summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorPaolo Bonzini <pbonzini@redhat.com>2021-09-06 13:34:11 +0300
committerPaolo Bonzini <pbonzini@redhat.com>2021-09-06 13:34:48 +0300
commite99314a340d27efafab3b7ea226beb239162cd46 (patch)
treee16aebf4ddd982518c89eda4ccebdaff1c430723
parent0d0a19395baa36ab186df8081ab7f7b57c3fade1 (diff)
parent419025b3b4190ee867ef4fc48fb3bd7da2e67a0c (diff)
downloadlinux-e99314a340d27efafab3b7ea226beb239162cd46.tar.xz
Merge tag 'kvmarm-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for 5.15 - Page ownership tracking between host EL1 and EL2 - Rely on userspace page tables to create large stage-2 mappings - Fix incompatibility between pKVM and kmemleak - Fix the PMU reset state, and improve the performance of the virtual PMU - Move over to the generic KVM entry code - Address PSCI reset issues w.r.t. save/restore - Preliminary rework for the upcoming pKVM fixed feature - A bunch of MM cleanups - a vGIC fix for timer spurious interrupts - Various cleanups
-rw-r--r--Documentation/arm64/tagged-address-abi.rst26
-rw-r--r--Documentation/devicetree/bindings/net/imx-dwmac.txt56
-rw-r--r--Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml93
-rw-r--r--Documentation/devicetree/bindings/net/snps,dwmac.yaml3
-rw-r--r--Documentation/devicetree/bindings/regulator/fixed-regulator.yaml2
-rw-r--r--Documentation/devicetree/bindings/sound/renesas,rsnd.yaml2
-rw-r--r--Documentation/networking/af_xdp.rst6
-rw-r--r--Documentation/networking/ip-sysctl.rst2
-rw-r--r--Documentation/trace/histogram.rst2
-rw-r--r--MAINTAINERS27
-rw-r--r--Makefile2
-rw-r--r--arch/alpha/Kconfig3
-rw-r--r--arch/alpha/boot/bootp.c2
-rw-r--r--arch/alpha/boot/bootpz.c2
-rw-r--r--arch/alpha/boot/misc.c2
-rw-r--r--arch/alpha/configs/defconfig1
-rw-r--r--arch/alpha/include/asm/compiler.h11
-rw-r--r--arch/alpha/include/asm/syscall.h6
-rw-r--r--arch/alpha/kernel/osf_sys.c4
-rw-r--r--arch/alpha/kernel/perf_event.c2
-rw-r--r--arch/alpha/kernel/process.c2
-rw-r--r--arch/alpha/kernel/setup.c13
-rw-r--r--arch/alpha/kernel/smp.c2
-rw-r--r--arch/alpha/kernel/sys_nautilus.c2
-rw-r--r--arch/alpha/kernel/traps.c2
-rw-r--r--arch/alpha/math-emu/math.c8
-rw-r--r--arch/arm/Kconfig6
-rw-r--r--arch/arm/mach-davinci/Kconfig1
-rw-r--r--arch/arm/mach-rpc/riscpc.c1
-rw-r--r--arch/arm/net/bpf_jit_32.c3
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp.dtsi10
-rw-r--r--arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/ipq8074.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/msm8996.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/msm8998.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/qcs404-evb.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/qcs404.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/sc7180.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/sdm845.dtsi4
-rw-r--r--arch/arm64/boot/dts/qcom/sm8150.dtsi2
-rw-r--r--arch/arm64/include/asm/cpufeature.h27
-rw-r--r--arch/arm64/include/asm/kvm_arm.h54
-rw-r--r--arch/arm64/include/asm/kvm_asm.h7
-rw-r--r--arch/arm64/include/asm/kvm_host.h17
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h2
-rw-r--r--arch/arm64/include/asm/kvm_mmu.h17
-rw-r--r--arch/arm64/include/asm/kvm_pgtable.h168
-rw-r--r--arch/arm64/include/asm/sysreg.h54
-rw-r--r--arch/arm64/kernel/cpufeature.c8
-rw-r--r--arch/arm64/kernel/smccc-call.S9
-rw-r--r--arch/arm64/kernel/vmlinux.lds.S4
-rw-r--r--arch/arm64/kvm/Kconfig10
-rw-r--r--arch/arm64/kvm/arm.c173
-rw-r--r--arch/arm64/kvm/debug.c2
-rw-r--r--arch/arm64/kvm/guest.c5
-rw-r--r--arch/arm64/kvm/handle_exit.c43
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h6
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/mem_protect.h35
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/mm.h3
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/spinlock.h25
-rw-r--r--arch/arm64/kvm/hyp/nvhe/debug-sr.c2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/host.S21
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c20
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c244
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mm.c22
-rw-r--r--arch/arm64/kvm/hyp/nvhe/setup.c82
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c17
-rw-r--r--arch/arm64/kvm/hyp/nvhe/tlb.c4
-rw-r--r--arch/arm64/kvm/hyp/pgtable.c247
-rw-r--r--arch/arm64/kvm/hyp/vhe/debug-sr.c2
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c18
-rw-r--r--arch/arm64/kvm/hyp/vhe/sysreg-sr.c2
-rw-r--r--arch/arm64/kvm/hyp/vhe/tlb.c4
-rw-r--r--arch/arm64/kvm/mmu.c75
-rw-r--r--arch/arm64/kvm/perf.c2
-rw-r--r--arch/arm64/kvm/pmu-emul.c14
-rw-r--r--arch/arm64/kvm/psci.c15
-rw-r--r--arch/arm64/kvm/reset.c43
-rw-r--r--arch/arm64/kvm/sys_regs.c134
-rw-r--r--arch/arm64/kvm/sys_regs.h31
-rw-r--r--arch/arm64/kvm/trace_handle_exit.h10
-rw-r--r--arch/arm64/kvm/vgic/vgic-mmio-v2.c4
-rw-r--r--arch/arm64/kvm/vgic/vgic-v2.c36
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3.c36
-rw-r--r--arch/arm64/kvm/vgic/vgic.c39
-rw-r--r--arch/arm64/kvm/vgic/vgic.h2
-rw-r--r--arch/arm64/mm/mmu.c20
-rw-r--r--arch/arm64/net/bpf_jit_comp.c13
-rw-r--r--arch/h8300/Kconfig.cpu1
-rw-r--r--arch/ia64/Kconfig1
-rw-r--r--arch/m68k/Kconfig1
-rw-r--r--arch/m68k/Kconfig.machine1
-rw-r--r--arch/m68k/coldfire/m525x.c2
-rw-r--r--arch/mips/Kconfig1
-rw-r--r--arch/mips/net/ebpf_jit.c3
-rw-r--r--arch/nds32/mm/mmap.c2
-rw-r--r--arch/parisc/Kconfig1
-rw-r--r--arch/powerpc/Kconfig1
-rw-r--r--arch/powerpc/kernel/vdso64/Makefile7
-rw-r--r--arch/powerpc/kvm/book3s_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_hv_nested.c20
-rw-r--r--arch/powerpc/kvm/book3s_hv_p9_entry.c25
-rw-r--r--arch/powerpc/kvm/book3s_rtas.c25
-rw-r--r--arch/powerpc/kvm/powerpc.c4
-rw-r--r--arch/powerpc/mm/nohash/8xx.c10
-rw-r--r--arch/powerpc/net/bpf_jit_comp32.c6
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c6
-rw-r--r--arch/powerpc/platforms/pasemi/idle.c1
-rw-r--r--arch/powerpc/platforms/pseries/setup.c2
-rw-r--r--arch/riscv/include/asm/efi.h4
-rw-r--r--arch/riscv/kernel/stacktrace.c6
-rw-r--r--arch/riscv/lib/uaccess.S27
-rw-r--r--arch/riscv/mm/init.c32
-rw-r--r--arch/riscv/net/bpf_jit_comp32.c4
-rw-r--r--arch/riscv/net/bpf_jit_comp64.c4
-rw-r--r--arch/s390/boot/text_dma.S19
-rw-r--r--arch/s390/configs/debug_defconfig27
-rw-r--r--arch/s390/configs/defconfig27
-rw-r--r--arch/s390/configs/zfcpdump_defconfig3
-rw-r--r--arch/s390/include/asm/ftrace.h1
-rw-r--r--arch/s390/kernel/ftrace.c2
-rw-r--r--arch/s390/kernel/mcount.S4
-rw-r--r--arch/s390/kernel/perf_cpum_cf.c2
-rw-r--r--arch/s390/kernel/vdso32/Makefile1
-rw-r--r--arch/s390/net/bpf_jit_comp.c7
-rw-r--r--arch/sh/Kconfig1
-rw-r--r--arch/sparc/Kconfig1
-rw-r--r--arch/sparc/net/bpf_jit_comp_64.c3
-rw-r--r--arch/x86/Kconfig1
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c2
-rw-r--r--arch/x86/kernel/jump_label.c7
-rw-r--r--arch/x86/mm/pgtable.c34
-rw-r--r--arch/x86/net/bpf_jit_comp.c7
-rw-r--r--arch/x86/net/bpf_jit_comp32.c6
-rw-r--r--arch/xtensa/Kconfig1
-rw-r--r--block/blk-iocost.c11
-rw-r--r--block/blk-mq-sched.c17
-rw-r--r--block/genhd.c3
-rw-r--r--drivers/acpi/Kconfig2
-rw-r--r--drivers/acpi/dptf/dptf_pch_fivr.c51
-rw-r--r--drivers/acpi/resource.c9
-rw-r--r--drivers/acpi/utils.c7
-rw-r--r--drivers/acpi/x86/s2idle.c10
-rw-r--r--drivers/ata/libata-sff.c35
-rw-r--r--drivers/base/auxiliary.c8
-rw-r--r--drivers/base/core.c6
-rw-r--r--drivers/block/loop.c128
-rw-r--r--drivers/block/rbd.c33
-rw-r--r--drivers/bus/mhi/core/main.c17
-rw-r--r--drivers/bus/mhi/pci_generic.c45
-rw-r--r--drivers/firmware/efi/dev-path-parser.c1
-rw-r--r--drivers/firmware/efi/efi.c13
-rw-r--r--drivers/firmware/efi/libstub/efi-stub-helper.c4
-rw-r--r--drivers/firmware/efi/mokvar-table.c5
-rw-r--r--drivers/firmware/efi/tpm.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu.h7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c8
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/nv.c248
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v12_0.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c176
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c59
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h54
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c12
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_resource.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc.h10
-rw-r--r--drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c50
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c16
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c13
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c13
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c18
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c5
-rw-r--r--drivers/gpu/drm/amd/display/dc/inc/hw/transform.h3
-rw-r--r--drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h1
-rw-r--r--drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h3
-rw-r--r--drivers/gpu/drm/amd/pm/inc/smu_types.h3
-rw-r--r--drivers/gpu/drm/amd/pm/inc/smu_v11_0.h2
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c46
-rw-r--r--drivers/gpu/drm/drm_ioctl.c3
-rw-r--r--drivers/gpu/drm/i915/display/intel_bios.c3
-rw-r--r--drivers/gpu/drm/i915/display/intel_display.c8
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c227
-rw-r--r--drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c4
-rw-r--r--drivers/gpu/drm/i915/gvt/handlers.c15
-rw-r--r--drivers/gpu/drm/i915/i915_cmd_parser.c136
-rw-r--r--drivers/gpu/drm/i915/i915_drv.h7
-rw-r--r--drivers/gpu/drm/i915/i915_request.c8
-rw-r--r--drivers/gpu/drm/i915/intel_device_info.c9
-rw-r--r--drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c2
-rw-r--r--drivers/gpu/drm/msm/dp/dp_catalog.c1
-rw-r--r--drivers/gpu/drm/msm/dp/dp_ctrl.c2
-rw-r--r--drivers/gpu/drm/msm/dp/dp_display.c5
-rw-r--r--drivers/gpu/drm/msm/msm_iommu.c11
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_bo.c6
-rw-r--r--drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c1
-rw-r--r--drivers/gpu/drm/panel/panel-simple.c2
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo.c3
-rw-r--r--drivers/gpu/drm/ttm/ttm_bo_util.c3
-rw-r--r--drivers/gpu/drm/ttm/ttm_device.c14
-rw-r--r--drivers/gpu/drm/ttm/ttm_module.c16
-rw-r--r--drivers/gpu/drm/vc4/vc4_hdmi.c49
-rw-r--r--drivers/hid/Kconfig2
-rw-r--r--drivers/hid/amd-sfh-hid/amd_sfh_pcie.c2
-rw-r--r--drivers/hid/hid-apple.c2
-rw-r--r--drivers/hid/hid-asus.c3
-rw-r--r--drivers/hid/hid-ft260.c27
-rw-r--r--drivers/hid/intel-ish-hid/ishtp-hid-client.c15
-rw-r--r--drivers/hid/intel-ish-hid/ishtp-hid.h1
-rw-r--r--drivers/hid/intel-ish-hid/ishtp/bus.c29
-rw-r--r--drivers/hid/usbhid/Kconfig2
-rw-r--r--drivers/hid/wacom_wac.c5
-rw-r--r--drivers/hv/channel_mgmt.c96
-rw-r--r--drivers/i2c/busses/i2c-mpc.c4
-rw-r--r--drivers/infiniband/hw/bnxt_re/main.c4
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_res.c10
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_res.h1
-rw-r--r--drivers/infiniband/hw/irdma/ctrl.c13
-rw-r--r--drivers/infiniband/hw/irdma/hw.c11
-rw-r--r--drivers/infiniband/hw/irdma/main.c9
-rw-r--r--drivers/infiniband/hw/irdma/type.h3
-rw-r--r--drivers/infiniband/hw/irdma/uk.c5
-rw-r--r--drivers/infiniband/hw/irdma/verbs.c6
-rw-r--r--drivers/infiniband/sw/rxe/rxe_mr.c27
-rw-r--r--drivers/media/pci/intel/ipu3/cio2-bridge.c6
-rw-r--r--drivers/media/pci/ngene/ngene-core.c2
-rw-r--r--drivers/media/pci/ngene/ngene.h14
-rw-r--r--drivers/misc/eeprom/at24.c17
-rw-r--r--drivers/mmc/core/block.c35
-rw-r--r--drivers/mmc/core/host.c20
-rw-r--r--drivers/net/bonding/bond_main.c2
-rw-r--r--drivers/net/can/spi/hi311x.c2
-rw-r--r--drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c1
-rw-r--r--drivers/net/can/usb/ems_usb.c14
-rw-r--r--drivers/net/can/usb/esd_usb2.c16
-rw-r--r--drivers/net/can/usb/mcba_usb.c2
-rw-r--r--drivers/net/can/usb/peak_usb/pcan_usb.c10
-rw-r--r--drivers/net/can/usb/usb_8dev.c15
-rw-r--r--drivers/net/dsa/mt7530.c2
-rw-r--r--drivers/net/dsa/mt7530.h1
-rw-r--r--drivers/net/dsa/mv88e6xxx/Kconfig2
-rw-r--r--drivers/net/dsa/mv88e6xxx/chip.c2
-rw-r--r--drivers/net/dsa/sja1105/sja1105_main.c6
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c90
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c10
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c31
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h5
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c9
-rw-r--r--drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c2
-rw-r--r--drivers/net/ethernet/dec/tulip/winbond-840.c7
-rw-r--r--drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c16
-rw-r--r--drivers/net/ethernet/freescale/fman/mac.c1
-rw-r--r--drivers/net/ethernet/hisilicon/hip04_eth.c6
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h7
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c8
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c1
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c36
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h10
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c10
-rw-r--r--drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c19
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c2
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_ethtool.c6
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_main.c61
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.c50
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_txrx.h2
-rw-r--r--drivers/net/ethernet/intel/ixgbe/ixgbe_main.c3
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/Makefile2
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/cgx.c2
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/npc.h3
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu.c16
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu.h21
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c3
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c5
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c48
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c53
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c58
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c29
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c259
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c14
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c7
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx4/main.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/dev.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/params.c11
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/trap.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_main.c38
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c33
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_core.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/health.c12
-rw-r--r--drivers/net/ethernet/microchip/sparx5/Kconfig1
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_lif.c197
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_lif.h11
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_phc.c10
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_txrx.c41
-rw-r--r--drivers/net/ethernet/qlogic/qede/qede_filter.c4
-rw-r--r--drivers/net/ethernet/qlogic/qla3xxx.c6
-rw-r--r--drivers/net/ethernet/realtek/r8169_main.c3
-rw-r--r--drivers/net/ethernet/renesas/ravb.h2
-rw-r--r--drivers/net/ethernet/renesas/ravb_main.c2
-rw-r--r--drivers/net/ethernet/sis/sis900.c7
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c2
-rw-r--r--drivers/net/ethernet/sun/niu.c3
-rw-r--r--drivers/net/ethernet/xscale/ptp_ixp46x.c2
-rw-r--r--drivers/net/phy/broadcom.c2
-rw-r--r--drivers/net/usb/hso.c33
-rw-r--r--drivers/net/usb/r8152.c30
-rw-r--r--drivers/net/wireless/virt_wifi.c52
-rw-r--r--drivers/net/wwan/wwan_core.c2
-rw-r--r--drivers/nfc/nfcsim.c3
-rw-r--r--drivers/nfc/s3fwrn5/firmware.c2
-rw-r--r--drivers/nvme/host/core.c19
-rw-r--r--drivers/nvme/host/multipath.c9
-rw-r--r--drivers/nvme/host/nvme.h11
-rw-r--r--drivers/nvme/host/pci.c4
-rw-r--r--drivers/nvme/host/trace.h6
-rw-r--r--drivers/platform/x86/amd-pmc.c249
-rw-r--r--drivers/platform/x86/gigabyte-wmi.c1
-rw-r--r--drivers/platform/x86/intel-hid.c1
-rw-r--r--drivers/platform/x86/think-lmi.c45
-rw-r--r--drivers/platform/x86/think-lmi.h1
-rw-r--r--drivers/platform/x86/wireless-hotkey.c2
-rw-r--r--drivers/regulator/bd9576-regulator.c4
-rw-r--r--drivers/regulator/hi6421-regulator.c22
-rw-r--r--drivers/regulator/hi6421v600-regulator.c16
-rw-r--r--drivers/regulator/mtk-dvfsrc-regulator.c3
-rw-r--r--drivers/regulator/rtmv20-regulator.c2
-rw-r--r--drivers/scsi/arm/acornscsi.c1
-rw-r--r--drivers/scsi/arm/fas216.c1
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_base.c32
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_base.h4
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_scsih.c7
-rw-r--r--drivers/scsi/scsi_transport_iscsi.c90
-rw-r--r--drivers/spi/spi-atmel.c9
-rw-r--r--drivers/spi/spi-bcm2835.c12
-rw-r--r--drivers/spi/spi-cadence-quadspi.c30
-rw-r--r--drivers/spi/spi-cadence.c14
-rw-r--r--drivers/spi/spi-imx.c38
-rw-r--r--drivers/spi/spi-mt65xx.c28
-rw-r--r--drivers/spi/spi-stm32.c24
-rw-r--r--drivers/target/target_core_sbc.c35
-rw-r--r--drivers/target/target_core_transport.c2
-rw-r--r--drivers/usb/class/cdc-wdm.c6
-rw-r--r--drivers/usb/core/devio.c2
-rw-r--r--drivers/usb/core/hub.c120
-rw-r--r--drivers/usb/core/quirks.c4
-rw-r--r--drivers/usb/dwc2/core.h4
-rw-r--r--drivers/usb/dwc2/core_intr.c3
-rw-r--r--drivers/usb/dwc2/gadget.c31
-rw-r--r--drivers/usb/dwc2/hcd.c6
-rw-r--r--drivers/usb/dwc2/params.c1
-rw-r--r--drivers/usb/dwc3/core.h1
-rw-r--r--drivers/usb/dwc3/ep0.c10
-rw-r--r--drivers/usb/dwc3/gadget.c21
-rw-r--r--drivers/usb/gadget/function/u_serial.c2
-rw-r--r--drivers/usb/gadget/udc/tegra-xudc.c1
-rw-r--r--drivers/usb/host/ehci-hcd.c18
-rw-r--r--drivers/usb/host/max3421-hcd.c44
-rw-r--r--drivers/usb/host/xhci-hub.c3
-rw-r--r--drivers/usb/host/xhci-pci-renesas.c16
-rw-r--r--drivers/usb/host/xhci-pci.c7
-rw-r--r--drivers/usb/phy/phy.c10
-rw-r--r--drivers/usb/renesas_usbhs/fifo.c7
-rw-r--r--drivers/usb/serial/cp210x.c5
-rw-r--r--drivers/usb/serial/option.c3
-rw-r--r--drivers/usb/storage/unusual_uas.h7
-rw-r--r--drivers/usb/typec/stusb160x.c20
-rw-r--r--drivers/usb/typec/tipd/core.c9
-rw-r--r--fs/Kconfig.binfmt15
-rw-r--r--fs/Makefile1
-rw-r--r--fs/afs/cmservice.c25
-rw-r--r--fs/afs/dir.c10
-rw-r--r--fs/afs/write.c18
-rw-r--r--fs/binfmt_em86.c110
-rw-r--r--fs/block_dev.c2
-rw-r--r--fs/btrfs/backref.c6
-rw-r--r--fs/btrfs/backref.h3
-rw-r--r--fs/btrfs/compression.c2
-rw-r--r--fs/btrfs/delayed-ref.c4
-rw-r--r--fs/btrfs/disk-io.c2
-rw-r--r--fs/btrfs/extent-tree.c3
-rw-r--r--fs/btrfs/inode.c2
-rw-r--r--fs/btrfs/ordered-data.c2
-rw-r--r--fs/btrfs/ordered-data.h3
-rw-r--r--fs/btrfs/qgroup.c38
-rw-r--r--fs/btrfs/qgroup.h2
-rw-r--r--fs/btrfs/tests/qgroup-tests.c20
-rw-r--r--fs/btrfs/tree-log.c35
-rw-r--r--fs/btrfs/volumes.c1
-rw-r--r--fs/btrfs/zoned.c12
-rw-r--r--fs/ceph/mds_client.c2
-rw-r--r--fs/cifs/cifssmb.c10
-rw-r--r--fs/cifs/connect.c4
-rw-r--r--fs/cifs/dfs_cache.c229
-rw-r--r--fs/cifs/dfs_cache.h3
-rw-r--r--fs/cifs/file.c2
-rw-r--r--fs/cifs/fs_context.c14
-rw-r--r--fs/cifs/smb2ops.c48
-rw-r--r--fs/ext2/dir.c12
-rw-r--r--fs/ext2/ext2.h3
-rw-r--r--fs/ext2/namei.c4
-rw-r--r--fs/fs-writeback.c3
-rw-r--r--fs/hugetlbfs/inode.c2
-rw-r--r--fs/internal.h1
-rw-r--r--fs/io-wq.c7
-rw-r--r--fs/io_uring.c93
-rw-r--r--fs/ocfs2/file.c103
-rw-r--r--fs/pipe.c10
-rw-r--r--fs/reiserfs/stree.c31
-rw-r--r--fs/reiserfs/super.c8
-rw-r--r--fs/seq_file.c3
-rw-r--r--fs/userfaultfd.c26
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h11
-rw-r--r--fs/xfs/xfs_buf_item_recover.c15
-rw-r--r--fs/xfs/xfs_inode_item_recover.c39
-rw-r--r--fs/xfs/xfs_log.c251
-rw-r--r--fs/xfs/xfs_log_cil.c13
-rw-r--r--fs/xfs/xfs_log_priv.h16
-rw-r--r--fs/xfs/xfs_trace.h5
-rw-r--r--include/acpi/acpi_bus.h8
-rw-r--r--include/drm/drm_ioctl.h1
-rw-r--r--include/linux/blkdev.h2
-rw-r--r--include/linux/bpf_types.h1
-rw-r--r--include/linux/bpf_verifier.h3
-rw-r--r--include/linux/entry-kvm.h6
-rw-r--r--include/linux/filter.h15
-rw-r--r--include/linux/fs_context.h1
-rw-r--r--include/linux/highmem.h6
-rw-r--r--include/linux/intel-ish-client-if.h2
-rw-r--r--include/linux/kvm_host.h1
-rw-r--r--include/linux/memblock.h4
-rw-r--r--include/linux/mfd/rt5033-private.h4
-rw-r--r--include/linux/page-flags.h37
-rw-r--r--include/linux/pgtable.h26
-rw-r--r--include/linux/skmsg.h54
-rw-r--r--include/net/llc_pdu.h31
-rw-r--r--include/net/sctp/structs.h5
-rw-r--r--include/net/tcp.h1
-rw-r--r--include/sound/soc.h6
-rw-r--r--include/trace/events/afs.h67
-rw-r--r--include/trace/events/net.h2
-rw-r--r--include/trace/events/qdisc.h28
-rw-r--r--include/uapi/linux/idxd.h2
-rw-r--r--include/uapi/rdma/irdma-abi.h2
-rw-r--r--kernel/bpf/core.c19
-rw-r--r--kernel/bpf/disasm.c16
-rw-r--r--kernel/bpf/verifier.c150
-rw-r--r--kernel/cgroup/cgroup-v1.c4
-rw-r--r--kernel/dma/ops_helpers.c12
-rw-r--r--kernel/smpboot.c2
-rw-r--r--kernel/time/posix-cpu-timers.c10
-rw-r--r--kernel/time/timer.c8
-rw-r--r--kernel/trace/ftrace.c5
-rw-r--r--kernel/trace/ring_buffer.c28
-rw-r--r--kernel/trace/trace.c4
-rw-r--r--kernel/trace/trace_events_hist.c22
-rw-r--r--kernel/trace/trace_events_synth.c8
-rw-r--r--kernel/trace/trace_synth.h2
-rw-r--r--kernel/tracepoint.c2
-rw-r--r--kernel/workqueue.c20
-rw-r--r--lib/Kconfig3
-rw-r--r--lib/Kconfig.debug3
-rw-r--r--mm/backing-dev.c2
-rw-r--r--mm/kfence/core.c19
-rw-r--r--mm/kfence/kfence_test.c2
-rw-r--r--mm/memblock.c3
-rw-r--r--mm/memcontrol.c3
-rw-r--r--mm/memory.c11
-rw-r--r--mm/migrate.c2
-rw-r--r--mm/mmap_lock.c4
-rw-r--r--mm/page_alloc.c29
-rw-r--r--mm/secretmem.c1
-rw-r--r--mm/slab.h2
-rw-r--r--mm/slub.c22
-rw-r--r--net/bpf/test_run.c3
-rw-r--r--net/bridge/br_fdb.c2
-rw-r--r--net/caif/caif_socket.c3
-rw-r--r--net/can/j1939/transport.c11
-rw-r--r--net/can/raw.c20
-rw-r--r--net/core/dev.c34
-rw-r--r--net/core/devlink.c10
-rw-r--r--net/core/flow_dissector.c18
-rw-r--r--net/core/skbuff.c18
-rw-r--r--net/core/skmsg.c55
-rw-r--r--net/decnet/af_decnet.c27
-rw-r--r--net/dsa/slave.c14
-rw-r--r--net/dsa/tag_ksz.c9
-rw-r--r--net/ipv4/ip_tunnel.c2
-rw-r--r--net/ipv4/tcp_bpf.c2
-rw-r--r--net/ipv4/tcp_fastopen.c28
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/udp.c25
-rw-r--r--net/ipv4/udp_bpf.c2
-rw-r--r--net/ipv6/ip6_output.c7
-rw-r--r--net/ipv6/route.c2
-rw-r--r--net/ipv6/udp.c25
-rw-r--r--net/llc/af_llc.c10
-rw-r--r--net/llc/llc_s_ac.c2
-rw-r--r--net/mac80211/cfg.c19
-rw-r--r--net/mac80211/ieee80211_i.h2
-rw-r--r--net/mac80211/mlme.c4
-rw-r--r--net/mac80211/rx.c3
-rw-r--r--net/mac80211/tx.c57
-rw-r--r--net/netfilter/nf_conntrack_core.c7
-rw-r--r--net/netfilter/nf_flow_table_core.c6
-rw-r--r--net/netfilter/nf_tables_api.c12
-rw-r--r--net/netfilter/nfnetlink_hook.c2
-rw-r--r--net/netfilter/nft_last.c20
-rw-r--r--net/netfilter/nft_nat.c4
-rw-r--r--net/netrom/nr_timer.c20
-rw-r--r--net/qrtr/qrtr.c6
-rw-r--r--net/sched/act_skbmod.c12
-rw-r--r--net/sched/cls_api.c2
-rw-r--r--net/sched/cls_tcindex.c5
-rw-r--r--net/sctp/auth.c2
-rw-r--r--net/sctp/input.c2
-rw-r--r--net/sctp/ipv6.c5
-rw-r--r--net/sctp/output.c4
-rw-r--r--net/sctp/sm_statefuns.c15
-rw-r--r--net/sctp/socket.c4
-rw-r--r--net/sctp/transport.c45
-rw-r--r--net/tipc/crypto.c14
-rw-r--r--net/tipc/socket.c30
-rw-r--r--net/unix/af_unix.c51
-rw-r--r--net/wireless/nl80211.c5
-rw-r--r--net/wireless/scan.c6
-rw-r--r--sound/core/pcm_native.c27
-rw-r--r--sound/hda/intel-dsp-config.c4
-rw-r--r--sound/isa/sb/sb16_csp.c4
-rw-r--r--sound/pci/hda/patch_hdmi.c2
-rw-r--r--sound/pci/hda/patch_realtek.c1
-rw-r--r--sound/soc/amd/acp-da7219-max98357a.c5
-rw-r--r--sound/soc/codecs/Kconfig8
-rw-r--r--sound/soc/codecs/rt5631.c2
-rw-r--r--sound/soc/codecs/rt5682.c8
-rw-r--r--sound/soc/codecs/tlv320aic31xx.c2
-rw-r--r--sound/soc/codecs/tlv320aic31xx.h4
-rw-r--r--sound/soc/codecs/tlv320aic32x4.c27
-rw-r--r--sound/soc/codecs/wcd938x.c18
-rw-r--r--sound/soc/codecs/wm_adsp.c6
-rw-r--r--sound/soc/intel/boards/sof_sdw_max98373.c81
-rw-r--r--sound/soc/soc-pcm.c22
-rw-r--r--sound/soc/sof/intel/pci-tgl.c1
-rw-r--r--sound/soc/tegra/tegra_pcm.c30
-rw-r--r--sound/soc/ti/j721e-evm.c18
-rw-r--r--sound/usb/mixer.c10
-rw-r--r--sound/usb/quirks.c3
-rw-r--r--tools/bpf/bpftool/common.c5
-rw-r--r--tools/perf/util/cs-etm.c20
-rw-r--r--tools/perf/util/map.c2
-rw-r--r--tools/perf/util/pmu.c33
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c229
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c121
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h3
-rw-r--r--tools/testing/selftests/net/nettest.c55
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh212
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c6
-rw-r--r--virt/kvm/kvm_main.c19
574 files changed, 7117 insertions, 3848 deletions
diff --git a/Documentation/arm64/tagged-address-abi.rst b/Documentation/arm64/tagged-address-abi.rst
index 459e6b66ff68..0c9120ec58ae 100644
--- a/Documentation/arm64/tagged-address-abi.rst
+++ b/Documentation/arm64/tagged-address-abi.rst
@@ -45,14 +45,24 @@ how the user addresses are used by the kernel:
1. User addresses not accessed by the kernel but used for address space
management (e.g. ``mprotect()``, ``madvise()``). The use of valid
- tagged pointers in this context is allowed with the exception of
- ``brk()``, ``mmap()`` and the ``new_address`` argument to
- ``mremap()`` as these have the potential to alias with existing
- user addresses.
-
- NOTE: This behaviour changed in v5.6 and so some earlier kernels may
- incorrectly accept valid tagged pointers for the ``brk()``,
- ``mmap()`` and ``mremap()`` system calls.
+ tagged pointers in this context is allowed with these exceptions:
+
+ - ``brk()``, ``mmap()`` and the ``new_address`` argument to
+ ``mremap()`` as these have the potential to alias with existing
+ user addresses.
+
+ NOTE: This behaviour changed in v5.6 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for the ``brk()``,
+ ``mmap()`` and ``mremap()`` system calls.
+
+ - The ``range.start``, ``start`` and ``dst`` arguments to the
+ ``UFFDIO_*`` ``ioctl()``s used on a file descriptor obtained from
+ ``userfaultfd()``, as fault addresses subsequently obtained by reading
+ the file descriptor will be untagged, which may otherwise confuse
+ tag-unaware programs.
+
+ NOTE: This behaviour changed in v5.14 and so some earlier kernels may
+ incorrectly accept valid tagged pointers for this system call.
2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
relaxation is disabled by default and the application thread needs to
diff --git a/Documentation/devicetree/bindings/net/imx-dwmac.txt b/Documentation/devicetree/bindings/net/imx-dwmac.txt
deleted file mode 100644
index 921d522fe8d7..000000000000
--- a/Documentation/devicetree/bindings/net/imx-dwmac.txt
+++ /dev/null
@@ -1,56 +0,0 @@
-IMX8 glue layer controller, NXP imx8 families support Synopsys MAC 5.10a IP.
-
-This file documents platform glue layer for IMX.
-Please see stmmac.txt for the other unchanged properties.
-
-The device node has following properties.
-
-Required properties:
-- compatible: Should be "nxp,imx8mp-dwmac-eqos" to select glue layer
- and "snps,dwmac-5.10a" to select IP version.
-- clocks: Must contain a phandle for each entry in clock-names.
-- clock-names: Should be "stmmaceth" for the host clock.
- Should be "pclk" for the MAC apb clock.
- Should be "ptp_ref" for the MAC timer clock.
- Should be "tx" for the MAC RGMII TX clock:
- Should be "mem" for EQOS MEM clock.
- - "mem" clock is required for imx8dxl platform.
- - "mem" clock is not required for imx8mp platform.
-- interrupt-names: Should contain a list of interrupt names corresponding to
- the interrupts in the interrupts property, if available.
- Should be "macirq" for the main MAC IRQ
- Should be "eth_wake_irq" for the IT which wake up system
-- intf_mode: Should be phandle/offset pair. The phandle to the syscon node which
- encompases the GPR register, and the offset of the GPR register.
- - required for imx8mp platform.
- - is optional for imx8dxl platform.
-
-Optional properties:
-- intf_mode: is optional for imx8dxl platform.
-- snps,rmii_refclk_ext: to select RMII reference clock from external.
-
-Example:
- eqos: ethernet@30bf0000 {
- compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
- reg = <0x30bf0000 0x10000>;
- interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "eth_wake_irq", "macirq";
- clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
- <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
- <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
- <&clk IMX8MP_CLK_ENET_QOS>;
- clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
- assigned-clocks = <&clk IMX8MP_CLK_ENET_AXI>,
- <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
- <&clk IMX8MP_CLK_ENET_QOS>;
- assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_266M>,
- <&clk IMX8MP_SYS_PLL2_100M>,
- <&clk IMX8MP_SYS_PLL2_125M>;
- assigned-clock-rates = <0>, <100000000>, <125000000>;
- nvmem-cells = <&eth_mac0>;
- nvmem-cell-names = "mac-address";
- nvmem_macaddr_swap;
- intf_mode = <&gpr 0x4>;
- status = "disabled";
- };
diff --git a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
new file mode 100644
index 000000000000..5629b2e4ccf8
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
@@ -0,0 +1,93 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/nxp,dwmac-imx.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NXP i.MX8 DWMAC glue layer Device Tree Bindings
+
+maintainers:
+ - Joakim Zhang <qiangqing.zhang@nxp.com>
+
+# We need a select here so we don't match all nodes with 'snps,dwmac'
+select:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - nxp,imx8mp-dwmac-eqos
+ - nxp,imx8dxl-dwmac-eqos
+ required:
+ - compatible
+
+allOf:
+ - $ref: "snps,dwmac.yaml#"
+
+properties:
+ compatible:
+ oneOf:
+ - items:
+ - enum:
+ - nxp,imx8mp-dwmac-eqos
+ - nxp,imx8dxl-dwmac-eqos
+ - const: snps,dwmac-5.10a
+
+ clocks:
+ minItems: 3
+ maxItems: 5
+ items:
+ - description: MAC host clock
+ - description: MAC apb clock
+ - description: MAC timer clock
+ - description: MAC RGMII TX clock
+ - description: EQOS MEM clock
+
+ clock-names:
+ minItems: 3
+ maxItems: 5
+ contains:
+ enum:
+ - stmmaceth
+ - pclk
+ - ptp_ref
+ - tx
+ - mem
+
+ intf_mode:
+ $ref: /schemas/types.yaml#/definitions/phandle-array
+ description:
+ Should be phandle/offset pair. The phandle to the syscon node which
+ encompases the GPR register, and the offset of the GPR register.
+
+ snps,rmii_refclk_ext:
+ $ref: /schemas/types.yaml#/definitions/flag
+ description:
+ To select RMII reference clock from external.
+
+required:
+ - compatible
+ - clocks
+ - clock-names
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/interrupt-controller/arm-gic.h>
+ #include <dt-bindings/interrupt-controller/irq.h>
+ #include <dt-bindings/clock/imx8mp-clock.h>
+
+ eqos: ethernet@30bf0000 {
+ compatible = "nxp,imx8mp-dwmac-eqos","snps,dwmac-5.10a";
+ reg = <0x30bf0000 0x10000>;
+ interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
+ clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
+ <&clk IMX8MP_CLK_QOS_ENET_ROOT>,
+ <&clk IMX8MP_CLK_ENET_QOS_TIMER>,
+ <&clk IMX8MP_CLK_ENET_QOS>;
+ clock-names = "stmmaceth", "pclk", "ptp_ref", "tx";
+ phy-mode = "rgmii";
+ status = "disabled";
+ };
diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index d7652596a09b..42689b7d03a2 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -28,6 +28,7 @@ select:
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
@@ -82,6 +83,7 @@ properties:
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
@@ -375,6 +377,7 @@ allOf:
- snps,dwmac-4.00
- snps,dwmac-4.10a
- snps,dwmac-4.20a
+ - snps,dwmac-5.10a
- snps,dwxgmac
- snps,dwxgmac-2.10
- st,spear600-gmac
diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
index 8850c01bd470..9b131c6facbc 100644
--- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
@@ -57,12 +57,14 @@ properties:
maxItems: 1
power-domains:
+ deprecated: true
description:
Power domain to use for enable control. This binding is only
available if the compatible is chosen to regulator-fixed-domain.
maxItems: 1
required-opps:
+ deprecated: true
description:
Performance state to use for enable control. This binding is only
available if the compatible is chosen to regulator-fixed-domain. The
diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml
index ee936d1aa724..c2930d65728e 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.yaml
@@ -114,7 +114,7 @@ properties:
ports:
$ref: /schemas/graph.yaml#/properties/ports
- properties:
+ patternProperties:
port(@[0-9a-f]+)?:
$ref: audio-graph-port.yaml#
unevaluatedProperties: false
diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst
index 42576880aa4a..60b217b436be 100644
--- a/Documentation/networking/af_xdp.rst
+++ b/Documentation/networking/af_xdp.rst
@@ -243,8 +243,8 @@ Configuration Flags and Socket Options
These are the various configuration flags that can be used to control
and monitor the behavior of AF_XDP sockets.
-XDP_COPY and XDP_ZERO_COPY bind flags
--------------------------------------
+XDP_COPY and XDP_ZEROCOPY bind flags
+------------------------------------
When you bind to a socket, the kernel will first try to use zero-copy
copy. If zero-copy is not supported, it will fall back on using copy
@@ -252,7 +252,7 @@ mode, i.e. copying all packets out to user space. But if you would
like to force a certain mode, you can use the following flags. If you
pass the XDP_COPY flag to the bind call, the kernel will force the
socket into copy mode. If it cannot use copy mode, the bind call will
-fail with an error. Conversely, the XDP_ZERO_COPY flag will force the
+fail with an error. Conversely, the XDP_ZEROCOPY flag will force the
socket into zero-copy mode or fail.
XDP_SHARED_UMEM bind flag
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index b3fa522e4cd9..316c7dfa9693 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -826,7 +826,7 @@ tcp_fastopen_blackhole_timeout_sec - INTEGER
initial value when the blackhole issue goes away.
0 to disable the blackhole detection.
- By default, it is set to 1hr.
+ By default, it is set to 0 (feature is disabled).
tcp_fastopen_key - list of comma separated 32-digit hexadecimal INTEGERs
The list consists of a primary key and an optional backup key. The
diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst
index b71e09f745c3..f99be8062bc8 100644
--- a/Documentation/trace/histogram.rst
+++ b/Documentation/trace/histogram.rst
@@ -191,7 +191,7 @@ Documentation written by Tom Zanussi
with the event, in nanoseconds. May be
modified by .usecs to have timestamps
interpreted as microseconds.
- cpu int the cpu on which the event occurred.
+ common_cpu int the cpu on which the event occurred.
====================== ==== =======================================
Extended error information
diff --git a/MAINTAINERS b/MAINTAINERS
index 6c8be735cc91..c9467d2839f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -445,7 +445,7 @@ F: drivers/platform/x86/wmi.c
F: include/uapi/linux/wmi.h
ACRN HYPERVISOR SERVICE MODULE
-M: Shuo Liu <shuo.a.liu@intel.com>
+M: Fei Li <fei1.li@intel.com>
L: acrn-dev@lists.projectacrn.org (subscribers-only)
S: Supported
W: https://projectacrn.org
@@ -7858,9 +7858,9 @@ S: Maintained
F: drivers/input/touchscreen/goodix.c
GOOGLE ETHERNET DRIVERS
-M: Catherine Sullivan <csully@google.com>
-R: Sagi Shahar <sagis@google.com>
-R: Jon Olson <jonolson@google.com>
+M: Jeroen de Borst <jeroendb@google.com>
+R: Catherine Sullivan <csully@google.com>
+R: David Awogbemila <awogbemila@google.com>
L: netdev@vger.kernel.org
S: Supported
F: Documentation/networking/device_drivers/ethernet/google/gve.rst
@@ -11327,6 +11327,12 @@ W: https://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: drivers/media/radio/radio-maxiradio*
+MCAB MICROCHIP CAN BUS ANALYZER TOOL DRIVER
+R: Yasushi SHOJI <yashi@spacecubics.com>
+L: linux-can@vger.kernel.org
+S: Maintained
+F: drivers/net/can/usb/mcba_usb.c
+
MCAN MMIO DEVICE DRIVER
M: Chandrasekar Ramakrishnan <rcsekar@samsung.com>
L: linux-can@vger.kernel.org
@@ -11758,6 +11764,7 @@ F: drivers/char/hw_random/mtk-rng.c
MEDIATEK SWITCH DRIVER
M: Sean Wang <sean.wang@mediatek.com>
M: Landen Chao <Landen.Chao@mediatek.com>
+M: DENG Qingfang <dqfext@gmail.com>
L: netdev@vger.kernel.org
S: Maintained
F: drivers/net/dsa/mt7530.*
@@ -15467,6 +15474,8 @@ M: Pan, Xinhui <Xinhui.Pan@amd.com>
L: amd-gfx@lists.freedesktop.org
S: Supported
T: git https://gitlab.freedesktop.org/agd5f/linux.git
+B: https://gitlab.freedesktop.org/drm/amd/-/issues
+C: irc://irc.oftc.net/radeon
F: drivers/gpu/drm/amd/
F: drivers/gpu/drm/radeon/
F: include/uapi/drm/amdgpu_drm.h
@@ -19122,7 +19131,7 @@ M: Mauro Carvalho Chehab <mchehab@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/phy/hisilicon,hi3670-usb3.yaml
-F: drivers/phy/hisilicon/phy-kirin970-usb3.c
+F: drivers/phy/hisilicon/phy-hi3670-usb3.c
USB ISP116X DRIVER
M: Olav Kongas <ok@artecdesign.ee>
@@ -19800,6 +19809,14 @@ L: netdev@vger.kernel.org
S: Supported
F: drivers/ptp/ptp_vmw.c
+VMWARE VMCI DRIVER
+M: Jorgen Hansen <jhansen@vmware.com>
+M: Vishnu Dasa <vdasa@vmware.com>
+L: linux-kernel@vger.kernel.org
+L: pv-drivers@vmware.com (private)
+S: Maintained
+F: drivers/misc/vmw_vmci/
+
VMWARE VMMOUSE SUBDRIVER
M: "VMware Graphics" <linux-graphics-maintainer@vmware.com>
M: "VMware, Inc." <pv-drivers@vmware.com>
diff --git a/Makefile b/Makefile
index e4f5895badb5..27a072cffcb9 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 14
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
NAME = Opossums on Parade
# *DOCUMENTATION*
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 77d3280dc678..6c50877841df 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -14,7 +14,6 @@ config ALPHA
select PCI_SYSCALL if PCI
select HAVE_AOUT
select HAVE_ASM_MODVERSIONS
- select HAVE_IDE
select HAVE_PCSPKR_PLATFORM
select HAVE_PERF_EVENTS
select NEED_DMA_MAP_STATE
@@ -532,7 +531,7 @@ config SMP
will run faster if you say N here.
See also the SMP-HOWTO available at
- <http://www.tldp.org/docs.html#howto>.
+ <https://www.tldp.org/docs.html#howto>.
If you don't know what to do here, say N.
diff --git a/arch/alpha/boot/bootp.c b/arch/alpha/boot/bootp.c
index 00266e6e1b71..b4faba2432d5 100644
--- a/arch/alpha/boot/bootp.c
+++ b/arch/alpha/boot/bootp.c
@@ -23,7 +23,7 @@
#include "ksize.h"
extern unsigned long switch_to_osf_pal(unsigned long nr,
- struct pcb_struct * pcb_va, struct pcb_struct * pcb_pa,
+ struct pcb_struct *pcb_va, struct pcb_struct *pcb_pa,
unsigned long *vptb);
extern void move_stack(unsigned long new_stack);
diff --git a/arch/alpha/boot/bootpz.c b/arch/alpha/boot/bootpz.c
index 43af71835adf..90a2b341e9c0 100644
--- a/arch/alpha/boot/bootpz.c
+++ b/arch/alpha/boot/bootpz.c
@@ -200,7 +200,7 @@ extern char _end;
START_ADDR KSEG address of the entry point of kernel code.
ZERO_PGE KSEG address of page full of zeroes, but
- upon entry to kerne cvan be expected
+ upon entry to kernel, it can be expected
to hold the parameter list and possible
INTRD information.
diff --git a/arch/alpha/boot/misc.c b/arch/alpha/boot/misc.c
index d65192202703..325d4dd4f904 100644
--- a/arch/alpha/boot/misc.c
+++ b/arch/alpha/boot/misc.c
@@ -30,7 +30,7 @@ extern long srm_printk(const char *, ...)
__attribute__ ((format (printf, 1, 2)));
/*
- * gzip delarations
+ * gzip declarations
*/
#define OF(args) args
#define STATIC static
diff --git a/arch/alpha/configs/defconfig b/arch/alpha/configs/defconfig
index dd2dd9f0861f..7f1ca30b115b 100644
--- a/arch/alpha/configs/defconfig
+++ b/arch/alpha/configs/defconfig
@@ -70,3 +70,4 @@ CONFIG_DEBUG_INFO=y
CONFIG_ALPHA_LEGACY_START_ADDRESS=y
CONFIG_MATHEMU=y
CONFIG_CRYPTO_HMAC=y
+CONFIG_DEVTMPFS=y
diff --git a/arch/alpha/include/asm/compiler.h b/arch/alpha/include/asm/compiler.h
index 5159ba259d65..ae645959018a 100644
--- a/arch/alpha/include/asm/compiler.h
+++ b/arch/alpha/include/asm/compiler.h
@@ -4,15 +4,4 @@
#include <uapi/asm/compiler.h>
-/* Some idiots over in <linux/compiler.h> thought inline should imply
- always_inline. This breaks stuff. We'll include this file whenever
- we run into such problems. */
-
-#include <linux/compiler.h>
-#undef inline
-#undef __inline__
-#undef __inline
-#undef __always_inline
-#define __always_inline inline __attribute__((always_inline))
-
#endif /* __ALPHA_COMPILER_H */
diff --git a/arch/alpha/include/asm/syscall.h b/arch/alpha/include/asm/syscall.h
index 11c688c1d7ec..f21babaeed85 100644
--- a/arch/alpha/include/asm/syscall.h
+++ b/arch/alpha/include/asm/syscall.h
@@ -9,4 +9,10 @@ static inline int syscall_get_arch(struct task_struct *task)
return AUDIT_ARCH_ALPHA;
}
+static inline long syscall_get_return_value(struct task_struct *task,
+ struct pt_regs *regs)
+{
+ return regs->r0;
+}
+
#endif /* _ASM_ALPHA_SYSCALL_H */
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index d5367a1c6300..d31167e3269c 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -834,7 +834,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
return -EFAULT;
state = &current_thread_info()->ieee_state;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
*state = (*state & ~IEEE_SW_MASK) | (swcr & IEEE_SW_MASK);
/* Update the real fpcr. */
@@ -854,7 +854,7 @@ SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer,
state = &current_thread_info()->ieee_state;
exc &= IEEE_STATUS_MASK;
- /* Update softare trap enable bits. */
+ /* Update software trap enable bits. */
swcr = (*state & IEEE_SW_MASK) | exc;
*state |= exc;
diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index e7a59d927d78..efcf7321701b 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -574,7 +574,7 @@ static void alpha_pmu_start(struct perf_event *event, int flags)
* Check that CPU performance counters are supported.
* - currently support EV67 and later CPUs.
* - actually some later revisions of the EV6 have the same PMC model as the
- * EV67 but we don't do suffiently deep CPU detection to detect them.
+ * EV67 but we don't do sufficiently deep CPU detection to detect them.
* Bad luck to the very few people who might have one, I guess.
*/
static int supported_cpu(void)
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index ef0c08ed0481..a5123ea426ce 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -256,7 +256,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
childstack->r26 = (unsigned long) ret_from_kernel_thread;
childstack->r9 = usp; /* function */
childstack->r10 = kthread_arg;
- childregs->hae = alpha_mv.hae_cache,
+ childregs->hae = alpha_mv.hae_cache;
childti->pcb.usp = 0;
return 0;
}
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 7d56c217b235..b4fbbba30aa2 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -319,18 +319,19 @@ setup_memory(void *kernel_end)
i, cluster->usage, cluster->start_pfn,
cluster->start_pfn + cluster->numpages);
- /* Bit 0 is console/PALcode reserved. Bit 1 is
- non-volatile memory -- we might want to mark
- this for later. */
- if (cluster->usage & 3)
- continue;
-
end = cluster->start_pfn + cluster->numpages;
if (end > max_low_pfn)
max_low_pfn = end;
memblock_add(PFN_PHYS(cluster->start_pfn),
cluster->numpages << PAGE_SHIFT);
+
+ /* Bit 0 is console/PALcode reserved. Bit 1 is
+ non-volatile memory -- we might want to mark
+ this for later. */
+ if (cluster->usage & 3)
+ memblock_reserve(PFN_PHYS(cluster->start_pfn),
+ cluster->numpages << PAGE_SHIFT);
}
/*
diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c
index 4b2575f936d4..cb64e4797d2a 100644
--- a/arch/alpha/kernel/smp.c
+++ b/arch/alpha/kernel/smp.c
@@ -582,7 +582,7 @@ void
smp_send_stop(void)
{
cpumask_t to_whom;
- cpumask_copy(&to_whom, cpu_possible_mask);
+ cpumask_copy(&to_whom, cpu_online_mask);
cpumask_clear_cpu(smp_processor_id(), &to_whom);
#ifdef DEBUG_IPI_MSG
if (hard_smp_processor_id() != boot_cpu_id)
diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c
index 53adf43dcd44..96fd6ff3fe81 100644
--- a/arch/alpha/kernel/sys_nautilus.c
+++ b/arch/alpha/kernel/sys_nautilus.c
@@ -212,7 +212,7 @@ nautilus_init_pci(void)
/* Use default IO. */
pci_add_resource(&bridge->windows, &ioport_resource);
- /* Irongate PCI memory aperture, calculate requred size before
+ /* Irongate PCI memory aperture, calculate required size before
setting it up. */
pci_add_resource(&bridge->windows, &irongate_mem);
diff --git a/arch/alpha/kernel/traps.c b/arch/alpha/kernel/traps.c
index 921d4b6e4d95..5398f982bdd1 100644
--- a/arch/alpha/kernel/traps.c
+++ b/arch/alpha/kernel/traps.c
@@ -730,7 +730,7 @@ do_entUnaUser(void __user * va, unsigned long opcode,
long error;
/* Check the UAC bits to decide what the user wants us to do
- with the unaliged access. */
+ with the unaligned access. */
if (!(current_thread_info()->status & TS_UAC_NOPRINT)) {
if (__ratelimit(&ratelimit)) {
diff --git a/arch/alpha/math-emu/math.c b/arch/alpha/math-emu/math.c
index d568cd9a3e43..f7cef66af88d 100644
--- a/arch/alpha/math-emu/math.c
+++ b/arch/alpha/math-emu/math.c
@@ -65,7 +65,7 @@ static long (*save_emul) (unsigned long pc);
long do_alpha_fp_emul_imprecise(struct pt_regs *, unsigned long);
long do_alpha_fp_emul(unsigned long);
-int init_module(void)
+static int alpha_fp_emul_init_module(void)
{
save_emul_imprecise = alpha_fp_emul_imprecise;
save_emul = alpha_fp_emul;
@@ -73,12 +73,14 @@ int init_module(void)
alpha_fp_emul = do_alpha_fp_emul;
return 0;
}
+module_init(alpha_fp_emul_init_module);
-void cleanup_module(void)
+static void alpha_fp_emul_cleanup_module(void)
{
alpha_fp_emul_imprecise = save_emul_imprecise;
alpha_fp_emul = save_emul;
}
+module_exit(alpha_fp_emul_cleanup_module);
#undef alpha_fp_emul_imprecise
#define alpha_fp_emul_imprecise do_alpha_fp_emul_imprecise
@@ -401,3 +403,5 @@ alpha_fp_emul_imprecise (struct pt_regs *regs, unsigned long write_mask)
egress:
return si_code;
}
+
+EXPORT_SYMBOL(__udiv_qrnnd);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 82f908fa5676..2fb7012c3246 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -95,7 +95,6 @@ config ARM
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
- select HAVE_IDE if PCI || ISA || PCMCIA
select HAVE_IRQ_TIME_ACCOUNTING
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
@@ -361,7 +360,6 @@ config ARCH_FOOTBRIDGE
bool "FootBridge"
select CPU_SA110
select FOOTBRIDGE
- select HAVE_IDE
select NEED_MACH_IO_H if !MMU
select NEED_MACH_MEMORY_H
help
@@ -430,7 +428,6 @@ config ARCH_PXA
select GENERIC_IRQ_MULTI_HANDLER
select GPIO_PXA
select GPIOLIB
- select HAVE_IDE
select IRQ_DOMAIN
select PLAT_PXA
select SPARSE_IRQ
@@ -446,7 +443,6 @@ config ARCH_RPC
select ARM_HAS_SG_CHAIN
select CPU_SA110
select FIQ
- select HAVE_IDE
select HAVE_PATA_PLATFORM
select ISA_DMA_API
select LEGACY_TIMER_TICK
@@ -469,7 +465,6 @@ config ARCH_SA1100
select CPU_SA1100
select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
- select HAVE_IDE
select IRQ_DOMAIN
select ISA
select NEED_MACH_MEMORY_H
@@ -505,7 +500,6 @@ config ARCH_OMAP1
select GENERIC_IRQ_CHIP
select GENERIC_IRQ_MULTI_HANDLER
select GPIOLIB
- select HAVE_IDE
select HAVE_LEGACY_CLK
select IRQ_DOMAIN
select NEED_MACH_IO_H if PCCARD
diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index de11030748d0..1d3aef84287d 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -9,7 +9,6 @@ menuconfig ARCH_DAVINCI
select PM_GENERIC_DOMAINS_OF if PM && OF
select REGMAP_MMIO
select RESET_CONTROLLER
- select HAVE_IDE
select PINCTRL_SINGLE
if ARCH_DAVINCI
diff --git a/arch/arm/mach-rpc/riscpc.c b/arch/arm/mach-rpc/riscpc.c
index d23970bd638d..f70fb9c4b0cb 100644
--- a/arch/arm/mach-rpc/riscpc.c
+++ b/arch/arm/mach-rpc/riscpc.c
@@ -49,6 +49,7 @@ static int __init parse_tag_acorn(const struct tag *tag)
fallthrough; /* ??? */
case 256:
vram_size += PAGE_SIZE * 256;
+ break;
default:
break;
}
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 897634d0a67c..a951276f0547 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1602,6 +1602,9 @@ exit:
rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 9f7c7f587d38..f4eaab3ecf03 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -579,7 +579,7 @@
};
flexcan1: can@308c0000 {
- compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+ compatible = "fsl,imx8mp-flexcan";
reg = <0x308c0000 0x10000>;
interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
@@ -594,7 +594,7 @@
};
flexcan2: can@308d0000 {
- compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+ compatible = "fsl,imx8mp-flexcan";
reg = <0x308d0000 0x10000>;
interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
@@ -821,9 +821,9 @@
eqos: ethernet@30bf0000 {
compatible = "nxp,imx8mp-dwmac-eqos", "snps,dwmac-5.10a";
reg = <0x30bf0000 0x10000>;
- interrupts = <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
- <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "eth_wake_irq", "macirq";
+ interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_wake_irq";
clocks = <&clk IMX8MP_CLK_ENET_QOS_ROOT>,
<&clk IMX8MP_CLK_QOS_ENET_ROOT>,
<&clk IMX8MP_CLK_ENET_QOS_TIMER>,
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
index 068692350e00..51e17094d7b1 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dtsi
@@ -1063,7 +1063,7 @@
status = "okay";
extcon = <&usb2_id>;
- usb@7600000 {
+ dwc3@7600000 {
extcon = <&usb2_id>;
dr_mode = "otg";
maximum-speed = "high-speed";
@@ -1074,7 +1074,7 @@
status = "okay";
extcon = <&usb3_id>;
- usb@6a00000 {
+ dwc3@6a00000 {
extcon = <&usb3_id>;
dr_mode = "otg";
};
diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
index 95d6cb8cd4c0..f39bc10cc5bd 100644
--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
@@ -443,7 +443,7 @@
resets = <&gcc GCC_USB0_BCR>;
status = "disabled";
- dwc_0: usb@8a00000 {
+ dwc_0: dwc3@8a00000 {
compatible = "snps,dwc3";
reg = <0x8a00000 0xcd00>;
interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
@@ -484,7 +484,7 @@
resets = <&gcc GCC_USB1_BCR>;
status = "disabled";
- dwc_1: usb@8c00000 {
+ dwc_1: dwc3@8c00000 {
compatible = "snps,dwc3";
reg = <0x8c00000 0xcd00>;
interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
index 0e1bc4669d7e..78c55ca10ba9 100644
--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
@@ -2566,7 +2566,7 @@
power-domains = <&gcc USB30_GDSC>;
status = "disabled";
- usb@6a00000 {
+ dwc3@6a00000 {
compatible = "snps,dwc3";
reg = <0x06a00000 0xcc00>;
interrupts = <0 131 IRQ_TYPE_LEVEL_HIGH>;
@@ -2873,7 +2873,7 @@
qcom,select-utmi-as-pipe-clk;
status = "disabled";
- usb@7600000 {
+ dwc3@7600000 {
compatible = "snps,dwc3";
reg = <0x07600000 0xcc00>;
interrupts = <0 138 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
index 6f294f9c0cdf..e9d3ce29937c 100644
--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
@@ -1964,7 +1964,7 @@
resets = <&gcc GCC_USB_30_BCR>;
- usb3_dwc3: usb@a800000 {
+ usb3_dwc3: dwc3@a800000 {
compatible = "snps,dwc3";
reg = <0x0a800000 0xcd00>;
interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
index f8a55307b855..a80c578484ba 100644
--- a/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404-evb.dtsi
@@ -337,7 +337,7 @@
&usb3 {
status = "okay";
- usb@7580000 {
+ dwc3@7580000 {
dr_mode = "host";
};
};
diff --git a/arch/arm64/boot/dts/qcom/qcs404.dtsi b/arch/arm64/boot/dts/qcom/qcs404.dtsi
index 9c4be020d568..339790ba585d 100644
--- a/arch/arm64/boot/dts/qcom/qcs404.dtsi
+++ b/arch/arm64/boot/dts/qcom/qcs404.dtsi
@@ -544,7 +544,7 @@
assigned-clock-rates = <19200000>, <200000000>;
status = "disabled";
- usb@7580000 {
+ dwc3@7580000 {
compatible = "snps,dwc3";
reg = <0x07580000 0xcd00>;
interrupts = <GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>;
@@ -573,7 +573,7 @@
assigned-clock-rates = <19200000>, <133333333>;
status = "disabled";
- usb@78c0000 {
+ dwc3@78c0000 {
compatible = "snps,dwc3";
reg = <0x078c0000 0xcc00>;
interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
index a5d58eb92896..a9a052f8c63c 100644
--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
+++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
@@ -2756,7 +2756,7 @@
<&gem_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xe000>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index 1796ae8372be..0a86fe71a66d 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -3781,7 +3781,7 @@
<&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_0 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
@@ -3829,7 +3829,7 @@
<&gladiator_noc MASTER_APPSS_PROC 0 &config_noc SLAVE_USB3_1 0>;
interconnect-names = "usb-ddr", "apps-usb";
- usb_2_dwc3: usb@a800000 {
+ usb_2_dwc3: dwc3@a800000 {
compatible = "snps,dwc3";
reg = <0 0x0a800000 0 0xcd00>;
interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index 612dda0fef43..eef9d79157e9 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -2344,7 +2344,7 @@
resets = <&gcc GCC_USB30_PRIM_BCR>;
- usb_1_dwc3: usb@a600000 {
+ usb_1_dwc3: dwc3@a600000 {
compatible = "snps,dwc3";
reg = <0 0x0a600000 0 0xcd00>;
interrupts = <GIC_SPI 133 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 9bb9d11750d7..20e0517eb669 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -602,14 +602,14 @@ static inline bool id_aa64pfr0_32bit_el1(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SHIFT);
- return val == ID_AA64PFR0_EL1_32BIT_64BIT;
+ return val == ID_AA64PFR0_ELx_32BIT_64BIT;
}
static inline bool id_aa64pfr0_32bit_el0(u64 pfr0)
{
u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL0_SHIFT);
- return val == ID_AA64PFR0_EL0_32BIT_64BIT;
+ return val == ID_AA64PFR0_ELx_32BIT_64BIT;
}
static inline bool id_aa64pfr0_sve(u64 pfr0)
@@ -657,7 +657,8 @@ static inline bool system_supports_4kb_granule(void)
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_TGRAN4_SHIFT);
- return val == ID_AA64MMFR0_TGRAN4_SUPPORTED;
+ return (val >= ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN) &&
+ (val <= ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX);
}
static inline bool system_supports_64kb_granule(void)
@@ -669,7 +670,8 @@ static inline bool system_supports_64kb_granule(void)
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_TGRAN64_SHIFT);
- return val == ID_AA64MMFR0_TGRAN64_SUPPORTED;
+ return (val >= ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN) &&
+ (val <= ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX);
}
static inline bool system_supports_16kb_granule(void)
@@ -681,7 +683,8 @@ static inline bool system_supports_16kb_granule(void)
val = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_TGRAN16_SHIFT);
- return val == ID_AA64MMFR0_TGRAN16_SUPPORTED;
+ return (val >= ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN) &&
+ (val <= ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX);
}
static inline bool system_supports_mixed_endian_el0(void)
@@ -781,13 +784,13 @@ extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange)
{
switch (parange) {
- case 0: return 32;
- case 1: return 36;
- case 2: return 40;
- case 3: return 42;
- case 4: return 44;
- case 5: return 48;
- case 6: return 52;
+ case ID_AA64MMFR0_PARANGE_32: return 32;
+ case ID_AA64MMFR0_PARANGE_36: return 36;
+ case ID_AA64MMFR0_PARANGE_40: return 40;
+ case ID_AA64MMFR0_PARANGE_42: return 42;
+ case ID_AA64MMFR0_PARANGE_44: return 44;
+ case ID_AA64MMFR0_PARANGE_48: return 48;
+ case ID_AA64MMFR0_PARANGE_52: return 52;
/*
* A future PE could use a value unknown to the kernel.
* However, by the "D10.1.4 Principles of the ID scheme
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index d436831dd706..327120c0089f 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -12,8 +12,13 @@
#include <asm/types.h>
/* Hyp Configuration Register (HCR) bits */
+
+#define HCR_TID5 (UL(1) << 58)
+#define HCR_DCT (UL(1) << 57)
#define HCR_ATA_SHIFT 56
#define HCR_ATA (UL(1) << HCR_ATA_SHIFT)
+#define HCR_AMVOFFEN (UL(1) << 51)
+#define HCR_FIEN (UL(1) << 47)
#define HCR_FWB (UL(1) << 46)
#define HCR_API (UL(1) << 41)
#define HCR_APK (UL(1) << 40)
@@ -32,9 +37,9 @@
#define HCR_TVM (UL(1) << 26)
#define HCR_TTLB (UL(1) << 25)
#define HCR_TPU (UL(1) << 24)
-#define HCR_TPC (UL(1) << 23)
+#define HCR_TPC (UL(1) << 23) /* HCR_TPCP if FEAT_DPB */
#define HCR_TSW (UL(1) << 22)
-#define HCR_TAC (UL(1) << 21)
+#define HCR_TACR (UL(1) << 21)
#define HCR_TIDCP (UL(1) << 20)
#define HCR_TSC (UL(1) << 19)
#define HCR_TID3 (UL(1) << 18)
@@ -56,12 +61,13 @@
#define HCR_PTW (UL(1) << 2)
#define HCR_SWIO (UL(1) << 1)
#define HCR_VM (UL(1) << 0)
+#define HCR_RES0 ((UL(1) << 48) | (UL(1) << 39))
/*
* The bits we set in HCR:
* TLOR: Trap LORegion register accesses
* RW: 64bit by default, can be overridden for 32bit VMs
- * TAC: Trap ACTLR
+ * TACR: Trap ACTLR
* TSC: Trap SMC
* TSW: Trap cache operations by set/way
* TWE: Trap WFE
@@ -76,7 +82,7 @@
* PTW: Take a stage2 fault if a stage1 walk steps in device memory
*/
#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \
- HCR_BSU_IS | HCR_FB | HCR_TAC | \
+ HCR_BSU_IS | HCR_FB | HCR_TACR | \
HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \
HCR_FMO | HCR_IMO | HCR_PTW )
#define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF)
@@ -275,24 +281,40 @@
#define CPTR_EL2_TTA (1 << 20)
#define CPTR_EL2_TFP (1 << CPTR_EL2_TFP_SHIFT)
#define CPTR_EL2_TZ (1 << 8)
-#define CPTR_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 */
-#define CPTR_EL2_DEFAULT CPTR_EL2_RES1
+#define CPTR_NVHE_EL2_RES1 0x000032ff /* known RES1 bits in CPTR_EL2 (nVHE) */
+#define CPTR_EL2_DEFAULT CPTR_NVHE_EL2_RES1
+#define CPTR_NVHE_EL2_RES0 (GENMASK(63, 32) | \
+ GENMASK(29, 21) | \
+ GENMASK(19, 14) | \
+ BIT(11))
/* Hyp Debug Configuration Register bits */
#define MDCR_EL2_E2TB_MASK (UL(0x3))
#define MDCR_EL2_E2TB_SHIFT (UL(24))
-#define MDCR_EL2_TTRF (1 << 19)
-#define MDCR_EL2_TPMS (1 << 14)
+#define MDCR_EL2_HPMFZS (UL(1) << 36)
+#define MDCR_EL2_HPMFZO (UL(1) << 29)
+#define MDCR_EL2_MTPME (UL(1) << 28)
+#define MDCR_EL2_TDCC (UL(1) << 27)
+#define MDCR_EL2_HCCD (UL(1) << 23)
+#define MDCR_EL2_TTRF (UL(1) << 19)
+#define MDCR_EL2_HPMD (UL(1) << 17)
+#define MDCR_EL2_TPMS (UL(1) << 14)
#define MDCR_EL2_E2PB_MASK (UL(0x3))
#define MDCR_EL2_E2PB_SHIFT (UL(12))
-#define MDCR_EL2_TDRA (1 << 11)
-#define MDCR_EL2_TDOSA (1 << 10)
-#define MDCR_EL2_TDA (1 << 9)
-#define MDCR_EL2_TDE (1 << 8)
-#define MDCR_EL2_HPME (1 << 7)
-#define MDCR_EL2_TPM (1 << 6)
-#define MDCR_EL2_TPMCR (1 << 5)
-#define MDCR_EL2_HPMN_MASK (0x1F)
+#define MDCR_EL2_TDRA (UL(1) << 11)
+#define MDCR_EL2_TDOSA (UL(1) << 10)
+#define MDCR_EL2_TDA (UL(1) << 9)
+#define MDCR_EL2_TDE (UL(1) << 8)
+#define MDCR_EL2_HPME (UL(1) << 7)
+#define MDCR_EL2_TPM (UL(1) << 6)
+#define MDCR_EL2_TPMCR (UL(1) << 5)
+#define MDCR_EL2_HPMN_MASK (UL(0x1F))
+#define MDCR_EL2_RES0 (GENMASK(63, 37) | \
+ GENMASK(35, 30) | \
+ GENMASK(25, 24) | \
+ GENMASK(22, 20) | \
+ BIT(18) | \
+ GENMASK(16, 15))
/* For compatibility with fault code shared with 32-bit */
#define FSC_FAULT ESR_ELx_FSC_FAULT
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 9f0bf2109be7..e86045ac43ba 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -59,12 +59,11 @@
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs 13
#define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs 14
#define __KVM_HOST_SMCCC_FUNC___pkvm_init 15
-#define __KVM_HOST_SMCCC_FUNC___pkvm_create_mappings 16
+#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp 16
#define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping 17
#define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18
#define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19
-#define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20
-#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21
+#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 20
#ifndef __ASSEMBLY__
@@ -210,7 +209,7 @@ extern u64 __vgic_v3_read_vmcr(void);
extern void __vgic_v3_write_vmcr(u32 vmcr);
extern void __vgic_v3_init_lrs(void);
-extern u32 __kvm_get_mdcr_el2(void);
+extern u64 __kvm_get_mdcr_el2(void);
#define __KVM_EXTABLE(from, to) \
" .pushsection __kvm_ex_table, \"a\"\n" \
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 41911585ae0c..f8be56d5342b 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -66,7 +66,7 @@ DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
extern unsigned int kvm_sve_max_vl;
int kvm_arm_init_sve(void);
-int __attribute_const__ kvm_target_cpu(void);
+u32 __attribute_const__ kvm_target_cpu(void);
int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
@@ -185,7 +185,6 @@ enum vcpu_sysreg {
PMCNTENSET_EL0, /* Count Enable Set Register */
PMINTENSET_EL1, /* Interrupt Enable Set Register */
PMOVSSET_EL0, /* Overflow Flag Status Set Register */
- PMSWINC_EL0, /* Software Increment Register */
PMUSERENR_EL0, /* User Enable Register */
/* Pointer Authentication Registers in a strict increasing order. */
@@ -287,9 +286,13 @@ struct kvm_vcpu_arch {
/* Stage 2 paging state used by the hardware on next switch */
struct kvm_s2_mmu *hw_mmu;
- /* HYP configuration */
+ /* Values of trap registers for the guest. */
u64 hcr_el2;
- u32 mdcr_el2;
+ u64 mdcr_el2;
+ u64 cptr_el2;
+
+ /* Values of trap registers for the host before guest entry. */
+ u64 mdcr_el2_host;
/* Exception Information */
struct kvm_vcpu_fault_info fault;
@@ -576,6 +579,7 @@ struct kvm_vcpu_stat {
u64 wfi_exit_stat;
u64 mmio_exit_user;
u64 mmio_exit_kernel;
+ u64 signal_exits;
u64 exits;
};
@@ -771,6 +775,11 @@ void kvm_arch_free_vm(struct kvm *kvm);
int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type);
+static inline bool kvm_vm_is_protected(struct kvm *kvm)
+{
+ return false;
+}
+
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 9d60b3006efc..657d0c94cf82 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -95,7 +95,7 @@ void __sve_restore_state(void *sve_pffr, u32 *fpsr);
#ifndef __KVM_NVHE_HYPERVISOR__
void activate_traps_vhe_load(struct kvm_vcpu *vcpu);
-void deactivate_traps_vhe_put(void);
+void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
#endif
u64 __guest_enter(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index b52c5c4b9a3d..02d378887743 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -252,6 +252,11 @@ static inline int kvm_write_guest_lock(struct kvm *kvm, gpa_t gpa,
#define kvm_phys_to_vttbr(addr) phys_to_ttbr(addr)
+/*
+ * When this is (directly or indirectly) used on the TLB invalidation
+ * path, we rely on a previously issued DSB so that page table updates
+ * and VMID reads are correctly ordered.
+ */
static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
{
struct kvm_vmid *vmid = &mmu->vmid;
@@ -259,7 +264,7 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
u64 cnp = system_supports_cnp() ? VTTBR_CNP_BIT : 0;
baddr = mmu->pgd_phys;
- vmid_field = (u64)vmid->vmid << VTTBR_VMID_SHIFT;
+ vmid_field = (u64)READ_ONCE(vmid->vmid) << VTTBR_VMID_SHIFT;
return kvm_phys_to_vttbr(baddr) | vmid_field | cnp;
}
@@ -267,9 +272,10 @@ static __always_inline u64 kvm_get_vttbr(struct kvm_s2_mmu *mmu)
* Must be called from hyp code running at EL2 with an updated VTTBR
* and interrupts disabled.
*/
-static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, unsigned long vtcr)
+static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu,
+ struct kvm_arch *arch)
{
- write_sysreg(vtcr, vtcr_el2);
+ write_sysreg(arch->vtcr, vtcr_el2);
write_sysreg(kvm_get_vttbr(mmu), vttbr_el2);
/*
@@ -280,11 +286,6 @@ static __always_inline void __load_stage2(struct kvm_s2_mmu *mmu, unsigned long
asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
}
-static __always_inline void __load_guest_stage2(struct kvm_s2_mmu *mmu)
-{
- __load_stage2(mmu, kern_hyp_va(mmu->arch)->vtcr);
-}
-
static inline struct kvm *kvm_s2_mmu_to_kvm(struct kvm_s2_mmu *mmu)
{
return container_of(mmu->arch, struct kvm, arch);
diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
index f004c0115d89..027783829584 100644
--- a/arch/arm64/include/asm/kvm_pgtable.h
+++ b/arch/arm64/include/asm/kvm_pgtable.h
@@ -25,6 +25,46 @@ static inline u64 kvm_get_parange(u64 mmfr0)
typedef u64 kvm_pte_t;
+#define KVM_PTE_VALID BIT(0)
+
+#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT)
+#define KVM_PTE_ADDR_51_48 GENMASK(15, 12)
+
+static inline bool kvm_pte_valid(kvm_pte_t pte)
+{
+ return pte & KVM_PTE_VALID;
+}
+
+static inline u64 kvm_pte_to_phys(kvm_pte_t pte)
+{
+ u64 pa = pte & KVM_PTE_ADDR_MASK;
+
+ if (PAGE_SHIFT == 16)
+ pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
+
+ return pa;
+}
+
+static inline u64 kvm_granule_shift(u32 level)
+{
+ /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
+ return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
+}
+
+static inline u64 kvm_granule_size(u32 level)
+{
+ return BIT(kvm_granule_shift(level));
+}
+
+static inline bool kvm_level_supports_block_mapping(u32 level)
+{
+ /*
+ * Reject invalid block mappings and don't bother with 4TB mappings for
+ * 52-bit PAs.
+ */
+ return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1));
+}
+
/**
* struct kvm_pgtable_mm_ops - Memory management callbacks.
* @zalloc_page: Allocate a single zeroed memory page.
@@ -76,30 +116,15 @@ enum kvm_pgtable_stage2_flags {
};
/**
- * struct kvm_pgtable - KVM page-table.
- * @ia_bits: Maximum input address size, in bits.
- * @start_level: Level at which the page-table walk starts.
- * @pgd: Pointer to the first top-level entry of the page-table.
- * @mm_ops: Memory management callbacks.
- * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
- */
-struct kvm_pgtable {
- u32 ia_bits;
- u32 start_level;
- kvm_pte_t *pgd;
- struct kvm_pgtable_mm_ops *mm_ops;
-
- /* Stage-2 only */
- struct kvm_s2_mmu *mmu;
- enum kvm_pgtable_stage2_flags flags;
-};
-
-/**
* enum kvm_pgtable_prot - Page-table permissions and attributes.
* @KVM_PGTABLE_PROT_X: Execute permission.
* @KVM_PGTABLE_PROT_W: Write permission.
* @KVM_PGTABLE_PROT_R: Read permission.
* @KVM_PGTABLE_PROT_DEVICE: Device attributes.
+ * @KVM_PGTABLE_PROT_SW0: Software bit 0.
+ * @KVM_PGTABLE_PROT_SW1: Software bit 1.
+ * @KVM_PGTABLE_PROT_SW2: Software bit 2.
+ * @KVM_PGTABLE_PROT_SW3: Software bit 3.
*/
enum kvm_pgtable_prot {
KVM_PGTABLE_PROT_X = BIT(0),
@@ -107,21 +132,48 @@ enum kvm_pgtable_prot {
KVM_PGTABLE_PROT_R = BIT(2),
KVM_PGTABLE_PROT_DEVICE = BIT(3),
+
+ KVM_PGTABLE_PROT_SW0 = BIT(55),
+ KVM_PGTABLE_PROT_SW1 = BIT(56),
+ KVM_PGTABLE_PROT_SW2 = BIT(57),
+ KVM_PGTABLE_PROT_SW3 = BIT(58),
};
-#define PAGE_HYP (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define KVM_PGTABLE_PROT_RW (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W)
+#define KVM_PGTABLE_PROT_RWX (KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X)
+
+#define PKVM_HOST_MEM_PROT KVM_PGTABLE_PROT_RWX
+#define PKVM_HOST_MMIO_PROT KVM_PGTABLE_PROT_RW
+
+#define PAGE_HYP KVM_PGTABLE_PROT_RW
#define PAGE_HYP_EXEC (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X)
#define PAGE_HYP_RO (KVM_PGTABLE_PROT_R)
#define PAGE_HYP_DEVICE (PAGE_HYP | KVM_PGTABLE_PROT_DEVICE)
+typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end,
+ enum kvm_pgtable_prot prot);
+
/**
- * struct kvm_mem_range - Range of Intermediate Physical Addresses
- * @start: Start of the range.
- * @end: End of the range.
+ * struct kvm_pgtable - KVM page-table.
+ * @ia_bits: Maximum input address size, in bits.
+ * @start_level: Level at which the page-table walk starts.
+ * @pgd: Pointer to the first top-level entry of the page-table.
+ * @mm_ops: Memory management callbacks.
+ * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables.
+ * @flags: Stage-2 page-table flags.
+ * @force_pte_cb: Function that returns true if page level mappings must
+ * be used instead of block mappings.
*/
-struct kvm_mem_range {
- u64 start;
- u64 end;
+struct kvm_pgtable {
+ u32 ia_bits;
+ u32 start_level;
+ kvm_pte_t *pgd;
+ struct kvm_pgtable_mm_ops *mm_ops;
+
+ /* Stage-2 only */
+ struct kvm_s2_mmu *mmu;
+ enum kvm_pgtable_stage2_flags flags;
+ kvm_pgtable_force_pte_cb_t force_pte_cb;
};
/**
@@ -216,21 +268,24 @@ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys,
u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift);
/**
- * kvm_pgtable_stage2_init_flags() - Initialise a guest stage-2 page-table.
+ * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table.
* @pgt: Uninitialised page-table structure to initialise.
* @arch: Arch-specific KVM structure representing the guest virtual
* machine.
* @mm_ops: Memory management callbacks.
* @flags: Stage-2 configuration flags.
+ * @force_pte_cb: Function that returns true if page level mappings must
+ * be used instead of block mappings.
*
* Return: 0 on success, negative error code on failure.
*/
-int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch,
- struct kvm_pgtable_mm_ops *mm_ops,
- enum kvm_pgtable_stage2_flags flags);
+int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch,
+ struct kvm_pgtable_mm_ops *mm_ops,
+ enum kvm_pgtable_stage2_flags flags,
+ kvm_pgtable_force_pte_cb_t force_pte_cb);
#define kvm_pgtable_stage2_init(pgt, arch, mm_ops) \
- kvm_pgtable_stage2_init_flags(pgt, arch, mm_ops, 0)
+ __kvm_pgtable_stage2_init(pgt, arch, mm_ops, 0, NULL)
/**
* kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table.
@@ -374,7 +429,8 @@ kvm_pte_t kvm_pgtable_stage2_mkold(struct kvm_pgtable *pgt, u64 addr);
* If there is a valid, leaf page-table entry used to translate @addr, then
* relax the permissions in that entry according to the read, write and
* execute permissions specified by @prot. No permissions are removed, and
- * TLB invalidation is performed after updating the entry.
+ * TLB invalidation is performed after updating the entry. Software bits cannot
+ * be set or cleared using kvm_pgtable_stage2_relax_perms().
*
* Return: 0 on success, negative error code on failure.
*/
@@ -433,22 +489,42 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
struct kvm_pgtable_walker *walker);
/**
- * kvm_pgtable_stage2_find_range() - Find a range of Intermediate Physical
- * Addresses with compatible permission
- * attributes.
- * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*().
- * @addr: Address that must be covered by the range.
- * @prot: Protection attributes that the range must be compatible with.
- * @range: Range structure used to limit the search space at call time and
- * that will hold the result.
+ * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry
+ * with its level.
+ * @pgt: Page-table structure initialised by kvm_pgtable_*_init()
+ * or a similar initialiser.
+ * @addr: Input address for the start of the walk.
+ * @ptep: Pointer to storage for the retrieved PTE.
+ * @level: Pointer to storage for the level of the retrieved PTE.
+ *
+ * The offset of @addr within a page is ignored.
*
- * The offset of @addr within a page is ignored. An IPA is compatible with @prot
- * iff its corresponding stage-2 page-table entry has default ownership and, if
- * valid, is mapped with protection attributes identical to @prot.
+ * The walker will walk the page-table entries corresponding to the input
+ * address specified, retrieving the leaf corresponding to this address.
+ * Invalid entries are treated as leaf entries.
*
* Return: 0 on success, negative error code on failure.
*/
-int kvm_pgtable_stage2_find_range(struct kvm_pgtable *pgt, u64 addr,
- enum kvm_pgtable_prot prot,
- struct kvm_mem_range *range);
+int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
+ kvm_pte_t *ptep, u32 *level);
+
+/**
+ * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a
+ * stage-2 Page-Table Entry.
+ * @pte: Page-table entry
+ *
+ * Return: protection attributes of the page-table entry in the enum
+ * kvm_pgtable_prot format.
+ */
+enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte);
+
+/**
+ * kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1
+ * Page-Table Entry.
+ * @pte: Page-table entry
+ *
+ * Return: protection attributes of the page-table entry in the enum
+ * kvm_pgtable_prot format.
+ */
+enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte);
#endif /* __ARM64_KVM_PGTABLE_H__ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 7b9c3acba684..7640fa27be94 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -784,14 +784,13 @@
#define ID_AA64PFR0_AMU 0x1
#define ID_AA64PFR0_SVE 0x1
#define ID_AA64PFR0_RAS_V1 0x1
+#define ID_AA64PFR0_RAS_V1P1 0x2
#define ID_AA64PFR0_FP_NI 0xf
#define ID_AA64PFR0_FP_SUPPORTED 0x0
#define ID_AA64PFR0_ASIMD_NI 0xf
#define ID_AA64PFR0_ASIMD_SUPPORTED 0x0
-#define ID_AA64PFR0_EL1_64BIT_ONLY 0x1
-#define ID_AA64PFR0_EL1_32BIT_64BIT 0x2
-#define ID_AA64PFR0_EL0_64BIT_ONLY 0x1
-#define ID_AA64PFR0_EL0_32BIT_64BIT 0x2
+#define ID_AA64PFR0_ELx_64BIT_ONLY 0x1
+#define ID_AA64PFR0_ELx_32BIT_64BIT 0x2
/* id_aa64pfr1 */
#define ID_AA64PFR1_MPAMFRAC_SHIFT 16
@@ -847,15 +846,29 @@
#define ID_AA64MMFR0_ASID_SHIFT 4
#define ID_AA64MMFR0_PARANGE_SHIFT 0
-#define ID_AA64MMFR0_TGRAN4_NI 0xf
-#define ID_AA64MMFR0_TGRAN4_SUPPORTED 0x0
-#define ID_AA64MMFR0_TGRAN64_NI 0xf
-#define ID_AA64MMFR0_TGRAN64_SUPPORTED 0x0
-#define ID_AA64MMFR0_TGRAN16_NI 0x0
-#define ID_AA64MMFR0_TGRAN16_SUPPORTED 0x1
+#define ID_AA64MMFR0_ASID_8 0x0
+#define ID_AA64MMFR0_ASID_16 0x2
+
+#define ID_AA64MMFR0_TGRAN4_NI 0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN 0x0
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN64_NI 0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN 0x0
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN16_NI 0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN 0x1
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX 0xf
+
+#define ID_AA64MMFR0_PARANGE_32 0x0
+#define ID_AA64MMFR0_PARANGE_36 0x1
+#define ID_AA64MMFR0_PARANGE_40 0x2
+#define ID_AA64MMFR0_PARANGE_42 0x3
+#define ID_AA64MMFR0_PARANGE_44 0x4
#define ID_AA64MMFR0_PARANGE_48 0x5
#define ID_AA64MMFR0_PARANGE_52 0x6
+#define ARM64_MIN_PARANGE_BITS 32
+
#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0
#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1
#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2
@@ -900,6 +913,7 @@
#define ID_AA64MMFR2_CNP_SHIFT 0
/* id_aa64dfr0 */
+#define ID_AA64DFR0_MTPMU_SHIFT 48
#define ID_AA64DFR0_TRBE_SHIFT 44
#define ID_AA64DFR0_TRACE_FILT_SHIFT 40
#define ID_AA64DFR0_DOUBLELOCK_SHIFT 36
@@ -1028,16 +1042,19 @@
#if defined(CONFIG_ARM64_4K_PAGES)
#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN4_2_SHIFT
#elif defined(CONFIG_ARM64_16K_PAGES)
#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0xF
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN16_2_SHIFT
#elif defined(CONFIG_ARM64_64K_PAGES)
#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED
-#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN64_2_SHIFT
#endif
#define MVFR2_FPMISC_SHIFT 4
@@ -1153,6 +1170,11 @@
#define ICH_VTR_A3V_SHIFT 21
#define ICH_VTR_A3V_MASK (1 << ICH_VTR_A3V_SHIFT)
+#define ARM64_FEATURE_FIELD_BITS 4
+
+/* Create a mask for the feature bits of the specified feature. */
+#define ARM64_FEATURE_MASK(x) (GENMASK_ULL(x##_SHIFT + ARM64_FEATURE_FIELD_BITS - 1, x##_SHIFT))
+
#ifdef __ASSEMBLY__
.irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0ead8bfedf20..5b59fe5e26e4 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -239,8 +239,8 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_ELx_64BIT_ONLY),
ARM64_FTR_END,
};
@@ -1956,7 +1956,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.sys_reg = SYS_ID_AA64PFR0_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64PFR0_EL0_SHIFT,
- .min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
+ .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT,
},
#ifdef CONFIG_KVM
{
@@ -1967,7 +1967,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.sys_reg = SYS_ID_AA64PFR0_EL1,
.sign = FTR_UNSIGNED,
.field_pos = ID_AA64PFR0_EL1_SHIFT,
- .min_field_value = ID_AA64PFR0_EL1_32BIT_64BIT,
+ .min_field_value = ID_AA64PFR0_ELx_32BIT_64BIT,
},
{
.desc = "Protected KVM",
diff --git a/arch/arm64/kernel/smccc-call.S b/arch/arm64/kernel/smccc-call.S
index d3d37f932b97..487381164ff6 100644
--- a/arch/arm64/kernel/smccc-call.S
+++ b/arch/arm64/kernel/smccc-call.S
@@ -32,20 +32,23 @@ SYM_FUNC_END(__arm_smccc_sve_check)
EXPORT_SYMBOL(__arm_smccc_sve_check)
.macro SMCCC instr
+ stp x29, x30, [sp, #-16]!
+ mov x29, sp
alternative_if ARM64_SVE
bl __arm_smccc_sve_check
alternative_else_nop_endif
\instr #0
- ldr x4, [sp]
+ ldr x4, [sp, #16]
stp x0, x1, [x4, #ARM_SMCCC_RES_X0_OFFS]
stp x2, x3, [x4, #ARM_SMCCC_RES_X2_OFFS]
- ldr x4, [sp, #8]
+ ldr x4, [sp, #24]
cbz x4, 1f /* no quirk structure */
ldr x9, [x4, #ARM_SMCCC_QUIRK_ID_OFFS]
cmp x9, #ARM_SMCCC_QUIRK_QCOM_A6
b.ne 1f
str x6, [x4, ARM_SMCCC_QUIRK_STATE_OFFS]
-1: ret
+1: ldp x29, x30, [sp], #16
+ ret
.endm
/*
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 709d2c433c5e..f6b1a88245db 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -181,6 +181,8 @@ SECTIONS
/* everything from this point to __init_begin will be marked RO NX */
RO_DATA(PAGE_SIZE)
+ HYPERVISOR_DATA_SECTIONS
+
idmap_pg_dir = .;
. += IDMAP_DIR_SIZE;
idmap_pg_end = .;
@@ -260,8 +262,6 @@ SECTIONS
_sdata = .;
RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
- HYPERVISOR_DATA_SECTIONS
-
/*
* Data written with the MMU off but read with the MMU on requires
* cache lines to be invalidated, discarding up to a Cache Writeback
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index a4eba0908bfa..d7eec0b43744 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -26,6 +26,7 @@ menuconfig KVM
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
+ select KVM_XFER_TO_GUEST_WORK
select SRCU
select KVM_VFIO
select HAVE_KVM_EVENTFD
@@ -46,6 +47,15 @@ if KVM
source "virt/kvm/Kconfig"
+config NVHE_EL2_DEBUG
+ bool "Debug mode for non-VHE EL2 object"
+ help
+ Say Y here to enable the debug mode for the non-VHE KVM EL2 object.
+ Failure reports will BUG() in the hypervisor. This is intended for
+ local EL2 hypervisor development.
+
+ If unsure, say N.
+
endif # KVM
endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e9a2b8f27792..fe102cd2e518 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -6,6 +6,7 @@
#include <linux/bug.h>
#include <linux/cpu_pm.h>
+#include <linux/entry-kvm.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
@@ -15,6 +16,7 @@
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
+#include <linux/kmemleak.h>
#include <linux/kvm.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
@@ -42,10 +44,6 @@
#include <kvm/arm_pmu.h>
#include <kvm/arm_psci.h>
-#ifdef REQUIRES_VIRT
-__asm__(".arch_extension virt");
-#endif
-
static enum kvm_mode kvm_mode = KVM_MODE_DEFAULT;
DEFINE_STATIC_KEY_FALSE(kvm_protected_mode_initialized);
@@ -94,10 +92,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
kvm->arch.return_nisv_io_abort_to_user = true;
break;
case KVM_CAP_ARM_MTE:
- if (!system_supports_mte() || kvm->created_vcpus)
- return -EINVAL;
- r = 0;
- kvm->arch.mte_enabled = true;
+ mutex_lock(&kvm->lock);
+ if (!system_supports_mte() || kvm->created_vcpus) {
+ r = -EINVAL;
+ } else {
+ r = 0;
+ kvm->arch.mte_enabled = true;
+ }
+ mutex_unlock(&kvm->lock);
break;
default:
r = -EINVAL;
@@ -571,7 +573,7 @@ static void update_vmid(struct kvm_vmid *vmid)
kvm_call_hyp(__kvm_flush_vm_context);
}
- vmid->vmid = kvm_next_vmid;
+ WRITE_ONCE(vmid->vmid, kvm_next_vmid);
kvm_next_vmid++;
kvm_next_vmid &= (1 << kvm_get_vmid_bits()) - 1;
@@ -715,6 +717,45 @@ static bool vcpu_mode_is_bad_32bit(struct kvm_vcpu *vcpu)
}
/**
+ * kvm_vcpu_exit_request - returns true if the VCPU should *not* enter the guest
+ * @vcpu: The VCPU pointer
+ * @ret: Pointer to write optional return code
+ *
+ * Returns: true if the VCPU needs to return to a preemptible + interruptible
+ * and skip guest entry.
+ *
+ * This function disambiguates between two different types of exits: exits to a
+ * preemptible + interruptible kernel context and exits to userspace. For an
+ * exit to userspace, this function will write the return code to ret and return
+ * true. For an exit to preemptible + interruptible kernel context (i.e. check
+ * for pending work and re-enter), return true without writing to ret.
+ */
+static bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu, int *ret)
+{
+ struct kvm_run *run = vcpu->run;
+
+ /*
+ * If we're using a userspace irqchip, then check if we need
+ * to tell a userspace irqchip about timer or PMU level
+ * changes and if so, exit to userspace (the actual level
+ * state gets updated in kvm_timer_update_run and
+ * kvm_pmu_update_run below).
+ */
+ if (static_branch_unlikely(&userspace_irqchip_in_use)) {
+ if (kvm_timer_should_notify_user(vcpu) ||
+ kvm_pmu_should_notify_user(vcpu)) {
+ *ret = -EINTR;
+ run->exit_reason = KVM_EXIT_INTR;
+ return true;
+ }
+ }
+
+ return kvm_request_pending(vcpu) ||
+ need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
+ xfer_to_guest_mode_work_pending();
+}
+
+/**
* kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
* @vcpu: The VCPU pointer
*
@@ -757,7 +798,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
/*
* Check conditions before entering the guest
*/
- cond_resched();
+ ret = xfer_to_guest_mode_handle_work(vcpu);
+ if (!ret)
+ ret = 1;
update_vmid(&vcpu->arch.hw_mmu->vmid);
@@ -777,30 +820,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
kvm_vgic_flush_hwstate(vcpu);
/*
- * Exit if we have a signal pending so that we can deliver the
- * signal to user space.
