, smp_load_acquire(&ctx->io_bl), bgid);
-
- if (!bl || !bl->is_mmap)
- return NULL;
/*
- * Ensure the list is fully setup. Only strictly needed for RCU lookup
- * via mmap, and in that case only for the array indexed groups. For
- * the xarray lookups, it's either visible and ready, or not at all.
+ * We have to be a bit careful here - we're inside mmap and cannot grab
+ * the uring_lock. This means the buffer_list could be simultaneously
+ * going away, if someone is trying to be sneaky. Look it up under rcu
+ * so we know it's not going away, and attempt to grab a reference to
+ * it. If the ref is already zero, then fail the mapping. If successful,
+ * the caller will call io_put_bl() to drop the the reference at at the
+ * end. This may then safely free the buffer_list (and drop the pages)
+ * at that point, vm_insert_pages() would've already grabbed the
+ * necessary vma references.
*/
- if (!smp_load_acquire(&bl->is_ready))
- return NULL;
-
- return bl->buf_ring;
+ rcu_read_lock();
+ bl = xa_load(&ctx->io_bl_xa, bgid);
+ /* must be a mmap'able buffer ring and have pages */
+ ret = false;
+ if (bl && bl->is_mmap)
+ ret = atomic_inc_not_zero(&bl->refs);
+ rcu_read_unlock();
+
+ if (ret)
+ return bl;
+
+ return ERR_PTR(-EINVAL);
}
/*
diff --git a/io_uring/kbuf.h b/io_uring/kbuf.h
index 1c7b654ee726..df365b8860cf 100644
--- a/io_uring/kbuf.h
+++ b/io_uring/kbuf.h
@@ -25,12 +25,12 @@ struct io_buffer_list {
__u16 head;
__u16 mask;
+ atomic_t refs;
+
/* ring mapped provided buffers */
__u8 is_buf_ring;
/* ring mapped provided buffers, but mmap'ed by application */
__u8 is_mmap;
- /* bl is visible from an RCU point of view for lookup */
- __u8 is_ready;
};
struct io_buffer {
@@ -61,7 +61,9 @@ void __io_put_kbuf(struct io_kiocb *req, unsigned issue_flags);
bool io_kbuf_recycle_legacy(struct io_kiocb *req, unsigned issue_flags);
-void *io_pbuf_get_address(struct io_ring_ctx *ctx, unsigned long bgid);
+void io_put_bl(struct io_ring_ctx *ctx, struct io_buffer_list *bl);
+struct io_buffer_list *io_pbuf_get_bl(struct io_ring_ctx *ctx,
+ unsigned long bgid);
static inline bool io_kbuf_recycle_ring(struct io_kiocb *req)
{
diff --git a/io_uring/rw.c b/io_uring/rw.c
index 0585ebcc9773..c8d48287439e 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -937,6 +937,13 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
ret = __io_read(req, issue_flags);
/*
+ * If the file doesn't support proper NOWAIT, then disable multishot
+ * and stay in single shot mode.
+ */
+ if (!io_file_supports_nowait(req))
+ req->flags &= ~REQ_F_APOLL_MULTISHOT;
+
+ /*
* If we get -EAGAIN, recycle our buffer and just let normal poll
* handling arm it.
*/
@@ -955,7 +962,7 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
/*
* Any successful return value will keep the multishot read armed.
*/
- if (ret > 0) {
+ if (ret > 0 && req->flags & REQ_F_APOLL_MULTISHOT) {
/*
* Put our buffer and post a CQE. If we fail to post a CQE, then
* jump to the termination path. This request is then done.
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 9d9095e81792..65adc815fc6e 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1567,10 +1567,17 @@ static int check_kprobe_address_safe(struct kprobe *p,
jump_label_lock();
preempt_disable();
- /* Ensure it is not in reserved area nor out of text */
- if (!(core_kernel_text((unsigned long) p->addr) ||
- is_module_text_address((unsigned long) p->addr)) ||
- in_gate_area_no_mm((unsigned long) p->addr) ||
+ /* Ensure the address is in a text area, and find a module if exists. */
+ *probed_mod = NULL;
+ if (!core_kernel_text((unsigned long) p->addr)) {
+ *probed_mod = __module_text_address((unsigned long) p->addr);
+ if (!(*probed_mod)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ }
+ /* Ensure it is not in reserved area. */
+ if (in_gate_area_no_mm((unsigned long) p->addr) ||
within_kprobe_blacklist((unsigned long) p->addr) ||
jump_label_text_reserved(p->addr, p->addr) ||
static_call_text_reserved(p->addr, p->addr) ||
@@ -1580,8 +1587,7 @@ static int check_kprobe_address_safe(struct kprobe *p,
goto out;
}
- /* Check if 'p' is probing a module. */
- *probed_mod = __module_text_address((unsigned long) p->addr);
+ /* Get module refcount and reject __init functions for loaded modules. */
if (*probed_mod) {
/*
* We must hold a refcount of the probed module while updating
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 269e21590df5..1331216a9cae 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -697,6 +697,7 @@ bool tick_nohz_tick_stopped_cpu(int cpu)
/**
* tick_nohz_update_jiffies - update jiffies when idle was interrupted
+ * @now: current ktime_t
*
* Called from interrupt entry when the CPU was idle
*
@@ -794,7 +795,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime,
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total idle time of the @cpu
*/
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
@@ -820,7 +821,7 @@ EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
* This time is measured via accounting rather than sampling,
* and is as accurate as ktime_get() is.
*
- * This function returns -1 if NOHZ is not enabled.
+ * Return: -1 if NOHZ is not enabled, else total iowait time of @cpu
*/
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
{
@@ -1287,6 +1288,8 @@ void tick_nohz_irq_exit(void)
/**
* tick_nohz_idle_got_tick - Check whether or not the tick handler has run
+ *
+ * Return: %true if the tick handler has run, otherwise %false
*/
bool tick_nohz_idle_got_tick(void)
{
@@ -1305,6 +1308,8 @@ bool tick_nohz_idle_got_tick(void)
* stopped, it returns the next hrtimer.
*
* Called from power state control code with interrupts disabled
+ *
+ * Return: the next expiration time
*/
ktime_t tick_nohz_get_next_hrtimer(void)
{
@@ -1320,6 +1325,8 @@ ktime_t tick_nohz_get_next_hrtimer(void)
* The return value of this function and/or the value returned by it through the
* @delta_next pointer can be negative which must be taken into account by its
* callers.
+ *
+ * Return: the expected length of the current sleep
*/
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
{
@@ -1357,8 +1364,11 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
/**
* tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
* for a particular CPU.
+ * @cpu: target CPU number
*
* Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for @cpu
*/
unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
{
@@ -1371,6 +1381,8 @@ unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
* Called from the schedutil frequency scaling governor in scheduler context.
+ *
+ * Return: the current idle calls counter value for the current CPU
*/
unsigned long tick_nohz_get_idle_calls(void)
{
@@ -1559,7 +1571,7 @@ early_param("skew_tick", skew_tick);
/**
* tick_setup_sched_timer - setup the tick emulation timer
- * @mode: tick_nohz_mode to setup for
+ * @hrtimer: whether to use the hrtimer or not
*/
void tick_setup_sched_timer(bool hrtimer)
{
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index e11c4dc65bcb..b4a7822f495d 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -46,8 +46,8 @@ struct tick_device {
* @next_tick: Next tick to be fired when in dynticks mode.
* @idle_jiffies: jiffies at the entry to idle for idle time accounting
* @idle_waketime: Time when the idle was interrupted
+ * @idle_sleeptime_seq: sequence counter for data consistency
* @idle_entrytime: Time when the idle call was entered
- * @nohz_mode: Mode - one state of tick_nohz_mode
* @last_jiffies: Base jiffies snapshot when next event was last computed
* @timer_expires_base: Base time clock monotonic for @timer_expires
* @timer_expires: Anticipated timer expiration time (in case sched tick is stopped)
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index dee29f1f5b75..3baf2fbe6848 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -64,15 +64,15 @@ EXPORT_SYMBOL(jiffies_64);
/*
* The timer wheel has LVL_DEPTH array levels. Each level provides an array of
- * LVL_SIZE buckets. Each level is driven by its own clock and therefor each
+ * LVL_SIZE buckets. Each level is driven by its own clock and therefore each
* level has a different granularity.
*
- * The level granularity is: LVL_CLK_DIV ^ lvl
+ * The level granularity is: LVL_CLK_DIV ^ level
* The level clock frequency is: HZ / (LVL_CLK_DIV ^ level)
*
* The array level of a newly armed timer depends on the relative expiry
* time. The farther the expiry time is away the higher the array level and
- * therefor the granularity becomes.
+ * therefore the granularity becomes.
*
* Contrary to the original timer wheel implementation, which aims for 'exact'
* expiry of the timers, this implementation removes the need for recascading
@@ -207,7 +207,7 @@ EXPORT_SYMBOL(jiffies_64);
* struct timer_base - Per CPU timer base (number of base depends on config)
* @lock: Lock protecting the timer_base
* @running_timer: When expiring timers, the lock is dropped. To make
- * sure not to race agains deleting/modifying a
+ * sure not to race against deleting/modifying a
* currently running timer, the pointer is set to the
* timer, which expires at the moment. If no timer is
* running, the pointer is NULL.
@@ -737,7 +737,7 @@ static bool timer_is_static_object(void *addr)
}
/*
- * fixup_init is called when:
+ * timer_fixup_init is called when:
* - an active object is initialized
*/
static bool timer_fixup_init(void *addr, enum debug_obj_state state)
@@ -761,7 +761,7 @@ static void stub_timer(struct timer_list *unused)
}
/*
- * fixup_activate is called when:
+ * timer_fixup_activate is called when:
* - an active object is activated
* - an unknown non-static object is activated
*/
@@ -783,7 +783,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state)
}
/*
- * fixup_free is called when:
+ * timer_fixup_free is called when:
* - an active object is freed
*/
static bool timer_fixup_free(void *addr, enum debug_obj_state state)
@@ -801,7 +801,7 @@ static bool timer_fixup_free(void *addr, enum debug_obj_state state)
}
/*
- * fixup_assert_init is called when:
+ * timer_fixup_assert_init is called when:
* - an untracked/uninit-ed object is found
*/
static bool timer_fixup_assert_init(void *addr, enum debug_obj_state state)
@@ -914,7 +914,7 @@ static void do_init_timer(struct timer_list *timer,
* @key: lockdep class key of the fake lock used for tracking timer
* sync lock dependencies
*
- * init_timer_key() must be done to a timer prior calling *any* of the
+ * init_timer_key() must be done to a timer prior to calling *any* of the
* other timer functions.
*/
void init_timer_key(struct timer_list *timer,
@@ -1417,7 +1417,7 @@ static int __timer_delete(struct timer_list *timer, bool shutdown)
* If @shutdown is set then the lock has to be taken whether the
* timer is pending or not to protect against a concurrent rearm
* which might hit between the lockless pending check and the lock
- * aquisition. By taking the lock it is ensured that such a newly
+ * acquisition. By taking the lock it is ensured that such a newly
* enqueued timer is dequeued and cannot end up with
* timer->function == NULL in the expiry code.
*
@@ -2306,7 +2306,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem,
/*
* When timer base is not set idle, undo the effect of
- * tmigr_cpu_deactivate() to prevent inconsitent states - active
+ * tmigr_cpu_deactivate() to prevent inconsistent states - active
* timer base but inactive timer migration hierarchy.
*
* When timer base was already marked idle, nothing will be
diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
index c63a0afdcebe..ccba875d2234 100644
--- a/kernel/time/timer_migration.c
+++ b/kernel/time/timer_migration.c
@@ -751,6 +751,33 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
first_childevt = evt = data->evt;
+ /*
+ * Walking the hierarchy is required in any case when a
+ * remote expiry was done before. This ensures to not lose
+ * already queued events in non active groups (see section
+ * "Required event and timerqueue update after a remote
+ * expiry" in the documentation at the top).
+ *
+ * The two call sites which are executed without a remote expiry
+ * before, are not prevented from propagating changes through
+ * the hierarchy by the return:
+ * - When entering this path by tmigr_new_timer(), @evt->ignore
+ * is never set.
+ * - tmigr_inactive_up() takes care of the propagation by
+ * itself and ignores the return value. But an immediate
+ * return is possible if there is a parent, sparing group
+ * locking at this level, because the upper walking call to
+ * the parent will take care about removing this event from
+ * within the group and update next_expiry accordingly.
+ *
+ * However if there is no parent, ie: the hierarchy has only a
+ * single level so @group is the top level group, make sure the
+ * first event information of the group is updated properly and
+ * also handled properly, so skip this fast return path.
+ */
+ if (evt->ignore && !remote && group->parent)
+ return true;
+
raw_spin_lock(&group->lock);
childstate.state = 0;
@@ -762,8 +789,11 @@ bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child,
* queue when the expiry time changed only or when it could be ignored.
*/
if (timerqueue_node_queued(&evt->nextevt)) {
- if ((evt->nextevt.expires == nextexp) && !evt->ignore)
+ if ((evt->nextevt.expires == nextexp) && !evt->ignore) {
+ /* Make sure not to miss a new CPU event with the same expiry */
+ evt->cpu = first_childevt->cpu;
goto check_toplvl;
+ }
if (!timerqueue_del(&group->events, &evt->nextevt))
WRITE_ONCE(group->next_expiry, KTIME_MAX);
diff --git a/lib/checksum_kunit.c b/lib/checksum_kunit.c
index bf70850035c7..404dba36bae3 100644
--- a/lib/checksum_kunit.c
+++ b/lib/checksum_kunit.c
@@ -594,13 +594,15 @@ static void test_ip_fast_csum(struct kunit *test)
static void test_csum_ipv6_magic(struct kunit *test)
{
-#if defined(CONFIG_NET)
const struct in6_addr *saddr;
const struct in6_addr *daddr;
unsigned int len;
unsigned char proto;
__wsum csum;
+ if (!IS_ENABLED(CONFIG_NET))
+ return;
+
const int daddr_offset = sizeof(struct in6_addr);
const int len_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr);
const int proto_offset = sizeof(struct in6_addr) + sizeof(struct in6_addr) +
@@ -618,7 +620,6 @@ static void test_csum_ipv6_magic(struct kunit *test)
CHECK_EQ(to_sum16(expected_csum_ipv6_magic[i]),
csum_ipv6_magic(saddr, daddr, len, proto, csum));
}
-#endif /* !CONFIG_NET */
}
static struct kunit_case __refdata checksum_test_cases[] = {
diff --git a/lib/stackdepot.c b/lib/stackdepot.c
index af6cc19a2003..68c97387aa54 100644
--- a/lib/stackdepot.c
+++ b/lib/stackdepot.c
@@ -330,7 +330,7 @@ static struct stack_record *depot_pop_free_pool(void **prealloc, size_t size)
stack = current_pool + pool_offset;
/* Pre-initialize handle once. */
- stack->handle.pool_index = pool_index + 1;
+ stack->handle.pool_index_plus_1 = pool_index + 1;
stack->handle.offset = pool_offset >> DEPOT_STACK_ALIGN;
stack->handle.extra = 0;
INIT_LIST_HEAD(&stack->hash_list);
@@ -441,7 +441,7 @@ static struct stack_record *depot_fetch_stack(depot_stack_handle_t handle)
const int pools_num_cached = READ_ONCE(pools_num);
union handle_parts parts = { .handle = handle };
void *pool;
- u32 pool_index = parts.pool_index - 1;
+ u32 pool_index = parts.pool_index_plus_1 - 1;
size_t offset = parts.offset << DEPOT_STACK_ALIGN;
struct stack_record *stack;
diff --git a/lib/test_ubsan.c b/lib/test_ubsan.c
index 276c12140ee2..c288df9372ed 100644
--- a/lib/test_ubsan.c
+++ b/lib/test_ubsan.c
@@ -134,7 +134,7 @@ static const test_ubsan_fp test_ubsan_array[] = {
};
/* Excluded because they Oops the module. */
-static const test_ubsan_fp skip_ubsan_array[] = {
+static __used const test_ubsan_fp skip_ubsan_array[] = {
test_ubsan_divrem_overflow,
};
diff --git a/mm/memory.c b/mm/memory.c
index 904f70b99498..d2155ced45f8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5973,6 +5973,10 @@ int follow_phys(struct vm_area_struct *vma,
goto out;
pte = ptep_get(ptep);
+ /* Never return PFNs of anon folios in COW mappings. */
+ if (vm_normal_folio(vma, address, pte))
+ goto unlock;
+
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 22aa63f4ef63..68fa001648cc 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -989,6 +989,27 @@ unsigned long vmalloc_nr_pages(void)
return atomic_long_read(&nr_vmalloc_pages);
}
+static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
+{
+ struct rb_node *n = root->rb_node;
+
+ addr = (unsigned long)kasan_reset_tag((void *)addr);
+
+ while (n) {
+ struct vmap_area *va;
+
+ va = rb_entry(n, struct vmap_area, rb_node);
+ if (addr < va->va_start)
+ n = n->rb_left;
+ else if (addr >= va->va_end)
+ n = n->rb_right;
+ else
+ return va;
+ }
+
+ return NULL;
+}
+
/* Look up the first VA which satisfies addr < va_end, NULL if none. */
static struct vmap_area *
__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
@@ -1025,47 +1046,39 @@ __find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
static struct vmap_node *
find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
{
- struct vmap_node *vn, *va_node = NULL;
- struct vmap_area *va_lowest;
+ unsigned long va_start_lowest;
+ struct vmap_node *vn;
int i;
- for (i = 0; i < nr_vmap_nodes; i++) {
+repeat:
+ for (i = 0, va_start_lowest = 0; i < nr_vmap_nodes; i++) {
vn = &vmap_nodes[i];
spin_lock(&vn->busy.lock);
- va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
- if (va_lowest) {
- if (!va_node || va_lowest->va_start < (*va)->va_start) {
- if (va_node)
- spin_unlock(&va_node->busy.lock);
-
- *va = va_lowest;
- va_node = vn;
- continue;
- }
- }
+ *va = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
+
+ if (*va)
+ if (!va_start_lowest || (*va)->va_start < va_start_lowest)
+ va_start_lowest = (*va)->va_start;
spin_unlock(&vn->busy.lock);
}
- return va_node;
-}
-
-static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
-{
- struct rb_node *n = root->rb_node;
+ /*
+ * Check if found VA exists, it might have gone away. In this case we
+ * repeat the search because a VA has been removed concurrently and we
+ * need to proceed to the next one, which is a rare case.
+ */
+ if (va_start_lowest) {
+ vn = addr_to_node(va_start_lowest);
- addr = (unsigned long)kasan_reset_tag((void *)addr);
+ spin_lock(&vn->busy.lock);
+ *va = __find_vmap_area(va_start_lowest, &vn->busy.root);
- while (n) {
- struct vmap_area *va;
+ if (*va)
+ return vn;
- va = rb_entry(n, struct vmap_area, rb_node);
- if (addr < va->va_start)
- n = n->rb_left;
- else if (addr >= va->va_end)
- n = n->rb_right;
- else
- return va;
+ spin_unlock(&vn->busy.lock);
+ goto repeat;
}
return NULL;
@@ -2343,6 +2356,9 @@ struct vmap_area *find_vmap_area(unsigned long addr)
struct vmap_area *va;
int i, j;
+ if (unlikely(!vmap_initialized))
+ return NULL;
+
/*
* An addr_to_node_id(addr) converts an address to a node index
* where a VA is located. If VA spans several zones and passed
diff --git a/net/9p/client.c b/net/9p/client.c
index e265a0ca6bdd..f7e90b4769bb 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1583,7 +1583,7 @@ p9_client_read_once(struct p9_fid *fid, u64 offset, struct iov_iter *to,
received = rsize;
}
- p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
+ p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", received);
if (non_zc) {
int n = copy_to_iter(dataptr, received, to);
@@ -1609,9 +1609,6 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
int total = 0;
*err = 0;
- p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n",
- fid->fid, offset, iov_iter_count(from));
-
while (iov_iter_count(from)) {
int count = iov_iter_count(from);
int rsize = fid->iounit;
@@ -1623,6 +1620,9 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
if (count < rsize)
rsize = count;
+ p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d (/%d)\n",
+ fid->fid, offset, rsize, count);
+
/* Don't bother zerocopy for small IO (< 1024) */
if (clnt->trans_mod->zc_request && rsize > 1024) {
req = p9_client_zc_rpc(clnt, P9_TWRITE, NULL, from, 0,
@@ -1650,7 +1650,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
written = rsize;
}
- p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
+ p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", written);
p9_req_put(clnt, req);
iov_iter_revert(from, count - written - iov_iter_count(from));
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 1a3948b8c493..196060dc6138 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -95,7 +95,6 @@ struct p9_poll_wait {
* @unsent_req_list: accounting for requests that haven't been sent
* @rreq: read request
* @wreq: write request
- * @req: current request being processed (if any)
* @tmp_buf: temporary buffer to read in header
* @rc: temporary fcall for reading current frame
* @wpos: write position for current frame
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 0555cb611489..b21ff3c36b07 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -3907,7 +3907,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface)
spin_lock_bh(&bat_priv->tt.commit_lock);
- while (true) {
+ while (timeout) {
table_size = batadv_tt_local_table_transmit_size(bat_priv);
if (packet_size_max >= table_size)
break;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 00e02138003e..efea25eb56ce 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -105,8 +105,10 @@ void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
if (hdev->req_status == HCI_REQ_PEND) {
hdev->req_result = result;
hdev->req_status = HCI_REQ_DONE;
- if (skb)
+ if (skb) {
+ kfree_skb(hdev->req_skb);
hdev->req_skb = skb_get(skb);
+ }
wake_up_interruptible(&hdev->req_wait_q);
}
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 4ee1b976678b..703b84bd48d5 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -1946,10 +1946,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname,
switch (optname) {
case HCI_DATA_DIR:
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
if (opt)
hci_pi(sk)->cmsg_mask |= HCI_CMSG_DIR;
@@ -1958,10 +1957,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname,
break;
case HCI_TIME_STAMP:
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
if (opt)
hci_pi(sk)->cmsg_mask |= HCI_CMSG_TSTAMP;
@@ -1979,11 +1977,9 @@ static int hci_sock_setsockopt_old(struct socket *sock, int level, int optname,
uf.event_mask[1] = *((u32 *) f->event_mask + 1);
}
- len = min_t(unsigned int, len, sizeof(uf));
- if (copy_from_sockptr(&uf, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&uf, sizeof(uf), optval, len);
+ if (err)
break;
- }
if (!capable(CAP_NET_RAW)) {
uf.type_mask &= hci_sec_filter.type_mask;
@@ -2042,10 +2038,9 @@ static int hci_sock_setsockopt(struct socket *sock, int level, int optname,
goto done;
}
- if (copy_from_sockptr(&opt, optval, sizeof(opt))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, len);
+ if (err)
break;
- }
hci_pi(sk)->mtu = opt;
break;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 8fe02921adf1..c5d8799046cc 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -2814,8 +2814,8 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type,
if (qos->bcast.in.phy & BT_ISO_PHY_CODED) {
cp->scanning_phys |= LE_SCAN_PHY_CODED;
hci_le_scan_phy_params(phy, type,
- interval,
- window);
+ interval * 3,
+ window * 3);
num_phy++;
phy++;
}
@@ -2835,7 +2835,7 @@ static int hci_le_set_ext_scan_param_sync(struct hci_dev *hdev, u8 type,
if (scan_coded(hdev)) {
cp->scanning_phys |= LE_SCAN_PHY_CODED;
- hci_le_scan_phy_params(phy, type, interval, window);
+ hci_le_scan_phy_params(phy, type, interval * 3, window * 3);
num_phy++;
phy++;
}
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index c8793e57f4b5..ef0cc80b4c0c 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -1451,8 +1451,8 @@ static bool check_ucast_qos(struct bt_iso_qos *qos)
static bool check_bcast_qos(struct bt_iso_qos *qos)
{
- if (qos->bcast.sync_factor == 0x00)
- return false;
+ if (!qos->bcast.sync_factor)
+ qos->bcast.sync_factor = 0x01;
if (qos->bcast.packing > 0x01)
return false;
@@ -1475,6 +1475,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos)
if (qos->bcast.skip > 0x01f3)
return false;
+ if (!qos->bcast.sync_timeout)
+ qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT;
+
if (qos->bcast.sync_timeout < 0x000a || qos->bcast.sync_timeout > 0x4000)
return false;
@@ -1484,6 +1487,9 @@ static bool check_bcast_qos(struct bt_iso_qos *qos)
if (qos->bcast.mse > 0x1f)
return false;
+ if (!qos->bcast.timeout)
+ qos->bcast.sync_timeout = BT_ISO_SYNC_TIMEOUT;
+
if (qos->bcast.timeout < 0x000a || qos->bcast.timeout > 0x4000)
return false;
@@ -1494,7 +1500,7 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
- int len, err = 0;
+ int err = 0;
struct bt_iso_qos qos = default_qos;
u32 opt;
@@ -1509,10 +1515,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -1521,10 +1526,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_PKT_STATUS:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
@@ -1539,17 +1543,9 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- len = min_t(unsigned int, sizeof(qos), optlen);
-
- if (copy_from_sockptr(&qos, optval, len)) {
- err = -EFAULT;
- break;
- }
-
- if (len == sizeof(qos.ucast) && !check_ucast_qos(&qos)) {
- err = -EINVAL;
+ err = bt_copy_from_sockptr(&qos, sizeof(qos), optval, optlen);
+ if (err)
break;
- }
iso_pi(sk)->qos = qos;
iso_pi(sk)->qos_user_set = true;
@@ -1564,18 +1560,16 @@ static int iso_sock_setsockopt(struct socket *sock, int level, int optname,
}
if (optlen > sizeof(iso_pi(sk)->base)) {
- err = -EOVERFLOW;
+ err = -EINVAL;
break;
}
- len = min_t(unsigned int, sizeof(iso_pi(sk)->base), optlen);
-
- if (copy_from_sockptr(iso_pi(sk)->base, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(iso_pi(sk)->base, optlen, optval,
+ optlen);
+ if (err)
break;
- }
- iso_pi(sk)->base_len = len;
+ iso_pi(sk)->base_len = optlen;
break;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 467b242d8be0..dc0897408793 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -4054,8 +4054,7 @@ static int l2cap_connect_req(struct l2cap_conn *conn,
return -EPROTO;
hci_dev_lock(hdev);
- if (hci_dev_test_flag(hdev, HCI_MGMT) &&
- !test_and_set_bit(HCI_CONN_MGMT_CONNECTED, &hcon->flags))
+ if (hci_dev_test_flag(hdev, HCI_MGMT))
mgmt_device_connected(hdev, hcon, NULL, 0);
hci_dev_unlock(hdev);
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index 4287aa6cc988..e7d810b23082 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -727,7 +727,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
struct sock *sk = sock->sk;
struct l2cap_chan *chan = l2cap_pi(sk)->chan;
struct l2cap_options opts;
- int len, err = 0;
+ int err = 0;
u32 opt;
BT_DBG("sk %p", sk);
@@ -754,11 +754,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
opts.max_tx = chan->max_tx;
opts.txwin_size = chan->tx_win;
- len = min_t(unsigned int, sizeof(opts), optlen);
- if (copy_from_sockptr(&opts, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opts, sizeof(opts), optval, optlen);
+ if (err)
break;
- }
if (opts.txwin_size > L2CAP_DEFAULT_EXT_WINDOW) {
err = -EINVAL;
@@ -801,10 +799,9 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname,
break;
case L2CAP_LM:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt & L2CAP_LM_FIPS) {
err = -EINVAL;
@@ -885,7 +882,7 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
struct bt_security sec;
struct bt_power pwr;
struct l2cap_conn *conn;
- int len, err = 0;
+ int err = 0;
u32 opt;
u16 mtu;
u8 mode;
@@ -911,11 +908,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
sec.level = BT_SECURITY_LOW;
- len = min_t(unsigned int, sizeof(sec), optlen);
- if (copy_from_sockptr(&sec, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen);
+ if (err)
break;
- }
if (sec.level < BT_SECURITY_LOW ||
sec.level > BT_SECURITY_FIPS) {
@@ -960,10 +955,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt) {
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -975,10 +969,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_FLUSHABLE:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt > BT_FLUSHABLE_ON) {
err = -EINVAL;
@@ -1010,11 +1003,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
pwr.force_active = BT_POWER_FORCE_ACTIVE_ON;
- len = min_t(unsigned int, sizeof(pwr), optlen);
- if (copy_from_sockptr(&pwr, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&pwr, sizeof(pwr), optval, optlen);
+ if (err)
break;
- }
if (pwr.force_active)
set_bit(FLAG_FORCE_ACTIVE, &chan->flags);
@@ -1023,10 +1014,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_CHANNEL_POLICY:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
err = -EOPNOTSUPP;
break;
@@ -1055,10 +1045,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&mtu, optval, sizeof(u16))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mtu, sizeof(mtu), optval, optlen);
+ if (err)
break;
- }
if (chan->mode == L2CAP_MODE_EXT_FLOWCTL &&
sk->sk_state == BT_CONNECTED)
@@ -1086,10 +1075,9 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&mode, optval, sizeof(u8))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&mode, sizeof(mode), optval, optlen);
+ if (err)
break;
- }
BT_DBG("mode %u", mode);
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index b54e8a530f55..29aa07e9db9d 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -629,7 +629,7 @@ static int rfcomm_sock_setsockopt_old(struct socket *sock, int optname,
switch (optname) {
case RFCOMM_LM:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
+ if (bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen)) {
err = -EFAULT;
break;
}
@@ -664,7 +664,6 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname,
struct sock *sk = sock->sk;
struct bt_security sec;
int err = 0;
- size_t len;
u32 opt;
BT_DBG("sk %p", sk);
@@ -686,11 +685,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname,
sec.level = BT_SECURITY_LOW;
- len = min_t(unsigned int, sizeof(sec), optlen);
- if (copy_from_sockptr(&sec, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&sec, sizeof(sec), optval, optlen);
+ if (err)
break;
- }
if (sec.level > BT_SECURITY_HIGH) {
err = -EINVAL;
@@ -706,10 +703,9 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 43daf965a01e..368e026f4d15 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -824,7 +824,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
- int len, err = 0;
+ int err = 0;
struct bt_voice voice;
u32 opt;
struct bt_codecs *codecs;
@@ -843,10 +843,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags);
@@ -863,11 +862,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
voice.setting = sco_pi(sk)->setting;
- len = min_t(unsigned int, sizeof(voice), optlen);
- if (copy_from_sockptr(&voice, optval, len)) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&voice, sizeof(voice), optval,
+ optlen);
+ if (err)
break;
- }
/* Explicitly check for these values */
if (voice.setting != BT_VOICE_TRANSPARENT &&
@@ -890,10 +888,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
case BT_PKT_STATUS:
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen);
+ if (err)
break;
- }
if (opt)
set_bit(BT_SK_PKT_STATUS, &bt_sk(sk)->flags);
@@ -934,9 +931,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(buffer, optval, optlen)) {
+ err = bt_copy_from_sockptr(buffer, optlen, optval, optlen);
+ if (err) {
hci_dev_put(hdev);
- err = -EFAULT;
break;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index b150c9929b12..14365b20f1c5 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -966,6 +966,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1266,6 +1268,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 487670759578..fe89a056eb06 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1118,6 +1118,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1504,6 +1506,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c8f76f56dc16..d36ace160d42 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -926,13 +926,11 @@ void ip_rt_send_redirect(struct sk_buff *skb)
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
-#ifdef CONFIG_IP_ROUTE_VERBOSE
- if (log_martians &&
+ if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
-#endif
}
out_put_peer:
inet_putpeer(peer);
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 82ad6b8fa007..3a92d002abe4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2092,9 +2092,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add
if (ipv6_addr_equal(&ifp->addr, addr)) {
if (!dev || ifp->idev->dev == dev ||
!(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) {
- result = ifp;
- in6_ifa_hold(ifp);
- break;
+ if (in6_ifa_hold_safe(ifp)) {
+ result = ifp;
+ break;
+ }
}
}
}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ddd8e3c2df4a..31d77885bcae 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1386,7 +1386,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->fib6_table;
- struct fib6_node *fn, *pn = NULL;
+ struct fib6_node *fn;
+#ifdef CONFIG_IPV6_SUBTREES
+ struct fib6_node *pn = NULL;
+#endif
int err = -ENOMEM;
int allow_create = 1;
int replace_required = 0;
@@ -1410,9 +1413,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt,
goto out;
}
+#ifdef CONFIG_IPV6_SUBTREES
pn = fn;
-#ifdef CONFIG_IPV6_SUBTREES
if (rt->fib6_src.plen) {
struct fib6_node *sn;
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 636b360311c5..131f7bb2110d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1135,6 +1135,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
@@ -1513,6 +1515,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len)
return -ENOMEM;
if (tmp.num_counters == 0)
return -EINVAL;
+ if ((u64)len < (u64)tmp.size + sizeof(tmp))
+ return -EINVAL;
tmp.name[sizeof(tmp.name)-1] = 0;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 819157bbb5a2..d5344563e525 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -252,10 +252,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt > LLCP_MAX_RW) {
err = -EINVAL;
@@ -274,10 +274,10 @@ static int nfc_llcp_setsockopt(struct socket *sock, int level, int optname,
break;
}
- if (copy_from_sockptr(&opt, optval, sizeof(u32))) {
- err = -EFAULT;
+ err = copy_safe_from_sockptr(&opt, sizeof(opt),
+ optval, optlen);
+ if (err)
break;
- }
if (opt > LLCP_MAX_MIUX) {
err = -EINVAL;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3019a4406ca4..74b63cdb5992 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1380,8 +1380,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
if (ct_info.timeout[0]) {
if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
ct_info.timeout))
- pr_info_ratelimited("Failed to associated timeout "
- "policy `%s'\n", ct_info.timeout);
+ OVS_NLERR(log,
+ "Failed to associated timeout policy '%s'",
+ ct_info.timeout);
else
ct_info.nf_ct_timeout = rcu_dereference(
nf_ct_timeout_find(ct_info.ct)->timeout);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 545017a3daa4..6b3f01beb294 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1206,15 +1206,6 @@ err_noclose:
* MSG_SPLICE_PAGES is used exclusively to reduce the number of
* copy operations in this path. Therefore the caller must ensure
* that the pages backing @xdr are unchanging.
- *
- * Note that the send is non-blocking. The caller has incremented
- * the reference count on each page backing the RPC message, and
- * the network layer will "put" these pages when transmission is
- * complete.
- *
- * This is safe for our RPC services because the memory backing
- * the head and tail components is never kmalloc'd. These always
- * come from pages in the svc_rqst::rq_pages array.
*/
static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
rpc_fraghdr marker, unsigned int *sentp)
@@ -1244,6 +1235,7 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, rqstp->rq_bvec,
1 + count, sizeof(marker) + rqstp->rq_res.len);
ret = sock_sendmsg(svsk->sk_sock, &msg);
+ page_frag_free(buf);
if (ret < 0)
return ret;
*sentp += ret;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 61ecfa9c9c6b..142d210b5b03 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2619,7 +2619,9 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
}
} else if (!(flags & MSG_PEEK)) {
skb_unlink(skb, &sk->sk_receive_queue);
- consume_skb(skb);
+ WRITE_ONCE(u->oob_skb, NULL);
+ if (!WARN_ON_ONCE(skb_unref(skb)))
+ kfree_skb(skb);
skb = skb_peek(&sk->sk_receive_queue);
}
}
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 3404d076a8a3..727aa20be4bd 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1417,6 +1417,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
struct xsk_queue **q;
int entries;
+ if (optlen < sizeof(entries))
+ return -EINVAL;
if (copy_from_sockptr(&entries, optval, sizeof(entries)))
return -EFAULT;
diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c
index c5c2ce113c92..d20c47d21ad8 100644
--- a/scripts/gcc-plugins/stackleak_plugin.c
+++ b/scripts/gcc-plugins/stackleak_plugin.c
@@ -467,6 +467,8 @@ static bool stackleak_gate(void)
return false;
if (STRING_EQUAL(section, ".entry.text"))
return false;
+ if (STRING_EQUAL(section, ".head.text"))
+ return false;
}
return track_frame_size >= 0;
diff --git a/sound/oss/dmasound/dmasound_paula.c b/sound/oss/dmasound/dmasound_paula.c
index 0ba8f0c4cd99..3a593da09280 100644
--- a/sound/oss/dmasound/dmasound_paula.c
+++ b/sound/oss/dmasound/dmasound_paula.c
@@ -725,7 +725,13 @@ static void __exit amiga_audio_remove(struct platform_device *pdev)
dmasound_deinit();
}
-static struct platform_driver amiga_audio_driver = {
+/*
+ * amiga_audio_remove() lives in .exit.text. For drivers registered via
+ * module_platform_driver_probe() this is ok because they cannot get unbound at
+ * runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver amiga_audio_driver __refdata = {
.remove_new = __exit_p(amiga_audio_remove),
.driver = {
.name = "amiga-audio",
diff --git a/sound/pci/emu10k1/emu10k1_callback.c b/sound/pci/emu10k1/emu10k1_callback.c
index d36234b88fb4..941bfbf812ed 100644
--- a/sound/pci/emu10k1/emu10k1_callback.c
+++ b/sound/pci/emu10k1/emu10k1_callback.c
@@ -255,7 +255,7 @@ lookup_voices(struct snd_emux *emu, struct snd_emu10k1 *hw,
/* check if sample is finished playing (non-looping only) */
if (bp != best + V_OFF && bp != best + V_FREE &&
(vp->reg.sample_mode & SNDRV_SFNT_SAMPLE_SINGLESHOT)) {
- val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch) - 64;
+ val = snd_emu10k1_ptr_read(hw, CCCA_CURRADDR, vp->ch);
if (val >= vp->reg.loopstart)
bp = best + V_OFF;
}
@@ -362,7 +362,7 @@ start_voice(struct snd_emux_voice *vp)
map = (hw->silent_page.addr << hw->address_mode) | (hw->address_mode ? MAP_PTI_MASK1 : MAP_PTI_MASK0);
- addr = vp->reg.start + 64;
+ addr = vp->reg.start;
temp = vp->reg.parm.filterQ;
ccca = (temp << 28) | addr;
if (vp->apitch < 0xe400)
@@ -430,9 +430,6 @@ start_voice(struct snd_emux_voice *vp)
/* Q & current address (Q 4bit value, MSB) */
CCCA, ccca,
- /* cache */
- CCR, REG_VAL_PUT(CCR_CACHEINVALIDSIZE, 64),
-
/* reset volume */
VTFT, vtarget | vp->ftarget,
CVCF, vtarget | CVCF_CURRENTFILTER_MASK,
diff --git a/sound/pci/hda/cs35l41_hda_property.c b/sound/pci/hda/cs35l41_hda_property.c
index 72ec872afb8d..8fb688e41414 100644
--- a/sound/pci/hda/cs35l41_hda_property.c
+++ b/sound/pci/hda/cs35l41_hda_property.c
@@ -108,7 +108,10 @@ static const struct cs35l41_config cs35l41_config_table[] = {
{ "10431F12", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 1000, 4500, 24 },
{ "10431F1F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, -1, 0, 0, 0, 0 },
{ "10431F62", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 0, 0, 0 },
+ { "10433A60", 2, INTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 1, 2, 0, 1000, 4500, 24 },
{ "17AA386F", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, -1, -1, 0, 0, 0 },
+ { "17AA3877", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
+ { "17AA3878", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
{ "17AA38A9", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
{ "17AA38AB", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 2, -1, 0, 0, 0 },
{ "17AA38B4", 2, EXTERNAL, { CS35L41_LEFT, CS35L41_RIGHT, 0, 0 }, 0, 1, -1, 0, 0, 0 },
@@ -496,7 +499,10 @@ static const struct cs35l41_prop_model cs35l41_prop_model_table[] = {
{ "CSC3551", "10431F12", generic_dsd_config },
{ "CSC3551", "10431F1F", generic_dsd_config },
{ "CSC3551", "10431F62", generic_dsd_config },
+ { "CSC3551", "10433A60", generic_dsd_config },
{ "CSC3551", "17AA386F", generic_dsd_config },
+ { "CSC3551", "17AA3877", generic_dsd_config },
+ { "CSC3551", "17AA3878", generic_dsd_config },
{ "CSC3551", "17AA38A9", generic_dsd_config },
{ "CSC3551", "17AA38AB", generic_dsd_config },
{ "CSC3551", "17AA38B4", generic_dsd_config },
diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c
index 13beee807308..40f2f97944d5 100644
--- a/sound/pci/hda/cs35l56_hda_i2c.c
+++ b/sound/pci/hda/cs35l56_hda_i2c.c
@@ -56,10 +56,19 @@ static const struct i2c_device_id cs35l56_hda_i2c_id[] = {
{}
};
+static const struct acpi_device_id cs35l56_acpi_hda_match[] = {
+ { "CSC3554", 0 },
+ { "CSC3556", 0 },
+ { "CSC3557", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match);
+
static struct i2c_driver cs35l56_hda_i2c_driver = {
.driver = {
- .name = "cs35l56-hda",
- .pm = &cs35l56_hda_pm_ops,
+ .name = "cs35l56-hda",
+ .acpi_match_table = cs35l56_acpi_hda_match,
+ .pm = &cs35l56_hda_pm_ops,
},
.id_table = cs35l56_hda_i2c_id,
.probe = cs35l56_hda_i2c_probe,
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index a3b2fa76663d..7f02155fe61e 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -56,10 +56,19 @@ static const struct spi_device_id cs35l56_hda_spi_id[] = {
{}
};
+static const struct acpi_device_id cs35l56_acpi_hda_match[] = {
+ { "CSC3554", 0 },
+ { "CSC3556", 0 },
+ { "CSC3557", 0 },
+ {}
+};
+MODULE_DEVICE_TABLE(acpi, cs35l56_acpi_hda_match);
+
static struct spi_driver cs35l56_hda_spi_driver = {
.driver = {
- .name = "cs35l56-hda",
- .pm = &cs35l56_hda_pm_ops,
+ .name = "cs35l56-hda",
+ .acpi_match_table = cs35l56_acpi_hda_match,
+ .pm = &cs35l56_hda_pm_ops,
},
.id_table = cs35l56_hda_spi_id,
.probe = cs35l56_hda_spi_probe,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a17c36a36aa5..cdcb28aa9d7b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6875,11 +6875,38 @@ static void alc287_fixup_legion_16ithg6_speakers(struct hda_codec *cdc, const st
comp_generic_fixup(cdc, action, "i2c", "CLSA0101", "-%s:00-cs35l41-hda.%d", 2);
}
+static void cs35l56_fixup_i2c_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
+{
+ comp_generic_fixup(cdc, action, "i2c", "CSC3556", "-%s:00-cs35l56-hda.%d", 2);
+}
+
+static void cs35l56_fixup_i2c_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
+{
+ comp_generic_fixup(cdc, action, "i2c", "CSC3556", "-%s:00-cs35l56-hda.%d", 4);
+}
+
+static void cs35l56_fixup_spi_two(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
+{
+ comp_generic_fixup(cdc, action, "spi", "CSC3556", "-%s:00-cs35l56-hda.%d", 2);
+}
+
static void cs35l56_fixup_spi_four(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
{
comp_generic_fixup(cdc, action, "spi", "CSC3556", "-%s:00-cs35l56-hda.%d", 4);
}
+static void alc285_fixup_asus_ga403u(struct hda_codec *cdc, const struct hda_fixup *fix, int action)
+{
+ /*
+ * The same SSID has been re-used in different hardware, they have
+ * different codecs and the newer GA403U has a ALC285.
+ */
+ if (cdc->core.vendor_id == 0x10ec0285)
+ cs35l56_fixup_i2c_two(cdc, fix, action);
+ else
+ alc_fixup_inv_dmic(cdc, fix, action);
+}
+
static void tas2781_fixup_i2c(struct hda_codec *cdc,
const struct hda_fixup *fix, int action)
{
@@ -7436,6 +7463,10 @@ enum {
ALC256_FIXUP_ACER_SFG16_MICMUTE_LED,
ALC256_FIXUP_HEADPHONE_AMP_VOL,
ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX,
+ ALC285_FIXUP_CS35L56_SPI_2,
+ ALC285_FIXUP_CS35L56_I2C_2,
+ ALC285_FIXUP_CS35L56_I2C_4,
+ ALC285_FIXUP_ASUS_GA403U,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -9643,6 +9674,22 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc245_fixup_hp_spectre_x360_eu0xxx,
},
+ [ALC285_FIXUP_CS35L56_SPI_2] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs35l56_fixup_spi_two,
+ },
+ [ALC285_FIXUP_CS35L56_I2C_2] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs35l56_fixup_i2c_two,
+ },
+ [ALC285_FIXUP_CS35L56_I2C_4] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cs35l56_fixup_i2c_four,
+ },
+ [ALC285_FIXUP_ASUS_GA403U] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_asus_ga403u,
+ },
};
static const struct snd_pci_quirk alc269_fixup_tbl[] = {
@@ -10096,7 +10143,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B),
- SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
+ SND_PCI_QUIRK(0x1043, 0x1b13, "ASUS U41SV/GA403U", ALC285_FIXUP_ASUS_GA403U),
SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10104,6 +10151,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401),
+ SND_PCI_QUIRK(0x1043, 0x1c63, "ASUS GU605M", ALC285_FIXUP_CS35L56_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS),
SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JU/JV/JI", ALC285_FIXUP_ASUS_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x1caf, "ASUS G634JY/JZ/JI/JG", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -10115,11 +10163,14 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
SND_PCI_QUIRK(0x1043, 0x1da2, "ASUS UP6502ZA/ZD", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1df3, "ASUS UM5606", ALC285_FIXUP_CS35L56_I2C_4),
SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
+ SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_CS35L56_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1e83, "ASUS GA605W", ALC285_FIXUP_CS35L56_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1ee2, "ASUS UM6702RA/RC", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401),
@@ -10133,7 +10184,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
- SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),
@@ -10159,7 +10210,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x10ec, 0x1254, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x10ec, 0x12cc, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
SND_PCI_QUIRK(0x10ec, 0x12f6, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
- SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
+ SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
SND_PCI_QUIRK(0x144d, 0xc169, "Samsung Notebook 9 Pen (NP930SBE-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
SND_PCI_QUIRK(0x144d, 0xc176, "Samsung Notebook 9 Pro (NP930MBE-K04US)", ALC298_FIXUP_SAMSUNG_AMP),
@@ -10333,6 +10384,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x3869, "Lenovo Yoga7 14IAL7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
SND_PCI_QUIRK(0x17aa, 0x386f, "Legion 7i 16IAX7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x3870, "Lenovo Yoga 7 14ARB7", ALC287_FIXUP_YOGA7_14ARB7_I2C),
+ SND_PCI_QUIRK(0x17aa, 0x3877, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x3878, "Lenovo Legion 7 Slim 16ARHA7", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x17aa, 0x387d, "Yoga S780-16 pro Quad AAC", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x387e, "Yoga S780-16 pro Quad YC", ALC287_FIXUP_TAS2781_I2C),
SND_PCI_QUIRK(0x17aa, 0x3881, "YB9 dual power mode2 YC", ALC287_FIXUP_TAS2781_I2C),
@@ -10403,6 +10456,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1d05, 0x1147, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x115c, "TongFang GMxTGxx", ALC269_FIXUP_NO_SHUTUP),
SND_PCI_QUIRK(0x1d05, 0x121b, "TongFang GMxAGxx", ALC269_FIXUP_NO_SHUTUP),
+ SND_PCI_QUIRK(0x1d05, 0x1387, "TongFang GMxIXxx", ALC2XX_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1602, "RedmiBook", ALC255_FIXUP_XIAOMI_HEADSET_MIC),
SND_PCI_QUIRK(0x1d72, 0x1701, "XiaomiNotebook Pro", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1d72, 0x1901, "RedmiBook 14", ALC256_FIXUP_ASUS_HEADSET_MIC),
diff --git a/sound/soc/amd/acp/acp-pci.c b/sound/soc/amd/acp/acp-pci.c
index 8c8b1dcac628..5f35b90eab8d 100644
--- a/sound/soc/amd/acp/acp-pci.c
+++ b/sound/soc/amd/acp/acp-pci.c
@@ -115,7 +115,10 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id
goto unregister_dmic_dev;
}
- acp_init(chip);
+ ret = acp_init(chip);
+ if (ret)
+ goto unregister_dmic_dev;
+
res = devm_kcalloc(&pci->dev, num_res, sizeof(struct resource), GFP_KERNEL);
if (!res) {
ret = -ENOMEM;
@@ -133,11 +136,9 @@ static int acp_pci_probe(struct pci_dev *pci, const struct pci_device_id *pci_id
}
}
- if (flag == FLAG_AMD_LEGACY_ONLY_DMIC) {
- ret = check_acp_pdm(pci, chip);
- if (ret < 0)
- goto skip_pdev_creation;
- }
+ ret = check_acp_pdm(pci, chip);
+ if (ret < 0)
+ goto skip_pdev_creation;
chip->flag = flag;
memset(&pdevinfo, 0, sizeof(pdevinfo));
diff --git a/sound/soc/codecs/cs-amp-lib.c b/sound/soc/codecs/cs-amp-lib.c
index 01ef4db5407d..287ac01a3873 100644
--- a/sound/soc/codecs/cs-amp-lib.c
+++ b/sound/soc/codecs/cs-amp-lib.c
@@ -56,6 +56,11 @@ static int _cs_amp_write_cal_coeffs(struct cs_dsp *dsp,
dev_dbg(dsp->dev, "Calibration: Ambient=%#x, Status=%#x, CalR=%d\n",
data->calAmbient, data->calStatus, data->calR);
+ if (list_empty(&dsp->ctl_list)) {
+ dev_info(dsp->dev, "Calibration disabled due to missing firmware controls\n");
+ return -ENOENT;
+ }
+
ret = cs_amp_write_cal_coeff(dsp, controls, controls->ambient, data->calAmbient);
if (ret)
return ret;
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 860d5cda67bf..94685449f0f4 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2364,7 +2364,8 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
static int cs42l43_codec_suspend(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
disable_irq(cs42l43->irq);
@@ -2373,7 +2374,8 @@ static int cs42l43_codec_suspend(struct device *dev)
static int cs42l43_codec_suspend_noirq(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
enable_irq(cs42l43->irq);
@@ -2382,7 +2384,8 @@ static int cs42l43_codec_suspend_noirq(struct device *dev)
static int cs42l43_codec_resume(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
enable_irq(cs42l43->irq);
@@ -2391,7 +2394,8 @@ static int cs42l43_codec_resume(struct device *dev)
static int cs42l43_codec_resume_noirq(struct device *dev)
{
- struct cs42l43 *cs42l43 = dev_get_drvdata(dev);
+ struct cs42l43_codec *priv = dev_get_drvdata(dev);
+ struct cs42l43 *cs42l43 = priv->core;
disable_irq(cs42l43->irq);
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 15289dadafea..17bd6b516077 100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -412,9 +412,9 @@ static const struct _coeff_div coeff_div_v3[] = {
{125, 48000, 6000000, 0x04, 0x04, 0x1F, 0x2D, 0x8A, 0x0A, 0x27, 0x27},
{128, 8000, 1024000, 0x60, 0x00, 0x05, 0x75, 0x8A, 0x1B, 0x1F, 0x7F},
- {128, 16000, 2048000, 0x20, 0x00, 0x31, 0x35, 0x8A, 0x1B, 0x1F, 0x3F},
- {128, 44100, 5644800, 0xE0, 0x00, 0x01, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
- {128, 48000, 6144000, 0xE0, 0x00, 0x01, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
+ {128, 16000, 2048000, 0x20, 0x00, 0x31, 0x35, 0x08, 0x19, 0x1F, 0x3F},
+ {128, 44100, 5644800, 0xE0, 0x00, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
+ {128, 48000, 6144000, 0xE0, 0x00, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
{144, 8000, 1152000, 0x20, 0x00, 0x03, 0x35, 0x8A, 0x1B, 0x23, 0x47},
{144, 16000, 2304000, 0x20, 0x00, 0x11, 0x35, 0x8A, 0x1B, 0x23, 0x47},
{192, 8000, 1536000, 0x60, 0x02, 0x0D, 0x75, 0x8A, 0x1B, 0x1F, 0x7F},
@@ -423,10 +423,10 @@ static const struct _coeff_div coeff_div_v3[] = {
{200, 48000, 9600000, 0x04, 0x04, 0x0F, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
{250, 48000, 12000000, 0x04, 0x04, 0x0F, 0x2D, 0xCA, 0x0A, 0x27, 0x27},
- {256, 8000, 2048000, 0x60, 0x00, 0x31, 0x35, 0x8A, 0x1B, 0x1F, 0x7F},
- {256, 16000, 4096000, 0x20, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x3F},
- {256, 44100, 11289600, 0xE0, 0x00, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
- {256, 48000, 12288000, 0xE0, 0x00, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
+ {256, 8000, 2048000, 0x60, 0x00, 0x31, 0x35, 0x08, 0x19, 0x1F, 0x7F},
+ {256, 16000, 4096000, 0x20, 0x00, 0x01, 0x35, 0x08, 0x19, 0x1F, 0x3F},
+ {256, 44100, 11289600, 0xE0, 0x01, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
+ {256, 48000, 12288000, 0xE0, 0x01, 0x01, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
{288, 8000, 2304000, 0x20, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x23, 0x47},
{384, 8000, 3072000, 0x60, 0x02, 0x05, 0x75, 0x8A, 0x1B, 0x1F, 0x7F},
{384, 16000, 6144000, 0x20, 0x02, 0x03, 0x35, 0x8A, 0x1B, 0x1F, 0x3F},
@@ -435,10 +435,10 @@ static const struct _coeff_div coeff_div_v3[] = {
{400, 48000, 19200000, 0xE4, 0x04, 0x35, 0x6d, 0xCA, 0x0A, 0x1F, 0x1F},
{500, 48000, 24000000, 0xF8, 0x04, 0x3F, 0x6D, 0xCA, 0x0A, 0x1F, 0x1F},
- {512, 8000, 4096000, 0x60, 0x00, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x7F},
- {512, 16000, 8192000, 0x20, 0x00, 0x30, 0x35, 0x8A, 0x1B, 0x1F, 0x3F},
- {512, 44100, 22579200, 0xE0, 0x00, 0x00, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
- {512, 48000, 24576000, 0xE0, 0x00, 0x00, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
+ {512, 8000, 4096000, 0x60, 0x00, 0x01, 0x08, 0x19, 0x1B, 0x1F, 0x7F},
+ {512, 16000, 8192000, 0x20, 0x00, 0x30, 0x35, 0x08, 0x19, 0x1F, 0x3F},
+ {512, 44100, 22579200, 0xE0, 0x00, 0x00, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
+ {512, 48000, 24576000, 0xE0, 0x00, 0x00, 0x2D, 0x48, 0x08, 0x1F, 0x1F},
{768, 8000, 6144000, 0x60, 0x02, 0x11, 0x35, 0x8A, 0x1B, 0x1F, 0x7F},
{768, 16000, 12288000, 0x20, 0x02, 0x01, 0x35, 0x8A, 0x1B, 0x1F, 0x3F},
{768, 32000, 24576000, 0xE0, 0x02, 0x30, 0x2D, 0xCA, 0x0A, 0x1F, 0x1F},
@@ -835,7 +835,6 @@ static void es8326_jack_detect_handler(struct work_struct *work)
dev_dbg(comp->dev, "Report hp remove event\n");
snd_soc_jack_report(es8326->jack, 0, SND_JACK_HEADSET);
/* mute adc when mic path switch */
- regmap_write(es8326->regmap, ES8326_ADC_SCALE, 0x33);
regmap_write(es8326->regmap, ES8326_ADC1_SRC, 0x44);
regmap_write(es8326->regmap, ES8326_ADC2_SRC, 0x66);
es8326->hp = 0;
@@ -843,6 +842,7 @@ static void es8326_jack_detect_handler(struct work_struct *work)
regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
regmap_write(es8326->regmap, ES8326_SYS_BIAS, 0x0a);
regmap_update_bits(es8326->regmap, ES8326_HP_DRIVER_REF, 0x0f, 0x03);
+ regmap_write(es8326->regmap, ES8326_INT_SOURCE, ES8326_INT_SRC_PIN9);
/*
* Inverted HPJACK_POL bit to trigger one IRQ to double check HP Removal event
*/
@@ -865,6 +865,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
* set auto-check mode, then restart jack_detect_work after 400ms.
* Don't report jack status.