- */
- if (signal_pending(current)) {
- ret = -EINTR;
- run->exit_reason = KVM_EXIT_INTR;
- }
-
- /*
- * If we're using a userspace irqchip, then check if we need
- * to tell a userspace irqchip about timer or PMU level
- * changes and if so, exit to userspace (the actual level
- * state gets updated in kvm_timer_update_run and
- * kvm_pmu_update_run below).
- */
- if (static_branch_unlikely(&userspace_irqchip_in_use)) {
- if (kvm_timer_should_notify_user(vcpu) ||
- kvm_pmu_should_notify_user(vcpu)) {
- ret = -EINTR;
- run->exit_reason = KVM_EXIT_INTR;
- }
- }
-
- /*
* Ensure we set mode to IN_GUEST_MODE after we disable
* interrupts and before the final VCPU requests check.
* See the comment in kvm_vcpu_exiting_guest_mode() and
@@ -808,8 +827,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
*/
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
- if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
- kvm_request_pending(vcpu)) {
+ if (ret <= 0 || kvm_vcpu_exit_request(vcpu, &ret)) {
vcpu->mode = OUTSIDE_GUEST_MODE;
isb(); /* Ensure work in x_flush_hwstate is committed */
kvm_pmu_sync_hwstate(vcpu);
@@ -1035,7 +1053,7 @@ static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
const struct kvm_vcpu_init *init)
{
unsigned int i, ret;
- int phys_target = kvm_target_cpu();
+ u32 phys_target = kvm_target_cpu();
if (init->target != phys_target)
return -EINVAL;
@@ -1104,6 +1122,7 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
}
vcpu_reset_hcr(vcpu);
+ vcpu->arch.cptr_el2 = CPTR_EL2_DEFAULT;
/*
* Handle the "start in power-off" case.
@@ -1215,6 +1234,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
if (copy_from_user(&reg, argp, sizeof(reg)))
break;
+ /*
+ * We could owe a reset due to PSCI. Handle the pending reset
+ * here to ensure userspace register accesses are ordered after
+ * the reset.
+ */
+ if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
+ kvm_reset_vcpu(vcpu);
+
if (ioctl == KVM_SET_ONE_REG)
r = kvm_arm_set_reg(vcpu, &reg);
else
@@ -1696,11 +1723,6 @@ static bool init_psci_relay(void)
return true;
}
-static int init_common_resources(void)
-{
- return kvm_set_ipa_limit();
-}
-
static int init_subsystems(void)
{
int err = 0;
@@ -1954,56 +1976,17 @@ static void _kvm_host_prot_finalize(void *discard)
WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize));
}
-static inline int pkvm_mark_hyp(phys_addr_t start, phys_addr_t end)
-{
- return kvm_call_hyp_nvhe(__pkvm_mark_hyp, start, end);
-}
-
-#define pkvm_mark_hyp_section(__section) \
- pkvm_mark_hyp(__pa_symbol(__section##_start), \
- __pa_symbol(__section##_end))
-
static int finalize_hyp_mode(void)
{
- int cpu, ret;
-
if (!is_protected_kvm_enabled())
return 0;
- ret = pkvm_mark_hyp_section(__hyp_idmap_text);
- if (ret)
- return ret;
-
- ret = pkvm_mark_hyp_section(__hyp_text);
- if (ret)
- return ret;
-
- ret = pkvm_mark_hyp_section(__hyp_rodata);
- if (ret)
- return ret;
-
- ret = pkvm_mark_hyp_section(__hyp_bss);
- if (ret)
- return ret;
-
- ret = pkvm_mark_hyp(hyp_mem_base, hyp_mem_base + hyp_mem_size);
- if (ret)
- return ret;
-
- for_each_possible_cpu(cpu) {
- phys_addr_t start = virt_to_phys((void *)kvm_arm_hyp_percpu_base[cpu]);
- phys_addr_t end = start + (PAGE_SIZE << nvhe_percpu_order());
-
- ret = pkvm_mark_hyp(start, end);
- if (ret)
- return ret;
-
- start = virt_to_phys((void *)per_cpu(kvm_arm_hyp_stack_page, cpu));
- end = start + PAGE_SIZE;
- ret = pkvm_mark_hyp(start, end);
- if (ret)
- return ret;
- }
+ /*
+ * Exclude HYP BSS from kmemleak so that it doesn't get peeked
+ * at, which would end badly once the section is inaccessible.
+ * None of other sections should ever be introspected.
+ */
+ kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
/*
* Flip the static key upfront as that may no longer be possible
@@ -2015,11 +1998,6 @@ static int finalize_hyp_mode(void)
return 0;
}
-static void check_kvm_target_cpu(void *ret)
-{
- *(int *)ret = kvm_target_cpu();
-}
-
struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
{
struct kvm_vcpu *vcpu;
@@ -2079,7 +2057,6 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *cons)
int kvm_arch_init(void *opaque)
{
int err;
- int ret, cpu;
bool in_hyp_mode;
if (!is_hyp_mode_available()) {
@@ -2094,15 +2071,7 @@ int kvm_arch_init(void *opaque)
kvm_info("Guests without required CPU erratum workarounds can deadlock system!\n" \
"Only trusted guests should be used on this system.\n");
- for_each_online_cpu(cpu) {
- smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
- if (ret < 0) {
- kvm_err("Error, CPU %d not supported!\n", cpu);
- return -ENODEV;
- }
- }
-
- err = init_common_resources();
+ err = kvm_set_ipa_limit();
if (err)
return err;
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index d5e79d7ee6e9..db9361338b2a 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -21,7 +21,7 @@
DBG_MDSCR_KDE | \
DBG_MDSCR_MDE)
-static DEFINE_PER_CPU(u32, mdcr_el2);
+static DEFINE_PER_CPU(u64, mdcr_el2);
/**
* save/restore_guest_debug_regs
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 5188184d25d0..5ce26bedf23c 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -48,6 +48,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
STATS_DESC_COUNTER(VCPU, mmio_exit_user),
STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
+ STATS_DESC_COUNTER(VCPU, signal_exits),
STATS_DESC_COUNTER(VCPU, exits)
};
@@ -838,7 +839,7 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
return 0;
}
-int __attribute_const__ kvm_target_cpu(void)
+u32 __attribute_const__ kvm_target_cpu(void)
{
unsigned long implementor = read_cpuid_implementor();
unsigned long part_number = read_cpuid_part_number();
@@ -870,7 +871,7 @@ int __attribute_const__ kvm_target_cpu(void)
int kvm_vcpu_preferred_target(struct kvm_vcpu_init *init)
{
- int target = kvm_target_cpu();
+ u32 target = kvm_target_cpu();
if (target < 0)
return -ENODEV;
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index 6f48336b1d86..275a27368a04 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/arch/arm64/kvm/handle_exit.c
@@ -113,34 +113,20 @@ static int kvm_handle_wfx(struct kvm_vcpu *vcpu)
* guest and host are using the same debug facilities it will be up to
* userspace to re-inject the correct exception for guest delivery.
*
- * @return: 0 (while setting vcpu->run->exit_reason), -1 for error
+ * @return: 0 (while setting vcpu->run->exit_reason)
*/
static int kvm_handle_guest_debug(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
u32 esr = kvm_vcpu_get_esr(vcpu);
- int ret = 0;
run->exit_reason = KVM_EXIT_DEBUG;
run->debug.arch.hsr = esr;
- switch (ESR_ELx_EC(esr)) {
- case ESR_ELx_EC_WATCHPT_LOW:
+ if (ESR_ELx_EC(esr) == ESR_ELx_EC_WATCHPT_LOW)
run->debug.arch.far = vcpu->arch.fault.far_el2;
- fallthrough;
- case ESR_ELx_EC_SOFTSTP_LOW:
- case ESR_ELx_EC_BREAKPT_LOW:
- case ESR_ELx_EC_BKPT32:
- case ESR_ELx_EC_BRK64:
- break;
- default:
- kvm_err("%s: un-handled case esr: %#08x\n",
- __func__, (unsigned int) esr);
- ret = -1;
- break;
- }
- return ret;
+ return 0;
}
static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
@@ -292,11 +278,12 @@ void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index)
kvm_handle_guest_serror(vcpu, kvm_vcpu_get_esr(vcpu));
}
-void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr,
+void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr,
+ u64 elr_virt, u64 elr_phys,
u64 par, uintptr_t vcpu,
u64 far, u64 hpfar) {
- u64 elr_in_kimg = __phys_to_kimg(__hyp_pa(elr));
- u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr;
+ u64 elr_in_kimg = __phys_to_kimg(elr_phys);
+ u64 hyp_offset = elr_in_kimg - kaslr_offset() - elr_virt;
u64 mode = spsr & PSR_MODE_MASK;
/*
@@ -309,20 +296,24 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr,
kvm_err("Invalid host exception to nVHE hyp!\n");
} else if (ESR_ELx_EC(esr) == ESR_ELx_EC_BRK64 &&
(esr & ESR_ELx_BRK64_ISS_COMMENT_MASK) == BUG_BRK_IMM) {
- struct bug_entry *bug = find_bug(elr_in_kimg);
const char *file = NULL;
unsigned int line = 0;
/* All hyp bugs, including warnings, are treated as fatal. */
- if (bug)
- bug_get_file_line(bug, &file, &line);
+ if (!is_protected_kvm_enabled() ||
+ IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) {
+ struct bug_entry *bug = find_bug(elr_in_kimg);
+
+ if (bug)
+ bug_get_file_line(bug, &file, &line);
+ }
if (file)
kvm_err("nVHE hyp BUG at: %s:%u!\n", file, line);
else
- kvm_err("nVHE hyp BUG at: %016llx!\n", elr + hyp_offset);
+ kvm_err("nVHE hyp BUG at: %016llx!\n", elr_virt + hyp_offset);
} else {
- kvm_err("nVHE hyp panic at: %016llx!\n", elr + hyp_offset);
+ kvm_err("nVHE hyp panic at: %016llx!\n", elr_virt + hyp_offset);
}
/*
@@ -334,5 +325,5 @@ void __noreturn __cold nvhe_hyp_panic_handler(u64 esr, u64 spsr, u64 elr,
kvm_err("Hyp Offset: 0x%llx\n", hyp_offset);
panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%016lx\n",
- spsr, elr, esr, far, hpfar, par, vcpu);
+ spsr, elr_virt, esr, far, hpfar, par, vcpu);
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index e4a2f295a394..a0e78a6027be 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -92,11 +92,15 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
write_sysreg(0, pmselr_el0);
write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0);
}
+
+ vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
}
-static inline void __deactivate_traps_common(void)
+static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
{
+ write_sysreg(vcpu->arch.mdcr_el2_host, mdcr_el2);
+
write_sysreg(0, hstr_el2);
if (kvm_arm_support_pmu_v3())
write_sysreg(0, pmuserenr_el0);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index 9c227d87c36d..b58c910babaf 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -12,6 +12,32 @@
#include <asm/virt.h>
#include <nvhe/spinlock.h>
+/*
+ * SW bits 0-1 are reserved to track the memory ownership state of each page:
+ * 00: The page is owned exclusively by the page-table owner.
+ * 01: The page is owned by the page-table owner, but is shared
+ * with another entity.
+ * 10: The page is shared with, but not owned by the page-table owner.
+ * 11: Reserved for future use (lending).
+ */
+enum pkvm_page_state {
+ PKVM_PAGE_OWNED = 0ULL,
+ PKVM_PAGE_SHARED_OWNED = KVM_PGTABLE_PROT_SW0,
+ PKVM_PAGE_SHARED_BORROWED = KVM_PGTABLE_PROT_SW1,
+};
+
+#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1)
+static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot,
+ enum pkvm_page_state state)
+{
+ return (prot & ~PKVM_PAGE_STATE_PROT_MASK) | state;
+}
+
+static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot)
+{
+ return prot & PKVM_PAGE_STATE_PROT_MASK;
+}
+
struct host_kvm {
struct kvm_arch arch;
struct kvm_pgtable pgt;
@@ -20,16 +46,21 @@ struct host_kvm {
};
extern struct host_kvm host_kvm;
+extern const u8 pkvm_hyp_id;
+
int __pkvm_prot_finalize(void);
-int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end);
+int __pkvm_host_share_hyp(u64 pfn);
+bool addr_is_memory(phys_addr_t phys);
+int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
+int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id);
int kvm_host_prepare_stage2(void *pgt_pool_base);
void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt);
static __always_inline void __load_host_stage2(void)
{
if (static_branch_likely(&kvm_protected_mode_initialized))
- __load_stage2(&host_kvm.arch.mmu, host_kvm.arch.vtcr);
+ __load_stage2(&host_kvm.arch.mmu, &host_kvm.arch);
else
write_sysreg(0, vttbr_el2);
}
diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h
index 8ec3a5a7744b..c9a8f535212e 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mm.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h
@@ -23,8 +23,7 @@ int hyp_map_vectors(void);
int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back);
int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot);
int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot);
-int __pkvm_create_mappings(unsigned long start, unsigned long size,
- unsigned long phys, enum kvm_pgtable_prot prot);
+int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot);
unsigned long __pkvm_create_private_mapping(phys_addr_t phys, size_t size,
enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
index 76b537f8d1c6..4652fd04bdbe 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h
@@ -15,6 +15,7 @@
#include <asm/alternative.h>
#include <asm/lse.h>
+#include <asm/rwonce.h>
typedef union hyp_spinlock {
u32 __val;
@@ -89,4 +90,28 @@ static inline void hyp_spin_unlock(hyp_spinlock_t *lock)
: "memory");
}
+static inline bool hyp_spin_is_locked(hyp_spinlock_t *lock)
+{
+ hyp_spinlock_t lockval = READ_ONCE(*lock);
+
+ return lockval.owner != lockval.next;
+}
+
+#ifdef CONFIG_NVHE_EL2_DEBUG
+static inline void hyp_assert_lock_held(hyp_spinlock_t *lock)
+{
+ /*
+ * The __pkvm_init() path accesses protected data-structures without
+ * holding locks as the other CPUs are guaranteed to not enter EL2
+ * concurrently at this point in time. The point by which EL2 is
+ * initialized on all CPUs is reflected in the pkvm static key, so
+ * wait until it is set before checking the lock state.
+ */
+ if (static_branch_likely(&kvm_protected_mode_initialized))
+ BUG_ON(!hyp_spin_is_locked(lock));
+}
+#else
+static inline void hyp_assert_lock_held(hyp_spinlock_t *lock) { }
+#endif
+
#endif /* __ARM64_KVM_NVHE_SPINLOCK_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
index 7d3f25868cae..df361d839902 100644
--- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c
@@ -109,7 +109,7 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
__debug_switch_to_host_common(vcpu);
}
-u32 __kvm_get_mdcr_el2(void)
+u64 __kvm_get_mdcr_el2(void)
{
return read_sysreg(mdcr_el2);
}
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 2b23400e0fb3..4b652ffb591d 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -7,6 +7,7 @@
#include <linux/linkage.h>
#include <asm/assembler.h>
+#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
@@ -85,12 +86,24 @@ SYM_FUNC_START(__hyp_do_panic)
mov x29, x0
+#ifdef CONFIG_NVHE_EL2_DEBUG
+ /* Ensure host stage-2 is disabled */
+ mrs x0, hcr_el2
+ bic x0, x0, #HCR_VM
+ msr hcr_el2, x0
+ isb
+ tlbi vmalls12e1
+ dsb nsh
+#endif
+
/* Load the panic arguments into x0-7 */
mrs x0, esr_el2
- get_vcpu_ptr x4, x5
- mrs x5, far_el2
- mrs x6, hpfar_el2
- mov x7, xzr // Unused argument
+ mov x4, x3
+ mov x3, x2
+ hyp_pa x3, x6
+ get_vcpu_ptr x5, x6
+ mrs x6, far_el2
+ mrs x7, hpfar_el2
/* Enter the host, conditionally restoring the host context. */
cbz x29, __host_enter_without_restoring
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 1632f001f4ed..2da6aa8da868 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -140,14 +140,11 @@ static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt)
cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot);
}
-static void handle___pkvm_create_mappings(struct kvm_cpu_context *host_ctxt)
+static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt)
{
- DECLARE_REG(unsigned long, start, host_ctxt, 1);
- DECLARE_REG(unsigned long, size, host_ctxt, 2);
- DECLARE_REG(unsigned long, phys, host_ctxt, 3);
- DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4);
+ DECLARE_REG(u64, pfn, host_ctxt, 1);
- cpu_reg(host_ctxt, 1) = __pkvm_create_mappings(start, size, phys, prot);
+ cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn);
}
static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt)
@@ -163,14 +160,6 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
{
cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
}
-
-static void handle___pkvm_mark_hyp(struct kvm_cpu_context *host_ctxt)
-{
- DECLARE_REG(phys_addr_t, start, host_ctxt, 1);
- DECLARE_REG(phys_addr_t, end, host_ctxt, 2);
-
- cpu_reg(host_ctxt, 1) = __pkvm_mark_hyp(start, end);
-}
typedef void (*hcall_t)(struct kvm_cpu_context *);
#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x
@@ -193,10 +182,9 @@ static const hcall_t host_hcall[] = {
HANDLE_FUNC(__vgic_v3_restore_aprs),
HANDLE_FUNC(__pkvm_init),
HANDLE_FUNC(__pkvm_cpu_set_vector),
- HANDLE_FUNC(__pkvm_create_mappings),
+ HANDLE_FUNC(__pkvm_host_share_hyp),
HANDLE_FUNC(__pkvm_create_private_mapping),
HANDLE_FUNC(__pkvm_prot_finalize),
- HANDLE_FUNC(__pkvm_mark_hyp),
};
static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index d938ce95d3bd..bacd493a4eac 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -31,7 +31,7 @@ static struct hyp_pool host_s2_pool;
u64 id_aa64mmfr0_el1_sys_val;
u64 id_aa64mmfr1_el1_sys_val;
-static const u8 pkvm_hyp_id = 1;
+const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
{
@@ -89,6 +89,8 @@ static void prepare_host_vtcr(void)
id_aa64mmfr1_el1_sys_val, phys_shift);
}
+static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot);
+
int kvm_host_prepare_stage2(void *pgt_pool_base)
{
struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu;
@@ -101,16 +103,17 @@ int kvm_host_prepare_stage2(void *pgt_pool_base)
if (ret)
return ret;
- ret = kvm_pgtable_stage2_init_flags(&host_kvm.pgt, &host_kvm.arch,
- &host_kvm.mm_ops, KVM_HOST_S2_FLAGS);
+ ret = __kvm_pgtable_stage2_init(&host_kvm.pgt, &host_kvm.arch,
+ &host_kvm.mm_ops, KVM_HOST_S2_FLAGS,
+ host_stage2_force_pte_cb);
if (ret)
return ret;
mmu->pgd_phys = __hyp_pa(host_kvm.pgt.pgd);
mmu->arch = &host_kvm.arch;
mmu->pgt = &host_kvm.pgt;
- mmu->vmid.vmid_gen = 0;
- mmu->vmid.vmid = 0;
+ WRITE_ONCE(mmu->vmid.vmid_gen, 0);
+ WRITE_ONCE(mmu->vmid.vmid, 0);
return 0;
}
@@ -126,7 +129,7 @@ int __pkvm_prot_finalize(void)
kvm_flush_dcache_to_poc(params, sizeof(*params));
write_sysreg(params->hcr_el2, hcr_el2);
- __load_stage2(&host_kvm.arch.mmu, host_kvm.arch.vtcr);
+ __load_stage2(&host_kvm.arch.mmu, &host_kvm.arch);
/*
* Make sure to have an ISB before the TLB maintenance below but only
@@ -159,6 +162,11 @@ static int host_stage2_unmap_dev_all(void)
return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr);
}
+struct kvm_mem_range {
+ u64 start;
+ u64 end;
+};
+
static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range)
{
int cur, left = 0, right = hyp_memblock_nr;
@@ -189,16 +197,26 @@ static bool find_mem_range(phys_addr_t addr, struct kvm_mem_range *range)
return false;
}
+bool addr_is_memory(phys_addr_t phys)
+{
+ struct kvm_mem_range range;
+
+ return find_mem_range(phys, &range);
+}
+
+static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range)
+{
+ return range->start <= addr && addr < range->end;
+}
+
static bool range_is_memory(u64 start, u64 end)
{
- struct kvm_mem_range r1, r2;
+ struct kvm_mem_range r;
- if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2))
- return false;
- if (r1.start != r2.start)
+ if (!find_mem_range(start, &r))
return false;
- return true;
+ return is_in_mem_range(end - 1, &r);
}
static inline int __host_stage2_idmap(u64 start, u64 end,
@@ -208,60 +226,208 @@ static inline int __host_stage2_idmap(u64 start, u64 end,
prot, &host_s2_pool);
}
+/*
+ * The pool has been provided with enough pages to cover all of memory with
+ * page granularity, but it is difficult to know how much of the MMIO range
+ * we will need to cover upfront, so we may need to 'recycle' the pages if we
+ * run out.
+ */
+#define host_stage2_try(fn, ...) \
+ ({ \
+ int __ret; \
+ hyp_assert_lock_held(&host_kvm.lock); \
+ __ret = fn(__VA_ARGS__); \
+ if (__ret == -ENOMEM) { \
+ __ret = host_stage2_unmap_dev_all(); \
+ if (!__ret) \
+ __ret = fn(__VA_ARGS__); \
+ } \
+ __ret; \
+ })
+
+static inline bool range_included(struct kvm_mem_range *child,
+ struct kvm_mem_range *parent)
+{
+ return parent->start <= child->start && child->end <= parent->end;
+}
+
+static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
+{
+ struct kvm_mem_range cur;
+ kvm_pte_t pte;
+ u32 level;
+ int ret;
+
+ hyp_assert_lock_held(&host_kvm.lock);
+ ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, &level);
+ if (ret)
+ return ret;
+
+ if (kvm_pte_valid(pte))
+ return -EAGAIN;
+
+ if (pte)
+ return -EPERM;
+
+ do {
+ u64 granule = kvm_granule_size(level);
+ cur.start = ALIGN_DOWN(addr, granule);
+ cur.end = cur.start + granule;
+ level++;
+ } while ((level < KVM_PGTABLE_MAX_LEVELS) &&
+ !(kvm_level_supports_block_mapping(level) &&
+ range_included(&cur, range)));
+
+ *range = cur;
+
+ return 0;
+}
+
+int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
+ enum kvm_pgtable_prot prot)
+{
+ hyp_assert_lock_held(&host_kvm.lock);
+
+ return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
+}
+
+int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
+{
+ hyp_assert_lock_held(&host_kvm.lock);
+
+ return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt,
+ addr, size, &host_s2_pool, owner_id);
+}
+
+static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
+{
+ /*
+ * Block mappings must be used with care in the host stage-2 as a
+ * kvm_pgtable_stage2_map() operation targeting a page in the range of
+ * an existing block will delete the block under the assumption that
+ * mappings in the rest of the block range can always be rebuilt lazily.
+ * That assumption is correct for the host stage-2 with RWX mappings
+ * targeting memory or RW mappings targeting MMIO ranges (see
+ * host_stage2_idmap() below which implements some of the host memory
+ * abort logic). However, this is not safe for any other mappings where
+ * the host stage-2 page-table is in fact the only place where this
+ * state is stored. In all those cases, it is safer to use page-level
+ * mappings, hence avoiding to lose the state because of side-effects in
+ * kvm_pgtable_stage2_map().
+ */
+ if (range_is_memory(addr, end))
+ return prot != PKVM_HOST_MEM_PROT;
+ else
+ return prot != PKVM_HOST_MMIO_PROT;
+}
+
static int host_stage2_idmap(u64 addr)
{
- enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W;
struct kvm_mem_range range;
bool is_memory = find_mem_range(addr, &range);
+ enum kvm_pgtable_prot prot;
int ret;
- if (is_memory)
- prot |= KVM_PGTABLE_PROT_X;
+ prot = is_memory ? PKVM_HOST_MEM_PROT : PKVM_HOST_MMIO_PROT;
hyp_spin_lock(&host_kvm.lock);
- ret = kvm_pgtable_stage2_find_range(&host_kvm.pgt, addr, prot, &range);
+ ret = host_stage2_adjust_range(addr, &range);
if (ret)
goto unlock;
- ret = __host_stage2_idmap(range.start, range.end, prot);
- if (ret != -ENOMEM)
+ ret = host_stage2_idmap_locked(range.start, range.end - range.start, prot);
+unlock:
+ hyp_spin_unlock(&host_kvm.lock);
+
+ return ret;
+}
+
+static inline bool check_prot(enum kvm_pgtable_prot prot,
+ enum kvm_pgtable_prot required,
+ enum kvm_pgtable_prot denied)
+{
+ return (prot & (required | denied)) == required;
+}
+
+int __pkvm_host_share_hyp(u64 pfn)
+{
+ phys_addr_t addr = hyp_pfn_to_phys(pfn);
+ enum kvm_pgtable_prot prot, cur;
+ void *virt = __hyp_va(addr);
+ enum pkvm_page_state state;
+ kvm_pte_t pte;
+ int ret;
+
+ if (!addr_is_memory(addr))
+ return -EINVAL;
+
+ hyp_spin_lock(&host_kvm.lock);
+ hyp_spin_lock(&pkvm_pgd_lock);
+
+ ret = kvm_pgtable_get_leaf(&host_kvm.pgt, addr, &pte, NULL);
+ if (ret)
goto unlock;
+ if (!pte)
+ goto map_shared;
/*
- * The pool has been provided with enough pages to cover all of memory
- * with page granularity, but it is difficult to know how much of the
- * MMIO range we will need to cover upfront, so we may need to 'recycle'
- * the pages if we run out.
+ * Check attributes in the host stage-2 PTE. We need the page to be:
+ * - mapped RWX as we're sharing memory;
+ * - not borrowed, as that implies absence of ownership.
+ * Otherwise, we can't let it got through
*/
- ret = host_stage2_unmap_dev_all();
- if (ret)
+ cur = kvm_pgtable_stage2_pte_prot(pte);
+ prot = pkvm_mkstate(0, PKVM_PAGE_SHARED_BORROWED);
+ if (!check_prot(cur, PKVM_HOST_MEM_PROT, prot)) {
+ ret = -EPERM;
goto unlock;
+ }
- ret = __host_stage2_idmap(range.start, range.end, prot);
+ state = pkvm_getstate(cur);
+ if (state == PKVM_PAGE_OWNED)
+ goto map_shared;
-unlock:
- hyp_spin_unlock(&host_kvm.lock);
+ /*
+ * Tolerate double-sharing the same page, but this requires
+ * cross-checking the hypervisor stage-1.
+ */
+ if (state != PKVM_PAGE_SHARED_OWNED) {
+ ret = -EPERM;
+ goto unlock;
+ }
- return ret;
-}
+ ret = kvm_pgtable_get_leaf(&pkvm_pgtable, (u64)virt, &pte, NULL);
+ if (ret)
+ goto unlock;
-int __pkvm_mark_hyp(phys_addr_t start, phys_addr_t end)
-{
- int ret;
+ /*
+ * If the page has been shared with the hypervisor, it must be
+ * already mapped as SHARED_BORROWED in its stage-1.
+ */
+ cur = kvm_pgtable_hyp_pte_prot(pte);
+ prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+ if (!check_prot(cur, prot, ~prot))
+ ret = -EPERM;
+ goto unlock;
+map_shared:
/*
- * host_stage2_unmap_dev_all() currently relies on MMIO mappings being
- * non-persistent, so don't allow changing page ownership in MMIO range.
+ * If the page is not yet shared, adjust mappings in both page-tables
+ * while both locks are held.
*/
- if (!range_is_memory(start, end))
- return -EINVAL;
+ prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_SHARED_BORROWED);
+ ret = pkvm_create_mappings_locked(virt, virt + PAGE_SIZE, prot);
+ BUG_ON(ret);
- hyp_spin_lock(&host_kvm.lock);
- ret = kvm_pgtable_stage2_set_owner(&host_kvm.pgt, start, end - start,
- &host_s2_pool, pkvm_hyp_id);
+ prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED);
+ ret = host_stage2_idmap_locked(addr, PAGE_SIZE, prot);
+ BUG_ON(ret);
+
+unlock:
+ hyp_spin_unlock(&pkvm_pgd_lock);
hyp_spin_unlock(&host_kvm.lock);
- return ret != -EAGAIN ? ret : 0;
+ return ret;
}
void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt)
diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c
index a8efdf0f9003..2fabeceb889a 100644
--- a/arch/arm64/kvm/hyp/nvhe/mm.c
+++ b/arch/arm64/kvm/hyp/nvhe/mm.c
@@ -23,8 +23,8 @@ u64 __io_map_base;
struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS];
unsigned int hyp_memblock_nr;
-int __pkvm_create_mappings(unsigned long start, unsigned long size,
- unsigned long phys, enum kvm_pgtable_prot prot)
+static int __pkvm_create_mappings(unsigned long start, unsigned long size,
+ unsigned long phys, enum kvm_pgtable_prot prot)
{
int err;
@@ -67,13 +67,15 @@ out:
return addr;
}
-int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
+int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot)
{
unsigned long start = (unsigned long)from;
unsigned long end = (unsigned long)to;
unsigned long virt_addr;
phys_addr_t phys;
+ hyp_assert_lock_held(&pkvm_pgd_lock);
+
start = start & PAGE_MASK;
end = PAGE_ALIGN(end);
@@ -81,7 +83,8 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
int err;
phys = hyp_virt_to_phys((void *)virt_addr);
- err = __pkvm_create_mappings(virt_addr, PAGE_SIZE, phys, prot);
+ err = kvm_pgtable_hyp_map(&pkvm_pgtable, virt_addr, PAGE_SIZE,
+ phys, prot);
if (err)
return err;
}
@@ -89,6 +92,17 @@ int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
return 0;
}
+int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
+{
+ int ret;
+
+ hyp_spin_lock(&pkvm_pgd_lock);
+ ret = pkvm_create_mappings_locked(from, to, prot);
+ hyp_spin_unlock(&pkvm_pgd_lock);
+
+ return ret;
+}
+
int hyp_back_vmemmap(phys_addr_t phys, unsigned long size, phys_addr_t back)
{
unsigned long start, end;
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 0b574d106519..57c27846320f 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -58,6 +58,7 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
{
void *start, *end, *virt = hyp_phys_to_virt(phys);
unsigned long pgt_size = hyp_s1_pgtable_pages() << PAGE_SHIFT;
+ enum kvm_pgtable_prot prot;
int ret, i;
/* Recreate the hyp page-table using the early page allocator */
@@ -83,10 +84,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
- ret = pkvm_create_mappings(__start_rodata, __end_rodata, PAGE_HYP_RO);
- if (ret)
- return ret;
-
ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO);
if (ret)
return ret;
@@ -95,10 +92,6 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
if (ret)
return ret;
- ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, PAGE_HYP_RO);
- if (ret)
- return ret;
-
ret = pkvm_create_mappings(virt, virt + size, PAGE_HYP);
if (ret)
return ret;
@@ -117,6 +110,24 @@ static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size,
return ret;
}
+ /*
+ * Map the host's .bss and .rodata sections RO in the hypervisor, but
+ * transfer the ownership from the host to the hypervisor itself to
+ * make sure it can't be donated or shared with another entity.
+ *
+ * The ownership transition requires matching changes in the host
+ * stage-2. This will be done later (see finalize_host_mappings()) once
+ * the hyp_vmemmap is addressable.
+ */
+ prot = pkvm_mkstate(PAGE_HYP_RO, PKVM_PAGE_SHARED_OWNED);
+ ret = pkvm_create_mappings(__start_rodata, __end_rodata, prot);
+ if (ret)
+ return ret;
+
+ ret = pkvm_create_mappings(__hyp_bss_end, __bss_stop, prot);
+ if (ret)
+ return ret;
+
return 0;
}
@@ -148,6 +159,57 @@ static void hpool_put_page(void *addr)
hyp_put_page(&hpool, addr);
}
+static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
+ kvm_pte_t *ptep,
+ enum kvm_pgtable_walk_flags flag,
+ void * const arg)
+{
+ enum kvm_pgtable_prot prot;
+ enum pkvm_page_state state;
+ kvm_pte_t pte = *ptep;
+ phys_addr_t phys;
+
+ if (!kvm_pte_valid(pte))
+ return 0;
+
+ if (level != (KVM_PGTABLE_MAX_LEVELS - 1))
+ return -EINVAL;
+
+ phys = kvm_pte_to_phys(pte);
+ if (!addr_is_memory(phys))
+ return 0;
+
+ /*
+ * Adjust the host stage-2 mappings to match the ownership attributes
+ * configured in the hypervisor stage-1.
+ */
+ state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
+ switch (state) {
+ case PKVM_PAGE_OWNED:
+ return host_stage2_set_owner_locked(phys, PAGE_SIZE, pkvm_hyp_id);
+ case PKVM_PAGE_SHARED_OWNED:
+ prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED);
+ break;
+ case PKVM_PAGE_SHARED_BORROWED:
+ prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_OWNED);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return host_stage2_idmap_locked(phys, PAGE_SIZE, prot);
+}
+
+static int finalize_host_mappings(void)
+{
+ struct kvm_pgtable_walker walker = {
+ .cb = finalize_host_mappings_walker,
+ .flags = KVM_PGTABLE_WALK_LEAF,
+ };
+
+ return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), &walker);
+}
+
void __noreturn __pkvm_init_finalise(void)
{
struct kvm_host_data *host_data = this_cpu_ptr(&kvm_host_data);
@@ -167,6 +229,10 @@ void __noreturn __pkvm_init_finalise(void)
if (ret)
goto out;
+ ret = finalize_host_mappings();
+ if (ret)
+ goto out;
+
pkvm_pgtable_mm_ops = (struct kvm_pgtable_mm_ops) {
.zalloc_page = hyp_zalloc_hyp_page,
.phys_to_virt = hyp_phys_to_virt,
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index f7af9688c1f7..a34b01cc8ab9 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -41,7 +41,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
___activate_traps(vcpu);
__activate_traps_common(vcpu);
- val = CPTR_EL2_DEFAULT;
+ val = vcpu->arch.cptr_el2;
val |= CPTR_EL2_TTA | CPTR_EL2_TAM;
if (!update_fp_enabled(vcpu)) {
val |= CPTR_EL2_TFP | CPTR_EL2_TZ;
@@ -69,12 +69,10 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
static void __deactivate_traps(struct kvm_vcpu *vcpu)
{
extern char __kvm_hyp_host_vector[];
- u64 mdcr_el2, cptr;
+ u64 cptr;
___deactivate_traps(vcpu);
- mdcr_el2 = read_sysreg(mdcr_el2);
-
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
u64 val;
@@ -92,13 +90,8 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
isb();
}
- __deactivate_traps_common();
-
- mdcr_el2 &= MDCR_EL2_HPMN_MASK;
- mdcr_el2 |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
- mdcr_el2 |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT;
+ __deactivate_traps_common(vcpu);
- write_sysreg(mdcr_el2, mdcr_el2);
write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
cptr = CPTR_EL2_DEFAULT;
@@ -170,6 +163,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct kvm_cpu_context *host_ctxt;
struct kvm_cpu_context *guest_ctxt;
+ struct kvm_s2_mmu *mmu;
bool pmu_switch_needed;
u64 exit_code;
@@ -213,7 +207,8 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
__sysreg32_restore_state(vcpu);
__sysreg_restore_state_nvhe(guest_ctxt);
- __load_guest_stage2(kern_hyp_va(vcpu->arch.hw_mmu));
+ mmu = kern_hyp_va(vcpu->arch.hw_mmu);
+ __load_stage2(mmu, kern_hyp_va(mmu->arch));
__activate_traps(vcpu);
__hyp_vgic_restore_state(vcpu);
diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c
index 38ed0f6f2703..d296d617f589 100644
--- a/arch/arm64/kvm/hyp/nvhe/tlb.c
+++ b/arch/arm64/kvm/hyp/nvhe/tlb.c
@@ -34,12 +34,12 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
}
/*
- * __load_guest_stage2() includes an ISB only when the AT
+ * __load_stage2() includes an ISB only when the AT
* workaround is applied. Take care of the opposite condition,
* ensuring that we always have an ISB, but not two ISBs back
* to back.
*/
- __load_guest_stage2(mmu);
+ __load_stage2(mmu, kern_hyp_va(mmu->arch));
asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT));
}
diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
index 05321f4165e3..f8ceebe4982e 100644
--- a/arch/arm64/kvm/hyp/pgtable.c
+++ b/arch/arm64/kvm/hyp/pgtable.c
@@ -11,16 +11,12 @@
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
-#define KVM_PTE_VALID BIT(0)
#define KVM_PTE_TYPE BIT(1)
#define KVM_PTE_TYPE_BLOCK 0
#define KVM_PTE_TYPE_PAGE 1
#define KVM_PTE_TYPE_TABLE 1
-#define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT)
-#define KVM_PTE_ADDR_51_48 GENMASK(15, 12)
-
#define KVM_PTE_LEAF_ATTR_LO GENMASK(11, 2)
#define KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX GENMASK(4, 2)
@@ -40,6 +36,8 @@
#define KVM_PTE_LEAF_ATTR_HI GENMASK(63, 51)
+#define KVM_PTE_LEAF_ATTR_HI_SW GENMASK(58, 55)
+
#define KVM_PTE_LEAF_ATTR_HI_S1_XN BIT(54)
#define KVM_PTE_LEAF_ATTR_HI_S2_XN BIT(54)
@@ -48,9 +46,7 @@
KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
KVM_PTE_LEAF_ATTR_HI_S2_XN)
-#define KVM_PTE_LEAF_ATTR_S2_IGNORED GENMASK(58, 55)
-
-#define KVM_INVALID_PTE_OWNER_MASK GENMASK(63, 56)
+#define KVM_INVALID_PTE_OWNER_MASK GENMASK(9, 2)
#define KVM_MAX_OWNER_ID 1
struct kvm_pgtable_walk_data {
@@ -61,17 +57,6 @@ struct kvm_pgtable_walk_data {
u64 end;
};
-static u64 kvm_granule_shift(u32 level)
-{
- /* Assumes KVM_PGTABLE_MAX_LEVELS is 4 */
- return ARM64_HW_PGTABLE_LEVEL_SHIFT(level);
-}
-
-static u64 kvm_granule_size(u32 level)
-{
- return BIT(kvm_granule_shift(level));
-}
-
#define KVM_PHYS_INVALID (-1ULL)
static bool kvm_phys_is_valid(u64 phys)
@@ -79,15 +64,6 @@ static bool kvm_phys_is_valid(u64 phys)
return phys < BIT(id_aa64mmfr0_parange_to_phys_shift(ID_AA64MMFR0_PARANGE_MAX));
}
-static bool kvm_level_supports_block_mapping(u32 level)
-{
- /*
- * Reject invalid block mappings and don't bother with 4TB mappings for
- * 52-bit PAs.
- */
- return !(level == 0 || (PAGE_SIZE != SZ_4K && level == 1));
-}
-
static bool kvm_block_mapping_supported(u64 addr, u64 end, u64 phys, u32 level)
{
u64 granule = kvm_granule_size(level);
@@ -135,11 +111,6 @@ static u32 kvm_pgd_pages(u32 ia_bits, u32 start_level)
return __kvm_pgd_page_idx(&pgt, -1ULL) + 1;
}
-static bool kvm_pte_valid(kvm_pte_t pte)
-{
- return pte & KVM_PTE_VALID;
-}
-
static bool kvm_pte_table(kvm_pte_t pte, u32 level)
{
if (level == KVM_PGTABLE_MAX_LEVELS - 1)
@@ -151,16 +122,6 @@ static bool kvm_pte_table(kvm_pte_t pte, u32 level)
return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE;
}
-static u64 kvm_pte_to_phys(kvm_pte_t pte)
-{
- u64 pa = pte & KVM_PTE_ADDR_MASK;
-
- if (PAGE_SHIFT == 16)
- pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48;
-
- return pa;
-}
-
static kvm_pte_t kvm_phys_to_pte(u64 pa)
{
kvm_pte_t pte = pa & KVM_PTE_ADDR_MASK;
@@ -326,6 +287,45 @@ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size,
return _kvm_pgtable_walk(&walk_data);
}
+struct leaf_walk_data {
+ kvm_pte_t pte;
+ u32 level;
+};
+
+static int leaf_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep,
+ enum kvm_pgtable_walk_flags flag, void * const arg)
+{
+ struct leaf_walk_data *data = arg;
+
+ data->pte = *ptep;
+ data->level = level;
+
+ return 0;
+}
+
+int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr,
+ kvm_pte_t *ptep, u32 *level)
+{
+ struct leaf_walk_data data;
+ struct kvm_pgtable_walker walker = {
+ .cb = leaf_walker,
+ .flags = KVM_PGTABLE_WALK_LEAF,
+ .arg = &data,
+ };
+ int ret;
+
+ ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE),
+ PAGE_SIZE, &walker);
+ if (!ret) {
+ if (ptep)
+ *ptep = data.pte;
+ if (level)
+ *level = data.level;
+ }
+
+ return ret;
+}
+
struct hyp_map_data {
u64 phys;
kvm_pte_t attr;
@@ -357,11 +357,47 @@ static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep)
attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap);
attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh);
attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF;
+ attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
*ptep = attr;
return 0;
}
+enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte)
+{
+ enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW;
+ u32 ap;
+
+ if (!kvm_pte_valid(pte))
+ return prot;
+
+ if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN))
+ prot |= KVM_PGTABLE_PROT_X;
+
+ ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte);
+ if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO)
+ prot |= KVM_PGTABLE_PROT_R;
+ else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW)
+ prot |= KVM_PGTABLE_PROT_RW;
+
+ return prot;
+}
+
+static bool hyp_pte_needs_update(kvm_pte_t old, kvm_pte_t new)
+{
+ /*
+ * Tolerate KVM recreating the exact same mapping, or changing software
+ * bits if the existing mapping was valid.
+ */
+ if (old == new)
+ return false;
+
+ if (!kvm_pte_valid(old))
+ return true;
+
+ return !WARN_ON((old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW);
+}
+
static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level,
kvm_pte_t *ptep, struct hyp_map_data *data)
{
@@ -371,9 +407,8 @@ static bool hyp_map_walker_try_leaf(u64 addr, u64 end, u32 level,
if (!kvm_block_mapping_supported(addr, end, phys, level))
return false;
- /* Tolerate KVM recreating the exact same mapping */
new = kvm_init_valid_leaf_pte(phys, data->attr, level);
- if (old != new && !WARN_ON(kvm_pte_valid(old)))
+ if (hyp_pte_needs_update(old, new))
smp_store_release(ptep, new);
data->phys += granule;
@@ -438,6 +473,8 @@ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits,
pgt->start_level = KVM_PGTABLE_MAX_LEVELS - levels;
pgt->mm_ops = mm_ops;
pgt->mmu = NULL;
+ pgt->force_pte_cb = NULL;
+
return 0;
}
@@ -475,6 +512,9 @@ struct stage2_map_data {
void *memcache;
struct kvm_pgtable_mm_ops *mm_ops;
+
+ /* Force mappings to page granularity */
+ bool force_pte;
};
u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift)
@@ -539,11 +579,29 @@ static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot p
attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh);
attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF;
+ attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW;
*ptep = attr;
return 0;
}
+enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte)
+{
+ enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW;
+
+ if (!kvm_pte_valid(pte))
+ return prot;
+
+ if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R)
+ prot |= KVM_PGTABLE_PROT_R;
+ if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W)
+ prot |= KVM_PGTABLE_PROT_W;
+ if (!(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN))
+ prot |= KVM_PGTABLE_PROT_X;
+
+ return prot;
+}
+
static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new)
{
if (!kvm_pte_valid(old) || !kvm_pte_valid(new))
@@ -588,6 +646,15 @@ static bool stage2_pte_executable(kvm_pte_t pte)
return !(pte & KVM_PTE_LEAF_ATTR_HI_S2_XN);
}
+static bool stage2_leaf_mapping_allowed(u64 addr, u64 end, u32 level,
+ struct stage2_map_data *data)
+{
+ if (data->force_pte && (level < (KVM_PGTABLE_MAX_LEVELS - 1)))
+ return false;
+
+ return kvm_block_mapping_supported(addr, end, data->phys, level);
+}
+
static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
kvm_pte_t *ptep,
struct stage2_map_data *data)
@@ -597,7 +664,7 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
struct kvm_pgtable *pgt = data->mmu->pgt;
struct kvm_pgtable_mm_ops *mm_ops = data->mm_ops;
- if (!kvm_block_mapping_supported(addr, end, phys, level))
+ if (!stage2_leaf_mapping_allowed(addr, end, level, data))
return -E2BIG;
if (kvm_phys_is_valid(phys))
@@ -641,7 +708,7 @@ static int stage2_map_walk_table_pre(u64 addr, u64 end, u32 level,
if (data->anchor)
return 0;
- if (!kvm_block_mapping_supported(addr, end, data->phys, level))
+ if (!stage2_leaf_mapping_allowed(addr, end, level, data))
return 0;
data->childp = kvm_pte_follow(*ptep, data->mm_ops);
@@ -771,6 +838,7 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
.mmu = pgt->mmu,
.memcache = mc,
.mm_ops = pgt->mm_ops,
+ .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot),
};
struct kvm_pgtable_walker walker = {
.cb = stage2_map_walker,
@@ -802,6 +870,7 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
.memcache = mc,
.mm_ops = pgt->mm_ops,
.owner_id = owner_id,
+ .force_pte = true,
};
struct kvm_pgtable_walker walker = {
.cb = stage2_map_walker,
@@ -995,6 +1064,9 @@ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr,
u32 level;
kvm_pte_t set = 0, clr = 0;
+ if (prot & KVM_PTE_LEAF_ATTR_HI_SW)
+ return -EINVAL;
+
if (prot & KVM_PGTABLE_PROT_R)
set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R;
@@ -1043,9 +1115,11 @@ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size)
return kvm_pgtable_walk(pgt, addr, size, &walker);
}
-int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch,
- struct kvm_pgtable_mm_ops *mm_ops,
- enum kvm_pgtable_stage2_flags flags)
+
+int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_arch *arch,
+ struct kvm_pgtable_mm_ops *mm_ops,
+ enum kvm_pgtable_stage2_flags flags,
+ kvm_pgtable_force_pte_cb_t force_pte_cb)
{
size_t pgd_sz;
u64 vtcr = arch->vtcr;
@@ -1063,6 +1137,7 @@ int kvm_pgtable_stage2_init_flags(struct kvm_pgtable *pgt, struct kvm_arch *arch
pgt->mm_ops = mm_ops;
pgt->mmu = &arch->mmu;
pgt->flags = flags;
+ pgt->force_pte_cb = force_pte_cb;
/* Ensure zeroed PGD pages are visible to the hardware walker */
dsb(ishst);
@@ -1102,77 +1177,3 @@ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt)
pgt->mm_ops->free_pages_exact(pgt->pgd, pgd_sz);
pgt->pgd = NULL;
}
-
-#define KVM_PTE_LEAF_S2_COMPAT_MASK (KVM_PTE_LEAF_ATTR_S2_PERMS | \
- KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR | \
- KVM_PTE_LEAF_ATTR_S2_IGNORED)
-
-static int stage2_check_permission_walker(u64 addr, u64 end, u32 level,
- kvm_pte_t *ptep,
- enum kvm_pgtable_walk_flags flag,
- void * const arg)
-{
- kvm_pte_t old_attr, pte = *ptep, *new_attr = arg;
-
- /*
- * Compatible mappings are either invalid and owned by the page-table
- * owner (whose id is 0), or valid with matching permission attributes.
- */
- if (kvm_pte_valid(pte)) {
- old_attr = pte & KVM_PTE_LEAF_S2_COMPAT_MASK;
- if (old_attr != *new_attr)
- return -EEXIST;
- } else if (pte) {
- return -EEXIST;
- }
-
- return 0;
-}
-
-int kvm_pgtable_stage2_find_range(struct kvm_pgtable *pgt, u64 addr,
- enum kvm_pgtable_prot prot,
- struct kvm_mem_range *range)
-{
- kvm_pte_t attr;
- struct kvm_pgtable_walker check_perm_walker = {
- .cb = stage2_check_permission_walker,
- .flags = KVM_PGTABLE_WALK_LEAF,
- .arg = &attr,
- };
- u64 granule, start, end;
- u32 level;
- int ret;
-
- ret = stage2_set_prot_attr(pgt, prot, &attr);
- if (ret)
- return ret;
- attr &= KVM_PTE_LEAF_S2_COMPAT_MASK;
-
- for (level = pgt->start_level; level < KVM_PGTABLE_MAX_LEVELS; level++) {
- granule = kvm_granule_size(level);
- start = ALIGN_DOWN(addr, granule);
- end = start + granule;
-
- if (!kvm_level_supports_block_mapping(level))
- continue;
-
- if (start < range->start || range->end < end)
- continue;
-
- /*
- * Check the presence of existing mappings with incompatible
- * permissions within the current block range, and try one level
- * deeper if one is found.
- */
- ret = kvm_pgtable_walk(pgt, start, granule, &check_perm_walker);
- if (ret != -EEXIST)
- break;
- }
-
- if (!ret) {
- range->start = start;
- range->end = end;
- }
-
- return ret;
-}
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
index f1e2e5a00933..289689b2682d 100644
--- a/arch/arm64/kvm/hyp/vhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -20,7 +20,7 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
__debug_switch_to_host_common(vcpu);
}
-u32 __kvm_get_mdcr_el2(void)
+u64 __kvm_get_mdcr_el2(void)
{
return read_sysreg(mdcr_el2);
}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index b3229924d243..ded2c66675f0 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -91,17 +91,9 @@ void activate_traps_vhe_load(struct kvm_vcpu *vcpu)
__activate_traps_common(vcpu);
}
-void deactivate_traps_vhe_put(void)
+void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
{
- u64 mdcr_el2 = read_sysreg(mdcr_el2);
-
- mdcr_el2 &= MDCR_EL2_HPMN_MASK |
- MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT |
- MDCR_EL2_TPMS;
-
- write_sysreg(mdcr_el2, mdcr_el2);
-
- __deactivate_traps_common();
+ __deactivate_traps_common(vcpu);
}
/* Switch to the guest for VHE systems running in EL2 */
@@ -124,11 +116,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
*
* We have already configured the guest's stage 1 translation in
* kvm_vcpu_load_sysregs_vhe above. We must now call
- * __load_guest_stage2 before __activate_traps, because
- * __load_guest_stage2 configures stage 2 translation, and
+ * __load_stage2 before __activate_traps, because
+ * __load_stage2 configures stage 2 translation, and
* __activate_traps clear HCR_EL2.TGE (among other things).
*/
- __load_guest_stage2(vcpu->arch.hw_mmu);
+ __load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
__activate_traps(vcpu);
__kvm_adjust_pc(vcpu);
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 2a0b8c88d74f..007a12dd4351 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -101,7 +101,7 @@ void kvm_vcpu_put_sysregs_vhe(struct kvm_vcpu *vcpu)
struct kvm_cpu_context *host_ctxt;
host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
- deactivate_traps_vhe_put();
+ deactivate_traps_vhe_put(vcpu);
__sysreg_save_el1_state(guest_ctxt);
__sysreg_save_user_state(guest_ctxt);
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 66f17349f0c3..24cef9b87f9e 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -50,10 +50,10 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
*
* ARM erratum 1165522 requires some special handling (again),
* as we need to make sure both stages of translation are in
- * place before clearing TGE. __load_guest_stage2() already
+ * place before clearing TGE. __load_stage2() already
* has an ISB in order to deal with this.
*/
- __load_guest_stage2(mmu);
+ __load_stage2(mmu, mmu->arch);
val = read_sysreg(hcr_el2);
val &= ~HCR_TGE;
write_sysreg(val, hcr_el2);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index f5bb235bbb59..1a94a7ca48f2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -260,10 +260,8 @@ static int __create_hyp_mappings(unsigned long start, unsigned long size,
{
int err;
- if (!kvm_host_owns_hyp_mappings()) {
- return kvm_call_hyp_nvhe(__pkvm_create_mappings,
- start, size, phys, prot);
- }
+ if (WARN_ON(!kvm_host_owns_hyp_mappings()))
+ return -EINVAL;
mutex_lock(&kvm_hyp_pgd_mutex);
err = kvm_pgtable_hyp_map(hyp_pgtable, start, size, phys, prot);
@@ -283,6 +281,21 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
}
}
+static int pkvm_share_hyp(phys_addr_t start, phys_addr_t end)
+{
+ phys_addr_t addr;
+ int ret;
+
+ for (addr = ALIGN_DOWN(start, PAGE_SIZE); addr < end; addr += PAGE_SIZE) {
+ ret = kvm_call_hyp_nvhe(__pkvm_host_share_hyp,
+ __phys_to_pfn(addr));
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
/**
* create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
* @from: The virtual kernel start address of the range
@@ -303,6 +316,13 @@ int create_hyp_mappings(void *from, void *to, enum kvm_pgtable_prot prot)
if (is_kernel_in_hyp_mode())
return 0;
+ if (!kvm_host_owns_hyp_mappings()) {
+ if (WARN_ON(prot != PAGE_HYP))
+ return -EPERM;
+ return pkvm_share_hyp(kvm_kaddr_to_phys(from),
+ kvm_kaddr_to_phys(to));
+ }
+
start = start & PAGE_MASK;
end = PAGE_ALIGN(end);
@@ -434,6 +454,32 @@ int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size,
return 0;
}
+static struct kvm_pgtable_mm_ops kvm_user_mm_ops = {
+ /* We shouldn't need any other callback to walk the PT */
+ .phys_to_virt = kvm_host_va,
+};
+
+static int get_user_mapping_size(struct kvm *kvm, u64 addr)
+{
+ struct kvm_pgtable pgt = {
+ .pgd = (kvm_pte_t *)kvm->mm->pgd,
+ .ia_bits = VA_BITS,
+ .start_level = (KVM_PGTABLE_MAX_LEVELS -
+ CONFIG_PGTABLE_LEVELS),
+ .mm_ops = &kvm_user_mm_ops,
+ };
+ kvm_pte_t pte = 0; /* Keep GCC quiet... */
+ u32 level = ~0;
+ int ret;
+
+ ret = kvm_pgtable_get_leaf(&pgt, addr, &pte, &level);
+ VM_BUG_ON(ret);
+ VM_BUG_ON(level >= KVM_PGTABLE_MAX_LEVELS);
+ VM_BUG_ON(!(pte & PTE_VALID));
+
+ return BIT(ARM64_HW_PGTABLE_LEVEL_SHIFT(level));
+}
+
static struct kvm_pgtable_mm_ops kvm_s2_mm_ops = {
.zalloc_page = stage2_memcache_zalloc_page,
.zalloc_pages_exact = kvm_host_zalloc_pages_exact,
@@ -486,7 +532,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
mmu->arch = &kvm->arch;
mmu->pgt = pgt;
mmu->pgd_phys = __pa(pgt->pgd);
- mmu->vmid.vmid_gen = 0;
+ WRITE_ONCE(mmu->vmid.vmid_gen, 0);
return 0;
out_destroy_pgtable:
@@ -781,7 +827,7 @@ static bool fault_supports_stage2_huge_mapping(struct kvm_memory_slot *memslot,
* Returns the size of the mapping.
*/
static unsigned long
-transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
+transparent_hugepage_adjust(struct kvm *kvm, struct kvm_memory_slot *memslot,
unsigned long hva, kvm_pfn_t *pfnp,
phys_addr_t *ipap)
{
@@ -792,8 +838,8 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
* sure that the HVA and IPA are sufficiently aligned and that the
* block map is contained within the memslot.
*/
- if (kvm_is_transparent_hugepage(pfn) &&
- fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE)) {
+ if (fault_supports_stage2_huge_mapping(memslot, hva, PMD_SIZE) &&
+ get_user_mapping_size(kvm, hva) >= PMD_SIZE) {
/*
* The address we faulted on is backed by a transparent huge
* page. However, because we map the compound huge page and
@@ -815,7 +861,7 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
*ipap &= PMD_MASK;
kvm_release_pfn_clean(pfn);
pfn &= ~(PTRS_PER_PMD - 1);
- kvm_get_pfn(pfn);
+ get_page(pfn_to_page(pfn));
*pfnp = pfn;
return PMD_SIZE;
@@ -1051,9 +1097,14 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
* If we are not forced to use page mapping, check if we are
* backed by a THP and thus use block mapping if possible.
*/
- if (vma_pagesize == PAGE_SIZE && !(force_pte || device))
- vma_pagesize = transparent_hugepage_adjust(memslot, hva,
- &pfn, &fault_ipa);
+ if (vma_pagesize == PAGE_SIZE && !(force_pte || device)) {
+ if (fault_status == FSC_PERM && fault_granule > PAGE_SIZE)
+ vma_pagesize = fault_granule;
+ else
+ vma_pagesize = transparent_hugepage_adjust(kvm, memslot,
+ hva, &pfn,
+ &fault_ipa);
+ }
if (fault_status != FSC_PERM && !device && kvm_has_mte(kvm)) {
/* Check the VMM hasn't introduced a new VM_SHARED VMA */
diff --git a/arch/arm64/kvm/perf.c b/arch/arm64/kvm/perf.c
index 151c31fb9860..f9bb3b14130e 100644
--- a/arch/arm64/kvm/perf.c
+++ b/arch/arm64/kvm/perf.c
@@ -50,7 +50,7 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = {
int kvm_perf_init(void)
{
- if (kvm_pmu_probe_pmuver() != 0xf && !is_protected_kvm_enabled())
+ if (kvm_pmu_probe_pmuver() != ID_AA64DFR0_PMUVER_IMP_DEF && !is_protected_kvm_enabled())
static_branch_enable(&kvm_arm_pmu_available);
return perf_register_guest_info_callbacks(&kvm_guest_cbs);
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index f33825c995cb..f5065f23b413 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -373,7 +373,6 @@ static u64 kvm_pmu_overflow_status(struct kvm_vcpu *vcpu)
reg = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
reg &= __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
reg &= __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
- reg &= kvm_pmu_valid_counter_mask(vcpu);
}
return reg;
@@ -564,20 +563,21 @@ void kvm_pmu_software_increment(struct kvm_vcpu *vcpu, u64 val)
*/
void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
{
- unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
int i;
if (val & ARMV8_PMU_PMCR_E) {
kvm_pmu_enable_counter_mask(vcpu,
- __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask);
+ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
} else {
- kvm_pmu_disable_counter_mask(vcpu, mask);
+ kvm_pmu_disable_counter_mask(vcpu,
+ __vcpu_sys_reg(vcpu, PMCNTENSET_EL0));
}
if (val & ARMV8_PMU_PMCR_C)
kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
if (val & ARMV8_PMU_PMCR_P) {
+ unsigned long mask = kvm_pmu_valid_counter_mask(vcpu);
mask &= ~BIT(ARMV8_PMU_CYCLE_IDX);
for_each_set_bit(i, &mask, 32)
kvm_pmu_set_counter_value(vcpu, i, 0);
@@ -745,7 +745,7 @@ int kvm_pmu_probe_pmuver(void)
struct perf_event_attr attr = { };
struct perf_event *event;
struct arm_pmu *pmu;
- int pmuver = 0xf;
+ int pmuver = ID_AA64DFR0_PMUVER_IMP_DEF;
/*
* Create a dummy event that only counts user cycles. As we'll never
@@ -770,7 +770,7 @@ int kvm_pmu_probe_pmuver(void)
if (IS_ERR(event)) {
pr_err_once("kvm: pmu event creation failed %ld\n",
PTR_ERR(event));
- return 0xf;
+ return ID_AA64DFR0_PMUVER_IMP_DEF;
}
if (event->pmu) {
@@ -923,7 +923,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
if (!vcpu->kvm->arch.pmuver)
vcpu->kvm->arch.pmuver = kvm_pmu_probe_pmuver();
- if (vcpu->kvm->arch.pmuver == 0xf)
+ if (vcpu->kvm->arch.pmuver == ID_AA64DFR0_PMUVER_IMP_DEF)
return -ENODEV;
switch (attr->attr) {
diff --git a/arch/arm64/kvm/psci.c b/arch/arm64/kvm/psci.c
index db4056ecccfd..74c47d420253 100644
--- a/arch/arm64/kvm/psci.c
+++ b/arch/arm64/kvm/psci.c
@@ -59,6 +59,12 @@ static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
kvm_vcpu_kick(vcpu);
}
+static inline bool kvm_psci_valid_affinity(struct kvm_vcpu *vcpu,
+ unsigned long affinity)
+{
+ return !(affinity & ~MPIDR_HWID_BITMASK);
+}
+
static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
{
struct vcpu_reset_state *reset_state;
@@ -66,9 +72,9 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
struct kvm_vcpu *vcpu = NULL;
unsigned long cpu_id;
- cpu_id = smccc_get_arg1(source_vcpu) & MPIDR_HWID_BITMASK;
- if (vcpu_mode_is_32bit(source_vcpu))
- cpu_id &= ~((u32) 0);
+ cpu_id = smccc_get_arg1(source_vcpu);
+ if (!kvm_psci_valid_affinity(source_vcpu, cpu_id))
+ return PSCI_RET_INVALID_PARAMS;
vcpu = kvm_mpidr_to_vcpu(kvm, cpu_id);
@@ -126,6 +132,9 @@ static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
target_affinity = smccc_get_arg1(vcpu);
lowest_affinity_level = smccc_get_arg2(vcpu);
+ if (!kvm_psci_valid_affinity(vcpu, target_affinity))
+ return PSCI_RET_INVALID_PARAMS;
+
/* Determine target affinity mask */
target_affinity_mask = psci_affinity_mask(lowest_affinity_level);
if (!target_affinity_mask)
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index cba7872d69a8..5ce36b0a3343 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -210,10 +210,16 @@ static bool vcpu_allowed_register_width(struct kvm_vcpu *vcpu)
*/
int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
{
+ struct vcpu_reset_state reset_state;
int ret;
bool loaded;
u32 pstate;
+ mutex_lock(&vcpu->kvm->lock);
+ reset_state = vcpu->arch.reset_state;
+ WRITE_ONCE(vcpu->arch.reset_state.reset, false);
+ mutex_unlock(&vcpu->kvm->lock);
+
/* Reset PMU outside of the non-preemptible section */
kvm_pmu_vcpu_reset(vcpu);
@@ -276,8 +282,8 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
* Additional reset state handling that PSCI may have imposed on us.
* Must be done after all the sys_reg reset.
*/
- if (vcpu->arch.reset_state.reset) {
- unsigned long target_pc = vcpu->arch.reset_state.pc;
+ if (reset_state.reset) {
+ unsigned long target_pc = reset_state.pc;
/* Gracefully handle Thumb2 entry point */
if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) {
@@ -286,13 +292,11 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
}
/* Propagate caller endianness */
- if (vcpu->arch.reset_state.be)
+ if (reset_state.be)
kvm_vcpu_set_be(vcpu);
*vcpu_pc(vcpu) = target_pc;
- vcpu_set_reg(vcpu, 0, vcpu->arch.reset_state.r0);
-
- vcpu->arch.reset_state.reset = false;
+ vcpu_set_reg(vcpu, 0, reset_state.r0);
}
/* Reset timer */
@@ -311,31 +315,26 @@ u32 get_kvm_ipa_limit(void)
int kvm_set_ipa_limit(void)
{
- unsigned int parange, tgran_2;
+ unsigned int parange;
u64 mmfr0;
mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
parange = cpuid_feature_extract_unsigned_field(mmfr0,
ID_AA64MMFR0_PARANGE_SHIFT);
+ /*
+ * IPA size beyond 48 bits could not be supported
+ * on either 4K or 16K page size. Hence let's cap
+ * it to 48 bits, in case it's reported as larger
+ * on the system.
+ */
+ if (PAGE_SIZE != SZ_64K)
+ parange = min(parange, (unsigned int)ID_AA64MMFR0_PARANGE_48);
/*
* Check with ARMv8.5-GTG that our PAGE_SIZE is supported at
* Stage-2. If not, things will stop very quickly.
*/
- switch (PAGE_SIZE) {
- default:
- case SZ_4K:
- tgran_2 = ID_AA64MMFR0_TGRAN4_2_SHIFT;
- break;
- case SZ_16K:
- tgran_2 = ID_AA64MMFR0_TGRAN16_2_SHIFT;
- break;
- case SZ_64K:
- tgran_2 = ID_AA64MMFR0_TGRAN64_2_SHIFT;
- break;
- }
-
- switch (cpuid_feature_extract_unsigned_field(mmfr0, tgran_2)) {
+ switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_TGRAN_2_SHIFT)) {
case ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE:
kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n");
return -EINVAL;
@@ -369,7 +368,7 @@ int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
if (phys_shift) {
if (phys_shift > kvm_ipa_limit ||
- phys_shift < 32)
+ phys_shift < ARM64_MIN_PARANGE_BITS)
return -EINVAL;
} else {
phys_shift = KVM_PHYS_SHIFT;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index f6f126eb6ac1..1d46e185f31e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -44,10 +44,6 @@
* 64bit interface.
*/
-#define reg_to_encoding(x) \
- sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \
- (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
-
static bool read_from_write_only(struct kvm_vcpu *vcpu,
struct sys_reg_params *params,
const struct sys_reg_desc *r)
@@ -318,14 +314,14 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
/*
* We want to avoid world-switching all the DBG registers all the
* time:
- *
+ *
* - If we've touched any debug register, it is likely that we're
* going to touch more of them. It then makes sense to disable the
* traps and start doing the save/restore dance
* - If debug is active (DBG_MDSCR_KDE or DBG_MDSCR_MDE set), it is
* then mandatory to save/restore the registers, as the guest
* depends on them.
- *
+ *
* For this, we use a DIRTY bit, indicating the guest has modified the
* debug registers, used as follow:
*
@@ -603,6 +599,41 @@ static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
return REG_HIDDEN;
}
+static void reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ u64 n, mask = BIT(ARMV8_PMU_CYCLE_IDX);
+
+ /* No PMU available, any PMU reg may UNDEF... */
+ if (!kvm_arm_support_pmu_v3())
+ return;
+
+ n = read_sysreg(pmcr_el0) >> ARMV8_PMU_PMCR_N_SHIFT;
+ n &= ARMV8_PMU_PMCR_N_MASK;
+ if (n)
+ mask |= GENMASK(n - 1, 0);
+
+ reset_unknown(vcpu, r);
+ __vcpu_sys_reg(vcpu, r->reg) &= mask;
+}
+
+static void reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ reset_unknown(vcpu, r);
+ __vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0);
+}
+
+static void reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ reset_unknown(vcpu, r);
+ __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_EVTYPE_MASK;
+}
+
+static void reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
+{
+ reset_unknown(vcpu, r);
+ __vcpu_sys_reg(vcpu, r->reg) &= ARMV8_PMU_COUNTER_MASK;
+}
+
static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
u64 pmcr, val;
@@ -845,7 +876,7 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
kvm_pmu_disable_counter_mask(vcpu, val);
}
} else {
- p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) & mask;
+ p->regval = __vcpu_sys_reg(vcpu, PMCNTENSET_EL0);
}
return true;
@@ -869,7 +900,7 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
/* accessing PMINTENCLR_EL1 */
__vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
} else {
- p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1) & mask;
+ p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
}
return true;
@@ -891,7 +922,7 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
/* accessing PMOVSCLR_EL0 */
__vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
} else {
- p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0) & mask;
+ p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
}
return true;
@@ -944,16 +975,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
trap_wcr, reset_wcr, 0, 0, get_wcr, set_wcr }
#define PMU_SYS_REG(r) \
- SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility
+ SYS_DESC(r), .reset = reset_pmu_reg, .visibility = pmu_visibility
/* Macro to expand the PMEVCNTRn_EL0 register */
#define PMU_PMEVCNTR_EL0(n) \
{ PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)), \
+ .reset = reset_pmevcntr, \
.access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
/* Macro to expand the PMEVTYPERn_EL0 register */
#define PMU_PMEVTYPER_EL0(n) \
{ PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)), \
+ .reset = reset_pmevtyper, \
.access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), }
static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
@@ -1026,8 +1059,6 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
return true;
}
-#define FEATURE(x) (GENMASK_ULL(x##_SHIFT + 3, x##_SHIFT))
-
/* Read a sanitised cpufeature ID register by sys_reg_desc */
static u64 read_id_reg(const struct kvm_vcpu *vcpu,
struct sys_reg_desc const *r, bool raz)
@@ -1038,40 +1069,40 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
switch (id) {
case SYS_ID_AA64PFR0_EL1:
if (!vcpu_has_sve(vcpu))
- val &= ~FEATURE(ID_AA64PFR0_SVE);
- val &= ~FEATURE(ID_AA64PFR0_AMU);
- val &= ~FEATURE(ID_AA64PFR0_CSV2);
- val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2);
- val &= ~FEATURE(ID_AA64PFR0_CSV3);
- val |= FIELD_PREP(FEATURE(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_AMU);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2);
+ val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3);
+ val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3);
break;
case SYS_ID_AA64PFR1_EL1:
- val &= ~FEATURE(ID_AA64PFR1_MTE);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
if (kvm_has_mte(vcpu->kvm)) {
u64 pfr, mte;
pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT);
- val |= FIELD_PREP(FEATURE(ID_AA64PFR1_MTE), mte);
+ val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), mte);
}
break;
case SYS_ID_AA64ISAR1_EL1:
if (!vcpu_has_ptrauth(vcpu))
- val &= ~(FEATURE(ID_AA64ISAR1_APA) |
- FEATURE(ID_AA64ISAR1_API) |
- FEATURE(ID_AA64ISAR1_GPA) |
- FEATURE(ID_AA64ISAR1_GPI));
+ val &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_API) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI));
break;
case SYS_ID_AA64DFR0_EL1:
/* Limit debug to ARMv8.0 */
- val &= ~FEATURE(ID_AA64DFR0_DEBUGVER);
- val |= FIELD_PREP(FEATURE(ID_AA64DFR0_DEBUGVER), 6);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER);
+ val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), 6);
/* Limit guests to PMUv3 for ARMv8.4 */
val = cpuid_feature_cap_perfmon_field(val,
ID_AA64DFR0_PMUVER_SHIFT,
kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_PMUVER_8_4 : 0);
/* Hide SPE from guests */
- val &= ~FEATURE(ID_AA64DFR0_PMSVER);
+ val &= ~ARM64_FEATURE_MASK(ID_AA64DFR0_PMSVER);
break;
case SYS_ID_DFR0_EL1:
/* Limit guests to PMUv3 for ARMv8.4 */
@@ -1249,6 +1280,20 @@ static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
return __set_id_reg(vcpu, rd, uaddr, true);
}
+static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+ const struct kvm_one_reg *reg, void __user *uaddr)
+{
+ int err;
+ u64 val;
+
+ /* Perform the access even if we are going to ignore the value */
+ err = reg_from_user(&val, uaddr, sys_reg_to_index(rd));
+ if (err)
+ return err;
+
+ return 0;
+}
+
static bool access_ctr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
const struct sys_reg_desc *r)
{
@@ -1592,16 +1637,21 @@ static const struct sys_reg_desc sys_reg_descs[] = {
.access = access_pmcnten, .reg = PMCNTENSET_EL0 },
{ PMU_SYS_REG(SYS_PMOVSCLR_EL0),
.access = access_pmovs, .reg = PMOVSSET_EL0 },
+ /*
+ * PM_SWINC_EL0 is exposed to userspace as RAZ/WI, as it was
+ * previously (and pointlessly) advertised in the past...
+ */
{ PMU_SYS_REG(SYS_PMSWINC_EL0),
- .access = access_pmswinc, .reg = PMSWINC_EL0 },
+ .get_user = get_raz_id_reg, .set_user = set_wi_reg,
+ .access = access_pmswinc, .reset = NULL },
{ PMU_SYS_REG(SYS_PMSELR_EL0),
- .access = access_pmselr, .reg = PMSELR_EL0 },
+ .access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 },
{ PMU_SYS_REG(SYS_PMCEID0_EL0),
.access = access_pmceid, .reset = NULL },
{ PMU_SYS_REG(SYS_PMCEID1_EL0),
.access = access_pmceid, .reset = NULL },
{ PMU_SYS_REG(SYS_PMCCNTR_EL0),
- .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 },
+ .access = access_pmu_evcntr, .reset = reset_unknown, .reg = PMCCNTR_EL0 },
{ PMU_SYS_REG(SYS_PMXEVTYPER_EL0),
.access = access_pmu_evtyper, .reset = NULL },
{ PMU_SYS_REG(SYS_PMXEVCNTR_EL0),
@@ -2106,23 +2156,6 @@ static int check_sysreg_table(const struct sys_reg_desc *table, unsigned int n,
return 0;
}
-static int match_sys_reg(const void *key, const void *elt)
-{
- const unsigned long pval = (unsigned long)key;
- const struct sys_reg_desc *r = elt;
-
- return pval - reg_to_encoding(r);
-}
-
-static const struct sys_reg_desc *find_reg(const struct sys_reg_params *params,
- const struct sys_reg_desc table[],
- unsigned int num)
-{
- unsigned long pval = reg_to_encoding(params);
-
- return bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
-}
-
int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu)
{
kvm_inject_undefined(vcpu);
@@ -2365,13 +2398,8 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu)
trace_kvm_handle_sys_reg(esr);
- params.Op0 = (esr >> 20) & 3;
- params.Op1 = (esr >> 14) & 0x7;
- params.CRn = (esr >> 10) & 0xf;
- params.CRm = (esr >> 1) & 0xf;
- params.Op2 = (esr >> 17) & 0x7;
+ params = esr_sys64_to_params(esr);
params.regval = vcpu_get_reg(vcpu, Rt);
- params.is_write = !(esr & 1);
ret = emulate_sys_reg(vcpu, &params);
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index 9d0621417c2a..cc0cc95a0280 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -11,6 +11,12 @@
#ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__
#define __ARM64_KVM_SYS_REGS_LOCAL_H__
+#include <linux/bsearch.h>
+
+#define reg_to_encoding(x) \
+ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \
+ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
+
struct sys_reg_params {
u8 Op0;
u8 Op1;
@@ -21,6 +27,14 @@ struct sys_reg_params {
bool is_write;
};
+#define esr_sys64_to_params(esr) \
+ ((struct sys_reg_params){ .Op0 = ((esr) >> 20) & 3, \
+ .Op1 = ((esr) >> 14) & 0x7, \
+ .CRn = ((esr) >> 10) & 0xf, \
+ .CRm = ((esr) >> 1) & 0xf, \
+ .Op2 = ((esr) >> 17) & 0x7, \
+ .is_write = !((esr) & 1) })
+
struct sys_reg_desc {
/* Sysreg string for debug */
const char *name;
@@ -152,6 +166,23 @@ static inline int cmp_sys_reg(const struct sys_reg_desc *i1,
return i1->Op2 - i2->Op2;
}
+static inline int match_sys_reg(const void *key, const void *elt)
+{
+ const unsigned long pval = (unsigned long)key;
+ const struct sys_reg_desc *r = elt;
+
+ return pval - reg_to_encoding(r);
+}
+
+static inline const struct sys_reg_desc *
+find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[],
+ unsigned int num)
+{
+ unsigned long pval = reg_to_encoding(params);
+
+ return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg);
+}
+
const struct sys_reg_desc *find_reg_by_id(u64 id,
struct sys_reg_params *params,
const struct sys_reg_desc table[],
diff --git a/arch/arm64/kvm/trace_handle_exit.h b/arch/arm64/kvm/trace_handle_exit.h
index 8d78acc4fba7..064a58c19f48 100644
--- a/arch/arm64/kvm/trace_handle_exit.h
+++ b/arch/arm64/kvm/trace_handle_exit.h
@@ -78,13 +78,17 @@ TRACE_EVENT(kvm_arm_clear_debug,
TP_printk("flags: 0x%08x", __entry->guest_debug)
);
+/*
+ * The dreg32 name is a leftover from a distant past. This will really
+ * output a 64bit value...
+ */
TRACE_EVENT(kvm_arm_set_dreg32,
- TP_PROTO(const char *name, __u32 value),
+ TP_PROTO(const char *name, __u64 value),
TP_ARGS(name, value),
TP_STRUCT__entry(
__field(const char *, name)
- __field(__u32, value)
+ __field(__u64, value)
),
TP_fast_assign(
@@ -92,7 +96,7 @@ TRACE_EVENT(kvm_arm_set_dreg32,
__entry->value = value;
),
- TP_printk("%s: 0x%08x", __entry->name, __entry->value)
+ TP_printk("%s: 0x%llx", __entry->name, __entry->value)
);
TRACE_DEFINE_SIZEOF(__u64);
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v2.c b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
index a016f07adc28..5f9014ae595b 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v2.c
@@ -282,7 +282,7 @@ static unsigned long vgic_mmio_read_vcpuif(struct kvm_vcpu *vcpu,
case GIC_CPU_PRIMASK:
/*
* Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
- * the PMR field as GICH_VMCR.VMPriMask rather than
+ * PMR field as GICH_VMCR.VMPriMask rather than
* GICC_PMR.Priority, so we expose the upper five bits of
* priority mask to userspace using the lower bits in the
* unsigned long.
@@ -329,7 +329,7 @@ static void vgic_mmio_write_vcpuif(struct kvm_vcpu *vcpu,
case GIC_CPU_PRIMASK:
/*
* Our KVM_DEV_TYPE_ARM_VGIC_V2 device ABI exports the
- * the PMR field as GICH_VMCR.VMPriMask rather than
+ * PMR field as GICH_VMCR.VMPriMask rather than
* GICC_PMR.Priority, so we expose the upper five bits of
* priority mask to userspace using the lower bits in the
* unsigned long.
diff --git a/arch/arm64/kvm/vgic/vgic-v2.c b/arch/arm64/kvm/vgic/vgic-v2.c
index 2c580204f1dc..95a18cec14a3 100644
--- a/arch/arm64/kvm/vgic/vgic-v2.c
+++ b/arch/arm64/kvm/vgic/vgic-v2.c
@@ -60,6 +60,7 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
u32 val = cpuif->vgic_lr[lr];
u32 cpuid, intid = val & GICH_LR_VIRTUALID;
struct vgic_irq *irq;
+ bool deactivated;
/* Extract the source vCPU id from the LR */
cpuid = val & GICH_LR_PHYSID_CPUID;
@@ -75,7 +76,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
raw_spin_lock(&irq->irq_lock);
- /* Always preserve the active bit */
+ /* Always preserve the active bit, note deactivation */
+ deactivated = irq->active && !(val & GICH_LR_ACTIVE_BIT);
irq->active = !!(val & GICH_LR_ACTIVE_BIT);
if (irq->active && vgic_irq_is_sgi(intid))
@@ -96,36 +98,8 @@ void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu)
if (irq->config == VGIC_CONFIG_LEVEL && !(val & GICH_LR_STATE))
irq->pending_latch = false;
- /*
- * Level-triggered mapped IRQs are special because we only
- * observe rising edges as input to the VGIC.
- *
- * If the guest never acked the interrupt we have to sample
- * the physical line and set the line level, because the
- * device state could have changed or we simply need to
- * process the still pending interrupt later.
- *
- * If this causes us to lower the level, we have to also clear
- * the physical active state, since we will otherwise never be
- * told when the interrupt becomes asserted again.
- *
- * Another case is when the interrupt requires a helping hand
- * on deactivation (no HW deactivation, for example).
- */
- if (vgic_irq_is_mapped_level(irq)) {
- bool resample = false;
-
- if (val & GICH_LR_PENDING_BIT) {
- irq->line_level = vgic_get_phys_line_level(irq);
- resample = !irq->line_level;
- } else if (vgic_irq_needs_resampling(irq) &&
- !(irq->active || irq->pending_latch)) {
- resample = true;
- }
-
- if (resample)
- vgic_irq_set_phys_active(irq, false);
- }
+ /* Handle resampling for mapped interrupts if required */
+ vgic_irq_handle_resampling(irq, deactivated, val & GICH_LR_PENDING_BIT);
raw_spin_unlock(&irq->irq_lock);
vgic_put_irq(vcpu->kvm, irq);
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 66004f61cd83..21a6207fb2ee 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -46,6 +46,7 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
u32 intid, cpuid;
struct vgic_irq *irq;
bool is_v2_sgi = false;
+ bool deactivated;
cpuid = val & GICH_LR_PHYSID_CPUID;
cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT;
@@ -68,7 +69,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
raw_spin_lock(&irq->irq_lock);
- /* Always preserve the active bit */
+ /* Always preserve the active bit, note deactivation */
+ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT);
irq->active = !!(val & ICH_LR_ACTIVE_BIT);
if (irq->active && is_v2_sgi)
@@ -89,36 +91,8 @@ void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu)
if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE))
irq->pending_latch = false;
- /*
- * Level-triggered mapped IRQs are special because we only
- * observe rising edges as input to the VGIC.
- *
- * If the guest never acked the interrupt we have to sample
- * the physical line and set the line level, because the
- * device state could have changed or we simply need to
- * process the still pending interrupt later.
- *
- * If this causes us to lower the level, we have to also clear
- * the physical active state, since we will otherwise never be
- * told when the interrupt becomes asserted again.
- *
- * Another case is when the interrupt requires a helping hand
- * on deactivation (no HW deactivation, for example).
- */
- if (vgic_irq_is_mapped_level(irq)) {
- bool resample = false;
-
- if (val & ICH_LR_PENDING_BIT) {
- irq->line_level = vgic_get_phys_line_level(irq);
- resample = !irq->line_level;
- } else if (vgic_irq_needs_resampling(irq) &&
- !(irq->active || irq->pending_latch)) {
- resample = true;
- }
-
- if (resample)
- vgic_irq_set_phys_active(irq, false);
- }
+ /* Handle resampling for mapped interrupts if required */
+ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT);
raw_spin_unlock(&irq->irq_lock);
vgic_put_irq(vcpu->kvm, irq);
diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c
index 111bff47e471..5dad4996cfb2 100644
--- a/arch/arm64/kvm/vgic/vgic.c
+++ b/arch/arm64/kvm/vgic/vgic.c
@@ -106,7 +106,6 @@ struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
if (intid >= VGIC_MIN_LPI)
return vgic_get_lpi(kvm, intid);
- WARN(1, "Looking up struct vgic_irq for reserved INTID");
return NULL;
}
@@ -1022,3 +1021,41 @@ bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid)
return map_is_active;
}
+
+/*
+ * Level-triggered mapped IRQs are special because we only observe rising
+ * edges as input to the VGIC.
+ *
+ * If the guest never acked the interrupt we have to sample the physical
+ * line and set the line level, because the device state could have changed
+ * or we simply need to process the still pending interrupt later.
+ *
+ * We could also have entered the guest with the interrupt active+pending.
+ * On the next exit, we need to re-evaluate the pending state, as it could
+ * otherwise result in a spurious interrupt by injecting a now potentially
+ * stale pending state.
+ *
+ * If this causes us to lower the level, we have to also clear the physical
+ * active state, since we will otherwise never be told when the interrupt
+ * becomes asserted again.
+ *
+ * Another case is when the interrupt requires a helping hand on
+ * deactivation (no HW deactivation, for example).
+ */
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+ bool lr_deactivated, bool lr_pending)
+{
+ if (vgic_irq_is_mapped_level(irq)) {
+ bool resample = false;
+
+ if (unlikely(vgic_irq_needs_resampling(irq))) {
+ resample = !(irq->active || irq->pending_latch);
+ } else if (lr_pending || (lr_deactivated && irq->line_level)) {
+ irq->line_level = vgic_get_phys_line_level(irq);
+ resample = !irq->line_level;
+ }
+
+ if (resample)
+ vgic_irq_set_phys_active(irq, false);
+ }
+}
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index dc1f3d1657ee..14a9218641f5 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -169,6 +169,8 @@ void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active);
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
unsigned long flags);
void vgic_kick_vcpus(struct kvm *kvm);
+void vgic_irq_handle_resampling(struct vgic_irq *irq,
+ bool lr_deactivated, bool lr_pending);
int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
phys_addr_t addr, phys_addr_t alignment);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index d74586508448..9ff0de1b2b93 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1339,7 +1339,6 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
return dt_virt;
}
-#if CONFIG_PGTABLE_LEVELS > 3
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
@@ -1354,16 +1353,6 @@ int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
return 1;
}
-int pud_clear_huge(pud_t *pudp)
-{
- if (!pud_sect(READ_ONCE(*pudp)))
- return 0;
- pud_clear(pudp);
- return 1;
-}
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 2
int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
{
pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), mk_pmd_sect_prot(prot));
@@ -1378,6 +1367,14 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot)
return 1;
}
+int pud_clear_huge(pud_t *pudp)
+{
+ if (!pud_sect(READ_ONCE(*pudp)))
+ return 0;
+ pud_clear(pudp);
+ return 1;
+}
+
int pmd_clear_huge(pmd_t *pmdp)
{
if (!pmd_sect(READ_ONCE(*pmdp)))
@@ -1385,7 +1382,6 @@ int pmd_clear_huge(pmd_t *pmdp)
pmd_clear(pmdp);
return 1;
}
-#endif
int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
{
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index dccf98a37283..41c23f474ea6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -823,6 +823,19 @@ emit_cond_jmp:
return ret;
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ /*
+ * Nothing required here.
+ *
+ * In case of arm64, we rely on the firmware mitigation of
+ * Speculative Store Bypass as controlled via the ssbd kernel
+ * parameter. Whenever the mitigation is enabled, it works
+ * for all of the kernel code with no need to provide any
+ * additional instructions.
+ */
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
diff --git a/arch/h8300/Kconfig.cpu b/arch/h8300/Kconfig.cpu
index b5e14d513e62..c30baa0499fc 100644
--- a/arch/h8300/Kconfig.cpu
+++ b/arch/h8300/Kconfig.cpu
@@ -44,7 +44,6 @@ config H8300_H8MAX
bool "H8MAX"
select H83069
select RAMKERNEL
- select HAVE_IDE
help
H8MAX Evaluation Board Support
More Information. (Japanese Only)
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index cf425c2c63af..4993c7ac7ff6 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -25,7 +25,6 @@ config IA64
select HAVE_ASM_MODVERSIONS
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_EXIT_THREAD
- select HAVE_IDE
select HAVE_KPROBES
select HAVE_KRETPROBES
select HAVE_FTRACE_MCOUNT_RECORD
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 96989ad46f66..d632a1d576f9 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -23,7 +23,6 @@ config M68K
select HAVE_DEBUG_BUGVERBOSE
select HAVE_EFFICIENT_UNALIGNED_ACCESS if !CPU_HAS_NO_UNALIGNED
select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
- select HAVE_IDE
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_UID16
select MMU_GATHER_NO_RANGE if MMU
diff --git a/arch/m68k/Kconfig.machine b/arch/m68k/Kconfig.machine
index d964c1f27399..6a07a6817885 100644
--- a/arch/m68k/Kconfig.machine
+++ b/arch/m68k/Kconfig.machine
@@ -33,6 +33,7 @@ config MAC
depends on MMU
select MMU_MOTOROLA if MMU
select HAVE_ARCH_NVRAM_OPS
+ select HAVE_PATA_PLATFORM
select LEGACY_TIMER_TICK
help
This option enables support for the Apple Macintosh series of
diff --git a/arch/m68k/coldfire/m525x.c b/arch/m68k/coldfire/m525x.c
index 2c4d2ca2f20d..485375112e28 100644
--- a/arch/m68k/coldfire/m525x.c
+++ b/arch/m68k/coldfire/m525x.c
@@ -26,7 +26,7 @@ DEFINE_CLK(pll, "pll.0", MCF_CLK);
DEFINE_CLK(sys, "sys.0", MCF_BUSCLK);
static struct clk_lookup m525x_clk_lookup[] = {
- CLKDEV_INIT(NULL, "pll.0", &pll),
+ CLKDEV_INIT(NULL, "pll.0", &clk_pll),
CLKDEV_INIT(NULL, "sys.0", &clk_sys),
CLKDEV_INIT("mcftmr.0", NULL, &clk_sys),
CLKDEV_INIT("mcftmr.1", NULL, &clk_sys),
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index cee6087cd686..6dfb27d531dd 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -71,7 +71,6 @@ config MIPS
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
select HAVE_GENERIC_VDSO
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c
index 939dd06764bc..3a73e9375712 100644
--- a/arch/mips/net/ebpf_jit.c
+++ b/arch/mips/net/ebpf_jit.c
@@ -1355,6 +1355,9 @@ jeq_common:
}
break;
+ case BPF_ST | BPF_NOSPEC: /* speculation barrier */
+ break;
+
case BPF_ST | BPF_B | BPF_MEM:
case BPF_ST | BPF_H | BPF_MEM:
case BPF_ST | BPF_W | BPF_MEM:
diff --git a/arch/nds32/mm/mmap.c b/arch/nds32/mm/mmap.c
index c206b31ce07a..1bdf5e7d1b43 100644
--- a/arch/nds32/mm/mmap.c
+++ b/arch/nds32/mm/mmap.c
@@ -59,7 +59,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
vma = find_vma(mm, addr);
if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start))
+ (!vma || addr + len <= vm_start_gap(vma)))
return addr;
}
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index bde9907bc5b2..4f8c1fbf8f2f 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -3,7 +3,6 @@ config PARISC
def_bool y
select ARCH_32BIT_OFF_T if !64BIT
select ARCH_MIGHT_HAVE_PC_PARPORT
- select HAVE_IDE
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index d01e3401581d..663766fbf505 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -220,7 +220,6 @@ config PPC
select HAVE_HARDLOCKUP_DETECTOR_ARCH if PPC_BOOK3S_64 && SMP
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 2813e3f98db6..3c5baaa6f1e7 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -27,6 +27,13 @@ KASAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin -nostdlib \
-Wl,-soname=linux-vdso64.so.1 -Wl,--hash-style=both
+
+# Go prior to 1.16.x assumes r30 is not clobbered by any VDSO code. That used to be true
+# by accident when the VDSO was hand-written asm code, but may not be now that the VDSO is
+# compiler generated. To avoid breaking Go tell GCC not to use r30. Impact on code
+# generation is minimal, it will just use r29 instead.
+ccflags-y += $(call cc-option, -ffixed-r30)
+
asflags-y := -D__VDSO64__ -s
targets += vdso64.lds
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6d63c8e6d4f0..829ff9bb5250 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2697,8 +2697,10 @@ static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
HFSCR_DSCR | HFSCR_VECVSX | HFSCR_FP | HFSCR_PREFIX;
if (cpu_has_feature(CPU_FTR_HVMODE)) {
vcpu->arch.hfscr &= mfspr(SPRN_HFSCR);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
vcpu->arch.hfscr |= HFSCR_TM;
+#endif
}
if (cpu_has_feature(CPU_FTR_TM_COMP))
vcpu->arch.hfscr |= HFSCR_TM;
diff --git a/arch/powerpc/kvm/book3s_hv_nested.c b/arch/powerpc/kvm/book3s_hv_nested.c
index 8543ad538b0c..898f942eb198 100644
--- a/arch/powerpc/kvm/book3s_hv_nested.c
+++ b/arch/powerpc/kvm/book3s_hv_nested.c
@@ -302,6 +302,9 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
if (vcpu->kvm->arch.l1_ptcr == 0)
return H_NOT_AVAILABLE;
+ if (MSR_TM_TRANSACTIONAL(vcpu->arch.shregs.msr))
+ return H_BAD_MODE;
+
/* copy parameters in */
hv_ptr = kvmppc_get_gpr(vcpu, 4);
regs_ptr = kvmppc_get_gpr(vcpu, 5);
@@ -322,6 +325,23 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
if (l2_hv.vcpu_token >= NR_CPUS)
return H_PARAMETER;
+ /*
+ * L1 must have set up a suspended state to enter the L2 in a
+ * transactional state, and only in that case. These have to be
+ * filtered out here to prevent causing a TM Bad Thing in the
+ * host HRFID. We could synthesize a TM Bad Thing back to the L1
+ * here but there doesn't seem like much point.
+ */
+ if (MSR_TM_SUSPENDED(vcpu->arch.shregs.msr)) {
+ if (!MSR_TM_ACTIVE(l2_regs.msr))
+ return H_BAD_MODE;
+ } else {
+ if (l2_regs.msr & MSR_TS_MASK)
+ return H_BAD_MODE;
+ if (WARN_ON_ONCE(vcpu->arch.shregs.msr & MSR_TS_MASK))
+ return H_BAD_MODE;
+ }
+
/* translate lpid */
l2 = kvmhv_get_nested(vcpu->kvm, l2_hv.lpid, true);
if (!l2)
diff --git a/arch/powerpc/kvm/book3s_hv_p9_entry.c b/arch/powerpc/kvm/book3s_hv_p9_entry.c
index 83f592eadcd2..961b3d70483c 100644
--- a/arch/powerpc/kvm/book3s_hv_p9_entry.c
+++ b/arch/powerpc/kvm/book3s_hv_p9_entry.c
@@ -317,6 +317,9 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
*/
mtspr(SPRN_HDEC, hdec);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+tm_return_to_guest:
+#endif
mtspr(SPRN_DAR, vcpu->arch.shregs.dar);
mtspr(SPRN_DSISR, vcpu->arch.shregs.dsisr);
mtspr(SPRN_SRR0, vcpu->arch.shregs.srr0);
@@ -415,11 +418,23 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
* is in real suspend mode and is trying to transition to
* transactional mode.
*/
- if (local_paca->kvm_hstate.fake_suspend &&
+ if (!local_paca->kvm_hstate.fake_suspend &&
(vcpu->arch.shregs.msr & MSR_TS_S)) {
if (kvmhv_p9_tm_emulation_early(vcpu)) {
- /* Prevent it being handled again. */
- trap = 0;
+ /*
+ * Go straight back into the guest with the
+ * new NIP/MSR as set by TM emulation.