*/
+ regmap_write(es8326->regmap, ES8326_INT_SOURCE,
+ (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x01);
es8326_enable_micbias(es8326->component);
usleep_range(50000, 70000);
@@ -891,7 +893,6 @@ static void es8326_jack_detect_handler(struct work_struct *work)
snd_soc_jack_report(es8326->jack,
SND_JACK_HEADSET, SND_JACK_HEADSET);
- regmap_write(es8326->regmap, ES8326_ADC_SCALE, 0x33);
regmap_update_bits(es8326->regmap, ES8326_PGA_PDN,
0x08, 0x08);
regmap_update_bits(es8326->regmap, ES8326_PGAGAIN,
@@ -987,7 +988,7 @@ static int es8326_resume(struct snd_soc_component *component)
regmap_write(es8326->regmap, ES8326_VMIDSEL, 0x0E);
regmap_write(es8326->regmap, ES8326_ANA_LP, 0xf0);
usleep_range(10000, 15000);
- regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xe9);
+ regmap_write(es8326->regmap, ES8326_HPJACK_TIMER, 0xd9);
regmap_write(es8326->regmap, ES8326_ANA_MICBIAS, 0xcb);
/* set headphone default type and detect pin */
regmap_write(es8326->regmap, ES8326_HPDET_TYPE, 0x83);
@@ -1038,8 +1039,7 @@ static int es8326_resume(struct snd_soc_component *component)
es8326_enable_micbias(es8326->component);
usleep_range(50000, 70000);
regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
- regmap_write(es8326->regmap, ES8326_INT_SOURCE,
- (ES8326_INT_SRC_PIN9 | ES8326_INT_SRC_BUTTON));
+ regmap_write(es8326->regmap, ES8326_INT_SOURCE, ES8326_INT_SRC_PIN9);
regmap_write(es8326->regmap, ES8326_INTOUT_IO,
es8326->interrupt_clk);
regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
@@ -1060,6 +1060,8 @@ static int es8326_resume(struct snd_soc_component *component)
es8326->hp = 0;
es8326->hpl_vol = 0x03;
es8326->hpr_vol = 0x03;
+
+ es8326_irq(es8326->irq, es8326);
return 0;
}
@@ -1070,6 +1072,9 @@ static int es8326_suspend(struct snd_soc_component *component)
cancel_delayed_work_sync(&es8326->jack_detect_work);
es8326_disable_micbias(component);
es8326->calibrated = false;
+ regmap_write(es8326->regmap, ES8326_CLK_MUX, 0x2d);
+ regmap_write(es8326->regmap, ES8326_DAC2HPMIX, 0x00);
+ regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x3b);
regmap_write(es8326->regmap, ES8326_CLK_CTL, ES8326_CLK_OFF);
regcache_cache_only(es8326->regmap, true);
regcache_mark_dirty(es8326->regmap);
diff --git a/sound/soc/codecs/es8326.h b/sound/soc/codecs/es8326.h
index ee12caef8105..c3e52e7bdef5 100644
--- a/sound/soc/codecs/es8326.h
+++ b/sound/soc/codecs/es8326.h
@@ -104,7 +104,7 @@
#define ES8326_MUTE (3 << 0)
/* ES8326_CLK_CTL */
-#define ES8326_CLK_ON (0x7e << 0)
+#define ES8326_CLK_ON (0x7f << 0)
#define ES8326_CLK_OFF (0 << 0)
/* ES8326_CLK_INV */
diff --git a/sound/soc/codecs/rt1316-sdw.c b/sound/soc/codecs/rt1316-sdw.c
index 47511f70119a..0b3bf920bcab 100644
--- a/sound/soc/codecs/rt1316-sdw.c
+++ b/sound/soc/codecs/rt1316-sdw.c
@@ -537,7 +537,7 @@ static int rt1316_sdw_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt1316->sdw_slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -577,12 +577,12 @@ static int rt1316_sdw_parse_dt(struct rt1316_sdw_priv *rt1316, struct device *de
if (rt1316->bq_params_cnt) {
rt1316->bq_params = devm_kzalloc(dev, rt1316->bq_params_cnt, GFP_KERNEL);
if (!rt1316->bq_params) {
- dev_err(dev, "Could not allocate bq_params memory\n");
+ dev_err(dev, "%s: Could not allocate bq_params memory\n", __func__);
ret = -ENOMEM;
} else {
ret = device_property_read_u8_array(dev, "realtek,bq-params", rt1316->bq_params, rt1316->bq_params_cnt);
if (ret < 0)
- dev_err(dev, "Could not read list of realtek,bq-params\n");
+ dev_err(dev, "%s: Could not read list of realtek,bq-params\n", __func__);
}
}
@@ -759,7 +759,7 @@ static int __maybe_unused rt1316_dev_resume(struct device *dev)
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT1316_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt1318-sdw.c b/sound/soc/codecs/rt1318-sdw.c
index ff364bde4a08..462c9a4b1be5 100644
--- a/sound/soc/codecs/rt1318-sdw.c
+++ b/sound/soc/codecs/rt1318-sdw.c
@@ -606,7 +606,7 @@ static int rt1318_sdw_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt1318->sdw_slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -631,8 +631,8 @@ static int rt1318_sdw_hw_params(struct snd_pcm_substream *substream,
sampling_rate = RT1318_SDCA_RATE_192000HZ;
break;
default:
- dev_err(component->dev, "Rate %d is not supported\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Rate %d is not supported\n",
+ __func__, params_rate(params));
return -EINVAL;
}
@@ -835,7 +835,7 @@ static int __maybe_unused rt1318_dev_resume(struct device *dev)
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT1318_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
return -ETIMEDOUT;
}
diff --git a/sound/soc/codecs/rt5682-sdw.c b/sound/soc/codecs/rt5682-sdw.c
index e67c2e19cb1a..f9ee42c13dba 100644
--- a/sound/soc/codecs/rt5682-sdw.c
+++ b/sound/soc/codecs/rt5682-sdw.c
@@ -132,7 +132,7 @@ static int rt5682_sdw_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt5682->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -315,8 +315,8 @@ static int rt5682_sdw_init(struct device *dev, struct regmap *regmap,
&rt5682_sdw_indirect_regmap);
if (IS_ERR(rt5682->regmap)) {
ret = PTR_ERR(rt5682->regmap);
- dev_err(dev, "Failed to allocate register map: %d\n",
- ret);
+ dev_err(dev, "%s: Failed to allocate register map: %d\n",
+ __func__, ret);
return ret;
}
@@ -400,7 +400,7 @@ static int rt5682_io_init(struct device *dev, struct sdw_slave *slave)
}
if (val != DEVICE_ID) {
- dev_err(dev, "Device with ID register %x is not rt5682\n", val);
+ dev_err(dev, "%s: Device with ID register %x is not rt5682\n", __func__, val);
ret = -ENODEV;
goto err_nodev;
}
@@ -648,7 +648,7 @@ static int rt5682_bus_config(struct sdw_slave *slave,
ret = rt5682_clock_config(&slave->dev);
if (ret < 0)
- dev_err(&slave->dev, "Invalid clk config");
+ dev_err(&slave->dev, "%s: Invalid clk config", __func__);
return ret;
}
@@ -763,19 +763,19 @@ static int __maybe_unused rt5682_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt5682->disable_irq_lock);
if (rt5682->disable_irq == true) {
- mutex_lock(&rt5682->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF);
rt5682->disable_irq = false;
- mutex_unlock(&rt5682->disable_irq_lock);
}
+ mutex_unlock(&rt5682->disable_irq_lock);
goto regmap_sync;
}
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT5682_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt700.c b/sound/soc/codecs/rt700.c
index 0ebf344a1b60..434b926f96c8 100644
--- a/sound/soc/codecs/rt700.c
+++ b/sound/soc/codecs/rt700.c
@@ -37,8 +37,8 @@ static int rt700_index_write(struct regmap *regmap,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ pr_err("%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -52,8 +52,8 @@ static int rt700_index_read(struct regmap *regmap,
*value = 0;
ret = regmap_read(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ pr_err("%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -930,14 +930,14 @@ static int rt700_pcm_hw_params(struct snd_pcm_substream *substream,
port_config.num += 2;
break;
default:
- dev_err(component->dev, "Invalid DAI id %d\n", dai->id);
+ dev_err(component->dev, "%s: Invalid DAI id %d\n", __func__, dai->id);
return -EINVAL;
}
retval = sdw_stream_add_slave(rt700->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -945,8 +945,8 @@ static int rt700_pcm_hw_params(struct snd_pcm_substream *substream,
/* bit 3:0 Number of Channel */
val |= (params_channels(params) - 1);
} else {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt711-sdca-sdw.c b/sound/soc/codecs/rt711-sdca-sdw.c
index 935e597022d3..2636c2eea4bc 100644
--- a/sound/soc/codecs/rt711-sdca-sdw.c
+++ b/sound/soc/codecs/rt711-sdca-sdw.c
@@ -438,20 +438,20 @@ static int __maybe_unused rt711_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt711->disable_irq_lock);
if (rt711->disable_irq == true) {
- mutex_lock(&rt711->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt711->disable_irq = false;
- mutex_unlock(&rt711->disable_irq_lock);
}
+ mutex_unlock(&rt711->disable_irq_lock);
goto regmap_sync;
}
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT711_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt711-sdca.c b/sound/soc/codecs/rt711-sdca.c
index 447154cb6010..1e8dbfc3ecd9 100644
--- a/sound/soc/codecs/rt711-sdca.c
+++ b/sound/soc/codecs/rt711-sdca.c
@@ -36,8 +36,8 @@ static int rt711_sdca_index_write(struct rt711_sdca_priv *rt711,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
dev_err(&rt711->slave->dev,
- "Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ "%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -52,8 +52,8 @@ static int rt711_sdca_index_read(struct rt711_sdca_priv *rt711,
ret = regmap_read(regmap, addr, value);
if (ret < 0)
dev_err(&rt711->slave->dev,
- "Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ "%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -1293,13 +1293,13 @@ static int rt711_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt711->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
if (params_channels(params) > 16) {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
@@ -1318,8 +1318,8 @@ static int rt711_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
sampling_rate = RT711_SDCA_RATE_192000HZ;
break;
default:
- dev_err(component->dev, "Rate %d is not supported\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Rate %d is not supported\n",
+ __func__, params_rate(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt711-sdw.c b/sound/soc/codecs/rt711-sdw.c
index 3f5773310ae8..0d3b43dd22e6 100644
--- a/sound/soc/codecs/rt711-sdw.c
+++ b/sound/soc/codecs/rt711-sdw.c
@@ -408,7 +408,7 @@ static int rt711_bus_config(struct sdw_slave *slave,
ret = rt711_clock_config(&slave->dev);
if (ret < 0)
- dev_err(&slave->dev, "Invalid clk config");
+ dev_err(&slave->dev, "%s: Invalid clk config", __func__);
return ret;
}
@@ -536,19 +536,19 @@ static int __maybe_unused rt711_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt711->disable_irq_lock);
if (rt711->disable_irq == true) {
- mutex_lock(&rt711->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_INTMASK1, SDW_SCP_INT1_IMPL_DEF);
rt711->disable_irq = false;
- mutex_unlock(&rt711->disable_irq_lock);
}
+ mutex_unlock(&rt711->disable_irq_lock);
goto regmap_sync;
}
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT711_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
return -ETIMEDOUT;
}
diff --git a/sound/soc/codecs/rt711.c b/sound/soc/codecs/rt711.c
index 66eaed13b0d6..5446f9506a16 100644
--- a/sound/soc/codecs/rt711.c
+++ b/sound/soc/codecs/rt711.c
@@ -37,8 +37,8 @@ static int rt711_index_write(struct regmap *regmap,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ pr_err("%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -52,8 +52,8 @@ static int rt711_index_read(struct regmap *regmap,
*value = 0;
ret = regmap_read(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ pr_err("%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -428,7 +428,7 @@ static void rt711_jack_init(struct rt711_priv *rt711)
RT711_HP_JD_FINAL_RESULT_CTL_JD12);
break;
default:
- dev_warn(rt711->component->dev, "Wrong JD source\n");
+ dev_warn(rt711->component->dev, "%s: Wrong JD source\n", __func__);
break;
}
@@ -1020,7 +1020,7 @@ static int rt711_pcm_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt711->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -1028,8 +1028,8 @@ static int rt711_pcm_hw_params(struct snd_pcm_substream *substream,
/* bit 3:0 Number of Channel */
val |= (params_channels(params) - 1);
} else {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt712-sdca-dmic.c b/sound/soc/codecs/rt712-sdca-dmic.c
index 0926b26619bd..012b79e72cf6 100644
--- a/sound/soc/codecs/rt712-sdca-dmic.c
+++ b/sound/soc/codecs/rt712-sdca-dmic.c
@@ -139,8 +139,8 @@ static int rt712_sdca_dmic_index_write(struct rt712_sdca_dmic_priv *rt712,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
dev_err(&rt712->slave->dev,
- "Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ "%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -155,8 +155,8 @@ static int rt712_sdca_dmic_index_read(struct rt712_sdca_dmic_priv *rt712,
ret = regmap_read(regmap, addr, value);
if (ret < 0)
dev_err(&rt712->slave->dev,
- "Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ "%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -317,7 +317,8 @@ static int rt712_sdca_dmic_set_gain_put(struct snd_kcontrol *kcontrol,
for (i = 0; i < p->count; i++) {
err = regmap_write(rt712->mbq_regmap, p->reg_base + i, gain_val[i]);
if (err < 0)
- dev_err(&rt712->slave->dev, "0x%08x can't be set\n", p->reg_base + i);
+ dev_err(&rt712->slave->dev, "%s: 0x%08x can't be set\n",
+ __func__, p->reg_base + i);
}
return changed;
@@ -667,13 +668,13 @@ static int rt712_sdca_dmic_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt712->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
if (params_channels(params) > 4) {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
@@ -698,8 +699,8 @@ static int rt712_sdca_dmic_hw_params(struct snd_pcm_substream *substream,
sampling_rate = RT712_SDCA_RATE_192000HZ;
break;
default:
- dev_err(component->dev, "Rate %d is not supported\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Rate %d is not supported\n",
+ __func__, params_rate(params));
return -EINVAL;
}
@@ -923,7 +924,8 @@ static int __maybe_unused rt712_sdca_dmic_dev_resume(struct device *dev)
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT712_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n",
+ __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt712-sdca-sdw.c b/sound/soc/codecs/rt712-sdca-sdw.c
index 01ac555cd79b..4e9ab3ef135b 100644
--- a/sound/soc/codecs/rt712-sdca-sdw.c
+++ b/sound/soc/codecs/rt712-sdca-sdw.c
@@ -438,20 +438,21 @@ static int __maybe_unused rt712_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt712->disable_irq_lock);
if (rt712->disable_irq == true) {
- mutex_lock(&rt712->disable_irq_lock);
+
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_0);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt712->disable_irq = false;
- mutex_unlock(&rt712->disable_irq_lock);
}
+ mutex_unlock(&rt712->disable_irq_lock);
goto regmap_sync;
}
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT712_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt712-sdca.c b/sound/soc/codecs/rt712-sdca.c
index 6954fbe7ec5f..b503de9fda80 100644
--- a/sound/soc/codecs/rt712-sdca.c
+++ b/sound/soc/codecs/rt712-sdca.c
@@ -34,8 +34,8 @@ static int rt712_sdca_index_write(struct rt712_sdca_priv *rt712,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
dev_err(&rt712->slave->dev,
- "Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ "%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -50,8 +50,8 @@ static int rt712_sdca_index_read(struct rt712_sdca_priv *rt712,
ret = regmap_read(regmap, addr, value);
if (ret < 0)
dev_err(&rt712->slave->dev,
- "Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ "%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -1060,13 +1060,13 @@ static int rt712_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt712->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
if (params_channels(params) > 16) {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
@@ -1085,8 +1085,8 @@ static int rt712_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
sampling_rate = RT712_SDCA_RATE_192000HZ;
break;
default:
- dev_err(component->dev, "Rate %d is not supported\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Rate %d is not supported\n",
+ __func__, params_rate(params));
return -EINVAL;
}
@@ -1106,7 +1106,7 @@ static int rt712_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
sampling_rate);
break;
default:
- dev_err(component->dev, "Wrong DAI id\n");
+ dev_err(component->dev, "%s: Wrong DAI id\n", __func__);
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt715-sdca-sdw.c b/sound/soc/codecs/rt715-sdca-sdw.c
index ab54a67a27eb..ee450126106f 100644
--- a/sound/soc/codecs/rt715-sdca-sdw.c
+++ b/sound/soc/codecs/rt715-sdca-sdw.c
@@ -237,7 +237,7 @@ static int __maybe_unused rt715_dev_resume(struct device *dev)
time = wait_for_completion_timeout(&slave->enumeration_complete,
msecs_to_jiffies(RT715_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Enumeration not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Enumeration not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt715-sdca.c b/sound/soc/codecs/rt715-sdca.c
index 4533eedd7e18..3fb7b9adb61d 100644
--- a/sound/soc/codecs/rt715-sdca.c
+++ b/sound/soc/codecs/rt715-sdca.c
@@ -41,8 +41,8 @@ static int rt715_sdca_index_write(struct rt715_sdca_priv *rt715,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
dev_err(&rt715->slave->dev,
- "Failed to set private value: %08x <= %04x %d\n",
- addr, value, ret);
+ "%s: Failed to set private value: %08x <= %04x %d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -59,8 +59,8 @@ static int rt715_sdca_index_read(struct rt715_sdca_priv *rt715,
ret = regmap_read(regmap, addr, value);
if (ret < 0)
dev_err(&rt715->slave->dev,
- "Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ "%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -152,8 +152,8 @@ static int rt715_sdca_set_amp_gain_put(struct snd_kcontrol *kcontrol,
mc->shift);
ret = regmap_write(rt715->mbq_regmap, mc->reg + i, gain_val);
if (ret != 0) {
- dev_err(component->dev, "Failed to write 0x%x=0x%x\n",
- mc->reg + i, gain_val);
+ dev_err(component->dev, "%s: Failed to write 0x%x=0x%x\n",
+ __func__, mc->reg + i, gain_val);
return ret;
}
}
@@ -188,8 +188,8 @@ static int rt715_sdca_set_amp_gain_4ch_put(struct snd_kcontrol *kcontrol,
ret = regmap_write(rt715->mbq_regmap, reg_base + i,
gain_val);
if (ret != 0) {
- dev_err(component->dev, "Failed to write 0x%x=0x%x\n",
- reg_base + i, gain_val);
+ dev_err(component->dev, "%s: Failed to write 0x%x=0x%x\n",
+ __func__, reg_base + i, gain_val);
return ret;
}
}
@@ -224,8 +224,8 @@ static int rt715_sdca_set_amp_gain_8ch_put(struct snd_kcontrol *kcontrol,
reg = i < 7 ? reg_base + i : (reg_base - 1) | BIT(15);
ret = regmap_write(rt715->mbq_regmap, reg, gain_val);
if (ret != 0) {
- dev_err(component->dev, "Failed to write 0x%x=0x%x\n",
- reg, gain_val);
+ dev_err(component->dev, "%s: Failed to write 0x%x=0x%x\n",
+ __func__, reg, gain_val);
return ret;
}
}
@@ -246,8 +246,8 @@ static int rt715_sdca_set_amp_gain_get(struct snd_kcontrol *kcontrol,
for (i = 0; i < 2; i++) {
ret = regmap_read(rt715->mbq_regmap, mc->reg + i, &val);
if (ret < 0) {
- dev_err(component->dev, "Failed to read 0x%x, ret=%d\n",
- mc->reg + i, ret);
+ dev_err(component->dev, "%s: Failed to read 0x%x, ret=%d\n",
+ __func__, mc->reg + i, ret);
return ret;
}
ucontrol->value.integer.value[i] = rt715_sdca_get_gain(val, mc->shift);
@@ -271,8 +271,8 @@ static int rt715_sdca_set_amp_gain_4ch_get(struct snd_kcontrol *kcontrol,
for (i = 0; i < 4; i++) {
ret = regmap_read(rt715->mbq_regmap, reg_base + i, &val);
if (ret < 0) {
- dev_err(component->dev, "Failed to read 0x%x, ret=%d\n",
- reg_base + i, ret);
+ dev_err(component->dev, "%s: Failed to read 0x%x, ret=%d\n",
+ __func__, reg_base + i, ret);
return ret;
}
ucontrol->value.integer.value[i] = rt715_sdca_get_gain(val, gain_sft);
@@ -297,8 +297,8 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol,
for (i = 0; i < 8; i += 2) {
ret = regmap_read(rt715->mbq_regmap, reg_base + i, &val_l);
if (ret < 0) {
- dev_err(component->dev, "Failed to read 0x%x, ret=%d\n",
- reg_base + i, ret);
+ dev_err(component->dev, "%s: Failed to read 0x%x, ret=%d\n",
+ __func__, reg_base + i, ret);
return ret;
}
ucontrol->value.integer.value[i] = (val_l >> gain_sft) / 10;
@@ -306,8 +306,8 @@ static int rt715_sdca_set_amp_gain_8ch_get(struct snd_kcontrol *kcontrol,
reg = (i == 6) ? (reg_base - 1) | BIT(15) : reg_base + 1 + i;
ret = regmap_read(rt715->mbq_regmap, reg, &val_r);
if (ret < 0) {
- dev_err(component->dev, "Failed to read 0x%x, ret=%d\n",
- reg, ret);
+ dev_err(component->dev, "%s: Failed to read 0x%x, ret=%d\n",
+ __func__, reg, ret);
return ret;
}
ucontrol->value.integer.value[i + 1] = (val_r >> gain_sft) / 10;
@@ -834,15 +834,15 @@ static int rt715_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
0xaf00);
break;
default:
- dev_err(component->dev, "Invalid DAI id %d\n", dai->id);
+ dev_err(component->dev, "%s: Invalid DAI id %d\n", __func__, dai->id);
return -EINVAL;
}
retval = sdw_stream_add_slave(rt715->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(component->dev, "Unable to configure port, retval:%d\n",
- retval);
+ dev_err(component->dev, "%s: Unable to configure port, retval:%d\n",
+ __func__, retval);
return retval;
}
@@ -893,8 +893,8 @@ static int rt715_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
val = 0xf;
break;
default:
- dev_err(component->dev, "Unsupported sample rate %d\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Unsupported sample rate %d\n",
+ __func__, params_rate(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt715-sdw.c b/sound/soc/codecs/rt715-sdw.c
index 21f37babd148..7e13868ff99f 100644
--- a/sound/soc/codecs/rt715-sdw.c
+++ b/sound/soc/codecs/rt715-sdw.c
@@ -482,7 +482,7 @@ static int rt715_bus_config(struct sdw_slave *slave,
ret = rt715_clock_config(&slave->dev);
if (ret < 0)
- dev_err(&slave->dev, "Invalid clk config");
+ dev_err(&slave->dev, "%s: Invalid clk config", __func__);
return 0;
}
@@ -554,7 +554,7 @@ static int __maybe_unused rt715_dev_resume(struct device *dev)
time = wait_for_completion_timeout(&slave->initialization_complete,
msecs_to_jiffies(RT715_PROBE_TIMEOUT));
if (!time) {
- dev_err(&slave->dev, "Initialization not complete, timed out\n");
+ dev_err(&slave->dev, "%s: Initialization not complete, timed out\n", __func__);
sdw_show_ping_status(slave->bus, true);
return -ETIMEDOUT;
diff --git a/sound/soc/codecs/rt715.c b/sound/soc/codecs/rt715.c
index 9f732a5abd53..299c9b12377c 100644
--- a/sound/soc/codecs/rt715.c
+++ b/sound/soc/codecs/rt715.c
@@ -40,8 +40,8 @@ static int rt715_index_write(struct regmap *regmap, unsigned int reg,
ret = regmap_write(regmap, addr, value);
if (ret < 0) {
- pr_err("Failed to set private value: %08x <= %04x %d\n",
- addr, value, ret);
+ pr_err("%s: Failed to set private value: %08x <= %04x %d\n",
+ __func__, addr, value, ret);
}
return ret;
@@ -55,8 +55,8 @@ static int rt715_index_write_nid(struct regmap *regmap,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ pr_err("%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -70,8 +70,8 @@ static int rt715_index_read_nid(struct regmap *regmap,
*value = 0;
ret = regmap_read(regmap, addr, value);
if (ret < 0)
- pr_err("Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ pr_err("%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -862,14 +862,14 @@ static int rt715_pcm_hw_params(struct snd_pcm_substream *substream,
rt715_index_write(rt715->regmap, RT715_SDW_INPUT_SEL, 0xa000);
break;
default:
- dev_err(component->dev, "Invalid DAI id %d\n", dai->id);
+ dev_err(component->dev, "%s: Invalid DAI id %d\n", __func__, dai->id);
return -EINVAL;
}
retval = sdw_stream_add_slave(rt715->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
@@ -883,8 +883,8 @@ static int rt715_pcm_hw_params(struct snd_pcm_substream *substream,
val |= 0x0 << 8;
break;
default:
- dev_err(component->dev, "Unsupported sample rate %d\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Unsupported sample rate %d\n",
+ __func__, params_rate(params));
return -EINVAL;
}
@@ -892,8 +892,8 @@ static int rt715_pcm_hw_params(struct snd_pcm_substream *substream,
/* bit 3:0 Number of Channel */
val |= (params_channels(params) - 1);
} else {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c
index eb76f4c675b6..65d584c1886e 100644
--- a/sound/soc/codecs/rt722-sdca-sdw.c
+++ b/sound/soc/codecs/rt722-sdca-sdw.c
@@ -467,13 +467,13 @@ static int __maybe_unused rt722_sdca_dev_resume(struct device *dev)
return 0;
if (!slave->unattach_request) {
+ mutex_lock(&rt722->disable_irq_lock);
if (rt722->disable_irq == true) {
- mutex_lock(&rt722->disable_irq_lock);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK1, SDW_SCP_SDCA_INTMASK_SDCA_6);
sdw_write_no_pm(slave, SDW_SCP_SDCA_INTMASK2, SDW_SCP_SDCA_INTMASK_SDCA_8);
rt722->disable_irq = false;
- mutex_unlock(&rt722->disable_irq_lock);
}
+ mutex_unlock(&rt722->disable_irq_lock);
goto regmap_sync;
}
diff --git a/sound/soc/codecs/rt722-sdca.c b/sound/soc/codecs/rt722-sdca.c
index 0e1c65a20392..e0ea3a23f7cc 100644
--- a/sound/soc/codecs/rt722-sdca.c
+++ b/sound/soc/codecs/rt722-sdca.c
@@ -35,8 +35,8 @@ int rt722_sdca_index_write(struct rt722_sdca_priv *rt722,
ret = regmap_write(regmap, addr, value);
if (ret < 0)
dev_err(&rt722->slave->dev,
- "Failed to set private value: %06x <= %04x ret=%d\n",
- addr, value, ret);
+ "%s: Failed to set private value: %06x <= %04x ret=%d\n",
+ __func__, addr, value, ret);
return ret;
}
@@ -51,8 +51,8 @@ int rt722_sdca_index_read(struct rt722_sdca_priv *rt722,
ret = regmap_read(regmap, addr, value);
if (ret < 0)
dev_err(&rt722->slave->dev,
- "Failed to get private value: %06x => %04x ret=%d\n",
- addr, *value, ret);
+ "%s: Failed to get private value: %06x => %04x ret=%d\n",
+ __func__, addr, *value, ret);
return ret;
}
@@ -663,7 +663,8 @@ static int rt722_sdca_dmic_set_gain_put(struct snd_kcontrol *kcontrol,
for (i = 0; i < p->count; i++) {
err = regmap_write(rt722->mbq_regmap, p->reg_base + i, gain_val[i]);
if (err < 0)
- dev_err(&rt722->slave->dev, "%#08x can't be set\n", p->reg_base + i);
+ dev_err(&rt722->slave->dev, "%s: %#08x can't be set\n",
+ __func__, p->reg_base + i);
}
return changed;
@@ -1211,13 +1212,13 @@ static int rt722_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
retval = sdw_stream_add_slave(rt722->slave, &stream_config,
&port_config, 1, sdw_stream);
if (retval) {
- dev_err(dai->dev, "Unable to configure port\n");
+ dev_err(dai->dev, "%s: Unable to configure port\n", __func__);
return retval;
}
if (params_channels(params) > 16) {
- dev_err(component->dev, "Unsupported channels %d\n",
- params_channels(params));
+ dev_err(component->dev, "%s: Unsupported channels %d\n",
+ __func__, params_channels(params));
return -EINVAL;
}
@@ -1236,8 +1237,8 @@ static int rt722_sdca_pcm_hw_params(struct snd_pcm_substream *substream,
sampling_rate = RT722_SDCA_RATE_192000HZ;
break;
default:
- dev_err(component->dev, "Rate %d is not supported\n",
- params_rate(params));
+ dev_err(component->dev, "%s: Rate %d is not supported\n",
+ __func__, params_rate(params));
return -EINVAL;
}
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index e451c009f2d9..7d5c096e06cd 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -683,11 +683,12 @@ static void wm_adsp_control_remove(struct cs_dsp_coeff_ctl *cs_ctl)
int wm_adsp_write_ctl(struct wm_adsp *dsp, const char *name, int type,
unsigned int alg, void *buf, size_t len)
{
- struct cs_dsp_coeff_ctl *cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg);
+ struct cs_dsp_coeff_ctl *cs_ctl;
struct wm_coeff_ctl *ctl;
int ret;
mutex_lock(&dsp->cs_dsp.pwr_lock);
+ cs_ctl = cs_dsp_get_ctl(&dsp->cs_dsp, name, type, alg);
ret = cs_dsp_coeff_write_ctrl(cs_ctl, 0, buf, len);
mutex_unlock(&dsp->cs_dsp.pwr_lock);
diff --git a/sound/soc/intel/avs/boards/da7219.c b/sound/soc/intel/avs/boards/da7219.c
index c018f84fe025..fc072dc58968 100644
--- a/sound/soc/intel/avs/boards/da7219.c
+++ b/sound/soc/intel/avs/boards/da7219.c
@@ -296,5 +296,6 @@ static struct platform_driver avs_da7219_driver = {
module_platform_driver(avs_da7219_driver);
+MODULE_DESCRIPTION("Intel da7219 machine driver");
MODULE_AUTHOR("Cezary Rojewski <cezary.rojewski@intel.com>");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/dmic.c b/sound/soc/intel/avs/boards/dmic.c
index ba2bc7f689eb..d9e5e85f5233 100644
--- a/sound/soc/intel/avs/boards/dmic.c
+++ b/sound/soc/intel/avs/boards/dmic.c
@@ -96,4 +96,5 @@ static struct platform_driver avs_dmic_driver = {
module_platform_driver(avs_dmic_driver);
+MODULE_DESCRIPTION("Intel DMIC machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/es8336.c b/sound/soc/intel/avs/boards/es8336.c
index 1090082e7d5b..5c90a6007577 100644
--- a/sound/soc/intel/avs/boards/es8336.c
+++ b/sound/soc/intel/avs/boards/es8336.c
@@ -326,4 +326,5 @@ static struct platform_driver avs_es8336_driver = {
module_platform_driver(avs_es8336_driver);
+MODULE_DESCRIPTION("Intel es8336 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/i2s_test.c b/sound/soc/intel/avs/boards/i2s_test.c
index 28f254eb0d03..027373d6a16d 100644
--- a/sound/soc/intel/avs/boards/i2s_test.c
+++ b/sound/soc/intel/avs/boards/i2s_test.c
@@ -204,4 +204,5 @@ static struct platform_driver avs_i2s_test_driver = {
module_platform_driver(avs_i2s_test_driver);
+MODULE_DESCRIPTION("Intel i2s test machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/max98357a.c b/sound/soc/intel/avs/boards/max98357a.c
index a83b95f25129..1ff85e4d8e16 100644
--- a/sound/soc/intel/avs/boards/max98357a.c
+++ b/sound/soc/intel/avs/boards/max98357a.c
@@ -154,4 +154,5 @@ static struct platform_driver avs_max98357a_driver = {
module_platform_driver(avs_max98357a_driver)
+MODULE_DESCRIPTION("Intel max98357a machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/max98373.c b/sound/soc/intel/avs/boards/max98373.c
index 3b980a025e6f..8d31586b73ea 100644
--- a/sound/soc/intel/avs/boards/max98373.c
+++ b/sound/soc/intel/avs/boards/max98373.c
@@ -211,4 +211,5 @@ static struct platform_driver avs_max98373_driver = {
module_platform_driver(avs_max98373_driver)
+MODULE_DESCRIPTION("Intel max98373 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/max98927.c b/sound/soc/intel/avs/boards/max98927.c
index 86dd2b228df3..572ec58073d0 100644
--- a/sound/soc/intel/avs/boards/max98927.c
+++ b/sound/soc/intel/avs/boards/max98927.c
@@ -208,4 +208,5 @@ static struct platform_driver avs_max98927_driver = {
module_platform_driver(avs_max98927_driver)
+MODULE_DESCRIPTION("Intel max98927 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/nau8825.c b/sound/soc/intel/avs/boards/nau8825.c
index 1c1e2083f474..55db75efae41 100644
--- a/sound/soc/intel/avs/boards/nau8825.c
+++ b/sound/soc/intel/avs/boards/nau8825.c
@@ -313,4 +313,5 @@ static struct platform_driver avs_nau8825_driver = {
module_platform_driver(avs_nau8825_driver)
+MODULE_DESCRIPTION("Intel nau8825 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/probe.c b/sound/soc/intel/avs/boards/probe.c
index a9469b5ecb40..8be6887bbc6e 100644
--- a/sound/soc/intel/avs/boards/probe.c
+++ b/sound/soc/intel/avs/boards/probe.c
@@ -69,4 +69,5 @@ static struct platform_driver avs_probe_mb_driver = {
module_platform_driver(avs_probe_mb_driver);
+MODULE_DESCRIPTION("Intel probe machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt274.c b/sound/soc/intel/avs/boards/rt274.c
index bfcb8845fd15..1cf524216087 100644
--- a/sound/soc/intel/avs/boards/rt274.c
+++ b/sound/soc/intel/avs/boards/rt274.c
@@ -276,4 +276,5 @@ static struct platform_driver avs_rt274_driver = {
module_platform_driver(avs_rt274_driver);
+MODULE_DESCRIPTION("Intel rt274 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt286.c b/sound/soc/intel/avs/boards/rt286.c
index 28d7d86b1cc9..4740bba10570 100644
--- a/sound/soc/intel/avs/boards/rt286.c
+++ b/sound/soc/intel/avs/boards/rt286.c
@@ -247,4 +247,5 @@ static struct platform_driver avs_rt286_driver = {
module_platform_driver(avs_rt286_driver);
+MODULE_DESCRIPTION("Intel rt286 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt298.c b/sound/soc/intel/avs/boards/rt298.c
index 80f490b9e118..6e409e29f697 100644
--- a/sound/soc/intel/avs/boards/rt298.c
+++ b/sound/soc/intel/avs/boards/rt298.c
@@ -266,4 +266,5 @@ static struct platform_driver avs_rt298_driver = {
module_platform_driver(avs_rt298_driver);
+MODULE_DESCRIPTION("Intel rt298 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt5514.c b/sound/soc/intel/avs/boards/rt5514.c
index 60105f453ae2..097ae5f73241 100644
--- a/sound/soc/intel/avs/boards/rt5514.c
+++ b/sound/soc/intel/avs/boards/rt5514.c
@@ -192,4 +192,5 @@ static struct platform_driver avs_rt5514_driver = {
module_platform_driver(avs_rt5514_driver);
+MODULE_DESCRIPTION("Intel rt5514 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt5663.c b/sound/soc/intel/avs/boards/rt5663.c
index b4762c2a7bf2..1880c315cc4d 100644
--- a/sound/soc/intel/avs/boards/rt5663.c
+++ b/sound/soc/intel/avs/boards/rt5663.c
@@ -265,4 +265,5 @@ static struct platform_driver avs_rt5663_driver = {
module_platform_driver(avs_rt5663_driver);
+MODULE_DESCRIPTION("Intel rt5663 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/rt5682.c b/sound/soc/intel/avs/boards/rt5682.c
index 243f979fda98..594a971ded9e 100644
--- a/sound/soc/intel/avs/boards/rt5682.c
+++ b/sound/soc/intel/avs/boards/rt5682.c
@@ -341,5 +341,6 @@ static struct platform_driver avs_rt5682_driver = {
module_platform_driver(avs_rt5682_driver)
+MODULE_DESCRIPTION("Intel rt5682 machine driver");
MODULE_AUTHOR("Cezary Rojewski <cezary.rojewski@intel.com>");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/intel/avs/boards/ssm4567.c b/sound/soc/intel/avs/boards/ssm4567.c
index 4a0e136835ff..d6f7f046c24e 100644
--- a/sound/soc/intel/avs/boards/ssm4567.c
+++ b/sound/soc/intel/avs/boards/ssm4567.c
@@ -200,4 +200,5 @@ static struct platform_driver avs_ssm4567_driver = {
module_platform_driver(avs_ssm4567_driver)
+MODULE_DESCRIPTION("Intel ssm4567 machine driver");
MODULE_LICENSE("GPL");
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 2d25748ca706..b27e89ff6a16 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -263,7 +263,7 @@ int snd_soc_get_volsw(struct snd_kcontrol *kcontrol,
int max = mc->max;
int min = mc->min;
int sign_bit = mc->sign_bit;
- unsigned int mask = (1 << fls(max)) - 1;
+ unsigned int mask = (1ULL << fls(max)) - 1;
unsigned int invert = mc->invert;
int val;
int ret;
diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
index be7dc1e02284..c12c7f820529 100644
--- a/sound/soc/sof/amd/acp.c
+++ b/sound/soc/sof/amd/acp.c
@@ -704,6 +704,10 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev)
goto unregister_dev;
}
+ ret = acp_init(sdev);
+ if (ret < 0)
+ goto free_smn_dev;
+
sdev->ipc_irq = pci->irq;
ret = request_threaded_irq(sdev->ipc_irq, acp_irq_handler, acp_irq_thread,
IRQF_SHARED, "AudioDSP", sdev);
@@ -713,10 +717,6 @@ int amd_sof_acp_probe(struct snd_sof_dev *sdev)
goto free_smn_dev;
}
- ret = acp_init(sdev);
- if (ret < 0)
- goto free_ipc_irq;
-
/* scan SoundWire capabilities exposed by DSDT */
ret = acp_sof_scan_sdw_devices(sdev, chip->sdw_acpi_dev_addr);
if (ret < 0) {
diff --git a/sound/soc/sof/core.c b/sound/soc/sof/core.c
index 9b00ede2a486..cc84d4c81be9 100644
--- a/sound/soc/sof/core.c
+++ b/sound/soc/sof/core.c
@@ -339,8 +339,7 @@ static int sof_init_environment(struct snd_sof_dev *sdev)
ret = snd_sof_probe(sdev);
if (ret < 0) {
dev_err(sdev->dev, "failed to probe DSP %d\n", ret);
- sof_ops_free(sdev);
- return ret;
+ goto err_sof_probe;
}
/* check machine info */
@@ -358,15 +357,18 @@ static int sof_init_environment(struct snd_sof_dev *sdev)
ret = validate_sof_ops(sdev);
if (ret < 0) {
snd_sof_remove(sdev);
+ snd_sof_remove_late(sdev);
return ret;
}
}
+ return 0;
+
err_machine_check:
- if (ret) {
- snd_sof_remove(sdev);
- sof_ops_free(sdev);
- }
+ snd_sof_remove(sdev);
+err_sof_probe:
+ snd_sof_remove_late(sdev);
+ sof_ops_free(sdev);
return ret;
}
diff --git a/sound/soc/sof/intel/hda-common-ops.c b/sound/soc/sof/intel/hda-common-ops.c
index 2b385cddc385..d71bb66b9991 100644
--- a/sound/soc/sof/intel/hda-common-ops.c
+++ b/sound/soc/sof/intel/hda-common-ops.c
@@ -57,6 +57,9 @@ struct snd_sof_dsp_ops sof_hda_common_ops = {
.pcm_pointer = hda_dsp_pcm_pointer,
.pcm_ack = hda_dsp_pcm_ack,
+ .get_dai_frame_counter = hda_dsp_get_stream_llp,
+ .get_host_byte_counter = hda_dsp_get_stream_ldp,
+
/* firmware loading */
.load_firmware = snd_sof_load_firmware_raw,
diff --git a/sound/soc/sof/intel/hda-dai-ops.c b/sound/soc/sof/intel/hda-dai-ops.c
index c50ca9e72d37..b073720b4cf4 100644
--- a/sound/soc/sof/intel/hda-dai-ops.c
+++ b/sound/soc/sof/intel/hda-dai-ops.c
@@ -7,6 +7,7 @@
#include <sound/pcm_params.h>
#include <sound/hdaudio_ext.h>
+#include <sound/hda_register.h>
#include <sound/hda-mlink.h>
#include <sound/sof/ipc4/header.h>
#include <uapi/sound/sof/header.h>
@@ -362,6 +363,16 @@ static int hda_trigger(struct snd_sof_dev *sdev, struct snd_soc_dai *cpu_dai,
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
snd_hdac_ext_stream_clear(hext_stream);
+
+ /*
+ * Save the LLP registers in case the stream is
+ * restarting due PAUSE_RELEASE, or START without a pcm
+ * close/open since in this case the LLP register is not reset
+ * to 0 and the delay calculation will return with invalid
+ * results.
+ */
+ hext_stream->pplcllpl = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+ hext_stream->pplcllpu = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
break;
default:
dev_err(sdev->dev, "unknown trigger command %d\n", cmd);
diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c
index 31ffa1a8f2ac..ef5c915db8ff 100644
--- a/sound/soc/sof/intel/hda-dsp.c
+++ b/sound/soc/sof/intel/hda-dsp.c
@@ -681,17 +681,27 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend)
struct sof_intel_hda_dev *hda = sdev->pdata->hw_pdata;
const struct sof_intel_dsp_desc *chip = hda->desc;
struct hdac_bus *bus = sof_to_bus(sdev);
+ bool imr_lost = false;
int ret, j;
/*
- * The memory used for IMR boot loses its content in deeper than S3 state
- * We must not try IMR boot on next power up (as it will fail).
- *
+ * The memory used for IMR boot loses its content in deeper than S3
+ * state on CAVS platforms.
+ * On ACE platforms due to the system architecture the IMR content is
+ * lost at S3 state already, they are tailored for s2idle use.
+ * We must not try IMR boot on next power up in these cases as it will
+ * fail.
+ */
+ if (sdev->system_suspend_target > SOF_SUSPEND_S3 ||
+ (chip->hw_ip_version >= SOF_INTEL_ACE_1_0 &&
+ sdev->system_suspend_target == SOF_SUSPEND_S3))
+ imr_lost = true;
+
+ /*
* In case of firmware crash or boot failure set the skip_imr_boot to true
* as well in order to try to re-load the firmware to do a 'cold' boot.
*/
- if (sdev->system_suspend_target > SOF_SUSPEND_S3 ||
- sdev->fw_state == SOF_FW_CRASHED ||
+ if (imr_lost || sdev->fw_state == SOF_FW_CRASHED ||
sdev->fw_state == SOF_FW_BOOT_FAILED)
hda->skip_imr_boot = true;
diff --git a/sound/soc/sof/intel/hda-pcm.c b/sound/soc/sof/intel/hda-pcm.c
index 18f07364d219..d7b446f3f973 100644
--- a/sound/soc/sof/intel/hda-pcm.c
+++ b/sound/soc/sof/intel/hda-pcm.c
@@ -259,8 +259,37 @@ int hda_dsp_pcm_open(struct snd_sof_dev *sdev,
snd_pcm_hw_constraint_mask64(substream->runtime, SNDRV_PCM_HW_PARAM_FORMAT,
SNDRV_PCM_FMTBIT_S16 | SNDRV_PCM_FMTBIT_S32);
+ /*
+ * The dsp_max_burst_size_in_ms is the length of the maximum burst size
+ * of the host DMA in the ALSA buffer.
+ *
+ * On playback start the DMA will transfer dsp_max_burst_size_in_ms
+ * amount of data in one initial burst to fill up the host DMA buffer.
+ * Consequent DMA burst sizes are shorter and their length can vary.
+ * To make sure that userspace allocate large enough ALSA buffer we need
+ * to place a constraint on the buffer time.
+ *
+ * On capture the DMA will transfer 1ms chunks.
+ *
+ * Exact dsp_max_burst_size_in_ms constraint is racy, so set the
+ * constraint to a minimum of 2x dsp_max_burst_size_in_ms.
+ */
+ if (spcm->stream[direction].dsp_max_burst_size_in_ms)
+ snd_pcm_hw_constraint_minmax(substream->runtime,
+ SNDRV_PCM_HW_PARAM_BUFFER_TIME,
+ spcm->stream[direction].dsp_max_burst_size_in_ms * USEC_PER_MSEC * 2,
+ UINT_MAX);
+
/* binding pcm substream to hda stream */
substream->runtime->private_data = &dsp_stream->hstream;
+
+ /*
+ * Reset the llp cache values (they are used for LLP compensation in
+ * case the counter is not reset)
+ */
+ dsp_stream->pplcllpl = 0;
+ dsp_stream->pplcllpu = 0;
+
return 0;
}
diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c
index b387b1a69d7e..0c189d3b19c1 100644
--- a/sound/soc/sof/intel/hda-stream.c
+++ b/sound/soc/sof/intel/hda-stream.c
@@ -1063,3 +1063,73 @@ snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
return pos;
}
+
+#define merge_u64(u32_u, u32_l) (((u64)(u32_u) << 32) | (u32_l))
+
+/**
+ * hda_dsp_get_stream_llp - Retrieve the LLP (Linear Link Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct hdac_stream *hstream = substream->runtime->private_data;
+ struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream);
+ u32 llp_l, llp_u;
+
+ /*
+ * The pplc_addr have been calculated during probe in
+ * hda_dsp_stream_init():
+ * pplc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+ * SOF_HDA_PPLC_BASE +
+ * SOF_HDA_PPLC_MULTI * total_stream +
+ * SOF_HDA_PPLC_INTERVAL * stream_index
+ *
+ * Use this pre-calculated address to avoid repeated re-calculation.
+ */
+ llp_l = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPL);
+ llp_u = readl(hext_stream->pplc_addr + AZX_REG_PPLCLLPU);
+
+ /* Compensate the LLP counter with the saved offset */
+ if (hext_stream->pplcllpl || hext_stream->pplcllpu)
+ return merge_u64(llp_u, llp_l) -
+ merge_u64(hext_stream->pplcllpu, hext_stream->pplcllpl);
+
+ return merge_u64(llp_u, llp_l);
+}
+
+/**
+ * hda_dsp_get_stream_ldp - Retrieve the LDP (Linear DMA Position) of the stream
+ * @sdev: SOF device
+ * @component: ASoC component
+ * @substream: PCM substream
+ *
+ * Returns the raw Linear Link Position value
+ */
+u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct hdac_stream *hstream = substream->runtime->private_data;
+ struct hdac_ext_stream *hext_stream = stream_to_hdac_ext_stream(hstream);
+ u32 ldp_l, ldp_u;
+
+ /*
+ * The pphc_addr have been calculated during probe in
+ * hda_dsp_stream_init():
+ * pphc_addr = sdev->bar[HDA_DSP_PP_BAR] +
+ * SOF_HDA_PPHC_BASE +
+ * SOF_HDA_PPHC_INTERVAL * stream_index
+ *
+ * Use this pre-calculated address to avoid repeated re-calculation.
+ */
+ ldp_l = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPL);
+ ldp_u = readl(hext_stream->pphc_addr + AZX_REG_PPHCLDPU);
+
+ return ((u64)ldp_u << 32) | ldp_l;
+}
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index b36eb7c78913..81a1d4606d3c 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -662,6 +662,12 @@ bool hda_dsp_check_stream_irq(struct snd_sof_dev *sdev);
snd_pcm_uframes_t hda_dsp_stream_get_position(struct hdac_stream *hstream,
int direction, bool can_sleep);
+u64 hda_dsp_get_stream_llp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream);
+u64 hda_dsp_get_stream_ldp(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream);
struct hdac_ext_stream *
hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction, u32 flags);
diff --git a/sound/soc/sof/intel/lnl.c b/sound/soc/sof/intel/lnl.c
index 7ae017a00184..aeb4350cce6b 100644
--- a/sound/soc/sof/intel/lnl.c
+++ b/sound/soc/sof/intel/lnl.c
@@ -29,15 +29,17 @@ static const struct snd_sof_debugfs_map lnl_dsp_debugfs[] = {
};
/* this helps allows the DSP to setup DMIC/SSP */
-static int hdac_bus_offload_dmic_ssp(struct hdac_bus *bus)
+static int hdac_bus_offload_dmic_ssp(struct hdac_bus *bus, bool enable)
{
int ret;
- ret = hdac_bus_eml_enable_offload(bus, true, AZX_REG_ML_LEPTR_ID_INTEL_SSP, true);
+ ret = hdac_bus_eml_enable_offload(bus, true,
+ AZX_REG_ML_LEPTR_ID_INTEL_SSP, enable);
if (ret < 0)
return ret;
- ret = hdac_bus_eml_enable_offload(bus, true, AZX_REG_ML_LEPTR_ID_INTEL_DMIC, true);
+ ret = hdac_bus_eml_enable_offload(bus, true,
+ AZX_REG_ML_LEPTR_ID_INTEL_DMIC, enable);
if (ret < 0)
return ret;
@@ -52,7 +54,19 @@ static int lnl_hda_dsp_probe(struct snd_sof_dev *sdev)
if (ret < 0)
return ret;
- return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev));
+ return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true);
+}
+
+static void lnl_hda_dsp_remove(struct snd_sof_dev *sdev)
+{
+ int ret;
+
+ ret = hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), false);
+ if (ret < 0)
+ dev_warn(sdev->dev,
+ "Failed to disable offload for DMIC/SSP: %d\n", ret);
+
+ hda_dsp_remove(sdev);
}
static int lnl_hda_dsp_resume(struct snd_sof_dev *sdev)
@@ -63,7 +77,7 @@ static int lnl_hda_dsp_resume(struct snd_sof_dev *sdev)
if (ret < 0)
return ret;
- return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev));
+ return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true);
}
static int lnl_hda_dsp_runtime_resume(struct snd_sof_dev *sdev)
@@ -74,7 +88,7 @@ static int lnl_hda_dsp_runtime_resume(struct snd_sof_dev *sdev)
if (ret < 0)
return ret;
- return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev));
+ return hdac_bus_offload_dmic_ssp(sof_to_bus(sdev), true);
}
static int lnl_dsp_post_fw_run(struct snd_sof_dev *sdev)
@@ -97,9 +111,11 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev)
/* common defaults */
memcpy(&sof_lnl_ops, &sof_hda_common_ops, sizeof(struct snd_sof_dsp_ops));
- /* probe */
- if (!sdev->dspless_mode_selected)
+ /* probe/remove */
+ if (!sdev->dspless_mode_selected) {
sof_lnl_ops.probe = lnl_hda_dsp_probe;
+ sof_lnl_ops.remove = lnl_hda_dsp_remove;
+ }
/* shutdown */
sof_lnl_ops.shutdown = hda_dsp_shutdown;
@@ -134,8 +150,6 @@ int sof_lnl_ops_init(struct snd_sof_dev *sdev)
sof_lnl_ops.runtime_resume = lnl_hda_dsp_runtime_resume;
}
- sof_lnl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
/* dsp core get/put */
sof_lnl_ops.core_get = mtl_dsp_core_get;
sof_lnl_ops.core_put = mtl_dsp_core_put;
diff --git a/sound/soc/sof/intel/mtl.c b/sound/soc/sof/intel/mtl.c
index df05dc77b8d5..060c34988e90 100644
--- a/sound/soc/sof/intel/mtl.c
+++ b/sound/soc/sof/intel/mtl.c
@@ -626,18 +626,6 @@ static int mtl_dsp_disable_interrupts(struct snd_sof_dev *sdev)
return mtl_enable_interrupts(sdev, false);
}
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
-{
- struct hdac_stream *hstream = substream->runtime->private_data;
- u32 llp_l, llp_u;
-
- llp_l = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPL(hstream->index));
- llp_u = snd_sof_dsp_read(sdev, HDA_DSP_HDA_BAR, MTL_PPLCLLPU(hstream->index));
- return ((u64)llp_u << 32) | llp_l;
-}
-
int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core)
{
const struct sof_ipc_pm_ops *pm_ops = sdev->ipc->ops->pm;
@@ -707,8 +695,6 @@ int sof_mtl_ops_init(struct snd_sof_dev *sdev)
sof_mtl_ops.core_get = mtl_dsp_core_get;
sof_mtl_ops.core_put = mtl_dsp_core_put;
- sof_mtl_ops.get_stream_position = mtl_dsp_get_stream_hda_link_position;
-
sdev->private = kzalloc(sizeof(struct sof_ipc4_fw_data), GFP_KERNEL);
if (!sdev->private)
return -ENOMEM;
diff --git a/sound/soc/sof/intel/mtl.h b/sound/soc/sof/intel/mtl.h
index cc5a1f46fd09..ea8c1b83f712 100644
--- a/sound/soc/sof/intel/mtl.h
+++ b/sound/soc/sof/intel/mtl.h
@@ -6,12 +6,6 @@
* Copyright(c) 2020-2022 Intel Corporation. All rights reserved.
*/
-/* HDA Registers */
-#define MTL_PPLCLLPL_BASE 0x948
-#define MTL_PPLCLLPU_STRIDE 0x10
-#define MTL_PPLCLLPL(x) (MTL_PPLCLLPL_BASE + (x) * MTL_PPLCLLPU_STRIDE)
-#define MTL_PPLCLLPU(x) (MTL_PPLCLLPL_BASE + 0x4 + (x) * MTL_PPLCLLPU_STRIDE)
-
/* DSP Registers */
#define MTL_HFDSSCS 0x1000
#define MTL_HFDSSCS_SPA_MASK BIT(16)
@@ -103,9 +97,5 @@ int mtl_dsp_ipc_get_window_offset(struct snd_sof_dev *sdev, u32 id);
void mtl_ipc_dump(struct snd_sof_dev *sdev);
-u64 mtl_dsp_get_stream_hda_link_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream);
-
int mtl_dsp_core_get(struct snd_sof_dev *sdev, int core);
int mtl_dsp_core_put(struct snd_sof_dev *sdev, int core);
diff --git a/sound/soc/sof/ipc4-mtrace.c b/sound/soc/sof/ipc4-mtrace.c
index 9f1e33ee8826..0e04bea9432d 100644
--- a/sound/soc/sof/ipc4-mtrace.c
+++ b/sound/soc/sof/ipc4-mtrace.c
@@ -4,6 +4,7 @@
#include <linux/debugfs.h>
#include <linux/sched/signal.h>
+#include <linux/sched/clock.h>
#include <sound/sof/ipc4/header.h>
#include "sof-priv.h"
#include "ipc4-priv.h"
@@ -412,7 +413,6 @@ static int ipc4_mtrace_enable(struct snd_sof_dev *sdev)
const struct sof_ipc_ops *iops = sdev->ipc->ops;
struct sof_ipc4_msg msg;
u64 system_time;
- ktime_t kt;
int ret;
if (priv->mtrace_state != SOF_MTRACE_DISABLED)
@@ -424,9 +424,12 @@ static int ipc4_mtrace_enable(struct snd_sof_dev *sdev)
msg.primary |= SOF_IPC4_MOD_INSTANCE(SOF_IPC4_MOD_INIT_BASEFW_INSTANCE_ID);
msg.extension = SOF_IPC4_MOD_EXT_MSG_PARAM_ID(SOF_IPC4_FW_PARAM_SYSTEM_TIME);
- /* The system time is in usec, UTC, epoch is 1601-01-01 00:00:00 */
- kt = ktime_add_us(ktime_get_real(), FW_EPOCH_DELTA * USEC_PER_SEC);
- system_time = ktime_to_us(kt);
+ /*
+ * local_clock() is used to align with dmesg, so both kernel and firmware logs have
+ * the same base and a minor delta due to the IPC. system time is in us format but
+ * local_clock() returns the time in ns, so convert to ns.