+ */
+ mtspr(SPRN_HSRR0, vcpu->arch.regs.nip);
+ mtspr(SPRN_HSRR1, vcpu->arch.shregs.msr);
+
+ /*
+ * tm_return_to_guest re-loads SRR0/1, DAR,
+ * DSISR after RI is cleared, in case they had
+ * been clobbered by a MCE.
+ */
+ __mtmsrd(0, 1); /* clear RI */
+ goto tm_return_to_guest;
}
}
#endif
@@ -499,6 +514,10 @@ int kvmhv_vcpu_entry_p9(struct kvm_vcpu *vcpu, u64 time_limit, unsigned long lpc
* If we are in real mode, only switch MMU on after the MMU is
* switched to host, to avoid the P9_RADIX_PREFETCH_BUG.
*/
+ if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+ vcpu->arch.shregs.msr & MSR_TS_MASK)
+ msr |= MSR_TS_S;
+
__mtmsrd(msr, 0);
end_timing(vcpu);
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index c5e677508d3b..0f847f1e5ddd 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -242,6 +242,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
* value so we can restore it on the way out.
*/
orig_rets = args.rets;
+ if (be32_to_cpu(args.nargs) >= ARRAY_SIZE(args.args)) {
+ /*
+ * Don't overflow our args array: ensure there is room for
+ * at least rets[0] (even if the call specifies 0 nret).
+ *
+ * Each handler must then check for the correct nargs and nret
+ * values, but they may always return failure in rets[0].
+ */
+ rc = -EINVAL;
+ goto fail;
+ }
args.rets = &args.args[be32_to_cpu(args.nargs)];
mutex_lock(&vcpu->kvm->arch.rtas_token_lock);
@@ -269,9 +280,17 @@ int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu)
fail:
/*
* We only get here if the guest has called RTAS with a bogus
- * args pointer. That means we can't get to the args, and so we
- * can't fail the RTAS call. So fail right out to userspace,
- * which should kill the guest.
+ * args pointer or nargs/nret values that would overflow the
+ * array. That means we can't get to the args, and so we can't
+ * fail the RTAS call. So fail right out to userspace, which
+ * should kill the guest.
+ *
+ * SLOF should actually pass the hcall return value from the
+ * rtas handler call in r3, so enter_rtas could be modified to
+ * return a failure indication in r3 and we could return such
+ * errors to the guest rather than failing to host userspace.
+ * However old guests that don't test for failure could then
+ * continue silently after errors, so for now we won't do this.
*/
return rc;
}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index be33b5321a76..b4e6f70b97b9 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -2048,9 +2048,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
{
struct kvm_enable_cap cap;
r = -EFAULT;
- vcpu_load(vcpu);
if (copy_from_user(&cap, argp, sizeof(cap)))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
vcpu_put(vcpu);
break;
@@ -2074,9 +2074,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_DIRTY_TLB: {
struct kvm_dirty_tlb dirty;
r = -EFAULT;
- vcpu_load(vcpu);
if (copy_from_user(&dirty, argp, sizeof(dirty)))
goto out;
+ vcpu_load(vcpu);
r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
vcpu_put(vcpu);
break;
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 60780e089118..0df9fe29dd56 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -240,3 +240,13 @@ void __init setup_kuap(bool disabled)
mtspr(SPRN_MD_AP, MD_APG_KUAP);
}
#endif
+
+int pud_clear_huge(pud_t *pud)
+{
+ return 0;
+}
+
+int pmd_clear_huge(pmd_t *pmd)
+{
+ return 0;
+}
diff --git a/arch/powerpc/net/bpf_jit_comp32.c b/arch/powerpc/net/bpf_jit_comp32.c
index 34bb1583fc0c..beb12cbc8c29 100644
--- a/arch/powerpc/net/bpf_jit_comp32.c
+++ b/arch/powerpc/net/bpf_jit_comp32.c
@@ -738,6 +738,12 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, struct codegen_context *
break;
/*
+ * BPF_ST NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index de8595880fee..b87a63dba9c8 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -628,6 +628,12 @@ emit_clear:
break;
/*
+ * BPF_ST NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src */
diff --git a/arch/powerpc/platforms/pasemi/idle.c b/arch/powerpc/platforms/pasemi/idle.c
index 9b88e3cded7d..534b0317fc15 100644
--- a/arch/powerpc/platforms/pasemi/idle.c
+++ b/arch/powerpc/platforms/pasemi/idle.c
@@ -42,6 +42,7 @@ static int pasemi_system_reset_exception(struct pt_regs *regs)
switch (regs->msr & SRR1_WAKEMASK) {
case SRR1_WAKEDEC:
set_dec(1);
+ break;
case SRR1_WAKEEE:
/*
* Handle these when interrupts get re-enabled and we take
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 631a0d57b6cd..6b0886668465 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -77,7 +77,7 @@
#include "../../../../drivers/pci/pci.h"
DEFINE_STATIC_KEY_FALSE(shared_processor);
-EXPORT_SYMBOL_GPL(shared_processor);
+EXPORT_SYMBOL(shared_processor);
int CMO_PrPSP = -1;
int CMO_SecPSP = -1;
diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h
index 6d98cd999680..7b3483ba2e84 100644
--- a/arch/riscv/include/asm/efi.h
+++ b/arch/riscv/include/asm/efi.h
@@ -27,10 +27,10 @@ int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md);
#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE)
-/* Load initrd at enough distance from DRAM start */
+/* Load initrd anywhere in system RAM */
static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr)
{
- return image_addr + SZ_256M;
+ return ULONG_MAX;
}
#define alloc_screen_info(x...) (&screen_info)
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index ff467b98c3e3..ac7593607fa6 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -132,8 +132,12 @@ unsigned long get_wchan(struct task_struct *task)
{
unsigned long pc = 0;
- if (likely(task && task != current && !task_is_running(task)))
+ if (likely(task && task != current && !task_is_running(task))) {
+ if (!try_get_task_stack(task))
+ return 0;
walk_stackframe(task, NULL, save_wchan, &pc);
+ put_task_stack(task);
+ }
return pc;
}
diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index bceb0629e440..63bc691cff91 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -30,23 +30,23 @@ ENTRY(__asm_copy_from_user)
* t0 - end of uncopied dst
*/
add t0, a0, a2
- bgtu a0, t0, 5f
/*
* Use byte copy only if too small.
+ * SZREG holds 4 for RV32 and 8 for RV64
*/
- li a3, 8*SZREG /* size must be larger than size in word_copy */
+ li a3, 9*SZREG /* size must be larger than size in word_copy */
bltu a2, a3, .Lbyte_copy_tail
/*
- * Copy first bytes until dst is align to word boundary.
+ * Copy first bytes until dst is aligned to word boundary.
* a0 - start of dst
* t1 - start of aligned dst
*/
addi t1, a0, SZREG-1
andi t1, t1, ~(SZREG-1)
/* dst is already aligned, skip */
- beq a0, t1, .Lskip_first_bytes
+ beq a0, t1, .Lskip_align_dst
1:
/* a5 - one byte for copying data */
fixup lb a5, 0(a1), 10f
@@ -55,7 +55,7 @@ ENTRY(__asm_copy_from_user)
addi a0, a0, 1 /* dst */
bltu a0, t1, 1b /* t1 - start of aligned dst */
-.Lskip_first_bytes:
+.Lskip_align_dst:
/*
* Now dst is aligned.
* Use shift-copy if src is misaligned.
@@ -72,10 +72,9 @@ ENTRY(__asm_copy_from_user)
*
* a0 - start of aligned dst
* a1 - start of aligned src
- * a3 - a1 & mask:(SZREG-1)
* t0 - end of aligned dst
*/
- addi t0, t0, -(8*SZREG-1) /* not to over run */
+ addi t0, t0, -(8*SZREG) /* not to over run */
2:
fixup REG_L a4, 0(a1), 10f
fixup REG_L a5, SZREG(a1), 10f
@@ -97,7 +96,7 @@ ENTRY(__asm_copy_from_user)
addi a1, a1, 8*SZREG
bltu a0, t0, 2b
- addi t0, t0, 8*SZREG-1 /* revert to original value */
+ addi t0, t0, 8*SZREG /* revert to original value */
j .Lbyte_copy_tail
.Lshift_copy:
@@ -107,7 +106,7 @@ ENTRY(__asm_copy_from_user)
* For misaligned copy we still perform aligned word copy, but
* we need to use the value fetched from the previous iteration and
* do some shifts.
- * This is safe because reading less than a word size.
+ * This is safe because reading is less than a word size.
*
* a0 - start of aligned dst
* a1 - start of src
@@ -117,7 +116,7 @@ ENTRY(__asm_copy_from_user)
*/
/* calculating aligned word boundary for dst */
andi t1, t0, ~(SZREG-1)
- /* Converting unaligned src to aligned arc */
+ /* Converting unaligned src to aligned src */
andi a1, a1, ~(SZREG-1)
/*
@@ -125,11 +124,11 @@ ENTRY(__asm_copy_from_user)
* t3 - prev shift
* t4 - current shift
*/
- slli t3, a3, LGREG
+ slli t3, a3, 3 /* converting bytes in a3 to bits */
li a5, SZREG*8
sub t4, a5, t3
- /* Load the first word to combine with seceond word */
+ /* Load the first word to combine with second word */
fixup REG_L a5, 0(a1), 10f
3:
@@ -161,7 +160,7 @@ ENTRY(__asm_copy_from_user)
* a1 - start of remaining src
* t0 - end of remaining dst
*/
- bgeu a0, t0, 5f
+ bgeu a0, t0, .Lout_copy_user /* check if end of copy */
4:
fixup lb a5, 0(a1), 10f
addi a1, a1, 1 /* src */
@@ -169,7 +168,7 @@ ENTRY(__asm_copy_from_user)
addi a0, a0, 1 /* dst */
bltu a0, t0, 4b /* t0 - end of dst */
-5:
+.Lout_copy_user:
/* Disable access to user memory */
csrc CSR_STATUS, t6
li a0, 0
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 269fc648ef3d..a14bf3910eec 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -127,10 +127,17 @@ void __init mem_init(void)
}
/*
- * The default maximal physical memory size is -PAGE_OFFSET,
- * limit the memory size via mem.
+ * The default maximal physical memory size is -PAGE_OFFSET for 32-bit kernel,
+ * whereas for 64-bit kernel, the end of the virtual address space is occupied
+ * by the modules/BPF/kernel mappings which reduces the available size of the
+ * linear mapping.
+ * Limit the memory size via mem.
*/
+#ifdef CONFIG_64BIT
+static phys_addr_t memory_limit = -PAGE_OFFSET - SZ_4G;
+#else
static phys_addr_t memory_limit = -PAGE_OFFSET;
+#endif
static int __init early_mem(char *p)
{
@@ -152,7 +159,7 @@ static void __init setup_bootmem(void)
{
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
- phys_addr_t max_mapped_addr = __pa(~(ulong)0);
+ phys_addr_t __maybe_unused max_mapped_addr;
phys_addr_t dram_end;
#ifdef CONFIG_XIP_KERNEL
@@ -175,14 +182,21 @@ static void __init setup_bootmem(void)
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
dram_end = memblock_end_of_DRAM();
+
+#ifndef CONFIG_64BIT
/*
* memblock allocator is not aware of the fact that last 4K bytes of
* the addressable memory can not be mapped because of IS_ERR_VALUE
* macro. Make sure that last 4k bytes are not usable by memblock
- * if end of dram is equal to maximum addressable memory.
+ * if end of dram is equal to maximum addressable memory. For 64-bit
+ * kernel, this problem can't happen here as the end of the virtual
+ * address space is occupied by the kernel mapping then this check must
+ * be done in create_kernel_page_table.
*/
+ max_mapped_addr = __pa(~(ulong)0);
if (max_mapped_addr == (dram_end - 1))
memblock_set_current_limit(max_mapped_addr - 4096);
+#endif
min_low_pfn = PFN_UP(memblock_start_of_DRAM());
max_low_pfn = max_pfn = PFN_DOWN(dram_end);
@@ -570,6 +584,14 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
BUG_ON((kernel_map.phys_addr % map_size) != 0);
+#ifdef CONFIG_64BIT
+ /*
+ * The last 4K bytes of the addressable memory can not be mapped because
+ * of IS_ERR_VALUE macro.
+ */
+ BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
+#endif
+
pt_ops.alloc_pte = alloc_pte_early;
pt_ops.get_pte_virt = get_pte_virt_early;
#ifndef __PAGETABLE_PMD_FOLDED
@@ -709,6 +731,8 @@ static void __init setup_vm_final(void)
if (start <= __pa(PAGE_OFFSET) &&
__pa(PAGE_OFFSET) < end)
start = __pa(PAGE_OFFSET);
+ if (end >= __pa(PAGE_OFFSET) + memory_limit)
+ end = __pa(PAGE_OFFSET) + memory_limit;
map_size = best_map_size(start, end - start);
for (pa = start; pa < end; pa += map_size) {
diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c
index 81de865f4c7c..e6497424cbf6 100644
--- a/arch/riscv/net/bpf_jit_comp32.c
+++ b/arch/riscv/net/bpf_jit_comp32.c
@@ -1251,6 +1251,10 @@ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
return -1;
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
case BPF_ST | BPF_MEM | BPF_B:
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_W:
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 87e3bf5b9086..3af4131c22c7 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -939,6 +939,10 @@ out_be:
emit_ld(rd, 0, RV_REG_T1, ctx);
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
emit_imm(RV_REG_T1, imm, ctx);
diff --git a/arch/s390/boot/text_dma.S b/arch/s390/boot/text_dma.S
index f7c77cd518f2..5ff5fee02801 100644
--- a/arch/s390/boot/text_dma.S
+++ b/arch/s390/boot/text_dma.S
@@ -9,16 +9,6 @@
#include <asm/errno.h>
#include <asm/sigp.h>
-#ifdef CC_USING_EXPOLINE
- .pushsection .dma.text.__s390_indirect_jump_r14,"axG"
-__dma__s390_indirect_jump_r14:
- larl %r1,0f
- ex 0,0(%r1)
- j .
-0: br %r14
- .popsection
-#endif
-
.section .dma.text,"ax"
/*
* Simplified version of expoline thunk. The normal thunks can not be used here,
@@ -27,11 +17,10 @@ __dma__s390_indirect_jump_r14:
* affects a few functions that are not performance-relevant.
*/
.macro BR_EX_DMA_r14
-#ifdef CC_USING_EXPOLINE
- jg __dma__s390_indirect_jump_r14
-#else
- br %r14
-#endif
+ larl %r1,0f
+ ex 0,0(%r1)
+ j .
+0: br %r14
.endm
/*
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 86afcc6b56bf..7de253f766e8 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -5,7 +5,12 @@ CONFIG_WATCH_QUEUE=y
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_LSM=y
CONFIG_PREEMPT=y
+CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
@@ -28,14 +33,13 @@ CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_LSM=y
-CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
@@ -76,6 +80,7 @@ CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
CONFIG_BLK_INLINE_ENCRYPTION=y
CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
CONFIG_PARTITION_ADVANCED=y
@@ -95,6 +100,7 @@ CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
CONFIG_CMA_DEBUG=y
CONFIG_CMA_DEBUGFS=y
+CONFIG_CMA_SYSFS=y
CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
@@ -158,6 +164,7 @@ CONFIG_IPV6_RPL_LWTUNNEL=y
CONFIG_MPTCP=y
CONFIG_NETFILTER=y
CONFIG_BRIDGE_NETFILTER=m
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_EVENTS=y
@@ -280,6 +287,7 @@ CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
+CONFIG_NF_LOG_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
@@ -384,12 +392,11 @@ CONFIG_VSOCKETS=m
CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
CONFIG_PCI=y
-CONFIG_PCI_IOV=y
# CONFIG_PCIEASPM is not set
CONFIG_PCI_DEBUG=y
+CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_DEVTMPFS=y
@@ -436,7 +443,7 @@ CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
-CONFIG_BLK_DEV_DM=m
+CONFIG_BLK_DEV_DM=y
CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
@@ -453,6 +460,7 @@ CONFIG_DM_MULTIPATH_ST=m
CONFIG_DM_MULTIPATH_HST=m
CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
+CONFIG_DM_INIT=y
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
@@ -495,6 +503,7 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
@@ -551,7 +560,6 @@ CONFIG_INPUT_EVDEV=y
CONFIG_LEGACY_PTY_COUNT=0
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
CONFIG_PPS=m
@@ -574,7 +582,6 @@ CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_VFIO_MDEV=m
-CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
@@ -619,6 +626,7 @@ CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_STATS=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
@@ -654,7 +662,6 @@ CONFIG_NFSD_V3_ACL=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_CIFS_XATTR=y
@@ -682,6 +689,7 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
@@ -696,6 +704,7 @@ CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECDSA=m
CONFIG_CRYPTO_ECRDSA=m
CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
@@ -843,7 +852,6 @@ CONFIG_FAULT_INJECTION_DEBUG_FS=y
CONFIG_FAIL_FUNCTION=y
CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y
CONFIG_LKDTM=m
-CONFIG_TEST_LIST_SORT=y
CONFIG_TEST_MIN_HEAP=y
CONFIG_TEST_SORT=y
CONFIG_KPROBES_SANITY_TEST=y
@@ -853,3 +861,4 @@ CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BITOPS=m
CONFIG_TEST_BPF=m
+CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 71b49ea5b058..b671642967ba 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -4,6 +4,11 @@ CONFIG_WATCH_QUEUE=y
CONFIG_AUDIT=y
CONFIG_NO_HZ_IDLE=y
CONFIG_HIGH_RES_TIMERS=y
+CONFIG_BPF_SYSCALL=y
+CONFIG_BPF_JIT=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_LSM=y
+CONFIG_SCHED_CORE=y
CONFIG_BSD_PROCESS_ACCT=y
CONFIG_BSD_PROCESS_ACCT_V3=y
CONFIG_TASKSTATS=y
@@ -26,14 +31,13 @@ CONFIG_CGROUP_DEVICE=y
CONFIG_CGROUP_CPUACCT=y
CONFIG_CGROUP_PERF=y
CONFIG_CGROUP_BPF=y
+CONFIG_CGROUP_MISC=y
CONFIG_NAMESPACES=y
CONFIG_USER_NS=y
CONFIG_CHECKPOINT_RESTORE=y
CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
-CONFIG_BPF_LSM=y
-CONFIG_BPF_SYSCALL=y
CONFIG_USERFAULTFD=y
# CONFIG_COMPAT_BRK is not set
CONFIG_PROFILING=y
@@ -70,6 +74,7 @@ CONFIG_BLK_DEV_THROTTLING=y
CONFIG_BLK_WBT=y
CONFIG_BLK_CGROUP_IOLATENCY=y
CONFIG_BLK_CGROUP_IOCOST=y
+CONFIG_BLK_CGROUP_IOPRIO=y
CONFIG_BLK_INLINE_ENCRYPTION=y
CONFIG_BLK_INLINE_ENCRYPTION_FALLBACK=y
CONFIG_PARTITION_ADVANCED=y
@@ -87,6 +92,7 @@ CONFIG_KSM=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_CLEANCACHE=y
CONFIG_FRONTSWAP=y
+CONFIG_CMA_SYSFS=y
CONFIG_CMA_AREAS=7
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ZSWAP=y
@@ -149,6 +155,7 @@ CONFIG_IPV6_RPL_LWTUNNEL=y
CONFIG_MPTCP=y
CONFIG_NETFILTER=y
CONFIG_BRIDGE_NETFILTER=m
+CONFIG_NETFILTER_NETLINK_HOOK=m
CONFIG_NF_CONNTRACK=m
CONFIG_NF_CONNTRACK_SECMARK=y
CONFIG_NF_CONNTRACK_EVENTS=y
@@ -271,6 +278,7 @@ CONFIG_IP_VS_FTP=m
CONFIG_IP_VS_PE_SIP=m
CONFIG_NFT_FIB_IPV4=m
CONFIG_NF_TABLES_ARP=y
+CONFIG_NF_LOG_IPV4=m
CONFIG_IP_NF_IPTABLES=m
CONFIG_IP_NF_MATCH_AH=m
CONFIG_IP_NF_MATCH_ECN=m
@@ -374,11 +382,10 @@ CONFIG_VSOCKETS=m
CONFIG_VIRTIO_VSOCKETS=m
CONFIG_NETLINK_DIAG=m
CONFIG_CGROUP_NET_PRIO=y
-CONFIG_BPF_JIT=y
CONFIG_NET_PKTGEN=m
CONFIG_PCI=y
-CONFIG_PCI_IOV=y
# CONFIG_PCIEASPM is not set
+CONFIG_PCI_IOV=y
CONFIG_HOTPLUG_PCI=y
CONFIG_HOTPLUG_PCI_S390=y
CONFIG_UEVENT_HELPER=y
@@ -427,7 +434,7 @@ CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
CONFIG_MD_CLUSTER=m
CONFIG_BCACHE=m
-CONFIG_BLK_DEV_DM=m
+CONFIG_BLK_DEV_DM=y
CONFIG_DM_UNSTRIPED=m
CONFIG_DM_CRYPT=m
CONFIG_DM_SNAPSHOT=m
@@ -444,6 +451,7 @@ CONFIG_DM_MULTIPATH_ST=m
CONFIG_DM_MULTIPATH_HST=m
CONFIG_DM_MULTIPATH_IOA=m
CONFIG_DM_DELAY=m
+CONFIG_DM_INIT=y
CONFIG_DM_UEVENT=y
CONFIG_DM_FLAKEY=m
CONFIG_DM_VERITY=m
@@ -487,6 +495,7 @@ CONFIG_NLMON=m
# CONFIG_NET_VENDOR_GOOGLE is not set
# CONFIG_NET_VENDOR_HUAWEI is not set
# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MICROSOFT is not set
# CONFIG_NET_VENDOR_MARVELL is not set
CONFIG_MLX4_EN=m
CONFIG_MLX5_CORE=m
@@ -543,7 +552,6 @@ CONFIG_INPUT_EVDEV=y
CONFIG_LEGACY_PTY_COUNT=0
CONFIG_VIRTIO_CONSOLE=m
CONFIG_HW_RANDOM_VIRTIO=m
-CONFIG_RAW_DRIVER=m
CONFIG_HANGCHECK_TIMER=m
CONFIG_TN3270_FS=y
# CONFIG_PTP_1588_CLOCK is not set
@@ -566,7 +574,6 @@ CONFIG_SYNC_FILE=y
CONFIG_VFIO=m
CONFIG_VFIO_PCI=m
CONFIG_VFIO_MDEV=m
-CONFIG_VFIO_MDEV_DEVICE=m
CONFIG_VIRTIO_PCI=m
CONFIG_VIRTIO_BALLOON=m
CONFIG_VIRTIO_INPUT=y
@@ -607,6 +614,7 @@ CONFIG_FUSE_FS=y
CONFIG_CUSE=m
CONFIG_VIRTIO_FS=m
CONFIG_OVERLAY_FS=m
+CONFIG_NETFS_STATS=y
CONFIG_FSCACHE=m
CONFIG_CACHEFILES=m
CONFIG_ISO9660_FS=y
@@ -642,7 +650,6 @@ CONFIG_NFSD_V3_ACL=y
CONFIG_NFSD_V4=y
CONFIG_NFSD_V4_SECURITY_LABEL=y
CONFIG_CIFS=m
-CONFIG_CIFS_STATS2=y
CONFIG_CIFS_WEAK_PW_HASH=y
CONFIG_CIFS_UPCALL=y
CONFIG_CIFS_XATTR=y
@@ -669,6 +676,7 @@ CONFIG_SECURITY_SELINUX_BOOTPARAM=y
CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_SECURITY_LOCKDOWN_LSM=y
CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
+CONFIG_SECURITY_LANDLOCK=y
CONFIG_INTEGRITY_SIGNATURE=y
CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
CONFIG_IMA=y
@@ -684,6 +692,7 @@ CONFIG_CRYPTO_CRYPTD=m
CONFIG_CRYPTO_TEST=m
CONFIG_CRYPTO_DH=m
CONFIG_CRYPTO_ECDH=m
+CONFIG_CRYPTO_ECDSA=m
CONFIG_CRYPTO_ECRDSA=m
CONFIG_CRYPTO_SM2=m
CONFIG_CRYPTO_CURVE25519=m
@@ -754,6 +763,7 @@ CONFIG_CRC8=m
CONFIG_DMA_CMA=y
CONFIG_CMA_SIZE_MBYTES=0
CONFIG_PRINTK_TIME=y
+CONFIG_DYNAMIC_DEBUG=y
CONFIG_DEBUG_INFO=y
CONFIG_DEBUG_INFO_DWARF4=y
CONFIG_GDB_SCRIPTS=y
@@ -781,3 +791,4 @@ CONFIG_LKDTM=m
CONFIG_PERCPU_TEST=m
CONFIG_ATOMIC64_SELFTEST=y
CONFIG_TEST_BPF=m
+CONFIG_TEST_LIVEPATCH=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 76123a4b26ab..d576aaab27c9 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -29,9 +29,9 @@ CONFIG_PARTITION_ADVANCED=y
# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
# CONFIG_COMPACTION is not set
# CONFIG_MIGRATION is not set
-# CONFIG_BOUNCE is not set
CONFIG_NET=y
# CONFIG_IUCV is not set
+# CONFIG_PCPU_DEV_REFCNT is not set
# CONFIG_ETHTOOL_NETLINK is not set
CONFIG_DEVTMPFS=y
CONFIG_BLK_DEV_RAM=y
@@ -51,7 +51,6 @@ CONFIG_ZFCP=y
# CONFIG_SERIO is not set
# CONFIG_HVC_IUCV is not set
# CONFIG_HW_RANDOM_S390 is not set
-CONFIG_RAW_DRIVER=y
# CONFIG_HMC_DRV is not set
# CONFIG_S390_TAPE is not set
# CONFIG_VMCP is not set
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index 695c61989f97..345cbe982a8b 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -19,6 +19,7 @@ void ftrace_caller(void);
extern char ftrace_graph_caller_end;
extern unsigned long ftrace_plt;
+extern void *ftrace_func;
struct dyn_arch_ftrace { };
diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index c6ddeb5029b4..2d8f595d9196 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -40,6 +40,7 @@
* trampoline (ftrace_plt), which clobbers also r1.
*/
+void *ftrace_func __read_mostly = ftrace_stub;
unsigned long ftrace_plt;
int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr,
@@ -85,6 +86,7 @@ int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr)
int ftrace_update_ftrace_func(ftrace_func_t func)
{
+ ftrace_func = func;
return 0;
}
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index faf64c2f90f5..6b13797143a7 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -59,13 +59,13 @@ ENTRY(ftrace_caller)
#ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
aghik %r2,%r0,-MCOUNT_INSN_SIZE
lgrl %r4,function_trace_op
- lgrl %r1,ftrace_trace_function
+ lgrl %r1,ftrace_func
#else
lgr %r2,%r0
aghi %r2,-MCOUNT_INSN_SIZE
larl %r4,function_trace_op
lg %r4,0(%r4)
- larl %r1,ftrace_trace_function
+ larl %r1,ftrace_func
lg %r1,0(%r1)
#endif
lgr %r3,%r14
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index 975a00c8c564..d7dc36ec0a60 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -745,7 +745,7 @@ static int __init cpumf_pmu_init(void)
if (!cf_dbg) {
pr_err("Registration of s390dbf(cpum_cf) failed\n");
return -ENOMEM;
- };
+ }
debug_register_view(cf_dbg, &debug_sprintf_view);
cpumf_pmu.attr_groups = cpumf_cf_event_group();
diff --git a/arch/s390/kernel/vdso32/Makefile b/arch/s390/kernel/vdso32/Makefile
index b2349a3f4fa3..3457dcf10396 100644
--- a/arch/s390/kernel/vdso32/Makefile
+++ b/arch/s390/kernel/vdso32/Makefile
@@ -29,6 +29,7 @@ $(targets:%=$(obj)/%.dbg): KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
$(targets:%=$(obj)/%.dbg): KBUILD_AFLAGS = $(KBUILD_AFLAGS_32)
obj-y += vdso32_wrapper.o
+targets += vdso32.lds
CPPFLAGS_vdso32.lds += -P -C -U$(ARCH)
# Disable gcov profiling, ubsan and kasan for VDSO code
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 63cae0476bb4..88419263a89a 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -112,7 +112,7 @@ static inline void reg_set_seen(struct bpf_jit *jit, u32 b1)
{
u32 r1 = reg2hex[b1];
- if (!jit->seen_reg[r1] && r1 >= 6 && r1 <= 15)
+ if (r1 >= 6 && r1 <= 15 && !jit->seen_reg[r1])
jit->seen_reg[r1] = 1;
}
@@ -1154,6 +1154,11 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
}
break;
/*
+ * BPF_NOSPEC (speculation barrier)
+ */
+ case BPF_ST | BPF_NOSPEC:
+ break;
+ /*
* BPF_ST(X)
*/
case BPF_STX | BPF_MEM | BPF_B: /* *(u8 *)(dst + off) = src_reg */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 45a0549421cd..b683b69a4556 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -39,7 +39,6 @@ config SUPERH
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_HW_BREAKPOINT
- select HAVE_IDE if HAS_IOPORT_MAP
select HAVE_IOREMAP_PROT if MMU && !X2TLB
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index c5fa7932b550..f0c0f955e169 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -19,7 +19,6 @@ config SPARC
select OF
select OF_PROMTREE
select HAVE_ASM_MODVERSIONS
- select HAVE_IDE
select HAVE_ARCH_KGDB if !SMP || SPARC64
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_SECCOMP if SPARC64
diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c
index 4b8d3c65d266..9a2f20cbd48b 100644
--- a/arch/sparc/net/bpf_jit_comp_64.c
+++ b/arch/sparc/net/bpf_jit_comp_64.c
@@ -1287,6 +1287,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
return 1;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ break;
/* ST: *(size *)(dst + off) = imm */
case BPF_ST | BPF_MEM | BPF_W:
case BPF_ST | BPF_MEM | BPF_H:
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 49270655e827..88fb922c23a0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -202,7 +202,6 @@ config X86
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT
- select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK if X86_64
select HAVE_IRQ_TIME_ACCOUNTING
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index cc8f1773deca..c890d67a64ad 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -237,7 +237,7 @@ static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
for_each_present_cpu(i) {
if (i == 0)
continue;
- ret = hv_call_add_logical_proc(numa_cpu_node(i), i, i);
+ ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
BUG_ON(ret);
}
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 674906fad43b..68f091ba8443 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -79,9 +79,10 @@ __jump_label_patch(struct jump_entry *entry, enum jump_label_type type)
return (struct jump_label_patch){.code = code, .size = size};
}
-static inline void __jump_label_transform(struct jump_entry *entry,
- enum jump_label_type type,
- int init)
+static __always_inline void
+__jump_label_transform(struct jump_entry *entry,
+ enum jump_label_type type,
+ int init)
{
const struct jump_label_patch jlp = __jump_label_patch(entry, type);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3364fe62b903..3481b35cb4ec 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -682,7 +682,6 @@ int p4d_clear_huge(p4d_t *p4d)
}
#endif
-#if CONFIG_PGTABLE_LEVELS > 3
/**
* pud_set_huge - setup kernel PUD mapping
*
@@ -722,23 +721,6 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
}
/**
- * pud_clear_huge - clear kernel PUD mapping when it is set
- *
- * Returns 1 on success and 0 on failure (no PUD map is found).
- */
-int pud_clear_huge(pud_t *pud)
-{
- if (pud_large(*pud)) {
- pud_clear(pud);
- return 1;
- }
-
- return 0;
-}
-#endif
-
-#if CONFIG_PGTABLE_LEVELS > 2
-/**
* pmd_set_huge - setup kernel PMD mapping
*
* See text over pud_set_huge() above.
@@ -769,6 +751,21 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
}
/**
+ * pud_clear_huge - clear kernel PUD mapping when it is set
+ *
+ * Returns 1 on success and 0 on failure (no PUD map is found).
+ */
+int pud_clear_huge(pud_t *pud)
+{
+ if (pud_large(*pud)) {
+ pud_clear(pud);
+ return 1;
+ }
+
+ return 0;
+}
+
+/**
* pmd_clear_huge - clear kernel PMD mapping when it is set
*
* Returns 1 on success and 0 on failure (no PMD map is found).
@@ -782,7 +779,6 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
-#endif
#ifdef CONFIG_X86_64
/**
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 4b951458c9fc..16d76f814e9b 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1219,6 +1219,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
}
break;
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
+
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_B:
if (is_ereg(dst_reg))
diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c
index 3da88ded6ee3..3bfda5f502cb 100644
--- a/arch/x86/net/bpf_jit_comp32.c
+++ b/arch/x86/net/bpf_jit_comp32.c
@@ -1886,6 +1886,12 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image,
i++;
break;
}
+ /* speculation barrier */
+ case BPF_ST | BPF_NOSPEC:
+ if (boot_cpu_has(X86_FEATURE_XMM2))
+ /* Emit 'lfence' */
+ EMIT3(0x0F, 0xAE, 0xE8);
+ break;
/* ST: *(u8*)(dst_reg + off) = imm */
case BPF_ST | BPF_MEM | BPF_H:
case BPF_ST | BPF_MEM | BPF_B:
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 2332b2156993..3878880469d1 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -327,7 +327,6 @@ config XTENSA_PLATFORM_ISS
config XTENSA_PLATFORM_XT2000
bool "XT2000"
- select HAVE_IDE
help
XT2000 is the name of Tensilica's feature-rich emulation platform.
This hardware is capable of running a full Linux distribution.
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index c2d6bc88d3f1..5fac3757e6e0 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -1440,16 +1440,17 @@ static int iocg_wake_fn(struct wait_queue_entry *wq_entry, unsigned mode,
return -1;
iocg_commit_bio(ctx->iocg, wait->bio, wait->abs_cost, cost);
+ wait->committed = true;
/*
* autoremove_wake_function() removes the wait entry only when it
- * actually changed the task state. We want the wait always
- * removed. Remove explicitly and use default_wake_function().
+ * actually changed the task state. We want the wait always removed.
+ * Remove explicitly and use default_wake_function(). Note that the
+ * order of operations is important as finish_wait() tests whether
+ * @wq_entry is removed without grabbing the lock.
*/
- list_del_init(&wq_entry->entry);
- wait->committed = true;
-
default_wake_function(wq_entry, mode, flags, key);
+ list_del_init_careful(&wq_entry->entry);
return 0;
}
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index c838d81ac058..0f006cabfd91 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -515,17 +515,6 @@ void blk_mq_sched_insert_requests(struct blk_mq_hw_ctx *hctx,
percpu_ref_put(&q->q_usage_counter);
}
-static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set,
- struct blk_mq_hw_ctx *hctx,
- unsigned int hctx_idx)
-{
- if (hctx->sched_tags) {
- blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx);
- blk_mq_free_rq_map(hctx->sched_tags, set->flags);
- hctx->sched_tags = NULL;
- }
-}
-
static int blk_mq_sched_alloc_tags(struct request_queue *q,
struct blk_mq_hw_ctx *hctx,
unsigned int hctx_idx)
@@ -539,8 +528,10 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q,
return -ENOMEM;
ret = blk_mq_alloc_rqs(set, hctx->sched_tags, hctx_idx, q->nr_requests);
- if (ret)
- blk_mq_sched_free_tags(set, hctx, hctx_idx);
+ if (ret) {
+ blk_mq_free_rq_map(hctx->sched_tags, set->flags);
+ hctx->sched_tags = NULL;
+ }
return ret;
}
diff --git a/block/genhd.c b/block/genhd.c
index af4d2ab4a633..298ee78c1bda 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1079,10 +1079,9 @@ static void disk_release(struct device *dev)
disk_release_events(disk);
kfree(disk->random);
xa_destroy(&disk->part_tbl);
- bdput(disk->part0);
if (test_bit(GD_QUEUE_REF, &disk->state) && disk->queue)
blk_put_queue(disk->queue);
- kfree(disk);
+ bdput(disk->part0); /* frees the disk */
}
struct class block_class = {
.name = "block",
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 9d872ea477a6..8f9940f40baa 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -370,7 +370,7 @@ config ACPI_TABLE_UPGRADE
config ACPI_TABLE_OVERRIDE_VIA_BUILTIN_INITRD
bool "Override ACPI tables from built-in initrd"
depends on ACPI_TABLE_UPGRADE
- depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION=""
+ depends on INITRAMFS_SOURCE!="" && INITRAMFS_COMPRESSION_NONE
help
This option provides functionality to override arbitrary ACPI tables
from built-in uncompressed initrd.
diff --git a/drivers/acpi/dptf/dptf_pch_fivr.c b/drivers/acpi/dptf/dptf_pch_fivr.c
index 5fca18296bf6..550b9081fcbc 100644
--- a/drivers/acpi/dptf/dptf_pch_fivr.c
+++ b/drivers/acpi/dptf/dptf_pch_fivr.c
@@ -9,6 +9,42 @@
#include <linux/module.h>
#include <linux/platform_device.h>
+struct pch_fivr_resp {
+ u64 status;
+ u64 result;
+};
+
+static int pch_fivr_read(acpi_handle handle, char *method, struct pch_fivr_resp *fivr_resp)
+{
+ struct acpi_buffer resp = { sizeof(struct pch_fivr_resp), fivr_resp};
+ struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+ struct acpi_buffer format = { sizeof("NN"), "NN" };
+ union acpi_object *obj;
+ acpi_status status;
+ int ret = -EFAULT;
+
+ status = acpi_evaluate_object(handle, method, NULL, &buffer);
+ if (ACPI_FAILURE(status))
+ return ret;
+
+ obj = buffer.pointer;
+ if (!obj || obj->type != ACPI_TYPE_PACKAGE)
+ goto release_buffer;
+
+ status = acpi_extract_package(obj, &format, &resp);
+ if (ACPI_FAILURE(status))
+ goto release_buffer;
+
+ if (fivr_resp->status)
+ goto release_buffer;
+
+ ret = 0;
+
+release_buffer:
+ kfree(buffer.pointer);
+ return ret;
+}
+
/*
* Presentation of attributes which are defined for INT1045
* They are:
@@ -23,15 +59,14 @@ static ssize_t name##_show(struct device *dev,\
char *buf)\
{\
struct acpi_device *acpi_dev = dev_get_drvdata(dev);\
- unsigned long long val;\
- acpi_status status;\
+ struct pch_fivr_resp fivr_resp;\
+ int status;\
\
- status = acpi_evaluate_integer(acpi_dev->handle, #method,\
- NULL, &val);\
- if (ACPI_SUCCESS(status))\
- return sprintf(buf, "%d\n", (int)val);\
- else\
- return -EINVAL;\
+ status = pch_fivr_read(acpi_dev->handle, #method, &fivr_resp);\
+ if (status)\
+ return status;\
+\
+ return sprintf(buf, "%llu\n", fivr_resp.result);\
}
#define PCH_FIVR_STORE(name, method) \
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index dc01fb550b28..ee78a210c606 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -423,13 +423,6 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
}
}
-static bool irq_is_legacy(struct acpi_resource_irq *irq)
-{
- return irq->triggering == ACPI_EDGE_SENSITIVE &&
- irq->polarity == ACPI_ACTIVE_HIGH &&
- irq->shareable == ACPI_EXCLUSIVE;
-}
-
/**
* acpi_dev_resource_interrupt - Extract ACPI interrupt resource information.
* @ares: Input ACPI resource object.
@@ -468,7 +461,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
}
acpi_dev_get_irqresource(res, irq->interrupts[index],
irq->triggering, irq->polarity,
- irq->shareable, irq_is_legacy(irq));
+ irq->shareable, true);
break;
case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
ext_irq = &ares->data.extended_irq;
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index e7ddd281afff..d5cedffeeff9 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -860,11 +860,9 @@ EXPORT_SYMBOL(acpi_dev_present);
* Return the next match of ACPI device if another matching device was present
* at the moment of invocation, or NULL otherwise.
*
- * FIXME: The function does not tolerate the sudden disappearance of @adev, e.g.
- * in the case of a hotplug event. That said, the caller should ensure that
- * this will never happen.
- *
* The caller is responsible for invoking acpi_dev_put() on the returned device.
+ * On the other hand the function invokes acpi_dev_put() on the given @adev
+ * assuming that its reference counter had been increased beforehand.
*
* See additional information in acpi_dev_present() as well.
*/
@@ -880,6 +878,7 @@ acpi_dev_get_next_match_dev(struct acpi_device *adev, const char *hid, const cha
match.hrv = hrv;
dev = bus_find_device(&acpi_bus_type, start, &match, acpi_dev_match_cb);
+ acpi_dev_put(adev);
return dev ? to_acpi_device(dev) : NULL;
}
EXPORT_SYMBOL(acpi_dev_get_next_match_dev);
diff --git a/drivers/acpi/x86/s2idle.c b/drivers/acpi/x86/s2idle.c
index 1c507804fb10..fbdbef0ab552 100644
--- a/drivers/acpi/x86/s2idle.c
+++ b/drivers/acpi/x86/s2idle.c
@@ -378,19 +378,25 @@ static int lps0_device_attach(struct acpi_device *adev,
* AMDI0006:
* - should use rev_id 0x0
* - function mask = 0x3: Should use Microsoft method
+ * AMDI0007:
+ * - Should use rev_id 0x2
+ * - Should only use AMD method
*/
const char *hid = acpi_device_hid(adev);
- rev_id = 0;
+ rev_id = strcmp(hid, "AMDI0007") ? 0 : 2;
lps0_dsm_func_mask = validate_dsm(adev->handle,
ACPI_LPS0_DSM_UUID_AMD, rev_id, &lps0_dsm_guid);
lps0_dsm_func_mask_microsoft = validate_dsm(adev->handle,
- ACPI_LPS0_DSM_UUID_MICROSOFT, rev_id,
+ ACPI_LPS0_DSM_UUID_MICROSOFT, 0,
&lps0_dsm_guid_microsoft);
if (lps0_dsm_func_mask > 0x3 && (!strcmp(hid, "AMD0004") ||
!strcmp(hid, "AMDI0005"))) {
lps0_dsm_func_mask = (lps0_dsm_func_mask << 1) | 0x1;
acpi_handle_debug(adev->handle, "_DSM UUID %s: Adjusted function mask: 0x%x\n",
ACPI_LPS0_DSM_UUID_AMD, lps0_dsm_func_mask);
+ } else if (lps0_dsm_func_mask_microsoft > 0 && !strcmp(hid, "AMDI0007")) {
+ lps0_dsm_func_mask_microsoft = -EINVAL;
+ acpi_handle_debug(adev->handle, "_DSM Using AMD method\n");
}
} else {
rev_id = 1;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index ae7189d1a568..b71ea4a680b0 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -637,6 +637,20 @@ unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, unsigned char *buf,
}
EXPORT_SYMBOL_GPL(ata_sff_data_xfer32);
+static void ata_pio_xfer(struct ata_queued_cmd *qc, struct page *page,
+ unsigned int offset, size_t xfer_size)
+{
+ bool do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
+ unsigned char *buf;
+
+ buf = kmap_atomic(page);
+ qc->ap->ops->sff_data_xfer(qc, buf + offset, xfer_size, do_write);
+ kunmap_atomic(buf);
+
+ if (!do_write && !PageSlab(page))
+ flush_dcache_page(page);
+}
+
/**
* ata_pio_sector - Transfer a sector of data.
* @qc: Command on going
@@ -648,11 +662,9 @@ EXPORT_SYMBOL_GPL(ata_sff_data_xfer32);
*/
static void ata_pio_sector(struct ata_queued_cmd *qc)
{
- int do_write = (qc->tf.flags & ATA_TFLAG_WRITE);
struct ata_port *ap = qc->ap;
struct page *page;
unsigned int offset;
- unsigned char *buf;
if (!qc->cursg) {
qc->curbytes = qc->nbytes;
@@ -670,13 +682,20 @@ static void ata_pio_sector(struct ata_queued_cmd *qc)
DPRINTK("data %s\n", qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
- /* do the actual data transfer */
- buf = kmap_atomic(page);
- ap->ops->sff_data_xfer(qc, buf + offset, qc->sect_size, do_write);
- kunmap_atomic(buf);
+ /*
+ * Split the transfer when it splits a page boundary. Note that the
+ * split still has to be dword aligned like all ATA data transfers.
+ */
+ WARN_ON_ONCE(offset % 4);
+ if (offset + qc->sect_size > PAGE_SIZE) {
+ unsigned int split_len = PAGE_SIZE - offset;
- if (!do_write && !PageSlab(page))
- flush_dcache_page(page);
+ ata_pio_xfer(qc, page, offset, split_len);
+ ata_pio_xfer(qc, nth_page(page, 1), 0,
+ qc->sect_size - split_len);
+ } else {
+ ata_pio_xfer(qc, page, offset, qc->sect_size);
+ }
qc->curbytes += qc->sect_size;
qc->cursg_ofs += qc->sect_size;
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index adc199dfba3c..6a30264ab2ba 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -231,6 +231,8 @@ EXPORT_SYMBOL_GPL(auxiliary_find_device);
int __auxiliary_driver_register(struct auxiliary_driver *auxdrv,
struct module *owner, const char *modname)
{
+ int ret;
+
if (WARN_ON(!auxdrv->probe) || WARN_ON(!auxdrv->id_table))
return -EINVAL;
@@ -246,7 +248,11 @@ int __auxiliary_driver_register(struct auxiliary_driver *auxdrv,
auxdrv->driver.bus = &auxiliary_bus_type;
auxdrv->driver.mod_name = modname;
- return driver_register(&auxdrv->driver);
+ ret = driver_register(&auxdrv->driver);
+ if (ret)
+ kfree(auxdrv->driver.name);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(__auxiliary_driver_register);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index cadcade65825..f6360490a4a3 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -574,8 +574,10 @@ static void devlink_remove_symlinks(struct device *dev,
return;
}
- snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
- sysfs_remove_link(&con->kobj, buf);
+ if (device_is_registered(con)) {
+ snprintf(buf, len, "supplier:%s:%s", dev_bus_name(sup), dev_name(sup));
+ sysfs_remove_link(&con->kobj, buf);
+ }
snprintf(buf, len, "consumer:%s:%s", dev_bus_name(con), dev_name(con));
sysfs_remove_link(&sup->kobj, buf);
kfree(buf);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f37b9e3d833c..f0cdff0c5fbf 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -88,6 +88,47 @@
static DEFINE_IDR(loop_index_idr);
static DEFINE_MUTEX(loop_ctl_mutex);
+static DEFINE_MUTEX(loop_validate_mutex);
+
+/**
+ * loop_global_lock_killable() - take locks for safe loop_validate_file() test
+ *
+ * @lo: struct loop_device
+ * @global: true if @lo is about to bind another "struct loop_device", false otherwise
+ *
+ * Returns 0 on success, -EINTR otherwise.
+ *
+ * Since loop_validate_file() traverses on other "struct loop_device" if
+ * is_loop_device() is true, we need a global lock for serializing concurrent
+ * loop_configure()/loop_change_fd()/__loop_clr_fd() calls.
+ */
+static int loop_global_lock_killable(struct loop_device *lo, bool global)
+{
+ int err;
+
+ if (global) {
+ err = mutex_lock_killable(&loop_validate_mutex);
+ if (err)
+ return err;
+ }
+ err = mutex_lock_killable(&lo->lo_mutex);
+ if (err && global)
+ mutex_unlock(&loop_validate_mutex);
+ return err;
+}
+
+/**
+ * loop_global_unlock() - release locks taken by loop_global_lock_killable()
+ *
+ * @lo: struct loop_device
+ * @global: true if @lo was about to bind another "struct loop_device", false otherwise
+ */
+static void loop_global_unlock(struct loop_device *lo, bool global)
+{
+ mutex_unlock(&lo->lo_mutex);
+ if (global)
+ mutex_unlock(&loop_validate_mutex);
+}
static int max_part;
static int part_shift;
@@ -672,13 +713,15 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
while (is_loop_device(f)) {
struct loop_device *l;
+ lockdep_assert_held(&loop_validate_mutex);
if (f->f_mapping->host->i_rdev == bdev->bd_dev)
return -EBADF;
l = I_BDEV(f->f_mapping->host)->bd_disk->private_data;
- if (l->lo_state != Lo_bound) {
+ if (l->lo_state != Lo_bound)
return -EINVAL;
- }
+ /* Order wrt setting lo->lo_backing_file in loop_configure(). */
+ rmb();
f = l->lo_backing_file;
}
if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
@@ -697,13 +740,18 @@ static int loop_validate_file(struct file *file, struct block_device *bdev)
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
unsigned int arg)
{
- struct file *file = NULL, *old_file;
- int error;
- bool partscan;
+ struct file *file = fget(arg);
+ struct file *old_file;
+ int error;
+ bool partscan;
+ bool is_loop;
- error = mutex_lock_killable(&lo->lo_mutex);
+ if (!file)
+ return -EBADF;
+ is_loop = is_loop_device(file);
+ error = loop_global_lock_killable(lo, is_loop);
if (error)
- return error;
+ goto out_putf;
error = -ENXIO;
if (lo->lo_state != Lo_bound)
goto out_err;
@@ -713,11 +761,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
goto out_err;
- error = -EBADF;
- file = fget(arg);
- if (!file)
- goto out_err;
-
error = loop_validate_file(file, bdev);
if (error)
goto out_err;
@@ -740,7 +783,16 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
loop_update_dio(lo);
blk_mq_unfreeze_queue(lo->lo_queue);
partscan = lo->lo_flags & LO_FLAGS_PARTSCAN;
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
+
+ /*
+ * Flush loop_validate_file() before fput(), for l->lo_backing_file
+ * might be pointing at old_file which might be the last reference.
+ */
+ if (!is_loop) {
+ mutex_lock(&loop_validate_mutex);
+ mutex_unlock(&loop_validate_mutex);
+ }
/*
* We must drop file reference outside of lo_mutex as dropping
* the file ref can take open_mutex which creates circular locking
@@ -752,9 +804,9 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
return 0;
out_err:
- mutex_unlock(&lo->lo_mutex);
- if (file)
- fput(file);
+ loop_global_unlock(lo, is_loop);
+out_putf:
+ fput(file);
return error;
}
@@ -1136,22 +1188,22 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
struct block_device *bdev,
const struct loop_config *config)
{
- struct file *file;
- struct inode *inode;
+ struct file *file = fget(config->fd);
+ struct inode *inode;
struct address_space *mapping;
- int error;
- loff_t size;
- bool partscan;
- unsigned short bsize;
+ int error;
+ loff_t size;
+ bool partscan;
+ unsigned short bsize;
+ bool is_loop;
+
+ if (!file)
+ return -EBADF;
+ is_loop = is_loop_device(file);
/* This is safe, since we have a reference from open(). */
__module_get(THIS_MODULE);
- error = -EBADF;
- file = fget(config->fd);
- if (!file)
- goto out;
-
/*
* If we don't hold exclusive handle for the device, upgrade to it
* here to avoid changing device under exclusive owner.
@@ -1162,7 +1214,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
goto out_putf;
}
- error = mutex_lock_killable(&lo->lo_mutex);
+ error = loop_global_lock_killable(lo, is_loop);
if (error)
goto out_bdev;
@@ -1242,6 +1294,9 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
size = get_loop_size(lo, file);
loop_set_size(lo, size);
+ /* Order wrt reading lo_state in loop_validate_file(). */
+ wmb();
+
lo->lo_state = Lo_bound;
if (part_shift)
lo->lo_flags |= LO_FLAGS_PARTSCAN;
@@ -1253,7 +1308,7 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
* put /dev/loopXX inode. Later in __loop_clr_fd() we bdput(bdev).
*/
bdgrab(bdev);
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
if (partscan)
loop_reread_partitions(lo);
if (!(mode & FMODE_EXCL))
@@ -1261,13 +1316,12 @@ static int loop_configure(struct loop_device *lo, fmode_t mode,
return 0;
out_unlock:
- mutex_unlock(&lo->lo_mutex);
+ loop_global_unlock(lo, is_loop);
out_bdev:
if (!(mode & FMODE_EXCL))
bd_abort_claiming(bdev, loop_configure);
out_putf:
fput(file);
-out:
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
return error;
@@ -1283,6 +1337,18 @@ static int __loop_clr_fd(struct loop_device *lo, bool release)
int lo_number;
struct loop_worker *pos, *worker;
+ /*
+ * Flush loop_configure() and loop_change_fd(). It is acceptable for
+ * loop_validate_file() to succeed, for actual clear operation has not
+ * started yet.
+ */
+ mutex_lock(&loop_validate_mutex);
+ mutex_unlock(&loop_validate_mutex);
+ /*
+ * loop_validate_file() now fails because l->lo_state != Lo_bound
+ * became visible.
+ */
+
mutex_lock(&lo->lo_mutex);
if (WARN_ON_ONCE(lo->lo_state != Lo_rundown)) {
err = -ENXIO;
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 531d390902dd..90b947c96402 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4100,8 +4100,6 @@ again:
static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
{
- bool need_wait;
-
dout("%s rbd_dev %p\n", __func__, rbd_dev);
lockdep_assert_held_write(&rbd_dev->lock_rwsem);
@@ -4113,11 +4111,11 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
*/
rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
rbd_assert(!completion_done(&rbd_dev->releasing_wait));
- need_wait = !list_empty(&rbd_dev->running_list);
- downgrade_write(&rbd_dev->lock_rwsem);
- if (need_wait)
- wait_for_completion(&rbd_dev->releasing_wait);
- up_read(&rbd_dev->lock_rwsem);
+ if (list_empty(&rbd_dev->running_list))
+ return true;
+
+ up_write(&rbd_dev->lock_rwsem);
+ wait_for_completion(&rbd_dev->releasing_wait);
down_write(&rbd_dev->lock_rwsem);
if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
@@ -4203,15 +4201,11 @@ static void rbd_handle_acquired_lock(struct rbd_device *rbd_dev, u8 struct_v,
if (!rbd_cid_equal(&cid, &rbd_empty_cid)) {
down_write(&rbd_dev->lock_rwsem);
if (rbd_cid_equal(&cid, &rbd_dev->owner_cid)) {
- /*
- * we already know that the remote client is
- * the owner
- */
- up_write(&rbd_dev->lock_rwsem);
- return;
+ dout("%s rbd_dev %p cid %llu-%llu == owner_cid\n",
+ __func__, rbd_dev, cid.gid, cid.handle);
+ } else {
+ rbd_set_owner_cid(rbd_dev, &cid);
}
-
- rbd_set_owner_cid(rbd_dev, &cid);
downgrade_write(&rbd_dev->lock_rwsem);
} else {
down_read(&rbd_dev->lock_rwsem);
@@ -4236,14 +4230,12 @@ static void rbd_handle_released_lock(struct rbd_device *rbd_dev, u8 struct_v,
if (!rbd_cid_equal(&cid, &rbd_empty_cid)) {
down_write(&rbd_dev->lock_rwsem);
if (!rbd_cid_equal(&cid, &rbd_dev->owner_cid)) {
- dout("%s rbd_dev %p unexpected owner, cid %llu-%llu != owner_cid %llu-%llu\n",
+ dout("%s rbd_dev %p cid %llu-%llu != owner_cid %llu-%llu\n",
__func__, rbd_dev, cid.gid, cid.handle,
rbd_dev->owner_cid.gid, rbd_dev->owner_cid.handle);
- up_write(&rbd_dev->lock_rwsem);
- return;
+ } else {
+ rbd_set_owner_cid(rbd_dev, &rbd_empty_cid);
}
-
- rbd_set_owner_cid(rbd_dev, &rbd_empty_cid);
downgrade_write(&rbd_dev->lock_rwsem);
} else {
down_read(&rbd_dev->lock_rwsem);
@@ -4951,6 +4943,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
disk->minors = RBD_MINORS_PER_MAJOR;
}
disk->fops = &rbd_bd_ops;
+ disk->private_data = rbd_dev;
blk_queue_flag_set(QUEUE_FLAG_NONROT, q);
/* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c
index 22acde118bc3..fc9196f11cb7 100644
--- a/drivers/bus/mhi/core/main.c
+++ b/drivers/bus/mhi/core/main.c
@@ -773,11 +773,18 @@ static void mhi_process_cmd_completion(struct mhi_controller *mhi_cntrl,
cmd_pkt = mhi_to_virtual(mhi_ring, ptr);
chan = MHI_TRE_GET_CMD_CHID(cmd_pkt);
- mhi_chan = &mhi_cntrl->mhi_chan[chan];
- write_lock_bh(&mhi_chan->lock);
- mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre);
- complete(&mhi_chan->completion);
- write_unlock_bh(&mhi_chan->lock);
+
+ if (chan < mhi_cntrl->max_chan &&
+ mhi_cntrl->mhi_chan[chan].configured) {
+ mhi_chan = &mhi_cntrl->mhi_chan[chan];
+ write_lock_bh(&mhi_chan->lock);
+ mhi_chan->ccs = MHI_TRE_GET_EV_CODE(tre);
+ complete(&mhi_chan->completion);
+ write_unlock_bh(&mhi_chan->lock);
+ } else {
+ dev_err(&mhi_cntrl->mhi_dev->dev,
+ "Completion packet for invalid channel ID: %d\n", chan);
+ }
mhi_del_ring_element(mhi_cntrl, mhi_ring);
}
diff --git a/drivers/bus/mhi/pci_generic.c b/drivers/bus/mhi/pci_generic.c
index ca3bc40427f8..4dd1077354af 100644
--- a/drivers/bus/mhi/pci_generic.c
+++ b/drivers/bus/mhi/pci_generic.c
@@ -32,6 +32,8 @@
* @edl: emergency download mode firmware path (if any)
* @bar_num: PCI base address register to use for MHI MMIO register space
* @dma_data_width: DMA transfer word size (32 or 64 bits)
+ * @sideband_wake: Devices using dedicated sideband GPIO for wakeup instead
+ * of inband wake support (such as sdx24)
*/
struct mhi_pci_dev_info {
const struct mhi_controller_config *config;
@@ -40,6 +42,7 @@ struct mhi_pci_dev_info {
const char *edl;
unsigned int bar_num;
unsigned int dma_data_width;
+ bool sideband_wake;
};
#define MHI_CHANNEL_CONFIG_UL(ch_num, ch_name, el_count, ev_ring) \
@@ -72,6 +75,22 @@ struct mhi_pci_dev_info {
.doorbell_mode_switch = false, \
}
+#define MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(ch_num, ch_name, el_count, ev_ring) \
+ { \
+ .num = ch_num, \
+ .name = ch_name, \
+ .num_elements = el_count, \
+ .event_ring = ev_ring, \
+ .dir = DMA_FROM_DEVICE, \
+ .ee_mask = BIT(MHI_EE_AMSS), \
+ .pollcfg = 0, \
+ .doorbell = MHI_DB_BRST_DISABLE, \
+ .lpm_notify = false, \
+ .offload_channel = false, \
+ .doorbell_mode_switch = false, \
+ .auto_queue = true, \
+ }
+
#define MHI_EVENT_CONFIG_CTRL(ev_ring, el_count) \
{ \
.num_elements = el_count, \
@@ -210,7 +229,7 @@ static const struct mhi_channel_config modem_qcom_v1_mhi_channels[] = {
MHI_CHANNEL_CONFIG_UL(14, "QMI", 4, 0),
MHI_CHANNEL_CONFIG_DL(15, "QMI", 4, 0),
MHI_CHANNEL_CONFIG_UL(20, "IPCR", 8, 0),
- MHI_CHANNEL_CONFIG_DL(21, "IPCR", 8, 0),
+ MHI_CHANNEL_CONFIG_DL_AUTOQUEUE(21, "IPCR", 8, 0),
MHI_CHANNEL_CONFIG_UL_FP(34, "FIREHOSE", 32, 0),
MHI_CHANNEL_CONFIG_DL_FP(35, "FIREHOSE", 32, 0),
MHI_CHANNEL_CONFIG_HW_UL(100, "IP_HW0", 128, 2),
@@ -242,7 +261,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx65_info = {
.edl = "qcom/sdx65m/edl.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = {
@@ -251,7 +271,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx55_info = {
.edl = "qcom/sdx55m/edl.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = {
@@ -259,7 +280,8 @@ static const struct mhi_pci_dev_info mhi_qcom_sdx24_info = {
.edl = "qcom/prog_firehose_sdx24.mbn",
.config = &modem_qcom_v1_mhiv_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = true,
};
static const struct mhi_channel_config mhi_quectel_em1xx_channels[] = {
@@ -301,7 +323,8 @@ static const struct mhi_pci_dev_info mhi_quectel_em1xx_info = {
.edl = "qcom/prog_firehose_sdx24.mbn",
.config = &modem_quectel_em1xx_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = true,
};
static const struct mhi_channel_config mhi_foxconn_sdx55_channels[] = {
@@ -339,7 +362,8 @@ static const struct mhi_pci_dev_info mhi_foxconn_sdx55_info = {
.edl = "qcom/sdx55m/edl.mbn",
.config = &modem_foxconn_sdx55_config,
.bar_num = MHI_PCI_DEFAULT_BAR_NUM,
- .dma_data_width = 32
+ .dma_data_width = 32,
+ .sideband_wake = false,
};
static const struct pci_device_id mhi_pci_id_table[] = {
@@ -640,9 +664,12 @@ static int mhi_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
mhi_cntrl->status_cb = mhi_pci_status_cb;
mhi_cntrl->runtime_get = mhi_pci_runtime_get;
mhi_cntrl->runtime_put = mhi_pci_runtime_put;
- mhi_cntrl->wake_get = mhi_pci_wake_get_nop;
- mhi_cntrl->wake_put = mhi_pci_wake_put_nop;
- mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop;
+
+ if (info->sideband_wake) {
+ mhi_cntrl->wake_get = mhi_pci_wake_get_nop;
+ mhi_cntrl->wake_put = mhi_pci_wake_put_nop;
+ mhi_cntrl->wake_toggle = mhi_pci_wake_toggle_nop;
+ }
err = mhi_pci_claim(mhi_cntrl, info->bar_num, DMA_BIT_MASK(info->dma_data_width));
if (err)
diff --git a/drivers/firmware/efi/dev-path-parser.c b/drivers/firmware/efi/dev-path-parser.c
index 10d4457417a4..eb9c65f97841 100644
--- a/drivers/firmware/efi/dev-path-parser.c
+++ b/drivers/firmware/efi/dev-path-parser.c
@@ -34,7 +34,6 @@ static long __init parse_acpi_path(const struct efi_dev_path *node,
break;
if (!adev->pnp.unique_id && node->acpi.uid == 0)
break;
- acpi_dev_put(adev);
}
if (!adev)
return -ENODEV;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 4b7ee3fa9224..847f33ffc4ae 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -896,6 +896,7 @@ static int __init efi_memreserve_map_root(void)
static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size)
{
struct resource *res, *parent;
+ int ret;
res = kzalloc(sizeof(struct resource), GFP_ATOMIC);
if (!res)
@@ -908,7 +909,17 @@ static int efi_mem_reserve_iomem(phys_addr_t addr, u64 size)
/* we expect a conflict with a 'System RAM' region */
parent = request_resource_conflict(&iomem_resource, res);
- return parent ? request_resource(parent, res) : 0;
+ ret = parent ? request_resource(parent, res) : 0;
+
+ /*
+ * Given that efi_mem_reserve_iomem() can be called at any
+ * time, only call memblock_reserve() if the architecture
+ * keeps the infrastructure around.
+ */
+ if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK) && !ret)
+ memblock_reserve(addr, size);
+
+ return ret;
}
int __ref efi_mem_reserve_persistent(phys_addr_t addr, u64 size)
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index aa8da0a49829..ae87dded989d 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -630,8 +630,8 @@ efi_status_t efi_load_initrd_cmdline(efi_loaded_image_t *image,
* @image: EFI loaded image protocol
* @load_addr: pointer to loaded initrd
* @load_size: size of loaded initrd
- * @soft_limit: preferred size of allocated memory for loading the initrd
- * @hard_limit: minimum size of allocated memory
+ * @soft_limit: preferred address for loading the initrd
+ * @hard_limit: upper limit address for loading the initrd
*
* Return: status code
*/
diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index d8bc01340686..38722d2009e2 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -180,7 +180,10 @@ void __init efi_mokvar_table_init(void)
pr_err("EFI MOKvar config table is not valid\n");
return;
}
- efi_mem_reserve(efi.mokvar_table, map_size_needed);
+
+ if (md.type == EFI_BOOT_SERVICES_DATA)
+ efi_mem_reserve(efi.mokvar_table, map_size_needed);
+
efi_mokvar_table_size = map_size_needed;
}
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index c1955d320fec..8f665678e9e3 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -62,9 +62,11 @@ int __init efi_tpm_eventlog_init(void)
tbl_size = sizeof(*log_tbl) + log_tbl->size;
memblock_reserve(efi.tpm_log, tbl_size);
- if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR ||
- log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
- pr_warn(FW_BUG "TPM Final Events table missing or invalid\n");
+ if (efi.tpm_final_log == EFI_INVALID_TABLE_ADDR) {
+ pr_info("TPM Final Events table not present\n");
+ goto out;
+ } else if (log_tbl->version != EFI_TCG2_EVENT_LOG_FORMAT_TCG_2) {
+ pr_warn(FW_BUG "TPM Final Events table invalid\n");
goto out;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c0316eaba547..8ac6eb9f1fdb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -619,6 +619,13 @@ struct amdgpu_video_codec_info {
u32 max_level;
};
+#define codec_info_build(type, width, height, level) \
+ .codec_type = type,\
+ .max_width = width,\
+ .max_height = height,\
+ .max_pixels_per_frame = height * width,\
+ .max_level = level,
+
struct amdgpu_video_codecs {
const u32 codec_count;
const struct amdgpu_video_codec_info *codec_array;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 84a1b4bc9bb4..6cc0d4fa4d0a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -26,6 +26,7 @@
#include <linux/slab.h>
#include <linux/power_supply.h>
#include <linux/pm_runtime.h>
+#include <linux/suspend.h>
#include <acpi/video.h>
#include <acpi/actbl.h>
@@ -1042,7 +1043,7 @@ bool amdgpu_acpi_is_s0ix_supported(struct amdgpu_device *adev)
#if defined(CONFIG_AMD_PMC) || defined(CONFIG_AMD_PMC_MODULE)
if (acpi_gbl_FADT.flags & ACPI_FADT_LOW_POWER_S0) {
if (adev->flags & AMD_IS_APU)
- return true;
+ return pm_suspend_target_state == PM_SUSPEND_TO_IDLE;
}
#endif
return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d303e88e3c23..f3fd5ec710b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3504,13 +3504,13 @@ int amdgpu_device_init(struct amdgpu_device *adev,
r = amdgpu_device_get_job_timeout_settings(adev);
if (r) {
dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
- goto failed_unmap;
+ return r;
}
/* early init functions */
r = amdgpu_device_ip_early_init(adev);
if (r)
- goto failed_unmap;
+ return r;
/* doorbell bar mapping and doorbell index init*/
amdgpu_device_doorbell_init(adev);
@@ -3736,10 +3736,6 @@ release_ras_con:
failed:
amdgpu_vf_error_trans_all(adev);
-failed_unmap:
- iounmap(adev->rmmio);
- adev->rmmio = NULL;
-
return r;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index abb928894eac..361b86b71b56 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1190,6 +1190,10 @@ static const struct pci_device_id pciidlist[] = {
/* Van Gogh */
{0x1002, 0x163F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VANGOGH|AMD_IS_APU},
+ /* Yellow Carp */
+ {0x1002, 0x164D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+ {0x1002, 0x1681, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_YELLOW_CARP|AMD_IS_APU},
+
/* Navy_Flounder */
{0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
{0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index d0d9bc445d7b..854fc497844b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -255,6 +255,15 @@ static int amdgpu_gem_object_mmap(struct drm_gem_object *obj, struct vm_area_str
if (bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS)
return -EPERM;
+ /* Workaround for Thunk bug creating PROT_NONE,MAP_PRIVATE mappings
+ * for debugger access to invisible VRAM. Should have used MAP_SHARED
+ * instead. Clearing VM_MAYWRITE prevents the mapping from ever
+ * becoming writable and makes is_cow_mapping(vm_flags) false.
+ */
+ if (is_cow_mapping(vma->vm_flags) &&
+ !(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
+ vma->vm_flags &= ~VM_MAYWRITE;
+
return drm_gem_ttm_mmap(obj, vma);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index f5e9c022960b..a64b2c706090 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -3300,6 +3300,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffbfffff, 0x00a00000)
};
@@ -3379,6 +3380,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_vangogh[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1_Vangogh, 0xffffffff, 0x00070103),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQG_CONFIG, 0x000017ff, 0x00001000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0xffffffff, 0x00400000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
@@ -3445,6 +3447,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3_4[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER7_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER8_SELECT, 0xf0f001ff, 0x00000000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_PERFCOUNTER9_SELECT, 0xf0f001ff, 0x00000000),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmSX_DEBUG_1, 0x00010000, 0x00010020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0x01030000, 0x01030000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x03a00000, 0x00a00000),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020)
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index 94a2c0742ee5..94d029dbf30d 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -64,32 +64,13 @@
#include "smuio_v11_0.h"
#include "smuio_v11_0_6.h"
-#define codec_info_build(type, width, height, level) \
- .codec_type = type,\
- .max_width = width,\
- .max_height = height,\
- .max_pixels_per_frame = height * width,\
- .max_level = level,
-
static const struct amd_ip_funcs nv_common_ip_funcs;
/* Navi */
static const struct amdgpu_video_codec_info nv_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static const struct amdgpu_video_codecs nv_video_codecs_encode =
@@ -101,55 +82,13 @@ static const struct amdgpu_video_codecs nv_video_codecs_encode =
/* Navi1x */
static const struct amdgpu_video_codec_info nv_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs nv_video_codecs_decode =
@@ -161,62 +100,14 @@ static const struct amdgpu_video_codecs nv_video_codecs_decode =
/* Sienna Cichlid */
static const struct amdgpu_video_codec_info sc_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs sc_video_codecs_decode =
@@ -228,80 +119,20 @@ static const struct amdgpu_video_codecs sc_video_codecs_decode =
/* SRIOV Sienna Cichlid, not const since data is controlled by host */
static struct amdgpu_video_codec_info sriov_sc_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static struct amdgpu_video_codec_info sriov_sc_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 8192 * 4352,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1, 8192, 4352, 0)},
};
static struct amdgpu_video_codecs sriov_sc_video_codecs_encode =
@@ -333,6 +164,19 @@ static const struct amdgpu_video_codecs bg_video_codecs_encode = {
.codec_array = NULL,
};
+/* Yellow Carp*/
+static const struct amdgpu_video_codec_info yc_video_codecs_decode_array[] = {
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+};
+
+static const struct amdgpu_video_codecs yc_video_codecs_decode = {
+ .codec_count = ARRAY_SIZE(yc_video_codecs_decode_array),
+ .codec_array = yc_video_codecs_decode_array,
+};
+
static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
const struct amdgpu_video_codecs **codecs)
{
@@ -353,12 +197,17 @@ static int nv_query_video_codecs(struct amdgpu_device *adev, bool encode,
case CHIP_NAVY_FLOUNDER:
case CHIP_DIMGREY_CAVEFISH:
case CHIP_VANGOGH:
- case CHIP_YELLOW_CARP:
if (encode)
*codecs = &nv_video_codecs_encode;
else
*codecs = &sc_video_codecs_decode;
return 0;
+ case CHIP_YELLOW_CARP:
+ if (encode)
+ *codecs = &nv_video_codecs_encode;
+ else
+ *codecs = &yc_video_codecs_decode;
+ return 0;
case CHIP_BEIGE_GOBY:
if (encode)
*codecs = &bg_video_codecs_encode;
@@ -1387,7 +1236,10 @@ static int nv_common_early_init(void *handle)
AMD_PG_SUPPORT_VCN |
AMD_PG_SUPPORT_VCN_DPG |
AMD_PG_SUPPORT_JPEG;
- adev->external_rev_id = adev->rev_id + 0x01;
+ if (adev->pdev->device == 0x1681)
+ adev->external_rev_id = adev->rev_id + 0x19;
+ else
+ adev->external_rev_id = adev->rev_id + 0x01;
break;
default:
/* FIXME: not supported yet */
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index 618e5b6b85d9..536d41f327c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -67,7 +67,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
err = psp_init_asd_microcode(psp, chip_name);
if (err)
- goto out;
+ return err;
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
@@ -80,7 +80,7 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
} else {
err = amdgpu_ucode_validate(adev->psp.ta_fw);
if (err)
- goto out2;
+ goto out;
ta_hdr = (const struct ta_firmware_header_v1_0 *)
adev->psp.ta_fw->data;
@@ -105,10 +105,9 @@ static int psp_v12_0_init_microcode(struct psp_context *psp)
return 0;
-out2:
+out:
release_firmware(adev->psp.ta_fw);
adev->psp.ta_fw = NULL;
-out:
if (err) {
dev_err(adev->dev,
"psp v12.0: Failed to load firmware \"%s\"\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index b02436401d46..b7d350be8050 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -88,20 +88,8 @@
/* Vega, Raven, Arcturus */
static const struct amdgpu_video_codec_info vega_video_codecs_encode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 2304,
- .max_pixels_per_frame = 4096 * 2304,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 2304, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 2304, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_encode =
@@ -113,48 +101,12 @@ static const struct amdgpu_video_codecs vega_video_codecs_encode =
/* Vega */
static const struct amdgpu_video_codec_info vega_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs vega_video_codecs_decode =
@@ -166,55 +118,13 @@ static const struct amdgpu_video_codecs vega_video_codecs_decode =
/* Raven */
static const struct amdgpu_video_codec_info rv_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 4096, 4096, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 4096, 4096, 0)},
};
static const struct amdgpu_video_codecs rv_video_codecs_decode =
@@ -226,55 +136,13 @@ static const struct amdgpu_video_codecs rv_video_codecs_decode =
/* Renoir, Arcturus */
static const struct amdgpu_video_codec_info rn_video_codecs_decode_array[] =
{
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 3,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 5,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 52,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 4,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 186,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG,
- .max_width = 4096,
- .max_height = 4096,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
- {
- .codec_type = AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9,
- .max_width = 8192,
- .max_height = 4352,
- .max_pixels_per_frame = 4096 * 4096,
- .max_level = 0,
- },
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2, 4096, 4906, 3)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4, 4096, 4906, 5)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC, 4096, 4906, 52)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1, 4096, 4906, 4)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC, 8192, 4352, 186)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG, 4096, 4096, 0)},
+ {codec_info_build(AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9, 8192, 4352, 0)},
};
static const struct amdgpu_video_codecs rn_video_codecs_decode =
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d3a2a5ff57e9..b53f49a23ddc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2429,9 +2429,9 @@ static void update_connector_ext_caps(struct amdgpu_dm_connector *aconnector)
max_cll = conn_base->hdr_sink_metadata.hdmi_type1.max_cll;
min_cll = conn_base->hdr_sink_metadata.hdmi_type1.min_cll;
- if (caps->ext_caps->bits.oled == 1 ||
+ if (caps->ext_caps->bits.oled == 1 /*||
caps->ext_caps->bits.sdr_aux_backlight_control == 1 ||
- caps->ext_caps->bits.hdr_aux_backlight_control == 1)
+ caps->ext_caps->bits.hdr_aux_backlight_control == 1*/)
caps->aux_support = true;
if (amdgpu_backlight == 0)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 6e0c5c664fdc..a5331b96f551 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -197,7 +197,7 @@ void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr, struct
REG_UPDATE(DENTIST_DISPCLK_CNTL,
DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider);
-// REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 5, 100);
+ REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 50, 1000);
REG_UPDATE(DENTIST_DISPCLK_CNTL,
DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider);
REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100);
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
index 513676a6f52b..af7004b770ae 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn30/dcn30_clk_mgr.c
@@ -190,6 +190,10 @@ void dcn3_init_clocks(struct clk_mgr *clk_mgr_base)
&clk_mgr_base->bw_params->clk_table.entries[0].dtbclk_mhz,
&num_levels);
+ /* SOCCLK */
+ dcn3_init_single_clock(clk_mgr, PPCLK_SOCCLK,
+ &clk_mgr_base->bw_params->clk_table.entries[0].socclk_mhz,
+ &num_levels);
// DPREFCLK ???
/* DISPCLK */
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
index 7b7d884d58be..4a4894e9d9c9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c
@@ -48,6 +48,21 @@
#include "dc_dmub_srv.h"
+#include "yellow_carp_offset.h"
+
+#define regCLK1_CLK_PLL_REQ 0x0237
+#define regCLK1_CLK_PLL_REQ_BASE_IDX 0
+
+#define CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
+#define CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
+#define CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
+#define CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
+#define CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
+#define CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
+
+#define REG(reg_name) \
+ (CLK_BASE.instance[0].segment[reg ## reg_name ## _BASE_IDX] + reg ## reg_name)
+
#define TO_CLK_MGR_DCN31(clk_mgr)\
container_of(clk_mgr, struct clk_mgr_dcn31, base)
@@ -124,10 +139,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
* also if safe to lower is false, we just go in the higher state
*/
if (safe_to_lower) {
- if (new_clocks->z9_support == DCN_Z9_SUPPORT_ALLOW &&
- new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+ if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_ALLOW &&
+ new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
dcn31_smu_set_Z9_support(clk_mgr, true);
- clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
}
if (clk_mgr_base->clks.dtbclk_en && !new_clocks->dtbclk_en) {
@@ -148,10 +163,10 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
}
}
} else {
- if (new_clocks->z9_support == DCN_Z9_SUPPORT_DISALLOW &&
- new_clocks->z9_support != clk_mgr_base->clks.z9_support) {
+ if (new_clocks->zstate_support == DCN_ZSTATE_SUPPORT_DISALLOW &&
+ new_clocks->zstate_support != clk_mgr_base->clks.zstate_support) {
dcn31_smu_set_Z9_support(clk_mgr, false);
- clk_mgr_base->clks.z9_support = new_clocks->z9_support;
+ clk_mgr_base->clks.zstate_support = new_clocks->zstate_support;
}
if (!clk_mgr_base->clks.dtbclk_en && new_clocks->dtbclk_en) {
@@ -229,7 +244,32 @@ static void dcn31_update_clocks(struct clk_mgr *clk_mgr_base,
static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr)
{
- return 0;
+ /* get FbMult value */
+ struct fixed31_32 pll_req;
+ unsigned int fbmult_frac_val = 0;
+ unsigned int fbmult_int_val = 0;
+
+ /*
+ * Register value of fbmult is in 8.16 format, we are converting to 31.32
+ * to leverage the fix point operations available in driver
+ */
+
+ REG_GET(CLK1_CLK_PLL_REQ, FbMult_frac, &fbmult_frac_val); /* 16 bit fractional part*/
+ REG_GET(CLK1_CLK_PLL_REQ, FbMult_int, &fbmult_int_val); /* 8 bit integer part */
+
+ pll_req = dc_fixpt_from_int(fbmult_int_val);
+
+ /*
+ * since fractional part is only 16 bit in register definition but is 32 bit
+ * in our fix point definiton, need to shift left by 16 to obtain correct value
+ */
+ pll_req.value |= fbmult_frac_val << 16;
+
+ /* multiply by REFCLK period */
+ pll_req = dc_fixpt_mul_int(pll_req, clk_mgr->dfs_ref_freq_khz);
+
+ /* integer part is now VCO frequency in kHz */
+ return dc_fixpt_floor(pll_req);
}
static void dcn31_enable_pme_wa(struct clk_mgr *clk_mgr_base)
@@ -246,7 +286,7 @@ static void dcn31_init_clocks(struct clk_mgr *clk_mgr)
clk_mgr->clks.p_state_change_support = true;
clk_mgr->clks.prev_p_state_change_support = true;
clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
- clk_mgr->clks.z9_support = DCN_Z9_SUPPORT_UNKNOWN;
+ clk_mgr->clks.zstate_support = DCN_ZSTATE_SUPPORT_UNKNOWN;
}
static bool dcn31_are_clock_states_equal(struct dc_clocks *a,
@@ -260,7 +300,7 @@ static bool dcn31_are_clock_states_equal(struct dc_clocks *a,
return false;
else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz)
return false;
- else if (a->z9_support != b->z9_support)
+ else if (a->zstate_support != b->zstate_support)
return false;
else if (a->dtbclk_en != b->dtbclk_en)
return false;
@@ -592,6 +632,7 @@ void dcn31_clk_mgr_construct(
clk_mgr->base.dprefclk_ss_percentage = 0;
clk_mgr->base.dprefclk_ss_divider = 1000;
clk_mgr->base.ss_on_dprefclk = false;
+ clk_mgr->base.dfs_ref_freq_khz = 48000;
clk_mgr->smu_wm_set.wm_set = (struct dcn31_watermarks *)dm_helpers_allocate_gpu_mem(
clk_mgr->base.base.ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
index cc21cf75eafd..f8f100535526 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.h
@@ -27,60 +27,6 @@
#define __DCN31_CLK_MGR_H__
#include "clk_mgr_internal.h"
-//CLK1_CLK_PLL_REQ
-#ifndef CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
-#define CLK11_CLK1_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
-#define CLK11_CLK1_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
-//CLK1_CLK0_DFS_CNTL
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER__SHIFT 0x0
-#define CLK11_CLK1_CLK0_DFS_CNTL__CLK0_DIVIDER_MASK 0x0000007FL
-/*DPREF clock related*/
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK0_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK1_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK2_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER__SHIFT 0x0
-#define CLK3_CLK3_DFS_CNTL__CLK3_DIVIDER_MASK 0x0000007FL
-
-//CLK3_0_CLK3_CLK_PLL_REQ
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int__SHIFT 0x0
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv__SHIFT 0xc
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac__SHIFT 0x10
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_int_MASK 0x000001FFL
-#define CLK3_0_CLK3_CLK_PLL_REQ__PllSpineDiv_MASK 0x0000F000L
-#define CLK3_0_CLK3_CLK_PLL_REQ__FbMult_frac_MASK 0xFFFF0000L
-
-#define mmCLK0_CLK3_DFS_CNTL 0x16C60
-#define mmCLK00_CLK0_CLK3_DFS_CNTL 0x16C60
-#define mmCLK01_CLK0_CLK3_DFS_CNTL 0x16E60
-#define mmCLK02_CLK0_CLK3_DFS_CNTL 0x17060
-#define mmCLK03_CLK0_CLK3_DFS_CNTL 0x17260
-
-#define mmCLK0_CLK_PLL_REQ 0x16C10
-#define mmCLK00_CLK0_CLK_PLL_REQ 0x16C10
-#define mmCLK01_CLK0_CLK_PLL_REQ 0x16E10
-#define mmCLK02_CLK0_CLK_PLL_REQ 0x17010
-#define mmCLK03_CLK0_CLK_PLL_REQ 0x17210
-
-#define mmCLK1_CLK_PLL_REQ 0x1B00D
-#define mmCLK10_CLK1_CLK_PLL_REQ 0x1B00D
-#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D
-#define mmCLK12_CLK1_CLK_PLL_REQ 0x1B40D
-#define mmCLK13_CLK1_CLK_PLL_REQ 0x1B60D
-
-#define mmCLK2_CLK_PLL_REQ 0x17E0D
-
-/*AMCLK*/
-#define mmCLK11_CLK1_CLK0_DFS_CNTL 0x1B23F
-#define mmCLK11_CLK1_CLK_PLL_REQ 0x1B20D
-#endif
-
struct dcn31_watermarks;
struct dcn31_smu_watermark_set {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 6da226bf11d5..9fb8c46dc606 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1820,8 +1820,7 @@ bool perform_link_training_with_retries(
*/
panel_mode = DP_PANEL_MODE_DEFAULT;
}
- } else
- panel_mode = DP_PANEL_MODE_DEFAULT;
+ }
}
#endif
@@ -4650,7 +4649,10 @@ enum dp_panel_mode dp_get_panel_mode(struct dc_link *link)
}
}
- if (link->dpcd_caps.panel_mode_edp) {
+ if (link->dpcd_caps.panel_mode_edp &&
+ (link->connector_signal == SIGNAL_TYPE_EDP ||
+ (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+ link->is_internal_display))) {
return DP_PANEL_MODE_EDP;
}
@@ -4914,9 +4916,7 @@ bool dc_link_set_default_brightness_aux(struct dc_link *link)
{
uint32_t default_backlight;
- if (link &&
- (link->dpcd_sink_ext_caps.bits.hdr_aux_backlight_control == 1 ||
- link->dpcd_sink_ext_caps.bits.sdr_aux_backlight_control == 1)) {
+ if (link && link->dpcd_sink_ext_caps.bits.oled == 1) {
if (!dc_link_read_default_bl_aux(link, &default_backlight))
default_backlight = 150000;
// if < 5 nits or > 5000, it might be wrong readback
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index a6a67244a322..1596f6b7fed7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1062,7 +1062,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
* so use only 30 bpp on DCE_VERSION_11_0. Testing with DCE 11.2 and 8.3
* did not show such problems, so this seems to be the exception.
*/
- if (plane_state->ctx->dce_version != DCE_VERSION_11_0)
+ if (plane_state->ctx->dce_version > DCE_VERSION_11_0)
pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_36BPP;
else
pipe_ctx->plane_res.scl_data.lb_params.depth = LB_PIXEL_DEPTH_30BPP;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 45640f1c26c4..8dcea8ff5c5a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -354,10 +354,10 @@ enum dcn_pwr_state {
};
#if defined(CONFIG_DRM_AMD_DC_DCN)
-enum dcn_z9_support_state {
- DCN_Z9_SUPPORT_UNKNOWN,
- DCN_Z9_SUPPORT_ALLOW,
- DCN_Z9_SUPPORT_DISALLOW,
+enum dcn_zstate_support_state {
+ DCN_ZSTATE_SUPPORT_UNKNOWN,
+ DCN_ZSTATE_SUPPORT_ALLOW,
+ DCN_ZSTATE_SUPPORT_DISALLOW,
};
#endif
/*
@@ -378,7 +378,7 @@ struct dc_clocks {
int dramclk_khz;
bool p_state_change_support;
#if defined(CONFIG_DRM_AMD_DC_DCN)
- enum dcn_z9_support_state z9_support;
+ enum dcn_zstate_support_state zstate_support;
bool dtbclk_en;
#endif
enum dcn_pwr_state pwr_state;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index df6539e4c730..0464a8f3db3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -636,6 +636,7 @@ struct dce_hwseq_registers {
uint32_t ODM_MEM_PWR_CTRL3;
uint32_t DMU_MEM_PWR_CNTL;
uint32_t MMHUBBUB_MEM_PWR_CNTL;
+ uint32_t DCHUBBUB_ARB_HOSTVM_CNTL;
};
/* set field name */
#define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -1110,7 +1111,8 @@ struct dce_hwseq_registers {
type DOMAIN_POWER_FORCEON;\
type DOMAIN_POWER_GATE;\
type DOMAIN_PGFSM_PWR_STATUS;\
- type HPO_HDMISTREAMCLK_G_GATE_DIS;
+ type HPO_HDMISTREAMCLK_G_GATE_DIS;\
+ type DISABLE_HOSTVM_FORCE_ALLOW_PSTATE;
struct dce_hwseq_shift {
HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index 673b93f4fea5..cb9767ddf93d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -217,6 +217,8 @@ static void dpp1_dscl_set_lb(
const struct line_buffer_params *lb_params,
enum lb_memory_config mem_size_config)
{
+ uint32_t max_partitions = 63; /* Currently hardcoded on all ASICs before DCN 3.2 */
+
/* LB */
if (dpp->base.caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT) {
/* DSCL caps: pixel data processed in fixed format */
@@ -239,9 +241,12 @@ static void dpp1_dscl_set_lb(
LB_DATA_FORMAT__ALPHA_EN, lb_params->alpha_en); /* Alpha enable */
}
+ if (dpp->base.caps->max_lb_partitions == 31)
+ max_partitions = 31;
+
REG_SET_2(LB_MEMORY_CTRL, 0,
MEMORY_CONFIG, mem_size_config,
- LB_MAX_PARTITIONS, 63);
+ LB_MAX_PARTITIONS, max_partitions);
}
static const uint16_t *dpp1_dscl_get_filter_coeffs_64p(int taps, struct fixed31_32 ratio)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 1b05a37b674d..b173fa3653b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -2093,8 +2093,10 @@ int dcn20_populate_dml_pipes_from_context(
- timing->v_border_bottom;
pipes[pipe_cnt].pipe.dest.htotal = timing->h_total;
pipes[pipe_cnt].pipe.dest.vtotal = v_total;
- pipes[pipe_cnt].pipe.dest.hactive = timing->h_addressable;
- pipes[pipe_cnt].pipe.dest.vactive = timing->v_addressable;
+ pipes[pipe_cnt].pipe.dest.hactive =
+ timing->h_addressable + timing->h_border_left + timing->h_border_right;
+ pipes[pipe_cnt].pipe.dest.vactive =
+ timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
pipes[pipe_cnt].pipe.dest.interlaced = timing->flags.INTERLACE;
pipes[pipe_cnt].pipe.dest.pixel_rate_mhz = timing->pix_clk_100hz/10000.0;
if (timing->timing_3d_format == TIMING_3D_FORMAT_HW_FRAME_PACKING)
@@ -3079,6 +3081,37 @@ static bool is_dtbclk_required(struct dc *dc, struct dc_state *context)
return false;
}
+static enum dcn_zstate_support_state decide_zstate_support(struct dc *dc, struct dc_state *context)
+{
+ int plane_count;
+ int i;
+
+ plane_count = 0;
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ if (context->res_ctx.pipe_ctx[i].plane_state)
+ plane_count++;
+ }
+
+ /*
+ * Zstate is allowed in following scenarios:
+ * 1. Single eDP with PSR enabled
+ * 2. 0 planes (No memory requests)
+ * 3. Single eDP without PSR but > 5ms stutter period
+ */
+ if (plane_count == 0)
+ return DCN_ZSTATE_SUPPORT_ALLOW;
+ else if (context->stream_count == 1 && context->streams[0]->signal == SIGNAL_TYPE_EDP) {
+ struct dc_link *link = context->streams[0]->sink->link;
+
+ if ((link->link_index == 0 && link->psr_settings.psr_feature_enabled)
+ || context->bw_ctx.dml.vba.StutterPeriod > 5000.0)
+ return DCN_ZSTATE_SUPPORT_ALLOW;
+ else
+ return DCN_ZSTATE_SUPPORT_DISALLOW;
+ } else
+ return DCN_ZSTATE_SUPPORT_DISALLOW;
+}
+
void dcn20_calculate_dlg_params(
struct dc *dc, struct dc_state *context,
display_e2e_pipe_params_st *pipes,
@@ -3086,7 +3119,6 @@ void dcn20_calculate_dlg_params(
int vlevel)
{
int i, pipe_idx;
- int plane_count;
/* Writeback MCIF_WB arbitration parameters */
dc->res_pool->funcs->set_mcif_arb_params(dc, context, pipes, pipe_cnt);
@@ -3102,17 +3134,7 @@ void dcn20_calculate_dlg_params(
!= dm_dram_clock_change_unsupported;
context->bw_ctx.bw.dcn.clk.dppclk_khz = 0;
- context->bw_ctx.bw.dcn.clk.z9_support = (context->bw_ctx.dml.vba.StutterPeriod > 5000.0) ?