+ */
+ system_time = div64_u64(local_clock(), NSEC_PER_USEC);
msg.data_size = sizeof(system_time);
msg.data_ptr = &system_time;
ret = iops->set_get_data(sdev, &msg, msg.data_size, true);
diff --git a/sound/soc/sof/ipc4-pcm.c b/sound/soc/sof/ipc4-pcm.c
index 0f332c8cdbe6..e915f9f87a6c 100644
--- a/sound/soc/sof/ipc4-pcm.c
+++ b/sound/soc/sof/ipc4-pcm.c
@@ -15,6 +15,28 @@
#include "ipc4-topology.h"
#include "ipc4-fw-reg.h"
+/**
+ * struct sof_ipc4_timestamp_info - IPC4 timestamp info
+ * @host_copier: the host copier of the pcm stream
+ * @dai_copier: the dai copier of the pcm stream
+ * @stream_start_offset: reported by fw in memory window (converted to frames)
+ * @stream_end_offset: reported by fw in memory window (converted to frames)
+ * @llp_offset: llp offset in memory window
+ * @boundary: wrap boundary should be used for the LLP frame counter
+ * @delay: Calculated and stored in pointer callback. The stored value is
+ * returned in the delay callback.
+ */
+struct sof_ipc4_timestamp_info {
+ struct sof_ipc4_copier *host_copier;
+ struct sof_ipc4_copier *dai_copier;
+ u64 stream_start_offset;
+ u64 stream_end_offset;
+ u32 llp_offset;
+
+ u64 boundary;
+ snd_pcm_sframes_t delay;
+};
+
static int sof_ipc4_set_multi_pipeline_state(struct snd_sof_dev *sdev, u32 state,
struct ipc4_pipeline_set_state_data *trigger_list)
{
@@ -423,8 +445,19 @@ static int sof_ipc4_trigger_pipelines(struct snd_soc_component *component,
}
/* return if this is the final state */
- if (state == SOF_IPC4_PIPE_PAUSED)
+ if (state == SOF_IPC4_PIPE_PAUSED) {
+ struct sof_ipc4_timestamp_info *time_info;
+
+ /*
+ * Invalidate the stream_start_offset to make sure that it is
+ * going to be updated if the stream resumes
+ */
+ time_info = spcm->stream[substream->stream].private;
+ if (time_info)
+ time_info->stream_start_offset = SOF_IPC4_INVALID_STREAM_POSITION;
+
goto free;
+ }
skip_pause_transition:
/* else set the RUNNING/RESET state in the DSP */
ret = sof_ipc4_set_multi_pipeline_state(sdev, state, trigger_list);
@@ -464,14 +497,12 @@ static int sof_ipc4_pcm_trigger(struct snd_soc_component *component,
/* determine the pipeline state */
switch (cmd) {
- case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- state = SOF_IPC4_PIPE_PAUSED;
- break;
case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
case SNDRV_PCM_TRIGGER_RESUME:
case SNDRV_PCM_TRIGGER_START:
state = SOF_IPC4_PIPE_RUNNING;
break;
+ case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_STOP:
state = SOF_IPC4_PIPE_PAUSED;
@@ -703,6 +734,10 @@ static int sof_ipc4_pcm_setup(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm
if (abi_version < SOF_IPC4_FW_REGS_ABI_VER)
support_info = false;
+ /* For delay reporting the get_host_byte_counter callback is needed */
+ if (!sof_ops(sdev) || !sof_ops(sdev)->get_host_byte_counter)
+ support_info = false;
+
for_each_pcm_streams(stream) {
pipeline_list = &spcm->stream[stream].pipeline_list;
@@ -835,7 +870,6 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
struct sof_ipc4_copier *host_copier = time_info->host_copier;
struct sof_ipc4_copier *dai_copier = time_info->dai_copier;
struct sof_ipc4_pipeline_registers ppl_reg;
- u64 stream_start_position;
u32 dai_sample_size;
u32 ch, node_index;
u32 offset;
@@ -852,38 +886,51 @@ static int sof_ipc4_get_stream_start_offset(struct snd_sof_dev *sdev,
if (ppl_reg.stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION)
return -EINVAL;
- stream_start_position = ppl_reg.stream_start_offset;
ch = dai_copier->data.out_format.fmt_cfg;
ch = SOF_IPC4_AUDIO_FORMAT_CFG_CHANNELS_COUNT(ch);
dai_sample_size = (dai_copier->data.out_format.bit_depth >> 3) * ch;
- /* convert offset to sample count */
- do_div(stream_start_position, dai_sample_size);
- time_info->stream_start_offset = stream_start_position;
+
+ /* convert offsets to frame count */
+ time_info->stream_start_offset = ppl_reg.stream_start_offset;
+ do_div(time_info->stream_start_offset, dai_sample_size);
+ time_info->stream_end_offset = ppl_reg.stream_end_offset;
+ do_div(time_info->stream_end_offset, dai_sample_size);
+
+ /*
+ * Calculate the wrap boundary need to be used for delay calculation
+ * The host counter is in bytes, it will wrap earlier than the frames
+ * based link counter.
+ */
+ time_info->boundary = div64_u64(~((u64)0),
+ frames_to_bytes(substream->runtime, 1));
+ /* Initialize the delay value to 0 (no delay) */
+ time_info->delay = 0;
return 0;
}
-static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
+static int sof_ipc4_pcm_pointer(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream,
+ snd_pcm_uframes_t *pointer)
{
struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct sof_ipc4_timestamp_info *time_info;
struct sof_ipc4_llp_reading_slot llp;
- snd_pcm_uframes_t head_ptr, tail_ptr;
+ snd_pcm_uframes_t head_cnt, tail_cnt;
struct snd_sof_pcm_stream *stream;
+ u64 dai_cnt, host_cnt, host_ptr;
struct snd_sof_pcm *spcm;
- u64 tmp_ptr;
int ret;
spcm = snd_sof_find_spcm_dai(component, rtd);
if (!spcm)
- return 0;
+ return -EOPNOTSUPP;
stream = &spcm->stream[substream->stream];
time_info = stream->private;
if (!time_info)
- return 0;
+ return -EOPNOTSUPP;
/*
* stream_start_offset is updated to memory window by FW based on
@@ -893,45 +940,116 @@ static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
if (time_info->stream_start_offset == SOF_IPC4_INVALID_STREAM_POSITION) {
ret = sof_ipc4_get_stream_start_offset(sdev, substream, stream, time_info);
if (ret < 0)
- return 0;
+ return -EOPNOTSUPP;
}
+ /* For delay calculation we need the host counter */
+ host_cnt = snd_sof_pcm_get_host_byte_counter(sdev, component, substream);
+ host_ptr = host_cnt;
+
+ /* convert the host_cnt to frames */
+ host_cnt = div64_u64(host_cnt, frames_to_bytes(substream->runtime, 1));
+
/*
- * HDaudio links don't support the LLP counter reported by firmware
- * the link position is read directly from hardware registers.
+ * If the LLP counter is not reported by firmware in the SRAM window
+ * then read the dai (link) counter via host accessible means if
+ * available.
*/
if (!time_info->llp_offset) {
- tmp_ptr = snd_sof_pcm_get_stream_position(sdev, component, substream);
- if (!tmp_ptr)
- return 0;
+ dai_cnt = snd_sof_pcm_get_dai_frame_counter(sdev, component, substream);
+ if (!dai_cnt)
+ return -EOPNOTSUPP;
} else {
sof_mailbox_read(sdev, time_info->llp_offset, &llp, sizeof(llp));
- tmp_ptr = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l;
+ dai_cnt = ((u64)llp.reading.llp_u << 32) | llp.reading.llp_l;
}
+ dai_cnt += time_info->stream_end_offset;
- /* In two cases dai dma position is not accurate
+ /* In two cases dai dma counter is not accurate
* (1) dai pipeline is started before host pipeline
- * (2) multiple streams mixed into one. Each stream has the same dai dma position
+ * (2) multiple streams mixed into one. Each stream has the same dai dma
+ * counter
*
- * Firmware calculates correct stream_start_offset for all cases including above two.
- * Driver subtracts stream_start_offset from dai dma position to get accurate one
+ * Firmware calculates correct stream_start_offset for all cases
+ * including above two.
+ * Driver subtracts stream_start_offset from dai dma counter to get
+ * accurate one
*/
- tmp_ptr -= time_info->stream_start_offset;
- /* Calculate the delay taking into account that both pointer can wrap */
- div64_u64_rem(tmp_ptr, substream->runtime->boundary, &tmp_ptr);
+ /*
+ * On stream start the dai counter might not yet have reached the
+ * stream_start_offset value which means that no frames have left the
+ * DSP yet from the audio stream (on playback, capture streams have
+ * offset of 0 as we start capturing right away).
+ * In this case we need to adjust the distance between the counters by
+ * increasing the host counter by (offset - dai_counter).
+ * Otherwise the dai_counter needs to be adjusted to reflect the number
+ * of valid frames passed on the DAI side.
+ *
+ * The delay is the difference between the counters on the two
+ * sides of the DSP.
+ */
+ if (dai_cnt < time_info->stream_start_offset) {
+ host_cnt += time_info->stream_start_offset - dai_cnt;
+ dai_cnt = 0;
+ } else {
+ dai_cnt -= time_info->stream_start_offset;
+ }
+
+ /* Wrap the dai counter at the boundary where the host counter wraps */
+ div64_u64_rem(dai_cnt, time_info->boundary, &dai_cnt);
+
if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
- head_ptr = substream->runtime->status->hw_ptr;
- tail_ptr = tmp_ptr;
+ head_cnt = host_cnt;
+ tail_cnt = dai_cnt;
} else {
- head_ptr = tmp_ptr;
- tail_ptr = substream->runtime->status->hw_ptr;
+ head_cnt = dai_cnt;
+ tail_cnt = host_cnt;
+ }
+
+ if (head_cnt < tail_cnt) {
+ time_info->delay = time_info->boundary - tail_cnt + head_cnt;
+ goto out;
}
- if (head_ptr < tail_ptr)
- return substream->runtime->boundary - tail_ptr + head_ptr;
+ time_info->delay = head_cnt - tail_cnt;
+
+out:
+ /*
+ * Convert the host byte counter to PCM pointer which wraps in buffer
+ * and it is in frames
+ */
+ div64_u64_rem(host_ptr, snd_pcm_lib_buffer_bytes(substream), &host_ptr);
+ *pointer = bytes_to_frames(substream->runtime, host_ptr);
+
+ return 0;
+}
+
+static snd_pcm_sframes_t sof_ipc4_pcm_delay(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
+ struct sof_ipc4_timestamp_info *time_info;
+ struct snd_sof_pcm_stream *stream;
+ struct snd_sof_pcm *spcm;
+
+ spcm = snd_sof_find_spcm_dai(component, rtd);
+ if (!spcm)
+ return 0;
+
+ stream = &spcm->stream[substream->stream];
+ time_info = stream->private;
+ /*
+ * Report the stored delay value calculated in the pointer callback.
+ * In the unlikely event that the calculation was skipped/aborted, the
+ * default 0 delay returned.
+ */
+ if (time_info)
+ return time_info->delay;
+
+ /* No delay information available, report 0 as delay */
+ return 0;
- return head_ptr - tail_ptr;
}
const struct sof_ipc_pcm_ops ipc4_pcm_ops = {
@@ -941,6 +1059,7 @@ const struct sof_ipc_pcm_ops ipc4_pcm_ops = {
.dai_link_fixup = sof_ipc4_pcm_dai_link_fixup,
.pcm_setup = sof_ipc4_pcm_setup,
.pcm_free = sof_ipc4_pcm_free,
+ .pointer = sof_ipc4_pcm_pointer,
.delay = sof_ipc4_pcm_delay,
.ipc_first_on_start = true,
.platform_stop_during_hw_free = true,
diff --git a/sound/soc/sof/ipc4-priv.h b/sound/soc/sof/ipc4-priv.h
index f3b908b093f9..afed618a15f0 100644
--- a/sound/soc/sof/ipc4-priv.h
+++ b/sound/soc/sof/ipc4-priv.h
@@ -92,20 +92,6 @@ struct sof_ipc4_fw_data {
struct mutex pipeline_state_mutex; /* protect pipeline triggers, ref counts and states */
};
-/**
- * struct sof_ipc4_timestamp_info - IPC4 timestamp info
- * @host_copier: the host copier of the pcm stream
- * @dai_copier: the dai copier of the pcm stream
- * @stream_start_offset: reported by fw in memory window
- * @llp_offset: llp offset in memory window
- */
-struct sof_ipc4_timestamp_info {
- struct sof_ipc4_copier *host_copier;
- struct sof_ipc4_copier *dai_copier;
- u64 stream_start_offset;
- u32 llp_offset;
-};
-
extern const struct sof_ipc_fw_loader_ops ipc4_loader_ops;
extern const struct sof_ipc_tplg_ops ipc4_tplg_ops;
extern const struct sof_ipc_tplg_control_ops tplg_ipc4_control_ops;
diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
index f28edd9830c1..5cca05842126 100644
--- a/sound/soc/sof/ipc4-topology.c
+++ b/sound/soc/sof/ipc4-topology.c
@@ -412,8 +412,9 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
struct sof_ipc4_available_audio_format *available_fmt;
struct snd_soc_component *scomp = swidget->scomp;
struct sof_ipc4_copier *ipc4_copier;
+ struct snd_sof_pcm *spcm;
int node_type = 0;
- int ret;
+ int ret, dir;
ipc4_copier = kzalloc(sizeof(*ipc4_copier), GFP_KERNEL);
if (!ipc4_copier)
@@ -447,6 +448,25 @@ static int sof_ipc4_widget_setup_pcm(struct snd_sof_widget *swidget)
}
dev_dbg(scomp->dev, "host copier '%s' node_type %u\n", swidget->widget->name, node_type);
+ spcm = snd_sof_find_spcm_comp(scomp, swidget->comp_id, &dir);
+ if (!spcm)
+ goto skip_gtw_cfg;
+
+ if (dir == SNDRV_PCM_STREAM_PLAYBACK) {
+ struct snd_sof_pcm_stream *sps = &spcm->stream[dir];
+
+ sof_update_ipc_object(scomp, &sps->dsp_max_burst_size_in_ms,
+ SOF_COPIER_DEEP_BUFFER_TOKENS,
+ swidget->tuples,
+ swidget->num_tuples, sizeof(u32), 1);
+ /* Set default DMA buffer size if it is not specified in topology */
+ if (!sps->dsp_max_burst_size_in_ms)
+ sps->dsp_max_burst_size_in_ms = SOF_IPC4_MIN_DMA_BUFFER_SIZE;
+ } else {
+ /* Capture data is copied from DSP to host in 1ms bursts */
+ spcm->stream[dir].dsp_max_burst_size_in_ms = 1;
+ }
+
skip_gtw_cfg:
ipc4_copier->gtw_attr = kzalloc(sizeof(*ipc4_copier->gtw_attr), GFP_KERNEL);
if (!ipc4_copier->gtw_attr) {
diff --git a/sound/soc/sof/ops.h b/sound/soc/sof/ops.h
index 6cf21e829e07..3cd748e13460 100644
--- a/sound/soc/sof/ops.h
+++ b/sound/soc/sof/ops.h
@@ -523,12 +523,26 @@ static inline int snd_sof_pcm_platform_ack(struct snd_sof_dev *sdev,
return 0;
}
-static inline u64 snd_sof_pcm_get_stream_position(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream)
+static inline u64
+snd_sof_pcm_get_dai_frame_counter(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
{
- if (sof_ops(sdev) && sof_ops(sdev)->get_stream_position)
- return sof_ops(sdev)->get_stream_position(sdev, component, substream);
+ if (sof_ops(sdev) && sof_ops(sdev)->get_dai_frame_counter)
+ return sof_ops(sdev)->get_dai_frame_counter(sdev, component,
+ substream);
+
+ return 0;
+}
+
+static inline u64
+snd_sof_pcm_get_host_byte_counter(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream)
+{
+ if (sof_ops(sdev) && sof_ops(sdev)->get_host_byte_counter)
+ return sof_ops(sdev)->get_host_byte_counter(sdev, component,
+ substream);
return 0;
}
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index 33d576b17647..f03cee94bce6 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -388,13 +388,21 @@ static snd_pcm_uframes_t sof_pcm_pointer(struct snd_soc_component *component,
{
struct snd_soc_pcm_runtime *rtd = snd_soc_substream_to_rtd(substream);
struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
+ const struct sof_ipc_pcm_ops *pcm_ops = sof_ipc_get_ops(sdev, pcm);
struct snd_sof_pcm *spcm;
snd_pcm_uframes_t host, dai;
+ int ret = -EOPNOTSUPP;
/* nothing to do for BE */
if (rtd->dai_link->no_pcm)
return 0;
+ if (pcm_ops && pcm_ops->pointer)
+ ret = pcm_ops->pointer(component, substream, &host);
+
+ if (ret != -EOPNOTSUPP)
+ return ret ? ret : host;
+
/* use dsp ops pointer callback directly if set */
if (sof_ops(sdev)->pcm_pointer)
return sof_ops(sdev)->pcm_pointer(sdev, substream);
diff --git a/sound/soc/sof/sof-audio.h b/sound/soc/sof/sof-audio.h
index 9ea2ac5adac7..86bbb531e142 100644
--- a/sound/soc/sof/sof-audio.h
+++ b/sound/soc/sof/sof-audio.h
@@ -103,7 +103,10 @@ struct snd_sof_dai_config_data {
* additional memory in the SOF PCM stream structure
* @pcm_free: Function pointer for PCM free that can be used for freeing any
* additional memory in the SOF PCM stream structure
- * @delay: Function pointer for pcm delay calculation
+ * @pointer: Function pointer for pcm pointer
+ * Note: the @pointer callback may return -EOPNOTSUPP which should be
+ * handled in a same way as if the callback is not provided
+ * @delay: Function pointer for pcm delay reporting
* @reset_hw_params_during_stop: Flag indicating whether the hw_params should be reset during the
* STOP pcm trigger
* @ipc_first_on_start: Send IPC before invoking platform trigger during
@@ -124,6 +127,9 @@ struct sof_ipc_pcm_ops {
int (*dai_link_fixup)(struct snd_soc_pcm_runtime *rtd, struct snd_pcm_hw_params *params);
int (*pcm_setup)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
void (*pcm_free)(struct snd_sof_dev *sdev, struct snd_sof_pcm *spcm);
+ int (*pointer)(struct snd_soc_component *component,
+ struct snd_pcm_substream *substream,
+ snd_pcm_uframes_t *pointer);
snd_pcm_sframes_t (*delay)(struct snd_soc_component *component,
struct snd_pcm_substream *substream);
bool reset_hw_params_during_stop;
@@ -322,6 +328,7 @@ struct snd_sof_pcm_stream {
struct work_struct period_elapsed_work;
struct snd_soc_dapm_widget_list *list; /* list of connected DAPM widgets */
bool d0i3_compatible; /* DSP can be in D0I3 when this pcm is opened */
+ unsigned int dsp_max_burst_size_in_ms; /* The maximum size of the host DMA burst in ms */
/*
* flag to indicate that the DSP pipelines should be kept
* active or not while suspending the stream
diff --git a/sound/soc/sof/sof-priv.h b/sound/soc/sof/sof-priv.h
index d453a4ce3b21..d3c436f82604 100644
--- a/sound/soc/sof/sof-priv.h
+++ b/sound/soc/sof/sof-priv.h
@@ -262,13 +262,25 @@ struct snd_sof_dsp_ops {
int (*pcm_ack)(struct snd_sof_dev *sdev, struct snd_pcm_substream *substream); /* optional */
/*
- * optional callback to retrieve the link DMA position for the substream
- * when the position is not reported in the shared SRAM windows but
- * instead from a host-accessible hardware counter.
+ * optional callback to retrieve the number of frames left/arrived from/to
+ * the DSP on the DAI side (link/codec/DMIC/etc).
+ *
+ * The callback is used when the firmware does not provide this information
+ * via the shared SRAM window and it can be retrieved by host.
*/
- u64 (*get_stream_position)(struct snd_sof_dev *sdev,
- struct snd_soc_component *component,
- struct snd_pcm_substream *substream); /* optional */
+ u64 (*get_dai_frame_counter)(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream); /* optional */
+
+ /*
+ * Optional callback to retrieve the number of bytes left/arrived from/to
+ * the DSP on the host side (bytes between host ALSA buffer and DSP).
+ *
+ * The callback is needed for ALSA delay reporting.
+ */
+ u64 (*get_host_byte_counter)(struct snd_sof_dev *sdev,
+ struct snd_soc_component *component,
+ struct snd_pcm_substream *substream); /* optional */
/* host read DSP stream data */
int (*ipc_msg_data)(struct snd_sof_dev *sdev,
diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
index b67617b68e50..f4437015d43a 100644
--- a/sound/usb/line6/driver.c
+++ b/sound/usb/line6/driver.c
@@ -202,7 +202,7 @@ int line6_send_raw_message_async(struct usb_line6 *line6, const char *buffer,
struct urb *urb;
/* create message: */
- msg = kmalloc(sizeof(struct message), GFP_ATOMIC);
+ msg = kzalloc(sizeof(struct message), GFP_ATOMIC);
if (msg == NULL)
return -ENOMEM;
@@ -688,7 +688,7 @@ static int line6_init_cap_control(struct usb_line6 *line6)
int ret;
/* initialize USB buffers: */
- line6->buffer_listen = kmalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL);
+ line6->buffer_listen = kzalloc(LINE6_BUFSIZE_LISTEN, GFP_KERNEL);
if (!line6->buffer_listen)
return -ENOMEM;
@@ -697,7 +697,7 @@ static int line6_init_cap_control(struct usb_line6 *line6)
return -ENOMEM;
if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) {
- line6->buffer_message = kmalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL);
+ line6->buffer_message = kzalloc(LINE6_MIDI_MESSAGE_MAXLEN, GFP_KERNEL);
if (!line6->buffer_message)
return -ENOMEM;
diff --git a/tools/include/linux/kernel.h b/tools/include/linux/kernel.h
index 4b0673bf52c2..07cfad817d53 100644
--- a/tools/include/linux/kernel.h
+++ b/tools/include/linux/kernel.h
@@ -8,6 +8,7 @@
#include <linux/build_bug.h>
#include <linux/compiler.h>
#include <linux/math.h>
+#include <linux/panic.h>
#include <endian.h>
#include <byteswap.h>
diff --git a/tools/include/linux/mm.h b/tools/include/linux/mm.h
index 7a6b98f4e579..dc0fc7125bc3 100644
--- a/tools/include/linux/mm.h
+++ b/tools/include/linux/mm.h
@@ -34,4 +34,9 @@ static inline void totalram_pages_add(long count)
{
}
+static inline int early_pfn_to_nid(unsigned long pfn)
+{
+ return 0;
+}
+
#endif
diff --git a/tools/include/linux/panic.h b/tools/include/linux/panic.h
new file mode 100644
index 000000000000..9c8f17a41ce8
--- /dev/null
+++ b/tools/include/linux/panic.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TOOLS_LINUX_PANIC_H
+#define _TOOLS_LINUX_PANIC_H
+
+#include <stdarg.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+static inline void panic(const char *fmt, ...)
+{
+ va_list argp;
+
+ va_start(argp, fmt);
+ vfprintf(stderr, fmt, argp);
+ va_end(argp);
+ exit(-1);
+}
+
+#endif
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 8f08c3fd498d..0d3672e5d9ed 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -67,6 +67,10 @@ The column name "all" can be used to enable all disabled-by-default built-in cou
.PP
\fB--quiet\fP Do not decode and print the system configuration header information.
.PP
++\fB--no-msr\fP Disable all the uses of the MSR driver.
++.PP
++\fB--no-perf\fP Disable all the uses of the perf API.
++.PP
\fB--interval seconds\fP overrides the default 5.0 second measurement interval.
.PP
\fB--num_iterations num\fP number of the measurement iterations.
@@ -125,9 +129,17 @@ The system configuration dump (if --quiet is not used) is followed by statistics
.PP
\fBPkgTmp\fP Degrees Celsius reported by the per-package Package Thermal Monitor.
.PP
-\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms.
+\fBGFX%rc6\fP The percentage of time the GPU is in the "render C6" state, rc6, during the measurement interval. From /sys/class/drm/card0/power/rc6_residency_ms or /sys/class/drm/card0/gt/gt0/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
.PP
-\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz.
+\fBGFXMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt_cur_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBGFXAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt_act_freq_mhz or /sys/class/drm/card0/gt/gt0/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
+.PP
+\fBSAM%mc6\fP The percentage of time the SA Media is in the "module C6" state, mc6, during the measurement interval. From /sys/class/drm/card0/gt/gt1/rc6_residency_ms or /sys/class/drm/card0/device/tile0/gtN/gtidle/idle_residency_ms depending on the graphics driver being used.
+.PP
+\fBSAMMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/cur_freq depending on the graphics driver being used.
+.PP
+\fBSAMAMHz\fP Instantaneous snapshot of what sysfs presents at the end of the measurement interval. From /sys/class/drm/card0/gt/gt1/rps_act_freq_mhz or /sys/class/drm/card0/device/tile0/gtN/freq0/act_freq depending on the graphics driver being used.
.PP
\fBPkg%pc2, Pkg%pc3, Pkg%pc6, Pkg%pc7\fP percentage residency in hardware package idle states. These numbers are from hardware residency counters.
.PP
@@ -370,7 +382,7 @@ below the processor's base frequency.
Busy% = MPERF_delta/TSC_delta
-Bzy_MHz = TSC_delta/APERF_delta/MPERF_delta/measurement_interval
+Bzy_MHz = TSC_delta*APERF_delta/MPERF_delta/measurement_interval
Note that these calculations depend on TSC_delta, so they
are not reliable during intervals when TSC_MHz is not running at the base frequency.
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 7a334377f92b..98256468e248 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
* turbostat -- show CPU frequency and C-state residency
* on modern Intel and AMD processors.
*
- * Copyright (c) 2023 Intel Corporation.
+ * Copyright (c) 2024 Intel Corporation.