- DCN_Z9_SUPPORT_ALLOW : DCN_Z9_SUPPORT_DISALLOW;
-
- plane_count = 0;
- for (i = 0; i < dc->res_pool->pipe_count; i++) {
- if (context->res_ctx.pipe_ctx[i].plane_state)
- plane_count++;
- }
-
- if (plane_count == 0)
- context->bw_ctx.bw.dcn.clk.z9_support = DCN_Z9_SUPPORT_ALLOW;
+ context->bw_ctx.bw.dcn.clk.zstate_support = decide_zstate_support(dc, context);
context->bw_ctx.bw.dcn.clk.dtbclk_en = is_dtbclk_required(dc, context);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index f3d98e3ba624..bf0a198eae15 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -109,6 +109,7 @@ struct _vcs_dpi_ip_params_st dcn2_1_ip = {
.max_page_table_levels = 4,
.pte_chunk_size_kbytes = 2,
.meta_chunk_size_kbytes = 2,
+ .min_meta_chunk_size_bytes = 256,
.writeback_chunk_size_kbytes = 2,
.line_buffer_size_bits = 789504,
.is_line_buffer_bpp_fixed = 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
index 2140b75540cf..23a52d47e61c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.c
@@ -383,13 +383,6 @@ bool dpp3_get_optimal_number_of_taps(
int min_taps_y, min_taps_c;
enum lb_memory_config lb_config;
- /* Some ASICs does not support FP16 scaling, so we reject modes require this*/
- if (scl_data->viewport.width != scl_data->h_active &&
- scl_data->viewport.height != scl_data->v_active &&
- dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
- scl_data->format == PIXEL_FORMAT_FP16)
- return false;
-
if (scl_data->viewport.width > scl_data->h_active &&
dpp->ctx->dc->debug.max_downscale_src_width != 0 &&
scl_data->viewport.width > dpp->ctx->dc->debug.max_downscale_src_width)
@@ -1440,15 +1433,6 @@ bool dpp3_construct(
dpp->tf_shift = tf_shift;
dpp->tf_mask = tf_mask;
- dpp->lb_pixel_depth_supported =
- LB_PIXEL_DEPTH_18BPP |
- LB_PIXEL_DEPTH_24BPP |
- LB_PIXEL_DEPTH_30BPP |
- LB_PIXEL_DEPTH_36BPP;
-
- dpp->lb_bits_per_entry = LB_BITS_PER_ENTRY;
- dpp->lb_memory_size = LB_TOTAL_NUMBER_OF_ENTRIES; /*0x1404*/
-
return true;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
index 3fa86cd090a0..ac644ae6b9f2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dpp.h
@@ -154,6 +154,7 @@
SRI(COLOR_KEYER_BLUE, CNVC_CFG, id), \
SRI(CURSOR_CONTROL, CURSOR0_, id),\
SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\
+ SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
SRI(DSCL_MEM_PWR_CTRL, DSCL, id)
#define DPP_REG_LIST_DCN30(id)\
@@ -163,8 +164,6 @@
SRI(CM_SHAPER_LUT_DATA, CM, id),\
SRI(CM_MEM_PWR_CTRL2, CM, id), \
SRI(CM_MEM_PWR_STATUS2, CM, id), \
- SRI(DSCL_MEM_PWR_STATUS, DSCL, id), \
- SRI(DSCL_MEM_PWR_CTRL, DSCL, id), \
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_B, CM, id),\
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_G, CM, id),\
SRI(CM_BLNDGAM_RAMA_START_SLOPE_CNTL_R, CM, id),\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
index 16a75ba0ca82..7d3ff5d44402 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn302/dcn302_resource.c
@@ -1398,11 +1398,18 @@ void dcn302_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
dcn3_02_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
dcn3_02_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz;
dcn3_02_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz;
- dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[0].dtbclk_mhz;
+ /* Populate from bw_params for DTBCLK, SOCCLK */
+ if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+ dcn3_02_soc.clock_limits[i].dtbclk_mhz = dcn3_02_soc.clock_limits[i-1].dtbclk_mhz;
+ else
+ dcn3_02_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+ if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+ dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[i-1].socclk_mhz;
+ else
+ dcn3_02_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
/* These clocks cannot come from bw_params, always fill from dcn3_02_soc[1] */
- /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+ /* FCLK, PHYCLK_D18, DSCCLK */
dcn3_02_soc.clock_limits[i].phyclk_d18_mhz = dcn3_02_soc.clock_limits[0].phyclk_d18_mhz;
- dcn3_02_soc.clock_limits[i].socclk_mhz = dcn3_02_soc.clock_limits[0].socclk_mhz;
dcn3_02_soc.clock_limits[i].dscclk_mhz = dcn3_02_soc.clock_limits[0].dscclk_mhz;
}
/* re-init DML with updated bb */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index 34b89464ae02..833ab13fa834 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -1326,11 +1326,18 @@ void dcn303_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
dcn3_03_soc.clock_limits[i].dispclk_mhz = max_dispclk_mhz;
dcn3_03_soc.clock_limits[i].dppclk_mhz = max_dppclk_mhz;
dcn3_03_soc.clock_limits[i].phyclk_mhz = max_phyclk_mhz;
- dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[0].dtbclk_mhz;
+ /* Populate from bw_params for DTBCLK, SOCCLK */
+ if (!bw_params->clk_table.entries[i].dtbclk_mhz && i > 0)
+ dcn3_03_soc.clock_limits[i].dtbclk_mhz = dcn3_03_soc.clock_limits[i-1].dtbclk_mhz;
+ else
+ dcn3_03_soc.clock_limits[i].dtbclk_mhz = bw_params->clk_table.entries[i].dtbclk_mhz;
+ if (!bw_params->clk_table.entries[i].socclk_mhz && i > 0)
+ dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[i-1].socclk_mhz;
+ else
+ dcn3_03_soc.clock_limits[i].socclk_mhz = bw_params->clk_table.entries[i].socclk_mhz;
/* These clocks cannot come from bw_params, always fill from dcn3_03_soc[1] */
- /* FCLK, PHYCLK_D18, SOCCLK, DSCCLK */
+ /* FCLK, PHYCLK_D18, DSCCLK */
dcn3_03_soc.clock_limits[i].phyclk_d18_mhz = dcn3_03_soc.clock_limits[0].phyclk_d18_mhz;
- dcn3_03_soc.clock_limits[i].socclk_mhz = dcn3_03_soc.clock_limits[0].socclk_mhz;
dcn3_03_soc.clock_limits[i].dscclk_mhz = dcn3_03_soc.clock_limits[0].dscclk_mhz;
}
/* re-init DML with updated bb */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
index 836864a5a5dc..6ac6faf0c533 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.c
@@ -47,6 +47,7 @@
#include "dce/dmub_outbox.h"
#include "dc_link_dp.h"
#include "inc/link_dpcd.h"
+#include "dcn10/dcn10_hw_sequencer.h"
#define DC_LOGGER_INIT(logger)
@@ -594,3 +595,20 @@ bool dcn31_is_abm_supported(struct dc *dc,
}
return false;
}
+
+static void apply_riommu_invalidation_wa(struct dc *dc)
+{
+ struct dce_hwseq *hws = dc->hwseq;
+
+ if (!hws->wa.early_riommu_invalidation)
+ return;
+
+ REG_UPDATE(DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, 0);
+}
+
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context)
+{
+ dcn10_init_pipes(dc, context);
+ apply_riommu_invalidation_wa(dc);
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
index ff72f0fdd5be..40dfebe78fdd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_hwseq.h
@@ -52,5 +52,6 @@ void dcn31_reset_hw_ctx_wrap(
struct dc_state *context);
bool dcn31_is_abm_supported(struct dc *dc,
struct dc_state *context, struct dc_stream_state *stream);
+void dcn31_init_pipes(struct dc *dc, struct dc_state *context);
#endif /* __DC_HWSS_DCN31_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
index e3048f8827d2..aaf2dbd095fe 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_init.c
@@ -93,7 +93,6 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
.set_flip_control_gsl = dcn20_set_flip_control_gsl,
.get_vupdate_offset_from_vsync = dcn10_get_vupdate_offset_from_vsync,
.calc_vupdate_position = dcn10_calc_vupdate_position,
- .apply_idle_power_optimizations = dcn30_apply_idle_power_optimizations,
.set_backlight_level = dcn21_set_backlight_level,
.set_abm_immediate_disable = dcn21_set_abm_immediate_disable,
.set_pipe = dcn21_set_pipe,
@@ -104,7 +103,7 @@ static const struct hw_sequencer_funcs dcn31_funcs = {
};
static const struct hwseq_private_funcs dcn31_private_funcs = {
- .init_pipes = dcn10_init_pipes,
+ .init_pipes = dcn31_init_pipes,
.update_plane_addr = dcn20_update_plane_addr,
.plane_atomic_disconnect = dcn10_plane_atomic_disconnect,
.update_mpcc = dcn20_update_mpcc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
index c67bc9544f5d..38c010afade1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_resource.c
@@ -220,6 +220,7 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_1_soc = {
.sr_exit_z8_time_us = 402.0,
.sr_enter_plus_exit_z8_time_us = 520.0,
.writeback_latency_us = 12.0,
+ .dram_channel_width_bytes = 4,
.round_trip_ping_latency_dcfclk_cycles = 106,
.urgent_latency_pixel_data_only_us = 4.0,
.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
@@ -741,6 +742,7 @@ static const struct dccg_mask dccg_mask = {
#define HWSEQ_DCN31_REG_LIST()\
SR(DCHUBBUB_GLOBAL_TIMER_CNTL), \
+ SR(DCHUBBUB_ARB_HOSTVM_CNTL), \
SR(DIO_MEM_PWR_CTRL), \
SR(ODM_MEM_PWR_CTRL3), \
SR(DMU_MEM_PWR_CNTL), \
@@ -801,6 +803,7 @@ static const struct dce_hwseq_registers hwseq_reg = {
#define HWSEQ_DCN31_MASK_SH_LIST(mask_sh)\
HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
+ HWS_SF(, DCHUBBUB_ARB_HOSTVM_CNTL, DISABLE_HOSTVM_FORCE_ALLOW_PSTATE, mask_sh), \
HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
HWS_SF(, DOMAIN0_PG_CONFIG, DOMAIN_POWER_GATE, mask_sh), \
HWS_SF(, DOMAIN1_PG_CONFIG, DOMAIN_POWER_FORCEON, mask_sh), \
@@ -1299,6 +1302,7 @@ static struct dce_hwseq *dcn31_hwseq_create(
hws->regs = &hwseq_reg;
hws->shifts = &hwseq_shift;
hws->masks = &hwseq_mask;
+ hws->wa.early_riommu_invalidation = true;
}
return hws;
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index c26e742e8137..6655bb99fdfd 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -841,6 +841,9 @@ static bool CalculatePrefetchSchedule(
else
*DestinationLinesForPrefetch = dst_y_prefetch_equ;
+ // Limit to prevent overflow in DST_Y_PREFETCH register
+ *DestinationLinesForPrefetch = dml_min(*DestinationLinesForPrefetch, 63.75);
+
dml_print("DML: VStartup: %d\n", VStartup);
dml_print("DML: TCalc: %f\n", TCalc);
dml_print("DML: TWait: %f\n", TWait);
@@ -4889,7 +4892,7 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
}
} while ((locals->PrefetchSupported[i][j] != true || locals->VRatioInPrefetchSupported[i][j] != true)
&& (mode_lib->vba.NextMaxVStartup != mode_lib->vba.MaxMaxVStartup[0][0]
- || mode_lib->vba.NextPrefetchMode < mode_lib->vba.MaxPrefetchMode));
+ || mode_lib->vba.NextPrefetchMode <= mode_lib->vba.MaxPrefetchMode));
if (locals->PrefetchSupported[i][j] == true && locals->VRatioInPrefetchSupported[i][j] == true) {
mode_lib->vba.BandwidthAvailableForImmediateFlip = locals->ReturnBWPerState[i][0];
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
index 2a0db2b03047..9ac9d5e8df8b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/transform.h
@@ -289,6 +289,9 @@ struct dpp_caps {
/* DSCL processing pixel data in fixed or float format */
enum dscl_data_processing_format dscl_data_proc_format;
+ /* max LB partitions */
+ unsigned int max_lb_partitions;
+
/* Calculates the number of partitions in the line buffer.
* The implementation of this function is overloaded for
* different versions of DSCL LB.
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
index f7f7e4fff0c2..082549f75978 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer_private.h
@@ -41,6 +41,7 @@ struct dce_hwseq_wa {
bool DEGVIDCN10_254;
bool DEGVIDCN21;
bool disallow_self_refresh_during_multi_plane_transition;
+ bool early_riommu_invalidation;
};
struct hwseq_wa_state {
diff --git a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
index 610266088ff1..35fa0d8e92dd 100644
--- a/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
+++ b/drivers/gpu/drm/amd/pm/inc/aldebaran_ppsmc.h
@@ -101,7 +101,8 @@
#define PPSMC_MSG_SetSystemVirtualSTBtoDramAddrLow 0x41
#define PPSMC_MSG_GfxDriverResetRecovery 0x42
-#define PPSMC_Message_Count 0x43
+#define PPSMC_MSG_BoardPowerCalibration 0x43
+#define PPSMC_Message_Count 0x44
//PPSMC Reset Types
#define PPSMC_RESET_TYPE_WARM_RESET 0x00
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_types.h b/drivers/gpu/drm/amd/pm/inc/smu_types.h
index 89a16dcd0fff..1d3765b873df 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_types.h
@@ -225,7 +225,8 @@
__SMU_DUMMY_MAP(DisableDeterminism), \
__SMU_DUMMY_MAP(SetUclkDpmMode), \
__SMU_DUMMY_MAP(LightSBR), \
- __SMU_DUMMY_MAP(GfxDriverResetRecovery),
+ __SMU_DUMMY_MAP(GfxDriverResetRecovery), \
+ __SMU_DUMMY_MAP(BoardPowerCalibration),
#undef __SMU_DUMMY_MAP
#define __SMU_DUMMY_MAP(type) SMU_MSG_##type
diff --git a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
index 1962a5877191..f61b5c914a3d 100644
--- a/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/pm/inc/smu_v11_0.h
@@ -34,7 +34,7 @@
#define SMU11_DRIVER_IF_VERSION_Navy_Flounder 0xE
#define SMU11_DRIVER_IF_VERSION_VANGOGH 0x03
#define SMU11_DRIVER_IF_VERSION_Dimgrey_Cavefish 0xF
-#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0x9
+#define SMU11_DRIVER_IF_VERSION_Beige_Goby 0xD
/* MP Apertures */
#define MP0_Public 0x03800000
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index 9316a726195c..cb5485cf243f 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -134,6 +134,7 @@ static const struct cmn2asic_msg_mapping aldebaran_message_map[SMU_MSG_MAX_COUNT
MSG_MAP(DisableDeterminism, PPSMC_MSG_DisableDeterminism, 0),
MSG_MAP(SetUclkDpmMode, PPSMC_MSG_SetUclkDpmMode, 0),
MSG_MAP(GfxDriverResetRecovery, PPSMC_MSG_GfxDriverResetRecovery, 0),
+ MSG_MAP(BoardPowerCalibration, PPSMC_MSG_BoardPowerCalibration, 0),
};
static const struct cmn2asic_mapping aldebaran_clk_map[SMU_CLK_COUNT] = {
@@ -440,6 +441,39 @@ static int aldebaran_setup_pptable(struct smu_context *smu)
return ret;
}
+static bool aldebaran_is_primary(struct smu_context *smu)
+{
+ struct amdgpu_device *adev = smu->adev;
+
+ if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
+ return adev->smuio.funcs->get_die_id(adev) == 0;
+
+ return true;
+}
+
+static int aldebaran_run_board_btc(struct smu_context *smu)
+{
+ u32 smu_version;
+ int ret;
+
+ if (!aldebaran_is_primary(smu))
+ return 0;
+
+ ret = smu_cmn_get_smc_version(smu, NULL, &smu_version);
+ if (ret) {
+ dev_err(smu->adev->dev, "Failed to get smu version!\n");
+ return ret;
+ }
+ if (smu_version <= 0x00441d00)
+ return 0;
+
+ ret = smu_cmn_send_smc_msg(smu, SMU_MSG_BoardPowerCalibration, NULL);
+ if (ret)
+ dev_err(smu->adev->dev, "Board power calibration failed!\n");
+
+ return ret;
+}
+
static int aldebaran_run_btc(struct smu_context *smu)
{
int ret;
@@ -447,6 +481,8 @@ static int aldebaran_run_btc(struct smu_context *smu)
ret = smu_cmn_send_smc_msg(smu, SMU_MSG_RunDcBtc, NULL);
if (ret)
dev_err(smu->adev->dev, "RunDcBtc failed!\n");
+ else
+ ret = aldebaran_run_board_btc(smu);
return ret;
}
@@ -524,16 +560,6 @@ static int aldebaran_freqs_in_same_level(int32_t frequency1,
return (abs(frequency1 - frequency2) <= EPSILON);
}
-static bool aldebaran_is_primary(struct smu_context *smu)
-{
- struct amdgpu_device *adev = smu->adev;
-
- if (adev->smuio.funcs && adev->smuio.funcs->get_die_id)
- return adev->smuio.funcs->get_die_id(adev) == 0;
-
- return true;
-}
-
static int aldebaran_get_smu_metrics_data(struct smu_context *smu,
MetricsMember_t member,
uint32_t *value)
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 98ae00661656..f454e0424086 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -834,6 +834,9 @@ long drm_ioctl(struct file *filp,
if (drm_dev_is_unplugged(dev))
return -ENODEV;
+ if (DRM_IOCTL_TYPE(cmd) != DRM_IOCTL_BASE)
+ return -ENOTTY;
+
is_driver_ioctl = nr >= DRM_COMMAND_BASE && nr < DRM_COMMAND_END;
if (is_driver_ioctl) {
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
index 5b6922e28ef2..aa667fa71158 100644
--- a/drivers/gpu/drm/i915/display/intel_bios.c
+++ b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -2166,7 +2166,8 @@ static void
init_vbt_missing_defaults(struct drm_i915_private *i915)
{
enum port port;
- int ports = PORT_A | PORT_B | PORT_C | PORT_D | PORT_E | PORT_F;
+ int ports = BIT(PORT_A) | BIT(PORT_B) | BIT(PORT_C) |
+ BIT(PORT_D) | BIT(PORT_E) | BIT(PORT_F);
if (!HAS_DDI(i915) && !IS_CHERRYVIEW(i915))
return;
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 3bad4e00f7be..2d5d21740c25 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -11361,13 +11361,19 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
intel_ddi_init(dev_priv, PORT_B);
intel_ddi_init(dev_priv, PORT_C);
vlv_dsi_init(dev_priv);
- } else if (DISPLAY_VER(dev_priv) >= 9) {
+ } else if (DISPLAY_VER(dev_priv) == 10) {
intel_ddi_init(dev_priv, PORT_A);
intel_ddi_init(dev_priv, PORT_B);
intel_ddi_init(dev_priv, PORT_C);
intel_ddi_init(dev_priv, PORT_D);
intel_ddi_init(dev_priv, PORT_E);
intel_ddi_init(dev_priv, PORT_F);
+ } else if (DISPLAY_VER(dev_priv) >= 9) {
+ intel_ddi_init(dev_priv, PORT_A);
+ intel_ddi_init(dev_priv, PORT_B);
+ intel_ddi_init(dev_priv, PORT_C);
+ intel_ddi_init(dev_priv, PORT_D);
+ intel_ddi_init(dev_priv, PORT_E);
} else if (HAS_DDI(dev_priv)) {
u32 found;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index a8abc9af5ff4..4a6419d7be93 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -25,10 +25,8 @@
#include "i915_gem_clflush.h"
#include "i915_gem_context.h"
#include "i915_gem_ioctls.h"
-#include "i915_sw_fence_work.h"
#include "i915_trace.h"
#include "i915_user_extensions.h"
-#include "i915_memcpy.h"
struct eb_vma {
struct i915_vma *vma;
@@ -1456,6 +1454,10 @@ static u32 *reloc_gpu(struct i915_execbuffer *eb,
int err;
struct intel_engine_cs *engine = eb->engine;
+ /* If we need to copy for the cmdparser, we will stall anyway */
+ if (eb_use_cmdparser(eb))
+ return ERR_PTR(-EWOULDBLOCK);
+
if (!reloc_can_use_engine(engine)) {
engine = engine->gt->engine_class[COPY_ENGINE_CLASS][0];
if (!engine)
@@ -2372,217 +2374,6 @@ shadow_batch_pin(struct i915_execbuffer *eb,
return vma;
}
-struct eb_parse_work {
- struct dma_fence_work base;
- struct intel_engine_cs *engine;
- struct i915_vma *batch;
- struct i915_vma *shadow;
- struct i915_vma *trampoline;
- unsigned long batch_offset;
- unsigned long batch_length;
- unsigned long *jump_whitelist;
- const void *batch_map;
- void *shadow_map;
-};
-
-static int __eb_parse(struct dma_fence_work *work)
-{
- struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
- int ret;
- bool cookie;
-
- cookie = dma_fence_begin_signalling();
- ret = intel_engine_cmd_parser(pw->engine,
- pw->batch,
- pw->batch_offset,
- pw->batch_length,
- pw->shadow,
- pw->jump_whitelist,
- pw->shadow_map,
- pw->batch_map);
- dma_fence_end_signalling(cookie);
-
- return ret;
-}
-
-static void __eb_parse_release(struct dma_fence_work *work)
-{
- struct eb_parse_work *pw = container_of(work, typeof(*pw), base);
-
- if (!IS_ERR_OR_NULL(pw->jump_whitelist))
- kfree(pw->jump_whitelist);
-
- if (pw->batch_map)
- i915_gem_object_unpin_map(pw->batch->obj);
- else
- i915_gem_object_unpin_pages(pw->batch->obj);
-
- i915_gem_object_unpin_map(pw->shadow->obj);
-
- if (pw->trampoline)
- i915_active_release(&pw->trampoline->active);
- i915_active_release(&pw->shadow->active);
- i915_active_release(&pw->batch->active);
-}
-
-static const struct dma_fence_work_ops eb_parse_ops = {
- .name = "eb_parse",
- .work = __eb_parse,
- .release = __eb_parse_release,
-};
-
-static inline int
-__parser_mark_active(struct i915_vma *vma,
- struct intel_timeline *tl,
- struct dma_fence *fence)
-{
- struct intel_gt_buffer_pool_node *node = vma->private;
-
- return i915_active_ref(&node->active, tl->fence_context, fence);
-}
-
-static int
-parser_mark_active(struct eb_parse_work *pw, struct intel_timeline *tl)
-{
- int err;
-
- mutex_lock(&tl->mutex);
-
- err = __parser_mark_active(pw->shadow, tl, &pw->base.dma);
- if (err)
- goto unlock;
-
- if (pw->trampoline) {
- err = __parser_mark_active(pw->trampoline, tl, &pw->base.dma);
- if (err)
- goto unlock;
- }
-
-unlock:
- mutex_unlock(&tl->mutex);
- return err;
-}
-
-static int eb_parse_pipeline(struct i915_execbuffer *eb,
- struct i915_vma *shadow,
- struct i915_vma *trampoline)
-{
- struct eb_parse_work *pw;
- struct drm_i915_gem_object *batch = eb->batch->vma->obj;
- bool needs_clflush;
- int err;
-
- GEM_BUG_ON(overflows_type(eb->batch_start_offset, pw->batch_offset));
- GEM_BUG_ON(overflows_type(eb->batch_len, pw->batch_length));
-
- pw = kzalloc(sizeof(*pw), GFP_KERNEL);
- if (!pw)
- return -ENOMEM;
-
- err = i915_active_acquire(&eb->batch->vma->active);
- if (err)
- goto err_free;
-
- err = i915_active_acquire(&shadow->active);
- if (err)
- goto err_batch;
-
- if (trampoline) {
- err = i915_active_acquire(&trampoline->active);
- if (err)
- goto err_shadow;
- }
-
- pw->shadow_map = i915_gem_object_pin_map(shadow->obj, I915_MAP_WB);
- if (IS_ERR(pw->shadow_map)) {
- err = PTR_ERR(pw->shadow_map);
- goto err_trampoline;
- }
-
- needs_clflush =
- !(batch->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
- pw->batch_map = ERR_PTR(-ENODEV);
- if (needs_clflush && i915_has_memcpy_from_wc())
- pw->batch_map = i915_gem_object_pin_map(batch, I915_MAP_WC);
-
- if (IS_ERR(pw->batch_map)) {
- err = i915_gem_object_pin_pages(batch);
- if (err)
- goto err_unmap_shadow;
- pw->batch_map = NULL;
- }
-
- pw->jump_whitelist =
- intel_engine_cmd_parser_alloc_jump_whitelist(eb->batch_len,
- trampoline);
- if (IS_ERR(pw->jump_whitelist)) {
- err = PTR_ERR(pw->jump_whitelist);
- goto err_unmap_batch;
- }
-
- dma_fence_work_init(&pw->base, &eb_parse_ops);
-
- pw->engine = eb->engine;
- pw->batch = eb->batch->vma;
- pw->batch_offset = eb->batch_start_offset;
- pw->batch_length = eb->batch_len;
- pw->shadow = shadow;
- pw->trampoline = trampoline;
-
- /* Mark active refs early for this worker, in case we get interrupted */
- err = parser_mark_active(pw, eb->context->timeline);
- if (err)
- goto err_commit;
-
- err = dma_resv_reserve_shared(pw->batch->resv, 1);
- if (err)
- goto err_commit;
-
- err = dma_resv_reserve_shared(shadow->resv, 1);
- if (err)
- goto err_commit;
-
- /* Wait for all writes (and relocs) into the batch to complete */
- err = i915_sw_fence_await_reservation(&pw->base.chain,
- pw->batch->resv, NULL, false,
- 0, I915_FENCE_GFP);
- if (err < 0)
- goto err_commit;
-
- /* Keep the batch alive and unwritten as we parse */
- dma_resv_add_shared_fence(pw->batch->resv, &pw->base.dma);
-
- /* Force execution to wait for completion of the parser */
- dma_resv_add_excl_fence(shadow->resv, &pw->base.dma);
-
- dma_fence_work_commit_imm(&pw->base);
- return 0;
-
-err_commit:
- i915_sw_fence_set_error_once(&pw->base.chain, err);
- dma_fence_work_commit_imm(&pw->base);
- return err;
-
-err_unmap_batch:
- if (pw->batch_map)
- i915_gem_object_unpin_map(batch);
- else
- i915_gem_object_unpin_pages(batch);
-err_unmap_shadow:
- i915_gem_object_unpin_map(shadow->obj);
-err_trampoline:
- if (trampoline)
- i915_active_release(&trampoline->active);
-err_shadow:
- i915_active_release(&shadow->active);
-err_batch:
- i915_active_release(&eb->batch->vma->active);
-err_free:
- kfree(pw);
- return err;
-}
-
static struct i915_vma *eb_dispatch_secure(struct i915_execbuffer *eb, struct i915_vma *vma)
{
/*
@@ -2672,7 +2463,15 @@ static int eb_parse(struct i915_execbuffer *eb)
goto err_trampoline;
}
- err = eb_parse_pipeline(eb, shadow, trampoline);
+ err = dma_resv_reserve_shared(shadow->resv, 1);
+ if (err)
+ goto err_trampoline;
+
+ err = intel_engine_cmd_parser(eb->engine,
+ eb->batch->vma,
+ eb->batch_start_offset,
+ eb->batch_len,
+ shadow, trampoline);
if (err)
goto err_unpin_batch;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
index 4df505e4c53a..16162fc2782d 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_execbuffer.c
@@ -125,6 +125,10 @@ static int igt_gpu_reloc(void *arg)
intel_gt_pm_get(&eb.i915->gt);
for_each_uabi_engine(eb.engine, eb.i915) {
+ if (intel_engine_requires_cmd_parser(eb.engine) ||
+ intel_engine_using_cmd_parser(eb.engine))
+ continue;
+
reloc_cache_init(&eb.reloc_cache, eb.i915);
memset(map, POISON_INUSE, 4096);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 98eb48c24c46..06024d321a1a 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1977,6 +1977,21 @@ static int elsp_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
if (drm_WARN_ON(&i915->drm, !engine))
return -EINVAL;
+ /*
+ * Due to d3_entered is used to indicate skipping PPGTT invalidation on
+ * vGPU reset, it's set on D0->D3 on PCI config write, and cleared after
+ * vGPU reset if in resuming.
+ * In S0ix exit, the device power state also transite from D3 to D0 as
+ * S3 resume, but no vGPU reset (triggered by QEMU devic model). After
+ * S0ix exit, all engines continue to work. However the d3_entered
+ * remains set which will break next vGPU reset logic (miss the expected
+ * PPGTT invalidation).
+ * Engines can only work in D0. Thus the 1st elsp write gives GVT a
+ * chance to clear d3_entered.
+ */
+ if (vgpu->d3_entered)
+ vgpu->d3_entered = false;
+
execlist = &vgpu->submission.execlist[engine->id];
execlist->elsp_dwords.data[3 - execlist->elsp_dwords.index] = data;
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 3992c25a191d..a3b4d99d64b9 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -1145,19 +1145,41 @@ find_reg(const struct intel_engine_cs *engine, u32 addr)
static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
struct drm_i915_gem_object *src_obj,
unsigned long offset, unsigned long length,
- void *dst, const void *src)
+ bool *needs_clflush_after)
{
- bool needs_clflush =
- !(src_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ);
-
- if (src) {
- GEM_BUG_ON(!needs_clflush);
- i915_unaligned_memcpy_from_wc(dst, src + offset, length);
- } else {
- struct scatterlist *sg;
+ unsigned int src_needs_clflush;
+ unsigned int dst_needs_clflush;
+ void *dst, *src;
+ int ret;
+
+ ret = i915_gem_object_prepare_write(dst_obj, &dst_needs_clflush);
+ if (ret)
+ return ERR_PTR(ret);
+
+ dst = i915_gem_object_pin_map(dst_obj, I915_MAP_WB);
+ i915_gem_object_finish_access(dst_obj);
+ if (IS_ERR(dst))
+ return dst;
+
+ ret = i915_gem_object_prepare_read(src_obj, &src_needs_clflush);
+ if (ret) {
+ i915_gem_object_unpin_map(dst_obj);
+ return ERR_PTR(ret);
+ }
+
+ src = ERR_PTR(-ENODEV);
+ if (src_needs_clflush && i915_has_memcpy_from_wc()) {
+ src = i915_gem_object_pin_map(src_obj, I915_MAP_WC);
+ if (!IS_ERR(src)) {
+ i915_unaligned_memcpy_from_wc(dst,
+ src + offset,
+ length);
+ i915_gem_object_unpin_map(src_obj);
+ }
+ }
+ if (IS_ERR(src)) {
+ unsigned long x, n, remain;
void *ptr;
- unsigned int x, sg_ofs;
- unsigned long remain;
/*
* We can avoid clflushing partial cachelines before the write
@@ -1168,40 +1190,34 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
* validate up to the end of the batch.
*/
remain = length;
- if (!(dst_obj->cache_coherent & I915_BO_CACHE_COHERENT_FOR_READ))
+ if (dst_needs_clflush & CLFLUSH_BEFORE)
remain = round_up(remain,
boot_cpu_data.x86_clflush_size);
ptr = dst;
x = offset_in_page(offset);
- sg = i915_gem_object_get_sg(src_obj, offset >> PAGE_SHIFT, &sg_ofs, false);
-
- while (remain) {
- unsigned long sg_max = sg->length >> PAGE_SHIFT;
-
- for (; remain && sg_ofs < sg_max; sg_ofs++) {
- unsigned long len = min(remain, PAGE_SIZE - x);
- void *map;
-
- map = kmap_atomic(nth_page(sg_page(sg), sg_ofs));
- if (needs_clflush)
- drm_clflush_virt_range(map + x, len);
- memcpy(ptr, map + x, len);
- kunmap_atomic(map);
-
- ptr += len;
- remain -= len;
- x = 0;
- }
-
- sg_ofs = 0;
- sg = sg_next(sg);
+ for (n = offset >> PAGE_SHIFT; remain; n++) {
+ int len = min(remain, PAGE_SIZE - x);
+
+ src = kmap_atomic(i915_gem_object_get_page(src_obj, n));
+ if (src_needs_clflush)
+ drm_clflush_virt_range(src + x, len);
+ memcpy(ptr, src + x, len);
+ kunmap_atomic(src);
+
+ ptr += len;
+ remain -= len;
+ x = 0;
}
}
+ i915_gem_object_finish_access(src_obj);
+
memset32(dst + length, 0, (dst_obj->base.size - length) / sizeof(u32));
/* dst_obj is returned with vmap pinned */
+ *needs_clflush_after = dst_needs_clflush & CLFLUSH_AFTER;
+
return dst;
}
@@ -1360,6 +1376,9 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
if (target_cmd_index == offset)
return 0;
+ if (IS_ERR(jump_whitelist))
+ return PTR_ERR(jump_whitelist);
+
if (!test_bit(target_cmd_index, jump_whitelist)) {
DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
jump_target);
@@ -1369,28 +1388,10 @@ static int check_bbstart(u32 *cmd, u32 offset, u32 length,
return 0;
}
-/**
- * intel_engine_cmd_parser_alloc_jump_whitelist() - preallocate jump whitelist for intel_engine_cmd_parser()
- * @batch_length: length of the commands in batch_obj
- * @trampoline: Whether jump trampolines are used.
- *
- * Preallocates a jump whitelist for parsing the cmd buffer in intel_engine_cmd_parser().
- * This has to be preallocated, because the command parser runs in signaling context,
- * and may not allocate any memory.
- *
- * Return: NULL or pointer to a jump whitelist, or ERR_PTR() on failure. Use
- * IS_ERR() to check for errors. Must bre freed() with kfree().
- *
- * NULL is a valid value, meaning no allocation was required.
- */
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
- bool trampoline)
+static unsigned long *alloc_whitelist(u32 batch_length)
{
unsigned long *jmp;
- if (trampoline)
- return NULL;
-
/*
* We expect batch_length to be less than 256KiB for known users,
* i.e. we need at most an 8KiB bitmap allocation which should be
@@ -1415,9 +1416,7 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
* @batch_offset: byte offset in the batch at which execution starts
* @batch_length: length of the commands in batch_obj
* @shadow: validated copy of the batch buffer in question
- * @jump_whitelist: buffer preallocated with intel_engine_cmd_parser_alloc_jump_whitelist()
- * @shadow_map: mapping to @shadow vma
- * @batch_map: mapping to @batch vma
+ * @trampoline: true if we need to trampoline into privileged execution
*
* Parses the specified batch buffer looking for privilege violations as
* described in the overview.
@@ -1425,21 +1424,21 @@ unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
* Return: non-zero if the parser finds violations or otherwise fails; -EACCES
* if the batch appears legal but should use hardware parsing
*/
+
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
struct i915_vma *batch,
unsigned long batch_offset,
unsigned long batch_length,
struct i915_vma *shadow,
- unsigned long *jump_whitelist,
- void *shadow_map,
- const void *batch_map)
+ bool trampoline)
{
u32 *cmd, *batch_end, offset = 0;
struct drm_i915_cmd_descriptor default_desc = noop_desc;
const struct drm_i915_cmd_descriptor *desc = &default_desc;
+ bool needs_clflush_after = false;
+ unsigned long *jump_whitelist;
u64 batch_addr, shadow_addr;
int ret = 0;
- bool trampoline = !jump_whitelist;
GEM_BUG_ON(!IS_ALIGNED(batch_offset, sizeof(*cmd)));
GEM_BUG_ON(!IS_ALIGNED(batch_length, sizeof(*cmd)));
@@ -1447,8 +1446,18 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
batch->size));
GEM_BUG_ON(!batch_length);
- cmd = copy_batch(shadow->obj, batch->obj, batch_offset, batch_length,
- shadow_map, batch_map);
+ cmd = copy_batch(shadow->obj, batch->obj,
+ batch_offset, batch_length,
+ &needs_clflush_after);
+ if (IS_ERR(cmd)) {
+ DRM_DEBUG("CMD: Failed to copy batch\n");
+ return PTR_ERR(cmd);
+ }
+
+ jump_whitelist = NULL;
+ if (!trampoline)
+ /* Defer failure until attempted use */
+ jump_whitelist = alloc_whitelist(batch_length);
shadow_addr = gen8_canonical_addr(shadow->node.start);
batch_addr = gen8_canonical_addr(batch->node.start + batch_offset);
@@ -1549,6 +1558,9 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
i915_gem_object_flush_map(shadow->obj);
+ if (!IS_ERR_OR_NULL(jump_whitelist))
+ kfree(jump_whitelist);
+ i915_gem_object_unpin_map(shadow->obj);
return ret;
}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 38ff2fb89744..b30397b04529 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1906,17 +1906,12 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
int intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-unsigned long *intel_engine_cmd_parser_alloc_jump_whitelist(u32 batch_length,
- bool trampoline);
-
int intel_engine_cmd_parser(struct intel_engine_cs *engine,
struct i915_vma *batch,
unsigned long batch_offset,
unsigned long batch_length,
struct i915_vma *shadow,
- unsigned long *jump_whitelist,
- void *shadow_map,
- const void *batch_map);
+ bool trampoline);
#define I915_CMD_PARSER_TRAMPOLINE_SIZE 8
/* intel_device_info.c */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1014c71cf7f5..37aef1308573 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1426,10 +1426,8 @@ i915_request_await_execution(struct i915_request *rq,
do {
fence = *child++;
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
- i915_sw_fence_set_error_once(&rq->submit, fence->error);
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
continue;
- }
if (fence->context == rq->fence.context)
continue;
@@ -1527,10 +1525,8 @@ i915_request_await_dma_fence(struct i915_request *rq, struct dma_fence *fence)
do {
fence = *child++;
- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
- i915_sw_fence_set_error_once(&rq->submit, fence->error);
+ if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
continue;
- }
/*
* Requests on the same timeline are explicitly ordered, along
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 7eaa92fee421..e0a10f36acc1 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -325,7 +325,7 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
info->pipe_mask &= ~BIT(PIPE_C);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
}
- } else if (HAS_DISPLAY(dev_priv) && GRAPHICS_VER(dev_priv) >= 9) {
+ } else if (HAS_DISPLAY(dev_priv) && DISPLAY_VER(dev_priv) >= 9) {
u32 dfsm = intel_de_read(dev_priv, SKL_DFSM);
if (dfsm & SKL_DFSM_PIPE_A_DISABLE) {
@@ -340,7 +340,8 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
info->pipe_mask &= ~BIT(PIPE_C);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_C);
}
- if (GRAPHICS_VER(dev_priv) >= 12 &&
+
+ if (DISPLAY_VER(dev_priv) >= 12 &&
(dfsm & TGL_DFSM_PIPE_D_DISABLE)) {
info->pipe_mask &= ~BIT(PIPE_D);
info->cpu_transcoder_mask &= ~BIT(TRANSCODER_D);
@@ -352,10 +353,10 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE)
info->display.has_fbc = 0;
- if (GRAPHICS_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
+ if (DISPLAY_VER(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
info->display.has_dmc = 0;
- if (GRAPHICS_VER(dev_priv) >= 10 &&
+ if (DISPLAY_VER(dev_priv) >= 10 &&
(dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE))
info->display.has_dsc = 0;
}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index d01c4c919504..704dace895cb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -296,7 +296,7 @@ static const struct dpu_mdp_cfg sc7180_mdp[] = {
static const struct dpu_mdp_cfg sm8250_mdp[] = {
{
.name = "top_0", .id = MDP_TOP,
- .base = 0x0, .len = 0x45C,
+ .base = 0x0, .len = 0x494,
.features = 0,
.highest_bank_bit = 0x3, /* TODO: 2 for LP_DDR4 */
.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
diff --git a/drivers/gpu/drm/msm/dp/dp_catalog.c b/drivers/gpu/drm/msm/dp/dp_catalog.c
index ca96e3514790..c0423e76eed7 100644
--- a/drivers/gpu/drm/msm/dp/dp_catalog.c
+++ b/drivers/gpu/drm/msm/dp/dp_catalog.c
@@ -771,6 +771,7 @@ int dp_catalog_panel_timing_cfg(struct dp_catalog *dp_catalog)
dp_write_link(catalog, REG_DP_HSYNC_VSYNC_WIDTH_POLARITY,
dp_catalog->width_blanking);
dp_write_link(catalog, REG_DP_ACTIVE_HOR_VER, dp_catalog->dp_active);
+ dp_write_p0(catalog, MMSS_DP_INTF_CONFIG, 0);
return 0;
}
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index ee221d835fa0..eaddfd739885 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1526,7 +1526,7 @@ static int dp_ctrl_process_phy_test_request(struct dp_ctrl_private *ctrl)
* running. Add the global reset just before disabling the
* link clocks and core clocks.
*/
- ret = dp_ctrl_off(&ctrl->dp_ctrl);
+ ret = dp_ctrl_off_link_stream(&ctrl->dp_ctrl);
if (ret) {
DRM_ERROR("failed to disable DP controller\n");
return ret;
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 051c1be1de7e..867388a399ad 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -219,6 +219,7 @@ static int dp_display_bind(struct device *dev, struct device *master,
goto end;
}
+ dp->aux->drm_dev = drm;
rc = dp_aux_register(dp->aux);
if (rc) {
DRM_ERROR("DRM DP AUX register failed\n");
@@ -1311,6 +1312,10 @@ static int dp_pm_resume(struct device *dev)
else
dp->dp_display.is_connected = false;
+ dp_display_handle_plugged_change(g_dp_display,
+ dp->dp_display.is_connected);
+
+
mutex_unlock(&dp->event_mutex);
return 0;
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index eed2a762e9dd..bcaddbba564d 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -142,6 +142,9 @@ static const struct iommu_flush_ops null_tlb_ops = {
.tlb_add_page = msm_iommu_tlb_add_page,
};
+static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
+ unsigned long iova, int flags, void *arg);
+
struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
{
struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(parent->dev);
@@ -157,6 +160,13 @@ struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent)
if (!ttbr1_cfg)
return ERR_PTR(-ENODEV);
+ /*
+ * Defer setting the fault handler until we have a valid adreno_smmu
+ * to avoid accidentially installing a GPU specific fault handler for
+ * the display's iommu
+ */
+ iommu_set_fault_handler(iommu->domain, msm_fault_handler, iommu);
+
pagetable = kzalloc(sizeof(*pagetable), GFP_KERNEL);
if (!pagetable)
return ERR_PTR(-ENOMEM);
@@ -300,7 +310,6 @@ struct msm_mmu *msm_iommu_new(struct device *dev, struct iommu_domain *domain)
iommu->domain = domain;
msm_mmu_init(&iommu->base, dev, &funcs, MSM_MMU_IOMMU);
- iommu_set_fault_handler(domain, msm_fault_handler, iommu);
atomic_set(&iommu->pagetables, 0);
diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c
index 4f3a5357dd56..6d07e653f82d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_bo.c
+++ b/drivers/gpu/drm/nouveau/nouveau_bo.c
@@ -149,6 +149,8 @@ nouveau_bo_del_ttm(struct ttm_buffer_object *bo)
*/
if (bo->base.dev)
drm_gem_object_release(&bo->base);
+ else
+ dma_resv_fini(&bo->base._resv);
kfree(nvbo);
}
@@ -330,6 +332,10 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align,
if (IS_ERR(nvbo))
return PTR_ERR(nvbo);
+ nvbo->bo.base.size = size;
+ dma_resv_init(&nvbo->bo.base._resv);
+ drm_vma_node_reset(&nvbo->bo.base.vma_node);
+
ret = nouveau_bo_init(nvbo, size, align, domain, sg, robj);
if (ret)
return ret;
diff --git a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
index 2229f1af2ca8..46029c5610c8 100644
--- a/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
+++ b/drivers/gpu/drm/panel/panel-raspberrypi-touchscreen.c
@@ -447,7 +447,6 @@ static int rpi_touchscreen_remove(struct i2c_client *i2c)
drm_panel_remove(&ts->base);
mipi_dsi_device_unregister(ts->dsi);
- kfree(ts->dsi);
return 0;
}
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 21939d4352cf..1b80290c2b53 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -4166,7 +4166,7 @@ static const struct drm_display_mode yes_optoelectronics_ytc700tlag_05_201c_mode
static const struct panel_desc yes_optoelectronics_ytc700tlag_05_201c = {
.modes = &yes_optoelectronics_ytc700tlag_05_201c_mode,
.num_modes = 1,
- .bpc = 6,
+ .bpc = 8,
.size = {
.width = 154,
.height = 90,
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 1b950b45cf4b..8d7fd65ccced 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -102,6 +102,9 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
return;
}
+ if (!mem)
+ return;
+
man = ttm_manager_type(bdev, mem->mem_type);
list_move_tail(&bo->lru, &man->lru[bo->priority]);
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 2f57f824e6db..763fa6f4e07d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -63,6 +63,9 @@ int ttm_mem_io_reserve(struct ttm_device *bdev,
void ttm_mem_io_free(struct ttm_device *bdev,
struct ttm_resource *mem)
{
+ if (!mem)
+ return;
+
if (!mem->bus.offset && !mem->bus.addr)
return;
diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c
index 5f31acec3ad7..74e3b460132b 100644
--- a/drivers/gpu/drm/ttm/ttm_device.c
+++ b/drivers/gpu/drm/ttm/ttm_device.c
@@ -44,6 +44,8 @@ static unsigned ttm_glob_use_count;
struct ttm_global ttm_glob;
EXPORT_SYMBOL(ttm_glob);
+struct dentry *ttm_debugfs_root;
+
static void ttm_global_release(void)
{
struct ttm_global *glob = &ttm_glob;
@@ -53,6 +55,7 @@ static void ttm_global_release(void)
goto out;
ttm_pool_mgr_fini();
+ debugfs_remove(ttm_debugfs_root);
__free_page(glob->dummy_read_page);
memset(glob, 0, sizeof(*glob));
@@ -73,6 +76,13 @@ static int ttm_global_init(void)
si_meminfo(&si);
+ ttm_debugfs_root = debugfs_create_dir("ttm", NULL);
+ if (IS_ERR(ttm_debugfs_root)) {
+ ret = PTR_ERR(ttm_debugfs_root);
+ ttm_debugfs_root = NULL;
+ goto out;
+ }
+
/* Limit the number of pages in the pool to about 50% of the total
* system memory.
*/
@@ -100,6 +110,10 @@ static int ttm_global_init(void)
debugfs_create_atomic_t("buffer_objects", 0444, ttm_debugfs_root,
&glob->bo_count);
out:
+ if (ret && ttm_debugfs_root)
+ debugfs_remove(ttm_debugfs_root);
+ if (ret)
+ --ttm_glob_use_count;
mutex_unlock(&ttm_global_mutex);
return ret;
}
diff --git a/drivers/gpu/drm/ttm/ttm_module.c b/drivers/gpu/drm/ttm/ttm_module.c
index 997c458f68a9..7fcdef278c74 100644
--- a/drivers/gpu/drm/ttm/ttm_module.c
+++ b/drivers/gpu/drm/ttm/ttm_module.c
@@ -72,22 +72,6 @@ pgprot_t ttm_prot_from_caching(enum ttm_caching caching, pgprot_t tmp)
return tmp;
}
-struct dentry *ttm_debugfs_root;
-
-static int __init ttm_init(void)
-{
- ttm_debugfs_root = debugfs_create_dir("ttm", NULL);
- return 0;
-}
-
-static void __exit ttm_exit(void)
-{
- debugfs_remove(ttm_debugfs_root);
-}
-
-module_init(ttm_init);
-module_exit(ttm_exit);
-
MODULE_AUTHOR("Thomas Hellstrom, Jerome Glisse");
MODULE_DESCRIPTION("TTM memory manager subsystem (for DRM device)");
MODULE_LICENSE("GPL and additional rights");
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index aab1b36ceb3c..c2876731ee2d 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1857,38 +1857,46 @@ static int vc4_hdmi_cec_init(struct vc4_hdmi *vc4_hdmi)
vc4_hdmi_cec_update_clk_div(vc4_hdmi);
if (vc4_hdmi->variant->external_irq_controller) {
- ret = devm_request_threaded_irq(&pdev->dev,
- platform_get_irq_byname(pdev, "cec-rx"),
- vc4_cec_irq_handler_rx_bare,
- vc4_cec_irq_handler_rx_thread, 0,
- "vc4 hdmi cec rx", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-rx"),
+ vc4_cec_irq_handler_rx_bare,
+ vc4_cec_irq_handler_rx_thread, 0,
+ "vc4 hdmi cec rx", vc4_hdmi);
if (ret)
goto err_delete_cec_adap;
- ret = devm_request_threaded_irq(&pdev->dev,
- platform_get_irq_byname(pdev, "cec-tx"),
- vc4_cec_irq_handler_tx_bare,
- vc4_cec_irq_handler_tx_thread, 0,
- "vc4 hdmi cec tx", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq_byname(pdev, "cec-tx"),
+ vc4_cec_irq_handler_tx_bare,
+ vc4_cec_irq_handler_tx_thread, 0,
+ "vc4 hdmi cec tx", vc4_hdmi);
if (ret)
- goto err_delete_cec_adap;
+ goto err_remove_cec_rx_handler;
} else {
HDMI_WRITE(HDMI_CEC_CPU_MASK_SET, 0xffffffff);
- ret = devm_request_threaded_irq(&pdev->dev, platform_get_irq(pdev, 0),
- vc4_cec_irq_handler,
- vc4_cec_irq_handler_thread, 0,
- "vc4 hdmi cec", vc4_hdmi);
+ ret = request_threaded_irq(platform_get_irq(pdev, 0),
+ vc4_cec_irq_handler,
+ vc4_cec_irq_handler_thread, 0,
+ "vc4 hdmi cec", vc4_hdmi);
if (ret)
goto err_delete_cec_adap;
}
ret = cec_register_adapter(vc4_hdmi->cec_adap, &pdev->dev);
if (ret < 0)
- goto err_delete_cec_adap;
+ goto err_remove_handlers;
return 0;
+err_remove_handlers:
+ if (vc4_hdmi->variant->external_irq_controller)
+ free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+ else
+ free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+
+err_remove_cec_rx_handler:
+ if (vc4_hdmi->variant->external_irq_controller)
+ free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+
err_delete_cec_adap:
cec_delete_adapter(vc4_hdmi->cec_adap);
@@ -1897,6 +1905,15 @@ err_delete_cec_adap:
static void vc4_hdmi_cec_exit(struct vc4_hdmi *vc4_hdmi)
{
+ struct platform_device *pdev = vc4_hdmi->pdev;
+
+ if (vc4_hdmi->variant->external_irq_controller) {
+ free_irq(platform_get_irq_byname(pdev, "cec-rx"), vc4_hdmi);
+ free_irq(platform_get_irq_byname(pdev, "cec-tx"), vc4_hdmi);
+ } else {
+ free_irq(platform_get_irq(pdev, 0), vc4_hdmi);
+ }
+
cec_unregister_adapter(vc4_hdmi->cec_adap);
}
#else
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 160554903ef9..76937f716fbe 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -576,7 +576,7 @@ config HID_LOGITECH_HIDPP
depends on HID_LOGITECH
select POWER_SUPPLY
help
- Support for Logitech devices relyingon the HID++ Logitech specification
+ Support for Logitech devices relying on the HID++ Logitech specification
Say Y if you want support for Logitech devices relying on the HID++
specification. Such devices are the various Logitech Touchpads (T650,
diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
index 96e2577fa37e..8d68796aa905 100644
--- a/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
+++ b/drivers/hid/amd-sfh-hid/amd_sfh_pcie.c
@@ -58,7 +58,7 @@ static void amd_stop_sensor_v2(struct amd_mp2_dev *privdata, u16 sensor_idx)
cmd_base.cmd_v2.sensor_id = sensor_idx;
cmd_base.cmd_v2.length = 16;
- writeq(0x0, privdata->mmio + AMD_C2P_MSG2);
+ writeq(0x0, privdata->mmio + AMD_C2P_MSG1);
writel(cmd_base.ul, privdata->mmio + AMD_C2P_MSG0);
}
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 6b8f0d004d34..dc6bd4299c54 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -501,6 +501,8 @@ static const struct hid_device_id apple_devices[] = {
APPLE_RDESC_JIS },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI),
.driver_data = APPLE_HAS_FN },
+ { HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ANSI),
+ .driver_data = APPLE_HAS_FN },
{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO),
.driver_data = APPLE_HAS_FN },
{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_REVB_ISO),
diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
index fca8fc78a78a..fb807c8e989b 100644
--- a/drivers/hid/hid-asus.c
+++ b/drivers/hid/hid-asus.c
@@ -485,9 +485,6 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev,
{
struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds,
cdev);
- if (led->brightness == brightness)
- return;
-
led->brightness = brightness;
schedule_work(&led->work);
}
diff --git a/drivers/hid/hid-ft260.c b/drivers/hid/hid-ft260.c
index f43a8406cb9a..4ef1c3b8094e 100644
--- a/drivers/hid/hid-ft260.c
+++ b/drivers/hid/hid-ft260.c
@@ -742,7 +742,7 @@ static int ft260_is_interface_enabled(struct hid_device *hdev)
int ret;
ret = ft260_get_system_config(hdev, &cfg);
- if (ret)
+ if (ret < 0)
return ret;
ft260_dbg("interface: 0x%02x\n", interface);
@@ -754,23 +754,16 @@ static int ft260_is_interface_enabled(struct hid_device *hdev)
switch (cfg.chip_mode) {
case FT260_MODE_ALL:
case FT260_MODE_BOTH:
- if (interface == 1) {
+ if (interface == 1)
hid_info(hdev, "uart interface is not supported\n");
- return 0;
- }
- ret = 1;
+ else
+ ret = 1;
break;
case FT260_MODE_UART:
- if (interface == 0) {
- hid_info(hdev, "uart is unsupported on interface 0\n");
- ret = 0;
- }
+ hid_info(hdev, "uart interface is not supported\n");
break;
case FT260_MODE_I2C:
- if (interface == 1) {
- hid_info(hdev, "i2c is unsupported on interface 1\n");
- ret = 0;
- }
+ ret = 1;
break;
}
return ret;
@@ -785,7 +778,7 @@ static int ft260_byte_show(struct hid_device *hdev, int id, u8 *cfg, int len,
if (ret < 0)
return ret;
- return scnprintf(buf, PAGE_SIZE, "%hi\n", *field);
+ return scnprintf(buf, PAGE_SIZE, "%d\n", *field);
}
static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len,
@@ -797,7 +790,7 @@ static int ft260_word_show(struct hid_device *hdev, int id, u8 *cfg, int len,
if (ret < 0)
return ret;
- return scnprintf(buf, PAGE_SIZE, "%hi\n", le16_to_cpu(*field));
+ return scnprintf(buf, PAGE_SIZE, "%d\n", le16_to_cpu(*field));
}
#define FT260_ATTR_SHOW(name, reptype, id, type, func) \
@@ -1004,11 +997,9 @@ err_hid_stop:
static void ft260_remove(struct hid_device *hdev)
{
- int ret;
struct ft260_device *dev = hid_get_drvdata(hdev);
- ret = ft260_is_interface_enabled(hdev);
- if (ret <= 0)
+ if (!dev)
return;
sysfs_remove_group(&hdev->dev.kobj, &ft260_attr_group);
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index 6b1fa971b33e..91bf4d01e91a 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -784,6 +784,17 @@ static void hid_ishtp_cl_reset_handler(struct work_struct *work)
}
}
+static void hid_ishtp_cl_resume_handler(struct work_struct *work)
+{
+ struct ishtp_cl_data *client_data = container_of(work, struct ishtp_cl_data, resume_work);
+ struct ishtp_cl *hid_ishtp_cl = client_data->hid_ishtp_cl;
+
+ if (ishtp_wait_resume(ishtp_get_ishtp_device(hid_ishtp_cl))) {
+ client_data->suspended = false;
+ wake_up_interruptible(&client_data->ishtp_resume_wait);
+ }
+}
+
ishtp_print_log ishtp_hid_print_trace;
/**
@@ -822,6 +833,8 @@ static int hid_ishtp_cl_probe(struct ishtp_cl_device *cl_device)
init_waitqueue_head(&client_data->ishtp_resume_wait);
INIT_WORK(&client_data->work, hid_ishtp_cl_reset_handler);
+ INIT_WORK(&client_data->resume_work, hid_ishtp_cl_resume_handler);
+
ishtp_hid_print_trace = ishtp_trace_callback(cl_device);
@@ -921,7 +934,7 @@ static int hid_ishtp_cl_resume(struct device *device)
hid_ishtp_trace(client_data, "%s hid_ishtp_cl %p\n", __func__,
hid_ishtp_cl);
- client_data->suspended = false;
+ schedule_work(&client_data->resume_work);
return 0;
}
diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.h b/drivers/hid/intel-ish-hid/ishtp-hid.h
index f88443a7d935..6a5cc11aefd8 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.h
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.h
@@ -135,6 +135,7 @@ struct ishtp_cl_data {
int multi_packet_cnt;
struct work_struct work;
+ struct work_struct resume_work;
struct ishtp_cl_device *cl_device;
};
diff --git a/drivers/hid/intel-ish-hid/ishtp/bus.c b/drivers/hid/intel-ish-hid/ishtp/bus.c
index f0802b047ed8..aa2c51624012 100644
--- a/drivers/hid/intel-ish-hid/ishtp/bus.c
+++ b/drivers/hid/intel-ish-hid/ishtp/bus.c
@@ -314,13 +314,6 @@ static int ishtp_cl_device_resume(struct device *dev)
if (!device)
return 0;
- /*
- * When ISH needs hard reset, it is done asynchrnously, hence bus
- * resume will be called before full ISH resume
- */
- if (device->ishtp_dev->resume_flag)
- return 0;
-
driver = to_ishtp_cl_driver(dev->driver);
if (driver && driver->driver.pm) {
if (driver->driver.pm->resume)
@@ -850,6 +843,28 @@ struct device *ishtp_device(struct ishtp_cl_device *device)
EXPORT_SYMBOL(ishtp_device);
/**
+ * ishtp_wait_resume() - Wait for IPC resume
+ *
+ * Wait for IPC resume
+ *
+ * Return: resume complete or not
+ */
+bool ishtp_wait_resume(struct ishtp_device *dev)
+{
+ /* 50ms to get resume response */
+ #define WAIT_FOR_RESUME_ACK_MS 50
+
+ /* Waiting to get resume response */
+ if (dev->resume_flag)
+ wait_event_interruptible_timeout(dev->resume_wait,
+ !dev->resume_flag,
+ msecs_to_jiffies(WAIT_FOR_RESUME_ACK_MS));
+
+ return (!dev->resume_flag);
+}
+EXPORT_SYMBOL_GPL(ishtp_wait_resume);
+
+/**
* ishtp_get_pci_device() - Return PCI device dev pointer
* This interface is used to return PCI device pointer
* from ishtp_cl_device instance.
diff --git a/drivers/hid/usbhid/Kconfig b/drivers/hid/usbhid/Kconfig
index dcf3a235870f..7c2032f7f44d 100644
--- a/drivers/hid/usbhid/Kconfig
+++ b/drivers/hid/usbhid/Kconfig
@@ -38,7 +38,7 @@ config USB_HIDDEV
help
Say Y here if you want to support HID devices (from the USB
specification standpoint) that aren't strictly user interface
- devices, like monitor controls and Uninterruptable Power Supplies.
+ devices, like monitor controls and Uninterruptible Power Supplies.
This module supports these devices separately using a separate
event interface on /dev/usb/hiddevX (char 180:96 to 180:111).
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 81d7d12bcf34..81ba642adcb7 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2548,6 +2548,9 @@ static void wacom_wac_finger_slot(struct wacom_wac *wacom_wac,
int slot;
slot = input_mt_get_slot_by_key(input, hid_data->id);
+ if (slot < 0)
+ return;
+
input_mt_slot(input, slot);
input_mt_report_slot_state(input, MT_TOOL_FINGER, prox);
}
@@ -3831,7 +3834,7 @@ int wacom_setup_touch_input_capabilities(struct input_dev *input_dev,
wacom_wac->shared->touch->product == 0xF6) {
input_dev->evbit[0] |= BIT_MASK(EV_SW);
__set_bit(SW_MUTE_DEVICE, input_dev->swbit);
- wacom_wac->shared->has_mute_touch_switch = true;
+ wacom_wac->has_mute_touch_switch = true;
}
fallthrough;
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index caf6d0c4bc1b..142308526ec6 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -605,6 +605,17 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
*/
mutex_lock(&vmbus_connection.channel_mutex);
+ list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+ if (guid_equal(&channel->offermsg.offer.if_type,
+ &newchannel->offermsg.offer.if_type) &&
+ guid_equal(&channel->offermsg.offer.if_instance,
+ &newchannel->offermsg.offer.if_instance)) {
+ fnew = false;
+ newchannel->primary_channel = channel;
+ break;
+ }
+ }
+
init_vp_index(newchannel);
/* Remember the channels that should be cleaned up upon suspend. */
@@ -617,16 +628,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
*/
atomic_dec(&vmbus_connection.offer_in_progress);
- list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
- if (guid_equal(&channel->offermsg.offer.if_type,
- &newchannel->offermsg.offer.if_type) &&
- guid_equal(&channel->offermsg.offer.if_instance,
- &newchannel->offermsg.offer.if_instance)) {
- fnew = false;
- break;
- }
- }
-
if (fnew) {
list_add_tail(&newchannel->listentry,
&vmbus_connection.chn_list);
@@ -647,7 +648,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
/*
* Process the sub-channel.
*/
- newchannel->primary_channel = channel;
list_add_tail(&newchannel->sc_list, &channel->sc_list);
}
@@ -684,6 +684,30 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
}
/*
+ * Check if CPUs used by other channels of the same device.
+ * It should only be called by init_vp_index().
+ */
+static bool hv_cpuself_used(u32 cpu, struct vmbus_channel *chn)
+{
+ struct vmbus_channel *primary = chn->primary_channel;
+ struct vmbus_channel *sc;
+
+ lockdep_assert_held(&vmbus_connection.channel_mutex);
+
+ if (!primary)
+ return false;
+
+ if (primary->target_cpu == cpu)
+ return true;
+
+ list_for_each_entry(sc, &primary->sc_list, sc_list)
+ if (sc != chn && sc->target_cpu == cpu)
+ return true;
+
+ return false;
+}
+
+/*
* We use this state to statically distribute the channel interrupt load.
*/
static int next_numa_node_id;
@@ -702,6 +726,7 @@ static int next_numa_node_id;
static void init_vp_index(struct vmbus_channel *channel)
{
bool perf_chn = hv_is_perf_channel(channel);
+ u32 i, ncpu = num_online_cpus();
cpumask_var_t available_mask;
struct cpumask *alloced_mask;
u32 target_cpu;
@@ -724,31 +749,38 @@ static void init_vp_index(struct vmbus_channel *channel)
return;
}
- while (true) {
- numa_node = next_numa_node_id++;
- if (numa_node == nr_node_ids) {
- next_numa_node_id = 0;
- continue;
+ for (i = 1; i <= ncpu + 1; i++) {
+ while (true) {
+ numa_node = next_numa_node_id++;
+ if (numa_node == nr_node_ids) {
+ next_numa_node_id = 0;
+ continue;
+ }
+ if (cpumask_empty(cpumask_of_node(numa_node)))
+ continue;
+ break;
+ }
+ alloced_mask = &hv_context.hv_numa_map[numa_node];
+
+ if (cpumask_weight(alloced_mask) ==
+ cpumask_weight(cpumask_of_node(numa_node))) {
+ /*
+ * We have cycled through all the CPUs in the node;
+ * reset the alloced map.
+ */
+ cpumask_clear(alloced_mask);
}
- if (cpumask_empty(cpumask_of_node(numa_node)))
- continue;
- break;
- }
- alloced_mask = &hv_context.hv_numa_map[numa_node];
- if (cpumask_weight(alloced_mask) ==
- cpumask_weight(cpumask_of_node(numa_node))) {
- /*
- * We have cycled through all the CPUs in the node;
- * reset the alloced map.
- */
- cpumask_clear(alloced_mask);
- }
+ cpumask_xor(available_mask, alloced_mask,
+ cpumask_of_node(numa_node));
- cpumask_xor(available_mask, alloced_mask, cpumask_of_node(numa_node));
+ target_cpu = cpumask_first(available_mask);
+ cpumask_set_cpu(target_cpu, alloced_mask);
- target_cpu = cpumask_first(available_mask);
- cpumask_set_cpu(target_cpu, alloced_mask);
+ if (channel->offermsg.offer.sub_channel_index >= ncpu ||
+ i > ncpu || !hv_cpuself_used(target_cpu, channel))
+ break;
+ }
channel->target_cpu = target_cpu;
diff --git a/drivers/i2c/busses/i2c-mpc.c b/drivers/i2c/busses/i2c-mpc.c
index 6d5014ebaab5..a6ea1eb1394e 100644
--- a/drivers/i2c/busses/i2c-mpc.c
+++ b/drivers/i2c/busses/i2c-mpc.c
@@ -635,8 +635,8 @@ static irqreturn_t mpc_i2c_isr(int irq, void *dev_id)
status = readb(i2c->base + MPC_I2C_SR);
if (status & CSR_MIF) {
- /* Read again to allow register to stabilise */
- status = readb(i2c->base + MPC_I2C_SR);
+ /* Wait up to 100us for transfer to properly complete */
+ readb_poll_timeout(i2c->base + MPC_I2C_SR, status, !(status & CSR_MCF), 0, 100);
writeb(0, i2c->base + MPC_I2C_SR);
mpc_i2c_do_intr(i2c, status);
return IRQ_HANDLED;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index d5674026512a..a8688a92c760 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -120,6 +120,7 @@ static int bnxt_re_setup_chip_ctx(struct bnxt_re_dev *rdev, u8 wqe_mode)
if (!chip_ctx)
return -ENOMEM;
chip_ctx->chip_num = bp->chip_num;
+ chip_ctx->hw_stats_size = bp->hw_ring_stats_size;
rdev->chip_ctx = chip_ctx;
/* rest members to follow eventually */
@@ -550,6 +551,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
dma_addr_t dma_map,
u32 *fw_stats_ctx_id)
{
+ struct bnxt_qplib_chip_ctx *chip_ctx = rdev->chip_ctx;
struct hwrm_stat_ctx_alloc_output resp = {0};
struct hwrm_stat_ctx_alloc_input req = {0};
struct bnxt_en_dev *en_dev = rdev->en_dev;
@@ -566,7 +568,7 @@ static int bnxt_re_net_stats_ctx_alloc(struct bnxt_re_dev *rdev,
bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_ALLOC, -1, -1);
req.update_period_ms = cpu_to_le32(1000);
req.stats_dma_addr = cpu_to_le64(dma_map);
- req.stats_dma_length = cpu_to_le16(sizeof(struct ctx_hw_stats_ext));
+ req.stats_dma_length = cpu_to_le16(chip_ctx->hw_stats_size);
req.stat_ctx_flags = STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE;
bnxt_re_fill_fw_msg(&fw_msg, (void *)&req, sizeof(req), (void *)&resp,
sizeof(resp), DFLT_HWRM_CMD_TIMEOUT);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 17f0701b3cee..44282a8cdd4f 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -56,6 +56,7 @@
static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
struct bnxt_qplib_stats *stats);
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats);
/* PBL */
@@ -559,7 +560,7 @@ int bnxt_qplib_alloc_ctx(struct bnxt_qplib_res *res,
goto fail;
stats_alloc:
/* Stats */
- rc = bnxt_qplib_alloc_stats_ctx(res->pdev, &ctx->stats);
+ rc = bnxt_qplib_alloc_stats_ctx(res->pdev, res->cctx, &ctx->stats);
if (rc)
goto fail;
@@ -889,15 +890,12 @@ static void bnxt_qplib_free_stats_ctx(struct pci_dev *pdev,
}
static int bnxt_qplib_alloc_stats_ctx(struct pci_dev *pdev,
+ struct bnxt_qplib_chip_ctx *cctx,
struct bnxt_qplib_stats *stats)
{
memset(stats, 0, sizeof(*stats));
stats->fw_id = -1;
- /* 128 byte aligned context memory is required only for 57500.
- * However making this unconditional, it does not harm previous
- * generation.
- */
- stats->size = ALIGN(sizeof(struct ctx_hw_stats), 128);
+ stats->size = cctx->hw_stats_size;
stats->dma = dma_alloc_coherent(&pdev->dev, stats->size,
&stats->dma_map, GFP_KERNEL);
if (!stats->dma) {
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index c291f495ae91..91031502e8f5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -54,6 +54,7 @@ struct bnxt_qplib_chip_ctx {
u16 chip_num;
u8 chip_rev;
u8 chip_metal;
+ u16 hw_stats_size;
struct bnxt_qplib_drv_modes modes;
};
diff --git a/drivers/infiniband/hw/irdma/ctrl.c b/drivers/infiniband/hw/irdma/ctrl.c
index b1023a7d0bd1..f1e5515256e0 100644
--- a/drivers/infiniband/hw/irdma/ctrl.c
+++ b/drivers/infiniband/hw/irdma/ctrl.c
@@ -2845,7 +2845,7 @@ static u64 irdma_sc_decode_fpm_commit(struct irdma_sc_dev *dev, __le64 *buf,
* parses fpm commit info and copy base value
* of hmc objects in hmc_info
*/
-static enum irdma_status_code
+static void
irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf,
struct irdma_hmc_obj_info *info, u32 *sd)
{
@@ -2915,7 +2915,6 @@ irdma_sc_parse_fpm_commit_buf(struct irdma_sc_dev *dev, __le64 *buf,
else
*sd = (u32)(size >> 21);
- return 0;
}
/**
@@ -4187,11 +4186,9 @@ enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq,
* @dev: sc device struct
* @count: allocate count
*/
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count)
{
writel(count, dev->hw_regs[IRDMA_AEQALLOC]);
-
- return 0;
}
/**
@@ -4434,9 +4431,9 @@ static enum irdma_status_code irdma_sc_cfg_iw_fpm(struct irdma_sc_dev *dev,
ret_code = irdma_sc_commit_fpm_val(dev->cqp, 0, hmc_info->hmc_fn_id,
&commit_fpm_mem, true, wait_type);
if (!ret_code)
- ret_code = irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
- hmc_info->hmc_obj,
- &hmc_info->sd_table.sd_cnt);
+ irdma_sc_parse_fpm_commit_buf(dev, dev->fpm_commit_buf,
+ hmc_info->hmc_obj,
+ &hmc_info->sd_table.sd_cnt);
print_hex_dump_debug("HMC: COMMIT FPM BUFFER", DUMP_PREFIX_OFFSET, 16,
8, commit_fpm_mem.va, IRDMA_COMMIT_FPM_BUF_SIZE,
false);
diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index 7afb8a6a0526..00de5ee9a260 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -1920,7 +1920,7 @@ enum irdma_status_code irdma_ctrl_init_hw(struct irdma_pci_f *rf)
* irdma_set_hw_rsrc - set hw memory resources.
* @rf: RDMA PCI function
*/
-static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf)
+static void irdma_set_hw_rsrc(struct irdma_pci_f *rf)
{
rf->allocated_qps = (void *)(rf->mem_rsrc +
(sizeof(struct irdma_arp_entry) * rf->arp_table_size));
@@ -1937,8 +1937,6 @@ static u32 irdma_set_hw_rsrc(struct irdma_pci_f *rf)
spin_lock_init(&rf->arp_lock);
spin_lock_init(&rf->qptable_lock);
spin_lock_init(&rf->qh_list_lock);
-
- return 0;
}
/**
@@ -2000,9 +1998,7 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf)
rf->arp_table = (struct irdma_arp_entry *)rf->mem_rsrc;
- ret = irdma_set_hw_rsrc(rf);
- if (ret)
- goto set_hw_rsrc_fail;
+ irdma_set_hw_rsrc(rf);
set_bit(0, rf->allocated_mrs);
set_bit(0, rf->allocated_qps);
@@ -2025,9 +2021,6 @@ u32 irdma_initialize_hw_rsrc(struct irdma_pci_f *rf)
return 0;
-set_hw_rsrc_fail:
- kfree(rf->mem_rsrc);
- rf->mem_rsrc = NULL;
mem_rsrc_kzalloc_fail:
kfree(rf->allocated_ws_nodes);
rf->allocated_ws_nodes = NULL;
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index ea59432351fb..51a41359e0b4 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -215,10 +215,10 @@ static void irdma_remove(struct auxiliary_device *aux_dev)
pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
}
-static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf)
+static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf,
+ struct ice_vsi *vsi)
{
struct irdma_pci_f *rf = iwdev->rf;
- struct ice_vsi *vsi = ice_get_main_vsi(pf);
rf->cdev = pf;
rf->gen_ops.register_qset = irdma_lan_register_qset;
@@ -253,12 +253,15 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
struct iidc_auxiliary_dev,
adev);
struct ice_pf *pf = iidc_adev->pf;
+ struct ice_vsi *vsi = ice_get_main_vsi(pf);
struct iidc_qos_params qos_info = {};
struct irdma_device *iwdev;
struct irdma_pci_f *rf;
struct irdma_l2params l2params = {};
int err;
+ if (!vsi)
+ return -EIO;
iwdev = ib_alloc_device(irdma_device, ibdev);
if (!iwdev)
return -ENOMEM;
@@ -268,7 +271,7 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
return -ENOMEM;
}
- irdma_fill_device_info(iwdev, pf);
+ irdma_fill_device_info(iwdev, pf, vsi);
rf = iwdev->rf;
if (irdma_ctrl_init_hw(rf)) {
diff --git a/drivers/infiniband/hw/irdma/type.h b/drivers/infiniband/hw/irdma/type.h
index 7387b83e826d..874bc25a938b 100644
--- a/drivers/infiniband/hw/irdma/type.h
+++ b/drivers/infiniband/hw/irdma/type.h
@@ -1222,8 +1222,7 @@ enum irdma_status_code irdma_sc_aeq_init(struct irdma_sc_aeq *aeq,
struct irdma_aeq_init_info *info);
enum irdma_status_code irdma_sc_get_next_aeqe(struct irdma_sc_aeq *aeq,
struct irdma_aeqe_info *info);
-enum irdma_status_code irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev,
- u32 count);
+void irdma_sc_repost_aeq_entries(struct irdma_sc_dev *dev, u32 count);
void irdma_sc_pd_init(struct irdma_sc_dev *dev, struct irdma_sc_pd *pd, u32 pd_id,
int abi_ver);
diff --git a/drivers/infiniband/hw/irdma/uk.c b/drivers/infiniband/hw/irdma/uk.c
index a6d52c20091c..5fb92de1f015 100644
--- a/drivers/infiniband/hw/irdma/uk.c
+++ b/drivers/infiniband/hw/irdma/uk.c
@@ -931,7 +931,7 @@ enum irdma_status_code irdma_uk_mw_bind(struct irdma_qp_uk *qp,
enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp,
struct irdma_post_rq_info *info)
{
- u32 total_size = 0, wqe_idx, i, byte_off;
+ u32 wqe_idx, i, byte_off;
u32 addl_frag_cnt;
__le64 *wqe;
u64 hdr;
@@ -939,9 +939,6 @@ enum irdma_status_code irdma_uk_post_receive(struct irdma_qp_uk *qp,
if (qp->max_rq_frag_cnt < info->num_sges)
return IRDMA_ERR_INVALID_FRAG_COUNT;
- for (i = 0; i < info->num_sges; i++)
- total_size += info->sg_list[i].len;
-
wqe = irdma_qp_get_next_recv_wqe(qp, &wqe_idx);
if (!wqe)
return IRDMA_ERR_QP_TOOMANY_WRS_POSTED;
diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index 9712f6902ba8..717147ed0519 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -557,7 +557,7 @@ static int irdma_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
* @iwqp: qp ptr
* @init_info: initialize info to return
*/
-static int irdma_setup_virt_qp(struct irdma_device *iwdev,
+static void irdma_setup_virt_qp(struct irdma_device *iwdev,
struct irdma_qp *iwqp,
struct irdma_qp_init_info *init_info)
{
@@ -574,8 +574,6 @@ static int irdma_setup_virt_qp(struct irdma_device *iwdev,
init_info->sq_pa = qpmr->sq_pbl.addr;
init_info->rq_pa = qpmr->rq_pbl.addr;
}
-
- return 0;
}
/**
@@ -914,7 +912,7 @@ static struct ib_qp *irdma_create_qp(struct ib_pd *ibpd,
}
}
init_info.qp_uk_init_info.abi_ver = iwpd->sc_pd.abi_ver;
- err_code = irdma_setup_virt_qp(iwdev, iwqp, &init_info);
+ irdma_setup_virt_qp(iwdev, iwqp, &init_info);
} else {
init_info.qp_uk_init_info.abi_ver = IRDMA_ABI_VER;
err_code = irdma_setup_kmode_qp(iwdev, iwqp, &init_info, init_attr);
diff --git a/drivers/infiniband/sw/rxe/rxe_mr.c b/drivers/infiniband/sw/rxe/rxe_mr.c
index 6aabcb4de235..be4bcb420fab 100644
--- a/drivers/infiniband/sw/rxe/rxe_mr.c
+++ b/drivers/infiniband/sw/rxe/rxe_mr.c
@@ -113,13 +113,14 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
int num_buf;
void *vaddr;
int err;
+ int i;
umem = ib_umem_get(pd->ibpd.device, start, length, access);
if (IS_ERR(umem)) {
- pr_warn("err %d from rxe_umem_get\n",
- (int)PTR_ERR(umem));
+ pr_warn("%s: Unable to pin memory region err = %d\n",
+ __func__, (int)PTR_ERR(umem));
err = PTR_ERR(umem);
- goto err1;
+ goto err_out;
}
mr->umem = umem;
@@ -129,9 +130,9 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
err = rxe_mr_alloc(mr, num_buf);
if (err) {
- pr_warn("err %d from rxe_mr_alloc\n", err);
- ib_umem_release(umem);
- goto err1;
+ pr_warn("%s: Unable to allocate memory for map\n",
+ __func__);
+ goto err_release_umem;
}
mr->page_shift = PAGE_SHIFT;
@@ -151,10 +152,10 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
vaddr = page_address(sg_page_iter_page(&sg_iter));
if (!vaddr) {
- pr_warn("null vaddr\n");
- ib_umem_release(umem);
+ pr_warn("%s: Unable to get virtual address\n",
+ __func__);
err = -ENOMEM;
- goto err1;
+ goto err_cleanup_map;
}
buf->addr = (uintptr_t)vaddr;
@@ -177,7 +178,13 @@ int rxe_mr_init_user(struct rxe_pd *pd, u64 start, u64 length, u64 iova,
return 0;
-err1:
+err_cleanup_map:
+ for (i = 0; i < mr->num_map; i++)
+ kfree(mr->map[i]);
+ kfree(mr->map);
+err_release_umem:
+ ib_umem_release(umem);
+err_out:
return err;
}
diff --git a/drivers/media/pci/intel/ipu3/cio2-bridge.c b/drivers/media/pci/intel/ipu3/cio2-bridge.c
index 4657e99df033..59a36f922675 100644
--- a/drivers/media/pci/intel/ipu3/cio2-bridge.c
+++ b/drivers/media/pci/intel/ipu3/cio2-bridge.c
@@ -173,10 +173,8 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg,
int ret;
for_each_acpi_dev_match(adev, cfg->hid, NULL, -1) {
- if (!adev->status.enabled) {
- acpi_dev_put(adev);
+ if (!adev->status.enabled)
continue;
- }
if (bridge->n_sensors >= CIO2_NUM_PORTS) {
acpi_dev_put(adev);
@@ -185,7 +183,6 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg,
}
sensor = &bridge->sensors[bridge->n_sensors];
- sensor->adev = adev;
strscpy(sensor->name, cfg->hid, sizeof(sensor->name));
ret = cio2_bridge_read_acpi_buffer(adev, "SSDB",
@@ -215,6 +212,7 @@ static int cio2_bridge_connect_sensor(const struct cio2_sensor_config *cfg,
goto err_free_swnodes;
}
+ sensor->adev = acpi_dev_get(adev);
adev->fwnode.secondary = fwnode;
dev_info(&cio2->dev, "Found supported sensor %s\n",
diff --git a/drivers/media/pci/ngene/ngene-core.c b/drivers/media/pci/ngene/ngene-core.c
index 07f342db6701..7481f553f959 100644
--- a/drivers/media/pci/ngene/ngene-core.c
+++ b/drivers/media/pci/ngene/ngene-core.c
@@ -385,7 +385,7 @@ static int ngene_command_config_free_buf(struct ngene *dev, u8 *config)
com.cmd.hdr.Opcode = CMD_CONFIGURE_FREE_BUFFER;
com.cmd.hdr.Length = 6;
- memcpy(&com.cmd.ConfigureBuffers.config, config, 6);
+ memcpy(&com.cmd.ConfigureFreeBuffers.config, config, 6);
com.in_len = 6;
com.out_len = 0;
diff --git a/drivers/media/pci/ngene/ngene.h b/drivers/media/pci/ngene/ngene.h
index 84f04e0e0cb9..3d296f1998a1 100644
--- a/drivers/media/pci/ngene/ngene.h
+++ b/drivers/media/pci/ngene/ngene.h
@@ -407,12 +407,14 @@ enum _BUFFER_CONFIGS {
struct FW_CONFIGURE_FREE_BUFFERS {
struct FW_HEADER hdr;
- u8 UVI1_BufferLength;
- u8 UVI2_BufferLength;
- u8 TVO_BufferLength;
- u8 AUD1_BufferLength;
- u8 AUD2_BufferLength;
- u8 TVA_BufferLength;
+ struct {
+ u8 UVI1_BufferLength;
+ u8 UVI2_BufferLength;
+ u8 TVO_BufferLength;
+ u8 AUD1_BufferLength;
+ u8 AUD2_BufferLength;
+ u8 TVA_BufferLength;
+ } __packed config;
} __attribute__ ((__packed__));
struct FW_CONFIGURE_UART {
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 7a6f01ace78a..305ffad131a2 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -714,23 +714,20 @@ static int at24_probe(struct i2c_client *client)
}
/*
- * If the 'label' property is not present for the AT24 EEPROM,
- * then nvmem_config.id is initialised to NVMEM_DEVID_AUTO,
- * and this will append the 'devid' to the name of the NVMEM
- * device. This is purely legacy and the AT24 driver has always
- * defaulted to this. However, if the 'label' property is
- * present then this means that the name is specified by the
- * firmware and this name should be used verbatim and so it is
- * not necessary to append the 'devid'.
+ * We initialize nvmem_config.id to NVMEM_DEVID_AUTO even if the
+ * label property is set as some platform can have multiple eeproms
+ * with same label and we can not register each of those with same
+ * label. Failing to register those eeproms trigger cascade failure
+ * on such platform.
*/
+ nvmem_config.id = NVMEM_DEVID_AUTO;
+
if (device_property_present(dev, "label")) {
- nvmem_config.id = NVMEM_DEVID_NONE;
err = device_property_read_string(dev, "label",
&nvmem_config.name);
if (err)
return err;
} else {
- nvmem_config.id = NVMEM_DEVID_AUTO;
nvmem_config.name = dev_name(dev);
}
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 9890a1532cb0..ce8aed562929 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -28,6 +28,7 @@
#include <linux/errno.h>
#include <linux/hdreg.h>
#include <linux/kdev_t.h>
+#include <linux/kref.h>
#include <linux/blkdev.h>
#include <linux/cdev.h>
#include <linux/mutex.h>
@@ -111,7 +112,7 @@ struct mmc_blk_data {
#define MMC_BLK_CMD23 (1 << 0) /* Can do SET_BLOCK_COUNT for multiblock */
#define MMC_BLK_REL_WR (1 << 1) /* MMC Reliable write support */
- unsigned int usage;
+ struct kref kref;
unsigned int read_only;
unsigned int part_type;
unsigned int reset_done;
@@ -181,10 +182,8 @@ static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk)
mutex_lock(&open_lock);
md = disk->private_data;
- if (md && md->usage == 0)
+ if (md && !kref_get_unless_zero(&md->kref))
md = NULL;
- if (md)
- md->usage++;
mutex_unlock(&open_lock);
return md;
@@ -196,18 +195,25 @@ static inline int mmc_get_devidx(struct gendisk *disk)
return devidx;
}
-static void mmc_blk_put(struct mmc_blk_data *md)
+static void mmc_blk_kref_release(struct kref *ref)
{
- mutex_lock(&open_lock);
- md->usage--;
- if (md->usage == 0) {
- int devidx = mmc_get_devidx(md->disk);
+ struct mmc_blk_data *md = container_of(ref, struct mmc_blk_data, kref);
+ int devidx;
- ida_simple_remove(&mmc_blk_ida, devidx);
- put_disk(md->disk);
- kfree(md);
- }
+ devidx = mmc_get_devidx(md->disk);
+ ida_simple_remove(&mmc_blk_ida, devidx);
+
+ mutex_lock(&open_lock);
+ md->disk->private_data = NULL;
mutex_unlock(&open_lock);
+
+ put_disk(md->disk);
+ kfree(md);
+}
+
+static void mmc_blk_put(struct mmc_blk_data *md)
+{
+ kref_put(&md->kref, mmc_blk_kref_release);
}
static ssize_t power_ro_lock_show(struct device *dev,
@@ -2327,7 +2333,8 @@ static struct mmc_blk_data *mmc_blk_alloc_req(struct mmc_card *card,
INIT_LIST_HEAD(&md->part);
INIT_LIST_HEAD(&md->rpmbs);
- md->usage = 1;
+ kref_init(&md->kref);
+
md->queue.blkdata = md;
md->disk->major = MMC_BLOCK_MAJOR;
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index eda4a1892c33..0475d96047c4 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -75,7 +75,8 @@ static void mmc_host_classdev_release(struct device *dev)
{
struct mmc_host *host = cls_dev_to_mmc_host(dev);
wakeup_source_unregister(host->ws);
- ida_simple_remove(&mmc_host_ida, host->index);
+ if (of_alias_get_id(host->parent->of_node, "mmc") < 0)
+ ida_simple_remove(&mmc_host_ida, host->index);
kfree(host);
}
@@ -502,7 +503,7 @@ static int mmc_first_nonreserved_index(void)
*/
struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
{
- int err;
+ int index;
struct mmc_host *host;
int alias_id, min_idx, max_idx;
@@ -515,20 +516,19 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev)
alias_id = of_alias_get_id(dev->of_node, "mmc");
if (alias_id >= 0) {
- min_idx = alias_id;
- max_idx = alias_id + 1;
+ index = alias_id;
} else {
min_idx = mmc_first_nonreserved_index();
max_idx = 0;
- }
- err = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL);
- if (err < 0) {
- kfree(host);
- return NULL;
+ index = ida_simple_get(&mmc_host_ida, min_idx, max_idx, GFP_KERNEL);
+ if (index < 0) {
+ kfree(host);
+ return NULL;
+ }
}
- host->index = err;
+ host->index = index;
dev_set_name(&host->class_dev, "mmc%d", host->index);
host->ws = wakeup_source_register(NULL, dev_name(&host->class_dev));
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d22d78303311..31730efa7538 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -3450,7 +3450,9 @@ static int bond_master_netdev_event(unsigned long event,
return bond_event_changename(event_bond);
case NETDEV_UNREGISTER:
bond_remove_proc_entry(event_bond);
+#ifdef CONFIG_XFRM_OFFLOAD
xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
+#endif /* CONFIG_XFRM_OFFLOAD */
break;
case NETDEV_REGISTER:
bond_create_proc_entry(event_bond);
diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c
index dd17b8c53e1c..89d9c986a229 100644
--- a/drivers/net/can/spi/hi311x.c
+++ b/drivers/net/can/spi/hi311x.c
@@ -218,7 +218,7 @@ static int hi3110_spi_trans(struct spi_device *spi, int len)
return ret;
}
-static u8 hi3110_cmd(struct spi_device *spi, u8 command)
+static int hi3110_cmd(struct spi_device *spi, u8 command)
{
struct hi3110_priv *priv = spi_get_drvdata(spi);
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
index 47c3f408a799..9ae48072b6c6 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
@@ -2300,6 +2300,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id)
err, priv->regs_status.intf);
mcp251xfd_dump(priv);
mcp251xfd_chip_interrupts_disable(priv);
+ mcp251xfd_timestamp_stop(priv);
return handled;
}
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 0a37af4a3fa4..2b5302e72435 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -255,6 +255,8 @@ struct ems_usb {
unsigned int free_slots; /* remember number of available slots */
struct ems_cpc_msg active_params; /* active controller parameters */
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
static void ems_usb_read_interrupt_callback(struct urb *urb)
@@ -587,6 +589,7 @@ static int ems_usb_start(struct ems_usb *dev)
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf = NULL;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -596,7 +599,7 @@ static int ems_usb_start(struct ems_usb *dev)
}
buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
netdev_err(netdev, "No memory left for USB buffer\n");
usb_free_urb(urb);
@@ -604,6 +607,8 @@ static int ems_usb_start(struct ems_usb *dev)
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, dev->udev, usb_rcvbulkpipe(dev->udev, 2),
buf, RX_BUFFER_SIZE,
ems_usb_read_bulk_callback, dev);
@@ -619,6 +624,9 @@ static int ems_usb_start(struct ems_usb *dev)
break;
}
+ dev->rxbuf[i] = buf;
+ dev->rxbuf_dma[i] = buf_dma;
+
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
}
@@ -684,6 +692,10 @@ static void unlink_all_urbs(struct ems_usb *dev)
usb_kill_anchored_urbs(&dev->rx_submitted);
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
+ dev->rxbuf[i], dev->rxbuf_dma[i]);
+
usb_kill_anchored_urbs(&dev->tx_submitted);
atomic_set(&dev->active_tx_urbs, 0);
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 65b58f8fc328..66fa8b07c2e6 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -195,6 +195,8 @@ struct esd_usb2 {
int net_count;
u32 version;
int rxinitdone;
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
struct esd_usb2_net_priv {
@@ -545,6 +547,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev)
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf = NULL;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -554,7 +557,7 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev)
}
buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
dev_warn(dev->udev->dev.parent,
"No memory left for USB buffer\n");
@@ -562,6 +565,8 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev)
goto freeurb;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, dev->udev,
usb_rcvbulkpipe(dev->udev, 1),
buf, RX_BUFFER_SIZE,
@@ -574,8 +579,12 @@ static int esd_usb2_setup_rx_urbs(struct esd_usb2 *dev)
usb_unanchor_urb(urb);
usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
urb->transfer_dma);
+ goto freeurb;
}
+ dev->rxbuf[i] = buf;
+ dev->rxbuf_dma[i] = buf_dma;
+
freeurb:
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
@@ -663,6 +672,11 @@ static void unlink_all_urbs(struct esd_usb2 *dev)
int i, j;
usb_kill_anchored_urbs(&dev->rx_submitted);
+
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
+ dev->rxbuf[i], dev->rxbuf_dma[i]);
+
for (i = 0; i < dev->net_count; i++) {
priv = dev->nets[i];
if (priv) {
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index a45865bd7254..a1a154c08b7f 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -653,6 +653,8 @@ static int mcba_usb_start(struct mcba_priv *priv)
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, priv->udev,
usb_rcvbulkpipe(priv->udev, MCBA_USB_EP_IN),
buf, MCBA_USB_RX_BUFF_SIZE,
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 1d6f77252f01..899a3d21b77f 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -117,7 +117,8 @@
#define PCAN_USB_BERR_MASK (PCAN_USB_ERR_RXERR | PCAN_USB_ERR_TXERR)
/* identify bus event packets with rx/tx error counters */
-#define PCAN_USB_ERR_CNT 0x80
+#define PCAN_USB_ERR_CNT_DEC 0x00 /* counters are decreasing */
+#define PCAN_USB_ERR_CNT_INC 0x80 /* counters are increasing */
/* private to PCAN-USB adapter */
struct pcan_usb {
@@ -608,11 +609,12 @@ static int pcan_usb_handle_bus_evt(struct pcan_usb_msg_context *mc, u8 ir)
/* acccording to the content of the packet */
switch (ir) {
- case PCAN_USB_ERR_CNT:
+ case PCAN_USB_ERR_CNT_DEC:
+ case PCAN_USB_ERR_CNT_INC:
/* save rx/tx error counters from in the device context */
- pdev->bec.rxerr = mc->ptr[0];
- pdev->bec.txerr = mc->ptr[1];
+ pdev->bec.rxerr = mc->ptr[1];
+ pdev->bec.txerr = mc->ptr[2];
break;
default:
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index b6e7ef0d5bc6..d1b83bd1b3cb 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -137,7 +137,8 @@ struct usb_8dev_priv {
u8 *cmd_msg_buffer;
struct mutex usb_8dev_cmd_lock;
-
+ void *rxbuf[MAX_RX_URBS];
+ dma_addr_t rxbuf_dma[MAX_RX_URBS];
};
/* tx frame */
@@ -733,6 +734,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv)
for (i = 0; i < MAX_RX_URBS; i++) {
struct urb *urb = NULL;
u8 *buf;
+ dma_addr_t buf_dma;
/* create a URB, and a buffer for it */
urb = usb_alloc_urb(0, GFP_KERNEL);
@@ -742,7 +744,7 @@ static int usb_8dev_start(struct usb_8dev_priv *priv)
}
buf = usb_alloc_coherent(priv->udev, RX_BUFFER_SIZE, GFP_KERNEL,
- &urb->transfer_dma);
+ &buf_dma);
if (!buf) {
netdev_err(netdev, "No memory left for USB buffer\n");
usb_free_urb(urb);
@@ -750,6 +752,8 @@ static int usb_8dev_start(struct usb_8dev_priv *priv)
break;
}
+ urb->transfer_dma = buf_dma;
+
usb_fill_bulk_urb(urb, priv->udev,
usb_rcvbulkpipe(priv->udev,
USB_8DEV_ENDP_DATA_RX),
@@ -767,6 +771,9 @@ static int usb_8dev_start(struct usb_8dev_priv *priv)
break;
}
+ priv->rxbuf[i] = buf;
+ priv->rxbuf_dma[i] = buf_dma;
+
/* Drop reference, USB core will take care of freeing it */
usb_free_urb(urb);
}
@@ -836,6 +843,10 @@ static void unlink_all_urbs(struct usb_8dev_priv *priv)
usb_kill_anchored_urbs(&priv->rx_submitted);
+ for (i = 0; i < MAX_RX_URBS; ++i)
+ usb_free_coherent(priv->udev, RX_BUFFER_SIZE,
+ priv->rxbuf[i], priv->rxbuf_dma[i]);
+
usb_kill_anchored_urbs(&priv->tx_submitted);
atomic_set(&priv->active_tx_urbs, 0);
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 93136f7e69f5..69f21b71614c 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -366,6 +366,8 @@ mt7530_fdb_write(struct mt7530_priv *priv, u16 vid,
int i;
reg[1] |= vid & CVID_MASK;
+ if (vid > 1)
+ reg[1] |= ATA2_IVL;
reg[2] |= (aging & AGE_TIMER_MASK) << AGE_TIMER;
reg[2] |= (port_mask & PORT_MAP_MASK) << PORT_MAP;
/* STATIC_ENT indicate that entry is static wouldn't
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 334d610a503d..b19b389ff10a 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -79,6 +79,7 @@ enum mt753x_bpdu_port_fw {
#define STATIC_EMP 0
#define STATIC_ENT 3
#define MT7530_ATA2 0x78
+#define ATA2_IVL BIT(15)
/* Register for address table write data */
#define MT7530_ATWD 0x7c
diff --git a/drivers/net/dsa/mv88e6xxx/Kconfig b/drivers/net/dsa/mv88e6xxx/Kconfig
index 05af632b0f59..634a48e6616b 100644
--- a/drivers/net/dsa/mv88e6xxx/Kconfig
+++ b/drivers/net/dsa/mv88e6xxx/Kconfig
@@ -12,7 +12,7 @@ config NET_DSA_MV88E6XXX
config NET_DSA_MV88E6XXX_PTP
bool "PTP support for Marvell 88E6xxx"
default n
- depends on PTP_1588_CLOCK
+ depends on NET_DSA_MV88E6XXX && PTP_1588_CLOCK
help
Say Y to enable PTP hardware timestamping on Marvell 88E6xxx switch
chips that support it.