* Len Brown <len.brown@intel.com>
*/
@@ -36,6 +36,8 @@
#include <linux/perf_event.h>
#include <asm/unistd.h>
#include <stdbool.h>
+#include <assert.h>
+#include <linux/kernel.h>
#define UNUSED(x) (void)(x)
@@ -53,9 +55,13 @@
#define NAME_BYTES 20
#define PATH_BYTES 128
+#define MAX_NOFILE 0x8000
+
enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
+enum amperf_source { AMPERF_SOURCE_PERF, AMPERF_SOURCE_MSR };
+enum rapl_source { RAPL_SOURCE_NONE, RAPL_SOURCE_PERF, RAPL_SOURCE_MSR };
struct msr_counter {
unsigned int msr_num;
@@ -127,6 +133,9 @@ struct msr_counter bic[] = {
{ 0x0, "IPC", "", 0, 0, 0, NULL, 0 },
{ 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 },
{ 0x0, "UncMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAM%mc6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SAMAMHz", "", 0, 0, 0, NULL, 0 },
};
#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
@@ -185,11 +194,14 @@ struct msr_counter bic[] = {
#define BIC_IPC (1ULL << 52)
#define BIC_CORE_THROT_CNT (1ULL << 53)
#define BIC_UNCORE_MHZ (1ULL << 54)
+#define BIC_SAM_mc6 (1ULL << 55)
+#define BIC_SAMMHz (1ULL << 56)
+#define BIC_SAMACTMHz (1ULL << 57)
#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
-#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_UNCORE_MHZ)
-#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX)
+#define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ)
+#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6)
#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
@@ -204,10 +216,13 @@ unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC
#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
+struct amperf_group_fd;
+
char *proc_stat = "/proc/stat";
FILE *outf;
int *fd_percpu;
int *fd_instr_count_percpu;
+struct amperf_group_fd *fd_amperf_percpu; /* File descriptors for perf group with APERF and MPERF counters. */
struct timeval interval_tv = { 5, 0 };
struct timespec interval_ts = { 5, 0 };
@@ -242,11 +257,8 @@ char *output_buffer, *outp;
unsigned int do_dts;
unsigned int do_ptm;
unsigned int do_ipc;
-unsigned long long gfx_cur_rc6_ms;
unsigned long long cpuidle_cur_cpu_lpi_us;
unsigned long long cpuidle_cur_sys_lpi_us;
-unsigned int gfx_cur_mhz;
-unsigned int gfx_act_mhz;
unsigned int tj_max;
unsigned int tj_max_override;
double rapl_power_units, rapl_time_units;
@@ -263,6 +275,28 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */
unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */
unsigned int first_counter_read = 1;
int ignore_stdin;
+bool no_msr;
+bool no_perf;
+enum amperf_source amperf_source;
+
+enum gfx_sysfs_idx {
+ GFX_rc6,
+ GFX_MHz,
+ GFX_ACTMHz,
+ SAM_mc6,
+ SAM_MHz,
+ SAM_ACTMHz,
+ GFX_MAX
+};
+
+struct gfx_sysfs_info {
+ const char *path;
+ FILE *fp;
+ unsigned int val;
+ unsigned long long val_ull;
+};
+
+static struct gfx_sysfs_info gfx_info[GFX_MAX];
int get_msr(int cpu, off_t offset, unsigned long long *msr);
@@ -652,6 +686,7 @@ static const struct platform_features icx_features = {
.bclk_freq = BCLK_100MHZ,
.supported_cstates = CC1 | CC6 | PC2 | PC6,
.cst_limit = CST_LIMIT_ICX,
+ .has_msr_core_c1_res = 1,
.has_irtl_msrs = 1,
.has_cst_prewake_bit = 1,
.trl_msrs = TRL_BASE | TRL_CORECOUNT,
@@ -948,6 +983,175 @@ size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affi
#define MAX_ADDED_THREAD_COUNTERS 24
#define BITMASK_SIZE 32
+/* Indexes used to map data read from perf and MSRs into global variables */
+enum rapl_rci_index {
+ RAPL_RCI_INDEX_ENERGY_PKG = 0,
+ RAPL_RCI_INDEX_ENERGY_CORES = 1,
+ RAPL_RCI_INDEX_DRAM = 2,
+ RAPL_RCI_INDEX_GFX = 3,
+ RAPL_RCI_INDEX_PKG_PERF_STATUS = 4,
+ RAPL_RCI_INDEX_DRAM_PERF_STATUS = 5,
+ RAPL_RCI_INDEX_CORE_ENERGY = 6,
+ NUM_RAPL_COUNTERS,
+};
+
+enum rapl_unit {
+ RAPL_UNIT_INVALID,
+ RAPL_UNIT_JOULES,
+ RAPL_UNIT_WATTS,
+};
+
+struct rapl_counter_info_t {
+ unsigned long long data[NUM_RAPL_COUNTERS];
+ enum rapl_source source[NUM_RAPL_COUNTERS];
+ unsigned long long flags[NUM_RAPL_COUNTERS];
+ double scale[NUM_RAPL_COUNTERS];
+ enum rapl_unit unit[NUM_RAPL_COUNTERS];
+
+ union {
+ /* Active when source == RAPL_SOURCE_MSR */
+ struct {
+ unsigned long long msr[NUM_RAPL_COUNTERS];
+ unsigned long long msr_mask[NUM_RAPL_COUNTERS];
+ int msr_shift[NUM_RAPL_COUNTERS];
+ };
+ };
+
+ int fd_perf;
+};
+
+/* struct rapl_counter_info_t for each RAPL domain */
+struct rapl_counter_info_t *rapl_counter_info_perdomain;
+
+#define RAPL_COUNTER_FLAG_USE_MSR_SUM (1u << 1)
+
+struct rapl_counter_arch_info {
+ int feature_mask; /* Mask for testing if the counter is supported on host */
+ const char *perf_subsys;
+ const char *perf_name;
+ unsigned long long msr;
+ unsigned long long msr_mask;
+ int msr_shift; /* Positive mean shift right, negative mean shift left */
+ double *platform_rapl_msr_scale; /* Scale applied to values read by MSR (platform dependent, filled at runtime) */
+ unsigned int rci_index; /* Maps data from perf counters to global variables */
+ unsigned long long bic;
+ double compat_scale; /* Some counters require constant scaling to be in the same range as other, similar ones */
+ unsigned long long flags;
+};
+
+static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = {
+ {
+ .feature_mask = RAPL_PKG,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = "power",
+ .perf_name = "energy-pkg",
+ .msr = MSR_PKG_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_PKG,
+ .bic = BIC_PkgWatt | BIC_Pkg_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_CORE_ENERGY_STATUS,
+ .perf_subsys = "power",
+ .perf_name = "energy-cores",
+ .msr = MSR_PP0_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_ENERGY_CORES,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM,
+ .perf_subsys = "power",
+ .perf_name = "energy-ram",
+ .msr = MSR_DRAM_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_dram_energy_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM,
+ .bic = BIC_RAMWatt | BIC_RAM_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_GFX,
+ .perf_subsys = "power",
+ .perf_name = "energy-gpu",
+ .msr = MSR_PP1_ENERGY_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_GFX,
+ .bic = BIC_GFXWatt | BIC_GFX_J,
+ .compat_scale = 1.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_PKG_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_PKG_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_PKG_PERF_STATUS,
+ .bic = BIC_PKG__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_DRAM_PERF_STATUS,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_DRAM_PERF_STATUS,
+ .msr_mask = 0xFFFFFFFFFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_time_units,
+ .rci_index = RAPL_RCI_INDEX_DRAM_PERF_STATUS,
+ .bic = BIC_RAM__,
+ .compat_scale = 100.0,
+ .flags = RAPL_COUNTER_FLAG_USE_MSR_SUM,
+ },
+ {
+ .feature_mask = RAPL_AMD_F17H,
+ .perf_subsys = NULL,
+ .perf_name = NULL,
+ .msr = MSR_CORE_ENERGY_STAT,
+ .msr_mask = 0xFFFFFFFF,
+ .msr_shift = 0,
+ .platform_rapl_msr_scale = &rapl_energy_units,
+ .rci_index = RAPL_RCI_INDEX_CORE_ENERGY,
+ .bic = BIC_CorWatt | BIC_Cor_J,
+ .compat_scale = 1.0,
+ .flags = 0,
+ },
+};
+
+struct rapl_counter {
+ unsigned long long raw_value;
+ enum rapl_unit unit;
+ double scale;
+};
+
struct thread_data {
struct timeval tv_begin;
struct timeval tv_end;
@@ -974,7 +1178,7 @@ struct core_data {
unsigned long long c7;
unsigned long long mc6_us; /* duplicate as per-core for now, even though per module */
unsigned int core_temp_c;
- unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */
+ struct rapl_counter core_energy; /* MSR_CORE_ENERGY_STAT */
unsigned int core_id;
unsigned long long core_throt_cnt;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -989,8 +1193,8 @@ struct pkg_data {
unsigned long long pc8;
unsigned long long pc9;
unsigned long long pc10;
- unsigned long long cpu_lpi;
- unsigned long long sys_lpi;
+ long long cpu_lpi;
+ long long sys_lpi;
unsigned long long pkg_wtd_core_c0;
unsigned long long pkg_any_core_c0;
unsigned long long pkg_any_gfxe_c0;
@@ -998,13 +1202,16 @@ struct pkg_data {
long long gfx_rc6_ms;
unsigned int gfx_mhz;
unsigned int gfx_act_mhz;
+ long long sam_mc6_ms;
+ unsigned int sam_mhz;
+ unsigned int sam_act_mhz;
unsigned int package_id;
- unsigned long long energy_pkg; /* MSR_PKG_ENERGY_STATUS */
- unsigned long long energy_dram; /* MSR_DRAM_ENERGY_STATUS */
- unsigned long long energy_cores; /* MSR_PP0_ENERGY_STATUS */
- unsigned long long energy_gfx; /* MSR_PP1_ENERGY_STATUS */
- unsigned long long rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
- unsigned long long rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
+ struct rapl_counter energy_pkg; /* MSR_PKG_ENERGY_STATUS */
+ struct rapl_counter energy_dram; /* MSR_DRAM_ENERGY_STATUS */
+ struct rapl_counter energy_cores; /* MSR_PP0_ENERGY_STATUS */
+ struct rapl_counter energy_gfx; /* MSR_PP1_ENERGY_STATUS */
+ struct rapl_counter rapl_pkg_perf_status; /* MSR_PKG_PERF_STATUS */
+ struct rapl_counter rapl_dram_perf_status; /* MSR_DRAM_PERF_STATUS */
unsigned int pkg_temp_c;
unsigned int uncore_mhz;
unsigned long long counter[MAX_ADDED_COUNTERS];
@@ -1150,6 +1357,38 @@ struct sys_counters {
struct msr_counter *pp;
} sys;
+void free_sys_counters(void)
+{
+ struct msr_counter *p = sys.tp, *pnext = NULL;
+
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.cp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ p = sys.pp, pnext = NULL;
+ while (p) {
+ pnext = p->next;
+ free(p);
+ p = pnext;
+ }
+
+ sys.added_thread_counters = 0;
+ sys.added_core_counters = 0;
+ sys.added_package_counters = 0;
+ sys.tp = NULL;
+ sys.cp = NULL;
+ sys.pp = NULL;
+}
+
struct system_summary {
struct thread_data threads;
struct core_data cores;
@@ -1280,34 +1519,60 @@ int get_msr_fd(int cpu)
sprintf(pathname, "/dev/cpu/%d/msr", cpu);
fd = open(pathname, O_RDONLY);
if (fd < 0)
- err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, or run as root", pathname);
+ err(-1, "%s open failed, try chown or chmod +r /dev/cpu/*/msr, "
+ "or run with --no-msr, or run as root", pathname);
fd_percpu[cpu] = fd;
return fd;
}
+static void bic_disable_msr_access(void)
+{
+ const unsigned long bic_msrs =
+ BIC_SMI |
+ BIC_CPU_c1 |
+ BIC_CPU_c3 |
+ BIC_CPU_c6 |
+ BIC_CPU_c7 |
+ BIC_Mod_c6 |
+ BIC_CoreTmp |
+ BIC_Totl_c0 |
+ BIC_Any_c0 |
+ BIC_GFX_c0 |
+ BIC_CPUGFX |
+ BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_PkgTmp;
+
+ bic_enabled &= ~bic_msrs;
+
+ free_sys_counters();
+}
+
static long perf_event_open(struct perf_event_attr *hw_event, pid_t pid, int cpu, int group_fd, unsigned long flags)
{
+ assert(!no_perf);
+
return syscall(__NR_perf_event_open, hw_event, pid, cpu, group_fd, flags);
}
-static int perf_instr_count_open(int cpu_num)
+static long open_perf_counter(int cpu, unsigned int type, unsigned int config, int group_fd, __u64 read_format)
{
- struct perf_event_attr pea;
- int fd;
+ struct perf_event_attr attr;
+ const pid_t pid = -1;
+ const unsigned long flags = 0;
- memset(&pea, 0, sizeof(struct perf_event_attr));
- pea.type = PERF_TYPE_HARDWARE;
- pea.size = sizeof(struct perf_event_attr);
- pea.config = PERF_COUNT_HW_INSTRUCTIONS;
+ assert(!no_perf);
- /* counter for cpu_num, including user + kernel and all processes */
- fd = perf_event_open(&pea, -1, cpu_num, -1, 0);
- if (fd == -1) {
- warnx("capget(CAP_PERFMON) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
- BIC_NOT_PRESENT(BIC_IPC);
- }
+ memset(&attr, 0, sizeof(struct perf_event_attr));
+
+ attr.type = type;
+ attr.size = sizeof(struct perf_event_attr);
+ attr.config = config;
+ attr.disabled = 0;
+ attr.sample_type = PERF_SAMPLE_IDENTIFIER;
+ attr.read_format = read_format;
+
+ const int fd = perf_event_open(&attr, pid, cpu, group_fd, flags);
return fd;
}
@@ -1317,7 +1582,7 @@ int get_instr_count_fd(int cpu)
if (fd_instr_count_percpu[cpu])
return fd_instr_count_percpu[cpu];
- fd_instr_count_percpu[cpu] = perf_instr_count_open(cpu);
+ fd_instr_count_percpu[cpu] = open_perf_counter(cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
return fd_instr_count_percpu[cpu];
}
@@ -1326,6 +1591,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
{
ssize_t retval;
+ assert(!no_msr);
+
retval = pread(get_msr_fd(cpu), msr, sizeof(*msr), offset);
if (retval != sizeof *msr)
@@ -1334,6 +1601,21 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
return 0;
}
+int probe_msr(int cpu, off_t offset)
+{
+ ssize_t retval;
+ unsigned long long dummy;
+
+ assert(!no_msr);
+
+ retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset);
+
+ if (retval != sizeof(dummy))
+ return 1;
+
+ return 0;
+}
+
#define MAX_DEFERRED 16
char *deferred_add_names[MAX_DEFERRED];
char *deferred_skip_names[MAX_DEFERRED];
@@ -1369,6 +1651,8 @@ void help(void)
" Override default 5-second measurement interval\n"
" -J, --Joules displays energy in Joules instead of Watts\n"
" -l, --list list column headers only\n"
+ " -M, --no-msr Disable all uses of the MSR driver\n"
+ " -P, --no-perf Disable all uses of the perf API\n"
" -n, --num_iterations num\n"
" number of the measurement iterations\n"
" -N, --header_iterations num\n"
@@ -1573,6 +1857,15 @@ void print_header(char *delim)
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%sGFXAMHz", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_SAM_mc6))
+ outp += sprintf(outp, "%sSAM%%mc6", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%sSAMMHz", (printed++ ? delim : ""));
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%sSAMAMHz", (printed++ ? delim : ""));
+
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%sTotl%%C0", (printed++ ? delim : ""));
if (DO_BIC(BIC_Any_c0))
@@ -1671,26 +1964,35 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
outp += sprintf(outp, "SMI: %d\n", t->smi_count);
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "tADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, t->counter[i]);
+ outp +=
+ sprintf(outp, "tADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ t->counter[i], mp->path);
}
}
- if (c) {
+ if (c && is_cpu_first_thread_in_core(t, c, p)) {
outp += sprintf(outp, "core: %d\n", c->core_id);
outp += sprintf(outp, "c3: %016llX\n", c->c3);
outp += sprintf(outp, "c6: %016llX\n", c->c6);
outp += sprintf(outp, "c7: %016llX\n", c->c7);
outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt);
- outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
+
+ const unsigned long long energy_value = c->core_energy.raw_value * c->core_energy.scale;
+ const double energy_scale = c->core_energy.scale;
+
+ if (c->core_energy.unit == RAPL_UNIT_JOULES)
+ outp += sprintf(outp, "Joules: %0llX (scale: %lf)\n", energy_value, energy_scale);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "cADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, c->counter[i]);
+ outp +=
+ sprintf(outp, "cADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ c->counter[i], mp->path);
}
outp += sprintf(outp, "mc6_us: %016llX\n", c->mc6_us);
}
- if (p) {
+ if (p && is_cpu_first_core_in_package(t, c, p)) {
outp += sprintf(outp, "package: %d\n", p->package_id);
outp += sprintf(outp, "Weighted cores: %016llX\n", p->pkg_wtd_core_c0);
@@ -1710,16 +2012,18 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
- outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg);
- outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores);
- outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx);
- outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram);
- outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status);
- outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status);
+ outp += sprintf(outp, "Joules PKG: %0llX\n", p->energy_pkg.raw_value);
+ outp += sprintf(outp, "Joules COR: %0llX\n", p->energy_cores.raw_value);
+ outp += sprintf(outp, "Joules GFX: %0llX\n", p->energy_gfx.raw_value);
+ outp += sprintf(outp, "Joules RAM: %0llX\n", p->energy_dram.raw_value);
+ outp += sprintf(outp, "Throttle PKG: %0llX\n", p->rapl_pkg_perf_status.raw_value);
+ outp += sprintf(outp, "Throttle RAM: %0llX\n", p->rapl_dram_perf_status.raw_value);
outp += sprintf(outp, "PTM: %dC\n", p->pkg_temp_c);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- outp += sprintf(outp, "pADDED [%d] msr0x%x: %08llX\n", i, mp->msr_num, p->counter[i]);
+ outp +=
+ sprintf(outp, "pADDED [%d] %8s msr0x%x: %08llX %s\n", i, mp->name, mp->msr_num,
+ p->counter[i], mp->path);
}
}
@@ -1728,6 +2032,23 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
return 0;
}
+double rapl_counter_get_value(const struct rapl_counter *c, enum rapl_unit desired_unit, double interval)
+{
+ assert(desired_unit != RAPL_UNIT_INVALID);
+
+ /*
+ * For now we don't expect anything other than joules,
+ * so just simplify the logic.
+ */
+ assert(c->unit == RAPL_UNIT_JOULES);
+
+ const double scaled = c->raw_value * c->scale;
+
+ if (desired_unit == RAPL_UNIT_WATTS)
+ return scaled / interval;
+ return scaled;
+}
+
/*
* column formatting convention & formats
*/
@@ -1921,9 +2242,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&c->core_energy, RAPL_UNIT_JOULES, interval_float));
/* print per-package data only for 1st core in package */
if (!is_cpu_first_core_in_package(t, c, p))
@@ -1951,6 +2274,24 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_GFXACTMHz))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->gfx_act_mhz);
+ /* SAMmc6 */
+ if (DO_BIC(BIC_SAM_mc6)) {
+ if (p->sam_mc6_ms == -1) { /* detect GFX counter reset */
+ outp += sprintf(outp, "%s**.**", (printed++ ? delim : ""));
+ } else {
+ outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ p->sam_mc6_ms / 10.0 / interval_float);
+ }
+ }
+
+ /* SAMMHz */
+ if (DO_BIC(BIC_SAMMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_mhz);
+
+ /* SAMACTMHz */
+ if (DO_BIC(BIC_SAMACTMHz))
+ outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->sam_act_mhz);
+
/* Totl%C0, Any%C0 GFX%C0 CPUGFX% */
if (DO_BIC(BIC_Totl_c0))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pkg_wtd_core_c0 / tsc);
@@ -1976,43 +2317,59 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_Pkgpc10))
outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10 / tsc);
- if (DO_BIC(BIC_CPU_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
- if (DO_BIC(BIC_SYS_LPI))
- outp +=
- sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ if (DO_BIC(BIC_CPU_LPI)) {
+ if (p->cpu_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
+ if (DO_BIC(BIC_SYS_LPI)) {
+ if (p->sys_lpi >= 0)
+ outp +=
+ sprintf(outp, "%s%.2f", (printed++ ? delim : ""),
+ 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+ else
+ outp += sprintf(outp, "%s(neg)", (printed++ ? delim : ""));
+ }
if (DO_BIC(BIC_PkgWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
-
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl)
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_GFXWatt))
outp +=
- sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units / interval_float);
+ sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAMWatt))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- p->energy_dram * rapl_dram_energy_units / interval_float);
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_Pkg_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_pkg, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl)
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_cores, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_GFX_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_gfx, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_RAM_J))
- outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_dram * rapl_dram_energy_units);
+ outp += sprintf(outp, fmt8, (printed++ ? delim : ""),
+ rapl_counter_get_value(&p->energy_dram, RAPL_UNIT_JOULES, interval_float));
if (DO_BIC(BIC_PKG__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_pkg_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_pkg_perf_status, RAPL_UNIT_WATTS, interval_float));
if (DO_BIC(BIC_RAM__))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""),
- 100.0 * p->rapl_dram_perf_status * rapl_time_units / interval_float);
+ rapl_counter_get_value(&p->rapl_dram_perf_status, RAPL_UNIT_WATTS, interval_float));
/* UncMHz */
if (DO_BIC(BIC_UNCORE_MHZ))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), p->uncore_mhz);
@@ -2121,12 +2478,22 @@ int delta_package(struct pkg_data *new, struct pkg_data *old)
old->gfx_mhz = new->gfx_mhz;
old->gfx_act_mhz = new->gfx_act_mhz;
- old->energy_pkg = new->energy_pkg - old->energy_pkg;
- old->energy_cores = new->energy_cores - old->energy_cores;
- old->energy_gfx = new->energy_gfx - old->energy_gfx;
- old->energy_dram = new->energy_dram - old->energy_dram;
- old->rapl_pkg_perf_status = new->rapl_pkg_perf_status - old->rapl_pkg_perf_status;
- old->rapl_dram_perf_status = new->rapl_dram_perf_status - old->rapl_dram_perf_status;
+ /* flag an error when mc6 counter resets/wraps */
+ if (old->sam_mc6_ms > new->sam_mc6_ms)
+ old->sam_mc6_ms = -1;
+ else
+ old->sam_mc6_ms = new->sam_mc6_ms - old->sam_mc6_ms;
+
+ old->sam_mhz = new->sam_mhz;
+ old->sam_act_mhz = new->sam_act_mhz;
+
+ old->energy_pkg.raw_value = new->energy_pkg.raw_value - old->energy_pkg.raw_value;
+ old->energy_cores.raw_value = new->energy_cores.raw_value - old->energy_cores.raw_value;
+ old->energy_gfx.raw_value = new->energy_gfx.raw_value - old->energy_gfx.raw_value;
+ old->energy_dram.raw_value = new->energy_dram.raw_value - old->energy_dram.raw_value;
+ old->rapl_pkg_perf_status.raw_value = new->rapl_pkg_perf_status.raw_value - old->rapl_pkg_perf_status.raw_value;
+ old->rapl_dram_perf_status.raw_value =
+ new->rapl_dram_perf_status.raw_value - old->rapl_dram_perf_status.raw_value;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2150,7 +2517,7 @@ void delta_core(struct core_data *new, struct core_data *old)
old->core_throt_cnt = new->core_throt_cnt;
old->mc6_us = new->mc6_us - old->mc6_us;
- DELTA_WRAP32(new->core_energy, old->core_energy);
+ DELTA_WRAP32(new->core_energy.raw_value, old->core_energy.raw_value);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2277,6 +2644,13 @@ int delta_cpu(struct thread_data *t, struct core_data *c,
return retval;
}
+void rapl_counter_clear(struct rapl_counter *c)
+{
+ c->raw_value = 0;
+ c->scale = 0.0;
+ c->unit = RAPL_UNIT_INVALID;
+}
+
void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2304,7 +2678,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
c->c7 = 0;
c->mc6_us = 0;
c->core_temp_c = 0;
- c->core_energy = 0;
+ rapl_counter_clear(&c->core_energy);
c->core_throt_cnt = 0;
p->pkg_wtd_core_c0 = 0;
@@ -2325,18 +2699,21 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
p->cpu_lpi = 0;
p->sys_lpi = 0;
- p->energy_pkg = 0;
- p->energy_dram = 0;
- p->energy_cores = 0;
- p->energy_gfx = 0;
- p->rapl_pkg_perf_status = 0;
- p->rapl_dram_perf_status = 0;
+ rapl_counter_clear(&p->energy_pkg);
+ rapl_counter_clear(&p->energy_dram);
+ rapl_counter_clear(&p->energy_cores);
+ rapl_counter_clear(&p->energy_gfx);
+ rapl_counter_clear(&p->rapl_pkg_perf_status);
+ rapl_counter_clear(&p->rapl_dram_perf_status);
p->pkg_temp_c = 0;
p->gfx_rc6_ms = 0;
p->uncore_mhz = 0;
p->gfx_mhz = 0;
p->gfx_act_mhz = 0;
+ p->sam_mc6_ms = 0;
+ p->sam_mhz = 0;
+ p->sam_act_mhz = 0;
for (i = 0, mp = sys.tp; mp; i++, mp = mp->next)
t->counter[i] = 0;
@@ -2347,6 +2724,20 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
p->counter[i] = 0;
}
+void rapl_counter_accumulate(struct rapl_counter *dst, const struct rapl_counter *src)
+{
+ /* Copy unit and scale from src if dst is not initialized */
+ if (dst->unit == RAPL_UNIT_INVALID) {
+ dst->unit = src->unit;
+ dst->scale = src->scale;
+ }
+
+ assert(dst->unit == src->unit);
+ assert(dst->scale == src->scale);
+
+ dst->raw_value += src->raw_value;
+}
+
int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int i;
@@ -2393,7 +2784,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt);
- average.cores.core_energy += c->core_energy;
+ rapl_counter_accumulate(&average.cores.core_energy, &c->core_energy);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW)
@@ -2428,25 +2819,29 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
average.packages.cpu_lpi = p->cpu_lpi;
average.packages.sys_lpi = p->sys_lpi;
- average.packages.energy_pkg += p->energy_pkg;
- average.packages.energy_dram += p->energy_dram;
- average.packages.energy_cores += p->energy_cores;
- average.packages.energy_gfx += p->energy_gfx;
+ rapl_counter_accumulate(&average.packages.energy_pkg, &p->energy_pkg);
+ rapl_counter_accumulate(&average.packages.energy_dram, &p->energy_dram);
+ rapl_counter_accumulate(&average.packages.energy_cores, &p->energy_cores);
+ rapl_counter_accumulate(&average.packages.energy_gfx, &p->energy_gfx);
average.packages.gfx_rc6_ms = p->gfx_rc6_ms;
average.packages.uncore_mhz = p->uncore_mhz;
average.packages.gfx_mhz = p->gfx_mhz;
average.packages.gfx_act_mhz = p->gfx_act_mhz;
+ average.packages.sam_mc6_ms = p->sam_mc6_ms;
+ average.packages.sam_mhz = p->sam_mhz;
+ average.packages.sam_act_mhz = p->sam_act_mhz;
average.packages.pkg_temp_c = MAX(average.packages.pkg_temp_c, p->pkg_temp_c);
- average.packages.rapl_pkg_perf_status += p->rapl_pkg_perf_status;
- average.packages.rapl_dram_perf_status += p->rapl_dram_perf_status;
+ rapl_counter_accumulate(&average.packages.rapl_pkg_perf_status, &p->rapl_pkg_perf_status);
+ rapl_counter_accumulate(&average.packages.rapl_dram_perf_status, &p->rapl_dram_perf_status);
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
- if (mp->format == FORMAT_RAW)
- continue;
- average.packages.counter[i] += p->counter[i];
+ if ((mp->format == FORMAT_RAW) && (topo.num_packages == 0))
+ average.packages.counter[i] = p->counter[i];
+ else
+ average.packages.counter[i] += p->counter[i];
}
return 0;
}
@@ -2578,6 +2973,7 @@ unsigned long long snapshot_sysfs_counter(char *path)
int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
{
if (mp->msr_num != 0) {
+ assert(!no_msr);
if (get_msr(cpu, mp->msr_num, counterp))
return -1;
} else {
@@ -2599,7 +2995,7 @@ unsigned long long get_uncore_mhz(int package, int die)
{
char path[128];
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/current_freq_khz", package,
+ sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d/current_freq_khz", package,
die);
return (snapshot_sysfs_counter(path) / 1000);
@@ -2627,6 +3023,9 @@ int get_epb(int cpu)
return epb;
msr_fallback:
+ if (no_msr)
+ return -1;
+
get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr);
return msr & 0xf;
@@ -2700,6 +3099,351 @@ int get_core_throt_cnt(int cpu, unsigned long long *cnt)
return 0;
}
+struct amperf_group_fd {
+ int aperf; /* Also the group descriptor */
+ int mperf;
+};
+
+static int read_perf_counter_info(const char *const path, const char *const parse_format, void *value_ptr)
+{
+ int fdmt;
+ int bytes_read;
+ char buf[64];
+ int ret = -1;
+
+ fdmt = open(path, O_RDONLY, 0);
+ if (fdmt == -1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ bytes_read = read(fdmt, buf, sizeof(buf) - 1);
+ if (bytes_read <= 0 || bytes_read >= (int)sizeof(buf)) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ buf[bytes_read] = '\0';
+
+ if (sscanf(buf, parse_format, value_ptr) != 1) {
+ if (debug)
+ fprintf(stderr, "Failed to parse perf counter info %s\n", path);
+ ret = -1;
+ goto cleanup_and_exit;
+ }
+
+ ret = 0;
+
+cleanup_and_exit:
+ close(fdmt);
+ return ret;
+}
+
+static unsigned int read_perf_counter_info_n(const char *const path, const char *const parse_format)
+{
+ unsigned int v;
+ int status;
+
+ status = read_perf_counter_info(path, parse_format, &v);
+ if (status)
+ v = -1;
+
+ return v;
+}
+
+static unsigned int read_msr_type(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/type";
+ const char *const format = "%u";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_aperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/aperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_mperf_config(void)
+{
+ const char *const path = "/sys/bus/event_source/devices/msr/events/mperf";
+ const char *const format = "event=%x";
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_type(const char *subsys)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/type";
+ const char *const format = "%u";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_rapl_config(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s";
+ const char *const format = "event=%x";
+ char path[128];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ return read_perf_counter_info_n(path, format);
+}
+
+static unsigned int read_perf_rapl_unit(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.unit";
+ const char *const format = "%s";
+ char path[128];
+ char unit_buffer[16];
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ read_perf_counter_info(path, format, &unit_buffer);
+ if (strcmp("Joules", unit_buffer) == 0)
+ return RAPL_UNIT_JOULES;
+
+ return RAPL_UNIT_INVALID;
+}
+
+static double read_perf_rapl_scale(const char *subsys, const char *event_name)
+{
+ const char *const path_format = "/sys/bus/event_source/devices/%s/events/%s.scale";
+ const char *const format = "%lf";
+ char path[128];
+ double scale;
+
+ snprintf(path, sizeof(path), path_format, subsys, event_name);
+
+ if (read_perf_counter_info(path, format, &scale))
+ return 0.0;
+
+ return scale;
+}
+
+static struct amperf_group_fd open_amperf_fd(int cpu)
+{
+ const unsigned int msr_type = read_msr_type();
+ const unsigned int aperf_config = read_aperf_config();
+ const unsigned int mperf_config = read_mperf_config();
+ struct amperf_group_fd fds = {.aperf = -1, .mperf = -1 };
+
+ fds.aperf = open_perf_counter(cpu, msr_type, aperf_config, -1, PERF_FORMAT_GROUP);
+ fds.mperf = open_perf_counter(cpu, msr_type, mperf_config, fds.aperf, PERF_FORMAT_GROUP);
+
+ return fds;
+}
+
+static int get_amperf_fd(int cpu)
+{
+ assert(fd_amperf_percpu);
+
+ if (fd_amperf_percpu[cpu].aperf)
+ return fd_amperf_percpu[cpu].aperf;
+
+ fd_amperf_percpu[cpu] = open_amperf_fd(cpu);
+
+ return fd_amperf_percpu[cpu].aperf;
+}
+
+/* Read APERF, MPERF and TSC using the perf API. */
+static int read_aperf_mperf_tsc_perf(struct thread_data *t, int cpu)
+{
+ union {
+ struct {
+ unsigned long nr_entries;
+ unsigned long aperf;
+ unsigned long mperf;
+ };
+
+ unsigned long as_array[3];
+ } cnt;
+
+ const int fd_amperf = get_amperf_fd(cpu);
+
+ /*
+ * Read the TSC with rdtsc, because we want the absolute value and not
+ * the offset from the start of the counter.