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index beb41572d04e..272b0535d946 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2155,7 +2155,7 @@ static int mv88e6xxx_port_vlan_leave(struct mv88e6xxx_chip *chip,
int i, err;
if (!vid)
- return -EOPNOTSUPP;
+ return 0;
err = mv88e6xxx_vtu_get(chip, vid, &vlan);
if (err)
diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c
index ced8c9cb29c2..e2dc997580a8 100644
--- a/drivers/net/dsa/sja1105/sja1105_main.c
+++ b/drivers/net/dsa/sja1105/sja1105_main.c
@@ -397,6 +397,12 @@ static int sja1105_init_static_vlan(struct sja1105_private *priv)
if (dsa_is_cpu_port(ds, port))
v->pvid = true;
list_add(&v->list, &priv->dsa_8021q_vlans);
+
+ v = kmemdup(v, sizeof(*v), GFP_KERNEL);
+ if (!v)
+ return -ENOMEM;
+
+ list_add(&v->list, &priv->bridge_vlans);
}
((struct sja1105_vlan_lookup_entry *)table->entries)[0] = pvid;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index f56245eeef7b..89606587b156 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1671,11 +1671,16 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp,
if ((tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) &&
(skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
- u16 vlan_proto = tpa_info->metadata >>
- RX_CMP_FLAGS2_METADATA_TPID_SFT;
+ __be16 vlan_proto = htons(tpa_info->metadata >>
+ RX_CMP_FLAGS2_METADATA_TPID_SFT);
u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK;
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+ if (eth_type_vlan(vlan_proto)) {
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+ } else {
+ dev_kfree_skb(skb);
+ return NULL;
+ }
}
skb_checksum_none_assert(skb);
@@ -1897,9 +1902,15 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
(skb->dev->features & BNXT_HW_FEATURE_VLAN_ALL_RX)) {
u32 meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data);
u16 vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK;
- u16 vlan_proto = meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT;
+ __be16 vlan_proto = htons(meta_data >>
+ RX_CMP_FLAGS2_METADATA_TPID_SFT);
- __vlan_hwaccel_put_tag(skb, htons(vlan_proto), vtag);
+ if (eth_type_vlan(vlan_proto)) {
+ __vlan_hwaccel_put_tag(skb, vlan_proto, vtag);
+ } else {
+ dev_kfree_skb(skb);
+ goto next_rx;
+ }
}
skb_checksum_none_assert(skb);
@@ -7563,8 +7574,12 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
bp->flags &= ~BNXT_FLAG_WOL_CAP;
if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED)
bp->flags |= BNXT_FLAG_WOL_CAP;
- if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED)
+ if (flags & FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED) {
__bnxt_hwrm_ptp_qcfg(bp);
+ } else {
+ kfree(bp->ptp_cfg);
+ bp->ptp_cfg = NULL;
+ }
} else {
#ifdef CONFIG_BNXT_SRIOV
struct bnxt_vf_info *vf = &bp->vf;
@@ -10123,7 +10138,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
}
}
- bnxt_ptp_start(bp);
rc = bnxt_init_nic(bp, irq_re_init);
if (rc) {
netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc);
@@ -10197,6 +10211,12 @@ int bnxt_half_open_nic(struct bnxt *bp)
{
int rc = 0;
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+ netdev_err(bp->dev, "A previous firmware reset has not completed, aborting half open\n");
+ rc = -ENODEV;
+ goto half_open_err;
+ }
+
rc = bnxt_alloc_mem(bp, false);
if (rc) {
netdev_err(bp->dev, "bnxt_alloc_mem err: %x\n", rc);
@@ -10256,9 +10276,16 @@ static int bnxt_open(struct net_device *dev)
rc = bnxt_hwrm_if_change(bp, true);
if (rc)
return rc;
+
+ if (bnxt_ptp_init(bp)) {
+ netdev_warn(dev, "PTP initialization failed.\n");
+ kfree(bp->ptp_cfg);
+ bp->ptp_cfg = NULL;
+ }
rc = __bnxt_open_nic(bp, true, true);
if (rc) {
bnxt_hwrm_if_change(bp, false);
+ bnxt_ptp_clear(bp);
} else {
if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state)) {
if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -10349,6 +10376,7 @@ static int bnxt_close(struct net_device *dev)
{
struct bnxt *bp = netdev_priv(dev);
+ bnxt_ptp_clear(bp);
bnxt_hwmon_close(bp);
bnxt_close_nic(bp, true, true);
bnxt_hwrm_shutdown_link(bp);
@@ -11335,6 +11363,7 @@ static void bnxt_fw_reset_close(struct bnxt *bp)
bnxt_clear_int_mode(bp);
pci_disable_device(bp->pdev);
}
+ bnxt_ptp_clear(bp);
__bnxt_close_nic(bp, true, false);
bnxt_vf_reps_free(bp);
bnxt_clear_int_mode(bp);
@@ -11959,10 +11988,21 @@ static bool bnxt_fw_reset_timeout(struct bnxt *bp)
(bp->fw_reset_max_dsecs * HZ / 10));
}
+static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
+{
+ clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
+ if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF) {
+ bnxt_ulp_start(bp, rc);
+ bnxt_dl_health_status_update(bp, false);
+ }
+ bp->fw_reset_state = 0;
+ dev_close(bp->dev);
+}
+
static void bnxt_fw_reset_task(struct work_struct *work)
{
struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work);
- int rc;
+ int rc = 0;
if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n");
@@ -11992,6 +12032,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
}
bp->fw_reset_timestamp = jiffies;
rtnl_lock();
+ if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
+ bnxt_fw_reset_abort(bp, rc);
+ rtnl_unlock();
+ return;
+ }
bnxt_fw_reset_close(bp);
if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) {
bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN;
@@ -12039,6 +12084,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
if (val == 0xffff) {
if (bnxt_fw_reset_timeout(bp)) {
netdev_err(bp->dev, "Firmware reset aborted, PCI config space invalid\n");
+ rc = -ETIMEDOUT;
goto fw_reset_abort;
}
bnxt_queue_fw_reset_work(bp, HZ / 1000);
@@ -12048,6 +12094,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
if (pci_enable_device(bp->pdev)) {
netdev_err(bp->dev, "Cannot re-enable PCI device\n");
+ rc = -ENODEV;
goto fw_reset_abort;
}
pci_set_master(bp->pdev);
@@ -12074,18 +12121,18 @@ static void bnxt_fw_reset_task(struct work_struct *work)
}
rc = bnxt_open(bp->dev);
if (rc) {
- netdev_err(bp->dev, "bnxt_open_nic() failed\n");
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- dev_close(bp->dev);
+ netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
+ bnxt_fw_reset_abort(bp, rc);
+ rtnl_unlock();
+ return;
}
bp->fw_reset_state = 0;
/* Make sure fw_reset_state is 0 before clearing the flag */
smp_mb__before_atomic();
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- bnxt_ulp_start(bp, rc);
- if (!rc)
- bnxt_reenable_sriov(bp);
+ bnxt_ulp_start(bp, 0);
+ bnxt_reenable_sriov(bp);
bnxt_vf_reps_alloc(bp);
bnxt_vf_reps_open(bp);
bnxt_dl_health_recovery_done(bp);
@@ -12103,12 +12150,8 @@ fw_reset_abort_status:
netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
}
fw_reset_abort:
- clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
- if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
- bnxt_dl_health_status_update(bp, false);
- bp->fw_reset_state = 0;
rtnl_lock();
- dev_close(bp->dev);
+ bnxt_fw_reset_abort(bp, rc);
rtnl_unlock();
}
@@ -12662,7 +12705,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
if (BNXT_PF(bp))
devlink_port_type_clear(&bp->dl_port);
- bnxt_ptp_clear(bp);
pci_disable_pcie_error_reporting(pdev);
unregister_netdev(dev);
clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
@@ -13246,11 +13288,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
rc);
}
- if (bnxt_ptp_init(bp)) {
- netdev_warn(dev, "PTP initialization failed.\n");
- kfree(bp->ptp_cfg);
- bp->ptp_cfg = NULL;
- }
bnxt_inv_fw_health_reg(bp);
bnxt_dl_register(bp);
@@ -13436,7 +13473,8 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
if (netif_running(netdev))
bnxt_close(netdev);
- pci_disable_device(pdev);
+ if (pci_is_enabled(pdev))
+ pci_disable_device(pdev);
bnxt_free_ctx_mem(bp);
kfree(bp->ctx);
bp->ctx = NULL;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 8e90224c43a2..8a68df4d9e59 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -433,6 +433,7 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
{
int total_ets_bw = 0;
+ bool zero = false;
u8 max_tc = 0;
int i;
@@ -453,13 +454,20 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
break;
case IEEE_8021QAZ_TSA_ETS:
total_ets_bw += ets->tc_tx_bw[i];
+ zero = zero || !ets->tc_tx_bw[i];
break;
default:
return -ENOTSUPP;
}
}
- if (total_ets_bw > 100)
+ if (total_ets_bw > 100) {
+ netdev_warn(bp->dev, "rejecting ETS config exceeding available bandwidth\n");
return -EINVAL;
+ }
+ if (zero && total_ets_bw == 100) {
+ netdev_warn(bp->dev, "rejecting ETS config starving a TC\n");
+ return -EINVAL;
+ }
if (max_tc >= bp->max_tc)
*tc = bp->max_tc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index f698b6bd4ff8..ec381c2423b8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -353,6 +353,12 @@ static long bnxt_ptp_ts_aux_work(struct ptp_clock_info *ptp_info)
bnxt_ptp_get_current_time(bp);
ptp->next_period = now + HZ;
+ if (time_after_eq(now, ptp->next_overflow_check)) {
+ spin_lock_bh(&ptp->ptp_lock);
+ timecounter_read(&ptp->tc);
+ spin_unlock_bh(&ptp->ptp_lock);
+ ptp->next_overflow_check = now + BNXT_PHC_OVERFLOW_PERIOD;
+ }
return HZ;
}
@@ -385,22 +391,6 @@ int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts)
return 0;
}
-void bnxt_ptp_start(struct bnxt *bp)
-{
- struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
-
- if (!ptp)
- return;
-
- if (bp->flags & BNXT_FLAG_CHIP_P5) {
- spin_lock_bh(&ptp->ptp_lock);
- ptp->current_time = bnxt_refclk_read(bp, NULL);
- WRITE_ONCE(ptp->old_time, ptp->current_time);
- spin_unlock_bh(&ptp->ptp_lock);
- ptp_schedule_worker(ptp->ptp_clock, 0);
- }
-}
-
static const struct ptp_clock_info bnxt_ptp_caps = {
.owner = THIS_MODULE,
.name = "bnxt clock",
@@ -439,6 +429,7 @@ int bnxt_ptp_init(struct bnxt *bp)
ptp->cc.shift = 0;
ptp->cc.mult = 1;
+ ptp->next_overflow_check = jiffies + BNXT_PHC_OVERFLOW_PERIOD;
timecounter_init(&ptp->tc, &ptp->cc, ktime_to_ns(ktime_get_real()));
ptp->ptp_info = bnxt_ptp_caps;
@@ -450,7 +441,13 @@ int bnxt_ptp_init(struct bnxt *bp)
bnxt_unmap_ptp_regs(bp);
return err;
}
-
+ if (bp->flags & BNXT_FLAG_CHIP_P5) {
+ spin_lock_bh(&ptp->ptp_lock);
+ ptp->current_time = bnxt_refclk_read(bp, NULL);
+ WRITE_ONCE(ptp->old_time, ptp->current_time);
+ spin_unlock_bh(&ptp->ptp_lock);
+ ptp_schedule_worker(ptp->ptp_clock, 0);
+ }
return 0;
}
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
index 6b6245750e20..254ba7bc0f99 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.h
@@ -32,6 +32,10 @@ struct bnxt_ptp_cfg {
u64 current_time;
u64 old_time;
unsigned long next_period;
+ unsigned long next_overflow_check;
+ /* 48-bit PHC overflows in 78 hours. Check overflow every 19 hours. */
+ #define BNXT_PHC_OVERFLOW_PERIOD (19 * 3600 * HZ)
+
u16 tx_seqid;
struct bnxt *bp;
atomic_t tx_avail;
@@ -75,7 +79,6 @@ int bnxt_hwtstamp_set(struct net_device *dev, struct ifreq *ifr);
int bnxt_hwtstamp_get(struct net_device *dev, struct ifreq *ifr);
int bnxt_get_tx_ts_p5(struct bnxt *bp, struct sk_buff *skb);
int bnxt_get_rx_ts_p5(struct bnxt *bp, u64 *ts, u32 pkt_ts);
-void bnxt_ptp_start(struct bnxt *bp);
int bnxt_ptp_init(struct bnxt *bp);
void bnxt_ptp_clear(struct bnxt *bp);
#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index a918e374f3c5..187ff643ad2a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -479,16 +479,17 @@ struct bnxt_en_dev *bnxt_ulp_probe(struct net_device *dev)
if (!edev)
return ERR_PTR(-ENOMEM);
edev->en_ops = &bnxt_en_ops_tbl;
- if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
- edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
- if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
- edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
edev->net = dev;
edev->pdev = bp->pdev;
edev->l2_db_size = bp->db_size;
edev->l2_db_size_nc = bp->db_size;
bp->edev = edev;
}
+ edev->flags &= ~BNXT_EN_FLAG_ROCE_CAP;
+ if (bp->flags & BNXT_FLAG_ROCEV1_CAP)
+ edev->flags |= BNXT_EN_FLAG_ROCEV1_CAP;
+ if (bp->flags & BNXT_FLAG_ROCEV2_CAP)
+ edev->flags |= BNXT_EN_FLAG_ROCEV2_CAP;
return bp->edev;
}
EXPORT_SYMBOL(bnxt_ulp_probe);
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 4cddd628d41b..9ed3d1ab2ca5 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -420,7 +420,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
* bits 32:47 indicate the PVF num.
*/
for (q_no = 0; q_no < ern; q_no++) {
- reg_val = oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
+ reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
/* for VF assigned queues. */
if (q_no < oct->sriov_info.pf_srn) {
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index f6ff1f76eacb..1876f15dd827 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -357,7 +357,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
int i, option = find_cnt < MAX_UNITS ? options[find_cnt] : 0;
void __iomem *ioaddr;
- i = pci_enable_device(pdev);
+ i = pcim_enable_device(pdev);
if (i) return i;
pci_set_master(pdev);
@@ -379,7 +379,7 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
ioaddr = pci_iomap(pdev, TULIP_BAR, netdev_res_size);
if (!ioaddr)
- goto err_out_free_res;
+ goto err_out_netdev;
for (i = 0; i < 3; i++)
((__le16 *)dev->dev_addr)[i] = cpu_to_le16(eeprom_read(ioaddr, i));
@@ -458,8 +458,6 @@ static int w840_probe1(struct pci_dev *pdev, const struct pci_device_id *ent)
err_out_cleardev:
pci_iounmap(pdev, ioaddr);
-err_out_free_res:
- pci_release_regions(pdev);
err_out_netdev:
free_netdev (dev);
return -ENODEV;
@@ -1526,7 +1524,6 @@ static void w840_remove1(struct pci_dev *pdev)
if (dev) {
struct netdev_private *np = netdev_priv(dev);
unregister_netdev(dev);
- pci_release_regions(pdev);
pci_iounmap(pdev, np->base_addr);
free_netdev(dev);
}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index f3d12d0714fb..68b78642c045 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -2770,32 +2770,32 @@ static int dpaa2_switch_ctrl_if_setup(struct ethsw_core *ethsw)
if (err)
return err;
- err = dpaa2_switch_seed_bp(ethsw);
- if (err)
- goto err_free_dpbp;
-
err = dpaa2_switch_alloc_rings(ethsw);
if (err)
- goto err_drain_dpbp;
+ goto err_free_dpbp;
err = dpaa2_switch_setup_dpio(ethsw);
if (err)
goto err_destroy_rings;
+ err = dpaa2_switch_seed_bp(ethsw);
+ if (err)
+ goto err_deregister_dpio;
+
err = dpsw_ctrl_if_enable(ethsw->mc_io, 0, ethsw->dpsw_handle);
if (err) {
dev_err(ethsw->dev, "dpsw_ctrl_if_enable err %d\n", err);
- goto err_deregister_dpio;
+ goto err_drain_dpbp;
}
return 0;
+err_drain_dpbp:
+ dpaa2_switch_drain_bp(ethsw);
err_deregister_dpio:
dpaa2_switch_free_dpio(ethsw);
err_destroy_rings:
dpaa2_switch_destroy_rings(ethsw);
-err_drain_dpbp:
- dpaa2_switch_drain_bp(ethsw);
err_free_dpbp:
dpaa2_switch_free_dpbp(ethsw);
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 46ecb42f2ef8..d9fc5c456bf3 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -524,6 +524,7 @@ static void setup_memac(struct mac_device *mac_dev)
| SUPPORTED_Autoneg \
| SUPPORTED_Pause \
| SUPPORTED_Asym_Pause \
+ | SUPPORTED_FIBRE \
| SUPPORTED_MII)
static DEFINE_MUTEX(eth_lock);
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 12f6c2442a7a..e53512f6878a 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -131,7 +131,7 @@
/* buf unit size is cache_line_size, which is 64, so the shift is 6 */
#define PPE_BUF_SIZE_SHIFT 6
#define PPE_TX_BUF_HOLD BIT(31)
-#define CACHE_LINE_MASK 0x3F
+#define SOC_CACHE_LINE_MASK 0x3F
#else
#define PPE_CFG_QOS_VMID_GRP_SHIFT 8
#define PPE_CFG_RX_CTRL_ALIGN_SHIFT 11
@@ -531,8 +531,8 @@ hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev)
#if defined(CONFIG_HI13X1_GMAC)
desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV
| TX_RELEASE_TO_PPE | priv->port << TX_POOL_SHIFT);
- desc->data_offset = (__force u32)cpu_to_be32(phys & CACHE_LINE_MASK);
- desc->send_addr = (__force u32)cpu_to_be32(phys & ~CACHE_LINE_MASK);
+ desc->data_offset = (__force u32)cpu_to_be32(phys & SOC_CACHE_LINE_MASK);
+ desc->send_addr = (__force u32)cpu_to_be32(phys & ~SOC_CACHE_LINE_MASK);
#else
desc->cfg = (__force u32)cpu_to_be32(TX_CLEAR_WB | TX_FINISH_CACHE_INV);
desc->send_addr = (__force u32)cpu_to_be32(phys);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 0a6cda309b24..aa86a81c8f4a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -98,6 +98,7 @@ struct hclgevf_mbx_resp_status {
u32 origin_mbx_msg;
bool received_resp;
int resp_status;
+ u16 match_id;
u8 additional_info[HCLGE_MBX_MAX_RESP_DATA_SIZE];
};
@@ -143,7 +144,8 @@ struct hclge_mbx_vf_to_pf_cmd {
u8 mbx_need_resp;
u8 rsv1[1];
u8 msg_len;
- u8 rsv2[3];
+ u8 rsv2;
+ u16 match_id;
struct hclge_vf_to_pf_msg msg;
};
@@ -153,7 +155,8 @@ struct hclge_mbx_pf_to_vf_cmd {
u8 dest_vfid;
u8 rsv[3];
u8 msg_len;
- u8 rsv1[3];
+ u8 rsv1;
+ u16 match_id;
struct hclge_pf_to_vf_msg msg;
};
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index dd3354a57c62..ebeaf12e409b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -9552,13 +9552,17 @@ static int hclge_set_vport_vlan_filter(struct hclge_vport *vport, bool enable)
if (ret)
return ret;
- if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps))
+ if (test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B, ae_dev->caps)) {
ret = hclge_set_port_vlan_filter_bypass(hdev, vport->vport_id,
!enable);
- else if (!vport->vport_id)
+ } else if (!vport->vport_id) {
+ if (test_bit(HNAE3_DEV_SUPPORT_VLAN_FLTR_MDF_B, ae_dev->caps))
+ enable = false;
+
ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
HCLGE_FILTER_FE_INGRESS,
enable, 0);
+ }
return ret;
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index e10a2c36b706..c0a478ae9583 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -47,6 +47,7 @@ static int hclge_gen_resp_to_vf(struct hclge_vport *vport,
resp_pf_to_vf->dest_vfid = vf_to_pf_req->mbx_src_vfid;
resp_pf_to_vf->msg_len = vf_to_pf_req->msg_len;
+ resp_pf_to_vf->match_id = vf_to_pf_req->match_id;
resp_pf_to_vf->msg.code = HCLGE_MBX_PF_VF_RESP;
resp_pf_to_vf->msg.vf_mbx_msg_code = vf_to_pf_req->msg.code;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 3b1f84502e36..befa9bcc2f2f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -5,9 +5,27 @@
#include "hclge_main.h"
#include "hnae3.h"
+static int hclge_ptp_get_cycle(struct hclge_dev *hdev)
+{
+ struct hclge_ptp *ptp = hdev->ptp;
+
+ ptp->cycle.quo = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG) &
+ HCLGE_PTP_CYCLE_QUO_MASK;
+ ptp->cycle.numer = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG);
+ ptp->cycle.den = readl(hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
+
+ if (ptp->cycle.den == 0) {
+ dev_err(&hdev->pdev->dev, "invalid ptp cycle denominator!\n");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
{
struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp);
+ struct hclge_ptp_cycle *cycle = &hdev->ptp->cycle;
u64 adj_val, adj_base, diff;
unsigned long flags;
bool is_neg = false;
@@ -18,7 +36,7 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
is_neg = true;
}
- adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT;
+ adj_base = (u64)cycle->quo * (u64)cycle->den + (u64)cycle->numer;
adj_val = adj_base * ppb;
diff = div_u64(adj_val, 1000000000ULL);
@@ -29,16 +47,16 @@ static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
/* This clock cycle is defined by three part: quotient, numerator
* and denominator. For example, 2.5ns, the quotient is 2,
- * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator
- * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT.
+ * denominator is fixed to ptp->cycle.den, and numerator
+ * is 0.5 * ptp->cycle.den.
*/
- quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator);
+ quo = div_u64_rem(adj_val, cycle->den, &numerator);
spin_lock_irqsave(&hdev->ptp->lock, flags);
- writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG);
+ writel(quo & HCLGE_PTP_CYCLE_QUO_MASK,
+ hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG);
writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG);
- writel(HCLGE_PTP_CYCLE_ADJ_UNIT,
- hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
+ writel(cycle->den, hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG);
writel(HCLGE_PTP_CYCLE_ADJ_EN,
hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG);
spin_unlock_irqrestore(&hdev->ptp->lock, flags);
@@ -475,6 +493,10 @@ int hclge_ptp_init(struct hclge_dev *hdev)
ret = hclge_ptp_create_clock(hdev);
if (ret)
return ret;
+
+ ret = hclge_ptp_get_cycle(hdev);
+ if (ret)
+ return ret;
}
ret = hclge_ptp_int_en(hdev, true);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
index 5a202b775471..dbf5f4c08019 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h
@@ -29,6 +29,7 @@
#define HCLGE_PTP_TIME_ADJ_REG 0x60
#define HCLGE_PTP_TIME_ADJ_EN BIT(0)
#define HCLGE_PTP_CYCLE_QUO_REG 0x64
+#define HCLGE_PTP_CYCLE_QUO_MASK GENMASK(7, 0)
#define HCLGE_PTP_CYCLE_DEN_REG 0x68
#define HCLGE_PTP_CYCLE_NUM_REG 0x6C
#define HCLGE_PTP_CYCLE_CFG_REG 0x70
@@ -37,9 +38,7 @@
#define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78
#define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C
-#define HCLGE_PTP_CYCLE_ADJ_BASE 2
#define HCLGE_PTP_CYCLE_ADJ_MAX 500000000
-#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000
#define HCLGE_PTP_SEC_H_OFFSET 32u
#define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0)
@@ -47,6 +46,12 @@
#define HCLGE_PTP_FLAG_TX_EN 1
#define HCLGE_PTP_FLAG_RX_EN 2
+struct hclge_ptp_cycle {
+ u32 quo;
+ u32 numer;
+ u32 den;
+};
+
struct hclge_ptp {
struct hclge_dev *hdev;
struct ptp_clock *clock;
@@ -58,6 +63,7 @@ struct hclge_ptp {
spinlock_t lock; /* protects ptp registers */
u32 ptp_cfg;
u32 last_tx_seqid;
+ struct hclge_ptp_cycle cycle;
unsigned long tx_start;
unsigned long tx_cnt;
unsigned long tx_skipped;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 52eaf82b7cd7..8784d61e833f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2641,6 +2641,16 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
{
+ struct hnae3_handle *nic = &hdev->nic;
+ int ret;
+
+ ret = hclgevf_en_hw_strip_rxvtag(nic, true);
+ if (ret) {
+ dev_err(&hdev->pdev->dev,
+ "failed to enable rx vlan offload, ret = %d\n", ret);
+ return ret;
+ }
+
return hclgevf_set_vlan_filter(&hdev->nic, htons(ETH_P_8021Q), 0,
false);
}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 9b17735b9f4c..772b2f8acd2e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -13,6 +13,7 @@ static int hclgevf_resp_to_errno(u16 resp_code)
return resp_code ? -resp_code : 0;
}
+#define HCLGEVF_MBX_MATCH_ID_START 1
static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev)
{
/* this function should be called with mbx_resp.mbx_mutex held
@@ -21,6 +22,10 @@ static void hclgevf_reset_mbx_resp_status(struct hclgevf_dev *hdev)
hdev->mbx_resp.received_resp = false;
hdev->mbx_resp.origin_mbx_msg = 0;
hdev->mbx_resp.resp_status = 0;
+ hdev->mbx_resp.match_id++;
+ /* Update match_id and ensure the value of match_id is not zero */
+ if (hdev->mbx_resp.match_id == 0)
+ hdev->mbx_resp.match_id = HCLGEVF_MBX_MATCH_ID_START;
memset(hdev->mbx_resp.additional_info, 0, HCLGE_MBX_MAX_RESP_DATA_SIZE);
}
@@ -115,6 +120,7 @@ int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev,
if (need_resp) {
mutex_lock(&hdev->mbx_resp.mbx_mutex);
hclgevf_reset_mbx_resp_status(hdev);
+ req->match_id = hdev->mbx_resp.match_id;
status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
if (status) {
dev_err(&hdev->pdev->dev,
@@ -211,6 +217,19 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
resp->additional_info[i] = *temp;
temp++;
}
+
+ /* If match_id is not zero, it means PF support
+ * match_id. If the match_id is right, VF get the
+ * right response, otherwise ignore the response.
+ * Driver will clear hdev->mbx_resp when send
+ * next message which need response.
+ */
+ if (req->match_id) {
+ if (req->match_id == resp->match_id)
+ resp->received_resp = true;
+ } else {
+ resp->received_resp = true;
+ }
break;
case HCLGE_MBX_LINK_STAT_CHANGE:
case HCLGE_MBX_ASSERTING_RESET:
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index ed77191d19f4..a775c69e4fd7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1731,7 +1731,6 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
tx_send_failed++;
tx_dropped++;
ret = NETDEV_TX_OK;
- ibmvnic_tx_scrq_flush(adapter, tx_scrq);
goto out;
}
@@ -1753,6 +1752,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
dev_kfree_skb_any(skb);
tx_send_failed++;
tx_dropped++;
+ ibmvnic_tx_scrq_flush(adapter, tx_scrq);
ret = NETDEV_TX_OK;
goto out;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 3e822bad4851..2c9e4eeb7270 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -980,7 +980,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
default:
/* if we got here and link is up something bad is afoot */
netdev_info(netdev,
- "WARNING: Link is up but PHY type 0x%x is not recognized.\n",
+ "WARNING: Link is up but PHY type 0x%x is not recognized, or incorrect cable is in use\n",
hw_link_info->phy_type);
}
@@ -5294,6 +5294,10 @@ flags_complete:
dev_warn(&pf->pdev->dev,
"Device configuration forbids SW from starting the LLDP agent.\n");
return -EINVAL;
+ case I40E_AQ_RC_EAGAIN:
+ dev_warn(&pf->pdev->dev,
+ "Stop FW LLDP agent command is still being processed, please try again in a second.\n");
+ return -EBUSY;
default:
dev_warn(&pf->pdev->dev,
"Starting FW LLDP agent failed: error: %s, %s\n",
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 861e59a350bd..1d1f52756a93 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4454,11 +4454,10 @@ int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q,
}
/**
- * i40e_vsi_control_tx - Start or stop a VSI's rings
+ * i40e_vsi_enable_tx - Start a VSI's rings
* @vsi: the VSI being configured
- * @enable: start or stop the rings
**/
-static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
+static int i40e_vsi_enable_tx(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
int i, pf_q, ret = 0;
@@ -4467,7 +4466,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
ret = i40e_control_wait_tx_q(vsi->seid, pf,
pf_q,
- false /*is xdp*/, enable);
+ false /*is xdp*/, true);
if (ret)
break;
@@ -4476,7 +4475,7 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable)
ret = i40e_control_wait_tx_q(vsi->seid, pf,
pf_q + vsi->alloc_queue_pairs,
- true /*is xdp*/, enable);
+ true /*is xdp*/, true);
if (ret)
break;
}
@@ -4574,32 +4573,25 @@ int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable)
}
/**
- * i40e_vsi_control_rx - Start or stop a VSI's rings
+ * i40e_vsi_enable_rx - Start a VSI's rings
* @vsi: the VSI being configured
- * @enable: start or stop the rings
**/
-static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable)
+static int i40e_vsi_enable_rx(struct i40e_vsi *vsi)
{
struct i40e_pf *pf = vsi->back;
int i, pf_q, ret = 0;
pf_q = vsi->base_queue;
for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) {
- ret = i40e_control_wait_rx_q(pf, pf_q, enable);
+ ret = i40e_control_wait_rx_q(pf, pf_q, true);
if (ret) {
dev_info(&pf->pdev->dev,
- "VSI seid %d Rx ring %d %sable timeout\n",
- vsi->seid, pf_q, (enable ? "en" : "dis"));
+ "VSI seid %d Rx ring %d enable timeout\n",
+ vsi->seid, pf_q);
break;
}
}
- /* Due to HW errata, on Rx disable only, the register can indicate done
- * before it really is. Needs 50ms to be sure
- */
- if (!enable)
- mdelay(50);
-
return ret;
}
@@ -4612,29 +4604,47 @@ int i40e_vsi_start_rings(struct i40e_vsi *vsi)
int ret = 0;
/* do rx first for enable and last for disable */
- ret = i40e_vsi_control_rx(vsi, true);
+ ret = i40e_vsi_enable_rx(vsi);
if (ret)
return ret;
- ret = i40e_vsi_control_tx(vsi, true);
+ ret = i40e_vsi_enable_tx(vsi);
return ret;
}
+#define I40E_DISABLE_TX_GAP_MSEC 50
+
/**
* i40e_vsi_stop_rings - Stop a VSI's rings
* @vsi: the VSI being configured
**/
void i40e_vsi_stop_rings(struct i40e_vsi *vsi)
{
+ struct i40e_pf *pf = vsi->back;
+ int pf_q, err, q_end;
+
/* When port TX is suspended, don't wait */
if (test_bit(__I40E_PORT_SUSPENDED, vsi->back->state))
return i40e_vsi_stop_rings_no_wait(vsi);
- /* do rx first for enable and last for disable
- * Ignore return value, we need to shutdown whatever we can
- */
- i40e_vsi_control_tx(vsi, false);
- i40e_vsi_control_rx(vsi, false);
+ q_end = vsi->base_queue + vsi->num_queue_pairs;
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ i40e_pre_tx_queue_cfg(&pf->hw, (u32)pf_q, false);
+
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++) {
+ err = i40e_control_wait_rx_q(pf, pf_q, false);
+ if (err)
+ dev_info(&pf->pdev->dev,
+ "VSI seid %d Rx ring %d dissable timeout\n",
+ vsi->seid, pf_q);
+ }
+
+ msleep(I40E_DISABLE_TX_GAP_MSEC);
+ pf_q = vsi->base_queue;
+ for (pf_q = vsi->base_queue; pf_q < q_end; pf_q++)
+ wr32(&pf->hw, I40E_QTX_ENA(pf_q), 0);
+
+ i40e_vsi_wait_queues_disabled(vsi);
}
/**
@@ -7280,6 +7290,8 @@ static int i40e_validate_mqprio_qopt(struct i40e_vsi *vsi,
}
if (vsi->num_queue_pairs <
(mqprio_qopt->qopt.offset[i] + mqprio_qopt->qopt.count[i])) {
+ dev_err(&vsi->back->pdev->dev,
+ "Failed to create traffic channel, insufficient number of queues.\n");
return -EINVAL;
}
if (sum_max_rate > i40e_get_link_speed(vsi)) {
@@ -13261,6 +13273,7 @@ static const struct net_device_ops i40e_netdev_ops = {
.ndo_poll_controller = i40e_netpoll,
#endif
.ndo_setup_tc = __i40e_setup_tc,
+ .ndo_select_queue = i40e_lan_select_queue,
.ndo_set_features = i40e_set_features,
.ndo_set_vf_mac = i40e_ndo_set_vf_mac,
.ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index 38eb8151ee9a..3f25bd8c4924 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -3631,6 +3631,56 @@ dma_error:
return -1;
}
+static u16 i40e_swdcb_skb_tx_hash(struct net_device *dev,
+ const struct sk_buff *skb,
+ u16 num_tx_queues)
+{
+ u32 jhash_initval_salt = 0xd631614b;
+ u32 hash;
+
+ if (skb->sk && skb->sk->sk_hash)
+ hash = skb->sk->sk_hash;
+ else
+ hash = (__force u16)skb->protocol ^ skb->hash;
+
+ hash = jhash_1word(hash, jhash_initval_salt);
+
+ return (u16)(((u64)hash * num_tx_queues) >> 32);
+}
+
+u16 i40e_lan_select_queue(struct net_device *netdev,
+ struct sk_buff *skb,
+ struct net_device __always_unused *sb_dev)
+{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+ struct i40e_vsi *vsi = np->vsi;
+ struct i40e_hw *hw;
+ u16 qoffset;
+ u16 qcount;
+ u8 tclass;
+ u16 hash;
+ u8 prio;
+
+ /* is DCB enabled at all? */
+ if (vsi->tc_config.numtc == 1)
+ return i40e_swdcb_skb_tx_hash(netdev, skb,
+ netdev->real_num_tx_queues);
+
+ prio = skb->priority;
+ hw = &vsi->back->hw;
+ tclass = hw->local_dcbx_config.etscfg.prioritytable[prio];
+ /* sanity check */
+ if (unlikely(!(vsi->tc_config.enabled_tc & BIT(tclass))))
+ tclass = 0;
+
+ /* select a queue assigned for the given TC */
+ qcount = vsi->tc_config.tc_info[tclass].qcount;
+ hash = i40e_swdcb_skb_tx_hash(netdev, skb, qcount);
+
+ qoffset = vsi->tc_config.tc_info[tclass].qoffset;
+ return qoffset + hash;
+}
+
/**
* i40e_xmit_xdp_ring - transmits an XDP buffer to an XDP Tx ring
* @xdpf: data to transmit
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 86fed05b4f19..bfc2845c99d1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -451,6 +451,8 @@ static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring)
bool i40e_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count);
netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+u16 i40e_lan_select_queue(struct net_device *netdev, struct sk_buff *skb,
+ struct net_device *sb_dev);
void i40e_clean_tx_ring(struct i40e_ring *tx_ring);
void i40e_clean_rx_ring(struct i40e_ring *rx_ring);
int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 913253f8ecb4..14aea40da50f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1825,7 +1825,8 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring,
struct sk_buff *skb)
{
if (ring_uses_build_skb(rx_ring)) {
- unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK;
+ unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1;
+ unsigned long offset = (unsigned long)(skb->data) & mask;
dma_sync_single_range_for_cpu(rx_ring->dev,
IXGBE_CB(skb)->dma,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
index 1a3455620b38..cc8ac36cf687 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile
@@ -10,4 +10,4 @@ obj-$(CONFIG_OCTEONTX2_AF) += rvu_af.o
rvu_mbox-y := mbox.o rvu_trace.o
rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \
rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \
- rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o
+ rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 9169849881bf..544c96c8fe1d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -1504,8 +1504,8 @@ static int cgx_lmac_init(struct cgx *cgx)
/* Add reference */
cgx->lmac_idmap[lmac->lmac_id] = lmac;
- cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true);
set_bit(lmac->lmac_id, &cgx->lmac_bmap);
+ cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, true);
}
return cgx_lmac_verify_fwi_version(cgx);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index 19bad9a59c8f..243cf8070e77 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -151,7 +151,10 @@ enum npc_kpu_lh_ltype {
* Software assigns pkind for each incoming port such as CGX
* Ethernet interfaces, LBK interfaces, etc.
*/
+#define NPC_UNRESERVED_PKIND_COUNT NPC_RX_VLAN_EXDSA_PKIND
+
enum npc_pkind_type {
+ NPC_RX_LBK_PKIND = 0ULL,
NPC_RX_VLAN_EXDSA_PKIND = 56ULL,
NPC_RX_CHLEN24B_PKIND = 57ULL,
NPC_RX_CPT_HDR_PKIND,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 10cddf1ac7b9..5fe277e354f7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -391,8 +391,10 @@ void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf)
/* Get numVFs attached to this PF and first HWVF */
cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
- *numvfs = (cfg >> 12) & 0xFF;
- *hwvf = cfg & 0xFFF;
+ if (numvfs)
+ *numvfs = (cfg >> 12) & 0xFF;
+ if (hwvf)
+ *hwvf = cfg & 0xFFF;
}
static int rvu_get_hwvf(struct rvu *rvu, int pcifunc)
@@ -1314,7 +1316,7 @@ int rvu_mbox_handler_detach_resources(struct rvu *rvu,
return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc);
}
-static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
{
struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
int blkaddr = BLKADDR_NIX0, vf;
@@ -2859,6 +2861,12 @@ static int rvu_enable_sriov(struct rvu *rvu)
if (!vfs)
return 0;
+ /* LBK channel number 63 is used for switching packets between
+ * CGX mapped VFs. Hence limit LBK pairs till 62 only.
+ */
+ if (vfs > 62)
+ vfs = 62;
+
/* Save VFs number for reference in VF interrupts handlers.
* Since interrupts might start arriving during SRIOV enablement
* ordinary API cannot be used to get number of enabled VFs.
@@ -3001,6 +3009,8 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
/* Initialize debugfs */
rvu_dbg_init(rvu);
+ mutex_init(&rvu->rswitch.switch_lock);
+
return 0;
err_dl:
rvu_unregister_dl(rvu);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 10e58a5d5861..91503fb2762c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -415,6 +415,16 @@ struct npc_kpu_profile_adapter {
size_t kpus;
};
+#define RVU_SWITCH_LBK_CHAN 63
+
+struct rvu_switch {
+ struct mutex switch_lock; /* Serialize flow installation */
+ u32 used_entries;
+ u16 *entry2pcifunc;
+ u16 mode;
+ u16 start_entry;
+};
+
struct rvu {
void __iomem *afreg_base;
void __iomem *pfreg_base;
@@ -445,6 +455,7 @@ struct rvu {
/* CGX */
#define PF_CGXMAP_BASE 1 /* PF 0 is reserved for RVU PF */
+ u16 cgx_mapped_vfs; /* maximum CGX mapped VFs */
u8 cgx_mapped_pfs;
u8 cgx_cnt_max; /* CGX port count max */
u8 *pf2cgxlmac_map; /* pf to cgx_lmac map */
@@ -477,6 +488,9 @@ struct rvu {
struct rvu_debugfs rvu_dbg;
#endif
struct rvu_devlink *rvu_dl;
+
+ /* RVU switch implementation over NPC with DMAC rules */
+ struct rvu_switch rswitch;
};
static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
@@ -691,6 +705,7 @@ int nix_aq_context_read(struct rvu *rvu, struct nix_hw *nix_hw,
struct nix_cn10k_aq_enq_req *aq_req,
struct nix_cn10k_aq_enq_rsp *aq_rsp,
u16 pcifunc, u8 ctype, u32 qidx);
+int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc);
/* NPC APIs */
int rvu_npc_init(struct rvu *rvu);
@@ -768,4 +783,10 @@ void rvu_dbg_exit(struct rvu *rvu);
static inline void rvu_dbg_init(struct rvu *rvu) {}
static inline void rvu_dbg_exit(struct rvu *rvu) {}
#endif
+
+/* RVU Switch */
+void rvu_switch_enable(struct rvu *rvu);
+void rvu_switch_disable(struct rvu *rvu);
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc);
+
#endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 6cc8fbb7190c..fe99ac4a4dd8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -126,6 +126,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
unsigned long lmac_bmap;
int size, free_pkind;
int cgx, lmac, iter;
+ int numvfs, hwvfs;
if (!cgx_cnt_max)
return 0;
@@ -166,6 +167,8 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16;
rvu_map_cgx_nix_block(rvu, pf, cgx, lmac);
rvu->cgx_mapped_pfs++;
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvfs);
+ rvu->cgx_mapped_vfs += numvfs;
pf++;
}
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index 370d4ca1e5ed..9b2dfbf90e51 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -2113,9 +2113,6 @@ static void rvu_print_npc_mcam_info(struct seq_file *s,
int entry_acnt, entry_ecnt;
int cntr_acnt, cntr_ecnt;
- /* Skip PF0 */
- if (!pcifunc)
- return;
rvu_npc_get_mcam_entry_alloc_info(rvu, pcifunc, blkaddr,
&entry_acnt, &entry_ecnt);
rvu_npc_get_mcam_counter_alloc_info(rvu, pcifunc, blkaddr,
@@ -2298,7 +2295,7 @@ static void rvu_dbg_npc_mcam_show_flows(struct seq_file *s,
static void rvu_dbg_npc_mcam_show_action(struct seq_file *s,
struct rvu_npc_mcam_rule *rule)
{
- if (rule->intf == NIX_INTF_TX) {
+ if (is_npc_intf_tx(rule->intf)) {
switch (rule->tx_action.op) {
case NIX_TX_ACTIONOP_DROP:
seq_puts(s, "\taction: Drop\n");
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
index 10a98bcb7c54..2688186066d9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c
@@ -1364,6 +1364,44 @@ static void rvu_health_reporters_destroy(struct rvu *rvu)
rvu_nix_health_reporters_destroy(rvu_dl);
}
+static int rvu_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+ struct rvu_switch *rswitch;
+
+ rswitch = &rvu->rswitch;
+ *mode = rswitch->mode;
+
+ return 0;
+}
+
+static int rvu_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
+ struct netlink_ext_ack *extack)
+{
+ struct rvu_devlink *rvu_dl = devlink_priv(devlink);
+ struct rvu *rvu = rvu_dl->rvu;
+ struct rvu_switch *rswitch;
+
+ rswitch = &rvu->rswitch;
+ switch (mode) {
+ case DEVLINK_ESWITCH_MODE_LEGACY:
+ case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+ if (rswitch->mode == mode)
+ return 0;
+ rswitch->mode = mode;
+ if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+ rvu_switch_enable(rvu);
+ else
+ rvu_switch_disable(rvu);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
struct netlink_ext_ack *extack)
{
@@ -1372,6 +1410,8 @@ static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req
static const struct devlink_ops rvu_devlink_ops = {
.info_get = rvu_devlink_info_get,
+ .eswitch_mode_get = rvu_devlink_eswitch_mode_get,
+ .eswitch_mode_set = rvu_devlink_eswitch_mode_set,
};
int rvu_register_dl(struct rvu *rvu)
@@ -1380,14 +1420,9 @@ int rvu_register_dl(struct rvu *rvu)
struct devlink *dl;
int err;
- rvu_dl = kzalloc(sizeof(*rvu_dl), GFP_KERNEL);
- if (!rvu_dl)
- return -ENOMEM;
-
dl = devlink_alloc(&rvu_devlink_ops, sizeof(struct rvu_devlink));
if (!dl) {
dev_warn(rvu->dev, "devlink_alloc failed\n");
- kfree(rvu_dl);
return -ENOMEM;
}
@@ -1395,10 +1430,10 @@ int rvu_register_dl(struct rvu *rvu)
if (err) {
dev_err(rvu->dev, "devlink register failed with error %d\n", err);
devlink_free(dl);
- kfree(rvu_dl);
return err;
}
+ rvu_dl = devlink_priv(dl);
rvu_dl->dl = dl;
rvu_dl->rvu = rvu;
rvu->rvu_dl = rvu_dl;
@@ -1417,5 +1452,4 @@ void rvu_unregister_dl(struct rvu *rvu)
rvu_health_reporters_destroy(rvu);
devlink_unregister(dl);
devlink_free(dl);
- kfree(rvu_dl);
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index aeae37704428..4bfbbdf38770 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -196,11 +196,22 @@ static void nix_rx_sync(struct rvu *rvu, int blkaddr)
{
int err;
- /*Sync all in flight RX packets to LLC/DRAM */
+ /* Sync all in flight RX packets to LLC/DRAM */
rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
if (err)
- dev_err(rvu->dev, "NIX RX software sync failed\n");
+ dev_err(rvu->dev, "SYNC1: NIX RX software sync failed\n");
+
+ /* SW_SYNC ensures all existing transactions are finished and pkts
+ * are written to LLC/DRAM, queues should be teared down after
+ * successful SW_SYNC. Due to a HW errata, in some rare scenarios
+ * an existing transaction might end after SW_SYNC operation. To
+ * ensure operation is fully done, do the SW_SYNC twice.
+ */
+ rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
+ err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
+ if (err)
+ dev_err(rvu->dev, "SYNC2: NIX RX software sync failed\n");
}
static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
@@ -298,6 +309,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
rvu_nix_chan_lbk(rvu, lbkid, vf + 1);
pfvf->rx_chan_cnt = 1;
pfvf->tx_chan_cnt = 1;
+ rvu_npc_set_pkind(rvu, NPC_RX_LBK_PKIND, pfvf);
rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
pfvf->rx_chan_base,
pfvf->rx_chan_cnt);
@@ -1952,6 +1964,35 @@ static void nix_tl1_default_cfg(struct rvu *rvu, struct nix_hw *nix_hw,
pfvf_map[schq] = TXSCH_SET_FLAG(pfvf_map[schq], NIX_TXSCHQ_CFG_DONE);
}
+static void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr,
+ u16 pcifunc, struct nix_txsch *txsch)
+{
+ struct rvu_hwinfo *hw = rvu->hw;
+ int lbk_link_start, lbk_links;
+ u8 pf = rvu_get_pf(pcifunc);
+ int schq;
+
+ if (!is_pf_cgxmapped(rvu, pf))
+ return;
+
+ lbk_link_start = hw->cgx_links;
+
+ for (schq = 0; schq < txsch->schq.max; schq++) {
+ if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
+ continue;
+ /* Enable all LBK links with channel 63 by default so that
+ * packets can be sent to LBK with a NPC TX MCAM rule
+ */
+ lbk_links = hw->lbk_links;
+ while (lbk_links--)
+ rvu_write64(rvu, blkaddr,
+ NIX_AF_TL3_TL2X_LINKX_CFG(schq,
+ lbk_link_start +
+ lbk_links),
+ BIT_ULL(12) | RVU_SWITCH_LBK_CHAN);
+ }
+}
+
int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
struct nix_txschq_config *req,
struct msg_rsp *rsp)
@@ -2040,6 +2081,9 @@ int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
rvu_write64(rvu, blkaddr, reg, regval);
}
+ rvu_nix_tx_tl2_cfg(rvu, blkaddr, pcifunc,
+ &nix_hw->txsch[NIX_TXSCH_LVL_TL2]);
+
return 0;
}
@@ -3180,6 +3224,8 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf)
ether_addr_copy(pfvf->default_mac, req->mac_addr);
+ rvu_switch_update_rules(rvu, pcifunc);
+
return 0;
}
@@ -3808,7 +3854,6 @@ static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr,
vlan = &nix_hw->txvlan;
kfree(vlan->rsrc.bmap);
mutex_destroy(&vlan->rsrc_lock);
- devm_kfree(rvu->dev, vlan->entry2pfvf_map);
mcast = &nix_hw->mcast;
qmem_free(rvu->dev, mcast->mce_ctx);
@@ -3849,6 +3894,8 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
pfvf = rvu_get_pfvf(rvu, pcifunc);
set_bit(NIXLF_INITIALIZED, &pfvf->flags);
+ rvu_switch_update_rules(rvu, pcifunc);
+
return rvu_cgx_start_stop_io(rvu, pcifunc, true);
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 3612e0a2cab3..52b255426c22 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -442,7 +442,8 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam,
owner = mcam->entry2pfvf_map[index];
target_func = (entry->action >> 4) & 0xffff;
/* do nothing when target is LBK/PF or owner is not PF */
- if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) ||
+ if (is_pffunc_af(owner) || is_afvf(target_func) ||
+ (owner & RVU_PFVF_FUNC_MASK) ||
!(target_func & RVU_PFVF_FUNC_MASK))
return;
@@ -468,6 +469,8 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
{
int bank = npc_get_bank(mcam, index);
int kw = 0, actbank, actindex;
+ u8 tx_intf_mask = ~intf & 0x3;
+ u8 tx_intf = intf;
u64 cam0, cam1;
actbank = bank; /* Save bank id, to set action later on */
@@ -488,12 +491,21 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
*/
for (; bank < (actbank + mcam->banks_per_entry); bank++, kw = kw + 2) {
/* Interface should be set in all banks */
+ if (is_npc_intf_tx(intf)) {
+ /* Last bit must be set and rest don't care
+ * for TX interfaces
+ */
+ tx_intf_mask = 0x1;
+ tx_intf = intf & tx_intf_mask;
+ tx_intf_mask = ~tx_intf & tx_intf_mask;
+ }
+
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 1),
- intf);
+ tx_intf);
rvu_write64(rvu, blkaddr,
NPC_AF_MCAMEX_BANKX_CAMX_INTF(index, bank, 0),
- ~intf & 0x3);
+ tx_intf_mask);
/* Set the match key */
npc_get_keyword(entry, kw, &cam0, &cam1);
@@ -650,6 +662,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
eth_broadcast_addr((u8 *)&req.mask.dmac);
req.features = BIT_ULL(NPC_DMAC);
req.channel = chan;
+ req.chan_mask = 0xFFFU;
req.intf = pfvf->nix_rx_intf;
req.op = action.op;
req.hdr.pcifunc = 0; /* AF is requester */
@@ -799,6 +812,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
eth_broadcast_addr((u8 *)&req.mask.dmac);
req.features = BIT_ULL(NPC_DMAC);
req.channel = chan;
+ req.chan_mask = 0xFFFU;
req.intf = pfvf->nix_rx_intf;
req.entry = index;
req.hdr.pcifunc = 0; /* AF is requester */
@@ -1707,7 +1721,6 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
{
struct rvu_hwinfo *hw = rvu->hw;
int num_pkinds, num_kpus, idx;
- struct npc_pkind *pkind;
/* Disable all KPUs and their entries */
for (idx = 0; idx < hw->npc_kpus; idx++) {
@@ -1725,9 +1738,8 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr)
* Check HW max count to avoid configuring junk or
* writing to unsupported CSR addresses.
*/
- pkind = &hw->pkind;
num_pkinds = rvu->kpu.pkinds;
- num_pkinds = min_t(int, pkind->rsrc.max, num_pkinds);
+ num_pkinds = min_t(int, hw->npc_pkinds, num_pkinds);
for (idx = 0; idx < num_pkinds; idx++)
npc_config_kpuaction(rvu, blkaddr, &rvu->kpu.ikpu[idx], 0, idx, true);
@@ -1745,6 +1757,8 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
int nixlf_count = rvu_get_nixlf_count(rvu);
struct npc_mcam *mcam = &rvu->hw->mcam;
int rsvd, err;
+ u16 index;
+ int cntr;
u64 cfg;
/* Actual number of MCAM entries vary by entry size */
@@ -1845,6 +1859,14 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
if (!mcam->entry2target_pffunc)
goto free_mem;
+ for (index = 0; index < mcam->bmap_entries; index++) {
+ mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+ mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
+ }
+
+ for (cntr = 0; cntr < mcam->counters.max; cntr++)
+ mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;
+
mutex_init(&mcam->lock);
return 0;
@@ -1867,7 +1889,8 @@ static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr)
if (npc_const1 & BIT_ULL(63))
npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2);
- pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL;
+ pkind->rsrc.max = NPC_UNRESERVED_PKIND_COUNT;
+ hw->npc_pkinds = (npc_const1 >> 12) & 0xFFULL;
hw->npc_kpu_entries = npc_const1 & 0xFFFULL;
hw->npc_kpus = (npc_const >> 8) & 0x1FULL;
hw->npc_intfs = npc_const & 0xFULL;
@@ -1978,6 +2001,10 @@ int rvu_npc_init(struct rvu *rvu)
err = rvu_alloc_bitmap(&pkind->rsrc);
if (err)
return err;
+ /* Reserve PKIND#0 for LBKs. Power reset value of LBK_CH_PKIND is '0',
+ * no need to configure PKIND for all LBKs separately.
+ */
+ rvu_alloc_rsrc(&pkind->rsrc);
/* Allocate mem for pkind to PF and channel mapping info */
pkind->pfchan_map = devm_kcalloc(rvu->dev, pkind->rsrc.max,
@@ -2562,7 +2589,7 @@ int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
}
/* Alloc request from PFFUNC with no NIXLF attached should be denied */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_ALLOC_DENIED;
return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp);
@@ -2582,7 +2609,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
return NPC_MCAM_INVALID_REQ;
/* Free request from PFFUNC with no NIXLF attached, ignore */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_INVALID_REQ;
mutex_lock(&mcam->lock);
@@ -2594,7 +2621,7 @@ int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
if (rc)
goto exit;
- mcam->entry2pfvf_map[req->entry] = 0;
+ mcam->entry2pfvf_map[req->entry] = NPC_MCAM_INVALID_MAP;
mcam->entry2target_pffunc[req->entry] = 0x0;
npc_mcam_clear_bit(mcam, req->entry);
npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
@@ -2679,13 +2706,14 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
else
nix_intf = pfvf->nix_rx_intf;
- if (npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
+ if (!is_pffunc_af(pcifunc) &&
+ npc_mcam_verify_channel(rvu, pcifunc, req->intf, channel)) {
rc = NPC_MCAM_INVALID_REQ;
goto exit;
}
- if (npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf,
- pcifunc)) {
+ if (!is_pffunc_af(pcifunc) &&
+ npc_mcam_verify_pf_func(rvu, &req->entry_data, req->intf, pcifunc)) {
rc = NPC_MCAM_INVALID_REQ;
goto exit;
}
@@ -2836,7 +2864,7 @@ int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
return NPC_MCAM_INVALID_REQ;
/* If the request is from a PFFUNC with no NIXLF attached, ignore */
- if (!is_nixlf_attached(rvu, pcifunc))
+ if (!is_pffunc_af(pcifunc) && !is_nixlf_attached(rvu, pcifunc))
return NPC_MCAM_INVALID_REQ;
/* Since list of allocated counter IDs needs to be sent to requester,
@@ -3081,7 +3109,7 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
if (rc) {
/* Free allocated MCAM entry */
mutex_lock(&mcam->lock);
- mcam->entry2pfvf_map[entry] = 0;
+ mcam->entry2pfvf_map[entry] = NPC_MCAM_INVALID_MAP;
npc_mcam_clear_bit(mcam, entry);
mutex_unlock(&mcam->lock);
return rc;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
index 68633145a8b8..5c01cf4a9c5b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c
@@ -910,14 +910,17 @@ static void rvu_mcam_add_counter_to_rule(struct rvu *rvu, u16 pcifunc,
static void npc_update_rx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
struct mcam_entry *entry,
- struct npc_install_flow_req *req, u16 target)
+ struct npc_install_flow_req *req,
+ u16 target, bool pf_set_vfs_mac)
{
+ struct rvu_switch *rswitch = &rvu->rswitch;
struct nix_rx_action action;
- u64 chan_mask;
- chan_mask = req->chan_mask ? req->chan_mask : ~0ULL;
- npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, chan_mask, 0,
- NIX_INTF_RX);
+ if (rswitch->mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && pf_set_vfs_mac)
+ req->chan_mask = 0x0; /* Do not care channel */
+
+ npc_update_entry(rvu, NPC_CHAN, entry, req->channel, 0, req->chan_mask,
+ 0, NIX_INTF_RX);
*(u64 *)&action = 0x00;
action.pf_func = target;
@@ -949,9 +952,16 @@ static void npc_update_tx_entry(struct rvu *rvu, struct rvu_pfvf *pfvf,
struct npc_install_flow_req *req, u16 target)
{
struct nix_tx_action action;
+ u64 mask = ~0ULL;
+
+ /* If AF is installing then do not care about
+ * PF_FUNC in Send Descriptor
+ */
+ if (is_pffunc_af(req->hdr.pcifunc))
+ mask = 0;
npc_update_entry(rvu, NPC_PF_FUNC, entry, (__force u16)htons(target),
- 0, ~0ULL, 0, NIX_INTF_TX);
+ 0, mask, 0, NIX_INTF_TX);
*(u64 *)&action = 0x00;
action.op = req->op;
@@ -1002,7 +1012,7 @@ static int npc_install_flow(struct rvu *rvu, int blkaddr, u16 target,
req->intf);
if (is_npc_intf_rx(req->intf))
- npc_update_rx_entry(rvu, pfvf, entry, req, target);
+ npc_update_rx_entry(rvu, pfvf, entry, req, target, pf_set_vfs_mac);
else
npc_update_tx_entry(rvu, pfvf, entry, req, target);
@@ -1164,7 +1174,9 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
if (err)
return err;
- if (npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
+ /* Skip channel validation if AF is installing */
+ if (!is_pffunc_af(req->hdr.pcifunc) &&
+ npc_mcam_verify_channel(rvu, target, req->intf, req->channel))
return -EINVAL;
pfvf = rvu_get_pfvf(rvu, target);
@@ -1180,6 +1192,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu,
eth_broadcast_addr((u8 *)&req->mask.dmac);
}
+ /* Proceed if NIXLF is attached or not for TX rules */
err = nix_get_nixlf(rvu, target, &nixlf, NULL);
if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac)
return -EINVAL;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
new file mode 100644
index 000000000000..820adf390b8e
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Admin Function driver
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include <linux/bitfield.h>
+#include "rvu.h"
+
+static int rvu_switch_install_rx_rule(struct rvu *rvu, u16 pcifunc,
+ u16 chan_mask)
+{
+ struct npc_install_flow_req req = { 0 };
+ struct npc_install_flow_rsp rsp = { 0 };
+ struct rvu_pfvf *pfvf;
+
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* If the pcifunc is not initialized then nothing to do.
+ * This same function will be called again via rvu_switch_update_rules
+ * after pcifunc is initialized.
+ */
+ if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+ return 0;
+
+ ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+ eth_broadcast_addr((u8 *)&req.mask.dmac);
+ req.hdr.pcifunc = 0; /* AF is requester */
+ req.vf = pcifunc;
+ req.features = BIT_ULL(NPC_DMAC);
+ req.channel = pfvf->rx_chan_base;
+ req.chan_mask = chan_mask;
+ req.intf = pfvf->nix_rx_intf;
+ req.op = NIX_RX_ACTION_DEFAULT;
+ req.default_rule = 1;
+
+ return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_tx_rule(struct rvu *rvu, u16 pcifunc, u16 entry)
+{
+ struct npc_install_flow_req req = { 0 };
+ struct npc_install_flow_rsp rsp = { 0 };
+ struct rvu_pfvf *pfvf;
+ u8 lbkid;
+
+ pfvf = rvu_get_pfvf(rvu, pcifunc);
+ /* If the pcifunc is not initialized then nothing to do.
+ * This same function will be called again via rvu_switch_update_rules
+ * after pcifunc is initialized.
+ */
+ if (!test_bit(NIXLF_INITIALIZED, &pfvf->flags))
+ return 0;
+
+ lbkid = pfvf->nix_blkaddr == BLKADDR_NIX0 ? 0 : 1;
+ ether_addr_copy(req.packet.dmac, pfvf->mac_addr);
+ eth_broadcast_addr((u8 *)&req.mask.dmac);
+ req.hdr.pcifunc = 0; /* AF is requester */
+ req.vf = pcifunc;
+ req.entry = entry;
+ req.features = BIT_ULL(NPC_DMAC);
+ req.intf = pfvf->nix_tx_intf;
+ req.op = NIX_TX_ACTIONOP_UCAST_CHAN;
+ req.index = (lbkid << 8) | RVU_SWITCH_LBK_CHAN;
+ req.set_cntr = 1;
+
+ return rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp);
+}
+
+static int rvu_switch_install_rules(struct rvu *rvu)
+{
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ u16 start = rswitch->start_entry;
+ struct rvu_hwinfo *hw = rvu->hw;
+ u16 pcifunc, entry = 0;
+ int pf, vf, numvfs;
+ int err;
+
+ for (pf = 1; pf < hw->total_pfs; pf++) {
+ if (!is_pf_cgxmapped(rvu, pf))
+ continue;
+
+ pcifunc = pf << 10;
+ /* rvu_get_nix_blkaddr sets up the corresponding NIX block
+ * address and NIX RX and TX interfaces for a pcifunc.
+ * Generally it is called during attach call of a pcifunc but it
+ * is called here since we are pre-installing rules before
+ * nixlfs are attached
+ */
+ rvu_get_nix_blkaddr(rvu, pcifunc);
+
+ /* MCAM RX rule for a PF/VF already exists as default unicast
+ * rules installed by AF. Hence change the channel in those
+ * rules to ignore channel so that packets with the required
+ * DMAC received from LBK(by other PF/VFs in system) or from
+ * external world (from wire) are accepted.
+ */
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+ if (err) {
+ dev_err(rvu->dev, "RX rule for PF%d failed(%d)\n",
+ pf, err);
+ return err;
+ }
+
+ err = rvu_switch_install_tx_rule(rvu, pcifunc, start + entry);
+ if (err) {
+ dev_err(rvu->dev, "TX rule for PF%d failed(%d)\n",
+ pf, err);
+ return err;
+ }
+
+ rswitch->entry2pcifunc[entry++] = pcifunc;
+
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
+ for (vf = 0; vf < numvfs; vf++) {
+ pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+ rvu_get_nix_blkaddr(rvu, pcifunc);
+
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+ if (err) {
+ dev_err(rvu->dev,
+ "RX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ return err;
+ }
+
+ err = rvu_switch_install_tx_rule(rvu, pcifunc,
+ start + entry);
+ if (err) {
+ dev_err(rvu->dev,
+ "TX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ return err;
+ }
+
+ rswitch->entry2pcifunc[entry++] = pcifunc;
+ }
+ }
+
+ return 0;
+}
+
+void rvu_switch_enable(struct rvu *rvu)
+{
+ struct npc_mcam_alloc_entry_req alloc_req = { 0 };
+ struct npc_mcam_alloc_entry_rsp alloc_rsp = { 0 };
+ struct npc_delete_flow_req uninstall_req = { 0 };
+ struct npc_mcam_free_entry_req free_req = { 0 };
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ struct msg_rsp rsp;
+ int ret;
+
+ alloc_req.contig = true;
+ alloc_req.count = rvu->cgx_mapped_pfs + rvu->cgx_mapped_vfs;
+ ret = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
+ &alloc_rsp);
+ if (ret) {
+ dev_err(rvu->dev,
+ "Unable to allocate MCAM entries\n");
+ goto exit;
+ }
+
+ if (alloc_rsp.count != alloc_req.count) {
+ dev_err(rvu->dev,
+ "Unable to allocate %d MCAM entries, got %d\n",
+ alloc_req.count, alloc_rsp.count);
+ goto free_entries;
+ }
+
+ rswitch->entry2pcifunc = kcalloc(alloc_req.count, sizeof(u16),
+ GFP_KERNEL);
+ if (!rswitch->entry2pcifunc)
+ goto free_entries;
+
+ rswitch->used_entries = alloc_rsp.count;
+ rswitch->start_entry = alloc_rsp.entry;
+
+ ret = rvu_switch_install_rules(rvu);
+ if (ret)
+ goto uninstall_rules;
+
+ return;
+
+uninstall_rules:
+ uninstall_req.start = rswitch->start_entry;
+ uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1;
+ rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+ kfree(rswitch->entry2pcifunc);
+free_entries:
+ free_req.all = 1;
+ rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+exit:
+ return;
+}
+
+void rvu_switch_disable(struct rvu *rvu)
+{
+ struct npc_delete_flow_req uninstall_req = { 0 };
+ struct npc_mcam_free_entry_req free_req = { 0 };
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ struct rvu_hwinfo *hw = rvu->hw;
+ int pf, vf, numvfs;
+ struct msg_rsp rsp;
+ u16 pcifunc;
+ int err;
+
+ if (!rswitch->used_entries)
+ return;
+
+ for (pf = 1; pf < hw->total_pfs; pf++) {
+ if (!is_pf_cgxmapped(rvu, pf))
+ continue;
+
+ pcifunc = pf << 10;
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+ if (err)
+ dev_err(rvu->dev,
+ "Reverting RX rule for PF%d failed(%d)\n",
+ pf, err);
+
+ rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
+ for (vf = 0; vf < numvfs; vf++) {
+ pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+ err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
+ if (err)
+ dev_err(rvu->dev,
+ "Reverting RX rule for PF%dVF%d failed(%d)\n",
+ pf, vf, err);
+ }
+ }
+
+ uninstall_req.start = rswitch->start_entry;
+ uninstall_req.end = rswitch->start_entry + rswitch->used_entries - 1;
+ free_req.all = 1;
+ rvu_mbox_handler_npc_delete_flow(rvu, &uninstall_req, &rsp);
+ rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, &rsp);
+ rswitch->used_entries = 0;
+ kfree(rswitch->entry2pcifunc);
+}
+
+void rvu_switch_update_rules(struct rvu *rvu, u16 pcifunc)
+{
+ struct rvu_switch *rswitch = &rvu->rswitch;
+ u32 max = rswitch->used_entries;
+ u16 entry;
+
+ if (!rswitch->used_entries)
+ return;
+
+ for (entry = 0; entry < max; entry++) {
+ if (rswitch->entry2pcifunc[entry] == pcifunc)
+ break;
+ }
+
+ if (entry >= max)
+ return;
+
+ rvu_switch_install_tx_rule(rvu, pcifunc, rswitch->start_entry + entry);
+ rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 7cccd802c4ed..70fcc1fd962f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -924,12 +924,14 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
aq->cq.drop = RQ_DROP_LVL_CQ(pfvf->hw.rq_skid, cq->cqe_cnt);
aq->cq.drop_ena = 1;
- /* Enable receive CQ backpressure */
- aq->cq.bp_ena = 1;
- aq->cq.bpid = pfvf->bpid[0];
+ if (!is_otx2_lbkvf(pfvf->pdev)) {
+ /* Enable receive CQ backpressure */
+ aq->cq.bp_ena = 1;
+ aq->cq.bpid = pfvf->bpid[0];
- /* Set backpressure level is same as cq pass level */
- aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt);
+ /* Set backpressure level is same as cq pass level */
+ aq->cq.bp = RQ_PASS_LVL_CQ(pfvf->hw.rq_skid, qset->rqe_cnt);
+ }
}
/* Fill AQ info */
@@ -1186,7 +1188,7 @@ static int otx2_aura_init(struct otx2_nic *pfvf, int aura_id,
aq->aura.fc_hyst_bits = 0; /* Store count on all updates */
/* Enable backpressure for RQ aura */
- if (aura_id < pfvf->hw.rqpool_cnt) {
+ if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) {
aq->aura.bp_ena = 0;
aq->aura.nix0_bpid = pfvf->bpid[0];
/* Set backpressure level for RQ's Aura */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 8df748e0677b..b906a0eb6e0d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -298,15 +298,14 @@ static int otx2_set_channels(struct net_device *dev,
err = otx2_set_real_num_queues(dev, channel->tx_count,
channel->rx_count);
if (err)
- goto fail;
+ return err;
pfvf->hw.rx_queues = channel->rx_count;
pfvf->hw.tx_queues = channel->tx_count;
pfvf->qset.cq_cnt = pfvf->hw.tx_queues + pfvf->hw.rx_queues;
-fail:
if (if_up)
- dev->netdev_ops->ndo_open(dev);
+ err = dev->netdev_ops->ndo_open(dev);
netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
pfvf->hw.tx_queues, pfvf->hw.rx_queues);
@@ -410,7 +409,7 @@ static int otx2_set_ringparam(struct net_device *netdev,
qs->rqe_cnt = rx_count;
if (if_up)
- netdev->netdev_ops->ndo_open(netdev);
+ return netdev->netdev_ops->ndo_open(netdev);
return 0;
}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index f300b807a85b..2c24944a4dba 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -1662,6 +1662,7 @@ int otx2_open(struct net_device *netdev)
err_tx_stop_queues:
netif_tx_stop_all_queues(netdev);
netif_carrier_off(netdev);
+ pf->flags |= OTX2_FLAG_INTF_DOWN;
err_free_cints:
otx2_free_cints(pf, qidx);
vec = pci_irq_vector(pf->pdev,
@@ -1689,6 +1690,10 @@ int otx2_stop(struct net_device *netdev)
struct otx2_rss_info *rss;
int qidx, vec, wrk;
+ /* If the DOWN flag is set resources are already freed */
+ if (pf->flags & OTX2_FLAG_INTF_DOWN)
+ return 0;
+
netif_carrier_off(netdev);
netif_tx_stop_all_queues(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 00c84656b2e7..28ac4693da3c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3535,6 +3535,7 @@ slave_start:
if (!SRIOV_VALID_STATE(dev->flags)) {
mlx4_err(dev, "Invalid SRIOV state\n");
+ err = -EINVAL;
goto err_close;
}
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index ceebfc20f65e..def2156e50ee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -500,10 +500,7 @@ static int next_phys_dev(struct device *dev, const void *data)
return 1;
}
-/* This function is called with two flows:
- * 1. During initialization of mlx5_core_dev and we don't need to lock it.
- * 2. During LAG configure stage and caller holds &mlx5_intf_mutex.
- */
+/* Must be called with intf_mutex held */
struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
{
struct auxiliary_device *adev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 150c8e82c738..2cbf18c967f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -471,6 +471,15 @@ static void mlx5e_build_rx_cq_param(struct mlx5_core_dev *mdev,
param->cq_period_mode = params->rx_cq_moderation.cq_period_mode;
}
+static u8 rq_end_pad_mode(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
+{
+ bool ro = pcie_relaxed_ordering_enabled(mdev->pdev) &&
+ MLX5_CAP_GEN(mdev, relaxed_ordering_write);
+
+ return ro && params->lro_en ?
+ MLX5_WQ_END_PAD_MODE_NONE : MLX5_WQ_END_PAD_MODE_ALIGN;
+}
+
int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
struct mlx5e_params *params,
struct mlx5e_xsk_param *xsk,
@@ -508,7 +517,7 @@ int mlx5e_build_rq_param(struct mlx5_core_dev *mdev,
}
MLX5_SET(wq, wq, wq_type, params->rq_wq_type);
- MLX5_SET(wq, wq, end_padding_mode, MLX5_WQ_END_PAD_MODE_ALIGN);
+ MLX5_SET(wq, wq, end_padding_mode, rq_end_pad_mode(mdev, params));
MLX5_SET(wq, wq, log_wq_stride,
mlx5e_get_rqwq_log_stride(params->rq_wq_type, ndsegs));
MLX5_SET(wq, wq, pd, mdev->mlx5e_res.hw_objs.pdn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 778e229310a9..efef4adce086 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -482,8 +482,11 @@ static void mlx5e_ptp_build_params(struct mlx5e_ptp *c,
params->log_sq_size = orig->log_sq_size;
mlx5e_ptp_build_sq_param(c->mdev, params, &cparams->txq_sq_param);
}
- if (test_bit(MLX5E_PTP_STATE_RX, c->state))
+ /* RQ */
+ if (test_bit(MLX5E_PTP_STATE_RX, c->state)) {
+ params->vlan_strip_disable = orig->vlan_strip_disable;
mlx5e_ptp_build_rq_param(c->mdev, c->netdev, c->priv->q_counter, cparams);
+ }
}
static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
@@ -494,7 +497,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
int err;
rq->wq_type = params->rq_wq_type;
- rq->pdev = mdev->device;
+ rq->pdev = c->pdev;
rq->netdev = priv->netdev;
rq->priv = priv;
rq->clock = &mdev->clock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 86ab4e864fe6..7f94508594fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -37,7 +37,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params
struct mlx5e_priv *priv = t->priv;
rq->wq_type = params->rq_wq_type;
- rq->pdev = mdev->device;
+ rq->pdev = t->pdev;
rq->netdev = priv->netdev;
rq->priv = priv;
rq->clock = &mdev->clock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d09e65557e75..37c440837945 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3384,7 +3384,7 @@ static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool en
static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
{
- int err = 0;
+ int err;
int i;
for (i = 0; i < chs->num; i++) {
@@ -3392,6 +3392,8 @@ static int mlx5e_modify_channels_vsd(struct mlx5e_channels *chs, bool vsd)
if (err)
return err;
}
+ if (chs->ptp && test_bit(MLX5E_PTP_STATE_RX, chs->ptp->state))
+ return mlx5e_modify_rq_vsd(&chs->ptp->rq, vsd);
return 0;
}
@@ -3829,6 +3831,24 @@ int mlx5e_set_features(struct net_device *netdev, netdev_features_t features)
return 0;
}
+static netdev_features_t mlx5e_fix_uplink_rep_features(struct net_device *netdev,
+ netdev_features_t features)
+{
+ features &= ~NETIF_F_HW_TLS_RX;
+ if (netdev->features & NETIF_F_HW_TLS_RX)
+ netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
+
+ features &= ~NETIF_F_HW_TLS_TX;
+ if (netdev->features & NETIF_F_HW_TLS_TX)
+ netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
+
+ features &= ~NETIF_F_NTUPLE;
+ if (netdev->features & NETIF_F_NTUPLE)
+ netdev_warn(netdev, "Disabling ntuple, not supported in switchdev mode\n");
+
+ return features;
+}
+
static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
netdev_features_t features)
{
@@ -3860,15 +3880,8 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
netdev_warn(netdev, "Disabling rxhash, not supported when CQE compress is active\n");
}
- if (mlx5e_is_uplink_rep(priv)) {
- features &= ~NETIF_F_HW_TLS_RX;
- if (netdev->features & NETIF_F_HW_TLS_RX)
- netdev_warn(netdev, "Disabling hw_tls_rx, not supported in switchdev mode\n");
-
- features &= ~NETIF_F_HW_TLS_TX;
- if (netdev->features & NETIF_F_HW_TLS_TX)
- netdev_warn(netdev, "Disabling hw_tls_tx, not supported in switchdev mode\n");
- }
+ if (mlx5e_is_uplink_rep(priv))
+ features = mlx5e_fix_uplink_rep_features(netdev, features);
mutex_unlock(&priv->state_lock);
@@ -4859,6 +4872,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
if (MLX5_CAP_ETH(mdev, scatter_fcs))
netdev->hw_features |= NETIF_F_RXFCS;
+ if (mlx5_qos_is_supported(mdev))
+ netdev->hw_features |= NETIF_F_HW_TC;
+
netdev->features = netdev->hw_features;
/* Defaults */
@@ -4879,8 +4895,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
netdev->hw_features |= NETIF_F_NTUPLE;
#endif
}
- if (mlx5_qos_is_supported(mdev))
- netdev->features |= NETIF_F_HW_TC;
netdev->features |= NETIF_F_HIGHDMA;
netdev->features |= NETIF_F_HW_VLAN_STAG_FILTER;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 629a61e8022f..d273758255c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -452,12 +452,32 @@ static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv,
static
struct mlx5_core_dev *mlx5e_hairpin_get_mdev(struct net *net, int ifindex)
{
+ struct mlx5_core_dev *mdev;
struct net_device *netdev;
struct mlx5e_priv *priv;
- netdev = __dev_get_by_index(net, ifindex);
+ netdev = dev_get_by_index(net, ifindex);
+ if (!netdev)
+ return ERR_PTR(-ENODEV);
+
priv = netdev_priv(netdev);
- return priv->mdev;
+ mdev = priv->mdev;
+ dev_put(netdev);
+
+ /* Mirred tc action holds a refcount on the ifindex net_device (see
+ * net/sched/act_mirred.c:tcf_mirred_get_dev). So, it's okay to continue using mdev
+ * after dev_put(netdev), while we're in the context of adding a tc flow.
+ *
+ * The mdev pointer corresponds to the peer/out net_device of a hairpin. It is then
+ * stored in a hairpin object, which exists until all flows, that refer to it, get
+ * removed.
+ *
+ * On the other hand, after a hairpin object has been created, the peer net_device may
+ * be removed/unbound while there are still some hairpin flows that are using it. This
+ * case is handled by mlx5e_tc_hairpin_update_dead_peer, which is hooked to
+ * NETDEV_UNREGISTER event of the peer net_device.
+ */
+ return mdev;
}
static int mlx5e_hairpin_create_transport(struct mlx5e_hairpin *hp)
@@ -666,6 +686,10 @@ mlx5e_hairpin_create(struct mlx5e_priv *priv, struct mlx5_hairpin_params *params
func_mdev = priv->mdev;
peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex);
+ if (IS_ERR(peer_mdev)) {
+ err = PTR_ERR(peer_mdev);
+ goto create_pair_err;
+ }
pair = mlx5_core_hairpin_create(func_mdev, peer_mdev, params);
if (IS_ERR(pair)) {
@@ -804,6 +828,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
int err;
peer_mdev = mlx5e_hairpin_get_mdev(dev_net(priv->netdev), peer_ifindex);
+ if (IS_ERR(peer_mdev)) {
+ NL_SET_ERR_MSG_MOD(extack, "invalid ifindex of mirred device");
+ return PTR_ERR(peer_mdev);
+ }
+
if (!MLX5_CAP_GEN(priv->mdev, hairpin) || !MLX5_CAP_GEN(peer_mdev, hairpin)) {
NL_SET_ERR_MSG_MOD(extack, "hairpin is not supported");
return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 48cac5bf606d..d562edf5b0bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -636,7 +636,7 @@ struct esw_vport_tbl_namespace {
};
struct mlx5_vport_tbl_attr {
- u16 chain;
+ u32 chain;
u16 prio;
u16 vport;
const struct esw_vport_tbl_namespace *vport_ns;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 7579f3402776..011e766e4f67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -382,10 +382,11 @@ esw_setup_vport_dest(struct mlx5_flow_destination *dest, struct mlx5_flow_act *f
{
dest[dest_idx].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
dest[dest_idx].vport.num = esw_attr->dests[attr_idx].rep->vport;
- dest[dest_idx].vport.vhca_id =
- MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
- if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+ if (MLX5_CAP_ESW(esw->dev, merged_eswitch)) {
+ dest[dest_idx].vport.vhca_id =
+ MLX5_CAP_GEN(esw_attr->dests[attr_idx].mdev, vhca_id);
dest[dest_idx].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+ }
if (esw_attr->dests[attr_idx].flags & MLX5_ESW_DEST_ENCAP) {
if (pkt_reformat) {
flow_act->action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -2367,6 +2368,9 @@ static int mlx5_esw_offloads_devcom_event(int event,
switch (event) {
case ESW_OFFLOADS_DEVCOM_PAIR:
+ if (mlx5_get_next_phys_dev(esw->dev) != peer_esw->dev)
+ break;
+
if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index d7bf0a3e4a52..c0697e1b7118 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1024,17 +1024,19 @@ static int connect_fwd_rules(struct mlx5_core_dev *dev,
static int connect_flow_table(struct mlx5_core_dev *dev, struct mlx5_flow_table *ft,
struct fs_prio *prio)
{
- struct mlx5_flow_table *next_ft;
+ struct mlx5_flow_table *next_ft, *first_ft;
int err = 0;
/* Connect_prev_fts and update_root_ft_create are mutually exclusive */
- if (list_empty(&prio->node.children)) {
+ first_ft = list_first_entry_or_null(&prio->node.children,
+ struct mlx5_flow_table, node.list);
+ if (!first_ft || first_ft->level > ft->level) {
err = connect_prev_fts(dev, ft, prio);
if (err)
return err;
- next_ft = find_next_chained_ft(prio);
+ next_ft = first_ft ? first_ft : find_next_chained_ft(prio);
err = connect_fwd_rules(dev, ft, next_ft);
if (err)
return err;
@@ -2120,7 +2122,7 @@ static int disconnect_flow_table(struct mlx5_flow_table *ft)
node.list) == ft))
return 0;
- next_ft = find_next_chained_ft(prio);
+ next_ft = find_next_ft(ft);
err = connect_fwd_rules(dev, next_ft, ft);
if (err)
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 9ff163c5bcde..9abeb80ffa31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -626,8 +626,16 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
}
fw_reporter_ctx.err_synd = health->synd;
fw_reporter_ctx.miss_counter = health->miss_counter;
- devlink_health_report(health->fw_fatal_reporter,
- "FW fatal error reported", &fw_reporter_ctx);
+ if (devlink_health_report(health->fw_fatal_reporter,
+ "FW fatal error reported", &fw_reporter_ctx) == -ECANCELED) {
+ /* If recovery wasn't performed, due to grace period,
+ * unload the driver. This ensures that the driver
+ * closes all its resources and it is not subjected to
+ * requests from the kernel.
+ */
+ mlx5_core_err(dev, "Driver is in error state. Unloading\n");
+ mlx5_unload_one(dev);
+ }
}
static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
diff --git a/drivers/net/ethernet/microchip/sparx5/Kconfig b/drivers/net/ethernet/microchip/sparx5/Kconfig
index ac403d43c74c..7bdbb2d09a14 100644
--- a/drivers/net/ethernet/microchip/sparx5/Kconfig
+++ b/drivers/net/ethernet/microchip/sparx5/Kconfig
@@ -3,6 +3,7 @@ config SPARX5_SWITCH
depends on NET_SWITCHDEV
depends on HAS_IOMEM
depends on OF
+ depends on ARCH_SPARX5 || COMPILE_TEST
select PHYLINK
select PHY_SPARX5_SERDES
select RESET_CONTROLLER
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index af3a5368529c..e795fa63ca12 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -29,7 +29,7 @@ static const u8 ionic_qtype_versions[IONIC_QTYPE_MAX] = {
*/
};
-static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode);
+static void ionic_lif_rx_mode(struct ionic_lif *lif);
static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr);
static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr);
static void ionic_link_status_check(struct ionic_lif *lif);
@@ -53,7 +53,19 @@ static void ionic_dim_work(struct work_struct *work)
cur_moder = net_dim_get_rx_moderation(dim->mode, dim->profile_ix);
qcq = container_of(dim, struct ionic_qcq, dim);
new_coal = ionic_coal_usec_to_hw(qcq->q.lif->ionic, cur_moder.usec);
- qcq->intr.dim_coal_hw = new_coal ? new_coal : 1;
+ new_coal = new_coal ? new_coal : 1;
+
+ if (qcq->intr.dim_coal_hw != new_coal) {
+ unsigned int qi = qcq->cq.bound_q->index;
+ struct ionic_lif *lif = qcq->q.lif;
+
+ qcq->intr.dim_coal_hw = new_coal;
+
+ ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
+ lif->rxqcqs[qi]->intr.index,
+ qcq->intr.dim_coal_hw);
+ }
+
dim->state = DIM_START_MEASURE;
}
@@ -77,7 +89,7 @@ static void ionic_lif_deferred_work(struct work_struct *work)
switch (w->type) {
case IONIC_DW_TYPE_RX_MODE:
- ionic_lif_rx_mode(lif, w->rx_mode);
+ ionic_lif_rx_mode(lif);
break;
case IONIC_DW_TYPE_RX_ADDR_ADD:
ionic_lif_addr_add(lif, w->addr);
@@ -1301,10 +1313,8 @@ static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr)
return 0;
}
-static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add,
- bool can_sleep)
+static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add)
{
- struct ionic_deferred_work *work;
unsigned int nmfilters;
unsigned int nufilters;
@@ -1330,97 +1340,46 @@ static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add,
lif->nucast--;
}
- if (!can_sleep) {
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work)
- return -ENOMEM;
- work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD :
- IONIC_DW_TYPE_RX_ADDR_DEL;
- memcpy(work->addr, addr, ETH_ALEN);
- netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n",
- add ? "add" : "del", addr);
- ionic_lif_deferred_enqueue(&lif->deferred, work);
- } else {
- netdev_dbg(lif->netdev, "rx_filter %s %pM\n",
- add ? "add" : "del", addr);
- if (add)
- return ionic_lif_addr_add(lif, addr);
- else
- return ionic_lif_addr_del(lif, addr);
- }
+ netdev_dbg(lif->netdev, "rx_filter %s %pM\n",
+ add ? "add" : "del", addr);
+ if (add)
+ return ionic_lif_addr_add(lif, addr);
+ else
+ return ionic_lif_addr_del(lif, addr);
return 0;
}
static int ionic_addr_add(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_SLEEP);
-}
-
-static int ionic_ndo_addr_add(struct net_device *netdev, const u8 *addr)
-{
- return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR, CAN_NOT_SLEEP);
+ return ionic_lif_addr(netdev_priv(netdev), addr, ADD_ADDR);
}
static int ionic_addr_del(struct net_device *netdev, const u8 *addr)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_SLEEP);
+ return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR);
}
-static int ionic_ndo_addr_del(struct net_device *netdev, const u8 *addr)
+static void ionic_lif_rx_mode(struct ionic_lif *lif)
{
- return ionic_lif_addr(netdev_priv(netdev), addr, DEL_ADDR, CAN_NOT_SLEEP);
-}
-
-static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode)
-{
- struct ionic_admin_ctx ctx = {
- .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
- .cmd.rx_mode_set = {
- .opcode = IONIC_CMD_RX_MODE_SET,
- .lif_index = cpu_to_le16(lif->index),
- .rx_mode = cpu_to_le16(rx_mode),
- },
- };
+ struct net_device *netdev = lif->netdev;
+ unsigned int nfilters;
+ unsigned int nd_flags;
char buf[128];
- int err;
+ u16 rx_mode;
int i;
#define REMAIN(__x) (sizeof(buf) - (__x))
- i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:",
- lif->rx_mode, rx_mode);
- if (rx_mode & IONIC_RX_MODE_F_UNICAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST");
- if (rx_mode & IONIC_RX_MODE_F_MULTICAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST");
- if (rx_mode & IONIC_RX_MODE_F_BROADCAST)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST");
- if (rx_mode & IONIC_RX_MODE_F_PROMISC)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC");
- if (rx_mode & IONIC_RX_MODE_F_ALLMULTI)
- i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI");
- netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf);
-
- err = ionic_adminq_post_wait(lif, &ctx);
- if (err)
- netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n",
- rx_mode, err);
- else
- lif->rx_mode = rx_mode;
-}
+ mutex_lock(&lif->config_lock);
-static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
-{
- struct ionic_lif *lif = netdev_priv(netdev);
- struct ionic_deferred_work *work;
- unsigned int nfilters;
- unsigned int rx_mode;
+ /* grab the flags once for local use */
+ nd_flags = netdev->flags;
rx_mode = IONIC_RX_MODE_F_UNICAST;
- rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0;
- rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0;
- rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0;
- rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0;
+ rx_mode |= (nd_flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0;
+ rx_mode |= (nd_flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0;
+ rx_mode |= (nd_flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0;
+ rx_mode |= (nd_flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0;
/* sync unicast addresses
* next check to see if we're in an overflow state
@@ -1429,49 +1388,83 @@ static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
* we remove our overflow flag and check the netdev flags
* to see if we can disable NIC PROMISC
*/
- if (can_sleep)
- __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
- else
- __dev_uc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
+ __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_ucast_filters);
if (netdev_uc_count(netdev) + 1 > nfilters) {
rx_mode |= IONIC_RX_MODE_F_PROMISC;
lif->uc_overflow = true;
} else if (lif->uc_overflow) {
lif->uc_overflow = false;
- if (!(netdev->flags & IFF_PROMISC))
+ if (!(nd_flags & IFF_PROMISC))
rx_mode &= ~IONIC_RX_MODE_F_PROMISC;
}
/* same for multicast */
- if (can_sleep)
- __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
- else
- __dev_mc_sync(netdev, ionic_ndo_addr_add, ionic_ndo_addr_del);
+ __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del);
nfilters = le32_to_cpu(lif->identity->eth.max_mcast_filters);
if (netdev_mc_count(netdev) > nfilters) {
rx_mode |= IONIC_RX_MODE_F_ALLMULTI;
lif->mc_overflow = true;
} else if (lif->mc_overflow) {
lif->mc_overflow = false;
- if (!(netdev->flags & IFF_ALLMULTI))
+ if (!(nd_flags & IFF_ALLMULTI))
rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI;
}
+ i = scnprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:",
+ lif->rx_mode, rx_mode);
+ if (rx_mode & IONIC_RX_MODE_F_UNICAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST");
+ if (rx_mode & IONIC_RX_MODE_F_MULTICAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST");
+ if (rx_mode & IONIC_RX_MODE_F_BROADCAST)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST");
+ if (rx_mode & IONIC_RX_MODE_F_PROMISC)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC");
+ if (rx_mode & IONIC_RX_MODE_F_ALLMULTI)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI");
+ if (rx_mode & IONIC_RX_MODE_F_RDMA_SNIFFER)
+ i += scnprintf(&buf[i], REMAIN(i), " RX_MODE_F_RDMA_SNIFFER");
+ netdev_dbg(netdev, "lif%d %s\n", lif->index, buf);
+
if (lif->rx_mode != rx_mode) {
- if (!can_sleep) {
- work = kzalloc(sizeof(*work), GFP_ATOMIC);
- if (!work) {
- netdev_err(lif->netdev, "rxmode change dropped\n");
- return;
- }
- work->type = IONIC_DW_TYPE_RX_MODE;
- work->rx_mode = rx_mode;
- netdev_dbg(lif->netdev, "deferred: rx_mode\n");
- ionic_lif_deferred_enqueue(&lif->deferred, work);
- } else {
- ionic_lif_rx_mode(lif, rx_mode);
+ struct ionic_admin_ctx ctx = {
+ .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work),
+ .cmd.rx_mode_set = {
+ .opcode = IONIC_CMD_RX_MODE_SET,
+ .lif_index = cpu_to_le16(lif->index),
+ },
+ };
+ int err;
+
+ ctx.cmd.rx_mode_set.rx_mode = cpu_to_le16(rx_mode);
+ err = ionic_adminq_post_wait(lif, &ctx);
+ if (err)
+ netdev_warn(netdev, "set rx_mode 0x%04x failed: %d\n",
+ rx_mode, err);
+ else
+ lif->rx_mode = rx_mode;
+ }
+
+ mutex_unlock(&lif->config_lock);
+}
+
+static void ionic_set_rx_mode(struct net_device *netdev, bool can_sleep)
+{
+ struct ionic_lif *lif = netdev_priv(netdev);
+ struct ionic_deferred_work *work;
+
+ if (!can_sleep) {
+ work = kzalloc(sizeof(*work), GFP_ATOMIC);
+ if (!work) {
+ netdev_err(lif->netdev, "rxmode change dropped\n");
+ return;
}
+ work->type = IONIC_DW_TYPE_RX_MODE;
+ netdev_dbg(lif->netdev, "deferred: rx_mode\n");
+ ionic_lif_deferred_enqueue(&lif->deferred, work);
+ } else {
+ ionic_lif_rx_mode(lif);
}
}
@@ -3058,6 +3051,7 @@ void ionic_lif_deinit(struct ionic_lif *lif)
ionic_lif_qcq_deinit(lif, lif->notifyqcq);
ionic_lif_qcq_deinit(lif, lif->adminqcq);
+ mutex_destroy(&lif->config_lock);
mutex_destroy(&lif->queue_lock);
ionic_lif_reset(lif);
}
@@ -3185,7 +3179,7 @@ static int ionic_station_set(struct ionic_lif *lif)
*/
if (!ether_addr_equal(ctx.comp.lif_getattr.mac,
netdev->dev_addr))
- ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
} else {
/* Update the netdev mac with the device's mac */
memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len);
@@ -3202,7 +3196,7 @@ static int ionic_station_set(struct ionic_lif *lif)
netdev_dbg(lif->netdev, "adding station MAC addr %pM\n",
netdev->dev_addr);
- ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR, CAN_SLEEP);
+ ionic_lif_addr(lif, netdev->dev_addr, ADD_ADDR);
return 0;
}
@@ -3225,6 +3219,7 @@ int ionic_lif_init(struct ionic_lif *lif)
lif->hw_index = le16_to_cpu(comp.hw_index);
mutex_init(&lif->queue_lock);
+ mutex_init(&lif->config_lock);
/* now that we have the hw_index we can figure out our doorbell page */
lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
index 346506f01715..69ab59fedb6c 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h
@@ -108,7 +108,6 @@ struct ionic_deferred_work {
struct list_head list;
enum ionic_deferred_work_type type;
union {
- unsigned int rx_mode;
u8 addr[ETH_ALEN];
u8 fw_status;
};
@@ -179,6 +178,7 @@ struct ionic_lif {
unsigned int index;
unsigned int hw_index;
struct mutex queue_lock; /* lock for queue structures */
+ struct mutex config_lock; /* lock for config actions */
spinlock_t adminq_lock; /* lock for AdminQ operations */
struct ionic_qcq *adminqcq;
struct ionic_qcq *notifyqcq;
@@ -199,7 +199,7 @@ struct ionic_lif {
unsigned int nrxq_descs;
u32 rx_copybreak;
u64 rxq_features;
- unsigned int rx_mode;
+ u16 rx_mode;
u64 hw_features;
bool registered;
bool mc_overflow;
@@ -302,7 +302,7 @@ int ionic_lif_identify(struct ionic *ionic, u8 lif_type,
int ionic_lif_size(struct ionic *ionic);
#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-int ionic_lif_hwstamp_replay(struct ionic_lif *lif);
+void ionic_lif_hwstamp_replay(struct ionic_lif *lif);
int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr);
int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr);
ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter);
@@ -311,10 +311,7 @@ void ionic_lif_unregister_phc(struct ionic_lif *lif);
void ionic_lif_alloc_phc(struct ionic_lif *lif);
void ionic_lif_free_phc(struct ionic_lif *lif);
#else
-static inline int ionic_lif_hwstamp_replay(struct ionic_lif *lif)
-{
- return -EOPNOTSUPP;
-}
+static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {}
static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
{
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
index a87c87e86aef..6e2403c71608 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
@@ -188,6 +188,9 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
struct hwtstamp_config config;
int err;
+ if (!lif->phc || !lif->phc->ptp)
+ return -EOPNOTSUPP;
+
if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
return -EFAULT;
@@ -203,15 +206,16 @@ int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr)
return 0;
}
-int ionic_lif_hwstamp_replay(struct ionic_lif *lif)
+void ionic_lif_hwstamp_replay(struct ionic_lif *lif)
{
int err;
+ if (!lif->phc || !lif->phc->ptp)
+ return;
+
err = ionic_lif_hwstamp_set_ts_config(lif, NULL);
if (err)
netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err);
-
- return err;
}
int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 08934888575c..08870190e4d2 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -274,12 +274,11 @@ static void ionic_rx_clean(struct ionic_queue *q,
}
}
- if (likely(netdev->features & NETIF_F_RXCSUM)) {
- if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) {
- skb->ip_summed = CHECKSUM_COMPLETE;
- skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
- stats->csum_complete++;
- }
+ if (likely(netdev->features & NETIF_F_RXCSUM) &&
+ (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC)) {
+ skb->ip_summed = CHECKSUM_COMPLETE;
+ skb->csum = (__force __wsum)le16_to_cpu(comp->csum);
+ stats->csum_complete++;
} else {
stats->csum_none++;
}
@@ -451,11 +450,12 @@ void ionic_rx_empty(struct ionic_queue *q)
q->tail_idx = 0;
}
-static void ionic_dim_update(struct ionic_qcq *qcq)
+static void ionic_dim_update(struct ionic_qcq *qcq, int napi_mode)
{
struct dim_sample dim_sample;
struct ionic_lif *lif;
unsigned int qi;
+ u64 pkts, bytes;
if (!qcq->intr.dim_coal_hw)
return;
@@ -463,14 +463,23 @@ static void ionic_dim_update(struct ionic_qcq *qcq)
lif = qcq->q.lif;
qi = qcq->cq.bound_q->index;
- ionic_intr_coal_init(lif->ionic->idev.intr_ctrl,
- lif->rxqcqs[qi]->intr.index,
- qcq->intr.dim_coal_hw);
+ switch (napi_mode) {
+ case IONIC_LIF_F_TX_DIM_INTR:
+ pkts = lif->txqstats[qi].pkts;
+ bytes = lif->txqstats[qi].bytes;
+ break;
+ case IONIC_LIF_F_RX_DIM_INTR:
+ pkts = lif->rxqstats[qi].pkts;
+ bytes = lif->rxqstats[qi].bytes;
+ break;
+ default:
+ pkts = lif->txqstats[qi].pkts + lif->rxqstats[qi].pkts;
+ bytes = lif->txqstats[qi].bytes + lif->rxqstats[qi].bytes;
+ break;
+ }
dim_update_sample(qcq->cq.bound_intr->rearm_count,
- lif->txqstats[qi].pkts,
- lif->txqstats[qi].bytes,
- &dim_sample);
+ pkts, bytes, &dim_sample);
net_dim(&qcq->dim, dim_sample);
}
@@ -491,7 +500,7 @@ int ionic_tx_napi(struct napi_struct *napi, int budget)
ionic_tx_service, NULL, NULL);
if (work_done < budget && napi_complete_done(napi, work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, IONIC_LIF_F_TX_DIM_INTR);
flags |= IONIC_INTR_CRED_UNMASK;
cq->bound_intr->rearm_count++;
}
@@ -530,7 +539,7 @@ int ionic_rx_napi(struct napi_struct *napi, int budget)
ionic_rx_fill(cq->bound_q);
if (work_done < budget && napi_complete_done(napi, work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, IONIC_LIF_F_RX_DIM_INTR);
flags |= IONIC_INTR_CRED_UNMASK;
cq->bound_intr->rearm_count++;
}
@@ -576,7 +585,7 @@ int ionic_txrx_napi(struct napi_struct *napi, int budget)
ionic_rx_fill(rxcq->bound_q);
if (rx_work_done < budget && napi_complete_done(napi, rx_work_done)) {
- ionic_dim_update(qcq);
+ ionic_dim_update(qcq, 0);
flags |= IONIC_INTR_CRED_UNMASK;
rxcq->bound_intr->rearm_count++;
}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index c59b72c90293..a2e4dfb5cb44 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -831,7 +831,7 @@ int qede_configure_vlan_filters(struct qede_dev *edev)
int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
{
struct qede_dev *edev = netdev_priv(dev);
- struct qede_vlan *vlan = NULL;
+ struct qede_vlan *vlan;
int rc = 0;
DP_VERBOSE(edev, NETIF_MSG_IFDOWN, "Removing vlan 0x%04x\n", vid);
@@ -842,7 +842,7 @@ int qede_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
if (vlan->vid == vid)
break;
- if (!vlan || (vlan->vid != vid)) {
+ if (list_entry_is_head(vlan, &edev->vlan_list, list)) {
DP_VERBOSE(edev, (NETIF_MSG_IFUP | NETIF_MSG_IFDOWN),
"Vlan isn't configured\n");
goto out;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 2376b2729633..c00ad57575ea 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -154,7 +154,7 @@ static int ql_wait_for_drvr_lock(struct ql3_adapter *qdev)
"driver lock acquired\n");
return 1;
}
- ssleep(1);
+ mdelay(1000);
} while (++i < 10);
netdev_err(qdev->ndev, "Timed out waiting for driver lock...\n");
@@ -3274,7 +3274,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev)
if ((value & ISP_CONTROL_SR) == 0)
break;
- ssleep(1);
+ mdelay(1000);
} while ((--max_wait_time));
/*
@@ -3310,7 +3310,7 @@ static int ql_adapter_reset(struct ql3_adapter *qdev)
ispControlStatus);
if ((value & ISP_CONTROL_FSR) == 0)
break;
- ssleep(1);
+ mdelay(1000);
} while ((--max_wait_time));
}
if (max_wait_time == 0)
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index f744557c33a3..c7af5bc3b8af 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5084,7 +5084,8 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
new_bus->priv = tp;
new_bus->parent = &pdev->dev;
new_bus->irq[0] = PHY_MAC_INTERRUPT;
- snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x", pci_dev_id(pdev));
+ snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
+ pci_domain_nr(pdev->bus), pci_dev_id(pdev));
new_bus->read = r8169_mdio_read_reg;
new_bus->write = r8169_mdio_write_reg;
diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 86a1eb0634e8..80e62ca2e3d3 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -864,7 +864,7 @@ enum GECMR_BIT {
/* The Ethernet AVB descriptor definitions. */
struct ravb_desc {
- __le16 ds; /* Descriptor size */
+ __le16 ds; /* Descriptor size */
u8 cc; /* Content control MSBs (reserved) */
u8 die_dt; /* Descriptor interrupt enable and type */
__le32 dptr; /* Descriptor pointer */
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 69c50f81e1cb..805397088850 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -920,7 +920,7 @@ static int ravb_poll(struct napi_struct *napi, int budget)
if (ravb_rx(ndev, &quota, q))
goto out;
- /* Processing RX Descriptor Ring */
+ /* Processing TX Descriptor Ring */
spin_lock_irqsave(&priv->lock, flags);
/* Clear TX interrupt */
ravb_write(ndev, ~(mask | TIS_RESERVED), TIS);
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index ca9c00b7f588..cff87de9178a 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -443,7 +443,7 @@ static int sis900_probe(struct pci_dev *pci_dev,
#endif
/* setup various bits in PCI command register */
- ret = pci_enable_device(pci_dev);
+ ret = pcim_enable_device(pci_dev);
if(ret) return ret;
i = dma_set_mask(&pci_dev->dev, DMA_BIT_MASK(32));
@@ -469,7 +469,7 @@ static int sis900_probe(struct pci_dev *pci_dev,
ioaddr = pci_iomap(pci_dev, 0, 0);
if (!ioaddr) {
ret = -ENOMEM;
- goto err_out_cleardev;
+ goto err_out;
}
sis_priv = netdev_priv(net_dev);
@@ -581,8 +581,6 @@ err_unmap_tx:
sis_priv->tx_ring_dma);
err_out_unmap:
pci_iounmap(pci_dev, ioaddr);
-err_out_cleardev:
- pci_release_regions(pci_dev);
err_out:
free_netdev(net_dev);
return ret;
@@ -2499,7 +2497,6 @@ static void sis900_remove(struct pci_dev *pci_dev)
sis_priv->tx_ring_dma);
pci_iounmap(pci_dev, sis_priv->ioaddr);
free_netdev(net_dev);
- pci_release_regions(pci_dev);
}
static int __maybe_unused sis900_suspend(struct device *dev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 67ba083eb90c..b21745368983 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -1249,6 +1249,7 @@ const struct stmmac_ops dwmac410_ops = {
.config_l3_filter = dwmac4_config_l3_filter,
.config_l4_filter = dwmac4_config_l4_filter,
.est_configure = dwmac5_est_configure,
+ .est_irq_status = dwmac5_est_irq_status,
.fpe_configure = dwmac5_fpe_configure,
.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
.fpe_irq_status = dwmac5_fpe_irq_status,
@@ -1300,6 +1301,7 @@ const struct stmmac_ops dwmac510_ops = {
.config_l3_filter = dwmac4_config_l3_filter,
.config_l4_filter = dwmac4_config_l4_filter,
.est_configure = dwmac5_est_configure,
+ .est_irq_status = dwmac5_est_irq_status,
.fpe_configure = dwmac5_fpe_configure,
.fpe_send_mpacket = dwmac5_fpe_send_mpacket,
.fpe_irq_status = dwmac5_fpe_irq_status,
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 74e748662ec0..860644d182ab 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -8191,8 +8191,9 @@ static int niu_pci_vpd_fetch(struct niu *np, u32 start)
err = niu_pci_vpd_scan_props(np, here, end);
if (err < 0)
return err;
+ /* ret == 1 is not an error */
if (err == 1)
- return -EINVAL;
+ return 0;
}
return 0;
}
diff --git a/drivers/net/ethernet/xscale/ptp_ixp46x.c b/drivers/net/ethernet/xscale/ptp_ixp46x.c
index 99d4d9439d05..a6fb88fd42f7 100644
--- a/drivers/net/ethernet/xscale/ptp_ixp46x.c
+++ b/drivers/net/ethernet/xscale/ptp_ixp46x.c
@@ -14,6 +14,8 @@
#include <linux/kernel.h>
#include <linux/ptp_clock_kernel.h>
#include <linux/soc/ixp4xx/cpu.h>
+#include <linux/module.h>
+#include <mach/ixp4xx-regs.h>
#include "ixp46x_ts.h"
diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 7bf3011b8e77..83aea5c5cd03 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -288,7 +288,7 @@ static void bcm54xx_adjust_rxrefclk(struct phy_device *phydev)
if (phydev->dev_flags & PHY_BRCM_DIS_TXCRXC_NOENRGY) {
if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E ||
BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54810 ||
- BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54210E)
+ BRCM_PHY_MODEL(phydev) == PHY_ID_BCM54811)
val |= BCM54XX_SHD_SCR3_RXCTXC_DIS;
else
val |= BCM54XX_SHD_SCR3_TRDDAPD;
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index 63006838bdcc..dec96e8ab567 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -2495,7 +2495,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
hso_net_init);
if (!net) {
dev_err(&interface->dev, "Unable to create ethernet device\n");
- goto exit;
+ goto err_hso_dev;
}
hso_net = netdev_priv(net);
@@ -2508,13 +2508,13 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
USB_DIR_IN);
if (!hso_net->in_endp) {
dev_err(&interface->dev, "Can't find BULK IN endpoint\n");
- goto exit;
+ goto err_net;
}
hso_net->out_endp = hso_get_ep(interface, USB_ENDPOINT_XFER_BULK,
USB_DIR_OUT);
if (!hso_net->out_endp) {
dev_err(&interface->dev, "Can't find BULK OUT endpoint\n");
- goto exit;
+ goto err_net;
}
SET_NETDEV_DEV(net, &interface->dev);
SET_NETDEV_DEVTYPE(net, &hso_type);
@@ -2523,18 +2523,18 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
hso_net->mux_bulk_rx_urb_pool[i] = usb_alloc_urb(0, GFP_KERNEL);
if (!hso_net->mux_bulk_rx_urb_pool[i])
- goto exit;
+ goto err_mux_bulk_rx;
hso_net->mux_bulk_rx_buf_pool[i] = kzalloc(MUX_BULK_RX_BUF_SIZE,
GFP_KERNEL);
if (!hso_net->mux_bulk_rx_buf_pool[i])
- goto exit;
+ goto err_mux_bulk_rx;
}
hso_net->mux_bulk_tx_urb = usb_alloc_urb(0, GFP_KERNEL);
if (!hso_net->mux_bulk_tx_urb)
- goto exit;
+ goto err_mux_bulk_rx;
hso_net->mux_bulk_tx_buf = kzalloc(MUX_BULK_TX_BUF_SIZE, GFP_KERNEL);
if (!hso_net->mux_bulk_tx_buf)
- goto exit;
+ goto err_free_tx_urb;
add_net_device(hso_dev);
@@ -2542,7 +2542,7 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
result = register_netdev(net);
if (result) {
dev_err(&interface->dev, "Failed to register device\n");
- goto exit;
+ goto err_free_tx_buf;
}
hso_log_port(hso_dev);
@@ -2550,8 +2550,21 @@ static struct hso_device *hso_create_net_device(struct usb_interface *interface,
hso_create_rfkill(hso_dev, interface);
return hso_dev;
-exit:
- hso_free_net_device(hso_dev, true);
+
+err_free_tx_buf:
+ remove_net_device(hso_dev);
+ kfree(hso_net->mux_bulk_tx_buf);
+err_free_tx_urb:
+ usb_free_urb(hso_net->mux_bulk_tx_urb);
+err_mux_bulk_rx:
+ for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
+ usb_free_urb(hso_net->mux_bulk_rx_urb_pool[i]);
+ kfree(hso_net->mux_bulk_rx_buf_pool[i]);
+ }
+err_net:
+ free_netdev(net);
+err_hso_dev:
+ kfree(hso_dev);
return NULL;
}
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 1692d3b1b6e1..e09b107b5c99 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1552,7 +1552,8 @@ static int
rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u32 speed, u8 duplex,
u32 advertising);
-static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+static int __rtl8152_set_mac_address(struct net_device *netdev, void *p,
+ bool in_resume)
{
struct r8152 *tp = netdev_priv(netdev);
struct sockaddr *addr = p;
@@ -1561,9 +1562,11 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
if (!is_valid_ether_addr(addr->sa_data))
goto out1;
- ret = usb_autopm_get_interface(tp->intf);
- if (ret < 0)
- goto out1;
+ if (!in_resume) {
+ ret = usb_autopm_get_interface(tp->intf);
+ if (ret < 0)
+ goto out1;
+ }
mutex_lock(&tp->control);
@@ -1575,11 +1578,17 @@ static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
mutex_unlock(&tp->control);
- usb_autopm_put_interface(tp->intf);
+ if (!in_resume)
+ usb_autopm_put_interface(tp->intf);
out1:
return ret;
}
+static int rtl8152_set_mac_address(struct net_device *netdev, void *p)
+{
+ return __rtl8152_set_mac_address(netdev, p, false);
+}
+
/* Devices containing proper chips can support a persistent
* host system provided MAC address.
* Examples of this are Dell TB15 and Dell WD15 docks
@@ -1698,7 +1707,7 @@ static int determine_ethernet_addr(struct r8152 *tp, struct sockaddr *sa)
return ret;
}
-static int set_ethernet_addr(struct r8152 *tp)
+static int set_ethernet_addr(struct r8152 *tp, bool in_resume)
{
struct net_device *dev = tp->netdev;
struct sockaddr sa;
@@ -1711,7 +1720,7 @@ static int set_ethernet_addr(struct r8152 *tp)
if (tp->version == RTL_VER_01)
ether_addr_copy(dev->dev_addr, sa.sa_data);
else
- ret = rtl8152_set_mac_address(dev, &sa);
+ ret = __rtl8152_set_mac_address(dev, &sa, in_resume);
return ret;
}
@@ -6763,9 +6772,10 @@ static int rtl8152_close(struct net_device *netdev)
tp->rtl_ops.down(tp);
mutex_unlock(&tp->control);
+ }
+ if (!res)
usb_autopm_put_interface(tp->intf);
- }
free_all_mem(tp);
@@ -8443,7 +8453,7 @@ static int rtl8152_reset_resume(struct usb_interface *intf)
clear_bit(SELECTIVE_SUSPEND, &tp->flags);
tp->rtl_ops.init(tp);
queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
- set_ethernet_addr(tp);
+ set_ethernet_addr(tp, true);
return rtl8152_resume(intf);
}
@@ -9644,7 +9654,7 @@ static int rtl8152_probe(struct usb_interface *intf,
tp->rtl_fw.retry = true;
#endif
queue_delayed_work(system_long_wq, &tp->hw_phy_work, 0);
- set_ethernet_addr(tp);
+ set_ethernet_addr(tp, false);
usb_set_intfdata(intf, tp);
diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c
index 1df959532c7d..514f2c1124b6 100644
--- a/drivers/net/wireless/virt_wifi.c
+++ b/drivers/net/wireless/virt_wifi.c
@@ -136,6 +136,29 @@ static struct ieee80211_supported_band band_5ghz = {
/* Assigned at module init. Guaranteed locally-administered and unicast. */
static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {};
+static void virt_wifi_inform_bss(struct wiphy *wiphy)
+{
+ u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
+ struct cfg80211_bss *informed_bss;
+ static const struct {
+ u8 tag;
+ u8 len;
+ u8 ssid[8];
+ } __packed ssid = {
+ .tag = WLAN_EID_SSID,
+ .len = 8,
+ .ssid = "VirtWifi",
+ };
+
+ informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
+ CFG80211_BSS_FTYPE_PRESP,
+ fake_router_bssid, tsf,
+ WLAN_CAPABILITY_ESS, 0,
+ (void *)&ssid, sizeof(ssid),
+ DBM_TO_MBM(-50), GFP_KERNEL);
+ cfg80211_put_bss(wiphy, informed_bss);
+}
+
/* Called with the rtnl lock held. */
static int virt_wifi_scan(struct wiphy *wiphy,
struct cfg80211_scan_request *request)
@@ -156,28 +179,13 @@ static int virt_wifi_scan(struct wiphy *wiphy,
/* Acquires and releases the rdev BSS lock. */
static void virt_wifi_scan_result(struct work_struct *work)
{
- struct {
- u8 tag;
- u8 len;
- u8 ssid[8];
- } __packed ssid = {
- .tag = WLAN_EID_SSID, .len = 8, .ssid = "VirtWifi",
- };
- struct cfg80211_bss *informed_bss;
struct virt_wifi_wiphy_priv *priv =
container_of(work, struct virt_wifi_wiphy_priv,
scan_result.work);
struct wiphy *wiphy = priv_to_wiphy(priv);
struct cfg80211_scan_info scan_info = { .aborted = false };
- u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
- informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
- CFG80211_BSS_FTYPE_PRESP,
- fake_router_bssid, tsf,
- WLAN_CAPABILITY_ESS, 0,
- (void *)&ssid, sizeof(ssid),
- DBM_TO_MBM(-50), GFP_KERNEL);
- cfg80211_put_bss(wiphy, informed_bss);
+ virt_wifi_inform_bss(wiphy);
/* Schedules work which acquires and releases the rtnl lock. */
cfg80211_scan_done(priv->scan_request, &scan_info);
@@ -225,10 +233,12 @@ static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev,
if (!could_schedule)
return -EBUSY;
- if (sme->bssid)
+ if (sme->bssid) {
ether_addr_copy(priv->connect_requested_bss, sme->bssid);
- else
+ } else {
+ virt_wifi_inform_bss(wiphy);
eth_zero_addr(priv->connect_requested_bss);
+ }
wiphy_debug(wiphy, "connect\n");
@@ -241,11 +251,13 @@ static void virt_wifi_connect_complete(struct work_struct *work)
struct virt_wifi_netdev_priv *priv =
container_of(work, struct virt_wifi_netdev_priv, connect.work);
u8 *requested_bss = priv->connect_requested_bss;
- bool has_addr = !is_zero_ether_addr(requested_bss);
bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid);
u16 status = WLAN_STATUS_SUCCESS;
- if (!priv->is_up || (has_addr && !right_addr))
+ if (is_zero_ether_addr(requested_bss))
+ requested_bss = NULL;
+
+ if (!priv->is_up || (requested_bss && !right_addr))
status = WLAN_STATUS_UNSPECIFIED_FAILURE;
else
priv->is_connected = true;
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index 3e16c318e705..674a81d79db3 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -984,6 +984,8 @@ static void wwan_create_default_link(struct wwan_device *wwandev,
goto unlock;
}
+ rtnl_configure_link(dev, NULL); /* Link initialized, notify new link */
+
unlock:
rtnl_unlock();
diff --git a/drivers/nfc/nfcsim.c b/drivers/nfc/nfcsim.c
index a9864fcdfba6..dd27c85190d3 100644
--- a/drivers/nfc/nfcsim.c
+++ b/drivers/nfc/nfcsim.c
@@ -192,8 +192,7 @@ static void nfcsim_recv_wq(struct work_struct *work)
if (!IS_ERR(skb))
dev_kfree_skb(skb);
-
- skb = ERR_PTR(-ENODEV);
+ return;
}
dev->cb(dev->nfc_digital_dev, dev->arg, skb);
diff --git a/drivers/nfc/s3fwrn5/firmware.c b/drivers/nfc/s3fwrn5/firmware.c
index eb5d7a5beac7..e3e72b8a29e3 100644
--- a/drivers/nfc/s3fwrn5/firmware.c
+++ b/drivers/nfc/s3fwrn5/firmware.c
@@ -423,7 +423,7 @@ int s3fwrn5_fw_download(struct s3fwrn5_fw_info *fw_info)
if (IS_ERR(tfm)) {
ret = PTR_ERR(tfm);
dev_err(&fw_info->ndev->nfc_dev->dev,
- "Cannot allocate shash (code=%d)\n", ret);
+ "Cannot allocate shash (code=%pe)\n", tfm);
goto out;
}
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 11779be42186..dfd9dec0c1f6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -900,7 +900,10 @@ static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
cmnd->write_zeroes.length =
cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
- cmnd->write_zeroes.control = 0;
+ if (nvme_ns_has_pi(ns))
+ cmnd->write_zeroes.control = cpu_to_le16(NVME_RW_PRINFO_PRACT);
+ else
+ cmnd->write_zeroes.control = 0;
return BLK_STS_OK;
}
@@ -3807,6 +3810,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
static void nvme_ns_remove(struct nvme_ns *ns)
{
+ bool last_path = false;
+
if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
return;
@@ -3815,8 +3820,6 @@ static void nvme_ns_remove(struct nvme_ns *ns)
mutex_lock(&ns->ctrl->subsys->lock);
list_del_rcu(&ns->siblings);
- if (list_empty(&ns->head->list))
- list_del_init(&ns->head->entry);
mutex_unlock(&ns->ctrl->subsys->lock);
synchronize_rcu(); /* guarantee not available in head->list */
@@ -3836,7 +3839,15 @@ static void nvme_ns_remove(struct nvme_ns *ns)
list_del_init(&ns->list);
up_write(&ns->ctrl->namespaces_rwsem);
- nvme_mpath_check_last_path(ns);
+ /* Synchronize with nvme_init_ns_head() */
+ mutex_lock(&ns->head->subsys->lock);
+ if (list_empty(&ns->head->list)) {
+ list_del_init(&ns->head->entry);
+ last_path = true;
+ }
+ mutex_unlock(&ns->head->subsys->lock);
+ if (last_path)
+ nvme_mpath_shutdown_disk(ns->head);
nvme_put_ns(ns);
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0ea5298469c3..3f32c5e86bfc 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -760,14 +760,21 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
#endif
}
-void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
{
if (!head->disk)
return;
+ kblockd_schedule_work(&head->requeue_work);
if (head->disk->flags & GENHD_FL_UP) {
nvme_cdev_del(&head->cdev, &head->cdev_device);
del_gendisk(head->disk);
}
+}
+
+void nvme_mpath_remove_disk(struct nvme_ns_head *head)
+{
+ if (!head->disk)
+ return;
blk_set_queue_dying(head->disk->queue);
/* make sure all pending bios are cleaned up */
kblockd_schedule_work(&head->requeue_work);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 18ef8dd03a90..5cd1fa3b8464 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -716,14 +716,7 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
void nvme_mpath_stop(struct nvme_ctrl *ctrl);
bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
-
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
-{
- struct nvme_ns_head *head = ns->head;
-
- if (head->disk && list_empty(&head->list))
- kblockd_schedule_work(&head->requeue_work);
-}
+void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
static inline void nvme_trace_bio_complete(struct request *req)
{
@@ -772,7 +765,7 @@ static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
{
}
-static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
+static inline void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
{
}
static inline void nvme_trace_bio_complete(struct request *req)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 320051f5a3dd..51852085239e 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2631,7 +2631,9 @@ static void nvme_reset_work(struct work_struct *work)
bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
int result;
- if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING)) {
+ if (dev->ctrl.state != NVME_CTRL_RESETTING) {
+ dev_warn(dev->ctrl.device, "ctrl state %d is not RESETTING\n",
+ dev->ctrl.state);
result = -ENODEV;
goto out;
}
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index daaf700eae79..35bac7a25422 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -56,7 +56,7 @@ TRACE_EVENT(nvme_setup_cmd,
__field(u8, fctype)
__field(u16, cid)
__field(u32, nsid)
- __field(u64, metadata)
+ __field(bool, metadata)
__array(u8, cdw10, 24)
),
TP_fast_assign(
@@ -66,13 +66,13 @@ TRACE_EVENT(nvme_setup_cmd,
__entry->flags = cmd->common.flags;
__entry->cid = cmd->common.command_id;
__entry->nsid = le32_to_cpu(cmd->common.nsid);
- __entry->metadata = le64_to_cpu(cmd->common.metadata);
+ __entry->metadata = !!blk_integrity_rq(req);
__entry->fctype = cmd->fabrics.fctype;
__assign_disk_name(__entry->disk, req->rq_disk);
memcpy(__entry->cdw10, &cmd->common.cdw10,
sizeof(__entry->cdw10));
),
- TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+ TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%x, cmd=(%s %s)",
__entry->ctrl_id, __print_disk_name(__entry->disk),
__entry->qid, __entry->cid, __entry->nsid,
__entry->flags, __entry->metadata,
diff --git a/drivers/platform/x86/amd-pmc.c b/drivers/platform/x86/amd-pmc.c
index b9da58ee9b1e..3481479a2942 100644
--- a/drivers/platform/x86/amd-pmc.c
+++ b/drivers/platform/x86/amd-pmc.c
@@ -46,34 +46,79 @@
#define AMD_PMC_RESULT_CMD_UNKNOWN 0xFE
#define AMD_PMC_RESULT_FAILED 0xFF
+/* FCH SSC Registers */
+#define FCH_S0I3_ENTRY_TIME_L_OFFSET 0x30
+#define FCH_S0I3_ENTRY_TIME_H_OFFSET 0x34
+#define FCH_S0I3_EXIT_TIME_L_OFFSET 0x38
+#define FCH_S0I3_EXIT_TIME_H_OFFSET 0x3C
+#define FCH_SSC_MAPPING_SIZE 0x800
+#define FCH_BASE_PHY_ADDR_LOW 0xFED81100
+#define FCH_BASE_PHY_ADDR_HIGH 0x00000000
+
+/* SMU Message Definations */
+#define SMU_MSG_GETSMUVERSION 0x02
+#define SMU_MSG_LOG_GETDRAM_ADDR_HI 0x04
+#define SMU_MSG_LOG_GETDRAM_ADDR_LO 0x05
+#define SMU_MSG_LOG_START 0x06
+#define SMU_MSG_LOG_RESET 0x07
+#define SMU_MSG_LOG_DUMP_DATA 0x08
+#define SMU_MSG_GET_SUP_CONSTRAINTS 0x09
/* List of supported CPU ids */
#define AMD_CPU_ID_RV 0x15D0
#define AMD_CPU_ID_RN 0x1630
#define AMD_CPU_ID_PCO AMD_CPU_ID_RV
#define AMD_CPU_ID_CZN AMD_CPU_ID_RN
+#define AMD_CPU_ID_YC 0x14B5
-#define AMD_SMU_FW_VERSION 0x0
#define PMC_MSG_DELAY_MIN_US 100
#define RESPONSE_REGISTER_LOOP_MAX 200
+#define SOC_SUBSYSTEM_IP_MAX 12
+#define DELAY_MIN_US 2000
+#define DELAY_MAX_US 3000
enum amd_pmc_def {
MSG_TEST = 0x01,
MSG_OS_HINT_PCO,
MSG_OS_HINT_RN,
};
+struct amd_pmc_bit_map {
+ const char *name;
+ u32 bit_mask;
+};
+
+static const struct amd_pmc_bit_map soc15_ip_blk[] = {
+ {"DISPLAY", BIT(0)},
+ {"CPU", BIT(1)},
+ {"GFX", BIT(2)},
+ {"VDD", BIT(3)},
+ {"ACP", BIT(4)},
+ {"VCN", BIT(5)},
+ {"ISP", BIT(6)},
+ {"NBIO", BIT(7)},
+ {"DF", BIT(8)},
+ {"USB0", BIT(9)},
+ {"USB1", BIT(10)},
+ {"LAPIC", BIT(11)},
+ {}
+};
+
struct amd_pmc_dev {
void __iomem *regbase;
- void __iomem *smu_base;
+ void __iomem *smu_virt_addr;
+ void __iomem *fch_virt_addr;
u32 base_addr;
u32 cpu_id;
+ u32 active_ips;
struct device *dev;
+ struct mutex lock; /* generic mutex lock */
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbgfs_dir;
#endif /* CONFIG_DEBUG_FS */
};
static struct amd_pmc_dev pmc;
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret);
static inline u32 amd_pmc_reg_read(struct amd_pmc_dev *dev, int reg_offset)
{
@@ -85,18 +130,77 @@ static inline void amd_pmc_reg_write(struct amd_pmc_dev *dev, int reg_offset, u3
iowrite32(val, dev->regbase + reg_offset);
}
+struct smu_metrics {
+ u32 table_version;
+ u32 hint_count;
+ u32 s0i3_cyclecount;
+ u32 timein_s0i2;
+ u64 timeentering_s0i3_lastcapture;
+ u64 timeentering_s0i3_totaltime;
+ u64 timeto_resume_to_os_lastcapture;
+ u64 timeto_resume_to_os_totaltime;
+ u64 timein_s0i3_lastcapture;
+ u64 timein_s0i3_totaltime;
+ u64 timein_swdrips_lastcapture;
+ u64 timein_swdrips_totaltime;
+ u64 timecondition_notmet_lastcapture[SOC_SUBSYSTEM_IP_MAX];
+ u64 timecondition_notmet_totaltime[SOC_SUBSYSTEM_IP_MAX];
+} __packed;
+
#ifdef CONFIG_DEBUG_FS
static int smu_fw_info_show(struct seq_file *s, void *unused)
{
struct amd_pmc_dev *dev = s->private;
- u32 value;
+ struct smu_metrics table;
+ int idx;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ memcpy_fromio(&table, dev->smu_virt_addr, sizeof(struct smu_metrics));
+
+ seq_puts(s, "\n=== SMU Statistics ===\n");
+ seq_printf(s, "Table Version: %d\n", table.table_version);
+ seq_printf(s, "Hint Count: %d\n", table.hint_count);
+ seq_printf(s, "S0i3 Cycle Count: %d\n", table.s0i3_cyclecount);
+ seq_printf(s, "Time (in us) to S0i3: %lld\n", table.timeentering_s0i3_lastcapture);
+ seq_printf(s, "Time (in us) in S0i3: %lld\n", table.timein_s0i3_lastcapture);
+
+ seq_puts(s, "\n=== Active time (in us) ===\n");
+ for (idx = 0 ; idx < SOC_SUBSYSTEM_IP_MAX ; idx++) {
+ if (soc15_ip_blk[idx].bit_mask & dev->active_ips)
+ seq_printf(s, "%-8s : %lld\n", soc15_ip_blk[idx].name,
+ table.timecondition_notmet_lastcapture[idx]);
+ }
- value = ioread32(dev->smu_base + AMD_SMU_FW_VERSION);
- seq_printf(s, "SMU FW Info: %x\n", value);
return 0;
}
DEFINE_SHOW_ATTRIBUTE(smu_fw_info);
+static int s0ix_stats_show(struct seq_file *s, void *unused)
+{
+ struct amd_pmc_dev *dev = s->private;
+ u64 entry_time, exit_time, residency;
+
+ entry_time = ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_H_OFFSET);
+ entry_time = entry_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_ENTRY_TIME_L_OFFSET);
+
+ exit_time = ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_H_OFFSET);
+ exit_time = exit_time << 32 | ioread32(dev->fch_virt_addr + FCH_S0I3_EXIT_TIME_L_OFFSET);
+
+ /* It's in 48MHz. We need to convert it */
+ residency = exit_time - entry_time;
+ do_div(residency, 48);
+
+ seq_puts(s, "=== S0ix statistics ===\n");
+ seq_printf(s, "S0ix Entry Time: %lld\n", entry_time);
+ seq_printf(s, "S0ix Exit Time: %lld\n", exit_time);
+ seq_printf(s, "Residency Time: %lld\n", residency);
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(s0ix_stats);
+
static void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev)
{
debugfs_remove_recursive(dev->dbgfs_dir);
@@ -107,6 +211,8 @@ static void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev)
dev->dbgfs_dir = debugfs_create_dir("amd_pmc", NULL);
debugfs_create_file("smu_fw_info", 0644, dev->dbgfs_dir, dev,
&smu_fw_info_fops);
+ debugfs_create_file("s0ix_stats", 0644, dev->dbgfs_dir, dev,
+ &s0ix_stats_fops);
}
#else
static inline void amd_pmc_dbgfs_register(struct amd_pmc_dev *dev)
@@ -118,6 +224,32 @@ static inline void amd_pmc_dbgfs_unregister(struct amd_pmc_dev *dev)
}
#endif /* CONFIG_DEBUG_FS */
+static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
+{
+ u32 phys_addr_low, phys_addr_hi;
+ u64 smu_phys_addr;
+
+ if (dev->cpu_id == AMD_CPU_ID_PCO)
+ return -EINVAL;
+
+ /* Get Active devices list from SMU */
+ amd_pmc_send_cmd(dev, 0, &dev->active_ips, SMU_MSG_GET_SUP_CONSTRAINTS, 1);
+
+ /* Get dram address */
+ amd_pmc_send_cmd(dev, 0, &phys_addr_low, SMU_MSG_LOG_GETDRAM_ADDR_LO, 1);
+ amd_pmc_send_cmd(dev, 0, &phys_addr_hi, SMU_MSG_LOG_GETDRAM_ADDR_HI, 1);
+ smu_phys_addr = ((u64)phys_addr_hi << 32 | phys_addr_low);
+
+ dev->smu_virt_addr = devm_ioremap(dev->dev, smu_phys_addr, sizeof(struct smu_metrics));
+ if (!dev->smu_virt_addr)
+ return -ENOMEM;
+
+ /* Start the logging */
+ amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, 0);
+
+ return 0;
+}
+
static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
{
u32 value;
@@ -132,19 +264,19 @@ static void amd_pmc_dump_registers(struct amd_pmc_dev *dev)
dev_dbg(dev->dev, "AMD_PMC_REGISTER_MESSAGE:%x\n", value);
}
-static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
+static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set, u32 *data, u8 msg, bool ret)
{
int rc;
- u8 msg;
u32 val;
+ mutex_lock(&dev->lock);
/* Wait until we get a valid response */
rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
- val, val > 0, PMC_MSG_DELAY_MIN_US,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
if (rc) {
dev_err(dev->dev, "failed to talk to SMU\n");
- return rc;
+ goto out_unlock;
}
/* Write zero to response register */
@@ -154,34 +286,91 @@ static int amd_pmc_send_cmd(struct amd_pmc_dev *dev, bool set)
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_ARGUMENT, set);
/* Write message ID to message ID register */
- msg = (dev->cpu_id == AMD_CPU_ID_RN) ? MSG_OS_HINT_RN : MSG_OS_HINT_PCO;
amd_pmc_reg_write(dev, AMD_PMC_REGISTER_MESSAGE, msg);
- return 0;
+
+ /* Wait until we get a valid response */
+ rc = readx_poll_timeout(ioread32, dev->regbase + AMD_PMC_REGISTER_RESPONSE,
+ val, val != 0, PMC_MSG_DELAY_MIN_US,
+ PMC_MSG_DELAY_MIN_US * RESPONSE_REGISTER_LOOP_MAX);
+ if (rc) {
+ dev_err(dev->dev, "SMU response timed out\n");
+ goto out_unlock;
+ }
+
+ switch (val) {
+ case AMD_PMC_RESULT_OK:
+ if (ret) {
+ /* PMFW may take longer time to return back the data */
+ usleep_range(DELAY_MIN_US, 10 * DELAY_MAX_US);
+ *data = amd_pmc_reg_read(dev, AMD_PMC_REGISTER_ARGUMENT);
+ }
+ break;
+ case AMD_PMC_RESULT_CMD_REJECT_BUSY:
+ dev_err(dev->dev, "SMU not ready. err: 0x%x\n", val);
+ rc = -EBUSY;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_UNKNOWN:
+ dev_err(dev->dev, "SMU cmd unknown. err: 0x%x\n", val);
+ rc = -EINVAL;
+ goto out_unlock;
+ case AMD_PMC_RESULT_CMD_REJECT_PREREQ:
+ case AMD_PMC_RESULT_FAILED:
+ default:
+ dev_err(dev->dev, "SMU cmd failed. err: 0x%x\n", val);
+ rc = -EIO;
+ goto out_unlock;
+ }
+
+out_unlock:
+ mutex_unlock(&dev->lock);
+ amd_pmc_dump_registers(dev);
+ return rc;
+}
+
+static int amd_pmc_get_os_hint(struct amd_pmc_dev *dev)
+{
+ switch (dev->cpu_id) {
+ case AMD_CPU_ID_PCO:
+ return MSG_OS_HINT_PCO;
+ case AMD_CPU_ID_RN:
+ case AMD_CPU_ID_YC:
+ return MSG_OS_HINT_RN;
+ }
+ return -EINVAL;
}
static int __maybe_unused amd_pmc_suspend(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Reset and Start SMU logging - to monitor the s0i3 stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_RESET, 0);
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_START, 0);
- rc = amd_pmc_send_cmd(pdev, 1);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 1, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "suspend failed\n");
- amd_pmc_dump_registers(pdev);
- return 0;
+ return rc;
}
static int __maybe_unused amd_pmc_resume(struct device *dev)
{
struct amd_pmc_dev *pdev = dev_get_drvdata(dev);
int rc;
+ u8 msg;
+
+ /* Let SMU know that we are looking for stats */
+ amd_pmc_send_cmd(pdev, 0, NULL, SMU_MSG_LOG_DUMP_DATA, 0);
- rc = amd_pmc_send_cmd(pdev, 0);
+ msg = amd_pmc_get_os_hint(pdev);
+ rc = amd_pmc_send_cmd(pdev, 0, NULL, msg, 0);
if (rc)
dev_err(pdev->dev, "resume failed\n");
- amd_pmc_dump_registers(pdev);
return 0;
}
@@ -190,6 +379,7 @@ static const struct dev_pm_ops amd_pmc_pm_ops = {
};
static const struct pci_device_id pmc_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_YC) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_CZN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RN) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PCO) },
@@ -201,9 +391,8 @@ static int amd_pmc_probe(struct platform_device *pdev)
{
struct amd_pmc_dev *dev = &pmc;
struct pci_dev *rdev;
- u32 base_addr_lo;
- u32 base_addr_hi;
- u64 base_addr;
+ u32 base_addr_lo, base_addr_hi;
+ u64 base_addr, fch_phys_addr;
int err;
u32 val;
@@ -248,16 +437,25 @@ static int amd_pmc_probe(struct platform_device *pdev)
pci_dev_put(rdev);
base_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
- dev->smu_base = devm_ioremap(dev->dev, base_addr, AMD_PMC_MAPPING_SIZE);
- if (!dev->smu_base)
- return -ENOMEM;
-
dev->regbase = devm_ioremap(dev->dev, base_addr + AMD_PMC_BASE_ADDR_OFFSET,
AMD_PMC_MAPPING_SIZE);
if (!dev->regbase)
return -ENOMEM;
- amd_pmc_dump_registers(dev);
+ mutex_init(&dev->lock);
+
+ /* Use FCH registers to get the S0ix stats */
+ base_addr_lo = FCH_BASE_PHY_ADDR_LOW;
+ base_addr_hi = FCH_BASE_PHY_ADDR_HIGH;
+ fch_phys_addr = ((u64)base_addr_hi << 32 | base_addr_lo);
+ dev->fch_virt_addr = devm_ioremap(dev->dev, fch_phys_addr, FCH_SSC_MAPPING_SIZE);
+ if (!dev->fch_virt_addr)
+ return -ENOMEM;
+
+ /* Use SMU to get the s0i3 debug stats */
+ err = amd_pmc_setup_smu_logging(dev);
+ if (err)
+ dev_err(dev->dev, "SMU debugging info not supported on this platform\n");
platform_set_drvdata(pdev, dev);
amd_pmc_dbgfs_register(dev);
@@ -269,11 +467,14 @@ static int amd_pmc_remove(struct platform_device *pdev)
struct amd_pmc_dev *dev = platform_get_drvdata(pdev);
amd_pmc_dbgfs_unregister(dev);
+ mutex_destroy(&dev->lock);
return 0;
}
static const struct acpi_device_id amd_pmc_acpi_ids[] = {
{"AMDI0005", 0},
+ {"AMDI0006", 0},
+ {"AMDI0007", 0},
{"AMD0004", 0},
{ }
};
diff --git a/drivers/platform/x86/gigabyte-wmi.c b/drivers/platform/x86/gigabyte-wmi.c
index 5529d7b0abea..fbb224a82e34 100644
--- a/drivers/platform/x86/gigabyte-wmi.c
+++ b/drivers/platform/x86/gigabyte-wmi.c
@@ -141,6 +141,7 @@ static u8 gigabyte_wmi_detect_sensor_usability(struct wmi_device *wdev)
static const struct dmi_system_id gigabyte_wmi_known_working_platforms[] = {
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE"),
+ DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 AORUS ELITE V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550 GAMING X V2"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M AORUS PRO-P"),
DMI_EXACT_MATCH_GIGABYTE_BOARD_NAME("B550M DS3H"),
diff --git a/drivers/platform/x86/intel-hid.c b/drivers/platform/x86/intel-hid.c
index 078648a9201b..e5fbe017f8e1 100644
--- a/drivers/platform/x86/intel-hid.c
+++ b/drivers/platform/x86/intel-hid.c
@@ -25,6 +25,7 @@ static const struct acpi_device_id intel_hid_ids[] = {
{"INT33D5", 0},
{"INTC1051", 0},
{"INTC1054", 0},
+ {"INTC1070", 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, intel_hid_ids);
diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c
index 3671b5d20613..6cfed4427fb0 100644
--- a/drivers/platform/x86/think-lmi.c
+++ b/drivers/platform/x86/think-lmi.c
@@ -571,6 +571,11 @@ static ssize_t current_value_store(struct kobject *kobj,
else
ret = tlmi_save_bios_settings("");
+ if (!ret && !tlmi_priv.pending_changes) {
+ tlmi_priv.pending_changes = true;
+ /* let userland know it may need to check reboot pending again */
+ kobject_uevent(&tlmi_priv.class_dev->kobj, KOBJ_CHANGE);
+ }
out:
kfree(auth_str);
kfree(set_str);
@@ -647,6 +652,14 @@ static struct kobj_type tlmi_pwd_setting_ktype = {
.sysfs_ops = &tlmi_kobj_sysfs_ops,
};
+static ssize_t pending_reboot_show(struct kobject *kobj, struct kobj_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "%d\n", tlmi_priv.pending_changes);
+}
+
+static struct kobj_attribute pending_reboot = __ATTR_RO(pending_reboot);
+
/* ---- Initialisation --------------------------------------------------------- */
static void tlmi_release_attr(void)
{
@@ -659,6 +672,7 @@ static void tlmi_release_attr(void)
kobject_put(&tlmi_priv.setting[i]->kobj);
}
}
+ sysfs_remove_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
kset_unregister(tlmi_priv.attribute_kset);
/* Authentication structures */
@@ -709,8 +723,8 @@ static int tlmi_sysfs_init(void)
/* Build attribute */
tlmi_priv.setting[i]->kobj.kset = tlmi_priv.attribute_kset;
- ret = kobject_init_and_add(&tlmi_priv.setting[i]->kobj, &tlmi_attr_setting_ktype,
- NULL, "%s", tlmi_priv.setting[i]->display_name);
+ ret = kobject_add(&tlmi_priv.setting[i]->kobj, NULL,
+ "%s", tlmi_priv.setting[i]->display_name);
if (ret)
goto fail_create_attr;
@@ -719,6 +733,10 @@ static int tlmi_sysfs_init(void)
goto fail_create_attr;
}
+ ret = sysfs_create_file(&tlmi_priv.attribute_kset->kobj, &pending_reboot.attr);
+ if (ret)
+ goto fail_create_attr;
+
/* Create authentication entries */
tlmi_priv.authentication_kset = kset_create_and_add("authentication", NULL,
&tlmi_priv.class_dev->kobj);
@@ -727,8 +745,7 @@ static int tlmi_sysfs_init(void)
goto fail_create_attr;
}
tlmi_priv.pwd_admin->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "Admin");
+ ret = kobject_add(&tlmi_priv.pwd_admin->kobj, NULL, "%s", "Admin");
if (ret)
goto fail_create_attr;
@@ -737,8 +754,7 @@ static int tlmi_sysfs_init(void)
goto fail_create_attr;
tlmi_priv.pwd_power->kobj.kset = tlmi_priv.authentication_kset;
- ret = kobject_init_and_add(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype,
- NULL, "%s", "System");
+ ret = kobject_add(&tlmi_priv.pwd_power->kobj, NULL, "%s", "System");
if (ret)
goto fail_create_attr;
@@ -818,6 +834,7 @@ static int tlmi_analyze(void)
pr_info("Error retrieving possible values for %d : %s\n",
i, setting->display_name);
}
+ kobject_init(&setting->kobj, &tlmi_attr_setting_ktype);
tlmi_priv.setting[i] = setting;
tlmi_priv.settings_count++;
kfree(item);
@@ -844,10 +861,12 @@ static int tlmi_analyze(void)
if (pwdcfg.password_state & TLMI_PAP_PWD)
tlmi_priv.pwd_admin->valid = true;
+ kobject_init(&tlmi_priv.pwd_admin->kobj, &tlmi_pwd_setting_ktype);
+
tlmi_priv.pwd_power = kzalloc(sizeof(struct tlmi_pwd_setting), GFP_KERNEL);
if (!tlmi_priv.pwd_power) {
ret = -ENOMEM;
- goto fail_clear_attr;
+ goto fail_free_pwd_admin;
}
strscpy(tlmi_priv.pwd_power->kbdlang, "us", TLMI_LANG_MAXLEN);
tlmi_priv.pwd_power->encoding = TLMI_ENCODING_ASCII;
@@ -859,11 +878,19 @@ static int tlmi_analyze(void)
if (pwdcfg.password_state & TLMI_POP_PWD)
tlmi_priv.pwd_power->valid = true;
+ kobject_init(&tlmi_priv.pwd_power->kobj, &tlmi_pwd_setting_ktype);
+
return 0;
+fail_free_pwd_admin:
+ kfree(tlmi_priv.pwd_admin);
fail_clear_attr:
- for (i = 0; i < TLMI_SETTINGS_COUNT; ++i)
- kfree(tlmi_priv.setting[i]);
+ for (i = 0; i < TLMI_SETTINGS_COUNT; ++i) {
+ if (tlmi_priv.setting[i]) {
+ kfree(tlmi_priv.setting[i]->possible_values);
+ kfree(tlmi_priv.setting[i]);
+ }
+ }
return ret;
}
diff --git a/drivers/platform/x86/think-lmi.h b/drivers/platform/x86/think-lmi.h
index 6fa8da7af6c7..eb598846628a 100644
--- a/drivers/platform/x86/think-lmi.h
+++ b/drivers/platform/x86/think-lmi.h
@@ -60,6 +60,7 @@ struct think_lmi {
bool can_get_bios_selections;
bool can_set_bios_password;
bool can_get_password_settings;
+ bool pending_changes;
struct tlmi_attr_setting *setting[TLMI_SETTINGS_COUNT];
struct device *class_dev;
diff --git a/drivers/platform/x86/wireless-hotkey.c b/drivers/platform/x86/wireless-hotkey.c
index b010e4ca3383..11c60a273446 100644
--- a/drivers/platform/x86/wireless-hotkey.c
+++ b/drivers/platform/x86/wireless-hotkey.c
@@ -78,7 +78,7 @@ static int wl_add(struct acpi_device *device)
err = wireless_input_setup();
if (err)
- pr_err("Failed to setup hp wireless hotkeys\n");
+ pr_err("Failed to setup wireless hotkeys\n");
return err;
}
diff --git a/drivers/regulator/bd9576-regulator.c b/drivers/regulator/bd9576-regulator.c
index e16c3727db7a..aa42da4d141e 100644
--- a/drivers/regulator/bd9576-regulator.c
+++ b/drivers/regulator/bd9576-regulator.c
@@ -294,9 +294,9 @@ static bool check_temp_flag_mismatch(struct regulator_dev *rdev, int severity,
struct bd957x_regulator_data *r)
{
if ((severity == REGULATOR_SEVERITY_ERR &&
- r->ovd_notif != REGULATOR_EVENT_OVER_TEMP) ||
+ r->temp_notif != REGULATOR_EVENT_OVER_TEMP) ||
(severity == REGULATOR_SEVERITY_WARN &&
- r->ovd_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) {
+ r->temp_notif != REGULATOR_EVENT_OVER_TEMP_WARN)) {
dev_warn(rdev_get_dev(rdev),
"Can't support both thermal WARN and ERR\n");
if (severity == REGULATOR_SEVERITY_WARN)
diff --git a/drivers/regulator/hi6421-regulator.c b/drivers/regulator/hi6421-regulator.c
index bff8c515dcde..d144a4bdb76d 100644
--- a/drivers/regulator/hi6421-regulator.c
+++ b/drivers/regulator/hi6421-regulator.c
@@ -366,9 +366,8 @@ static struct hi6421_regulator_info
static int hi6421_regulator_enable(struct regulator_dev *rdev)
{
- struct hi6421_regulator_pdata *pdata;
+ struct hi6421_regulator_pdata *pdata = rdev_get_drvdata(rdev);
- pdata = dev_get_drvdata(rdev->dev.parent);
/* hi6421 spec requires regulator enablement must be serialized:
* - Because when BUCK, LDO switching from off to on, it will have
* a huge instantaneous current; so you can not turn on two or
@@ -385,9 +384,10 @@ static int hi6421_regulator_enable(struct regulator_dev *rdev)
static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int reg_val;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, &reg_val);
if (reg_val & info->mode_mask)
return REGULATOR_MODE_IDLE;
@@ -397,9 +397,10 @@ static unsigned int hi6421_regulator_ldo_get_mode(struct regulator_dev *rdev)
static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int reg_val;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, &reg_val);
if (reg_val & info->mode_mask)
return REGULATOR_MODE_STANDBY;
@@ -410,9 +411,10 @@ static unsigned int hi6421_regulator_buck_get_mode(struct regulator_dev *rdev)
static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int new_mode;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
new_mode = 0;
@@ -434,9 +436,10 @@ static int hi6421_regulator_ldo_set_mode(struct regulator_dev *rdev,
static int hi6421_regulator_buck_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
unsigned int new_mode;
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
new_mode = 0;
@@ -459,7 +462,9 @@ static unsigned int
hi6421_regulator_ldo_get_optimum_mode(struct regulator_dev *rdev,
int input_uV, int output_uV, int load_uA)
{
- struct hi6421_regulator_info *info = rdev_get_drvdata(rdev);
+ struct hi6421_regulator_info *info;
+
+ info = container_of(rdev->desc, struct hi6421_regulator_info, desc);
if (load_uA > info->eco_microamp)
return REGULATOR_MODE_NORMAL;
@@ -543,14 +548,13 @@ static int hi6421_regulator_probe(struct platform_device *pdev)
if (!pdata)
return -ENOMEM;
mutex_init(&pdata->lock);
- platform_set_drvdata(pdev, pdata);
for (i = 0; i < ARRAY_SIZE(hi6421_regulator_info); i++) {
/* assign per-regulator data */
info = &hi6421_regulator_info[i];
config.dev = pdev->dev.parent;
- config.driver_data = info;
+ config.driver_data = pdata;
config.regmap = pmic->regmap;
rdev = devm_regulator_register(&pdev->dev, &info->desc,
diff --git a/drivers/regulator/hi6421v600-regulator.c b/drivers/regulator/hi6421v600-regulator.c
index 9b162c0555c3..845bc3b4026d 100644
--- a/drivers/regulator/hi6421v600-regulator.c
+++ b/drivers/regulator/hi6421v600-regulator.c
@@ -98,10 +98,9 @@ static const unsigned int ldo34_voltages[] = {
static int hi6421_spmi_regulator_enable(struct regulator_dev *rdev)
{
- struct hi6421_spmi_reg_priv *priv;
+ struct hi6421_spmi_reg_priv *priv = rdev_get_drvdata(rdev);
int ret;
- priv = dev_get_drvdata(rdev->dev.parent);
/* cannot enable more than one regulator at one time */
mutex_lock(&priv->enable_mutex);
@@ -119,9 +118,10 @@ static int hi6421_spmi_regulator_enable(struct regulator_dev *rdev)
static unsigned int hi6421_spmi_regulator_get_mode(struct regulator_dev *rdev)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
unsigned int reg_val;
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
regmap_read(rdev->regmap, rdev->desc->enable_reg, &reg_val);
if (reg_val & sreg->eco_mode_mask)
@@ -133,9 +133,10 @@ static unsigned int hi6421_spmi_regulator_get_mode(struct regulator_dev *rdev)
static int hi6421_spmi_regulator_set_mode(struct regulator_dev *rdev,
unsigned int mode)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
unsigned int val;
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
switch (mode) {
case REGULATOR_MODE_NORMAL:
val = 0;
@@ -159,7 +160,9 @@ hi6421_spmi_regulator_get_optimum_mode(struct regulator_dev *rdev,
int input_uV, int output_uV,
int load_uA)
{
- struct hi6421_spmi_reg_info *sreg = rdev_get_drvdata(rdev);
+ struct hi6421_spmi_reg_info *sreg;
+
+ sreg = container_of(rdev->desc, struct hi6421_spmi_reg_info, desc);
if (!sreg->eco_uA || ((unsigned int)load_uA > sreg->eco_uA))
return REGULATOR_MODE_NORMAL;
@@ -252,13 +255,12 @@ static int hi6421_spmi_regulator_probe(struct platform_device *pdev)
return -ENOMEM;
mutex_init(&priv->enable_mutex);
- platform_set_drvdata(pdev, priv);
for (i = 0; i < ARRAY_SIZE(regulator_info); i++) {
info = &regulator_info[i];
config.dev = pdev->dev.parent;
- config.driver_data = info;
+ config.driver_data = priv;
config.regmap = pmic->regmap;
rdev = devm_regulator_register(dev, &info->desc, &config);
diff --git a/drivers/regulator/mtk-dvfsrc-regulator.c b/drivers/regulator/mtk-dvfsrc-regulator.c
index d3d876198d6e..234af3a66c77 100644
--- a/drivers/regulator/mtk-dvfsrc-regulator.c
+++ b/drivers/regulator/mtk-dvfsrc-regulator.c
@@ -179,8 +179,7 @@ static int dvfsrc_vcore_regulator_probe(struct platform_device *pdev)
for (i = 0; i < regulator_init_data->size; i++) {
config.dev = dev->parent;
config.driver_data = (mt_regulators + i);
- rdev = devm_regulator_register(dev->parent,
- &(mt_regulators + i)->desc,
+ rdev = devm_regulator_register(dev, &(mt_regulators + i)->desc,
&config);
if (IS_ERR(rdev)) {
dev_err(dev, "failed to register %s\n",
diff --git a/drivers/regulator/rtmv20-regulator.c b/drivers/regulator/rtmv20-regulator.c
index 4bca64de0f67..2ee334174e2b 100644
--- a/drivers/regulator/rtmv20-regulator.c
+++ b/drivers/regulator/rtmv20-regulator.c
@@ -37,7 +37,7 @@
#define RTMV20_WIDTH2_MASK GENMASK(7, 0)
#define RTMV20_LBPLVL_MASK GENMASK(3, 0)
#define RTMV20_LBPEN_MASK BIT(7)
-#define RTMV20_STROBEPOL_MASK BIT(1)
+#define RTMV20_STROBEPOL_MASK BIT(0)
#define RTMV20_VSYNPOL_MASK BIT(1)
#define RTMV20_FSINEN_MASK BIT(7)
#define RTMV20_ESEN_MASK BIT(6)
diff --git a/drivers/scsi/arm/acornscsi.c b/drivers/scsi/arm/acornscsi.c
index 84fc7a0c6ff4..4a84599ff491 100644
--- a/drivers/scsi/arm/acornscsi.c
+++ b/drivers/scsi/arm/acornscsi.c
@@ -2642,6 +2642,7 @@ int acornscsi_abort(struct scsi_cmnd *SCpnt)
//#endif
clear_bit(SCpnt->device->id * 8 +
(u8)(SCpnt->device->lun & 0x7), host->busyluns);
+ fallthrough;
/*
* We found the command, and cleared it out. Either
diff --git a/drivers/scsi/arm/fas216.c b/drivers/scsi/arm/fas216.c
index 6baa9b36367d..9c4458a99025 100644
--- a/drivers/scsi/arm/fas216.c
+++ b/drivers/scsi/arm/fas216.c
@@ -1375,6 +1375,7 @@ static void fas216_busservice_intr(FAS216_Info *info, unsigned int stat, unsigne
case IS_COMPLETE:
break;
}
+ break;
default:
break;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index c39955239d1c..19b1c0cf5f2a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2983,13 +2983,13 @@ _base_check_enable_msix(struct MPT3SAS_ADAPTER *ioc)
}
/**
- * _base_free_irq - free irq
+ * mpt3sas_base_free_irq - free irq
* @ioc: per adapter object
*
* Freeing respective reply_queue from the list.
*/
-static void
-_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc)
{
struct adapter_reply_queue *reply_q, *next;
@@ -3191,12 +3191,12 @@ _base_check_and_enable_high_iops_queues(struct MPT3SAS_ADAPTER *ioc,
}
/**
- * _base_disable_msix - disables msix
+ * mpt3sas_base_disable_msix - disables msix
* @ioc: per adapter object
*
*/
-static void
-_base_disable_msix(struct MPT3SAS_ADAPTER *ioc)
+void
+mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc)
{
if (!ioc->msix_enable)
return;
@@ -3304,8 +3304,8 @@ _base_enable_msix(struct MPT3SAS_ADAPTER *ioc)
for (i = 0; i < ioc->reply_queue_count; i++) {
r = _base_request_irq(ioc, i);
if (r) {
- _base_free_irq(ioc);
- _base_disable_msix(ioc);
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
goto try_ioapic;
}
}
@@ -3342,8 +3342,8 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
dexitprintk(ioc, ioc_info(ioc, "%s\n", __func__));
- _base_free_irq(ioc);
- _base_disable_msix(ioc);
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
kfree(ioc->replyPostRegisterIndex);
ioc->replyPostRegisterIndex = NULL;
@@ -7613,14 +7613,14 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
}
/**
- * _base_make_ioc_ready - put controller in READY state
+ * mpt3sas_base_make_ioc_ready - put controller in READY state
* @ioc: per adapter object
* @type: FORCE_BIG_HAMMER or SOFT_RESET
*
* Return: 0 for success, non-zero for failure.
*/
-static int
-_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
+int
+mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
{
u32 ioc_state;
int rc;
@@ -7897,7 +7897,7 @@ mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc)
if (ioc->chip_phys && ioc->chip) {
mpt3sas_base_mask_interrupts(ioc);
ioc->shost_recovery = 1;
- _base_make_ioc_ready(ioc, SOFT_RESET);
+ mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
ioc->shost_recovery = 0;
}
@@ -8017,7 +8017,7 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
ioc->build_sg_mpi = &_base_build_sg;
ioc->build_zero_len_sge_mpi = &_base_build_zero_len_sge;
- r = _base_make_ioc_ready(ioc, SOFT_RESET);
+ r = mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
if (r)
goto out_free_resources;
@@ -8471,7 +8471,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
_base_pre_reset_handler(ioc);
mpt3sas_wait_for_commands_to_complete(ioc);
mpt3sas_base_mask_interrupts(ioc);
- r = _base_make_ioc_ready(ioc, type);
+ r = mpt3sas_base_make_ioc_ready(ioc, type);
if (r)
goto out;
_base_clear_outstanding_commands(ioc);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index d4834c8ee9c0..0c6c3df0038d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1730,6 +1730,10 @@ do { ioc_err(ioc, "In func: %s\n", __func__); \
status, mpi_request, sz); } while (0)
int mpt3sas_wait_for_ioc(struct MPT3SAS_ADAPTER *ioc, int wait_count);
+int
+mpt3sas_base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type);
+void mpt3sas_base_free_irq(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_base_disable_msix(struct MPT3SAS_ADAPTER *ioc);
/* scsih shared API */
struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 866d118f7931..8e64a6f14542 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -11295,7 +11295,12 @@ scsih_shutdown(struct pci_dev *pdev)
_scsih_ir_shutdown(ioc);
_scsih_nvme_shutdown(ioc);
- mpt3sas_base_detach(ioc);
+ mpt3sas_base_mask_interrupts(ioc);
+ ioc->shost_recovery = 1;
+ mpt3sas_base_make_ioc_ready(ioc, SOFT_RESET);
+ ioc->shost_recovery = 0;
+ mpt3sas_base_free_irq(ioc);
+ mpt3sas_base_disable_msix(ioc);
}
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index b07105ae7c91..d8b05d8b5470 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -439,39 +439,10 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj,
struct device *dev = container_of(kobj, struct device, kobj);
struct iscsi_iface *iface = iscsi_dev_to_iface(dev);
struct iscsi_transport *t = iface->transport;
- int param;
- int param_type;
+ int param = -1;
if (attr == &dev_attr_iface_enabled.attr)
param = ISCSI_NET_PARAM_IFACE_ENABLE;
- else if (attr == &dev_attr_iface_vlan_id.attr)
- param = ISCSI_NET_PARAM_VLAN_ID;
- else if (attr == &dev_attr_iface_vlan_priority.attr)
- param = ISCSI_NET_PARAM_VLAN_PRIORITY;
- else if (attr == &dev_attr_iface_vlan_enabled.attr)
- param = ISCSI_NET_PARAM_VLAN_ENABLED;
- else if (attr == &dev_attr_iface_mtu.attr)
- param = ISCSI_NET_PARAM_MTU;
- else if (attr == &dev_attr_iface_port.attr)
- param = ISCSI_NET_PARAM_PORT;
- else if (attr == &dev_attr_iface_ipaddress_state.attr)
- param = ISCSI_NET_PARAM_IPADDR_STATE;
- else if (attr == &dev_attr_iface_delayed_ack_en.attr)
- param = ISCSI_NET_PARAM_DELAYED_ACK_EN;
- else if (attr == &dev_attr_iface_tcp_nagle_disable.attr)
- param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE;
- else if (attr == &dev_attr_iface_tcp_wsf_disable.attr)
- param = ISCSI_NET_PARAM_TCP_WSF_DISABLE;
- else if (attr == &dev_attr_iface_tcp_wsf.attr)
- param = ISCSI_NET_PARAM_TCP_WSF;
- else if (attr == &dev_attr_iface_tcp_timer_scale.attr)
- param = ISCSI_NET_PARAM_TCP_TIMER_SCALE;
- else if (attr == &dev_attr_iface_tcp_timestamp_en.attr)
- param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN;
- else if (attr == &dev_attr_iface_cache_id.attr)
- param = ISCSI_NET_PARAM_CACHE_ID;
- else if (attr == &dev_attr_iface_redirect_en.attr)
- param = ISCSI_NET_PARAM_REDIRECT_EN;
else if (attr == &dev_attr_iface_def_taskmgmt_tmo.attr)
param = ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO;
else if (attr == &dev_attr_iface_header_digest.attr)
@@ -508,6 +479,38 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj,
param = ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN;
else if (attr == &dev_attr_iface_initiator_name.attr)
param = ISCSI_IFACE_PARAM_INITIATOR_NAME;
+
+ if (param != -1)
+ return t->attr_is_visible(ISCSI_IFACE_PARAM, param);
+
+ if (attr == &dev_attr_iface_vlan_id.attr)
+ param = ISCSI_NET_PARAM_VLAN_ID;
+ else if (attr == &dev_attr_iface_vlan_priority.attr)
+ param = ISCSI_NET_PARAM_VLAN_PRIORITY;
+ else if (attr == &dev_attr_iface_vlan_enabled.attr)
+ param = ISCSI_NET_PARAM_VLAN_ENABLED;
+ else if (attr == &dev_attr_iface_mtu.attr)
+ param = ISCSI_NET_PARAM_MTU;
+ else if (attr == &dev_attr_iface_port.attr)
+ param = ISCSI_NET_PARAM_PORT;
+ else if (attr == &dev_attr_iface_ipaddress_state.attr)
+ param = ISCSI_NET_PARAM_IPADDR_STATE;
+ else if (attr == &dev_attr_iface_delayed_ack_en.attr)
+ param = ISCSI_NET_PARAM_DELAYED_ACK_EN;
+ else if (attr == &dev_attr_iface_tcp_nagle_disable.attr)
+ param = ISCSI_NET_PARAM_TCP_NAGLE_DISABLE;
+ else if (attr == &dev_attr_iface_tcp_wsf_disable.attr)
+ param = ISCSI_NET_PARAM_TCP_WSF_DISABLE;
+ else if (attr == &dev_attr_iface_tcp_wsf.attr)
+ param = ISCSI_NET_PARAM_TCP_WSF;
+ else if (attr == &dev_attr_iface_tcp_timer_scale.attr)
+ param = ISCSI_NET_PARAM_TCP_TIMER_SCALE;
+ else if (attr == &dev_attr_iface_tcp_timestamp_en.attr)
+ param = ISCSI_NET_PARAM_TCP_TIMESTAMP_EN;
+ else if (attr == &dev_attr_iface_cache_id.attr)
+ param = ISCSI_NET_PARAM_CACHE_ID;
+ else if (attr == &dev_attr_iface_redirect_en.attr)
+ param = ISCSI_NET_PARAM_REDIRECT_EN;
else if (iface->iface_type == ISCSI_IFACE_TYPE_IPV4) {
if (attr == &dev_attr_ipv4_iface_ipaddress.attr)
param = ISCSI_NET_PARAM_IPV4_ADDR;
@@ -598,32 +601,7 @@ static umode_t iscsi_iface_attr_is_visible(struct kobject *kobj,
return 0;
}
- switch (param) {
- case ISCSI_IFACE_PARAM_DEF_TASKMGMT_TMO:
- case ISCSI_IFACE_PARAM_HDRDGST_EN:
- case ISCSI_IFACE_PARAM_DATADGST_EN:
- case ISCSI_IFACE_PARAM_IMM_DATA_EN:
- case ISCSI_IFACE_PARAM_INITIAL_R2T_EN:
- case ISCSI_IFACE_PARAM_DATASEQ_INORDER_EN:
- case ISCSI_IFACE_PARAM_PDU_INORDER_EN:
- case ISCSI_IFACE_PARAM_ERL:
- case ISCSI_IFACE_PARAM_MAX_RECV_DLENGTH:
- case ISCSI_IFACE_PARAM_FIRST_BURST:
- case ISCSI_IFACE_PARAM_MAX_R2T:
- case ISCSI_IFACE_PARAM_MAX_BURST:
- case ISCSI_IFACE_PARAM_CHAP_AUTH_EN:
- case ISCSI_IFACE_PARAM_BIDI_CHAP_EN:
- case ISCSI_IFACE_PARAM_DISCOVERY_AUTH_OPTIONAL:
- case ISCSI_IFACE_PARAM_DISCOVERY_LOGOUT_EN:
- case ISCSI_IFACE_PARAM_STRICT_LOGIN_COMP_EN:
- case ISCSI_IFACE_PARAM_INITIATOR_NAME:
- param_type = ISCSI_IFACE_PARAM;
- break;
- default:
- param_type = ISCSI_NET_PARAM;
- }
-
- return t->attr_is_visible(param_type, param);
+ return t->attr_is_visible(ISCSI_NET_PARAM, param);
}
static struct attribute *iscsi_iface_attrs[] = {
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 2ef74885ffa2..788dcdf25f00 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -352,8 +352,6 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
}
mr = spi_readl(as, MR);
- if (spi->cs_gpiod)
- gpiod_set_value(spi->cs_gpiod, 1);
} else {
u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0;
int i;
@@ -369,8 +367,6 @@ static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
mr = spi_readl(as, MR);
mr = SPI_BFINS(PCS, ~(1 << chip_select), mr);
- if (spi->cs_gpiod)
- gpiod_set_value(spi->cs_gpiod, 1);
spi_writel(as, MR, mr);
}
@@ -400,8 +396,6 @@ static void cs_deactivate(struct atmel_spi *as, struct spi_device *spi)
if (!spi->cs_gpiod)
spi_writel(as, CR, SPI_BIT(LASTXFER));
- else
- gpiod_set_value(spi->cs_gpiod, 0);
}
static void atmel_spi_lock(struct atmel_spi *as) __acquires(&as->lock)
@@ -1483,7 +1477,8 @@ static int atmel_spi_probe(struct platform_device *pdev)
master->bus_num = pdev->id;
master->num_chipselect = 4;
master->setup = atmel_spi_setup;
- master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX);
+ master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX |
+ SPI_MASTER_GPIO_SS);
master->transfer_one = atmel_spi_one_transfer;
master->set_cs = atmel_spi_set_cs;
master->cleanup = atmel_spi_cleanup;
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 5f8771fe1a31..775c0bf2f923 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -83,6 +83,7 @@ MODULE_PARM_DESC(polling_limit_us,
* struct bcm2835_spi - BCM2835 SPI controller
* @regs: base address of register map
* @clk: core clock, divided to calculate serial clock
+ * @clk_hz: core clock cached speed
* @irq: interrupt, signals TX FIFO empty or RX FIFO ¾ full
* @tfr: SPI transfer currently processed
* @ctlr: SPI controller reverse lookup
@@ -116,6 +117,7 @@ MODULE_PARM_DESC(polling_limit_us,
struct bcm2835_spi {
void __iomem *regs;
struct clk *clk;
+ unsigned long clk_hz;
int irq;
struct spi_transfer *tfr;
struct spi_controller *ctlr;
@@ -1045,19 +1047,18 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
{
struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
struct bcm2835_spidev *slv = spi_get_ctldata(spi);
- unsigned long spi_hz, clk_hz, cdiv;
+ unsigned long spi_hz, cdiv;
unsigned long hz_per_byte, byte_limit;
u32 cs = slv->prepare_cs;
/* set clock */
spi_hz = tfr->speed_hz;
- clk_hz = clk_get_rate(bs->clk);
- if (spi_hz >= clk_hz / 2) {
+ if (spi_hz >= bs->clk_hz / 2) {
cdiv = 2; /* clk_hz/2 is the fastest we can go */
} else if (spi_hz) {
/* CDIV must be a multiple of two */
- cdiv = DIV_ROUND_UP(clk_hz, spi_hz);
+ cdiv = DIV_ROUND_UP(bs->clk_hz, spi_hz);
cdiv += (cdiv % 2);
if (cdiv >= 65536)
@@ -1065,7 +1066,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
} else {
cdiv = 0; /* 0 is the slowest we can go */
}
- tfr->effective_speed_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536);
+ tfr->effective_speed_hz = cdiv ? (bs->clk_hz / cdiv) : (bs->clk_hz / 65536);
bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
/* handle all the 3-wire mode */
@@ -1354,6 +1355,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
return bs->irq ? bs->irq : -ENODEV;
clk_prepare_enable(bs->clk);
+ bs->clk_hz = clk_get_rate(bs->clk);
err = bcm2835_dma_init(ctlr, &pdev->dev, bs);
if (err)
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index 7a00346ff9b9..a2de23516553 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -309,6 +309,9 @@ static unsigned int cqspi_calc_dummy(const struct spi_mem_op *op, bool dtr)
{
unsigned int dummy_clk;
+ if (!op->dummy.nbytes)
+ return 0;
+
dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth);
if (dtr)
dummy_clk /= 2;
@@ -797,19 +800,20 @@ static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
reg = cqspi_calc_rdreg(f_pdata);
writel(reg, reg_base + CQSPI_REG_RD_INSTR);
- if (f_pdata->dtr) {
- /*
- * Some flashes like the cypress Semper flash expect a 4-byte
- * dummy address with the Read SR command in DTR mode, but this
- * controller does not support sending address with the Read SR
- * command. So, disable write completion polling on the
- * controller's side. spi-nor will take care of polling the
- * status register.
- */
- reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
- reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
- writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
- }
+ /*
+ * SPI NAND flashes require the address of the status register to be
+ * passed in the Read SR command. Also, some SPI NOR flashes like the
+ * cypress Semper flash expect a 4-byte dummy address in the Read SR
+ * command in DTR mode.
+ *
+ * But this controller does not support address phase in the Read SR
+ * command when doing auto-HW polling. So, disable write completion
+ * polling on the controller's side. spinand and spi-nor will take
+ * care of polling the status register.
+ */
+ reg = readl(reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
+ reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+ writel(reg, reg_base + CQSPI_REG_WR_COMPLETION_CTRL);
reg = readl(reg_base + CQSPI_REG_SIZE);
reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index a3afd1b9ac56..ceb16e70d235 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -517,6 +517,12 @@ static int cdns_spi_probe(struct platform_device *pdev)
goto clk_dis_apb;
}
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_get_noresume(&pdev->dev);
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
+
ret = of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs);
if (ret < 0)
master->num_chipselect = CDNS_SPI_DEFAULT_NUM_CS;
@@ -531,11 +537,6 @@ static int cdns_spi_probe(struct platform_device *pdev)
/* SPI controller initializations */
cdns_spi_init_hw(xspi);
- pm_runtime_set_active(&pdev->dev);
- pm_runtime_enable(&pdev->dev);
- pm_runtime_use_autosuspend(&pdev->dev);
- pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
-
irq = platform_get_irq(pdev, 0);
if (irq <= 0) {
ret = -ENXIO;
@@ -566,6 +567,9 @@ static int cdns_spi_probe(struct platform_device *pdev)
master->bits_per_word_mask = SPI_BPW_MASK(8);
+ pm_runtime_mark_last_busy(&pdev->dev);
+ pm_runtime_put_autosuspend(&pdev->dev);
+
ret = spi_register_master(master);
if (ret) {
dev_err(&pdev->dev, "spi_register_master failed\n");
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 39dc02e366f4..4aee3db6d6df 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -506,7 +506,7 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
{
struct spi_device *spi = msg->spi;
u32 ctrl = MX51_ECSPI_CTRL_ENABLE;
- u32 testreg;
+ u32 testreg, delay;
u32 cfg = readl(spi_imx->base + MX51_ECSPI_CONFIG);
/* set Master or Slave mode */
@@ -567,6 +567,23 @@ static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx,
writel(cfg, spi_imx->base + MX51_ECSPI_CONFIG);
+ /*
+ * Wait until the changes in the configuration register CONFIGREG
+ * propagate into the hardware. It takes exactly one tick of the
+ * SCLK clock, but we will wait two SCLK clock just to be sure. The
+ * effect of the delay it takes for the hardware to apply changes
+ * is noticable if the SCLK clock run very slow. In such a case, if
+ * the polarity of SCLK should be inverted, the GPIO ChipSelect might
+ * be asserted before the SCLK polarity changes, which would disrupt
+ * the SPI communication as the device on the other end would consider
+ * the change of SCLK polarity as a clock tick already.
+ */
+ delay = (2 * 1000000) / spi_imx->spi_bus_clk;
+ if (likely(delay < 10)) /* SCLK is faster than 100 kHz */
+ udelay(delay);
+ else /* SCLK is _very_ slow */
+ usleep_range(delay, delay + 10);
+
return 0;
}
@@ -574,7 +591,7 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
struct spi_device *spi)
{
u32 ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
- u32 clk, delay;
+ u32 clk;
/* Clear BL field and set the right value */
ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
@@ -596,23 +613,6 @@ static int mx51_ecspi_prepare_transfer(struct spi_imx_data *spi_imx,
writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
- /*
- * Wait until the changes in the configuration register CONFIGREG
- * propagate into the hardware. It takes exactly one tick of the
- * SCLK clock, but we will wait two SCLK clock just to be sure. The
- * effect of the delay it takes for the hardware to apply changes
- * is noticable if the SCLK clock run very slow. In such a case, if
- * the polarity of SCLK should be inverted, the GPIO ChipSelect might
- * be asserted before the SCLK polarity changes, which would disrupt
- * the SPI communication as the device on the other end would consider
- * the change of SCLK polarity as a clock tick already.
- */
- delay = (2 * 1000000) / clk;
- if (likely(delay < 10)) /* SCLK is faster than 100 kHz */
- udelay(delay);
- else /* SCLK is _very_ slow */
- usleep_range(delay, delay + 10);
-
return 0;
}
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index 976f73b9e299..68dca8ceb3ad 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -427,13 +427,23 @@ static int mtk_spi_fifo_transfer(struct spi_master *master,
mtk_spi_setup_packet(master);
cnt = xfer->len / 4;
- iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt);
+ if (xfer->tx_buf)
+ iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt);
+
+ if (xfer->rx_buf)
+ ioread32_rep(mdata->base + SPI_RX_DATA_REG, xfer->rx_buf, cnt);
remainder = xfer->len % 4;
if (remainder > 0) {
reg_val = 0;
- memcpy(&reg_val, xfer->tx_buf + (cnt * 4), remainder);
- writel(reg_val, mdata->base + SPI_TX_DATA_REG);
+ if (xfer->tx_buf) {
+ memcpy(&reg_val, xfer->tx_buf + (cnt * 4), remainder);
+ writel(reg_val, mdata->base + SPI_TX_DATA_REG);
+ }
+ if (xfer->rx_buf) {
+ reg_val = readl(mdata->base + SPI_RX_DATA_REG);
+ memcpy(xfer->rx_buf + (cnt * 4), &reg_val, remainder);
+ }
}
mtk_spi_enable_transfer(master);
@@ -793,12 +803,6 @@ static int mtk_spi_probe(struct platform_device *pdev)
pm_runtime_enable(&pdev->dev);
- ret = devm_spi_register_master(&pdev->dev, master);
- if (ret) {
- dev_err(&pdev->dev, "failed to register master (%d)\n", ret);
- goto err_disable_runtime_pm;
- }
-
if (mdata->dev_comp->need_pad_sel) {
if (mdata->pad_num != master->num_chipselect) {
dev_err(&pdev->dev,
@@ -838,6 +842,12 @@ static int mtk_spi_probe(struct platform_device *pdev)
dev_notice(&pdev->dev, "SPI dma_set_mask(%d) failed, ret:%d\n",
addr_bits, ret);
+ ret = devm_spi_register_master(&pdev->dev, master);
+ if (ret) {
+ dev_err(&pdev->dev, "failed to register master (%d)\n", ret);
+ goto err_disable_runtime_pm;
+ }
+
return 0;
err_disable_runtime_pm:
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index 8ffcffbb8157..05618a618939 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -884,15 +884,18 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
ier = readl_relaxed(spi->base + STM32H7_SPI_IER);
mask = ier;
- /* EOTIE is triggered on EOT, SUSP and TXC events. */
+ /*
+ * EOTIE enables irq from EOT, SUSP and TXC events. We need to set
+ * SUSP to acknowledge it later. TXC is automatically cleared
+ */
+
mask |= STM32H7_SPI_SR_SUSP;
/*
- * When TXTF is set, DXPIE and TXPIE are cleared. So in case of
- * Full-Duplex, need to poll RXP event to know if there are remaining
- * data, before disabling SPI.
+ * DXPIE is set in Full-Duplex, one IT will be raised if TXP and RXP
+ * are set. So in case of Full-Duplex, need to poll TXP and RXP event.
*/
- if (spi->rx_buf && !spi->cur_usedma)
- mask |= STM32H7_SPI_SR_RXP;
+ if ((spi->cur_comm == SPI_FULL_DUPLEX) && !spi->cur_usedma)
+ mask |= STM32H7_SPI_SR_TXP | STM32H7_SPI_SR_RXP;
if (!(sr & mask)) {
dev_warn(spi->dev, "spurious IT (sr=0x%08x, ier=0x%08x)\n",
@@ -1925,6 +1928,7 @@ static int stm32_spi_probe(struct platform_device *pdev)
master->can_dma = stm32_spi_can_dma;
pm_runtime_set_active(&pdev->dev);
+ pm_runtime_get_noresume(&pdev->dev);
pm_runtime_enable(&pdev->dev);
ret = spi_register_master(master);
@@ -1940,6 +1944,8 @@ static int stm32_spi_probe(struct platform_device *pdev)
err_pm_disable:
pm_runtime_disable(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
err_dma_release:
if (spi->dma_tx)
dma_release_channel(spi->dma_tx);
@@ -1956,9 +1962,14 @@ static int stm32_spi_remove(struct platform_device *pdev)
struct spi_master *master = platform_get_drvdata(pdev);
struct stm32_spi *spi = spi_master_get_devdata(master);
+ pm_runtime_get_sync(&pdev->dev);
+
spi_unregister_master(master);
spi->cfg->disable(spi);
+ pm_runtime_disable(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+ pm_runtime_set_suspended(&pdev->dev);
if (master->dma_tx)
dma_release_channel(master->dma_tx);
if (master->dma_rx)
@@ -1966,7 +1977,6 @@ static int stm32_spi_remove(struct platform_device *pdev)
clk_disable_unprepare(spi->clk);
- pm_runtime_disable(&pdev->dev);
pinctrl_pm_select_sleep_state(&pdev->dev);
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index b32f4ee88e79..ca1b2312d6e7 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -25,7 +25,7 @@
#include "target_core_alua.h"
static sense_reason_t
-sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char *, u32, bool);
+sbc_check_prot(struct se_device *, struct se_cmd *, unsigned char, u32, bool);
static sense_reason_t sbc_execute_unmap(struct se_cmd *cmd);
static sense_reason_t
@@ -279,14 +279,14 @@ static inline unsigned long long transport_lba_64_ext(unsigned char *cdb)
}
static sense_reason_t
-sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *ops)
+sbc_setup_write_same(struct se_cmd *cmd, unsigned char flags, struct sbc_ops *ops)
{
struct se_device *dev = cmd->se_dev;
sector_t end_lba = dev->transport->get_blocks(dev) + 1;
unsigned int sectors = sbc_get_write_same_sectors(cmd);
sense_reason_t ret;
- if ((flags[0] & 0x04) || (flags[0] & 0x02)) {
+ if ((flags & 0x04) || (flags & 0x02)) {
pr_err("WRITE_SAME PBDATA and LBDATA"
" bits not supported for Block Discard"
" Emulation\n");
@@ -308,7 +308,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
}
/* We always have ANC_SUP == 0 so setting ANCHOR is always an error */
- if (flags[0] & 0x10) {
+ if (flags & 0x10) {
pr_warn("WRITE SAME with ANCHOR not supported\n");
return TCM_INVALID_CDB_FIELD;
}
@@ -316,7 +316,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
* Special case for WRITE_SAME w/ UNMAP=1 that ends up getting
* translated into block discard requests within backend code.
*/
- if (flags[0] & 0x08) {
+ if (flags & 0x08) {
if (!ops->execute_unmap)
return TCM_UNSUPPORTED_SCSI_OPCODE;
@@ -331,7 +331,7 @@ sbc_setup_write_same(struct se_cmd *cmd, unsigned char *flags, struct sbc_ops *o
if (!ops->execute_write_same)
return TCM_UNSUPPORTED_SCSI_OPCODE;
- ret = sbc_check_prot(dev, cmd, &cmd->t_task_cdb[0], sectors, true);
+ ret = sbc_check_prot(dev, cmd, flags >> 5, sectors, true);
if (ret)
return ret;
@@ -717,10 +717,9 @@ sbc_set_prot_op_checks(u8 protect, bool fabric_prot, enum target_prot_type prot_
}
static sense_reason_t
-sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
+sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char protect,
u32 sectors, bool is_write)
{
- u8 protect = cdb[1] >> 5;
int sp_ops = cmd->se_sess->sup_prot_ops;
int pi_prot_type = dev->dev_attrib.pi_prot_type;
bool fabric_prot = false;
@@ -768,7 +767,7 @@ sbc_check_prot(struct se_device *dev, struct se_cmd *cmd, unsigned char *cdb,
fallthrough;
default:
pr_err("Unable to determine pi_prot_type for CDB: 0x%02x "
- "PROTECT: 0x%02x\n", cdb[0], protect);
+ "PROTECT: 0x%02x\n", cmd->t_task_cdb[0], protect);
return TCM_INVALID_CDB_FIELD;
}
@@ -843,7 +842,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
@@ -857,7 +856,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
@@ -871,7 +870,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, false);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, false);
if (ret)
return ret;
@@ -892,7 +891,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
@@ -906,7 +905,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
@@ -921,7 +920,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
if (sbc_check_dpofua(dev, cmd, cdb))
return TCM_INVALID_CDB_FIELD;
- ret = sbc_check_prot(dev, cmd, cdb, sectors, true);
+ ret = sbc_check_prot(dev, cmd, cdb[1] >> 5, sectors, true);
if (ret)
return ret;
@@ -980,7 +979,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
size = sbc_get_size(cmd, 1);
cmd->t_task_lba = get_unaligned_be64(&cdb[12]);
- ret = sbc_setup_write_same(cmd, &cdb[10], ops);
+ ret = sbc_setup_write_same(cmd, cdb[10], ops);
if (ret)
return ret;
break;
@@ -1079,7 +1078,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
size = sbc_get_size(cmd, 1);
cmd->t_task_lba = get_unaligned_be64(&cdb[2]);
- ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+ ret = sbc_setup_write_same(cmd, cdb[1], ops);
if (ret)
return ret;
break;
@@ -1097,7 +1096,7 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
* Follow sbcr26 with WRITE_SAME (10) and check for the existence
* of byte 1 bit 3 UNMAP instead of original reserved field
*/
- ret = sbc_setup_write_same(cmd, &cdb[1], ops);
+ ret = sbc_setup_write_same(cmd, cdb[1], ops);
if (ret)
return ret;
break;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7e35eddd9eb7..26ceabe34de5 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -886,7 +886,7 @@ void target_complete_cmd(struct se_cmd *cmd, u8 scsi_status)
INIT_WORK(&cmd->work, success ? target_complete_ok_work :
target_complete_failure_work);
- if (wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID)
+ if (!wwn || wwn->cmd_compl_affinity == SE_COMPL_AFFINITY_CPUID)
cpu = cmd->cpuid;
else
cpu = wwn->cmd_compl_affinity;
diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c
index fdf79bcf7eb0..35d5908b5478 100644
--- a/drivers/usb/class/cdc-wdm.c
+++ b/drivers/usb/class/cdc-wdm.c
@@ -824,7 +824,7 @@ static struct usb_class_driver wdm_class = {
};
/* --- WWAN framework integration --- */
-#ifdef CONFIG_WWAN
+#ifdef CONFIG_WWAN_CORE
static int wdm_wwan_port_start(struct wwan_port *port)
{
struct wdm_device *desc = wwan_port_get_drvdata(port);
@@ -963,11 +963,11 @@ static void wdm_wwan_rx(struct wdm_device *desc, int length)
/* inbuf has been copied, it is safe to check for outstanding data */
schedule_work(&desc->service_outs_intr);
}
-#else /* CONFIG_WWAN */
+#else /* CONFIG_WWAN_CORE */
static void wdm_wwan_init(struct wdm_device *desc) {}
static void wdm_wwan_deinit(struct wdm_device *desc) {}
static void wdm_wwan_rx(struct wdm_device *desc, int length) {}
-#endif /* CONFIG_WWAN */
+#endif /* CONFIG_WWAN_CORE */
/* --- error handling --- */
static void wdm_rxwork(struct work_struct *work)
diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c
index b97464498763..9618ba622a2d 100644
--- a/drivers/usb/core/devio.c
+++ b/drivers/usb/core/devio.c
@@ -1133,7 +1133,7 @@ static int do_proc_control(struct usb_dev_state *ps,
"wIndex=%04x wLength=%04x\n",
ctrl->bRequestType, ctrl->bRequest, ctrl->wValue,
ctrl->wIndex, ctrl->wLength);
- if (ctrl->bRequestType & 0x80) {
+ if ((ctrl->bRequestType & USB_DIR_IN) && ctrl->wLength) {
pipe = usb_rcvctrlpipe(dev, 0);
snoop_urb(dev, NULL, pipe, ctrl->wLength, tmo, SUBMIT, NULL, 0);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index d1efc7141333..86658a81d284 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -48,6 +48,7 @@
#define USB_TP_TRANSMISSION_DELAY 40 /* ns */
#define USB_TP_TRANSMISSION_DELAY_MAX 65535 /* ns */
+#define USB_PING_RESPONSE_TIME 400 /* ns */
/* Protect struct usb_device->state and ->children members
* Note: Both are also protected by ->dev.sem, except that ->state can
@@ -182,8 +183,9 @@ int usb_device_supports_lpm(struct usb_device *udev)
}
/*
- * Set the Maximum Exit Latency (MEL) for the host to initiate a transition from
- * either U1 or U2.
+ * Set the Maximum Exit Latency (MEL) for the host to wakup up the path from
+ * U1/U2, send a PING to the device and receive a PING_RESPONSE.
+ * See USB 3.1 section C.1.5.2
*/
static void usb_set_lpm_mel(struct usb_device *udev,
struct usb3_lpm_parameters *udev_lpm_params,
@@ -193,35 +195,37 @@ static void usb_set_lpm_mel(struct usb_device *udev,
unsigned int hub_exit_latency)
{
unsigned int total_mel;
- unsigned int device_mel;
- unsigned int hub_mel;
/*
- * Calculate the time it takes to transition all links from the roothub
- * to the parent hub into U0. The parent hub must then decode the
- * packet (hub header decode latency) to figure out which port it was
- * bound for.
- *
- * The Hub Header decode latency is expressed in 0.1us intervals (0x1
- * means 0.1us). Multiply that by 100 to get nanoseconds.
+ * tMEL1. time to transition path from host to device into U0.
+ * MEL for parent already contains the delay up to parent, so only add
+ * the exit latency for the last link (pick the slower exit latency),
+ * and the hub header decode latency. See USB 3.1 section C 2.2.1
+ * Store MEL in nanoseconds
*/
total_mel = hub_lpm_params->mel +
- (hub->descriptor->u.ss.bHubHdrDecLat * 100);
+ max(udev_exit_latency, hub_exit_latency) * 1000 +
+ hub->descriptor->u.ss.bHubHdrDecLat * 100;
/*
- * How long will it take to transition the downstream hub's port into
- * U0? The greater of either the hub exit latency or the device exit
- * latency.
- *
- * The BOS U1/U2 exit latencies are expressed in 1us intervals.
- * Multiply that by 1000 to get nanoseconds.
+ * tMEL2. Time to submit PING packet. Sum of tTPTransmissionDelay for
+ * each link + wHubDelay for each hub. Add only for last link.
+ * tMEL4, the time for PING_RESPONSE to traverse upstream is similar.
+ * Multiply by 2 to include it as well.
*/
- device_mel = udev_exit_latency * 1000;
- hub_mel = hub_exit_latency * 1000;
- if (device_mel > hub_mel)
- total_mel += device_mel;
- else
- total_mel += hub_mel;
+ total_mel += (__le16_to_cpu(hub->descriptor->u.ss.wHubDelay) +
+ USB_TP_TRANSMISSION_DELAY) * 2;
+
+ /*
+ * tMEL3, tPingResponse. Time taken by device to generate PING_RESPONSE
+ * after receiving PING. Also add 2100ns as stated in USB 3.1 C 1.5.2.4
+ * to cover the delay if the PING_RESPONSE is queued behind a Max Packet
+ * Size DP.
+ * Note these delays should be added only once for the entire path, so
+ * add them to the MEL of the device connected to the roothub.
+ */
+ if (!hub->hdev->parent)
+ total_mel += USB_PING_RESPONSE_TIME + 2100;
udev_lpm_params->mel = total_mel;
}
@@ -4113,6 +4117,47 @@ static int usb_set_lpm_timeout(struct usb_device *udev,
}
/*
+ * Don't allow device intiated U1/U2 if the system exit latency + one bus
+ * interval is greater than the minimum service interval of any active
+ * periodic endpoint. See USB 3.2 section 9.4.9
+ */
+static bool usb_device_may_initiate_lpm(struct usb_device *udev,
+ enum usb3_link_state state)
+{
+ unsigned int sel; /* us */
+ int i, j;
+
+ if (state == USB3_LPM_U1)
+ sel = DIV_ROUND_UP(udev->u1_params.sel, 1000);
+ else if (state == USB3_LPM_U2)
+ sel = DIV_ROUND_UP(udev->u2_params.sel, 1000);
+ else
+ return false;
+
+ for (i = 0; i < udev->actconfig->desc.bNumInterfaces; i++) {
+ struct usb_interface *intf;
+ struct usb_endpoint_descriptor *desc;
+ unsigned int interval;
+
+ intf = udev->actconfig->interface[i];
+ if (!intf)
+ continue;
+
+ for (j = 0; j < intf->cur_altsetting->desc.bNumEndpoints; j++) {
+ desc = &intf->cur_altsetting->endpoint[j].desc;
+
+ if (usb_endpoint_xfer_int(desc) ||
+ usb_endpoint_xfer_isoc(desc)) {
+ interval = (1 << (desc->bInterval - 1)) * 125;
+ if (sel + 125 > interval)
+ return false;
+ }
+ }
+ }
+ return true;
+}
+
+/*
* Enable the hub-initiated U1/U2 idle timeouts, and enable device-initiated
* U1/U2 entry.