+ */
+ t->tsc = rdtsc();
+
+ const int n = read(fd_amperf, &cnt.as_array[0], sizeof(cnt.as_array));
+
+ if (n != sizeof(cnt.as_array))
+ return -2;
+
+ t->aperf = cnt.aperf * aperf_mperf_multiplier;
+ t->mperf = cnt.mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+/* Read APERF, MPERF and TSC using the MSR driver and rdtsc instruction. */
+static int read_aperf_mperf_tsc_msr(struct thread_data *t, int cpu)
+{
+ unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
+ int aperf_mperf_retry_count = 0;
+
+ /*
+ * The TSC, APERF and MPERF must be read together for
+ * APERF/MPERF and MPERF/TSC to give accurate results.
+ *
+ * Unfortunately, APERF and MPERF are read by
+ * individual system call, so delays may occur
+ * between them. If the time to read them
+ * varies by a large amount, we re-read them.
+ */
+
+ /*
+ * This initial dummy APERF read has been seen to
+ * reduce jitter in the subsequent reads.
+ */
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+retry:
+ t->tsc = rdtsc(); /* re-read close to APERF */
+
+ tsc_before = t->tsc;
+
+ if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
+ return -3;
+
+ tsc_between = rdtsc();
+
+ if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
+ return -4;
+
+ tsc_after = rdtsc();
+
+ aperf_time = tsc_between - tsc_before;
+ mperf_time = tsc_after - tsc_between;
+
+ /*
+ * If the system call latency to read APERF and MPERF
+ * differ by more than 2x, then try again.
+ */
+ if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
+ aperf_mperf_retry_count++;
+ if (aperf_mperf_retry_count < 5)
+ goto retry;
+ else
+ warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ }
+ aperf_mperf_retry_count = 0;
+
+ t->aperf = t->aperf * aperf_mperf_multiplier;
+ t->mperf = t->mperf * aperf_mperf_multiplier;
+
+ return 0;
+}
+
+size_t rapl_counter_info_count_perf(const struct rapl_counter_info_t *rci)
+{
+ size_t ret = 0;
+
+ for (int i = 0; i < NUM_RAPL_COUNTERS; ++i)
+ if (rci->source[i] == RAPL_SOURCE_PERF)
+ ++ret;
+
+ return ret;
+}
+
+void write_rapl_counter(struct rapl_counter *rc, struct rapl_counter_info_t *rci, unsigned int idx)
+{
+ rc->raw_value = rci->data[idx];
+ rc->unit = rci->unit[idx];
+ rc->scale = rci->scale[idx];
+}
+
+int get_rapl_counters(int cpu, int domain, struct core_data *c, struct pkg_data *p)
+{
+ unsigned long long perf_data[NUM_RAPL_COUNTERS + 1];
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain];
+
+ if (debug)
+ fprintf(stderr, "%s: cpu%d domain%d\n", __func__, cpu, domain);
+
+ assert(rapl_counter_info_perdomain);
+
+ /*
+ * If we have any perf counters to read, read them all now, in bulk
+ */
+ if (rci->fd_perf != -1) {
+ size_t num_perf_counters = rapl_counter_info_count_perf(rci);
+ const ssize_t expected_read_size = (num_perf_counters + 1) * sizeof(unsigned long long);
+ const ssize_t actual_read_size = read(rci->fd_perf, &perf_data[0], sizeof(perf_data));
+
+ if (actual_read_size != expected_read_size)
+ err(-1, "%s: failed to read perf_data (%zu %zu)", __func__, expected_read_size,
+ actual_read_size);
+ }
+
+ for (unsigned int i = 0, pi = 1; i < NUM_RAPL_COUNTERS; ++i) {
+ switch (rci->source[i]) {
+ case RAPL_SOURCE_NONE:
+ break;
+
+ case RAPL_SOURCE_PERF:
+ assert(pi < ARRAY_SIZE(perf_data));
+ assert(rci->fd_perf != -1);
+
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via perf at %u (%llu %e %lf)\n",
+ i, perf_data[pi], rci->scale[i], perf_data[pi] * rci->scale[i]);
+
+ rci->data[i] = perf_data[pi];
+
+ ++pi;
+ break;
+
+ case RAPL_SOURCE_MSR:
+ if (debug)
+ fprintf(stderr, "Reading rapl counter via msr at %u\n", i);
+
+ assert(!no_msr);
+ if (rci->flags[i] & RAPL_COUNTER_FLAG_USE_MSR_SUM) {
+ if (get_msr_sum(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ } else {
+ if (get_msr(cpu, rci->msr[i], &rci->data[i]))
+ return -13 - i;
+ }
+
+ rci->data[i] &= rci->msr_mask[i];
+ if (rci->msr_shift[i] >= 0)
+ rci->data[i] >>= abs(rci->msr_shift[i]);
+ else
+ rci->data[i] <<= abs(rci->msr_shift[i]);
+
+ break;
+ }
+ }
+
+ _Static_assert(NUM_RAPL_COUNTERS == 7);
+ write_rapl_counter(&p->energy_pkg, rci, RAPL_RCI_INDEX_ENERGY_PKG);
+ write_rapl_counter(&p->energy_cores, rci, RAPL_RCI_INDEX_ENERGY_CORES);
+ write_rapl_counter(&p->energy_dram, rci, RAPL_RCI_INDEX_DRAM);
+ write_rapl_counter(&p->energy_gfx, rci, RAPL_RCI_INDEX_GFX);
+ write_rapl_counter(&p->rapl_pkg_perf_status, rci, RAPL_RCI_INDEX_PKG_PERF_STATUS);
+ write_rapl_counter(&p->rapl_dram_perf_status, rci, RAPL_RCI_INDEX_DRAM_PERF_STATUS);
+ write_rapl_counter(&c->core_energy, rci, RAPL_RCI_INDEX_CORE_ENERGY);
+
+ return 0;
+}
+
/*
* get_counters(...)
* migrate to cpu
@@ -2709,12 +3453,12 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
int cpu = t->cpu_id;
unsigned long long msr;
- int aperf_mperf_retry_count = 0;
struct msr_counter *mp;
int i;
+ int status;
if (cpu_migrate(cpu)) {
- fprintf(outf, "get_counters: Could not migrate to CPU %d\n", cpu);
+ fprintf(outf, "%s: Could not migrate to CPU %d\n", __func__, cpu);
return -1;
}
@@ -2722,63 +3466,26 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
if (first_counter_read)
get_apic_id(t);
-retry:
+
t->tsc = rdtsc(); /* we are running on local CPU of interest */
if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC)
|| soft_c1_residency_display(BIC_Avg_MHz)) {
- unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time;
-
- /*
- * The TSC, APERF and MPERF must be read together for
- * APERF/MPERF and MPERF/TSC to give accurate results.
- *
- * Unfortunately, APERF and MPERF are read by
- * individual system call, so delays may occur
- * between them. If the time to read them
- * varies by a large amount, we re-read them.
- */
-
- /*
- * This initial dummy APERF read has been seen to
- * reduce jitter in the subsequent reads.
- */
-
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
-
- t->tsc = rdtsc(); /* re-read close to APERF */
-
- tsc_before = t->tsc;
+ int status = -1;
- if (get_msr(cpu, MSR_IA32_APERF, &t->aperf))
- return -3;
+ assert(!no_perf || !no_msr);
- tsc_between = rdtsc();
-
- if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
- return -4;
-
- tsc_after = rdtsc();
-
- aperf_time = tsc_between - tsc_before;
- mperf_time = tsc_after - tsc_between;
-
- /*
- * If the system call latency to read APERF and MPERF
- * differ by more than 2x, then try again.
- */
- if ((aperf_time > (2 * mperf_time)) || (mperf_time > (2 * aperf_time))) {
- aperf_mperf_retry_count++;
- if (aperf_mperf_retry_count < 5)
- goto retry;
- else
- warnx("cpu%d jitter %lld %lld", cpu, aperf_time, mperf_time);
+ switch (amperf_source) {
+ case AMPERF_SOURCE_PERF:
+ status = read_aperf_mperf_tsc_perf(t, cpu);
+ break;
+ case AMPERF_SOURCE_MSR:
+ status = read_aperf_mperf_tsc_msr(t, cpu);
+ break;
}
- aperf_mperf_retry_count = 0;
- t->aperf = t->aperf * aperf_mperf_multiplier;
- t->mperf = t->mperf * aperf_mperf_multiplier;
+ if (status != 0)
+ return status;
}
if (DO_BIC(BIC_IPC))
@@ -2806,6 +3513,12 @@ retry:
if (!is_cpu_first_thread_in_core(t, c, p))
goto done;
+ if (platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, c->core_id, c, p);
+ if (status != 0)
+ return status;
+ }
+
if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) {
if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
return -6;
@@ -2846,12 +3559,6 @@ retry:
if (DO_BIC(BIC_CORE_THROT_CNT))
get_core_throt_cnt(cpu, &c->core_throt_cnt);
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
- return -14;
- c->core_energy = msr & 0xFFFFFFFF;
- }
-
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &c->counter[i]))
return -10;
@@ -2911,59 +3618,39 @@ retry:
if (DO_BIC(BIC_SYS_LPI))
p->sys_lpi = cpuidle_cur_sys_lpi_us;
- if (platform->rapl_msrs & RAPL_PKG) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr))
- return -13;
- p->energy_pkg = msr;
- }
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) {
- if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr))
- return -14;
- p->energy_cores = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM) {
- if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr))
- return -15;
- p->energy_dram = msr;
- }
- if (platform->rapl_msrs & RAPL_GFX) {
- if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr))
- return -16;
- p->energy_gfx = msr;
- }
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr))
- return -16;
- p->rapl_pkg_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) {
- if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr))
- return -16;
- p->rapl_dram_perf_status = msr;
- }
- if (platform->rapl_msrs & RAPL_AMD_F17H) {
- if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr))
- return -13;
- p->energy_pkg = msr;
+ if (!platform->has_per_core_rapl) {
+ status = get_rapl_counters(cpu, p->package_id, c, p);
+ if (status != 0)
+ return status;
}
+
if (DO_BIC(BIC_PkgTmp)) {
if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr))
return -17;
p->pkg_temp_c = tj_max - ((msr >> 16) & 0x7F);
}
- if (DO_BIC(BIC_GFX_rc6))
- p->gfx_rc6_ms = gfx_cur_rc6_ms;
-
/* n.b. assume die0 uncore frequency applies to whole package */
if (DO_BIC(BIC_UNCORE_MHZ))
p->uncore_mhz = get_uncore_mhz(p->package_id, 0);
+ if (DO_BIC(BIC_GFX_rc6))
+ p->gfx_rc6_ms = gfx_info[GFX_rc6].val_ull;
+
if (DO_BIC(BIC_GFXMHz))
- p->gfx_mhz = gfx_cur_mhz;
+ p->gfx_mhz = gfx_info[GFX_MHz].val;
if (DO_BIC(BIC_GFXACTMHz))
- p->gfx_act_mhz = gfx_act_mhz;
+ p->gfx_act_mhz = gfx_info[GFX_ACTMHz].val;
+
+ if (DO_BIC(BIC_SAM_mc6))
+ p->sam_mc6_ms = gfx_info[SAM_mc6].val_ull;
+
+ if (DO_BIC(BIC_SAMMHz))
+ p->sam_mhz = gfx_info[SAM_MHz].val;
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ p->sam_act_mhz = gfx_info[SAM_ACTMHz].val;
for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) {
if (get_mp(cpu, mp, &p->counter[i]))
@@ -3053,7 +3740,7 @@ void probe_cst_limit(void)
unsigned long long msr;
int *pkg_cstate_limits;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
switch (platform->cst_limit) {
@@ -3097,7 +3784,7 @@ static void dump_platform_info(void)
unsigned long long msr;
unsigned int ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PLATFORM_INFO, &msr);
@@ -3115,7 +3802,7 @@ static void dump_power_ctl(void)
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr);
@@ -3321,7 +4008,7 @@ static void dump_cst_cfg(void)
{
unsigned long long msr;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
@@ -3393,7 +4080,7 @@ void print_irtl(void)
{
unsigned long long msr;
- if (!platform->has_irtl_msrs)
+ if (!platform->has_irtl_msrs || no_msr)
return;
if (platform->supported_cstates & PC3) {
@@ -3443,12 +4130,64 @@ void free_fd_percpu(void)
{
int i;
+ if (!fd_percpu)
+ return;
+
for (i = 0; i < topo.max_cpu_num + 1; ++i) {
if (fd_percpu[i] != 0)
close(fd_percpu[i]);
}
free(fd_percpu);
+ fd_percpu = NULL;
+}
+
+void free_fd_amperf_percpu(void)
+{
+ int i;
+
+ if (!fd_amperf_percpu)
+ return;
+
+ for (i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_amperf_percpu[i].mperf != 0)
+ close(fd_amperf_percpu[i].mperf);
+
+ if (fd_amperf_percpu[i].aperf != 0)
+ close(fd_amperf_percpu[i].aperf);
+ }
+
+ free(fd_amperf_percpu);
+ fd_amperf_percpu = NULL;
+}
+
+void free_fd_instr_count_percpu(void)
+{
+ if (!fd_instr_count_percpu)
+ return;
+
+ for (int i = 0; i < topo.max_cpu_num + 1; ++i) {
+ if (fd_instr_count_percpu[i] != 0)
+ close(fd_instr_count_percpu[i]);
+ }
+
+ free(fd_instr_count_percpu);
+ fd_instr_count_percpu = NULL;
+}
+
+void free_fd_rapl_percpu(void)
+{
+ if (!rapl_counter_info_perdomain)
+ return;
+
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ if (rapl_counter_info_perdomain[domain_id].fd_perf != -1)
+ close(rapl_counter_info_perdomain[domain_id].fd_perf);
+ }
+
+ free(rapl_counter_info_perdomain);
}
void free_all_buffers(void)
@@ -3492,6 +4231,9 @@ void free_all_buffers(void)
outp = NULL;
free_fd_percpu();
+ free_fd_instr_count_percpu();
+ free_fd_amperf_percpu();
+ free_fd_rapl_percpu();
free(irq_column_2_cpu);
free(irqs_per_cpu);
@@ -3825,11 +4567,17 @@ static void update_effective_set(bool startup)
err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str);
}
+void linux_perf_init(void);
+void rapl_perf_init(void);
+
void re_initialize(void)
{
free_all_buffers();
setup_all_buffers(false);
- fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus);
+ linux_perf_init();
+ rapl_perf_init();
+ fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus,
+ topo.allowed_cpus);
}
void set_max_cpu_num(void)
@@ -3940,85 +4688,43 @@ int snapshot_proc_interrupts(void)
}
/*
- * snapshot_gfx_rc6_ms()
+ * snapshot_graphics()
*
- * record snapshot of
- * /sys/class/drm/card0/power/rc6_residency_ms
+ * record snapshot of specified graphics sysfs knob
*
* return 1 if config change requires a restart, else return 0
*/
-int snapshot_gfx_rc6_ms(void)
+int snapshot_graphics(int idx)
{
FILE *fp;
int retval;
- fp = fopen_or_die("/sys/class/drm/card0/power/rc6_residency_ms", "r");
-
- retval = fscanf(fp, "%lld", &gfx_cur_rc6_ms);
- if (retval != 1)
- err(1, "GFX rc6");
-
- fclose(fp);
-
- return 0;
-}
-
-/*
- * snapshot_gfx_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz
- * when /sys/class/drm/card0/gt_cur_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
- }
-
- retval = fscanf(fp, "%d", &gfx_cur_mhz);
- if (retval != 1)
- err(1, "GFX MHz");
-
- return 0;
-}
-
-/*
- * snapshot_gfx_cur_mhz()
- *
- * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz
- * when /sys/class/drm/card0/gt_act_freq_mhz is not available.
- *
- * return 1 if config change requires a restart, else return 0
- */
-int snapshot_gfx_act_mhz(void)
-{
- static FILE *fp;
- int retval;
-
- if (fp == NULL) {
- fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r");
- if (!fp)
- fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r");
- } else {
- rewind(fp);
- fflush(fp);
+ switch (idx) {
+ case GFX_rc6:
+ case SAM_mc6:
+ fp = fopen_or_die(gfx_info[idx].path, "r");
+ retval = fscanf(fp, "%lld", &gfx_info[idx].val_ull);
+ if (retval != 1)
+ err(1, "rc6");
+ fclose(fp);
+ return 0;
+ case GFX_MHz:
+ case GFX_ACTMHz:
+ case SAM_MHz:
+ case SAM_ACTMHz:
+ if (gfx_info[idx].fp == NULL) {
+ gfx_info[idx].fp = fopen_or_die(gfx_info[idx].path, "r");
+ } else {
+ rewind(gfx_info[idx].fp);
+ fflush(gfx_info[idx].fp);
+ }
+ retval = fscanf(gfx_info[idx].fp, "%d", &gfx_info[idx].val);
+ if (retval != 1)
+ err(1, "MHz");
+ return 0;
+ default:
+ return -EINVAL;
}
-
- retval = fscanf(fp, "%d", &gfx_act_mhz);
- if (retval != 1)
- err(1, "GFX ACT MHz");
-
- return 0;
}
/*
@@ -4083,13 +4789,22 @@ int snapshot_proc_sysfs_files(void)
return 1;
if (DO_BIC(BIC_GFX_rc6))
- snapshot_gfx_rc6_ms();
+ snapshot_graphics(GFX_rc6);
if (DO_BIC(BIC_GFXMHz))
- snapshot_gfx_mhz();
+ snapshot_graphics(GFX_MHz);
if (DO_BIC(BIC_GFXACTMHz))
- snapshot_gfx_act_mhz();
+ snapshot_graphics(GFX_ACTMHz);
+
+ if (DO_BIC(BIC_SAM_mc6))
+ snapshot_graphics(SAM_mc6);
+
+ if (DO_BIC(BIC_SAMMHz))
+ snapshot_graphics(SAM_MHz);
+
+ if (DO_BIC(BIC_SAMACTMHz))
+ snapshot_graphics(SAM_ACTMHz);
if (DO_BIC(BIC_CPU_LPI))
snapshot_cpu_lpi_us();
@@ -4173,6 +4888,8 @@ int get_msr_sum(int cpu, off_t offset, unsigned long long *msr)
int ret, idx;
unsigned long long msr_cur, msr_last;
+ assert(!no_msr);
+
if (!per_cpu_msr_sum)
return 1;
@@ -4201,6 +4918,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg
UNUSED(c);
UNUSED(p);
+ assert(!no_msr);
+
for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
unsigned long long msr_cur, msr_last;
off_t offset;
@@ -4280,7 +4999,8 @@ release_msr:
/*
* set_my_sched_priority(pri)
- * return previous
+ * return previous priority on success
+ * return value < -20 on failure
*/
int set_my_sched_priority(int priority)
{
@@ -4290,16 +5010,16 @@ int set_my_sched_priority(int priority)
errno = 0;
original_priority = getpriority(PRIO_PROCESS, 0);
if (errno && (original_priority == -1))
- err(errno, "getpriority");
+ return -21;
retval = setpriority(PRIO_PROCESS, 0, priority);
if (retval)
- errx(retval, "capget(CAP_SYS_NICE) failed,try \"# setcap cap_sys_nice=ep %s\"", progname);
+ return -21;
errno = 0;
retval = getpriority(PRIO_PROCESS, 0);
if (retval != priority)
- err(retval, "getpriority(%d) != setpriority(%d)", retval, priority);
+ return -21;
return original_priority;
}
@@ -4314,6 +5034,9 @@ void turbostat_loop()
/*
* elevate own priority for interval mode
+ *
+ * ignore on error - we probably don't have permission to set it, but
+ * it's not a big deal
*/
set_my_sched_priority(-20);
@@ -4399,10 +5122,13 @@ void check_dev_msr()
struct stat sb;
char pathname[32];
+ if (no_msr)
+ return;
+
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (stat(pathname, &sb))
if (system("/sbin/modprobe msr > /dev/null 2>&1"))
- err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" ");
+ no_msr = 1;
}
/*
@@ -4414,47 +5140,51 @@ int check_for_cap_sys_rawio(void)
{
cap_t caps;
cap_flag_value_t cap_flag_value;
+ int ret = 0;
caps = cap_get_proc();
if (caps == NULL)
- err(-6, "cap_get_proc\n");
+ return 1;
- if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value))
- err(-6, "cap_get\n");
+ if (cap_get_flag(caps, CAP_SYS_RAWIO, CAP_EFFECTIVE, &cap_flag_value)) {
+ ret = 1;
+ goto free_and_exit;
+ }
if (cap_flag_value != CAP_SET) {
- warnx("capget(CAP_SYS_RAWIO) failed," " try \"# setcap cap_sys_rawio=ep %s\"", progname);
- return 1;
+ ret = 1;
+ goto free_and_exit;
}
+free_and_exit:
if (cap_free(caps) == -1)
err(-6, "cap_free\n");
- return 0;
+ return ret;
}
-void check_permissions(void)
+void check_msr_permission(void)
{
- int do_exit = 0;
+ int failed = 0;
char pathname[32];
+ if (no_msr)
+ return;
+
/* check for CAP_SYS_RAWIO */
- do_exit += check_for_cap_sys_rawio();
+ failed += check_for_cap_sys_rawio();
/* test file permissions */
sprintf(pathname, "/dev/cpu/%d/msr", base_cpu);
if (euidaccess(pathname, R_OK)) {
- do_exit++;
- warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr");
+ failed++;
}
- /* if all else fails, thell them to be root */
- if (do_exit)
- if (getuid() != 0)
- warnx("... or simply run as root");
-
- if (do_exit)
- exit(-6);
+ if (failed) {
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly", pathname, "--no-msr");
+ no_msr = 1;
+ }
}
void probe_bclk(void)
@@ -4462,7 +5192,7 @@ void probe_bclk(void)
unsigned long long msr;
unsigned int base_ratio;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->bclk_freq == BCLK_100MHZ)
@@ -4502,7 +5232,7 @@ static void dump_turbo_ratio_info(void)
if (!has_turbo)
return;
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
return;
if (platform->trl_msrs & TRL_LIMIT2)
@@ -4567,20 +5297,15 @@ static void dump_sysfs_file(char *path)
static void probe_intel_uncore_frequency(void)
{
int i, j;
- char path[128];
+ char path[256];
if (!genuine_intel)
return;
- if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK))
- return;
-
- /* Cluster level sysfs not supported yet. */
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK))
- return;
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
+ goto probe_cluster;
- if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK))
- BIC_PRESENT(BIC_UNCORE_MHZ);
+ BIC_PRESENT(BIC_UNCORE_MHZ);
if (quiet)
return;
@@ -4588,40 +5313,178 @@ static void probe_intel_uncore_frequency(void)
for (i = 0; i < topo.num_packages; ++i) {
for (j = 0; j < topo.num_die; ++j) {
int k, l;
+ char path_base[128];
+
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/package_%02d_die_%02d", i,
+ j);
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/min_freq_khz",
- i, j);
+ sprintf(path, "%s/min_freq_khz", path_base);
k = read_sysfs_int(path);
- sprintf(path, "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/max_freq_khz",
- i, j);
+ sprintf(path, "%s/max_freq_khz", path_base);
l = read_sysfs_int(path);
- fprintf(outf, "Uncore Frequency pkg%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
+ fprintf(outf, "Uncore Frequency package%d die%d: %d - %d MHz ", i, j, k / 1000, l / 1000);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_min_freq_khz",
- i, j);
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
k = read_sysfs_int(path);
- sprintf(path,
- "/sys/devices/system/cpu/intel_uncore_frequency/package_0%d_die_0%d/initial_max_freq_khz",
- i, j);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
l = read_sysfs_int(path);
- fprintf(outf, "(%d - %d MHz)\n", k / 1000, l / 1000);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
}
}
+ return;
+
+probe_cluster:
+ if (access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00/current_freq_khz", R_OK))
+ return;
+
+ if (quiet)
+ return;
+
+ for (i = 0;; ++i) {
+ int k, l;
+ char path_base[128];
+ int package_id, domain_id, cluster_id;
+
+ sprintf(path_base, "/sys/devices/system/cpu/intel_uncore_frequency/uncore%02d", i);
+
+ if (access(path_base, R_OK))
+ break;
+
+ sprintf(path, "%s/package_id", path_base);
+ package_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/domain_id", path_base);
+ domain_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/fabric_cluster_id", path_base);
+ cluster_id = read_sysfs_int(path);
+
+ sprintf(path, "%s/min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "Uncore Frequency package%d domain%d cluster%d: %d - %d MHz ", package_id, domain_id,
+ cluster_id, k / 1000, l / 1000);
+
+ sprintf(path, "%s/initial_min_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ sprintf(path, "%s/initial_max_freq_khz", path_base);
+ l = read_sysfs_int(path);
+ fprintf(outf, "(%d - %d MHz)", k / 1000, l / 1000);
+
+ sprintf(path, "%s/current_freq_khz", path_base);
+ k = read_sysfs_int(path);
+ fprintf(outf, " %d MHz\n", k / 1000);
+ }
}
static void probe_graphics(void)
{
+ /* Xe graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms", R_OK)) {
+ FILE *fp;
+ char buf[8];
+ bool gt0_is_gt;
+ int idx;
+
+ fp = fopen("/sys/class/drm/card0/device/tile0/gt0/gtidle/name", "r");
+ if (!fp)
+ goto next;
+
+ if (!fread(buf, sizeof(char), 7, fp)) {
+ fclose(fp);
+ goto next;
+ }
+ fclose(fp);
+
+ if (!strncmp(buf, "gt0-rc", strlen("gt0-rc")))
+ gt0_is_gt = true;
+ else if (!strncmp(buf, "gt0-mc", strlen("gt0-mc")))
+ gt0_is_gt = false;
+ else
+ goto next;
+
+ idx = gt0_is_gt ? GFX_rc6 : SAM_mc6;
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? GFX_MHz : SAM_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/cur_freq";
+
+ idx = gt0_is_gt ? GFX_ACTMHz : SAM_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt0/freq0/act_freq";
+
+ idx = gt0_is_gt ? SAM_mc6 : GFX_rc6;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/gtidle/idle_residency_ms";
+
+ idx = gt0_is_gt ? SAM_MHz : GFX_MHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/cur_freq";
+
+ idx = gt0_is_gt ? SAM_ACTMHz : GFX_ACTMHz;
+ if (!access("/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq", R_OK))
+ gfx_info[idx].path = "/sys/class/drm/card0/device/tile0/gt1/freq0/act_freq";
+
+ goto end;
+ }
+
+next:
+ /* New i915 graphics sysfs knobs */
+ if (!access("/sys/class/drm/card0/gt/gt0/rc6_residency_ms", R_OK)) {
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/gt/gt0/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt/gt0/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt/gt0/rps_act_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rc6_residency_ms", R_OK))