*
@@ -4184,20 +4229,23 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev,
* U1/U2_ENABLE
*/
if (udev->actconfig &&
- usb_set_device_initiated_lpm(udev, state, true) == 0) {
- if (state == USB3_LPM_U1)
- udev->usb3_lpm_u1_enabled = 1;
- else if (state == USB3_LPM_U2)
- udev->usb3_lpm_u2_enabled = 1;
- } else {
- /* Don't request U1/U2 entry if the device
- * cannot transition to U1/U2.
- */
- usb_set_lpm_timeout(udev, state, 0);
- hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state);
+ usb_device_may_initiate_lpm(udev, state)) {
+ if (usb_set_device_initiated_lpm(udev, state, true)) {
+ /*
+ * Request to enable device initiated U1/U2 failed,
+ * better to turn off lpm in this case.
+ */
+ usb_set_lpm_timeout(udev, state, 0);
+ hcd->driver->disable_usb3_lpm_timeout(hcd, udev, state);
+ return;
+ }
}
-}
+ if (state == USB3_LPM_U1)
+ udev->usb3_lpm_u1_enabled = 1;
+ else if (state == USB3_LPM_U2)
+ udev->usb3_lpm_u2_enabled = 1;
+}
/*
* Disable the hub-initiated U1/U2 idle timeouts, and disable device-initiated
* U1/U2 entry.
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 6114cf83bb44..8239fe7129dd 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -501,10 +501,6 @@ static const struct usb_device_id usb_quirk_list[] = {
/* DJI CineSSD */
{ USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM },
- /* Fibocom L850-GL LTE Modem */
- { USB_DEVICE(0x2cb7, 0x0007), .driver_info =
- USB_QUIRK_IGNORE_REMOTE_WAKEUP },
-
/* INTEL VALUE SSD */
{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index ab6b815e0089..483de2bbfaab 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -383,6 +383,9 @@ enum dwc2_ep0_state {
* 0 - No (default)
* 1 - Partial power down
* 2 - Hibernation
+ * @no_clock_gating: Specifies whether to avoid clock gating feature.
+ * 0 - No (use clock gating)
+ * 1 - Yes (avoid it)
* @lpm: Enable LPM support.
* 0 - No
* 1 - Yes
@@ -480,6 +483,7 @@ struct dwc2_core_params {
#define DWC2_POWER_DOWN_PARAM_NONE 0
#define DWC2_POWER_DOWN_PARAM_PARTIAL 1
#define DWC2_POWER_DOWN_PARAM_HIBERNATION 2
+ bool no_clock_gating;
bool lpm;
bool lpm_clock_gating;
diff --git a/drivers/usb/dwc2/core_intr.c b/drivers/usb/dwc2/core_intr.c
index a5ab03808da6..a5c52b237e72 100644
--- a/drivers/usb/dwc2/core_intr.c
+++ b/drivers/usb/dwc2/core_intr.c
@@ -556,7 +556,8 @@ static void dwc2_handle_usb_suspend_intr(struct dwc2_hsotg *hsotg)
* If neither hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_gadget_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_gadget_enter_clock_gating(hsotg);
}
/*
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index c581ee41ac81..3146df6e6510 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -2749,12 +2749,14 @@ static void dwc2_hsotg_complete_in(struct dwc2_hsotg *hsotg,
return;
}
- /* Zlp for all endpoints, for ep0 only in DATA IN stage */
+ /* Zlp for all endpoints in non DDMA, for ep0 only in DATA IN stage */
if (hs_ep->send_zlp) {
- dwc2_hsotg_program_zlp(hsotg, hs_ep);
hs_ep->send_zlp = 0;
- /* transfer will be completed on next complete interrupt */
- return;
+ if (!using_desc_dma(hsotg)) {
+ dwc2_hsotg_program_zlp(hsotg, hs_ep);
+ /* transfer will be completed on next complete interrupt */
+ return;
+ }
}
if (hs_ep->index == 0 && hsotg->ep0_state == DWC2_EP0_DATA_IN) {
@@ -3900,9 +3902,27 @@ static void dwc2_hsotg_ep_stop_xfr(struct dwc2_hsotg *hsotg,
__func__);
}
} else {
+ /* Mask GINTSTS_GOUTNAKEFF interrupt */
+ dwc2_hsotg_disable_gsint(hsotg, GINTSTS_GOUTNAKEFF);
+
if (!(dwc2_readl(hsotg, GINTSTS) & GINTSTS_GOUTNAKEFF))
dwc2_set_bit(hsotg, DCTL, DCTL_SGOUTNAK);
+ if (!using_dma(hsotg)) {
+ /* Wait for GINTSTS_RXFLVL interrupt */
+ if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS,
+ GINTSTS_RXFLVL, 100)) {
+ dev_warn(hsotg->dev, "%s: timeout GINTSTS.RXFLVL\n",
+ __func__);
+ } else {
+ /*
+ * Pop GLOBAL OUT NAK status packet from RxFIFO
+ * to assert GOUTNAKEFF interrupt
+ */
+ dwc2_readl(hsotg, GRXSTSP);
+ }
+ }
+
/* Wait for global nak to take effect */
if (dwc2_hsotg_wait_bit_set(hsotg, GINTSTS,
GINTSTS_GOUTNAKEFF, 100))
@@ -4348,6 +4368,9 @@ static int dwc2_hsotg_ep_sethalt(struct usb_ep *ep, int value, bool now)
epctl = dwc2_readl(hs, epreg);
if (value) {
+ /* Unmask GOUTNAKEFF interrupt */
+ dwc2_hsotg_en_gsint(hs, GINTSTS_GOUTNAKEFF);
+
if (!(dwc2_readl(hs, GINTSTS) & GINTSTS_GOUTNAKEFF))
dwc2_set_bit(hs, DCTL, DCTL_SGOUTNAK);
// STALL bit will be set in GOUTNAKEFF interrupt handler
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index 035d4911a3c3..2a7828971d05 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -3338,7 +3338,8 @@ int dwc2_port_suspend(struct dwc2_hsotg *hsotg, u16 windex)
* If not hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_host_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_host_enter_clock_gating(hsotg);
break;
}
@@ -4402,7 +4403,8 @@ static int _dwc2_hcd_suspend(struct usb_hcd *hcd)
* If not hibernation nor partial power down are supported,
* clock gating is used to save power.
*/
- dwc2_host_enter_clock_gating(hsotg);
+ if (!hsotg->params.no_clock_gating)
+ dwc2_host_enter_clock_gating(hsotg);
/* After entering suspend, hardware is not accessible */
clear_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index 67c5eb140232..59e119345994 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -76,6 +76,7 @@ static void dwc2_set_s3c6400_params(struct dwc2_hsotg *hsotg)
struct dwc2_core_params *p = &hsotg->params;
p->power_down = DWC2_POWER_DOWN_PARAM_NONE;
+ p->no_clock_gating = true;
p->phy_utmi_width = 8;
}
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index dccdf13b5f9e..5991766239ba 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1279,6 +1279,7 @@ struct dwc3 {
unsigned dis_metastability_quirk:1;
unsigned dis_split_quirk:1;
+ unsigned async_callbacks:1;
u16 imod_interval;
};
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 3cd294264372..2f9e45eed228 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -597,11 +597,13 @@ static int dwc3_ep0_set_address(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
static int dwc3_ep0_delegate_req(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl)
{
- int ret;
+ int ret = -EINVAL;
- spin_unlock(&dwc->lock);
- ret = dwc->gadget_driver->setup(dwc->gadget, ctrl);
- spin_lock(&dwc->lock);
+ if (dwc->async_callbacks) {
+ spin_unlock(&dwc->lock);
+ ret = dwc->gadget_driver->setup(dwc->gadget, ctrl);
+ spin_lock(&dwc->lock);
+ }
return ret;
}
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index af6d7f157989..45f2bc0807e8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2585,6 +2585,16 @@ static int dwc3_gadget_vbus_draw(struct usb_gadget *g, unsigned int mA)
return ret;
}
+static void dwc3_gadget_async_callbacks(struct usb_gadget *g, bool enable)
+{
+ struct dwc3 *dwc = gadget_to_dwc(g);
+ unsigned long flags;
+
+ spin_lock_irqsave(&dwc->lock, flags);
+ dwc->async_callbacks = enable;
+ spin_unlock_irqrestore(&dwc->lock, flags);
+}
+
static const struct usb_gadget_ops dwc3_gadget_ops = {
.get_frame = dwc3_gadget_get_frame,
.wakeup = dwc3_gadget_wakeup,
@@ -2596,6 +2606,7 @@ static const struct usb_gadget_ops dwc3_gadget_ops = {
.udc_set_ssp_rate = dwc3_gadget_set_ssp_rate,
.get_config_params = dwc3_gadget_config_params,
.vbus_draw = dwc3_gadget_vbus_draw,
+ .udc_async_callbacks = dwc3_gadget_async_callbacks,
};
/* -------------------------------------------------------------------------- */
@@ -3231,7 +3242,7 @@ static void dwc3_endpoint_interrupt(struct dwc3 *dwc,
static void dwc3_disconnect_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->disconnect) {
+ if (dwc->async_callbacks && dwc->gadget_driver->disconnect) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->disconnect(dwc->gadget);
spin_lock(&dwc->lock);
@@ -3240,7 +3251,7 @@ static void dwc3_disconnect_gadget(struct dwc3 *dwc)
static void dwc3_suspend_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->suspend) {
+ if (dwc->async_callbacks && dwc->gadget_driver->suspend) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->suspend(dwc->gadget);
spin_lock(&dwc->lock);
@@ -3249,7 +3260,7 @@ static void dwc3_suspend_gadget(struct dwc3 *dwc)
static void dwc3_resume_gadget(struct dwc3 *dwc)
{
- if (dwc->gadget_driver && dwc->gadget_driver->resume) {
+ if (dwc->async_callbacks && dwc->gadget_driver->resume) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->resume(dwc->gadget);
spin_lock(&dwc->lock);
@@ -3261,7 +3272,7 @@ static void dwc3_reset_gadget(struct dwc3 *dwc)
if (!dwc->gadget_driver)
return;
- if (dwc->gadget->speed != USB_SPEED_UNKNOWN) {
+ if (dwc->async_callbacks && dwc->gadget->speed != USB_SPEED_UNKNOWN) {
spin_unlock(&dwc->lock);
usb_gadget_udc_reset(dwc->gadget, dwc->gadget_driver);
spin_lock(&dwc->lock);
@@ -3585,7 +3596,7 @@ static void dwc3_gadget_wakeup_interrupt(struct dwc3 *dwc)
* implemented.
*/
- if (dwc->gadget_driver && dwc->gadget_driver->resume) {
+ if (dwc->async_callbacks && dwc->gadget_driver->resume) {
spin_unlock(&dwc->lock);
dwc->gadget_driver->resume(dwc->gadget);
spin_lock(&dwc->lock);
diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
index bffef8e47dac..281ca766698a 100644
--- a/drivers/usb/gadget/function/u_serial.c
+++ b/drivers/usb/gadget/function/u_serial.c
@@ -1198,7 +1198,7 @@ void gserial_free_line(unsigned char port_num)
struct gs_port *port;
mutex_lock(&ports[port_num].lock);
- if (WARN_ON(!ports[port_num].port)) {
+ if (!ports[port_num].port) {
mutex_unlock(&ports[port_num].lock);
return;
}
diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c
index a54d1cef17db..c0ca7144e512 100644
--- a/drivers/usb/gadget/udc/tegra-xudc.c
+++ b/drivers/usb/gadget/udc/tegra-xudc.c
@@ -3853,6 +3853,7 @@ static int tegra_xudc_probe(struct platform_device *pdev)
return 0;
free_eps:
+ pm_runtime_disable(&pdev->dev);
tegra_xudc_free_eps(xudc);
free_event_ring:
tegra_xudc_free_event_ring(xudc);
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c
index 36f5bf6a0752..10b0365f3439 100644
--- a/drivers/usb/host/ehci-hcd.c
+++ b/drivers/usb/host/ehci-hcd.c
@@ -703,24 +703,28 @@ EXPORT_SYMBOL_GPL(ehci_setup);
static irqreturn_t ehci_irq (struct usb_hcd *hcd)
{
struct ehci_hcd *ehci = hcd_to_ehci (hcd);
- u32 status, masked_status, pcd_status = 0, cmd;
+ u32 status, current_status, masked_status, pcd_status = 0;
+ u32 cmd;
int bh;
spin_lock(&ehci->lock);
- status = ehci_readl(ehci, &ehci->regs->status);
+ status = 0;
+ current_status = ehci_readl(ehci, &ehci->regs->status);
+restart:
/* e.g. cardbus physical eject */
- if (status == ~(u32) 0) {
+ if (current_status == ~(u32) 0) {
ehci_dbg (ehci, "device removed\n");
goto dead;
}
+ status |= current_status;
/*
* We don't use STS_FLR, but some controllers don't like it to
* remain on, so mask it out along with the other status bits.
*/
- masked_status = status & (INTR_MASK | STS_FLR);
+ masked_status = current_status & (INTR_MASK | STS_FLR);
/* Shared IRQ? */
if (!masked_status || unlikely(ehci->rh_state == EHCI_RH_HALTED)) {
@@ -730,6 +734,12 @@ static irqreturn_t ehci_irq (struct usb_hcd *hcd)
/* clear (just) interrupts */
ehci_writel(ehci, masked_status, &ehci->regs->status);
+
+ /* For edge interrupts, don't race with an interrupt bit being raised */
+ current_status = ehci_readl(ehci, &ehci->regs->status);
+ if (current_status & INTR_MASK)
+ goto restart;
+
cmd = ehci_readl(ehci, &ehci->regs->command);
bh = 0;
diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index e7a8e0609853..59cc1bc7f12f 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -153,8 +153,6 @@ struct max3421_hcd {
*/
struct urb *curr_urb;
enum scheduling_pass sched_pass;
- struct usb_device *loaded_dev; /* dev that's loaded into the chip */
- int loaded_epnum; /* epnum whose toggles are loaded */
int urb_done; /* > 0 -> no errors, < 0: errno */
size_t curr_len;
u8 hien;
@@ -492,39 +490,17 @@ max3421_set_speed(struct usb_hcd *hcd, struct usb_device *dev)
* Caller must NOT hold HCD spinlock.
*/
static void
-max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum,
- int force_toggles)
+max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum)
{
- struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd);
- int old_epnum, same_ep, rcvtog, sndtog;
- struct usb_device *old_dev;
+ int rcvtog, sndtog;
u8 hctl;
- old_dev = max3421_hcd->loaded_dev;
- old_epnum = max3421_hcd->loaded_epnum;
-
- same_ep = (dev == old_dev && epnum == old_epnum);
- if (same_ep && !force_toggles)
- return;
-
- if (old_dev && !same_ep) {
- /* save the old end-points toggles: */
- u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL);
-
- rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1;
- sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1;
-
- /* no locking: HCD (i.e., we) own toggles, don't we? */
- usb_settoggle(old_dev, old_epnum, 0, rcvtog);
- usb_settoggle(old_dev, old_epnum, 1, sndtog);
- }
/* setup new endpoint's toggle bits: */
rcvtog = usb_gettoggle(dev, epnum, 0);
sndtog = usb_gettoggle(dev, epnum, 1);
hctl = (BIT(rcvtog + MAX3421_HCTL_RCVTOG0_BIT) |
BIT(sndtog + MAX3421_HCTL_SNDTOG0_BIT));
- max3421_hcd->loaded_epnum = epnum;
spi_wr8(hcd, MAX3421_REG_HCTL, hctl);
/*
@@ -532,7 +508,6 @@ max3421_set_address(struct usb_hcd *hcd, struct usb_device *dev, int epnum,
* address-assignment so it's best to just always load the
* address whenever the end-point changed/was forced.
*/
- max3421_hcd->loaded_dev = dev;
spi_wr8(hcd, MAX3421_REG_PERADDR, dev->devnum);
}
@@ -667,7 +642,7 @@ max3421_select_and_start_urb(struct usb_hcd *hcd)
struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd);
struct urb *urb, *curr_urb = NULL;
struct max3421_ep *max3421_ep;
- int epnum, force_toggles = 0;
+ int epnum;
struct usb_host_endpoint *ep;
struct list_head *pos;
unsigned long flags;
@@ -777,7 +752,6 @@ done:
usb_settoggle(urb->dev, epnum, 0, 1);
usb_settoggle(urb->dev, epnum, 1, 1);
max3421_ep->pkt_state = PKT_STATE_SETUP;
- force_toggles = 1;
} else
max3421_ep->pkt_state = PKT_STATE_TRANSFER;
}
@@ -785,7 +759,7 @@ done:
spin_unlock_irqrestore(&max3421_hcd->lock, flags);
max3421_ep->last_active = max3421_hcd->frame_number;
- max3421_set_address(hcd, urb->dev, epnum, force_toggles);
+ max3421_set_address(hcd, urb->dev, epnum);
max3421_set_speed(hcd, urb->dev);
max3421_next_transfer(hcd, 0);
return 1;
@@ -1379,6 +1353,16 @@ max3421_urb_done(struct usb_hcd *hcd)
status = 0;
urb = max3421_hcd->curr_urb;
if (urb) {
+ /* save the old end-points toggles: */
+ u8 hrsl = spi_rd8(hcd, MAX3421_REG_HRSL);
+ int rcvtog = (hrsl >> MAX3421_HRSL_RCVTOGRD_BIT) & 1;
+ int sndtog = (hrsl >> MAX3421_HRSL_SNDTOGRD_BIT) & 1;
+ int epnum = usb_endpoint_num(&urb->ep->desc);
+
+ /* no locking: HCD (i.e., we) own toggles, don't we? */
+ usb_settoggle(urb->dev, epnum, 0, rcvtog);
+ usb_settoggle(urb->dev, epnum, 1, sndtog);
+
max3421_hcd->curr_urb = NULL;
spin_lock_irqsave(&max3421_hcd->lock, flags);
usb_hcd_unlink_urb_from_ep(hcd, urb);
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index e9b18fc17617..151e93c4bd57 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -1638,11 +1638,12 @@ int xhci_hub_status_data(struct usb_hcd *hcd, char *buf)
* Inform the usbcore about resume-in-progress by returning
* a non-zero value even if there are no status changes.
*/
+ spin_lock_irqsave(&xhci->lock, flags);
+
status = bus_state->resuming_ports;
mask = PORT_CSC | PORT_PEC | PORT_OCC | PORT_PLC | PORT_WRC | PORT_CEC;
- spin_lock_irqsave(&xhci->lock, flags);
/* For each port, did anything change? If so, set that bit in buf. */
for (i = 0; i < max_ports; i++) {
temp = readl(ports[i]->addr);
diff --git a/drivers/usb/host/xhci-pci-renesas.c b/drivers/usb/host/xhci-pci-renesas.c
index 1da647961c25..5923844ed821 100644
--- a/drivers/usb/host/xhci-pci-renesas.c
+++ b/drivers/usb/host/xhci-pci-renesas.c
@@ -207,8 +207,7 @@ static int renesas_check_rom_state(struct pci_dev *pdev)
return 0;
case RENESAS_ROM_STATUS_NO_RESULT: /* No result yet */
- dev_dbg(&pdev->dev, "Unknown ROM status ...\n");
- break;
+ return 0;
case RENESAS_ROM_STATUS_ERROR: /* Error State */
default: /* All other states are marked as "Reserved states" */
@@ -225,12 +224,13 @@ static int renesas_fw_check_running(struct pci_dev *pdev)
u8 fw_state;
int err;
- /*
- * Only if device has ROM and loaded FW we can skip loading and
- * return success. Otherwise (even unknown state), attempt to load FW.
- */
- if (renesas_check_rom(pdev) && !renesas_check_rom_state(pdev))
- return 0;
+ /* Check if device has ROM and loaded, if so skip everything */
+ err = renesas_check_rom(pdev);
+ if (err) { /* we have rom */
+ err = renesas_check_rom_state(pdev);
+ if (!err)
+ return err;
+ }
/*
* Test if the device is actually needing the firmware. As most
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 18c2bbddf080..1c9a7957c45c 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -636,7 +636,14 @@ static const struct pci_device_id pci_ids[] = {
{ /* end: all zeroes */ }
};
MODULE_DEVICE_TABLE(pci, pci_ids);
+
+/*
+ * Without CONFIG_USB_XHCI_PCI_RENESAS renesas_xhci_check_request_fw() won't
+ * load firmware, so don't encumber the xhci-pci driver with it.
+ */
+#if IS_ENABLED(CONFIG_USB_XHCI_PCI_RENESAS)
MODULE_FIRMWARE("renesas_usb_fw.mem");
+#endif
/* pci driver glue; this is a "new style" PCI driver module */
static struct pci_driver xhci_pci_driver = {
diff --git a/drivers/usb/phy/phy.c b/drivers/usb/phy/phy.c
index 83ed5089475a..1b24492bb4e5 100644
--- a/drivers/usb/phy/phy.c
+++ b/drivers/usb/phy/phy.c
@@ -86,10 +86,10 @@ static struct usb_phy *__device_to_usb_phy(struct device *dev)
list_for_each_entry(usb_phy, &phy_list, head) {
if (usb_phy->dev == dev)
- break;
+ return usb_phy;
}
- return usb_phy;
+ return NULL;
}
static void usb_phy_set_default_current(struct usb_phy *usb_phy)
@@ -150,8 +150,14 @@ static int usb_phy_uevent(struct device *dev, struct kobj_uevent_env *env)
struct usb_phy *usb_phy;
char uchger_state[50] = { 0 };
char uchger_type[50] = { 0 };
+ unsigned long flags;
+ spin_lock_irqsave(&phy_lock, flags);
usb_phy = __device_to_usb_phy(dev);
+ spin_unlock_irqrestore(&phy_lock, flags);
+
+ if (!usb_phy)
+ return -ENODEV;
snprintf(uchger_state, ARRAY_SIZE(uchger_state),
"USB_CHARGER_STATE=%s", usb_chger_state[usb_phy->chg_state]);
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index b5e7991dc7d9..a3c2b01ccf7b 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -101,6 +101,8 @@ static struct dma_chan *usbhsf_dma_chan_get(struct usbhs_fifo *fifo,
#define usbhsf_dma_map(p) __usbhsf_dma_map_ctrl(p, 1)
#define usbhsf_dma_unmap(p) __usbhsf_dma_map_ctrl(p, 0)
static int __usbhsf_dma_map_ctrl(struct usbhs_pkt *pkt, int map);
+static void usbhsf_tx_irq_ctrl(struct usbhs_pipe *pipe, int enable);
+static void usbhsf_rx_irq_ctrl(struct usbhs_pipe *pipe, int enable);
struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt)
{
struct usbhs_priv *priv = usbhs_pipe_to_priv(pipe);
@@ -123,6 +125,11 @@ struct usbhs_pkt *usbhs_pkt_pop(struct usbhs_pipe *pipe, struct usbhs_pkt *pkt)
if (chan) {
dmaengine_terminate_all(chan);
usbhsf_dma_unmap(pkt);
+ } else {
+ if (usbhs_pipe_is_dir_in(pipe))
+ usbhsf_rx_irq_ctrl(pipe, 0);
+ else
+ usbhsf_tx_irq_ctrl(pipe, 0);
}
usbhs_pipe_clear_without_sequence(pipe, 0, 0);
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index 09b845d0da41..3c80bfbf3bec 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -155,6 +155,7 @@ static const struct usb_device_id id_table[] = {
{ USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
{ USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
+ { USB_DEVICE(0x10C4, 0x8A5B) }, /* CEL EM3588 ZigBee USB Stick */
{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
{ USB_DEVICE(0x10C4, 0xEA60) }, /* Silicon Labs factory default */
@@ -202,8 +203,8 @@ static const struct usb_device_id id_table[] = {
{ USB_DEVICE(0x1901, 0x0194) }, /* GE Healthcare Remote Alarm Box */
{ USB_DEVICE(0x1901, 0x0195) }, /* GE B850/B650/B450 CP2104 DP UART interface */
{ USB_DEVICE(0x1901, 0x0196) }, /* GE B850 CP2105 DP UART interface */
- { USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 Display serial interface */
- { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 M.2 Key E serial interface */
+ { USB_DEVICE(0x1901, 0x0197) }, /* GE CS1000 M.2 Key E serial interface */
+ { USB_DEVICE(0x1901, 0x0198) }, /* GE CS1000 Display serial interface */
{ USB_DEVICE(0x199B, 0xBA30) }, /* LORD WSDA-200-USB */
{ USB_DEVICE(0x19CF, 0x3000) }, /* Parrot NMEA GPS Flight Recorder */
{ USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 7608584ef4fe..0fbe253dc570 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -238,6 +238,7 @@ static void option_instat_callback(struct urb *urb);
#define QUECTEL_PRODUCT_UC15 0x9090
/* These u-blox products use Qualcomm's vendor ID */
#define UBLOX_PRODUCT_R410M 0x90b2
+#define UBLOX_PRODUCT_R6XX 0x90fa
/* These Yuga products use Qualcomm's vendor ID */
#define YUGA_PRODUCT_CLM920_NC5 0x9625
@@ -1101,6 +1102,8 @@ static const struct usb_device_id option_ids[] = {
/* u-blox products using Qualcomm vendor ID */
{ USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R410M),
.driver_info = RSVD(1) | RSVD(3) },
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, UBLOX_PRODUCT_R6XX),
+ .driver_info = RSVD(3) },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE_AND_INTERFACE_INFO(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21, 0xff, 0xff, 0xff),
.driver_info = NUMEP2 },
diff --git a/drivers/usb/storage/unusual_uas.h b/drivers/usb/storage/unusual_uas.h
index f9677a5ec31b..c35a6db993f1 100644
--- a/drivers/usb/storage/unusual_uas.h
+++ b/drivers/usb/storage/unusual_uas.h
@@ -45,6 +45,13 @@ UNUSUAL_DEV(0x059f, 0x105f, 0x0000, 0x9999,
USB_SC_DEVICE, USB_PR_DEVICE, NULL,
US_FL_NO_REPORT_OPCODES | US_FL_NO_SAME),
+/* Reported-by: Julian Sikorski <belegdol@gmail.com> */
+UNUSUAL_DEV(0x059f, 0x1061, 0x0000, 0x9999,
+ "LaCie",
+ "Rugged USB3-FW",
+ USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+ US_FL_IGNORE_UAS),
+
/*
* Apricorn USB3 dongle sometimes returns "USBSUSBSUSBS" in response to SCSI
* commands in UAS mode. Observed with the 1.28 firmware; are there others?
diff --git a/drivers/usb/typec/stusb160x.c b/drivers/usb/typec/stusb160x.c
index 6eaeba9b096e..e7745d1c2a5c 100644
--- a/drivers/usb/typec/stusb160x.c
+++ b/drivers/usb/typec/stusb160x.c
@@ -686,6 +686,15 @@ static int stusb160x_probe(struct i2c_client *client)
return -ENODEV;
/*
+ * This fwnode has a "compatible" property, but is never populated as a
+ * struct device. Instead we simply parse it to read the properties.
+ * This it breaks fw_devlink=on. To maintain backward compatibility
+ * with existing DT files, we work around this by deleting any
+ * fwnode_links to/from this fwnode.
+ */
+ fw_devlink_purge_absent_suppliers(fwnode);
+
+ /*
* When both VDD and VSYS power supplies are present, the low power
* supply VSYS is selected when VSYS voltage is above 3.1 V.
* Otherwise VDD is selected.
@@ -739,10 +748,6 @@ static int stusb160x_probe(struct i2c_client *client)
typec_set_pwr_opmode(chip->port, chip->pwr_opmode);
if (client->irq) {
- ret = stusb160x_irq_init(chip, client->irq);
- if (ret)
- goto port_unregister;
-
chip->role_sw = fwnode_usb_role_switch_get(fwnode);
if (IS_ERR(chip->role_sw)) {
ret = PTR_ERR(chip->role_sw);
@@ -752,6 +757,10 @@ static int stusb160x_probe(struct i2c_client *client)
ret);
goto port_unregister;
}
+
+ ret = stusb160x_irq_init(chip, client->irq);
+ if (ret)
+ goto role_sw_put;
} else {
/*
* If Source or Dual power role, need to enable VDD supply
@@ -775,6 +784,9 @@ static int stusb160x_probe(struct i2c_client *client)
return 0;
+role_sw_put:
+ if (chip->role_sw)
+ usb_role_switch_put(chip->role_sw);
port_unregister:
typec_unregister_port(chip->port);
all_reg_disable:
diff --git a/drivers/usb/typec/tipd/core.c b/drivers/usb/typec/tipd/core.c
index 938219bc1b4b..21b3ae25c76d 100644
--- a/drivers/usb/typec/tipd/core.c
+++ b/drivers/usb/typec/tipd/core.c
@@ -629,6 +629,15 @@ static int tps6598x_probe(struct i2c_client *client)
if (!fwnode)
return -ENODEV;
+ /*
+ * This fwnode has a "compatible" property, but is never populated as a
+ * struct device. Instead we simply parse it to read the properties.
+ * This breaks fw_devlink=on. To maintain backward compatibility
+ * with existing DT files, we work around this by deleting any
+ * fwnode_links to/from this fwnode.
+ */
+ fw_devlink_purge_absent_suppliers(fwnode);
+
tps->role_sw = fwnode_usb_role_switch_get(fwnode);
if (IS_ERR(tps->role_sw)) {
ret = PTR_ERR(tps->role_sw);
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 06fb7a93a1bd..4d5ae61580aa 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -168,21 +168,6 @@ config OSF4_COMPAT
with v4 shared libraries freely available from Compaq. If you're
going to use shared libraries from Tru64 version 5.0 or later, say N.
-config BINFMT_EM86
- tristate "Kernel support for Linux/Intel ELF binaries"
- depends on ALPHA
- help
- Say Y here if you want to be able to execute Linux/Intel ELF
- binaries just like native Alpha binaries on your Alpha machine. For
- this to work, you need to have the emulator /usr/bin/em86 in place.
-
- You can get the same functionality by saying N here and saying Y to
- "Kernel support for MISC binaries".
-
- You may answer M to compile the emulation support as a module and
- later load the module when you want to use a Linux/Intel binary. The
- module will be called binfmt_em86. If unsure, say Y.
-
config BINFMT_MISC
tristate "Kernel support for MISC binaries"
help
diff --git a/fs/Makefile b/fs/Makefile
index 9c708e1fbe8f..f98f3e691c37 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -39,7 +39,6 @@ obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FS_VERITY) += verity/
obj-$(CONFIG_FILE_LOCKING) += locks.o
obj-$(CONFIG_BINFMT_AOUT) += binfmt_aout.o
-obj-$(CONFIG_BINFMT_EM86) += binfmt_em86.o
obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o
obj-$(CONFIG_BINFMT_SCRIPT) += binfmt_script.o
obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index d3c6bb22c5f4..a3f5de28be79 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -29,16 +29,11 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);
static int afs_deliver_yfs_cb_callback(struct afs_call *);
-#define CM_NAME(name) \
- char afs_SRXCB##name##_name[] __tracepoint_string = \
- "CB." #name
-
/*
* CB.CallBack operation type
*/
-static CM_NAME(CallBack);
static const struct afs_call_type afs_SRXCBCallBack = {
- .name = afs_SRXCBCallBack_name,
+ .name = "CB.CallBack",
.deliver = afs_deliver_cb_callback,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_CallBack,
@@ -47,9 +42,8 @@ static const struct afs_call_type afs_SRXCBCallBack = {
/*
* CB.InitCallBackState operation type
*/
-static CM_NAME(InitCallBackState);
static const struct afs_call_type afs_SRXCBInitCallBackState = {
- .name = afs_SRXCBInitCallBackState_name,
+ .name = "CB.InitCallBackState",
.deliver = afs_deliver_cb_init_call_back_state,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_InitCallBackState,
@@ -58,9 +52,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState = {
/*
* CB.InitCallBackState3 operation type
*/
-static CM_NAME(InitCallBackState3);
static const struct afs_call_type afs_SRXCBInitCallBackState3 = {
- .name = afs_SRXCBInitCallBackState3_name,
+ .name = "CB.InitCallBackState3",
.deliver = afs_deliver_cb_init_call_back_state3,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_InitCallBackState,
@@ -69,9 +62,8 @@ static const struct afs_call_type afs_SRXCBInitCallBackState3 = {
/*
* CB.Probe operation type
*/
-static CM_NAME(Probe);
static const struct afs_call_type afs_SRXCBProbe = {
- .name = afs_SRXCBProbe_name,
+ .name = "CB.Probe",
.deliver = afs_deliver_cb_probe,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_Probe,
@@ -80,9 +72,8 @@ static const struct afs_call_type afs_SRXCBProbe = {
/*
* CB.ProbeUuid operation type
*/
-static CM_NAME(ProbeUuid);
static const struct afs_call_type afs_SRXCBProbeUuid = {
- .name = afs_SRXCBProbeUuid_name,
+ .name = "CB.ProbeUuid",
.deliver = afs_deliver_cb_probe_uuid,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_ProbeUuid,
@@ -91,9 +82,8 @@ static const struct afs_call_type afs_SRXCBProbeUuid = {
/*
* CB.TellMeAboutYourself operation type
*/
-static CM_NAME(TellMeAboutYourself);
static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
- .name = afs_SRXCBTellMeAboutYourself_name,
+ .name = "CB.TellMeAboutYourself",
.deliver = afs_deliver_cb_tell_me_about_yourself,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_TellMeAboutYourself,
@@ -102,9 +92,8 @@ static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
/*
* YFS CB.CallBack operation type
*/
-static CM_NAME(YFS_CallBack);
static const struct afs_call_type afs_SRXYFSCB_CallBack = {
- .name = afs_SRXCBYFS_CallBack_name,
+ .name = "YFSCB.CallBack",
.deliver = afs_deliver_yfs_cb_callback,
.destructor = afs_cm_destructor,
.work = SRXAFSCB_CallBack,
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 78719f2f567e..ac829e63c570 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -656,7 +656,6 @@ static int afs_do_lookup_one(struct inode *dir, struct dentry *dentry,
return ret;
}
- ret = -ENOENT;
if (!cookie.found) {
_leave(" = -ENOENT [not found]");
return -ENOENT;
@@ -2020,17 +2019,20 @@ static int afs_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
if (d_count(new_dentry) > 2) {
/* copy the target dentry's name */
- ret = -ENOMEM;
op->rename.tmp = d_alloc(new_dentry->d_parent,
&new_dentry->d_name);
- if (!op->rename.tmp)
+ if (!op->rename.tmp) {
+ op->error = -ENOMEM;
goto error;
+ }
ret = afs_sillyrename(new_dvnode,
AFS_FS_I(d_inode(new_dentry)),
new_dentry, op->key);
- if (ret)
+ if (ret) {
+ op->error = ret;
goto error;
+ }
op->dentry_2 = op->rename.tmp;
op->rename.rehash = NULL;
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 3104b62c2082..c0534697268e 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -771,14 +771,20 @@ int afs_writepages(struct address_space *mapping,
if (wbc->range_cyclic) {
start = mapping->writeback_index * PAGE_SIZE;
ret = afs_writepages_region(mapping, wbc, start, LLONG_MAX, &next);
- if (start > 0 && wbc->nr_to_write > 0 && ret == 0)
- ret = afs_writepages_region(mapping, wbc, 0, start,
- &next);
- mapping->writeback_index = next / PAGE_SIZE;
+ if (ret == 0) {
+ mapping->writeback_index = next / PAGE_SIZE;
+ if (start > 0 && wbc->nr_to_write > 0) {
+ ret = afs_writepages_region(mapping, wbc, 0,
+ start, &next);
+ if (ret == 0)
+ mapping->writeback_index =
+ next / PAGE_SIZE;
+ }
+ }
} else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
ret = afs_writepages_region(mapping, wbc, 0, LLONG_MAX, &next);
- if (wbc->nr_to_write > 0)
- mapping->writeback_index = next;
+ if (wbc->nr_to_write > 0 && ret == 0)
+ mapping->writeback_index = next / PAGE_SIZE;
} else {
ret = afs_writepages_region(mapping, wbc,
wbc->range_start, wbc->range_end, &next);
diff --git a/fs/binfmt_em86.c b/fs/binfmt_em86.c
deleted file mode 100644
index 06b9b9fddf70..000000000000
--- a/fs/binfmt_em86.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * linux/fs/binfmt_em86.c
- *
- * Based on linux/fs/binfmt_script.c
- * Copyright (C) 1996 Martin von Löwis
- * original #!-checking implemented by tytso.
- *
- * em86 changes Copyright (C) 1997 Jim Paradis
- */
-
-#include <linux/module.h>
-#include <linux/string.h>
-#include <linux/stat.h>
-#include <linux/binfmts.h>
-#include <linux/elf.h>
-#include <linux/init.h>
-#include <linux/fs.h>
-#include <linux/file.h>
-#include <linux/errno.h>
-
-
-#define EM86_INTERP "/usr/bin/em86"
-#define EM86_I_NAME "em86"
-
-static int load_em86(struct linux_binprm *bprm)
-{
- const char *i_name, *i_arg;
- char *interp;
- struct file * file;
- int retval;
- struct elfhdr elf_ex;
-
- /* Make sure this is a Linux/Intel ELF executable... */
- elf_ex = *((struct elfhdr *)bprm->buf);
-
- if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
- return -ENOEXEC;
-
- /* First of all, some simple consistency checks */
- if ((elf_ex.e_type != ET_EXEC && elf_ex.e_type != ET_DYN) ||
- (!((elf_ex.e_machine == EM_386) || (elf_ex.e_machine == EM_486))) ||
- !bprm->file->f_op->mmap) {
- return -ENOEXEC;
- }
-
- /* Need to be able to load the file after exec */
- if (bprm->interp_flags & BINPRM_FLAGS_PATH_INACCESSIBLE)
- return -ENOENT;
-
- /* Unlike in the script case, we don't have to do any hairy
- * parsing to find our interpreter... it's hardcoded!
- */
- interp = EM86_INTERP;
- i_name = EM86_I_NAME;
- i_arg = NULL; /* We reserve the right to add an arg later */
-
- /*
- * Splice in (1) the interpreter's name for argv[0]
- * (2) (optional) argument to interpreter
- * (3) filename of emulated file (replace argv[0])
- *
- * This is done in reverse order, because of how the
- * user environment and arguments are stored.
- */
- remove_arg_zero(bprm);
- retval = copy_string_kernel(bprm->filename, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- if (i_arg) {
- retval = copy_string_kernel(i_arg, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
- }
- retval = copy_string_kernel(i_name, bprm);
- if (retval < 0) return retval;
- bprm->argc++;
-
- /*
- * OK, now restart the process with the interpreter's inode.
- * Note that we use open_exec() as the name is now in kernel
- * space, and we don't need to copy it.
- */
- file = open_exec(interp);
- if (IS_ERR(file))
- return PTR_ERR(file);
-
- bprm->interpreter = file;
- return 0;
-}
-
-static struct linux_binfmt em86_format = {
- .module = THIS_MODULE,
- .load_binary = load_em86,
-};
-
-static int __init init_em86_binfmt(void)
-{
- register_binfmt(&em86_format);
- return 0;
-}
-
-static void __exit exit_em86_binfmt(void)
-{
- unregister_binfmt(&em86_format);
-}
-
-core_initcall(init_em86_binfmt);
-module_exit(exit_em86_binfmt);
-MODULE_LICENSE("GPL");
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0c424a0cadaa..9ef4f1fc2cb0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -812,6 +812,8 @@ static void bdev_free_inode(struct inode *inode)
free_percpu(bdev->bd_stats);
kfree(bdev->bd_meta_info);
+ if (!bdev_is_partition(bdev))
+ kfree(bdev->bd_disk);
kmem_cache_free(bdev_cachep, BDEV_I(inode));
}
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 7a8a2fc19533..78b202d198b8 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1488,15 +1488,15 @@ static int btrfs_find_all_roots_safe(struct btrfs_trans_handle *trans,
int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
u64 time_seq, struct ulist **roots,
- bool ignore_offset)
+ bool ignore_offset, bool skip_commit_root_sem)
{
int ret;
- if (!trans)
+ if (!trans && !skip_commit_root_sem)
down_read(&fs_info->commit_root_sem);
ret = btrfs_find_all_roots_safe(trans, fs_info, bytenr,
time_seq, roots, ignore_offset);
- if (!trans)
+ if (!trans && !skip_commit_root_sem)
up_read(&fs_info->commit_root_sem);
return ret;
}
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index 17abde7f794c..ff5f07f9940b 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -47,7 +47,8 @@ int btrfs_find_all_leafs(struct btrfs_trans_handle *trans,
const u64 *extent_item_pos, bool ignore_offset);
int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
- u64 time_seq, struct ulist **roots, bool ignore_offset);
+ u64 time_seq, struct ulist **roots, bool ignore_offset,
+ bool skip_commit_root_sem);
char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
u32 name_len, unsigned long name_off,
struct extent_buffer *eb_in, u64 parent,
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 9a023ae0f98b..30d82cdf128c 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -352,7 +352,7 @@ static void end_compressed_bio_write(struct bio *bio)
btrfs_record_physical_zoned(inode, cb->start, bio);
btrfs_writepage_endio_finish_ordered(BTRFS_I(inode), NULL,
cb->start, cb->start + cb->len - 1,
- bio->bi_status == BLK_STS_OK);
+ !cb->errors);
end_compressed_writeback(inode, cb);
/* note, our inode could be gone now */
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 06bc842ecdb3..ca848b183474 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -974,7 +974,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
if (qrecord_inserted)
- btrfs_qgroup_trace_extent_post(fs_info, record);
+ btrfs_qgroup_trace_extent_post(trans, record);
return 0;
}
@@ -1069,7 +1069,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
if (qrecord_inserted)
- return btrfs_qgroup_trace_extent_post(fs_info, record);
+ return btrfs_qgroup_trace_extent_post(trans, record);
return 0;
}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b117dd3b8172..a59ab7b9aea0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -209,7 +209,7 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
static void csum_tree_block(struct extent_buffer *buf, u8 *result)
{
struct btrfs_fs_info *fs_info = buf->fs_info;
- const int num_pages = fs_info->nodesize >> PAGE_SHIFT;
+ const int num_pages = num_extent_pages(buf);
const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
char *kaddr;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d296483d148f..268ce58d4569 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6019,6 +6019,9 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
mutex_lock(&fs_info->fs_devices->device_list_mutex);
devices = &fs_info->fs_devices->devices;
list_for_each_entry(device, devices, dev_list) {
+ if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
+ continue;
+
ret = btrfs_trim_free_extents(device, &group_trimmed);
if (ret) {
dev_failed++;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8f60314c36c5..0117d867ecf8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2992,7 +2992,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
goto out;
}
- if (ordered_extent->disk)
+ if (ordered_extent->bdev)
btrfs_rewrite_logical_zoned(ordered_extent);
btrfs_free_io_failure_record(inode, start, end);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 6eb41b7c0c84..5c0f8481e25e 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -190,8 +190,6 @@ static int __btrfs_add_ordered_extent(struct btrfs_inode *inode, u64 file_offset
entry->truncated_len = (u64)-1;
entry->qgroup_rsv = ret;
entry->physical = (u64)-1;
- entry->disk = NULL;
- entry->partno = (u8)-1;
ASSERT(type == BTRFS_ORDERED_REGULAR ||
type == BTRFS_ORDERED_NOCOW ||
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 566472004edd..b2d88aba8420 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -145,8 +145,7 @@ struct btrfs_ordered_extent {
* command in a workqueue context
*/
u64 physical;
- struct gendisk *disk;
- u8 partno;
+ struct block_device *bdev;
};
/*
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 07ec06d4e972..0fa121171ca1 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1704,17 +1704,39 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
return 0;
}
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans,
struct btrfs_qgroup_extent_record *qrecord)
{
struct ulist *old_root;
u64 bytenr = qrecord->bytenr;
int ret;
- ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false);
+ /*
+ * We are always called in a context where we are already holding a
+ * transaction handle. Often we are called when adding a data delayed
+ * reference from btrfs_truncate_inode_items() (truncating or unlinking),
+ * in which case we will be holding a write lock on extent buffer from a
+ * subvolume tree. In this case we can't allow btrfs_find_all_roots() to
+ * acquire fs_info->commit_root_sem, because that is a higher level lock
+ * that must be acquired before locking any extent buffers.
+ *
+ * So we want btrfs_find_all_roots() to not acquire the commit_root_sem
+ * but we can't pass it a non-NULL transaction handle, because otherwise
+ * it would not use commit roots and would lock extent buffers, causing
+ * a deadlock if it ends up trying to read lock the same extent buffer
+ * that was previously write locked at btrfs_truncate_inode_items().
+ *
+ * So pass a NULL transaction handle to btrfs_find_all_roots() and
+ * explicitly tell it to not acquire the commit_root_sem - if we are
+ * holding a transaction handle we don't need its protection.
+ */
+ ASSERT(trans != NULL);
+
+ ret = btrfs_find_all_roots(NULL, trans->fs_info, bytenr, 0, &old_root,
+ false, true);
if (ret < 0) {
- fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- btrfs_warn(fs_info,
+ trans->fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ btrfs_warn(trans->fs_info,
"error accounting new delayed refs extent (err code: %d), quota inconsistent",
ret);
return 0;
@@ -1758,7 +1780,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
kfree(record);
return 0;
}
- return btrfs_qgroup_trace_extent_post(fs_info, record);
+ return btrfs_qgroup_trace_extent_post(trans, record);
}
int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
@@ -2629,7 +2651,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
/* Search commit root to find old_roots */
ret = btrfs_find_all_roots(NULL, fs_info,
record->bytenr, 0,
- &record->old_roots, false);
+ &record->old_roots, false, false);
if (ret < 0)
goto cleanup;
}
@@ -2645,7 +2667,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
* current root. It's safe inside commit_transaction().
*/
ret = btrfs_find_all_roots(trans, fs_info,
- record->bytenr, BTRFS_SEQ_LAST, &new_roots, false);
+ record->bytenr, BTRFS_SEQ_LAST, &new_roots, false, false);
if (ret < 0)
goto cleanup;
if (qgroup_to_skip) {
@@ -3179,7 +3201,7 @@ static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
num_bytes = found.offset;
ret = btrfs_find_all_roots(NULL, fs_info, found.objectid, 0,
- &roots, false);
+ &roots, false, false);
if (ret < 0)
goto out;
/* For rescan, just pass old_roots as NULL */
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 7283e4f549af..880e9df0dac1 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -298,7 +298,7 @@ int btrfs_qgroup_trace_extent_nolock(
* using current root, then we can move all expensive backref walk out of
* transaction committing, but not now as qgroup accounting will be wrong again.
*/
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+int btrfs_qgroup_trace_extent_post(struct btrfs_trans_handle *trans,
struct btrfs_qgroup_extent_record *qrecord);
/*
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index f3137285a9e2..98b5aaba46f1 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -224,7 +224,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
* quota.
*/
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
@@ -237,7 +237,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -261,7 +261,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
new_roots = NULL;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
@@ -273,7 +273,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
return -EINVAL;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -325,7 +325,7 @@ static int test_multiple_refs(struct btrfs_root *root,
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
@@ -338,7 +338,7 @@ static int test_multiple_refs(struct btrfs_root *root,
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -360,7 +360,7 @@ static int test_multiple_refs(struct btrfs_root *root,
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
@@ -373,7 +373,7 @@ static int test_multiple_refs(struct btrfs_root *root,
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
@@ -401,7 +401,7 @@ static int test_multiple_refs(struct btrfs_root *root,
}
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
@@ -414,7 +414,7 @@ static int test_multiple_refs(struct btrfs_root *root,
return ret;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots,
- false);
+ false, false);
if (ret) {
ulist_free(old_roots);
ulist_free(new_roots);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index dc6eb088d73e..e6430ac9bbe8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -5526,16 +5526,29 @@ log_extents:
spin_lock(&inode->lock);
inode->logged_trans = trans->transid;
/*
- * Don't update last_log_commit if we logged that an inode exists
- * after it was loaded to memory (full_sync bit set).
- * This is to prevent data loss when we do a write to the inode,
- * then the inode gets evicted after all delalloc was flushed,
- * then we log it exists (due to a rename for example) and then
- * fsync it. This last fsync would do nothing (not logging the
- * extents previously written).
+ * Don't update last_log_commit if we logged that an inode exists.
+ * We do this for two reasons:
+ *
+ * 1) We might have had buffered writes to this inode that were
+ * flushed and had their ordered extents completed in this
+ * transaction, but we did not previously log the inode with
+ * LOG_INODE_ALL. Later the inode was evicted and after that
+ * it was loaded again and this LOG_INODE_EXISTS log operation
+ * happened. We must make sure that if an explicit fsync against
+ * the inode is performed later, it logs the new extents, an
+ * updated inode item, etc, and syncs the log. The same logic
+ * applies to direct IO writes instead of buffered writes.
+ *
+ * 2) When we log the inode with LOG_INODE_EXISTS, its inode item
+ * is logged with an i_size of 0 or whatever value was logged
+ * before. If later the i_size of the inode is increased by a
+ * truncate operation, the log is synced through an fsync of
+ * some other inode and then finally an explicit fsync against
+ * this inode is made, we must make sure this fsync logs the
+ * inode with the new i_size, the hole between old i_size and
+ * the new i_size, and syncs the log.
*/
- if (inode_only != LOG_INODE_EXISTS ||
- !test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags))
+ if (inode_only != LOG_INODE_EXISTS)
inode->last_log_commit = inode->last_sub_trans;
spin_unlock(&inode->lock);
}
@@ -6490,8 +6503,8 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans,
* if this inode hasn't been logged and directory we're renaming it
* from hasn't been logged, we don't need to log it
*/
- if (inode->logged_trans < trans->transid &&
- (!old_dir || old_dir->logged_trans < trans->transid))
+ if (!inode_logged(trans, inode) &&
+ (!old_dir || !inode_logged(trans, old_dir)))
return;
/*
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1e4d43ffe38b..70f94b75f25a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1078,6 +1078,7 @@ static void __btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices,
if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state)) {
list_del_init(&device->dev_alloc_list);
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
+ fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 297c0b1c0634..907c2cc45c9c 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1349,8 +1349,7 @@ void btrfs_record_physical_zoned(struct inode *inode, u64 file_offset,
return;
ordered->physical = physical;
- ordered->disk = bio->bi_bdev->bd_disk;
- ordered->partno = bio->bi_bdev->bd_partno;
+ ordered->bdev = bio->bi_bdev;
btrfs_put_ordered_extent(ordered);
}
@@ -1362,18 +1361,16 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
struct extent_map_tree *em_tree;
struct extent_map *em;
struct btrfs_ordered_sum *sum;
- struct block_device *bdev;
u64 orig_logical = ordered->disk_bytenr;
u64 *logical = NULL;
int nr, stripe_len;
/* Zoned devices should not have partitions. So, we can assume it is 0 */
- ASSERT(ordered->partno == 0);
- bdev = bdgrab(ordered->disk->part0);
- if (WARN_ON(!bdev))
+ ASSERT(!bdev_is_partition(ordered->bdev));
+ if (WARN_ON(!ordered->bdev))
return;
- if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, bdev,
+ if (WARN_ON(btrfs_rmap_block(fs_info, orig_logical, ordered->bdev,
ordered->physical, &logical, &nr,
&stripe_len)))
goto out;
@@ -1402,7 +1399,6 @@ void btrfs_rewrite_logical_zoned(struct btrfs_ordered_extent *ordered)
out:
kfree(logical);
- bdput(bdev);
}
bool btrfs_check_meta_write_pointer(struct btrfs_fs_info *fs_info,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index a818213c972f..9db1b39df773 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -4456,7 +4456,7 @@ bool check_session_state(struct ceph_mds_session *s)
break;
case CEPH_MDS_SESSION_CLOSING:
/* Should never reach this when we're unmounting */
- WARN_ON_ONCE(true);
+ WARN_ON_ONCE(s->s_ttl);
fallthrough;
case CEPH_MDS_SESSION_NEW:
case CEPH_MDS_SESSION_RESTARTING:
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index f72e3b3dca69..65d1a65bfc37 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -873,8 +873,11 @@ PsxDelete:
InformationLevel) - 4;
offset = param_offset + params;
- /* Setup pointer to Request Data (inode type) */
- pRqD = (struct unlink_psx_rq *)(((char *)&pSMB->hdr.Protocol) + offset);
+ /* Setup pointer to Request Data (inode type).
+ * Note that SMB offsets are from the beginning of SMB which is 4 bytes
+ * in, after RFC1001 field
+ */
+ pRqD = (struct unlink_psx_rq *)((char *)(pSMB) + offset + 4);
pRqD->type = cpu_to_le16(type);
pSMB->ParameterOffset = cpu_to_le16(param_offset);
pSMB->DataOffset = cpu_to_le16(offset);
@@ -1081,7 +1084,8 @@ PsxCreat:
param_offset = offsetof(struct smb_com_transaction2_spi_req,
InformationLevel) - 4;
offset = param_offset + params;
- pdata = (OPEN_PSX_REQ *)(((char *)&pSMB->hdr.Protocol) + offset);
+ /* SMB offsets are from the beginning of SMB which is 4 bytes in, after RFC1001 field */
+ pdata = (OPEN_PSX_REQ *)((char *)(pSMB) + offset + 4);
pdata->Level = cpu_to_le16(SMB_QUERY_FILE_UNIX_BASIC);
pdata->Permissions = cpu_to_le64(mode);
pdata->PosixOpenFlags = cpu_to_le32(posix_flags);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 1b04d6ec14dd..3781eee9360a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -220,7 +220,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
#ifdef CONFIG_CIFS_DFS_UPCALL
struct super_block *sb = NULL;
struct cifs_sb_info *cifs_sb = NULL;
- struct dfs_cache_tgt_list tgt_list = {0};
+ struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
struct dfs_cache_tgt_iterator *tgt_it = NULL;
#endif
@@ -3130,7 +3130,7 @@ static int do_dfs_failover(const char *path, const char *full_path, struct cifs_
{
int rc;
char *npath = NULL;
- struct dfs_cache_tgt_list tgt_list = {0};
+ struct dfs_cache_tgt_list tgt_list = DFS_CACHE_TGT_LIST_INIT(tgt_list);
struct dfs_cache_tgt_iterator *tgt_it = NULL;
struct smb3_fs_context tmp_ctx = {NULL};
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 7c1769714609..283745592844 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -19,6 +19,7 @@
#include "cifs_debug.h"
#include "cifs_unicode.h"
#include "smb2glob.h"
+#include "dns_resolve.h"
#include "dfs_cache.h"
@@ -911,6 +912,7 @@ static int get_targets(struct cache_entry *ce, struct dfs_cache_tgt_list *tl)
err_free_it:
list_for_each_entry_safe(it, nit, head, it_list) {
+ list_del(&it->it_list);
kfree(it->it_name);
kfree(it);
}
@@ -1293,6 +1295,194 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it,
return 0;
}
+static bool target_share_equal(struct TCP_Server_Info *server, const char *s1, const char *s2)
+{
+ char unc[sizeof("\\\\") + SERVER_NAME_LENGTH] = {0};
+ const char *host;
+ size_t hostlen;
+ char *ip = NULL;
+ struct sockaddr sa;
+ bool match;
+ int rc;
+
+ if (strcasecmp(s1, s2))
+ return false;
+
+ /*
+ * Resolve share's hostname and check if server address matches. Otherwise just ignore it
+ * as we could not have upcall to resolve hostname or failed to convert ip address.
+ */
+ match = true;
+ extract_unc_hostname(s1, &host, &hostlen);
+ scnprintf(unc, sizeof(unc), "\\\\%.*s", (int)hostlen, host);
+
+ rc = dns_resolve_server_name_to_ip(unc, &ip, NULL);
+ if (rc < 0) {
+ cifs_dbg(FYI, "%s: could not resolve %.*s. assuming server address matches.\n",
+ __func__, (int)hostlen, host);
+ return true;
+ }
+
+ if (!cifs_convert_address(&sa, ip, strlen(ip))) {
+ cifs_dbg(VFS, "%s: failed to convert address \'%s\'. skip address matching.\n",
+ __func__, ip);
+ } else {
+ mutex_lock(&server->srv_mutex);
+ match = cifs_match_ipaddr((struct sockaddr *)&server->dstaddr, &sa);
+ mutex_unlock(&server->srv_mutex);
+ }
+
+ kfree(ip);
+ return match;
+}
+
+/*
+ * Mark dfs tcon for reconnecting when the currently connected tcon does not match any of the new
+ * target shares in @refs.
+ */
+static void mark_for_reconnect_if_needed(struct cifs_tcon *tcon, struct dfs_cache_tgt_list *tl,
+ const struct dfs_info3_param *refs, int numrefs)
+{
+ struct dfs_cache_tgt_iterator *it;
+ int i;
+
+ for (it = dfs_cache_get_tgt_iterator(tl); it; it = dfs_cache_get_next_tgt(tl, it)) {
+ for (i = 0; i < numrefs; i++) {
+ if (target_share_equal(tcon->ses->server, dfs_cache_get_tgt_name(it),
+ refs[i].node_name))
+ return;
+ }
+ }
+
+ cifs_dbg(FYI, "%s: no cached or matched targets. mark dfs share for reconnect.\n", __func__);
+ for (i = 0; i < tcon->ses->chan_count; i++) {
+ spin_lock(&GlobalMid_Lock);
+ if (tcon->ses->chans[i].server->tcpStatus != CifsExiting)
+ tcon->ses->chans[i].server->tcpStatus = CifsNeedReconnect;
+ spin_unlock(&GlobalMid_Lock);
+ }
+}
+
+/* Refresh dfs referral of tcon and mark it for reconnect if needed */
+static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool force_refresh)
+{
+ const char *path = tcon->dfs_path + 1;
+ struct cifs_ses *ses;
+ struct cache_entry *ce;
+ struct dfs_info3_param *refs = NULL;
+ int numrefs = 0;
+ bool needs_refresh = false;
+ struct dfs_cache_tgt_list tl = DFS_CACHE_TGT_LIST_INIT(tl);
+ int rc = 0;
+ unsigned int xid;
+
+ ses = find_ipc_from_server_path(sessions, path);
+ if (IS_ERR(ses)) {
+ cifs_dbg(FYI, "%s: could not find ipc session\n", __func__);
+ return PTR_ERR(ses);
+ }
+
+ down_read(&htable_rw_lock);
+ ce = lookup_cache_entry(path);
+ needs_refresh = force_refresh || IS_ERR(ce) || cache_entry_expired(ce);
+ if (!IS_ERR(ce)) {
+ rc = get_targets(ce, &tl);
+ if (rc)
+ cifs_dbg(FYI, "%s: could not get dfs targets: %d\n", __func__, rc);
+ }
+ up_read(&htable_rw_lock);
+
+ if (!needs_refresh) {
+ rc = 0;
+ goto out;
+ }
+
+ xid = get_xid();
+ rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
+ free_xid(xid);
+
+ /* Create or update a cache entry with the new referral */
+ if (!rc) {
+ dump_refs(refs, numrefs);
+
+ down_write(&htable_rw_lock);
+ ce = lookup_cache_entry(path);
+ if (IS_ERR(ce))
+ add_cache_entry_locked(refs, numrefs);
+ else if (force_refresh || cache_entry_expired(ce))
+ update_cache_entry_locked(ce, refs, numrefs);
+ up_write(&htable_rw_lock);
+
+ mark_for_reconnect_if_needed(tcon, &tl, refs, numrefs);
+ }
+
+out:
+ dfs_cache_free_tgts(&tl);
+ free_dfs_info_array(refs, numrefs);
+ return rc;
+}
+
+/**
+ * dfs_cache_remount_fs - remount a DFS share
+ *
+ * Reconfigure dfs mount by forcing a new DFS referral and if the currently cached targets do not
+ * match any of the new targets, mark it for reconnect.
+ *
+ * @cifs_sb: cifs superblock.
+ *
+ * Return zero if remounted, otherwise non-zero.
+ */
+int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb)
+{
+ struct cifs_tcon *tcon;
+ struct mount_group *mg;
+ struct cifs_ses *sessions[CACHE_MAX_ENTRIES + 1] = {NULL};
+ int rc;
+
+ if (!cifs_sb || !cifs_sb->master_tlink)
+ return -EINVAL;
+
+ tcon = cifs_sb_master_tcon(cifs_sb);
+ if (!tcon->dfs_path) {
+ cifs_dbg(FYI, "%s: not a dfs tcon\n", __func__);
+ return 0;
+ }
+
+ if (uuid_is_null(&cifs_sb->dfs_mount_id)) {
+ cifs_dbg(FYI, "%s: tcon has no dfs mount group id\n", __func__);
+ return -EINVAL;
+ }
+
+ mutex_lock(&mount_group_list_lock);
+ mg = find_mount_group_locked(&cifs_sb->dfs_mount_id);
+ if (IS_ERR(mg)) {
+ mutex_unlock(&mount_group_list_lock);
+ cifs_dbg(FYI, "%s: tcon has ipc session to refresh referral\n", __func__);
+ return PTR_ERR(mg);
+ }
+ kref_get(&mg->refcount);
+ mutex_unlock(&mount_group_list_lock);
+
+ spin_lock(&mg->lock);
+ memcpy(&sessions, mg->sessions, mg->num_sessions * sizeof(mg->sessions[0]));
+ spin_unlock(&mg->lock);
+
+ /*
+ * After reconnecting to a different server, unique ids won't match anymore, so we disable
+ * serverino. This prevents dentry revalidation to think the dentry are stale (ESTALE).
+ */
+ cifs_autodisable_serverino(cifs_sb);
+ /*
+ * Force the use of prefix path to support failover on DFS paths that resolve to targets
+ * that have different prefix paths.
+ */
+ cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_USE_PREFIX_PATH;
+ rc = refresh_tcon(sessions, tcon, true);
+
+ kref_put(&mg->refcount, mount_group_release);
+ return rc;
+}
+
/*
* Refresh all active dfs mounts regardless of whether they are in cache or not.
* (cache can be cleared)
@@ -1303,7 +1493,6 @@ static void refresh_mounts(struct cifs_ses **sessions)
struct cifs_ses *ses;
struct cifs_tcon *tcon, *ntcon;
struct list_head tcons;
- unsigned int xid;
INIT_LIST_HEAD(&tcons);
@@ -1321,44 +1510,8 @@ static void refresh_mounts(struct cifs_ses **sessions)
spin_unlock(&cifs_tcp_ses_lock);
list_for_each_entry_safe(tcon, ntcon, &tcons, ulist) {
- const char *path = tcon->dfs_path + 1;
- struct cache_entry *ce;
- struct dfs_info3_param *refs = NULL;
- int numrefs = 0;
- bool needs_refresh = false;
- int rc = 0;
-
list_del_init(&tcon->ulist);
-
- ses = find_ipc_from_server_path(sessions, path);
- if (IS_ERR(ses))
- goto next_tcon;
-
- down_read(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- needs_refresh = IS_ERR(ce) || cache_entry_expired(ce);
- up_read(&htable_rw_lock);
-
- if (!needs_refresh)
- goto next_tcon;
-
- xid = get_xid();
- rc = get_dfs_referral(xid, ses, path, &refs, &numrefs);
- free_xid(xid);
-
- /* Create or update a cache entry with the new referral */
- if (!rc) {
- down_write(&htable_rw_lock);
- ce = lookup_cache_entry(path);
- if (IS_ERR(ce))
- add_cache_entry_locked(refs, numrefs);
- else if (cache_entry_expired(ce))
- update_cache_entry_locked(ce, refs, numrefs);
- up_write(&htable_rw_lock);
- }
-
-next_tcon:
- free_dfs_info_array(refs, numrefs);
+ refresh_tcon(sessions, tcon, false);
cifs_put_tcon(tcon);
}
}
diff --git a/fs/cifs/dfs_cache.h b/fs/cifs/dfs_cache.h
index b29d3ae64829..52070d1df189 100644
--- a/fs/cifs/dfs_cache.h
+++ b/fs/cifs/dfs_cache.h
@@ -13,6 +13,8 @@
#include <linux/uuid.h>
#include "cifsglob.h"
+#define DFS_CACHE_TGT_LIST_INIT(var) { .tl_numtgts = 0, .tl_list = LIST_HEAD_INIT((var).tl_list), }
+
struct dfs_cache_tgt_list {
int tl_numtgts;
struct list_head tl_list;
@@ -44,6 +46,7 @@ int dfs_cache_get_tgt_share(char *path, const struct dfs_cache_tgt_iterator *it,
void dfs_cache_put_refsrv_sessions(const uuid_t *mount_id);
void dfs_cache_add_refsrv_session(const uuid_t *mount_id, struct cifs_ses *ses);
char *dfs_cache_canonical_path(const char *path, const struct nls_table *cp, int remap);
+int dfs_cache_remount_fs(struct cifs_sb_info *cifs_sb);
static inline struct dfs_cache_tgt_iterator *
dfs_cache_get_next_tgt(struct dfs_cache_tgt_list *tl,
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index cd108607a070..0a72840a88f1 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -4619,7 +4619,7 @@ read_complete:
static int cifs_readpage(struct file *file, struct page *page)
{
- loff_t offset = (loff_t)page->index << PAGE_SHIFT;
+ loff_t offset = page_file_offset(page);
int rc = -EACCES;
unsigned int xid;
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 553adfbcc22a..eed59bc1d913 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -13,6 +13,9 @@
#include <linux/magic.h>
#include <linux/security.h>
#include <net/net_namespace.h>
+#ifdef CONFIG_CIFS_DFS_UPCALL
+#include "dfs_cache.h"
+#endif
*/
#include <linux/ctype.h>
@@ -779,6 +782,10 @@ static int smb3_reconfigure(struct fs_context *fc)
smb3_cleanup_fs_context_contents(cifs_sb->ctx);
rc = smb3_fs_context_dup(cifs_sb->ctx, ctx);
smb3_update_mnt_flags(cifs_sb);
+#ifdef CONFIG_CIFS_DFS_UPCALL
+ if (!rc)
+ rc = dfs_cache_remount_fs(cifs_sb);
+#endif
return rc;
}
@@ -918,6 +925,13 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
ctx->cred_uid = uid;
ctx->cruid_specified = true;
break;
+ case Opt_backupuid:
+ uid = make_kuid(current_user_ns(), result.uint_32);
+ if (!uid_valid(uid))
+ goto cifs_parse_mount_err;
+ ctx->backupuid = uid;
+ ctx->backupuid_specified = true;
+ break;
case Opt_backupgid:
gid = make_kgid(current_user_ns(), result.uint_32);
if (!gid_valid(gid))
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ba3c58e1f725..2dfd0d8297eb 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -3618,6 +3618,7 @@ static int smb3_simple_fallocate_write_range(unsigned int xid,
{
struct cifs_io_parms io_parms = {0};
int nbytes;
+ int rc = 0;
struct kvec iov[2];
io_parms.netfid = cfile->fid.netfid;
@@ -3625,13 +3626,25 @@ static int smb3_simple_fallocate_write_range(unsigned int xid,
io_parms.tcon = tcon;
io_parms.persistent_fid = cfile->fid.persistent_fid;
io_parms.volatile_fid = cfile->fid.volatile_fid;
- io_parms.offset = off;
- io_parms.length = len;
- /* iov[0] is reserved for smb header */
- iov[1].iov_base = buf;
- iov[1].iov_len = io_parms.length;
- return SMB2_write(xid, &io_parms, &nbytes, iov, 1);
+ while (len) {
+ io_parms.offset = off;
+ io_parms.length = len;
+ if (io_parms.length > SMB2_MAX_BUFFER_SIZE)
+ io_parms.length = SMB2_MAX_BUFFER_SIZE;
+ /* iov[0] is reserved for smb header */
+ iov[1].iov_base = buf;
+ iov[1].iov_len = io_parms.length;
+ rc = SMB2_write(xid, &io_parms, &nbytes, iov, 1);
+ if (rc)
+ break;
+ if (nbytes > len)
+ return -EINVAL;
+ buf += nbytes;
+ off += nbytes;
+ len -= nbytes;
+ }
+ return rc;
}
static int smb3_simple_fallocate_range(unsigned int xid,
@@ -3655,11 +3668,6 @@ static int smb3_simple_fallocate_range(unsigned int xid,
(char **)&out_data, &out_data_len);
if (rc)
goto out;
- /*
- * It is already all allocated
- */
- if (out_data_len == 0)
- goto out;
buf = kzalloc(1024 * 1024, GFP_KERNEL);
if (buf == NULL) {
@@ -3782,6 +3790,24 @@ static long smb3_simple_falloc(struct file *file, struct cifs_tcon *tcon,
goto out;
}
+ if (keep_size == true) {
+ /*
+ * We can not preallocate pages beyond the end of the file
+ * in SMB2
+ */
+ if (off >= i_size_read(inode)) {
+ rc = 0;
+ goto out;
+ }
+ /*
+ * For fallocates that are partially beyond the end of file,
+ * clamp len so we only fallocate up to the end of file.
+ */
+ if (off + len > i_size_read(inode)) {
+ len = i_size_read(inode) - off;
+ }
+ }
+
if ((keep_size == true) || (i_size_read(inode) >= off + len)) {
/*
* At this point, we are trying to fallocate an internal
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 14292dba3a12..2c2f179b6977 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -106,12 +106,11 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
return err;
}
-static bool ext2_check_page(struct page *page, int quiet)
+static bool ext2_check_page(struct page *page, int quiet, char *kaddr)
{
struct inode *dir = page->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned chunk_size = ext2_chunk_size(dir);
- char *kaddr = page_address(page);
u32 max_inumber = le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count);
unsigned offs, rec_len;
unsigned limit = PAGE_SIZE;
@@ -205,7 +204,8 @@ static struct page * ext2_get_page(struct inode *dir, unsigned long n,
if (!IS_ERR(page)) {
*page_addr = kmap_local_page(page);
if (unlikely(!PageChecked(page))) {
- if (PageError(page) || !ext2_check_page(page, quiet))
+ if (PageError(page) || !ext2_check_page(page, quiet,
+ *page_addr))
goto fail;
}
}
@@ -584,10 +584,10 @@ out_unlock:
* ext2_delete_entry deletes a directory entry by merging it with the
* previous entry. Page is up-to-date.
*/
-int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
+int ext2_delete_entry (struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr)
{
struct inode *inode = page->mapping->host;
- char *kaddr = page_address(page);
unsigned from = ((char*)dir - kaddr) & ~(ext2_chunk_size(inode)-1);
unsigned to = ((char *)dir - kaddr) +
ext2_rec_len_from_disk(dir->rec_len);
@@ -607,7 +607,7 @@ int ext2_delete_entry (struct ext2_dir_entry_2 * dir, struct page * page )
de = ext2_next_entry(de);
}
if (pde)
- from = (char*)pde - (char*)page_address(page);
+ from = (char *)pde - kaddr;
pos = page_offset(page) + from;
lock_page(page);
err = ext2_prepare_chunk(page, pos, to - from);
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index b0a694820cb7..e512630cb63e 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -740,7 +740,8 @@ extern int ext2_inode_by_name(struct inode *dir,
extern int ext2_make_empty(struct inode *, struct inode *);
extern struct ext2_dir_entry_2 *ext2_find_entry(struct inode *, const struct qstr *,
struct page **, void **res_page_addr);
-extern int ext2_delete_entry (struct ext2_dir_entry_2 *, struct page *);
+extern int ext2_delete_entry(struct ext2_dir_entry_2 *dir, struct page *page,
+ char *kaddr);
extern int ext2_empty_dir (struct inode *);
extern struct ext2_dir_entry_2 *ext2_dotdot(struct inode *dir, struct page **p, void **pa);
extern void ext2_set_link(struct inode *, struct ext2_dir_entry_2 *, struct page *, void *,
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 1f69b81655b6..5f6b7560eb3f 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -293,7 +293,7 @@ static int ext2_unlink(struct inode * dir, struct dentry *dentry)
goto out;
}
- err = ext2_delete_entry (de, page);
+ err = ext2_delete_entry (de, page, page_addr);
ext2_put_page(page, page_addr);
if (err)
goto out;
@@ -397,7 +397,7 @@ static int ext2_rename (struct user_namespace * mnt_userns,
old_inode->i_ctime = current_time(old_inode);
mark_inode_dirty(old_inode);
- ext2_delete_entry(old_de, old_page);
+ ext2_delete_entry(old_de, old_page, old_page_addr);
if (dir_de) {
if (old_dir != new_dir)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 06d04a74ab6c..4c3370548982 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -521,6 +521,9 @@ static bool inode_prepare_wbs_switch(struct inode *inode,
*/
smp_mb();
+ if (IS_DAX(inode))
+ return false;
+
/* while holding I_WB_SWITCH, no one else can update the association */
spin_lock(&inode->i_lock);
if (!(inode->i_sb->s_flags & SB_ACTIVE) ||
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 926eeb9bf4eb..cdfb1ae78a3f 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -77,7 +77,7 @@ enum hugetlb_param {
static const struct fs_parameter_spec hugetlb_fs_parameters[] = {
fsparam_u32 ("gid", Opt_gid),
fsparam_string("min_size", Opt_min_size),
- fsparam_u32 ("mode", Opt_mode),
+ fsparam_u32oct("mode", Opt_mode),
fsparam_string("nr_inodes", Opt_nr_inodes),
fsparam_string("pagesize", Opt_pagesize),
fsparam_string("size", Opt_size),
diff --git a/fs/internal.h b/fs/internal.h
index 3ce8edbaa3ca..82e8eb32ff3d 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -61,7 +61,6 @@ extern void __init chrdev_init(void);
*/
extern const struct fs_context_operations legacy_fs_context_ops;
extern int parse_monolithic_mount_data(struct fs_context *, void *);
-extern void fc_drop_locked(struct fs_context *);
extern void vfs_clean_context(struct fs_context *fc);
extern int finish_clean_context(struct fs_context *fc);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 843d4a7bcd6e..cf086b01c6c6 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -731,7 +731,12 @@ static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
int work_flags;
unsigned long flags;
- if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state)) {
+ /*
+ * If io-wq is exiting for this task, or if the request has explicitly
+ * been marked as one that should not get executed, cancel it here.
+ */
+ if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
+ (work->flags & IO_WQ_WORK_CANCEL)) {
io_run_cancel(work, wqe);
return;
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 0cac361bf6b8..bf548af0426c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1279,8 +1279,17 @@ static void io_prep_async_link(struct io_kiocb *req)
{
struct io_kiocb *cur;
- io_for_each_link(cur, req)
- io_prep_async_work(cur);
+ if (req->flags & REQ_F_LINK_TIMEOUT) {
+ struct io_ring_ctx *ctx = req->ctx;
+
+ spin_lock_irq(&ctx->completion_lock);
+ io_for_each_link(cur, req)
+ io_prep_async_work(cur);
+ spin_unlock_irq(&ctx->completion_lock);
+ } else {
+ io_for_each_link(cur, req)
+ io_prep_async_work(cur);
+ }
}
static void io_queue_async_work(struct io_kiocb *req)
@@ -1294,6 +1303,17 @@ static void io_queue_async_work(struct io_kiocb *req)
/* init ->work of the whole link before punting */
io_prep_async_link(req);
+
+ /*
+ * Not expected to happen, but if we do have a bug where this _can_
+ * happen, catch it here and ensure the request is marked as
+ * canceled. That will make io-wq go through the usual work cancel
+ * procedure rather than attempt to run this request (or create a new
+ * worker for it).
+ */
+ if (WARN_ON_ONCE(!same_thread_group(req->task, current)))
+ req->work.flags |= IO_WQ_WORK_CANCEL;
+
trace_io_uring_queue_async_work(ctx, io_wq_is_hashed(&req->work), req,
&req->work, req->flags);
io_wq_enqueue(tctx->io_wq, &req->work);
@@ -1939,9 +1959,13 @@ static void tctx_task_work(struct callback_head *cb)
node = next;
}
if (wq_list_empty(&tctx->task_list)) {
+ spin_lock_irq(&tctx->task_lock);
clear_bit(0, &tctx->task_state);
- if (wq_list_empty(&tctx->task_list))
+ if (wq_list_empty(&tctx->task_list)) {
+ spin_unlock_irq(&tctx->task_lock);
break;
+ }
+ spin_unlock_irq(&tctx->task_lock);
/* another tctx_task_work() is enqueued, yield */
if (test_and_set_bit(0, &tctx->task_state))
break;
@@ -2036,6 +2060,12 @@ static void io_req_task_queue(struct io_kiocb *req)
io_req_task_work_add(req);
}
+static void io_req_task_queue_reissue(struct io_kiocb *req)
+{
+ req->io_task_work.func = io_queue_async_work;
+ io_req_task_work_add(req);
+}
+
static inline void io_queue_next(struct io_kiocb *req)
{
struct io_kiocb *nxt = io_req_find_next(req);
@@ -2205,7 +2235,7 @@ static inline bool io_run_task_work(void)
* Find and free completed poll iocbs
*/
static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
- struct list_head *done)
+ struct list_head *done, bool resubmit)
{
struct req_batch rb;
struct io_kiocb *req;
@@ -2220,11 +2250,11 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
req = list_first_entry(done, struct io_kiocb, inflight_entry);
list_del(&req->inflight_entry);
- if (READ_ONCE(req->result) == -EAGAIN &&
+ if (READ_ONCE(req->result) == -EAGAIN && resubmit &&
!(req->flags & REQ_F_DONT_REISSUE)) {
req->iopoll_completed = 0;
req_ref_get(req);
- io_queue_async_work(req);
+ io_req_task_queue_reissue(req);
continue;
}
@@ -2244,7 +2274,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
}
static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
- long min)
+ long min, bool resubmit)
{
struct io_kiocb *req, *tmp;
LIST_HEAD(done);
@@ -2287,7 +2317,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
}
if (!list_empty(&done))
- io_iopoll_complete(ctx, nr_events, &done);
+ io_iopoll_complete(ctx, nr_events, &done, resubmit);
return ret;
}
@@ -2305,7 +2335,7 @@ static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
while (!list_empty(&ctx->iopoll_list)) {
unsigned int nr_events = 0;
- io_do_iopoll(ctx, &nr_events, 0);
+ io_do_iopoll(ctx, &nr_events, 0, false);
/* let it sleep and repeat later if can't complete a request */
if (nr_events == 0)
@@ -2367,7 +2397,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
list_empty(&ctx->iopoll_list))
break;
}
- ret = io_do_iopoll(ctx, &nr_events, min);
+ ret = io_do_iopoll(ctx, &nr_events, min, true);
} while (!ret && nr_events < min && !need_resched());
out:
mutex_unlock(&ctx->uring_lock);
@@ -2417,6 +2447,12 @@ static bool io_rw_should_reissue(struct io_kiocb *req)
*/
if (percpu_ref_is_dying(&ctx->refs))
return false;
+ /*
+ * Play it safe and assume not safe to re-import and reissue if we're
+ * not in the original thread group (or in task context).
+ */
+ if (!same_thread_group(req->task, current) || !in_task())
+ return false;
return true;
}
#else
@@ -2747,7 +2783,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret,
req->flags &= ~REQ_F_REISSUE;
if (io_resubmit_prep(req)) {
req_ref_get(req);
- io_queue_async_work(req);
+ io_req_task_queue_reissue(req);
} else {
int cflags = 0;
@@ -4802,6 +4838,7 @@ IO_NETOP_FN(recv);
struct io_poll_table {
struct poll_table_struct pt;
struct io_kiocb *req;
+ int nr_entries;
int error;
};
@@ -4902,7 +4939,6 @@ static bool io_poll_complete(struct io_kiocb *req, __poll_t mask)
if (req->poll.events & EPOLLONESHOT)
flags = 0;
if (!io_cqring_fill_event(ctx, req->user_data, error, flags)) {
- io_poll_remove_waitqs(req);
req->poll.done = true;
flags = 0;
}
@@ -4925,6 +4961,7 @@ static void io_poll_task_func(struct io_kiocb *req)
done = io_poll_complete(req, req->result);
if (done) {
+ io_poll_remove_double(req);
hash_del(&req->hash_node);
} else {
req->result = 0;
@@ -4995,11 +5032,11 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
struct io_kiocb *req = pt->req;
/*
- * If poll->head is already set, it's because the file being polled
- * uses multiple waitqueues for poll handling (eg one for read, one
- * for write). Setup a separate io_poll_iocb if this happens.
+ * The file being polled uses multiple waitqueues for poll handling
+ * (e.g. one for read, one for write). Setup a separate io_poll_iocb
+ * if this happens.
*/
- if (unlikely(poll->head)) {
+ if (unlikely(pt->nr_entries)) {
struct io_poll_iocb *poll_one = poll;
/* already have a 2nd entry, fail a third attempt */
@@ -5027,7 +5064,7 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt,
*poll_ptr = poll;
}
- pt->error = 0;
+ pt->nr_entries++;
poll->head = head;
if (poll->events & EPOLLEXCLUSIVE)
@@ -5104,11 +5141,16 @@ static __poll_t __io_arm_poll_handler(struct io_kiocb *req,
ipt->pt._key = mask;
ipt->req = req;
- ipt->error = -EINVAL;
+ ipt->error = 0;
+ ipt->nr_entries = 0;
mask = vfs_poll(req->file, &ipt->pt) & poll->events;
+ if (unlikely(!ipt->nr_entries) && !ipt->error)
+ ipt->error = -EINVAL;
spin_lock_irq(&ctx->completion_lock);
+ if (ipt->error || (mask && (poll->events & EPOLLONESHOT)))
+ io_poll_remove_double(req);
if (likely(poll->head)) {
spin_lock(&poll->head->lock);
if (unlikely(list_empty(&poll->wait.entry))) {
@@ -5179,7 +5221,6 @@ static int io_arm_poll_handler(struct io_kiocb *req)
ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask,
io_async_wake);
if (ret || ipt.error) {
- io_poll_remove_double(req);
spin_unlock_irq(&ctx->completion_lock);
if (ret)
return IO_APOLL_READY;
@@ -6792,7 +6833,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries)
mutex_lock(&ctx->uring_lock);
if (!list_empty(&ctx->iopoll_list))
- io_do_iopoll(ctx, &nr_events, 0);
+ io_do_iopoll(ctx, &nr_events, 0, true);
/*
* Don't submit if refs are dying, good for io_uring_register(),
@@ -7899,15 +7940,19 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx,
struct io_wq_data data;
unsigned int concurrency;
+ mutex_lock(&ctx->uring_lock);
hash = ctx->hash_map;
if (!hash) {
hash = kzalloc(sizeof(*hash), GFP_KERNEL);
- if (!hash)
+ if (!hash) {
+ mutex_unlock(&ctx->uring_lock);
return ERR_PTR(-ENOMEM);
+ }
refcount_set(&hash->refs, 1);
init_waitqueue_head(&hash->wait);
ctx->hash_map = hash;
}
+ mutex_unlock(&ctx->uring_lock);
data.hash = hash;
data.task = task;
@@ -7981,9 +8026,11 @@ static int io_sq_offload_create(struct io_ring_ctx *ctx,
f = fdget(p->wq_fd);
if (!f.file)
return -ENXIO;
- fdput(f);
- if (f.file->f_op != &io_uring_fops)
+ if (f.file->f_op != &io_uring_fops) {
+ fdput(f);
return -EINVAL;
+ }
+ fdput(f);
}
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct task_struct *tsk;
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 775657943057..54d7843c0211 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1529,6 +1529,45 @@ static void ocfs2_truncate_cluster_pages(struct inode *inode, u64 byte_start,
}
}
+/*
+ * zero out partial blocks of one cluster.
+ *
+ * start: file offset where zero starts, will be made upper block aligned.
+ * len: it will be trimmed to the end of current cluster if "start + len"
+ * is bigger than it.
+ */
+static int ocfs2_zeroout_partial_cluster(struct inode *inode,
+ u64 start, u64 len)
+{
+ int ret;
+ u64 start_block, end_block, nr_blocks;
+ u64 p_block, offset;
+ u32 cluster, p_cluster, nr_clusters;
+ struct super_block *sb = inode->i_sb;
+ u64 end = ocfs2_align_bytes_to_clusters(sb, start);
+
+ if (start + len < end)
+ end = start + len;
+
+ start_block = ocfs2_blocks_for_bytes(sb, start);
+ end_block = ocfs2_blocks_for_bytes(sb, end);
+ nr_blocks = end_block - start_block;
+ if (!nr_blocks)
+ return 0;
+
+ cluster = ocfs2_bytes_to_clusters(sb, start);
+ ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
+ &nr_clusters, NULL);
+ if (ret)
+ return ret;
+ if (!p_cluster)
+ return 0;
+
+ offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
+ p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
+ return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
+}
+
static int ocfs2_zero_partial_clusters(struct inode *inode,
u64 start, u64 len)
{
@@ -1538,6 +1577,7 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
unsigned int csize = osb->s_clustersize;
handle_t *handle;
+ loff_t isize = i_size_read(inode);
/*
* The "start" and "end" values are NOT necessarily part of
@@ -1558,6 +1598,26 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
if ((start & (csize - 1)) == 0 && (end & (csize - 1)) == 0)
goto out;
+ /* No page cache for EOF blocks, issue zero out to disk. */
+ if (end > isize) {
+ /*
+ * zeroout eof blocks in last cluster starting from
+ * "isize" even "start" > "isize" because it is
+ * complicated to zeroout just at "start" as "start"
+ * may be not aligned with block size, buffer write
+ * would be required to do that, but out of eof buffer
+ * write is not supported.
+ */
+ ret = ocfs2_zeroout_partial_cluster(inode, isize,
+ end - isize);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ if (start >= isize)
+ goto out;
+ end = isize;
+ }
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
@@ -1856,45 +1916,6 @@ out:
}
/*
- * zero out partial blocks of one cluster.
- *
- * start: file offset where zero starts, will be made upper block aligned.
- * len: it will be trimmed to the end of current cluster if "start + len"
- * is bigger than it.
- */
-static int ocfs2_zeroout_partial_cluster(struct inode *inode,
- u64 start, u64 len)
-{
- int ret;
- u64 start_block, end_block, nr_blocks;
- u64 p_block, offset;
- u32 cluster, p_cluster, nr_clusters;
- struct super_block *sb = inode->i_sb;
- u64 end = ocfs2_align_bytes_to_clusters(sb, start);
-
- if (start + len < end)
- end = start + len;
-
- start_block = ocfs2_blocks_for_bytes(sb, start);
- end_block = ocfs2_blocks_for_bytes(sb, end);
- nr_blocks = end_block - start_block;
- if (!nr_blocks)
- return 0;
-
- cluster = ocfs2_bytes_to_clusters(sb, start);
- ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
- &nr_clusters, NULL);
- if (ret)
- return ret;
- if (!p_cluster)
- return 0;
-
- offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
- p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
- return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
-}
-
-/*
* Parts of this function taken from xfs_change_file_space()
*/
static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
@@ -1935,7 +1956,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
goto out_inode_unlock;
}
- orig_isize = i_size_read(inode);
switch (sr->l_whence) {
case 0: /*SEEK_SET*/
break;
@@ -1943,7 +1963,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
sr->l_start += f_pos;
break;
case 2: /*SEEK_END*/
- sr->l_start += orig_isize;
+ sr->l_start += i_size_read(inode);
break;
default:
ret = -EINVAL;
@@ -1998,6 +2018,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
ret = -EINVAL;
}
+ orig_isize = i_size_read(inode);
/* zeroout eof blocks in the cluster. */
if (!ret && change_size && orig_isize < size) {
ret = ocfs2_zeroout_partial_cluster(inode, orig_isize,
diff --git a/fs/pipe.c b/fs/pipe.c
index bfd946a9ad01..9ef4231cce61 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -429,20 +429,20 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
#endif
/*
- * Only wake up if the pipe started out empty, since
- * otherwise there should be no readers waiting.
+ * Epoll nonsensically wants a wakeup whether the pipe
+ * was already empty or not.
*
* If it wasn't empty we try to merge new data into
* the last buffer.
*
* That naturally merges small writes, but it also
- * page-aligs the rest of the writes for large writes
+ * page-aligns the rest of the writes for large writes
* spanning multiple pages.
*/
head = pipe->head;
- was_empty = pipe_empty(head, pipe->tail);
+ was_empty = true;
chars = total_len & (PAGE_SIZE-1);
- if (chars && !was_empty) {
+ if (chars && !pipe_empty(head, pipe->tail)) {
unsigned int mask = pipe->ring_size - 1;
struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask];
int offset = buf->offset + buf->len;
diff --git a/fs/reiserfs/stree.c b/fs/reiserfs/stree.c
index 476a7ff49482..ef42729216d1 100644
--- a/fs/reiserfs/stree.c
+++ b/fs/reiserfs/stree.c
@@ -387,6 +387,24 @@ void pathrelse(struct treepath *search_path)
search_path->path_length = ILLEGAL_PATH_ELEMENT_OFFSET;
}
+static int has_valid_deh_location(struct buffer_head *bh, struct item_head *ih)
+{
+ struct reiserfs_de_head *deh;
+ int i;
+
+ deh = B_I_DEH(bh, ih);
+ for (i = 0; i < ih_entry_count(ih); i++) {
+ if (deh_location(&deh[i]) > ih_item_len(ih)) {
+ reiserfs_warning(NULL, "reiserfs-5094",
+ "directory entry location seems wrong %h",
+ &deh[i]);
+ return 0;
+ }
+ }
+
+ return 1;
+}
+
static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
{
struct block_head *blkh;
@@ -454,11 +472,14 @@ static int is_leaf(char *buf, int blocksize, struct buffer_head *bh)
"(second one): %h", ih);
return 0;
}
- if (is_direntry_le_ih(ih) && (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE))) {
- reiserfs_warning(NULL, "reiserfs-5093",
- "item entry count seems wrong %h",
- ih);
- return 0;
+ if (is_direntry_le_ih(ih)) {
+ if (ih_item_len(ih) < (ih_entry_count(ih) * IH_SIZE)) {
+ reiserfs_warning(NULL, "reiserfs-5093",
+ "item entry count seems wrong %h",
+ ih);
+ return 0;
+ }
+ return has_valid_deh_location(bh, ih);
}
prev_location = ih_location(ih);
}
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 3ffafc73acf0..58481f8d63d5 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -2082,6 +2082,14 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
unlock_new_inode(root_inode);
}
+ if (!S_ISDIR(root_inode->i_mode) || !inode_get_bytes(root_inode) ||
+ !root_inode->i_size) {
+ SWARN(silent, s, "", "corrupt root inode, run fsck");
+ iput(root_inode);
+ errval = -EUCLEAN;
+ goto error;
+ }
+
s->s_root = d_make_root(root_inode);
if (!s->s_root)
goto error;
diff --git a/fs/seq_file.c b/fs/seq_file.c
index b117b212ef28..4a2cda04d3e2 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -32,6 +32,9 @@ static void seq_set_overflow(struct seq_file *m)
static void *seq_buf_alloc(unsigned long size)
{
+ if (unlikely(size > MAX_RW_COUNT))
+ return NULL;
+
return kvmalloc(size, GFP_KERNEL_ACCOUNT);
}
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f6e0f0c0d0e5..5c2d806e6ae5 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1236,23 +1236,21 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
}
static __always_inline int validate_range(struct mm_struct *mm,
- __u64 *start, __u64 len)
+ __u64 start, __u64 len)
{
__u64 task_size = mm->task_size;
- *start = untagged_addr(*start);
-
- if (*start & ~PAGE_MASK)
+ if (start & ~PAGE_MASK)
return -EINVAL;
if (len & ~PAGE_MASK)
return -EINVAL;
if (!len)
return -EINVAL;
- if (*start < mmap_min_addr)
+ if (start < mmap_min_addr)
return -EINVAL;
- if (*start >= task_size)
+ if (start >= task_size)
return -EINVAL;
- if (len > task_size - *start)
+ if (len > task_size - start)
return -EINVAL;
return 0;
}
@@ -1316,7 +1314,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
vm_flags |= VM_UFFD_MINOR;
}
- ret = validate_range(mm, &uffdio_register.range.start,
+ ret = validate_range(mm, uffdio_register.range.start,
uffdio_register.range.len);
if (ret)
goto out;
@@ -1522,7 +1520,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
goto out;
- ret = validate_range(mm, &uffdio_unregister.start,
+ ret = validate_range(mm, uffdio_unregister.start,
uffdio_unregister.len);
if (ret)
goto out;
@@ -1671,7 +1669,7 @@ static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_wake.start, uffdio_wake.len);
+ ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
if (ret)
goto out;
@@ -1711,7 +1709,7 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
sizeof(uffdio_copy)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_copy.dst, uffdio_copy.len);
+ ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
if (ret)
goto out;
/*
@@ -1768,7 +1766,7 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
sizeof(uffdio_zeropage)-sizeof(__s64)))
goto out;
- ret = validate_range(ctx->mm, &uffdio_zeropage.range.start,
+ ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
uffdio_zeropage.range.len);
if (ret)
goto out;
@@ -1818,7 +1816,7 @@ static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
sizeof(struct uffdio_writeprotect)))
return -EFAULT;
- ret = validate_range(ctx->mm, &uffdio_wp.range.start,
+ ret = validate_range(ctx->mm, uffdio_wp.range.start,
uffdio_wp.range.len);
if (ret)
return ret;
@@ -1866,7 +1864,7 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
sizeof(uffdio_continue) - (sizeof(__s64))))
goto out;
- ret = validate_range(ctx->mm, &uffdio_continue.range.start,
+ ret = validate_range(ctx->mm, uffdio_continue.range.start,
uffdio_continue.range.len);
if (ret)
goto out;
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index d548ea4b6aab..2c5bcbc19264 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -411,7 +411,16 @@ struct xfs_log_dinode {
/* start of the extended dinode, writable fields */
uint32_t di_crc; /* CRC of the inode */
uint64_t di_changecount; /* number of attribute changes */
- xfs_lsn_t di_lsn; /* flush sequence */
+
+ /*
+ * The LSN we write to this field during formatting is not a reflection
+ * of the current on-disk LSN. It should never be used for recovery
+ * sequencing, nor should it be recovered into the on-disk inode at all.