+ gfx_info[SAM_mc6].path = "/sys/class/drm/card0/gt/gt1/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz", R_OK))
+ gfx_info[SAM_MHz].path = "/sys/class/drm/card0/gt/gt1/rps_cur_freq_mhz";
+
+ if (!access("/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz", R_OK))
+ gfx_info[SAM_ACTMHz].path = "/sys/class/drm/card0/gt/gt1/rps_act_freq_mhz";
+
+ goto end;
+ }
+
+ /* Fall back to traditional i915 graphics sysfs knobs */
if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK))
- BIC_PRESENT(BIC_GFX_rc6);
+ gfx_info[GFX_rc6].path = "/sys/class/drm/card0/power/rc6_residency_ms";
+
+ if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/drm/card0/gt_cur_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
+ gfx_info[GFX_MHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz";
- if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
- BIC_PRESENT(BIC_GFXMHz);
- if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) ||
- !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/drm/card0/gt_act_freq_mhz";
+ else if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK))
+ gfx_info[GFX_ACTMHz].path = "/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz";
+
+end:
+ if (gfx_info[GFX_rc6].path)
+ BIC_PRESENT(BIC_GFX_rc6);
+ if (gfx_info[GFX_MHz].path)
+ BIC_PRESENT(BIC_GFXMHz);
+ if (gfx_info[GFX_ACTMHz].path)
BIC_PRESENT(BIC_GFXACTMHz);
+ if (gfx_info[SAM_mc6].path)
+ BIC_PRESENT(BIC_SAM_mc6);
+ if (gfx_info[SAM_MHz].path)
+ BIC_PRESENT(BIC_SAMMHz);
+ if (gfx_info[SAM_ACTMHz].path)
+ BIC_PRESENT(BIC_SAMACTMHz);
}
static void dump_sysfs_cstate_config(void)
@@ -4783,6 +5646,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!has_hwp)
return 0;
@@ -4869,6 +5735,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
cpu = t->cpu_id;
/* per-package */
@@ -4983,31 +5852,18 @@ void rapl_probe_intel(void)
unsigned long long msr;
unsigned int time_unit;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt | BIC_RAMWatt | BIC_GFXWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J | BIC_RAM_J | BIC_GFX_J;
- if (rapl_joules) {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_Pkg_J);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_Cor_J);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAM_J);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFX_J);
- } else {
- if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS)
- BIC_PRESENT(BIC_PkgWatt);
- if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS)
- BIC_PRESENT(BIC_CorWatt);
- if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS)
- BIC_PRESENT(BIC_RAMWatt);
- if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS)
- BIC_PRESENT(BIC_GFXWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
- if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS)
- BIC_PRESENT(BIC_PKG__);
- if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS)
- BIC_PRESENT(BIC_RAM__);
+ if (!(platform->rapl_msrs & RAPL_PKG_PERF_STATUS))
+ bic_enabled &= ~BIC_PKG__;
+ if (!(platform->rapl_msrs & RAPL_DRAM_PERF_STATUS))
+ bic_enabled &= ~BIC_RAM__;
/* units on package 0, verify later other packages match */
if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr))
@@ -5041,14 +5897,13 @@ void rapl_probe_amd(void)
{
unsigned long long msr;
double tdp;
+ const unsigned long long bic_watt_bits = BIC_PkgWatt | BIC_CorWatt;
+ const unsigned long long bic_joules_bits = BIC_Pkg_J | BIC_Cor_J;
- if (rapl_joules) {
- BIC_PRESENT(BIC_Pkg_J);
- BIC_PRESENT(BIC_Cor_J);
- } else {
- BIC_PRESENT(BIC_PkgWatt);
- BIC_PRESENT(BIC_CorWatt);
- }
+ if (rapl_joules)
+ bic_enabled &= ~bic_watt_bits;
+ else
+ bic_enabled &= ~bic_joules_bits;
if (get_msr(base_cpu, MSR_RAPL_PWR_UNIT, &msr))
return;
@@ -5202,7 +6057,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
*/
void probe_rapl(void)
{
- if (!platform->rapl_msrs)
+ if (!platform->rapl_msrs || no_msr)
return;
if (genuine_intel)
@@ -5258,7 +6113,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
}
/* Temperature Target MSR is Nehalem and newer only */
- if (!platform->has_nhm_msrs)
+ if (!platform->has_nhm_msrs || no_msr)
goto guess;
if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr))
@@ -5305,6 +6160,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
UNUSED(c);
UNUSED(p);
+ if (no_msr)
+ return 0;
+
if (!(do_dts || do_ptm))
return 0;
@@ -5402,6 +6260,9 @@ void decode_feature_control_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!get_msr(base_cpu, MSR_IA32_FEAT_CTL, &msr))
fprintf(outf, "cpu%d: MSR_IA32_FEATURE_CONTROL: 0x%08llx (%sLocked %s)\n",
base_cpu, msr, msr & FEAT_CTL_LOCKED ? "" : "UN-", msr & (1 << 18) ? "SGX" : "");
@@ -5411,6 +6272,9 @@ void decode_misc_enable_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!genuine_intel)
return;
@@ -5428,6 +6292,9 @@ void decode_misc_feature_control(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_feature_control)
return;
@@ -5449,6 +6316,9 @@ void decode_misc_pwr_mgmt_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_misc_pwr_mgmt)
return;
@@ -5468,6 +6338,9 @@ void decode_c6_demotion_policy_msr(void)
{
unsigned long long msr;
+ if (no_msr)
+ return;
+
if (!platform->has_msr_c6_demotion_policy_config)
return;
@@ -5489,7 +6362,8 @@ void print_dev_latency(void)
fd = open(path, O_RDONLY);
if (fd < 0) {
- warnx("capget(CAP_SYS_ADMIN) failed, try \"# setcap cap_sys_admin=ep %s\"", progname);
+ if (debug)
+ warnx("Read %s failed", path);
return;
}
@@ -5504,23 +6378,260 @@ void print_dev_latency(void)
close(fd);
}
+static int has_instr_count_access(void)
+{
+ int fd;
+ int has_access;
+
+ if (no_perf)
+ return 0;
+
+ fd = open_perf_counter(base_cpu, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS, -1, 0);
+ has_access = fd != -1;
+
+ if (fd != -1)
+ close(fd);
+
+ if (!has_access)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "instructions retired perf counter", "--no-perf");
+
+ return has_access;
+}
+
+bool is_aperf_access_required(void)
+{
+ return BIC_IS_ENABLED(BIC_Avg_MHz)
+ || BIC_IS_ENABLED(BIC_Busy)
+ || BIC_IS_ENABLED(BIC_Bzy_MHz)
+ || BIC_IS_ENABLED(BIC_IPC);
+}
+
+int add_rapl_perf_counter_(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale_, enum rapl_unit *unit_)
+{
+ if (no_perf)
+ return -1;
+
+ const double scale = read_perf_rapl_scale(cai->perf_subsys, cai->perf_name);
+
+ if (scale == 0.0)
+ return -1;
+
+ const enum rapl_unit unit = read_perf_rapl_unit(cai->perf_subsys, cai->perf_name);
+
+ if (unit == RAPL_UNIT_INVALID)
+ return -1;
+
+ const unsigned int rapl_type = read_perf_type(cai->perf_subsys);
+ const unsigned int rapl_energy_pkg_config = read_rapl_config(cai->perf_subsys, cai->perf_name);
+
+ const int fd_counter =
+ open_perf_counter(cpu, rapl_type, rapl_energy_pkg_config, rci->fd_perf, PERF_FORMAT_GROUP);
+ if (fd_counter == -1)
+ return -1;
+
+ /* If it's the first counter opened, make it a group descriptor */
+ if (rci->fd_perf == -1)
+ rci->fd_perf = fd_counter;
+
+ *scale_ = scale;
+ *unit_ = unit;
+ return fd_counter;
+}
+
+int add_rapl_perf_counter(int cpu, struct rapl_counter_info_t *rci, const struct rapl_counter_arch_info *cai,
+ double *scale, enum rapl_unit *unit)
+{
+ int ret = add_rapl_perf_counter_(cpu, rci, cai, scale, unit);
+
+ if (debug)
+ fprintf(stderr, "%s: %d (cpu: %d)\n", __func__, ret, cpu);
+
+ return ret;
+}
+
/*
* Linux-perf manages the HW instructions-retired counter
* by enabling when requested, and hiding rollover
*/
void linux_perf_init(void)
{
- if (!BIC_IS_ENABLED(BIC_IPC))
- return;
-
if (access("/proc/sys/kernel/perf_event_paranoid", F_OK))
return;
- fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
- if (fd_instr_count_percpu == NULL)
- err(-1, "calloc fd_instr_count_percpu");
+ if (BIC_IS_ENABLED(BIC_IPC) && has_aperf) {
+ fd_instr_count_percpu = calloc(topo.max_cpu_num + 1, sizeof(int));
+ if (fd_instr_count_percpu == NULL)
+ err(-1, "calloc fd_instr_count_percpu");
+ }
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (aperf_required && has_aperf && amperf_source == AMPERF_SOURCE_PERF) {
+ fd_amperf_percpu = calloc(topo.max_cpu_num + 1, sizeof(*fd_amperf_percpu));
+ if (fd_amperf_percpu == NULL)
+ err(-1, "calloc fd_amperf_percpu");
+ }
+}
+
+void rapl_perf_init(void)
+{
+ const int num_domains = platform->has_per_core_rapl ? topo.num_cores : topo.num_packages;
+ bool *domain_visited = calloc(num_domains, sizeof(bool));
+
+ rapl_counter_info_perdomain = calloc(num_domains, sizeof(*rapl_counter_info_perdomain));
+ if (rapl_counter_info_perdomain == NULL)
+ err(-1, "calloc rapl_counter_info_percpu");
+
+ /*
+ * Initialize rapl_counter_info_percpu
+ */
+ for (int domain_id = 0; domain_id < num_domains; ++domain_id) {
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[domain_id];
+
+ rci->fd_perf = -1;
+ for (size_t i = 0; i < NUM_RAPL_COUNTERS; ++i) {
+ rci->data[i] = 0;
+ rci->source[i] = RAPL_SOURCE_NONE;
+ }
+ }
- BIC_PRESENT(BIC_IPC);
+ /*
+ * Open/probe the counters
+ * If can't get it via perf, fallback to MSR
+ */
+ for (size_t i = 0; i < ARRAY_SIZE(rapl_counter_arch_infos); ++i) {
+
+ const struct rapl_counter_arch_info *const cai = &rapl_counter_arch_infos[i];
+ bool has_counter = 0;
+ double scale;
+ enum rapl_unit unit;
+ int next_domain;
+
+ memset(domain_visited, 0, num_domains * sizeof(*domain_visited));
+
+ for (int cpu = 0; cpu < topo.max_cpu_num + 1; ++cpu) {
+
+ if (cpu_is_not_allowed(cpu))
+ continue;
+
+ /* Skip already seen and handled RAPL domains */
+ next_domain =
+ platform->has_per_core_rapl ? cpus[cpu].physical_core_id : cpus[cpu].physical_package_id;
+
+ if (domain_visited[next_domain])
+ continue;
+
+ domain_visited[next_domain] = 1;
+
+ struct rapl_counter_info_t *rci = &rapl_counter_info_perdomain[next_domain];
+
+ /* Check if the counter is enabled and accessible */
+ if (BIC_IS_ENABLED(cai->bic) && (platform->rapl_msrs & cai->feature_mask)) {
+
+ /* Use perf API for this counter */
+ if (!no_perf && cai->perf_name
+ && add_rapl_perf_counter(cpu, rci, cai, &scale, &unit) != -1) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_PERF;
+ rci->scale[cai->rci_index] = scale * cai->compat_scale;
+ rci->unit[cai->rci_index] = unit;
+ rci->flags[cai->rci_index] = cai->flags;
+
+ /* Use MSR for this counter */
+ } else if (!no_msr && cai->msr && probe_msr(cpu, cai->msr) == 0) {
+ rci->source[cai->rci_index] = RAPL_SOURCE_MSR;
+ rci->msr[cai->rci_index] = cai->msr;
+ rci->msr_mask[cai->rci_index] = cai->msr_mask;
+ rci->msr_shift[cai->rci_index] = cai->msr_shift;
+ rci->unit[cai->rci_index] = RAPL_UNIT_JOULES;
+ rci->scale[cai->rci_index] = *cai->platform_rapl_msr_scale * cai->compat_scale;
+ rci->flags[cai->rci_index] = cai->flags;
+ }
+ }
+
+ if (rci->source[cai->rci_index] != RAPL_SOURCE_NONE)
+ has_counter = 1;
+ }
+
+ /* If any CPU has access to the counter, make it present */
+ if (has_counter)
+ BIC_PRESENT(cai->bic);
+ }
+
+ free(domain_visited);
+}
+
+static int has_amperf_access_via_msr(void)
+{
+ if (no_msr)
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_APERF))
+ return 0;
+
+ if (probe_msr(base_cpu, MSR_IA32_MPERF))
+ return 0;
+
+ return 1;
+}
+
+static int has_amperf_access_via_perf(void)
+{
+ struct amperf_group_fd fds;
+
+ /*
+ * Cache the last result, so we don't warn the user multiple times
+ *
+ * Negative means cached, no access
+ * Zero means not cached
+ * Positive means cached, has access
+ */
+ static int has_access_cached;
+
+ if (no_perf)
+ return 0;
+
+ if (has_access_cached != 0)
+ return has_access_cached > 0;
+
+ fds = open_amperf_fd(base_cpu);
+ has_access_cached = (fds.aperf != -1) && (fds.mperf != -1);
+
+ if (fds.aperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "APERF perf counter", "--no-perf");
+ else
+ close(fds.aperf);
+
+ if (fds.mperf == -1)
+ warnx("Failed to access %s. Some of the counters may not be available\n"
+ "\tRun as root to enable them or use %s to disable the access explicitly",
+ "MPERF perf counter", "--no-perf");
+ else
+ close(fds.mperf);
+
+ if (has_access_cached == 0)
+ has_access_cached = -1;
+
+ return has_access_cached > 0;
+}
+
+/* Check if we can access APERF and MPERF */
+static int has_amperf_access(void)
+{
+ if (!is_aperf_access_required())
+ return 0;
+
+ if (!no_msr && has_amperf_access_via_msr())
+ return 1;
+
+ if (!no_perf && has_amperf_access_via_perf())
+ return 1;
+
+ return 0;
}
void probe_cstates(void)
@@ -5563,7 +6674,7 @@ void probe_cstates(void)
if (platform->has_msr_module_c6_res_ms)
BIC_PRESENT(BIC_Mod_c6);
- if (platform->has_ext_cst_msrs) {
+ if (platform->has_ext_cst_msrs && !no_msr) {
BIC_PRESENT(BIC_Totl_c0);
BIC_PRESENT(BIC_Any_c0);
BIC_PRESENT(BIC_GFX_c0);
@@ -5623,6 +6734,7 @@ void process_cpuid()
unsigned int eax, ebx, ecx, edx;
unsigned int fms, family, model, stepping, ecx_flags, edx_flags;
unsigned long long ucode_patch = 0;
+ bool ucode_patch_valid = false;
eax = ebx = ecx = edx = 0;
@@ -5650,8 +6762,12 @@ void process_cpuid()
ecx_flags = ecx;
edx_flags = edx;
- if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
- warnx("get_msr(UCODE)");
+ if (!no_msr) {
+ if (get_msr(sched_getcpu(), MSR_IA32_UCODE_REV, &ucode_patch))
+ warnx("get_msr(UCODE)");
+ else
+ ucode_patch_valid = true;
+ }
/*
* check max extended function levels of CPUID.
@@ -5662,9 +6778,12 @@ void process_cpuid()
__cpuid(0x80000000, max_extended_level, ebx, ecx, edx);
if (!quiet) {
- fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d) microcode 0x%x\n",
- family, model, stepping, family, model, stepping,
- (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fprintf(outf, "CPUID(1): family:model:stepping 0x%x:%x:%x (%d:%d:%d)",
+ family, model, stepping, family, model, stepping);
+ if (ucode_patch_valid)
+ fprintf(outf, " microcode 0x%x", (unsigned int)((ucode_patch >> 32) & 0xFFFFFFFF));
+ fputc('\n', outf);
+
fprintf(outf, "CPUID(0x80000000): max_extended_levels: 0x%x\n", max_extended_level);
fprintf(outf, "CPUID(1): %s %s %s %s %s %s %s %s %s %s\n",
ecx_flags & (1 << 0) ? "SSE3" : "-",
@@ -5700,10 +6819,11 @@ void process_cpuid()
__cpuid(0x6, eax, ebx, ecx, edx);
has_aperf = ecx & (1 << 0);
- if (has_aperf) {
+ if (has_aperf && has_amperf_access()) {
BIC_PRESENT(BIC_Avg_MHz);
BIC_PRESENT(BIC_Busy);
BIC_PRESENT(BIC_Bzy_MHz);
+ BIC_PRESENT(BIC_IPC);
}
do_dts = eax & (1 << 0);
if (do_dts)
@@ -5786,6 +6906,15 @@ void process_cpuid()
base_mhz = max_mhz = bus_mhz = edx = 0;
__cpuid(0x16, base_mhz, max_mhz, bus_mhz, edx);
+
+ bclk = bus_mhz;
+
+ base_hz = base_mhz * 1000000;
+ has_base_hz = 1;
+
+ if (platform->enable_tsc_tweak)
+ tsc_tweak = base_hz / tsc_hz;
+
if (!quiet)
fprintf(outf, "CPUID(0x16): base_mhz: %d max_mhz: %d bus_mhz: %d\n",
base_mhz, max_mhz, bus_mhz);
@@ -5814,7 +6943,7 @@ void probe_pm_features(void)
probe_thermal();
- if (platform->has_nhm_msrs)
+ if (platform->has_nhm_msrs && !no_msr)
BIC_PRESENT(BIC_SMI);
if (!quiet)
@@ -6142,6 +7271,7 @@ void topology_update(void)
topo.allowed_packages = 0;
for_all_cpus(update_topo, ODD_COUNTERS);
}
+
void setup_all_buffers(bool startup)
{
topology_probe(startup);
@@ -6169,21 +7299,129 @@ void set_base_cpu(void)
err(-ENODEV, "No valid cpus found");
}
+static void set_amperf_source(void)
+{
+ amperf_source = AMPERF_SOURCE_PERF;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (no_perf || !aperf_required || !has_amperf_access_via_perf())
+ amperf_source = AMPERF_SOURCE_MSR;
+
+ if (quiet || !debug)
+ return;
+
+ fprintf(outf, "aperf/mperf source preference: %s\n", amperf_source == AMPERF_SOURCE_MSR ? "msr" : "perf");
+}
+
+bool has_added_counters(void)
+{
+ /*
+ * It only makes sense to call this after the command line is parsed,
+ * otherwise sys structure is not populated.
+ */
+
+ return sys.added_core_counters | sys.added_thread_counters | sys.added_package_counters;
+}
+
+bool is_msr_access_required(void)
+{
+ if (no_msr)
+ return false;
+
+ if (has_added_counters())
+ return true;
+
+ return BIC_IS_ENABLED(BIC_SMI)
+ || BIC_IS_ENABLED(BIC_CPU_c1)
+ || BIC_IS_ENABLED(BIC_CPU_c3)
+ || BIC_IS_ENABLED(BIC_CPU_c6)
+ || BIC_IS_ENABLED(BIC_CPU_c7)
+ || BIC_IS_ENABLED(BIC_Mod_c6)
+ || BIC_IS_ENABLED(BIC_CoreTmp)
+ || BIC_IS_ENABLED(BIC_Totl_c0)
+ || BIC_IS_ENABLED(BIC_Any_c0)
+ || BIC_IS_ENABLED(BIC_GFX_c0)
+ || BIC_IS_ENABLED(BIC_CPUGFX)
+ || BIC_IS_ENABLED(BIC_Pkgpc3)
+ || BIC_IS_ENABLED(BIC_Pkgpc6)
+ || BIC_IS_ENABLED(BIC_Pkgpc2)
+ || BIC_IS_ENABLED(BIC_Pkgpc7)
+ || BIC_IS_ENABLED(BIC_Pkgpc8)
+ || BIC_IS_ENABLED(BIC_Pkgpc9)
+ || BIC_IS_ENABLED(BIC_Pkgpc10)
+ /* TODO: Multiplex access with perf */
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_PkgWatt)
+ || BIC_IS_ENABLED(BIC_CorWatt)
+ || BIC_IS_ENABLED(BIC_GFXWatt)
+ || BIC_IS_ENABLED(BIC_RAMWatt)
+ || BIC_IS_ENABLED(BIC_Pkg_J)
+ || BIC_IS_ENABLED(BIC_Cor_J)
+ || BIC_IS_ENABLED(BIC_GFX_J)
+ || BIC_IS_ENABLED(BIC_RAM_J)
+ || BIC_IS_ENABLED(BIC_PKG__)
+ || BIC_IS_ENABLED(BIC_RAM__)
+ || BIC_IS_ENABLED(BIC_PkgTmp)
+ || (is_aperf_access_required() && !has_amperf_access_via_perf());
+}
+
+void check_msr_access(void)
+{
+ if (!is_msr_access_required())
+ no_msr = 1;
+
+ check_dev_msr();
+ check_msr_permission();
+
+ if (no_msr)
+ bic_disable_msr_access();
+}
+
+void check_perf_access(void)
+{
+ const bool intrcount_required = BIC_IS_ENABLED(BIC_IPC);
+
+ if (no_perf || !intrcount_required || !has_instr_count_access())
+ bic_enabled &= ~BIC_IPC;
+
+ const bool aperf_required = is_aperf_access_required();
+
+ if (!aperf_required || !has_amperf_access()) {
+ bic_enabled &= ~BIC_Avg_MHz;
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ bic_enabled &= ~BIC_IPC;
+ }
+}
+
void turbostat_init()
{
setup_all_buffers(true);
set_base_cpu();
- check_dev_msr();
- check_permissions();
+ check_msr_access();
+ check_perf_access();
process_cpuid();
probe_pm_features();
+ set_amperf_source();
linux_perf_init();
+ rapl_perf_init();
for_all_cpus(get_cpu_type, ODD_COUNTERS);
for_all_cpus(get_cpu_type, EVEN_COUNTERS);
if (DO_BIC(BIC_IPC))
(void)get_instr_count_fd(base_cpu);
+
+ /*
+ * If TSC tweak is needed, but couldn't get it,
+ * disable more BICs, since it can't be reported accurately.
+ */
+ if (platform->enable_tsc_tweak && !has_base_hz) {
+ bic_enabled &= ~BIC_Busy;
+ bic_enabled &= ~BIC_Bzy_MHz;
+ }
}
int fork_it(char **argv)
@@ -6259,7 +7497,7 @@ int get_and_dump_counters(void)
void print_version()
{
- fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n");
+ fprintf(outf, "turbostat version 2024.04.08 - Len Brown <lenb@kernel.org>\n");
}
#define COMMAND_LINE_SIZE 2048
@@ -6291,6 +7529,9 @@ int add_counter(unsigned int msr_num, char *path, char *name,
{
struct msr_counter *msrp;
+ if (no_msr && msr_num)
+ errx(1, "Requested MSR counter 0x%x, but in --no-msr mode", msr_num);
+
msrp = calloc(1, sizeof(struct msr_counter));
if (msrp == NULL) {
perror("calloc");
@@ -6595,6 +7836,8 @@ void cmdline(int argc, char **argv)
{ "list", no_argument, 0, 'l' },
{ "out", required_argument, 0, 'o' },
{ "quiet", no_argument, 0, 'q' },
+ { "no-msr", no_argument, 0, 'M' },
+ { "no-perf", no_argument, 0, 'P' },
{ "show", required_argument, 0, 's' },
{ "Summary", no_argument, 0, 'S' },
{ "TCC", required_argument, 0, 'T' },
@@ -6604,7 +7847,25 @@ void cmdline(int argc, char **argv)
progname = argv[0];
- while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v", long_options, &option_index)) != -1) {
+ /*
+ * Parse some options early, because they may make other options invalid,
+ * like adding the MSR counter with --add and at the same time using --no-msr.
+ */
+ while ((opt = getopt_long_only(argc, argv, "MP", long_options, &option_index)) != -1) {
+ switch (opt) {
+ case 'M':
+ no_msr = 1;
+ break;
+ case 'P':
+ no_perf = 1;
+ break;
+ default:
+ break;
+ }
+ }
+ optind = 0;
+
+ while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qMST:v", long_options, &option_index)) != -1) {
switch (opt) {
case 'a':
parse_add_command(optarg);
@@ -6662,6 +7923,10 @@ void cmdline(int argc, char **argv)
case 'q':
quiet = 1;
break;
+ case 'M':
+ case 'P':
+ /* Parsed earlier */
+ break;
case 'n':
num_iterations = strtod(optarg, NULL);
@@ -6704,6 +7969,22 @@ void cmdline(int argc, char **argv)
}
}
+void set_rlimit(void)
+{
+ struct rlimit limit;
+
+ if (getrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to get rlimit");
+
+ if (limit.rlim_max < MAX_NOFILE)
+ limit.rlim_max = MAX_NOFILE;
+ if (limit.rlim_cur < MAX_NOFILE)
+ limit.rlim_cur = MAX_NOFILE;
+
+ if (setrlimit(RLIMIT_NOFILE, &limit) < 0)
+ err(1, "Failed to set rlimit");
+}
+
int main(int argc, char **argv)
{
int fd, ret;
@@ -6729,9 +8010,13 @@ skip_cgroup_setting:
probe_sysfs();
+ if (!getuid())
+ set_rlimit();
+
turbostat_init();
- msr_sum_record();
+ if (!no_msr)
+ msr_sum_record();
/* dump counters and exit */
if (dump_only)
diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h
index c02990bbd56f..9007c420d52c 100644
--- a/tools/testing/selftests/mm/vm_util.h
+++ b/tools/testing/selftests/mm/vm_util.h
@@ -3,7 +3,7 @@
#include <stdbool.h>
#include <sys/mman.h>
#include <err.h>
-#include <string.h> /* ffsl() */
+#include <strings.h> /* ffsl() */
#include <unistd.h> /* _SC_PAGESIZE */
#define BIT_ULL(nr) (1ULL << (nr))
diff --git a/tools/testing/selftests/turbostat/defcolumns.py b/tools/testing/selftests/turbostat/defcolumns.py
new file mode 100755
index 000000000000..d9b042097da7
--- /dev/null
+++ b/tools/testing/selftests/turbostat/defcolumns.py
@@ -0,0 +1,60 @@
+#!/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import subprocess
+from shutil import which
+
+turbostat = which('turbostat')
+if turbostat is None:
+ print('Could not find turbostat binary')
+ exit(1)
+
+timeout = which('timeout')
+if timeout is None:
+ print('Could not find timeout binary')
+ exit(1)
+
+proc_turbostat = subprocess.run([turbostat, '--list'], capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+
+#
+# By default --list reports also "usec" and "Time_Of_Day_Seconds" columns
+# which are only visible when running with --debug.
+#
+expected_columns_debug = proc_turbostat.stdout.replace(b',', b'\t').strip()
+expected_columns = expected_columns_debug.replace(b'usec\t', b'').replace(b'Time_Of_Day_Seconds\t', b'').replace(b'X2APIC\t', b'').replace(b'APIC\t', b'')
+
+#
+# Run turbostat with no options for 10 seconds and send SIGINT
+#
+timeout_argv = [timeout, '--preserve-status', '-s', 'SIGINT', '-k', '3', '1s']
+turbostat_argv = [turbostat, '-i', '0.250']
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns=}\n{actual_columns=}')
+ exit(1)
+print('OK')
+
+#
+# Same, but with --debug
+#
+turbostat_argv.append('--debug')
+
+print(f'Running turbostat with {turbostat_argv=}... ', end = '', flush = True)
+proc_turbostat = subprocess.run(timeout_argv + turbostat_argv, capture_output = True)
+if proc_turbostat.returncode != 0:
+ print(f'turbostat failed with {proc_turbostat.returncode}')
+ exit(1)
+actual_columns = proc_turbostat.stdout.split(b'\n')[0]
+if expected_columns_debug != actual_columns:
+ print(f'turbostat column check failed\n{expected_columns_debug=}\n{actual_columns=}')
+ exit(1)
+print('OK')