+ * See xlog_recover_inode_commit_pass2() and xfs_log_dinode_to_disk()
+ * for details.
+ */
+ xfs_lsn_t di_lsn;
+
uint64_t di_flags2; /* more random flags */
uint32_t di_cowextsize; /* basic cow extent size for file */
uint8_t di_pad2[12]; /* more padding for future expansion */
diff --git a/fs/xfs/xfs_buf_item_recover.c b/fs/xfs/xfs_buf_item_recover.c
index d44e8b4a3391..4775485b4062 100644
--- a/fs/xfs/xfs_buf_item_recover.c
+++ b/fs/xfs/xfs_buf_item_recover.c
@@ -698,7 +698,8 @@ xlog_recover_do_inode_buffer(
static xfs_lsn_t
xlog_recover_get_buf_lsn(
struct xfs_mount *mp,
- struct xfs_buf *bp)
+ struct xfs_buf *bp,
+ struct xfs_buf_log_format *buf_f)
{
uint32_t magic32;
uint16_t magic16;
@@ -706,11 +707,20 @@ xlog_recover_get_buf_lsn(
void *blk = bp->b_addr;
uuid_t *uuid;
xfs_lsn_t lsn = -1;
+ uint16_t blft;
/* v4 filesystems always recover immediately */
if (!xfs_sb_version_hascrc(&mp->m_sb))
goto recover_immediately;
+ /*
+ * realtime bitmap and summary file blocks do not have magic numbers or
+ * UUIDs, so we must recover them immediately.
+ */
+ blft = xfs_blft_from_flags(buf_f);
+ if (blft == XFS_BLFT_RTBITMAP_BUF || blft == XFS_BLFT_RTSUMMARY_BUF)
+ goto recover_immediately;
+
magic32 = be32_to_cpu(*(__be32 *)blk);
switch (magic32) {
case XFS_ABTB_CRC_MAGIC:
@@ -796,6 +806,7 @@ xlog_recover_get_buf_lsn(
switch (magicda) {
case XFS_DIR3_LEAF1_MAGIC:
case XFS_DIR3_LEAFN_MAGIC:
+ case XFS_ATTR3_LEAF_MAGIC:
case XFS_DA3_NODE_MAGIC:
lsn = be64_to_cpu(((struct xfs_da3_blkinfo *)blk)->lsn);
uuid = &((struct xfs_da3_blkinfo *)blk)->uuid;
@@ -919,7 +930,7 @@ xlog_recover_buf_commit_pass2(
* the verifier will be reset to match whatever recover turns that
* buffer into.
*/
- lsn = xlog_recover_get_buf_lsn(mp, bp);
+ lsn = xlog_recover_get_buf_lsn(mp, bp, buf_f);
if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
trace_xfs_log_recover_buf_skip(log, buf_f);
xlog_recover_validate_buf_type(mp, bp, buf_f, NULLCOMMITLSN);
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index 7b79518b6c20..e0072a6cd2d3 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -145,7 +145,8 @@ xfs_log_dinode_to_disk_ts(
STATIC void
xfs_log_dinode_to_disk(
struct xfs_log_dinode *from,
- struct xfs_dinode *to)
+ struct xfs_dinode *to,
+ xfs_lsn_t lsn)
{
to->di_magic = cpu_to_be16(from->di_magic);
to->di_mode = cpu_to_be16(from->di_mode);
@@ -182,7 +183,7 @@ xfs_log_dinode_to_disk(
to->di_flags2 = cpu_to_be64(from->di_flags2);
to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
to->di_ino = cpu_to_be64(from->di_ino);
- to->di_lsn = cpu_to_be64(from->di_lsn);
+ to->di_lsn = cpu_to_be64(lsn);
memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
uuid_copy(&to->di_uuid, &from->di_uuid);
to->di_flushiter = 0;
@@ -261,16 +262,25 @@ xlog_recover_inode_commit_pass2(
}
/*
- * If the inode has an LSN in it, recover the inode only if it's less
- * than the lsn of the transaction we are replaying. Note: we still
- * need to replay an owner change even though the inode is more recent
- * than the transaction as there is no guarantee that all the btree
- * blocks are more recent than this transaction, too.
+ * If the inode has an LSN in it, recover the inode only if the on-disk
+ * inode's LSN is older than the lsn of the transaction we are
+ * replaying. We can have multiple checkpoints with the same start LSN,
+ * so the current LSN being equal to the on-disk LSN doesn't necessarily
+ * mean that the on-disk inode is more recent than the change being
+ * replayed.
+ *
+ * We must check the current_lsn against the on-disk inode
+ * here because the we can't trust the log dinode to contain a valid LSN
+ * (see comment below before replaying the log dinode for details).
+ *
+ * Note: we still need to replay an owner change even though the inode
+ * is more recent than the transaction as there is no guarantee that all
+ * the btree blocks are more recent than this transaction, too.
*/
if (dip->di_version >= 3) {
xfs_lsn_t lsn = be64_to_cpu(dip->di_lsn);
- if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) >= 0) {
+ if (lsn && lsn != -1 && XFS_LSN_CMP(lsn, current_lsn) > 0) {
trace_xfs_log_recover_inode_skip(log, in_f);
error = 0;
goto out_owner_change;
@@ -368,8 +378,17 @@ xlog_recover_inode_commit_pass2(
goto out_release;
}
- /* recover the log dinode inode into the on disk inode */
- xfs_log_dinode_to_disk(ldip, dip);
+ /*
+ * Recover the log dinode inode into the on disk inode.
+ *
+ * The LSN in the log dinode is garbage - it can be zero or reflect
+ * stale in-memory runtime state that isn't coherent with the changes
+ * logged in this transaction or the changes written to the on-disk
+ * inode. Hence we write the current lSN into the inode because that
+ * matches what xfs_iflush() would write inode the inode when flushing
+ * the changes in this transaction.
+ */
+ xfs_log_dinode_to_disk(ldip, dip, current_lsn);
fields = in_f->ilf_fields;
if (fields & XFS_ILOG_DEV)
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 36fa2650b081..60ac5fd63f1e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -78,13 +78,12 @@ xlog_verify_iclog(
STATIC void
xlog_verify_tail_lsn(
struct xlog *log,
- struct xlog_in_core *iclog,
- xfs_lsn_t tail_lsn);
+ struct xlog_in_core *iclog);
#else
#define xlog_verify_dest_ptr(a,b)
#define xlog_verify_grant_tail(a)
#define xlog_verify_iclog(a,b,c)
-#define xlog_verify_tail_lsn(a,b,c)
+#define xlog_verify_tail_lsn(a,b)
#endif
STATIC int
@@ -487,51 +486,80 @@ out_error:
return error;
}
-static bool
-__xlog_state_release_iclog(
- struct xlog *log,
- struct xlog_in_core *iclog)
-{
- lockdep_assert_held(&log->l_icloglock);
-
- if (iclog->ic_state == XLOG_STATE_WANT_SYNC) {
- /* update tail before writing to iclog */
- xfs_lsn_t tail_lsn = xlog_assign_tail_lsn(log->l_mp);
-
- iclog->ic_state = XLOG_STATE_SYNCING;
- iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
- xlog_verify_tail_lsn(log, iclog, tail_lsn);
- /* cycle incremented when incrementing curr_block */
- trace_xlog_iclog_syncing(iclog, _RET_IP_);
- return true;
- }
-
- ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
- return false;
-}
-
/*
* Flush iclog to disk if this is the last reference to the given iclog and the
* it is in the WANT_SYNC state.
+ *
+ * If the caller passes in a non-zero @old_tail_lsn and the current log tail
+ * does not match, there may be metadata on disk that must be persisted before
+ * this iclog is written. To satisfy that requirement, set the
+ * XLOG_ICL_NEED_FLUSH flag as a condition for writing this iclog with the new
+ * log tail value.
+ *
+ * If XLOG_ICL_NEED_FUA is already set on the iclog, we need to ensure that the
+ * log tail is updated correctly. NEED_FUA indicates that the iclog will be
+ * written to stable storage, and implies that a commit record is contained
+ * within the iclog. We need to ensure that the log tail does not move beyond
+ * the tail that the first commit record in the iclog ordered against, otherwise
+ * correct recovery of that checkpoint becomes dependent on future operations
+ * performed on this iclog.
+ *
+ * Hence if NEED_FUA is set and the current iclog tail lsn is empty, write the
+ * current tail into iclog. Once the iclog tail is set, future operations must
+ * not modify it, otherwise they potentially violate ordering constraints for
+ * the checkpoint commit that wrote the initial tail lsn value. The tail lsn in
+ * the iclog will get zeroed on activation of the iclog after sync, so we
+ * always capture the tail lsn on the iclog on the first NEED_FUA release
+ * regardless of the number of active reference counts on this iclog.
*/
+
int
xlog_state_release_iclog(
struct xlog *log,
- struct xlog_in_core *iclog)
+ struct xlog_in_core *iclog,
+ xfs_lsn_t old_tail_lsn)
{
+ xfs_lsn_t tail_lsn;
lockdep_assert_held(&log->l_icloglock);
trace_xlog_iclog_release(iclog, _RET_IP_);
if (iclog->ic_state == XLOG_STATE_IOERROR)
return -EIO;
- if (atomic_dec_and_test(&iclog->ic_refcnt) &&
- __xlog_state_release_iclog(log, iclog)) {
- spin_unlock(&log->l_icloglock);
- xlog_sync(log, iclog);
- spin_lock(&log->l_icloglock);
+ /*
+ * Grabbing the current log tail needs to be atomic w.r.t. the writing
+ * of the tail LSN into the iclog so we guarantee that the log tail does
+ * not move between deciding if a cache flush is required and writing
+ * the LSN into the iclog below.
+ */
+ if (old_tail_lsn || iclog->ic_state == XLOG_STATE_WANT_SYNC) {
+ tail_lsn = xlog_assign_tail_lsn(log->l_mp);
+
+ if (old_tail_lsn && tail_lsn != old_tail_lsn)
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH;
+
+ if ((iclog->ic_flags & XLOG_ICL_NEED_FUA) &&
+ !iclog->ic_header.h_tail_lsn)
+ iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
}
+ if (!atomic_dec_and_test(&iclog->ic_refcnt))
+ return 0;
+
+ if (iclog->ic_state != XLOG_STATE_WANT_SYNC) {
+ ASSERT(iclog->ic_state == XLOG_STATE_ACTIVE);
+ return 0;
+ }
+
+ iclog->ic_state = XLOG_STATE_SYNCING;
+ if (!iclog->ic_header.h_tail_lsn)
+ iclog->ic_header.h_tail_lsn = cpu_to_be64(tail_lsn);
+ xlog_verify_tail_lsn(log, iclog);
+ trace_xlog_iclog_syncing(iclog, _RET_IP_);
+
+ spin_unlock(&log->l_icloglock);
+ xlog_sync(log, iclog);
+ spin_lock(&log->l_icloglock);
return 0;
}
@@ -774,6 +802,21 @@ xfs_log_mount_cancel(
}
/*
+ * Flush out the iclog to disk ensuring that device caches are flushed and
+ * the iclog hits stable storage before any completion waiters are woken.
+ */
+static inline int
+xlog_force_iclog(
+ struct xlog_in_core *iclog)
+{
+ atomic_inc(&iclog->ic_refcnt);
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+ if (iclog->ic_state == XLOG_STATE_ACTIVE)
+ xlog_state_switch_iclogs(iclog->ic_log, iclog, 0);
+ return xlog_state_release_iclog(iclog->ic_log, iclog, 0);
+}
+
+/*
* Wait for the iclog and all prior iclogs to be written disk as required by the
* log force state machine. Waiting on ic_force_wait ensures iclog completions
* have been ordered and callbacks run before we are woken here, hence
@@ -827,13 +870,6 @@ xlog_write_unmount_record(
/* account for space used by record data */
ticket->t_curr_res -= sizeof(ulf);
- /*
- * For external log devices, we need to flush the data device cache
- * first to ensure all metadata writeback is on stable storage before we
- * stamp the tail LSN into the unmount record.
- */
- if (log->l_targ != log->l_mp->m_ddev_targp)
- blkdev_issue_flush(log->l_targ->bt_bdev);
return xlog_write(log, &vec, ticket, NULL, NULL, XLOG_UNMOUNT_TRANS);
}
@@ -865,18 +901,7 @@ out_err:
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
- atomic_inc(&iclog->ic_refcnt);
- if (iclog->ic_state == XLOG_STATE_ACTIVE)
- xlog_state_switch_iclogs(log, iclog, 0);
- else
- ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC ||
- iclog->ic_state == XLOG_STATE_IOERROR);
- /*
- * Ensure the journal is fully flushed and on stable storage once the
- * iclog containing the unmount record is written.
- */
- iclog->ic_flags |= (XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_force_iclog(iclog);
xlog_wait_on_iclog(iclog);
if (tic) {
@@ -1796,10 +1821,20 @@ xlog_write_iclog(
* metadata writeback and causing priority inversions.
*/
iclog->ic_bio.bi_opf = REQ_OP_WRITE | REQ_META | REQ_SYNC | REQ_IDLE;
- if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH)
+ if (iclog->ic_flags & XLOG_ICL_NEED_FLUSH) {
iclog->ic_bio.bi_opf |= REQ_PREFLUSH;
+ /*
+ * For external log devices, we also need to flush the data
+ * device cache first to ensure all metadata writeback covered
+ * by the LSN in this iclog is on stable storage. This is slow,
+ * but it *must* complete before we issue the external log IO.
+ */
+ if (log->l_targ != log->l_mp->m_ddev_targp)
+ blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev);
+ }
if (iclog->ic_flags & XLOG_ICL_NEED_FUA)
iclog->ic_bio.bi_opf |= REQ_FUA;
+
iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA);
if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) {
@@ -2310,7 +2345,7 @@ xlog_write_copy_finish(
return 0;
release_iclog:
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
spin_unlock(&log->l_icloglock);
return error;
}
@@ -2529,7 +2564,7 @@ next_lv:
ASSERT(optype & XLOG_COMMIT_TRANS);
*commit_iclog = iclog;
} else {
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
}
spin_unlock(&log->l_icloglock);
@@ -2567,6 +2602,7 @@ xlog_state_activate_iclog(
memset(iclog->ic_header.h_cycle_data, 0,
sizeof(iclog->ic_header.h_cycle_data));
iclog->ic_header.h_lsn = 0;
+ iclog->ic_header.h_tail_lsn = 0;
}
/*
@@ -2967,7 +3003,7 @@ restart:
* reference to the iclog.
*/
if (!atomic_add_unless(&iclog->ic_refcnt, -1, 1))
- error = xlog_state_release_iclog(log, iclog);
+ error = xlog_state_release_iclog(log, iclog, 0);
spin_unlock(&log->l_icloglock);
if (error)
return error;
@@ -3132,6 +3168,35 @@ xlog_state_switch_iclogs(
}
/*
+ * Force the iclog to disk and check if the iclog has been completed before
+ * xlog_force_iclog() returns. This can happen on synchronous (e.g.
+ * pmem) or fast async storage because we drop the icloglock to issue the IO.
+ * If completion has already occurred, tell the caller so that it can avoid an
+ * unnecessary wait on the iclog.
+ */
+static int
+xlog_force_and_check_iclog(
+ struct xlog_in_core *iclog,
+ bool *completed)
+{
+ xfs_lsn_t lsn = be64_to_cpu(iclog->ic_header.h_lsn);
+ int error;
+
+ *completed = false;
+ error = xlog_force_iclog(iclog);
+ if (error)
+ return error;
+
+ /*
+ * If the iclog has already been completed and reused the header LSN
+ * will have been rewritten by completion
+ */
+ if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+ *completed = true;
+ return 0;
+}
+
+/*
* Write out all data in the in-core log as of this exact moment in time.
*
* Data may be written to the in-core log during this call. However,
@@ -3165,7 +3230,6 @@ xfs_log_force(
{
struct xlog *log = mp->m_log;
struct xlog_in_core *iclog;
- xfs_lsn_t lsn;
XFS_STATS_INC(mp, xs_log_force);
trace_xfs_log_force(mp, 0, _RET_IP_);
@@ -3193,39 +3257,33 @@ xfs_log_force(
iclog = iclog->ic_prev;
} else if (iclog->ic_state == XLOG_STATE_ACTIVE) {
if (atomic_read(&iclog->ic_refcnt) == 0) {
- /*
- * We are the only one with access to this iclog.
- *
- * Flush it out now. There should be a roundoff of zero
- * to show that someone has already taken care of the
- * roundoff from the previous sync.
- */
- atomic_inc(&iclog->ic_refcnt);
- lsn = be64_to_cpu(iclog->ic_header.h_lsn);
- xlog_state_switch_iclogs(log, iclog, 0);
- if (xlog_state_release_iclog(log, iclog))
+ /* We have exclusive access to this iclog. */
+ bool completed;
+
+ if (xlog_force_and_check_iclog(iclog, &completed))
goto out_error;
- if (be64_to_cpu(iclog->ic_header.h_lsn) != lsn)
+ if (completed)
goto out_unlock;
} else {
/*
- * Someone else is writing to this iclog.
- *
- * Use its call to flush out the data. However, the
- * other thread may not force out this LR, so we mark
- * it WANT_SYNC.
+ * Someone else is still writing to this iclog, so we
+ * need to ensure that when they release the iclog it
+ * gets synced immediately as we may be waiting on it.
*/
xlog_state_switch_iclogs(log, iclog, 0);
}
- } else {
- /*
- * If the head iclog is not active nor dirty, we just attach
- * ourselves to the head and go to sleep if necessary.
- */
- ;
}
+ /*
+ * The iclog we are about to wait on may contain the checkpoint pushed
+ * by the above xlog_cil_force() call, but it may not have been pushed
+ * to disk yet. Like the ACTIVE case above, we need to make sure caches
+ * are flushed when this iclog is written.
+ */
+ if (iclog->ic_state == XLOG_STATE_WANT_SYNC)
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+
if (flags & XFS_LOG_SYNC)
return xlog_wait_on_iclog(iclog);
out_unlock:
@@ -3245,6 +3303,7 @@ xlog_force_lsn(
bool already_slept)
{
struct xlog_in_core *iclog;
+ bool completed;
spin_lock(&log->l_icloglock);
iclog = log->l_iclog;
@@ -3258,7 +3317,8 @@ xlog_force_lsn(
goto out_unlock;
}
- if (iclog->ic_state == XLOG_STATE_ACTIVE) {
+ switch (iclog->ic_state) {
+ case XLOG_STATE_ACTIVE:
/*
* We sleep here if we haven't already slept (e.g. this is the
* first time we've looked at the correct iclog buf) and the
@@ -3281,12 +3341,31 @@ xlog_force_lsn(
&log->l_icloglock);
return -EAGAIN;
}
- atomic_inc(&iclog->ic_refcnt);
- xlog_state_switch_iclogs(log, iclog, 0);
- if (xlog_state_release_iclog(log, iclog))
+ if (xlog_force_and_check_iclog(iclog, &completed))
goto out_error;
if (log_flushed)
*log_flushed = 1;
+ if (completed)
+ goto out_unlock;
+ break;
+ case XLOG_STATE_WANT_SYNC:
+ /*
+ * This iclog may contain the checkpoint pushed by the
+ * xlog_cil_force_seq() call, but there are other writers still
+ * accessing it so it hasn't been pushed to disk yet. Like the
+ * ACTIVE case above, we need to make sure caches are flushed
+ * when this iclog is written.
+ */
+ iclog->ic_flags |= XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA;
+ break;
+ default:
+ /*
+ * The entire checkpoint was written by the CIL force and is on
+ * its way to disk already. It will be stable when it
+ * completes, so we don't need to manipulate caches here at all.
+ * We just need to wait for completion if necessary.
+ */
+ break;
}
if (flags & XFS_LOG_SYNC)
@@ -3559,10 +3638,10 @@ xlog_verify_grant_tail(
STATIC void
xlog_verify_tail_lsn(
struct xlog *log,
- struct xlog_in_core *iclog,
- xfs_lsn_t tail_lsn)
+ struct xlog_in_core *iclog)
{
- int blocks;
+ xfs_lsn_t tail_lsn = be64_to_cpu(iclog->ic_header.h_tail_lsn);
+ int blocks;
if (CYCLE_LSN(tail_lsn) == log->l_prev_cycle) {
blocks =
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index b128aaa9b870..4c44bc3786c0 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -654,8 +654,9 @@ xlog_cil_push_work(
struct xfs_trans_header thdr;
struct xfs_log_iovec lhdr;
struct xfs_log_vec lvhdr = { NULL };
+ xfs_lsn_t preflush_tail_lsn;
xfs_lsn_t commit_lsn;
- xfs_lsn_t push_seq;
+ xfs_csn_t push_seq;
struct bio bio;
DECLARE_COMPLETION_ONSTACK(bdev_flush);
@@ -730,7 +731,15 @@ xlog_cil_push_work(
* because we hold the flush lock exclusively. Hence we can now issue
* a cache flush to ensure all the completed metadata in the journal we
* are about to overwrite is on stable storage.
+ *
+ * Because we are issuing this cache flush before we've written the
+ * tail lsn to the iclog, we can have metadata IO completions move the
+ * tail forwards between the completion of this flush and the iclog
+ * being written. In this case, we need to re-issue the cache flush
+ * before the iclog write. To detect whether the log tail moves, sample
+ * the tail LSN *before* we issue the flush.
*/
+ preflush_tail_lsn = atomic64_read(&log->l_tail_lsn);
xfs_flush_bdev_async(&bio, log->l_mp->m_ddev_targp->bt_bdev,
&bdev_flush);
@@ -941,7 +950,7 @@ restart:
* storage.
*/
commit_iclog->ic_flags |= XLOG_ICL_NEED_FUA;
- xlog_state_release_iclog(log, commit_iclog);
+ xlog_state_release_iclog(log, commit_iclog, preflush_tail_lsn);
spin_unlock(&log->l_icloglock);
return;
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 4c41bbfa33b0..f3e79a45d60a 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -59,6 +59,16 @@ enum xlog_iclog_state {
{ XLOG_STATE_DIRTY, "XLOG_STATE_DIRTY" }, \
{ XLOG_STATE_IOERROR, "XLOG_STATE_IOERROR" }
+/*
+ * In core log flags
+ */
+#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */
+#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */
+
+#define XLOG_ICL_STRINGS \
+ { XLOG_ICL_NEED_FLUSH, "XLOG_ICL_NEED_FLUSH" }, \
+ { XLOG_ICL_NEED_FUA, "XLOG_ICL_NEED_FUA" }
+
/*
* Log ticket flags
@@ -143,9 +153,6 @@ enum xlog_iclog_state {
#define XLOG_COVER_OPS 5
-#define XLOG_ICL_NEED_FLUSH (1 << 0) /* iclog needs REQ_PREFLUSH */
-#define XLOG_ICL_NEED_FUA (1 << 1) /* iclog needs REQ_FUA */
-
/* Ticket reservation region accounting */
#define XLOG_TIC_LEN_MAX 15
@@ -497,7 +504,8 @@ int xlog_commit_record(struct xlog *log, struct xlog_ticket *ticket,
void xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket);
void xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
-int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog);
+int xlog_state_release_iclog(struct xlog *log, struct xlog_in_core *iclog,
+ xfs_lsn_t log_tail_lsn);
/*
* When we crack an atomic LSN, we sample it first so that the value will not
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index f9d8d605f9b1..19260291ff8b 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3944,6 +3944,7 @@ DECLARE_EVENT_CLASS(xlog_iclog_class,
__field(uint32_t, state)
__field(int32_t, refcount)
__field(uint32_t, offset)
+ __field(uint32_t, flags)
__field(unsigned long long, lsn)
__field(unsigned long, caller_ip)
),
@@ -3952,15 +3953,17 @@ DECLARE_EVENT_CLASS(xlog_iclog_class,
__entry->state = iclog->ic_state;
__entry->refcount = atomic_read(&iclog->ic_refcnt);
__entry->offset = iclog->ic_offset;
+ __entry->flags = iclog->ic_flags;
__entry->lsn = be64_to_cpu(iclog->ic_header.h_lsn);
__entry->caller_ip = caller_ip;
),
- TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx caller %pS",
+ TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS",
MAJOR(__entry->dev), MINOR(__entry->dev),
__print_symbolic(__entry->state, XLOG_STATE_STRINGS),
__entry->refcount,
__entry->offset,
__entry->lsn,
+ __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS),
(char *)__entry->caller_ip)
);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 1ae993fee4a5..13d93371790e 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -707,11 +707,6 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv);
* @hrv: Hardware Revision of the device, pass -1 to not check _HRV
*
* The caller is responsible for invoking acpi_dev_put() on the returned device.
- *
- * FIXME: Due to above requirement there is a window that may invalidate @adev
- * and next iteration will use a dangling pointer, e.g. in the case of a
- * hotplug event. That said, the caller should ensure that this will never
- * happen.
*/
#define for_each_acpi_dev_match(adev, hid, uid, hrv) \
for (adev = acpi_dev_get_first_match_dev(hid, uid, hrv); \
@@ -725,7 +720,8 @@ static inline struct acpi_device *acpi_dev_get(struct acpi_device *adev)
static inline void acpi_dev_put(struct acpi_device *adev)
{
- put_device(&adev->dev);
+ if (adev)
+ put_device(&adev->dev);
}
struct acpi_device *acpi_bus_get_acpi_device(acpi_handle handle);
diff --git a/include/drm/drm_ioctl.h b/include/drm/drm_ioctl.h
index 10100a4bbe2a..afb27cb6a7bd 100644
--- a/include/drm/drm_ioctl.h
+++ b/include/drm/drm_ioctl.h
@@ -68,6 +68,7 @@ typedef int drm_ioctl_compat_t(struct file *filp, unsigned int cmd,
unsigned long arg);
#define DRM_IOCTL_NR(n) _IOC_NR(n)
+#define DRM_IOCTL_TYPE(n) _IOC_TYPE(n)
#define DRM_MAJOR 226
/**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 3177181c4326..d3afea47ade6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -57,7 +57,7 @@ struct blk_keyslot_manager;
* Maximum number of blkcg policies allowed to be registered concurrently.
* Defined here to simplify include dependency.
*/
-#define BLKCG_MAX_POLS 5
+#define BLKCG_MAX_POLS 6
typedef void (rq_end_io_fn)(struct request *, blk_status_t);
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index a9db1eae6796..ae3ac3a2018c 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -134,4 +134,5 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_CGROUP, cgroup)
BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
#ifdef CONFIG_NET
BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
+BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
#endif
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e774ecc1cd1f..828d08afeee0 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -340,8 +340,8 @@ struct bpf_insn_aux_data {
};
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
- int sanitize_stack_off; /* stack slot to be cleared */
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
+ bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
bool zext_dst; /* this insn zero extends dst reg */
u8 alu_state; /* used in combination with alu_limit */
@@ -414,6 +414,7 @@ struct bpf_verifier_env {
u32 used_map_cnt; /* number of used maps */
u32 used_btf_cnt; /* number of used BTF objects */
u32 id_gen; /* used to generate unique reg IDs */
+ bool explore_alu_limits;
bool allow_ptr_leaks;
bool allow_uninit_stack;
bool allow_ptr_to_map_access;
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-kvm.h
index 136b8d97d8c0..0d7865a0731c 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-kvm.h
@@ -2,7 +2,11 @@
#ifndef __LINUX_ENTRYKVM_H
#define __LINUX_ENTRYKVM_H
-#include <linux/entry-common.h>
+#include <linux/static_call_types.h>
+#include <linux/tracehook.h>
+#include <linux/syscalls.h>
+#include <linux/seccomp.h>
+#include <linux/sched.h>
#include <linux/tick.h>
/* Transfer to guest mode work */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 472f97074da0..83b896044e79 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -73,6 +73,11 @@ struct ctl_table_header;
/* unused opcode to mark call to interpreter with arguments */
#define BPF_CALL_ARGS 0xe0
+/* unused opcode to mark speculation barrier for mitigating
+ * Speculative Store Bypass
+ */
+#define BPF_NOSPEC 0xc0
+
/* As per nm, we expose JITed images as text (code) section for
* kallsyms. That way, tools like perf can find it to match
* addresses.
@@ -390,6 +395,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
.off = 0, \
.imm = 0 })
+/* Speculation barrier */
+
+#define BPF_ST_NOSPEC() \
+ ((struct bpf_insn) { \
+ .code = BPF_ST | BPF_NOSPEC, \
+ .dst_reg = 0, \
+ .src_reg = 0, \
+ .off = 0, \
+ .imm = 0 })
+
/* Internal classic blocks for direct assignment */
#define __BPF_STMT(CODE, K) \
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index e2bc16300c82..6b54982fc5f3 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -141,6 +141,7 @@ extern int vfs_get_tree(struct fs_context *fc);
extern void put_fs_context(struct fs_context *fc);
extern int vfs_parse_fs_param_source(struct fs_context *fc,
struct fs_parameter *param);
+extern void fc_drop_locked(struct fs_context *fc);
/*
* sget() wrappers to be called from the ->get_tree() op.
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 8c6e8e996c87..d9a606a9fc64 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -318,14 +318,16 @@ static inline void memcpy_to_page(struct page *page, size_t offset,
VM_BUG_ON(offset + len > PAGE_SIZE);
memcpy(to + offset, from, len);
+ flush_dcache_page(page);
kunmap_local(to);
}
static inline void memzero_page(struct page *page, size_t offset, size_t len)
{
- char *addr = kmap_atomic(page);
+ char *addr = kmap_local_page(page);
memset(addr + offset, 0, len);
- kunmap_atomic(addr);
+ flush_dcache_page(page);
+ kunmap_local(addr);
}
#endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h
index 25e2b4e80502..aee8ff4739b1 100644
--- a/include/linux/intel-ish-client-if.h
+++ b/include/linux/intel-ish-client-if.h
@@ -81,6 +81,8 @@ int ishtp_register_event_cb(struct ishtp_cl_device *device,
/* Get the device * from ishtp device instance */
struct device *ishtp_device(struct ishtp_cl_device *cl_device);
+/* wait for IPC resume */
+bool ishtp_wait_resume(struct ishtp_device *dev);
/* Trace interface for clients */
ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device);
/* Get device pointer of PCI device for DMA acces */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c177789a8542..041ca7f15ea4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -872,7 +872,6 @@ void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_dirty(kvm_pfn_t pfn);
void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-void kvm_get_pfn(kvm_pfn_t pfn);
void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache);
int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index cbf46f56d105..4a53c3ca86bd 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -209,7 +209,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
*/
#define for_each_mem_range(i, p_start, p_end) \
__for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, \
- MEMBLOCK_NONE, p_start, p_end, NULL)
+ MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
/**
* for_each_mem_range_rev - reverse iterate through memblock areas from
@@ -220,7 +220,7 @@ static inline void __next_physmem_range(u64 *idx, struct memblock_type *type,
*/
#define for_each_mem_range_rev(i, p_start, p_end) \
__for_each_mem_range_rev(i, &memblock.memory, NULL, NUMA_NO_NODE, \
- MEMBLOCK_NONE, p_start, p_end, NULL)
+ MEMBLOCK_HOTPLUG, p_start, p_end, NULL)
/**
* for_each_reserved_mem_range - iterate over all reserved memblock areas
diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h
index 2d1895c3efbf..40a0c2dfb80f 100644
--- a/include/linux/mfd/rt5033-private.h
+++ b/include/linux/mfd/rt5033-private.h
@@ -200,13 +200,13 @@ enum rt5033_reg {
#define RT5033_REGULATOR_BUCK_VOLTAGE_MIN 1000000U
#define RT5033_REGULATOR_BUCK_VOLTAGE_MAX 3000000U
#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP 100000U
-#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 32
+#define RT5033_REGULATOR_BUCK_VOLTAGE_STEP_NUM 21
/* RT5033 regulator LDO output voltage uV */
#define RT5033_REGULATOR_LDO_VOLTAGE_MIN 1200000U
#define RT5033_REGULATOR_LDO_VOLTAGE_MAX 3000000U
#define RT5033_REGULATOR_LDO_VOLTAGE_STEP 100000U
-#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 32
+#define RT5033_REGULATOR_LDO_VOLTAGE_STEP_NUM 19
/* RT5033 regulator SAFE LDO output voltage uV */
#define RT5033_REGULATOR_SAFE_LDO_VOLTAGE 4900000U
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5922031ffab6..1ace27c4a8e0 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -633,43 +633,6 @@ static inline int PageTransCompound(struct page *page)
}
/*
- * PageTransCompoundMap is the same as PageTransCompound, but it also
- * guarantees the primary MMU has the entire compound page mapped
- * through pmd_trans_huge, which in turn guarantees the secondary MMUs
- * can also map the entire compound page. This allows the secondary
- * MMUs to call get_user_pages() only once for each compound page and
- * to immediately map the entire compound page with a single secondary
- * MMU fault. If there will be a pmd split later, the secondary MMUs
- * will get an update through the MMU notifier invalidation through
- * split_huge_pmd().
- *
- * Unlike PageTransCompound, this is safe to be called only while
- * split_huge_pmd() cannot run from under us, like if protected by the
- * MMU notifier, otherwise it may result in page->_mapcount check false
- * positives.
- *
- * We have to treat page cache THP differently since every subpage of it
- * would get _mapcount inc'ed once it is PMD mapped. But, it may be PTE
- * mapped in the current process so comparing subpage's _mapcount to
- * compound_mapcount to filter out PTE mapped case.
- */
-static inline int PageTransCompoundMap(struct page *page)
-{
- struct page *head;
-
- if (!PageTransCompound(page))
- return 0;
-
- if (PageAnon(page))
- return atomic_read(&page->_mapcount) < 0;
-
- head = compound_head(page);
- /* File THP is PMD mapped and not PTE mapped */
- return atomic_read(&page->_mapcount) ==
- atomic_read(compound_mapcount_ptr(head));
-}
-
-/*
* PageTransTail returns true for both transparent huge pages
* and hugetlbfs pages, so it should only be called when it's known
* that hugetlbfs pages aren't involved.
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index d147480cdefc..e24d2c992b11 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1397,34 +1397,10 @@ static inline int p4d_clear_huge(p4d_t *p4d)
}
#endif /* !__PAGETABLE_P4D_FOLDED */
-#ifndef __PAGETABLE_PUD_FOLDED
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
-int pud_clear_huge(pud_t *pud);
-#else
-static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
-{
- return 0;
-}
-static inline int pud_clear_huge(pud_t *pud)
-{
- return 0;
-}
-#endif /* !__PAGETABLE_PUD_FOLDED */
-
-#ifndef __PAGETABLE_PMD_FOLDED
int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
+int pud_clear_huge(pud_t *pud);
int pmd_clear_huge(pmd_t *pmd);
-#else
-static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
-{
- return 0;
-}
-static inline int pmd_clear_huge(pmd_t *pmd)
-{
- return 0;
-}
-#endif /* !__PAGETABLE_PMD_FOLDED */
-
int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
int pud_free_pmd_page(pud_t *pud, unsigned long addr);
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index 96f319099744..14ab0c0bc924 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -285,11 +285,45 @@ static inline struct sk_psock *sk_psock(const struct sock *sk)
return rcu_dereference_sk_user_data(sk);
}
+static inline void sk_psock_set_state(struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ set_bit(bit, &psock->state);
+}
+
+static inline void sk_psock_clear_state(struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ clear_bit(bit, &psock->state);
+}
+
+static inline bool sk_psock_test_state(const struct sk_psock *psock,
+ enum sk_psock_state_bits bit)
+{
+ return test_bit(bit, &psock->state);
+}
+
+static inline void sock_drop(struct sock *sk, struct sk_buff *skb)
+{
+ sk_drops_add(sk, skb);
+ kfree_skb(skb);
+}
+
+static inline void drop_sk_msg(struct sk_psock *psock, struct sk_msg *msg)
+{
+ if (msg->skb)
+ sock_drop(psock->sk, msg->skb);
+ kfree(msg);
+}
+
static inline void sk_psock_queue_msg(struct sk_psock *psock,
struct sk_msg *msg)
{
spin_lock_bh(&psock->ingress_lock);
- list_add_tail(&msg->list, &psock->ingress_msg);
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))
+ list_add_tail(&msg->list, &psock->ingress_msg);
+ else
+ drop_sk_msg(psock, msg);
spin_unlock_bh(&psock->ingress_lock);
}
@@ -406,24 +440,6 @@ static inline void sk_psock_restore_proto(struct sock *sk,
psock->psock_update_sk_prot(sk, psock, true);
}
-static inline void sk_psock_set_state(struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- set_bit(bit, &psock->state);
-}
-
-static inline void sk_psock_clear_state(struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- clear_bit(bit, &psock->state);
-}
-
-static inline bool sk_psock_test_state(const struct sk_psock *psock,
- enum sk_psock_state_bits bit)
-{
- return test_bit(bit, &psock->state);
-}
-
static inline struct sk_psock *sk_psock_get(struct sock *sk)
{
struct sk_psock *psock;
diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h
index c0f0a13ed818..49aa79c7b278 100644
--- a/include/net/llc_pdu.h
+++ b/include/net/llc_pdu.h
@@ -15,9 +15,11 @@
#include <linux/if_ether.h>
/* Lengths of frame formats */
-#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */
-#define LLC_PDU_LEN_S 4
-#define LLC_PDU_LEN_U 3 /* header and 1 control byte */
+#define LLC_PDU_LEN_I 4 /* header and 2 control bytes */
+#define LLC_PDU_LEN_S 4
+#define LLC_PDU_LEN_U 3 /* header and 1 control byte */
+/* header and 1 control byte and XID info */
+#define LLC_PDU_LEN_U_XID (LLC_PDU_LEN_U + sizeof(struct llc_xid_info))
/* Known SAP addresses */
#define LLC_GLOBAL_SAP 0xFF
#define LLC_NULL_SAP 0x00 /* not network-layer visible */
@@ -50,9 +52,10 @@
#define LLC_PDU_TYPE_U_MASK 0x03 /* 8-bit control field */
#define LLC_PDU_TYPE_MASK 0x03
-#define LLC_PDU_TYPE_I 0 /* first bit */
-#define LLC_PDU_TYPE_S 1 /* first two bits */
-#define LLC_PDU_TYPE_U 3 /* first two bits */
+#define LLC_PDU_TYPE_I 0 /* first bit */
+#define LLC_PDU_TYPE_S 1 /* first two bits */
+#define LLC_PDU_TYPE_U 3 /* first two bits */
+#define LLC_PDU_TYPE_U_XID 4 /* private type for detecting XID commands */
#define LLC_PDU_TYPE_IS_I(pdu) \
((!(pdu->ctrl_1 & LLC_PDU_TYPE_I_MASK)) ? 1 : 0)
@@ -230,9 +233,18 @@ static inline struct llc_pdu_un *llc_pdu_un_hdr(struct sk_buff *skb)
static inline void llc_pdu_header_init(struct sk_buff *skb, u8 type,
u8 ssap, u8 dsap, u8 cr)
{
- const int hlen = type == LLC_PDU_TYPE_U ? 3 : 4;
+ int hlen = 4; /* default value for I and S types */
struct llc_pdu_un *pdu;
+ switch (type) {
+ case LLC_PDU_TYPE_U:
+ hlen = 3;
+ break;
+ case LLC_PDU_TYPE_U_XID:
+ hlen = 6;
+ break;
+ }
+
skb_push(skb, hlen);
skb_reset_network_header(skb);
pdu = llc_pdu_un_hdr(skb);
@@ -374,7 +386,10 @@ static inline void llc_pdu_init_as_xid_cmd(struct sk_buff *skb,
xid_info->fmt_id = LLC_XID_FMT_ID; /* 0x81 */
xid_info->type = svcs_supported;
xid_info->rw = rx_window << 1; /* size of receive window */
- skb_put(skb, sizeof(struct llc_xid_info));
+
+ /* no need to push/put since llc_pdu_header_init() has already
+ * pushed 3 + 3 bytes
+ */
}
/**
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 32fc4a309df5..651bba654d77 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -984,6 +984,7 @@ struct sctp_transport {
} cacc;
struct {
+ __u32 last_rtx_chunks;
__u16 pmtu;
__u16 probe_size;
__u16 probe_high;
@@ -1024,8 +1025,8 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu);
void sctp_transport_immediate_rtx(struct sctp_transport *);
void sctp_transport_dst_release(struct sctp_transport *t);
void sctp_transport_dst_confirm(struct sctp_transport *t);
-void sctp_transport_pl_send(struct sctp_transport *t);
-void sctp_transport_pl_recv(struct sctp_transport *t);
+bool sctp_transport_pl_send(struct sctp_transport *t);
+bool sctp_transport_pl_recv(struct sctp_transport *t);
/* This is the structure we use to queue packets as they come into
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 17df9b047ee4..784d5c3ef1c5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1709,7 +1709,6 @@ struct tcp_fastopen_context {
struct rcu_head rcu;
};
-extern unsigned int sysctl_tcp_fastopen_blackhole_timeout;
void tcp_fastopen_active_disable(struct sock *sk);
bool tcp_fastopen_active_should_disable(struct sock *sk);
void tcp_fastopen_active_disable_ofo_check(struct sock *sk);
diff --git a/include/sound/soc.h b/include/sound/soc.h
index 675849d07284..8e6dd8a257c5 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -712,6 +712,12 @@ struct snd_soc_dai_link {
/* Do not create a PCM for this DAI link (Backend link) */
unsigned int ignore:1;
+ /* This flag will reorder stop sequence. By enabling this flag
+ * DMA controller stop sequence will be invoked first followed by
+ * CPU DAI driver stop sequence
+ */
+ unsigned int stop_dma_first:1;
+
#ifdef CONFIG_SND_SOC_TOPOLOGY
struct snd_soc_dobj dobj; /* For topology */
#endif
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 3ccf591b2374..9f73ed2cf061 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -174,6 +174,34 @@ enum afs_vl_operation {
afs_VL_GetCapabilities = 65537, /* AFS Get VL server capabilities */
};
+enum afs_cm_operation {
+ afs_CB_CallBack = 204, /* AFS break callback promises */
+ afs_CB_InitCallBackState = 205, /* AFS initialise callback state */
+ afs_CB_Probe = 206, /* AFS probe client */
+ afs_CB_GetLock = 207, /* AFS get contents of CM lock table */
+ afs_CB_GetCE = 208, /* AFS get cache file description */
+ afs_CB_GetXStatsVersion = 209, /* AFS get version of extended statistics */
+ afs_CB_GetXStats = 210, /* AFS get contents of extended statistics data */
+ afs_CB_InitCallBackState3 = 213, /* AFS initialise callback state, version 3 */
+ afs_CB_ProbeUuid = 214, /* AFS check the client hasn't rebooted */
+};
+
+enum yfs_cm_operation {
+ yfs_CB_Probe = 206, /* YFS probe client */
+ yfs_CB_GetLock = 207, /* YFS get contents of CM lock table */
+ yfs_CB_XStatsVersion = 209, /* YFS get version of extended statistics */
+ yfs_CB_GetXStats = 210, /* YFS get contents of extended statistics data */
+ yfs_CB_InitCallBackState3 = 213, /* YFS initialise callback state, version 3 */
+ yfs_CB_ProbeUuid = 214, /* YFS check the client hasn't rebooted */
+ yfs_CB_GetServerPrefs = 215,
+ yfs_CB_GetCellServDV = 216,
+ yfs_CB_GetLocalCell = 217,
+ yfs_CB_GetCacheConfig = 218,
+ yfs_CB_GetCellByNum = 65537,
+ yfs_CB_TellMeAboutYourself = 65538, /* get client capabilities */
+ yfs_CB_CallBack = 64204,
+};
+
enum afs_edit_dir_op {
afs_edit_dir_create,
afs_edit_dir_create_error,
@@ -436,6 +464,32 @@ enum afs_cb_break_reason {
EM(afs_YFSVL_GetCellName, "YFSVL.GetCellName") \
E_(afs_VL_GetCapabilities, "VL.GetCapabilities")
+#define afs_cm_operations \
+ EM(afs_CB_CallBack, "CB.CallBack") \
+ EM(afs_CB_InitCallBackState, "CB.InitCallBackState") \
+ EM(afs_CB_Probe, "CB.Probe") \
+ EM(afs_CB_GetLock, "CB.GetLock") \
+ EM(afs_CB_GetCE, "CB.GetCE") \
+ EM(afs_CB_GetXStatsVersion, "CB.GetXStatsVersion") \
+ EM(afs_CB_GetXStats, "CB.GetXStats") \
+ EM(afs_CB_InitCallBackState3, "CB.InitCallBackState3") \
+ E_(afs_CB_ProbeUuid, "CB.ProbeUuid")
+
+#define yfs_cm_operations \
+ EM(yfs_CB_Probe, "YFSCB.Probe") \
+ EM(yfs_CB_GetLock, "YFSCB.GetLock") \
+ EM(yfs_CB_XStatsVersion, "YFSCB.XStatsVersion") \
+ EM(yfs_CB_GetXStats, "YFSCB.GetXStats") \
+ EM(yfs_CB_InitCallBackState3, "YFSCB.InitCallBackState3") \
+ EM(yfs_CB_ProbeUuid, "YFSCB.ProbeUuid") \
+ EM(yfs_CB_GetServerPrefs, "YFSCB.GetServerPrefs") \
+ EM(yfs_CB_GetCellServDV, "YFSCB.GetCellServDV") \
+ EM(yfs_CB_GetLocalCell, "YFSCB.GetLocalCell") \
+ EM(yfs_CB_GetCacheConfig, "YFSCB.GetCacheConfig") \
+ EM(yfs_CB_GetCellByNum, "YFSCB.GetCellByNum") \
+ EM(yfs_CB_TellMeAboutYourself, "YFSCB.TellMeAboutYourself") \
+ E_(yfs_CB_CallBack, "YFSCB.CallBack")
+
#define afs_edit_dir_ops \
EM(afs_edit_dir_create, "create") \
EM(afs_edit_dir_create_error, "c_fail") \
@@ -569,6 +623,8 @@ afs_server_traces;
afs_cell_traces;
afs_fs_operations;
afs_vl_operations;
+afs_cm_operations;
+yfs_cm_operations;
afs_edit_dir_ops;
afs_edit_dir_reasons;
afs_eproto_causes;
@@ -649,20 +705,21 @@ TRACE_EVENT(afs_cb_call,
TP_STRUCT__entry(
__field(unsigned int, call )
- __field(const char *, name )
__field(u32, op )
+ __field(u16, service_id )
),
TP_fast_assign(
__entry->call = call->debug_id;
- __entry->name = call->type->name;
__entry->op = call->operation_ID;
+ __entry->service_id = call->service_id;
),
- TP_printk("c=%08x %s o=%u",
+ TP_printk("c=%08x %s",
__entry->call,
- __entry->name,
- __entry->op)
+ __entry->service_id == 2501 ?
+ __print_symbolic(__entry->op, yfs_cm_operations) :
+ __print_symbolic(__entry->op, afs_cm_operations))
);
TRACE_EVENT(afs_call,
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 2399073c3afc..78c448c6ab4c 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -136,7 +136,7 @@ DECLARE_EVENT_CLASS(net_dev_template,
__assign_str(name, skb->dev->name);
),
- TP_printk("dev=%s skbaddr=%p len=%u",
+ TP_printk("dev=%s skbaddr=%px len=%u",
__get_str(name), __entry->skbaddr, __entry->len)
)
diff --git a/include/trace/events/qdisc.h b/include/trace/events/qdisc.h
index 330d32d84485..c3006c6b4a87 100644
--- a/include/trace/events/qdisc.h
+++ b/include/trace/events/qdisc.h
@@ -41,11 +41,37 @@ TRACE_EVENT(qdisc_dequeue,
__entry->txq_state = txq->state;
),
- TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%p",
+ TP_printk("dequeue ifindex=%d qdisc handle=0x%X parent=0x%X txq_state=0x%lX packets=%d skbaddr=%px",
__entry->ifindex, __entry->handle, __entry->parent,
__entry->txq_state, __entry->packets, __entry->skbaddr )
);
+TRACE_EVENT(qdisc_enqueue,
+
+ TP_PROTO(struct Qdisc *qdisc, const struct netdev_queue *txq, struct sk_buff *skb),
+
+ TP_ARGS(qdisc, txq, skb),
+
+ TP_STRUCT__entry(
+ __field(struct Qdisc *, qdisc)
+ __field(void *, skbaddr)
+ __field(int, ifindex)
+ __field(u32, handle)
+ __field(u32, parent)
+ ),
+
+ TP_fast_assign(
+ __entry->qdisc = qdisc;
+ __entry->skbaddr = skb;
+ __entry->ifindex = txq->dev ? txq->dev->ifindex : 0;
+ __entry->handle = qdisc->handle;
+ __entry->parent = qdisc->parent;
+ ),
+
+ TP_printk("enqueue ifindex=%d qdisc handle=0x%X parent=0x%X skbaddr=%px",
+ __entry->ifindex, __entry->handle, __entry->parent, __entry->skbaddr)
+);
+
TRACE_EVENT(qdisc_reset,
TP_PROTO(struct Qdisc *q),
diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h
index e33997b4d750..edc346a77c91 100644
--- a/include/uapi/linux/idxd.h
+++ b/include/uapi/linux/idxd.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: LGPL-2.1 WITH Linux-syscall-note */
/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */
#ifndef _USR_IDXD_H_
#define _USR_IDXD_H_
diff --git a/include/uapi/rdma/irdma-abi.h b/include/uapi/rdma/irdma-abi.h
index 26b638a7ad97..a7085e092d34 100644
--- a/include/uapi/rdma/irdma-abi.h
+++ b/include/uapi/rdma/irdma-abi.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB */
/*
* Copyright (c) 2006 - 2021 Intel Corporation. All rights reserved.
* Copyright (c) 2005 Topspin Communications. All rights reserved.
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9b1577498373..b1a5fc04492b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -32,6 +32,8 @@
#include <linux/perf_event.h>
#include <linux/extable.h>
#include <linux/log2.h>
+
+#include <asm/barrier.h>
#include <asm/unaligned.h>
/* Registers */
@@ -1377,6 +1379,7 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn)
/* Non-UAPI available opcodes. */
[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
+ [BPF_ST | BPF_NOSPEC] = &&ST_NOSPEC,
[BPF_LDX | BPF_PROBE_MEM | BPF_B] = &&LDX_PROBE_MEM_B,
[BPF_LDX | BPF_PROBE_MEM | BPF_H] = &&LDX_PROBE_MEM_H,
[BPF_LDX | BPF_PROBE_MEM | BPF_W] = &&LDX_PROBE_MEM_W,
@@ -1621,7 +1624,21 @@ out:
COND_JMP(s, JSGE, >=)
COND_JMP(s, JSLE, <=)
#undef COND_JMP
- /* STX and ST and LDX*/
+ /* ST, STX and LDX*/
+ ST_NOSPEC:
+ /* Speculation barrier for mitigating Speculative Store Bypass.
+ * In case of arm64, we rely on the firmware mitigation as
+ * controlled via the ssbd kernel parameter. Whenever the
+ * mitigation is enabled, it works for all of the kernel code
+ * with no need to provide any additional instructions here.
+ * In case of x86, we use 'lfence' insn for mitigation. We
+ * reuse preexisting logic from Spectre v1 mitigation that
+ * happens to produce the required code on x86 for v4 as well.
+ */
+#ifdef CONFIG_X86
+ barrier_nospec();
+#endif
+ CONT;
#define LDST(SIZEOP, SIZE) \
STX_MEM_##SIZEOP: \
*(SIZE *)(unsigned long) (DST + insn->off) = SRC; \
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index bbfc6bb79240..ca3cd9aaa6ce 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -206,15 +206,17 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
verbose(cbs->private_data, "BUG_%02x\n", insn->code);
}
} else if (class == BPF_ST) {
- if (BPF_MODE(insn->code) != BPF_MEM) {
+ if (BPF_MODE(insn->code) == BPF_MEM) {
+ verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) {
+ verbose(cbs->private_data, "(%02x) nospec\n", insn->code);
+ } else {
verbose(cbs->private_data, "BUG_st_%02x\n", insn->code);
- return;
}
- verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n",
- insn->code,
- bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
- insn->dst_reg,
- insn->off, insn->imm);
} else if (class == BPF_LDX) {
if (BPF_MODE(insn->code) != BPF_MEM) {
verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 42a4063de7cd..f9bda5476ea5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2610,6 +2610,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
+ if (!env->bypass_spec_v4) {
+ bool sanitize = reg && is_spillable_regtype(reg->type);
+
+ for (i = 0; i < size; i++) {
+ if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ sanitize = true;
+ break;
+ }
+ }
+
+ if (sanitize)
+ env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ }
if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
@@ -2632,47 +2645,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
-
if (state != cur && reg->type == PTR_TO_STACK) {
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
-
- if (!env->bypass_spec_v4) {
- bool sanitize = false;
-
- if (state->stack[spi].slot_type[0] == STACK_SPILL &&
- register_is_const(&state->stack[spi].spilled_ptr))
- sanitize = true;
- for (i = 0; i < BPF_REG_SIZE; i++)
- if (state->stack[spi].slot_type[i] == STACK_MISC) {
- sanitize = true;
- break;
- }
- if (sanitize) {
- int *poff = &env->insn_aux_data[insn_idx].sanitize_stack_off;
- int soff = (-spi - 1) * BPF_REG_SIZE;
-
- /* detected reuse of integer stack slot with a pointer
- * which means either llvm is reusing stack slot or
- * an attacker is trying to exploit CVE-2018-3639
- * (speculative store bypass)
- * Have to sanitize that slot with preemptive
- * store of zero.
- */
- if (*poff && *poff != soff) {
- /* disallow programs where single insn stores
- * into two different stack slots, since verifier
- * cannot sanitize them
- */
- verbose(env,
- "insn %d cannot access two stack slots fp%d and fp%d",
- insn_idx, *poff, soff);
- return -EINVAL;
- }
- *poff = soff;
- }
- }
save_register_state(state, spi, reg);
} else {
u8 type = STACK_MISC;
@@ -3677,6 +3653,8 @@ continue_func:
if (tail_call_reachable)
for (j = 0; j < frame; j++)
subprog[ret_prog[j]].tail_call_reachable = true;
+ if (subprog[0].tail_call_reachable)
+ env->prog->aux->tail_call_reachable = true;
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
@@ -6559,6 +6537,12 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+ /* Limit pruning on unknown scalars to enable deep search for
+ * potential masking differences from other program paths.
+ */
+ if (!off_is_imm)
+ env->explore_alu_limits = true;
}
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
@@ -9934,8 +9918,8 @@ next:
}
/* Returns true if (rold safe implies rcur safe) */
-static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
- struct bpf_id_pair *idmap)
+static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
+ struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
{
bool equal;
@@ -9961,6 +9945,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
switch (rold->type) {
case SCALAR_VALUE:
+ if (env->explore_alu_limits)
+ return false;
if (rcur->type == SCALAR_VALUE) {
if (!rold->precise && !rcur->precise)
return true;
@@ -10051,9 +10037,8 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
return false;
}
-static bool stacksafe(struct bpf_func_state *old,
- struct bpf_func_state *cur,
- struct bpf_id_pair *idmap)
+static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ struct bpf_func_state *cur, struct bpf_id_pair *idmap)
{
int i, spi;
@@ -10098,9 +10083,8 @@ static bool stacksafe(struct bpf_func_state *old,
continue;
if (old->stack[spi].slot_type[0] != STACK_SPILL)
continue;
- if (!regsafe(&old->stack[spi].spilled_ptr,
- &cur->stack[spi].spilled_ptr,
- idmap))
+ if (!regsafe(env, &old->stack[spi].spilled_ptr,
+ &cur->stack[spi].spilled_ptr, idmap))
/* when explored and current stack slot are both storing
* spilled registers, check that stored pointers types
* are the same as well.
@@ -10157,10 +10141,11 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
for (i = 0; i < MAX_BPF_REG; i++)
- if (!regsafe(&old->regs[i], &cur->regs[i], env->idmap_scratch))
+ if (!regsafe(env, &old->regs[i], &cur->regs[i],
+ env->idmap_scratch))
return false;
- if (!stacksafe(old, cur, env->idmap_scratch))
+ if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
if (!refsafe(old, cur))
@@ -11904,35 +11889,33 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ bool ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW))
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
type = BPF_READ;
- else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_STX | BPF_MEM | BPF_DW))
+ ctx_access = true;
+ } else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_STX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_B) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_H) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_W) ||
+ insn->code == (BPF_ST | BPF_MEM | BPF_DW)) {
type = BPF_WRITE;
- else
+ ctx_access = BPF_CLASS(insn->code) == BPF_STX;
+ } else {
continue;
+ }
if (type == BPF_WRITE &&
- env->insn_aux_data[i + delta].sanitize_stack_off) {
+ env->insn_aux_data[i + delta].sanitize_stack_spill) {
struct bpf_insn patch[] = {
- /* Sanitize suspicious stack slot with zero.
- * There are no memory dependencies for this store,
- * since it's only using frame pointer and immediate
- * constant of zero
- */
- BPF_ST_MEM(BPF_DW, BPF_REG_FP,
- env->insn_aux_data[i + delta].sanitize_stack_off,
- 0),
- /* the original STX instruction will immediately
- * overwrite the same stack slot with appropriate value
- */
*insn,
+ BPF_ST_NOSPEC(),
};
cnt = ARRAY_SIZE(patch);
@@ -11946,6 +11929,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
continue;
}
+ if (!ctx_access)
+ continue;
+
switch (env->insn_aux_data[i + delta].ptr_type) {
case PTR_TO_CTX:
if (!ops->convert_ctx_access)
@@ -12750,37 +12736,6 @@ static void free_states(struct bpf_verifier_env *env)
}
}
-/* The verifier is using insn_aux_data[] to store temporary data during
- * verification and to store information for passes that run after the
- * verification like dead code sanitization. do_check_common() for subprogram N
- * may analyze many other subprograms. sanitize_insn_aux_data() clears all
- * temporary data after do_check_common() finds that subprogram N cannot be
- * verified independently. pass_cnt counts the number of times
- * do_check_common() was run and insn->aux->seen tells the pass number
- * insn_aux_data was touched. These variables are compared to clear temporary
- * data from failed pass. For testing and experiments do_check_common() can be
- * run multiple times even when prior attempt to verify is unsuccessful.
- *
- * Note that special handling is needed on !env->bypass_spec_v1 if this is
- * ever called outside of error path with subsequent program rejection.
- */
-static void sanitize_insn_aux_data(struct bpf_verifier_env *env)
-{
- struct bpf_insn *insn = env->prog->insnsi;
- struct bpf_insn_aux_data *aux;
- int i, class;
-
- for (i = 0; i < env->prog->len; i++) {
- class = BPF_CLASS(insn[i].code);
- if (class != BPF_LDX && class != BPF_STX)
- continue;
- aux = &env->insn_aux_data[i];
- if (aux->seen != env->pass_cnt)
- continue;
- memset(aux, 0, offsetof(typeof(*aux), orig_idx));
- }
-}
-
static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
@@ -12857,9 +12812,6 @@ out:
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
- if (ret)
- /* clean aux data in case subprog was rejected */
- sanitize_insn_aux_data(env);
return ret;
}
diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
index 8d6bf56ed77a..de2c432dee20 100644
--- a/kernel/cgroup/cgroup-v1.c
+++ b/kernel/cgroup/cgroup-v1.c
@@ -1221,9 +1221,7 @@ int cgroup1_get_tree(struct fs_context *fc)
ret = cgroup_do_get_tree(fc);
if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) {
- struct super_block *sb = fc->root->d_sb;
- dput(fc->root);
- deactivate_locked_super(sb);
+ fc_drop_locked(fc);
ret = 1;
}
diff --git a/kernel/dma/ops_helpers.c b/kernel/dma/ops_helpers.c
index 910ae69cae77..af4a6ef48ce0 100644
--- a/kernel/dma/ops_helpers.c
+++ b/kernel/dma/ops_helpers.c
@@ -5,6 +5,13 @@
*/
#include <linux/dma-map-ops.h>
+static struct page *dma_common_vaddr_to_page(void *cpu_addr)
+{
+ if (is_vmalloc_addr(cpu_addr))
+ return vmalloc_to_page(cpu_addr);
+ return virt_to_page(cpu_addr);
+}
+
/*
* Create scatter-list for the already allocated DMA buffer.
*/
@@ -12,7 +19,7 @@ int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
void *cpu_addr, dma_addr_t dma_addr, size_t size,
unsigned long attrs)
{
- struct page *page = virt_to_page(cpu_addr);
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret;
ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
@@ -32,6 +39,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
unsigned long user_count = vma_pages(vma);
unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
unsigned long off = vma->vm_pgoff;
+ struct page *page = dma_common_vaddr_to_page(cpu_addr);
int ret = -ENXIO;
vma->vm_page_prot = dma_pgprot(dev, vma->vm_page_prot, attrs);
@@ -43,7 +51,7 @@ int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
return -ENXIO;
return remap_pfn_range(vma, vma->vm_start,
- page_to_pfn(virt_to_page(cpu_addr)) + vma->vm_pgoff,
+ page_to_pfn(page) + vma->vm_pgoff,
user_count << PAGE_SHIFT, vma->vm_page_prot);
#else
return -ENXIO;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index e4163042c4d6..cf6acab78538 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -47,7 +47,7 @@ void __init idle_thread_set_boot_cpu(void)
*
* Creates the thread if it does not exist.
*/
-static inline void idle_init(unsigned int cpu)
+static __always_inline void idle_init(unsigned int cpu)
{
struct task_struct *tsk = per_cpu(idle_threads, cpu);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 29a5e54e6e10..517be7fd175e 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -991,6 +991,11 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
if (!p)
goto out;
+ /* Protect timer list r/w in arm_timer() */
+ sighand = lock_task_sighand(p, &flags);
+ if (unlikely(sighand == NULL))
+ goto out;
+
/*
* Fetch the current sample and update the timer's expiry time.
*/
@@ -1001,11 +1006,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
bump_cpu_timer(timer, now);
- /* Protect timer list r/w in arm_timer() */
- sighand = lock_task_sighand(p, &flags);
- if (unlikely(sighand == NULL))
- goto out;
-
/*
* Now re-arm for the new expiry time.
*/
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 3fadb58fc9d7..9eb11c2209e5 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -207,6 +207,7 @@ struct timer_base {
unsigned int cpu;
bool next_expiry_recalc;
bool is_idle;
+ bool timers_pending;
DECLARE_BITMAP(pending_map, WHEEL_SIZE);
struct hlist_head vectors[WHEEL_SIZE];
} ____cacheline_aligned;
@@ -595,6 +596,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer,
* can reevaluate the wheel:
*/
base->next_expiry = bucket_expiry;
+ base->timers_pending = true;
base->next_expiry_recalc = false;
trigger_dyntick_cpu(base, timer);
}
@@ -1582,6 +1584,7 @@ static unsigned long __next_timer_interrupt(struct timer_base *base)
}
base->next_expiry_recalc = false;
+ base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA);
return next;
}
@@ -1633,7 +1636,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
u64 expires = KTIME_MAX;
unsigned long nextevt;
- bool is_max_delta;
/*
* Pretend that there is no timer pending if the cpu is offline.
@@ -1646,7 +1648,6 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
if (base->next_expiry_recalc)
base->next_expiry = __next_timer_interrupt(base);
nextevt = base->next_expiry;
- is_max_delta = (nextevt == base->clk + NEXT_TIMER_MAX_DELTA);
/*
* We have a fresh next event. Check whether we can forward the
@@ -1664,7 +1665,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
expires = basem;
base->is_idle = false;
} else {
- if (!is_max_delta)
+ if (base->timers_pending)
expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
/*
* If we expect to sleep more than a tick, mark the base idle.
@@ -1947,6 +1948,7 @@ int timers_prepare_cpu(unsigned int cpu)
base = per_cpu_ptr(&timer_bases[b], cpu);
base->clk = jiffies;
base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->timers_pending = false;
base->is_idle = false;
}
return 0;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index e6fb3e6e1ffc..7b180f61e6d3 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5985,7 +5985,8 @@ ftrace_graph_release(struct inode *inode, struct file *file)
* infrastructure to do the synchronization, thus we must do it
* ourselves.
*/
- synchronize_rcu_tasks_rude();
+ if (old_hash != EMPTY_HASH)
+ synchronize_rcu_tasks_rude();
free_ftrace_hash(old_hash);
}
@@ -7544,7 +7545,7 @@ int ftrace_is_dead(void)
*/
int register_ftrace_function(struct ftrace_ops *ops)
{
- int ret = -1;
+ int ret;
ftrace_ops_init(ops);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index d1463eac11a3..e592d1df6f88 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3880,10 +3880,30 @@ static bool rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
if (unlikely(!head))
return true;
- return reader->read == rb_page_commit(reader) &&
- (commit == reader ||
- (commit == head &&
- head->read == rb_page_commit(commit)));
+ /* Reader should exhaust content in reader page */
+ if (reader->read != rb_page_commit(reader))
+ return false;
+
+ /*
+ * If writers are committing on the reader page, knowing all
+ * committed content has been read, the ring buffer is empty.
+ */
+ if (commit == reader)
+ return true;
+
+ /*
+ * If writers are committing on a page other than reader page
+ * and head page, there should always be content to read.
+ */
+ if (commit != head)
+ return false;
+
+ /*
+ * Writers are committing on the head page, we just need
+ * to care about there're committed data, and the reader will
+ * swap reader page with head page when it is to read data.
+ */
+ return rb_page_commit(commit) == 0;
}
/**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index f8b80b5bab71..c59dd35a6da5 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5609,6 +5609,10 @@ static const char readme_msg[] =
"\t [:name=histname1]\n"
"\t [:<handler>.<action>]\n"
"\t [if <filter>]\n\n"
+ "\t Note, special fields can be used as well:\n"
+ "\t common_timestamp - to record current timestamp\n"
+ "\t common_cpu - to record the CPU the event happened on\n"
+ "\n"
"\t When a matching event is hit, an entry is added to a hash\n"
"\t table using the key(s) and value(s) named, and the value of a\n"
"\t sum called 'hitcount' is incremented. Keys and values\n"
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 16a9dfc9fffc..34325f41ebc0 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -1111,7 +1111,7 @@ static const char *hist_field_name(struct hist_field *field,
field->flags & HIST_FIELD_FL_ALIAS)
field_name = hist_field_name(field->operands[0], ++level);
else if (field->flags & HIST_FIELD_FL_CPU)
- field_name = "cpu";
+ field_name = "common_cpu";
else if (field->flags & HIST_FIELD_FL_EXPR ||
field->flags & HIST_FIELD_FL_VAR_REF) {
if (field->system) {
@@ -1991,14 +1991,24 @@ parse_field(struct hist_trigger_data *hist_data, struct trace_event_file *file,
hist_data->enable_timestamps = true;
if (*flags & HIST_FIELD_FL_TIMESTAMP_USECS)
hist_data->attrs->ts_in_usecs = true;
- } else if (strcmp(field_name, "cpu") == 0)
+ } else if (strcmp(field_name, "common_cpu") == 0)
*flags |= HIST_FIELD_FL_CPU;
else {
field = trace_find_event_field(file->event_call, field_name);
if (!field || !field->size) {
- hist_err(tr, HIST_ERR_FIELD_NOT_FOUND, errpos(field_name));
- field = ERR_PTR(-EINVAL);
- goto out;
+ /*
+ * For backward compatibility, if field_name
+ * was "cpu", then we treat this the same as
+ * common_cpu.
+ */
+ if (strcmp(field_name, "cpu") == 0) {
+ *flags |= HIST_FIELD_FL_CPU;
+ } else {
+ hist_err(tr, HIST_ERR_FIELD_NOT_FOUND,
+ errpos(field_name));
+ field = ERR_PTR(-EINVAL);
+ goto out;
+ }
}
}
out:
@@ -5085,7 +5095,7 @@ static void hist_field_print(struct seq_file *m, struct hist_field *hist_field)
seq_printf(m, "%s=", hist_field->var.name);
if (hist_field->flags & HIST_FIELD_FL_CPU)
- seq_puts(m, "cpu");
+ seq_puts(m, "common_cpu");
else if (field_name) {
if (hist_field->flags & HIST_FIELD_FL_VAR_REF ||
hist_field->flags & HIST_FIELD_FL_ALIAS)
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 2ac75eb6aa86..9315fc03e303 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -893,15 +893,13 @@ static struct synth_event *alloc_synth_event(const char *name, int n_fields,
dyn_event_init(&event->devent, &synth_event_ops);
for (i = 0, j = 0; i < n_fields; i++) {
+ fields[i]->field_pos = i;
event->fields[i] = fields[i];
- if (fields[i]->is_dynamic) {
- event->dynamic_fields[j] = fields[i];
- event->dynamic_fields[j]->field_pos = i;
+ if (fields[i]->is_dynamic)
event->dynamic_fields[j++] = fields[i];
- event->n_dynamic_fields++;
- }
}
+ event->n_dynamic_fields = j;
event->n_fields = n_fields;
out:
return event;
diff --git a/kernel/trace/trace_synth.h b/kernel/trace/trace_synth.h
index 6e146b959dcd..4007fe95cf42 100644
--- a/kernel/trace/trace_synth.h
+++ b/kernel/trace/trace_synth.h
@@ -14,10 +14,10 @@ struct synth_field {
char *name;
size_t size;
unsigned int offset;
+ unsigned int field_pos;
bool is_signed;
bool is_string;
bool is_dynamic;
- bool field_pos;
};
struct synth_event {
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index 976bf8ce8039..fc32821f8240 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -299,8 +299,8 @@ static int tracepoint_add_func(struct tracepoint *tp,
* a pointer to it. This array is referenced by __DO_TRACE from
* include/linux/tracepoint.h using rcu_dereference_sched().
*/
- rcu_assign_pointer(tp->funcs, tp_funcs);
tracepoint_update_call(tp, tp_funcs, false);
+ rcu_assign_pointer(tp->funcs, tp_funcs);
static_key_enable(&tp->key);
release_probes(old);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 50142fc08902..f148eacda55a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3676,15 +3676,21 @@ static void pwq_unbound_release_workfn(struct work_struct *work)
unbound_release_work);
struct workqueue_struct *wq = pwq->wq;
struct worker_pool *pool = pwq->pool;
- bool is_last;
+ bool is_last = false;
- if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
- return;
+ /*
+ * when @pwq is not linked, it doesn't hold any reference to the
+ * @wq, and @wq is invalid to access.
+ */
+ if (!list_empty(&pwq->pwqs_node)) {
+ if (WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)))
+ return;
- mutex_lock(&wq->mutex);
- list_del_rcu(&pwq->pwqs_node);
- is_last = list_empty(&wq->pwqs);
- mutex_unlock(&wq->mutex);
+ mutex_lock(&wq->mutex);
+ list_del_rcu(&pwq->pwqs_node);
+ is_last = list_empty(&wq->pwqs);
+ mutex_unlock(&wq->mutex);
+ }
mutex_lock(&wq_pool_mutex);
put_unbound_pool(pool);
diff --git a/lib/Kconfig b/lib/Kconfig
index d241fe476fda..5c9c0687f76d 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -683,9 +683,6 @@ config PARMAN
config OBJAGG
tristate "objagg" if COMPILE_TEST
-config STRING_SELFTEST
- tristate "Test string functions"
-
endmenu
config GENERIC_IOREMAP
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 831212722924..5ddd575159fb 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2180,6 +2180,9 @@ config ASYNC_RAID6_TEST
config TEST_HEXDUMP
tristate "Test functions located in the hexdump module at runtime"
+config STRING_SELFTEST
+ tristate "Test string functions at runtime"
+
config TEST_STRING_HELPERS
tristate "Test functions located in the string_helpers module at runtime"
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 271f2ca862c8..f5561ea7d90a 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -398,12 +398,12 @@ static void cgwb_release_workfn(struct work_struct *work)
blkcg_unpin_online(blkcg);
fprop_local_destroy_percpu(&wb->memcg_completions);
- percpu_ref_exit(&wb->refcnt);
spin_lock_irq(&cgwb_lock);
list_del(&wb->offline_node);
spin_unlock_irq(&cgwb_lock);
+ percpu_ref_exit(&wb->refcnt);
wb_exit(wb);
WARN_ON_ONCE(!list_empty(&wb->b_attached));
kfree_rcu(wb, rcu);
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index d7666ace9d2e..575c685aa642 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -734,6 +734,22 @@ void kfence_shutdown_cache(struct kmem_cache *s)
void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
{
/*
+ * Perform size check before switching kfence_allocation_gate, so that
+ * we don't disable KFENCE without making an allocation.
+ */
+ if (size > PAGE_SIZE)
+ return NULL;
+
+ /*
+ * Skip allocations from non-default zones, including DMA. We cannot
+ * guarantee that pages in the KFENCE pool will have the requested
+ * properties (e.g. reside in DMAable memory).
+ */
+ if ((flags & GFP_ZONEMASK) ||
+ (s->flags & (SLAB_CACHE_DMA | SLAB_CACHE_DMA32)))
+ return NULL;
+
+ /*
* allocation_gate only needs to become non-zero, so it doesn't make
* sense to continue writing to it and pay the associated contention
* cost, in case we have a large number of concurrent allocations.
@@ -757,9 +773,6 @@ void *__kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags)
if (!READ_ONCE(kfence_enabled))
return NULL;
- if (size > PAGE_SIZE)
- return NULL;
-
return kfence_guarded_alloc(s, size, flags);
}
diff --git a/mm/kfence/kfence_test.c b/mm/kfence/kfence_test.c
index 7f24b9bcb2ec..942cbc16ad26 100644
--- a/mm/kfence/kfence_test.c
+++ b/mm/kfence/kfence_test.c
@@ -852,7 +852,7 @@ static void kfence_test_exit(void)
tracepoint_synchronize_unregister();
}
-late_initcall(kfence_test_init);
+late_initcall_sync(kfence_test_init);
module_exit(kfence_test_exit);
MODULE_LICENSE("GPL v2");
diff --git a/mm/memblock.c b/mm/memblock.c
index 0041ff62c584..de7b553baa50 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -947,7 +947,8 @@ static bool should_skip_region(struct memblock_type *type,
return true;
/* skip hotpluggable memory regions if needed */
- if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
+ if (movable_node_is_enabled() && memblock_is_hotpluggable(m) &&
+ !(flags & MEMBLOCK_HOTPLUG))
return true;
/* if we want mirror memory skip non-mirror memory regions */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae1f5d0cb581..eb8e87c4833f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3574,7 +3574,8 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
unsigned long val;
if (mem_cgroup_is_root(memcg)) {
- cgroup_rstat_flush(memcg->css.cgroup);
+ /* mem_cgroup_threshold() calls here from irqsafe context */
+ cgroup_rstat_flush_irqsafe(memcg->css.cgroup);
val = memcg_page_state(memcg, NR_FILE_PAGES) +
memcg_page_state(memcg, NR_ANON_MAPPED);
if (swap)
diff --git a/mm/memory.c b/mm/memory.c
index 747a01d495f2..25fc46e87214 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4026,8 +4026,17 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
return ret;
}
- if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd)))
+ if (vmf->prealloc_pte) {
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (likely(pmd_none(*vmf->pmd))) {
+ mm_inc_nr_ptes(vma->vm_mm);
+ pmd_populate(vma->vm_mm, vmf->pmd, vmf->prealloc_pte);
+ vmf->prealloc_pte = NULL;
+ }
+ spin_unlock(vmf->ptl);
+ } else if (unlikely(pte_alloc(vma->vm_mm, vmf->pmd))) {
return VM_FAULT_OOM;
+ }
}
/* See comment in handle_pte_fault() */
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a9ad3e0a4f..7e240437e7d9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2068,7 +2068,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
LIST_HEAD(migratepages);
new_page_t *new;
bool compound;
- unsigned int nr_pages = thp_nr_pages(page);
+ int nr_pages = thp_nr_pages(page);
/*
* PTE mapped THP or HugeTLB page can't reach here so the page could
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index f5852a058ce0..1854850b4b89 100644
--- a/mm/mmap_lock.c
+++ b/mm/mmap_lock.c
@@ -156,14 +156,14 @@ static inline void put_memcg_path_buf(void)
#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
do { \
const char *memcg_path; \
- preempt_disable(); \
+ local_lock(&memcg_paths.lock); \
memcg_path = get_mm_memcg_path(mm); \
trace_mmap_lock_##type(mm, \
memcg_path != NULL ? memcg_path : "", \
##__VA_ARGS__); \
if (likely(memcg_path != NULL)) \
put_memcg_path_buf(); \
- preempt_enable(); \
+ local_unlock(&memcg_paths.lock); \
} while (0)
#else /* !CONFIG_MEMCG */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3e97e68aef7a..856b175c15a4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -840,21 +840,24 @@ void init_mem_debugging_and_hardening(void)
}
#endif
- if (_init_on_alloc_enabled_early) {
- if (page_poisoning_requested)
- pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
- "will take precedence over init_on_alloc\n");
- else
- static_branch_enable(&init_on_alloc);
- }
- if (_init_on_free_enabled_early) {
- if (page_poisoning_requested)
- pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
- "will take precedence over init_on_free\n");
- else
- static_branch_enable(&init_on_free);
+ if ((_init_on_alloc_enabled_early || _init_on_free_enabled_early) &&
+ page_poisoning_requested) {
+ pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, "
+ "will take precedence over init_on_alloc and init_on_free\n");
+ _init_on_alloc_enabled_early = false;
+ _init_on_free_enabled_early = false;
}
+ if (_init_on_alloc_enabled_early)
+ static_branch_enable(&init_on_alloc);
+ else
+ static_branch_disable(&init_on_alloc);
+
+ if (_init_on_free_enabled_early)
+ static_branch_enable(&init_on_free);
+ else
+ static_branch_disable(&init_on_free);
+
#ifdef CONFIG_DEBUG_PAGEALLOC
if (!debug_pagealloc_enabled())
return;
diff --git a/mm/secretmem.c b/mm/secretmem.c
index f77d25467a14..030f02ddc7c1 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -152,6 +152,7 @@ static void secretmem_freepage(struct page *page)
}
const struct address_space_operations secretmem_aops = {
+ .set_page_dirty = __set_page_dirty_no_writeback,
.freepage = secretmem_freepage,
.migratepage = secretmem_migratepage,
.isolate_page = secretmem_isolate_page,
diff --git a/mm/slab.h b/mm/slab.h
index f997fd5e42c8..58c01a34e5b8 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -346,7 +346,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
continue;
page = virt_to_head_page(p[i]);
- objcgs = page_objcgs(page);
+ objcgs = page_objcgs_check(page);
if (!objcgs)
continue;
diff --git a/mm/slub.c b/mm/slub.c
index 090fa14628f9..af984e4990e8 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3236,6 +3236,16 @@ struct detached_freelist {
struct kmem_cache *s;
};
+static inline void free_nonslab_page(struct page *page)
+{
+ unsigned int order = compound_order(page);
+
+ VM_BUG_ON_PAGE(!PageCompound(page), page);
+ kfree_hook(page_address(page));
+ mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order));
+ __free_pages(page, order);
+}
+
/*
* This function progressively scans the array with free objects (with
* a limited look ahead) and extract objects belonging to the same
@@ -3272,9 +3282,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size,
if (!s) {
/* Handle kalloc'ed objects */
if (unlikely(!PageSlab(page))) {
- BUG_ON(!PageCompound(page));
- kfree_hook(object);
- __free_pages(page, compound_order(page));
+ free_nonslab_page(page);
p[size] = NULL; /* mark object processed */
return size;
}
@@ -4250,13 +4258,7 @@ void kfree(const void *x)
page = virt_to_head_page(x);
if (unlikely(!PageSlab(page))) {
- unsigned int order = compound_order(page);
-
- BUG_ON(!PageCompound(page));
- kfree_hook(object);
- mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
- -(PAGE_SIZE << order));
- __free_pages(page, order);
+ free_nonslab_page(page);
return;
}
slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aa47af349ba8..1cc75c811e24 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -701,6 +701,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
void *data;
int ret;
+ if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
+ prog->expected_attach_type == BPF_XDP_CPUMAP)
+ return -EINVAL;
if (kattr->test.ctx_in || kattr->test.ctx_out)
return -EINVAL;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index 2b862cffc03a..a16191dcaed1 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -780,7 +780,7 @@ int br_fdb_replay(const struct net_device *br_dev, const struct net_device *dev,
struct net_device *dst_dev;
dst_dev = dst ? dst->dev : br->dev;
- if (dst_dev != br_dev && dst_dev != dev)
+ if (dst_dev && dst_dev != dev)
continue;
err = br_fdb_replay_one(nb, fdb, dst_dev, action, ctx);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 647554c9813b..e12fd3cad619 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -539,7 +539,8 @@ static int caif_seqpkt_sendmsg(struct socket *sock, struct msghdr *msg,
goto err;
ret = -EINVAL;
- if (unlikely(msg->msg_iter.iov->iov_base == NULL))
+ if (unlikely(msg->msg_iter.nr_segs == 0) ||
+ unlikely(msg->msg_iter.iov->iov_base == NULL))
goto err;
noblock = msg->msg_flags & MSG_DONTWAIT;
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index c3946c355882..bdc95bd7a851 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1075,11 +1075,16 @@ static bool j1939_session_deactivate_locked(struct j1939_session *session)
static bool j1939_session_deactivate(struct j1939_session *session)
{
+ struct j1939_priv *priv = session->priv;
bool active;
- j1939_session_list_lock(session->priv);
+ j1939_session_list_lock(priv);
+ /* This function should be called with a session ref-count of at
+ * least 2.
+ */
+ WARN_ON_ONCE(kref_read(&session->kref) < 2);
active = j1939_session_deactivate_locked(session);
- j1939_session_list_unlock(session->priv);
+ j1939_session_list_unlock(priv);
return active;
}
@@ -1869,7 +1874,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
if (!session->transmission)
j1939_tp_schedule_txtimer(session, 0);
} else {
- j1939_tp_set_rxtimeout(session, 250);
+ j1939_tp_set_rxtimeout(session, 750);
}
session->last_cmd = 0xff;
consume_skb(se_skb);
diff --git a/net/can/raw.c b/net/can/raw.c
index ed4fcb7ab0c3..cd5a49380116 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -546,10 +546,18 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
return -EFAULT;
}
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ if (count > 1)
+ kfree(filter);
+ err = -ENODEV;
+ goto out_fil;
+ }
+ }
if (ro->bound) {
/* (try to) register the new filters */
@@ -588,6 +596,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
@@ -600,10 +609,16 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
err_mask &= CAN_ERR_MASK;
+ rtnl_lock();
lock_sock(sk);
- if (ro->bound && ro->ifindex)
+ if (ro->bound && ro->ifindex) {
dev = dev_get_by_index(sock_net(sk), ro->ifindex);
+ if (!dev) {
+ err = -ENODEV;
+ goto out_err;
+ }
+ }
/* remove current error mask */
if (ro->bound) {
@@ -627,6 +642,7 @@ static int raw_setsockopt(struct socket *sock, int level, int optname,
dev_put(dev);
release_sock(sk);
+ rtnl_unlock();
break;
diff --git a/net/core/dev.c b/net/core/dev.c
index 64b21f0a2048..8f1a47ad6781 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -131,6 +131,7 @@
#include <trace/events/napi.h>
#include <trace/events/net.h>
#include <trace/events/skb.h>
+#include <trace/events/qdisc.h>
#include <linux/inetdevice.h>
#include <linux/cpu_rmap.h>
#include <linux/static_key.h>
@@ -3844,6 +3845,18 @@ static void qdisc_pkt_len_init(struct sk_buff *skb)
}
}
+static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q,
+ struct sk_buff **to_free,
+ struct netdev_queue *txq)
+{
+ int rc;
+
+ rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK;
+ if (rc == NET_XMIT_SUCCESS)
+ trace_qdisc_enqueue(q, txq, skb);
+ return rc;
+}
+
static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev,
struct netdev_queue *txq)
@@ -3862,8 +3875,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
* of q->seqlock to protect from racing with requeuing.
*/
if (unlikely(!nolock_qdisc_is_empty(q))) {
- rc = q->enqueue(skb, q, &to_free) &
- NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
__qdisc_run(q);
qdisc_run_end(q);
@@ -3879,7 +3891,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
return NET_XMIT_SUCCESS;
}
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
qdisc_run(q);
no_lock_out:
@@ -3923,7 +3935,7 @@ no_lock_out:
qdisc_run_end(q);
rc = NET_XMIT_SUCCESS;
} else {
- rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK;
+ rc = dev_qdisc_enqueue(skb, q, &to_free, txq);
if (qdisc_run_begin(q)) {
if (unlikely(contended)) {
spin_unlock(&q->busylock);
@@ -9700,14 +9712,17 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
struct net_device *dev;
int err, fd;
+ rtnl_lock();
dev = dev_get_by_index(net, attr->link_create.target_ifindex);
- if (!dev)
+ if (!dev) {
+ rtnl_unlock();
return -EINVAL;
+ }
link = kzalloc(sizeof(*link), GFP_USER);
if (!link) {
err = -ENOMEM;
- goto out_put_dev;
+ goto unlock;
}
bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
@@ -9717,14 +9732,14 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
err = bpf_link_prime(&link->link, &link_primer);
if (err) {
kfree(link);
- goto out_put_dev;
+ goto unlock;
}
- rtnl_lock();
err = dev_xdp_attach_link(dev, NULL, link);
rtnl_unlock();
if (err) {
+ link->dev = NULL;
bpf_link_cleanup(&link_primer);
goto out_put_dev;
}
@@ -9734,6 +9749,9 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
dev_put(dev);
return fd;
+unlock:
+ rtnl_unlock();
+
out_put_dev:
dev_put(dev);
return err;
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 8fdd04f00fd7..85032626de24 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -9328,18 +9328,10 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
switch (attrs->flavour) {
case DEVLINK_PORT_FLAVOUR_PHYSICAL:
- case DEVLINK_PORT_FLAVOUR_VIRTUAL:
n = snprintf(name, len, "p%u", attrs->phys.port_number);
if (n < len && attrs->split)
n += snprintf(name + n, len - n, "s%u",
attrs->phys.split_subport_number);
- if (!attrs->split)
- n = snprintf(name, len, "p%u", attrs->phys.port_number);
- else
- n = snprintf(name, len, "p%us%u",
- attrs->phys.port_number,
- attrs->phys.split_subport_number);
-
break;
case DEVLINK_PORT_FLAVOUR_CPU:
case DEVLINK_PORT_FLAVOUR_DSA:
@@ -9381,6 +9373,8 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
attrs->pci_sf.sf);
break;
+ case DEVLINK_PORT_FLAVOUR_VIRTUAL:
+ return -EOPNOTSUPP;
}
if (n >= len)
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 2aadbfc5193b..4b2415d34873 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1504,7 +1504,7 @@ __be32 flow_get_u32_dst(const struct flow_keys *flow)
}
EXPORT_SYMBOL(flow_get_u32_dst);
-/* Sort the source and destination IP (and the ports if the IP are the same),
+/* Sort the source and destination IP and the ports,
* to have consistent hash within the two directions
*/
static inline void __flow_hash_consistentify(struct flow_keys *keys)
@@ -1515,11 +1515,11 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
addr_diff = (__force u32)keys->addrs.v4addrs.dst -
(__force u32)keys->addrs.v4addrs.src;
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0)
swap(keys->addrs.v4addrs.src, keys->addrs.v4addrs.dst);
+
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
@@ -1527,13 +1527,13 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
addr_diff = memcmp(&keys->addrs.v6addrs.dst,
&keys->addrs.v6addrs.src,
sizeof(keys->addrs.v6addrs.dst));
- if ((addr_diff < 0) ||
- (addr_diff == 0 &&
- ((__force u16)keys->ports.dst <
- (__force u16)keys->ports.src))) {
+ if (addr_diff < 0) {
for (i = 0; i < 4; i++)
swap(keys->addrs.v6addrs.src.s6_addr32[i],
keys->addrs.v6addrs.dst.s6_addr32[i]);
+ }
+ if ((__force u16)keys->ports.dst <
+ (__force u16)keys->ports.src) {
swap(keys->ports.src, keys->ports.dst);
}
break;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index f63de967ac25..fc7942c0dddc 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -663,7 +663,7 @@ static void skb_release_data(struct sk_buff *skb)
if (skb->cloned &&
atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1,
&shinfo->dataref))
- return;
+ goto exit;
skb_zcopy_clear(skb, true);
@@ -674,6 +674,17 @@ static void skb_release_data(struct sk_buff *skb)
kfree_skb_list(shinfo->frag_list);
skb_free_head(skb);
+exit:
+ /* When we clone an SKB we copy the reycling bit. The pp_recycle
+ * bit is only set on the head though, so in order to avoid races
+ * while trying to recycle fragments on __skb_frag_unref() we need
+ * to make one SKB responsible for triggering the recycle path.
+ * So disable the recycling bit if an SKB is cloned and we have
+ * additional references to to the fragmented part of the SKB.
+ * Eventually the last SKB will have the recycling bit set and it's
+ * dataref set to 0, which will trigger the recycling
+ */
+ skb->pp_recycle = 0;
}
/*
@@ -3011,8 +3022,11 @@ skb_zerocopy_headlen(const struct sk_buff *from)
if (!from->head_frag ||
skb_headlen(from) < L1_CACHE_BYTES ||
- skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS)
+ skb_shinfo(from)->nr_frags >= MAX_SKB_FRAGS) {
hlen = skb_headlen(from);
+ if (!hlen)
+ hlen = from->len;
+ }
if (skb_has_frag_list(from))
hlen = from->len;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 9b6160a191f8..2d6249b28928 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -508,10 +508,8 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
if (skb_linearize(skb))
return -EAGAIN;
num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
- if (unlikely(num_sge < 0)) {
- kfree(msg);
+ if (unlikely(num_sge < 0))
return num_sge;
- }
copied = skb->len;
msg->sg.start = 0;
@@ -530,6 +528,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
{
struct sock *sk = psock->sk;
struct sk_msg *msg;
+ int err;
/* If we are receiving on the same sock skb->sk is already assigned,
* skip memory accounting and owner transition seeing it already set
@@ -548,7 +547,10 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
* into user buffers.
*/
skb_set_owner_r(skb, sk);
- return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
/* Puts an skb on the ingress queue of the socket already assigned to the
@@ -559,12 +561,16 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
{
struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
struct sock *sk = psock->sk;
+ int err;
if (unlikely(!msg))
return -EAGAIN;
sk_msg_init(msg);
skb_set_owner_r(skb, sk);
- return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ if (err < 0)
+ kfree(msg);
+ return err;
}
static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
@@ -578,29 +584,42 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
return sk_psock_skb_ingress(psock, skb);
}
-static void sock_drop(struct sock *sk, struct sk_buff *skb)
+static void sk_psock_skb_state(struct sk_psock *psock,
+ struct sk_psock_work_state *state,
+ struct sk_buff *skb,
+ int len, int off)
{
- sk_drops_add(sk, skb);
- kfree_skb(skb);
+ spin_lock_bh(&psock->ingress_lock);
+ if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
+ state->skb = skb;
+ state->len = len;
+ state->off = off;
+ } else {
+ sock_drop(psock->sk, skb);
+ }
+ spin_unlock_bh(&psock->ingress_lock);
}
static void sk_psock_backlog(struct work_struct *work)
{
struct sk_psock *psock = container_of(work, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
bool ingress;
u32 len, off;
int ret;
mutex_lock(&psock->work_mutex);
- if (state->skb) {
+ if (unlikely(state->skb)) {
+ spin_lock_bh(&psock->ingress_lock);
skb = state->skb;
len = state->len;
off = state->off;
state->skb = NULL;
- goto start;
+ spin_unlock_bh(&psock->ingress_lock);
}
+ if (skb)
+ goto start;
while ((skb = skb_dequeue(&psock->ingress_skb))) {
len = skb->len;
@@ -615,9 +634,8 @@ start:
len, ingress);
if (ret <= 0) {
if (ret == -EAGAIN) {
- state->skb = skb;
- state->len = len;
- state->off = off;
+ sk_psock_skb_state(psock, state, skb,
+ len, off);
goto end;
}
/* Hard errors break pipe and stop xmit. */
@@ -716,6 +734,11 @@ static void __sk_psock_zap_ingress(struct sk_psock *psock)
skb_bpf_redirect_clear(skb);
sock_drop(psock->sk, skb);
}
+ kfree_skb(psock->work_state.skb);
+ /* We null the skb here to ensure that calls to sk_psock_backlog
+ * do not pick up the free'd skb.
+ */
+ psock->work_state.skb = NULL;
__sk_psock_purge_ingress_msg(psock);
}
@@ -767,8 +790,6 @@ static void sk_psock_destroy(struct work_struct *work)
void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
{
- sk_psock_stop(psock, false);
-
write_lock_bh(&sk->sk_callback_lock);
sk_psock_restore_proto(sk, psock);
rcu_assign_sk_user_data(sk, NULL);
@@ -778,6 +799,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
sk_psock_stop_verdict(sk, psock);
write_unlock_bh(&sk->sk_callback_lock);
+ sk_psock_stop(psock, false);
+
INIT_RCU_WORK(&psock->rwork, sk_psock_destroy);
queue_rcu_work(system_wq, &psock->rwork);
}
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 5dbd45dc35ad..dc92a67baea3 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -816,7 +816,7 @@ static int dn_auto_bind(struct socket *sock)
static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
if (scp->state != DN_CR)
@@ -826,11 +826,11 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
scp->segsize_loc = dst_metric_advmss(__sk_dst_get(sk));
dn_send_conn_conf(sk, allocation);
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
@@ -844,9 +844,8 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
} else if (scp->state != DN_CC) {
@@ -858,7 +857,7 @@ static int dn_confirm_accept(struct sock *sk, long *timeo, gfp_t allocation)
static int dn_wait_run(struct sock *sk, long *timeo)
{
struct dn_scp *scp = DN_SK(sk);
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err = 0;
if (scp->state == DN_RUN)
@@ -867,11 +866,11 @@ static int dn_wait_run(struct sock *sk, long *timeo)
if (!*timeo)
return -EALREADY;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
if (scp->state == DN_CI || scp->state == DN_CC)
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
lock_sock(sk);
err = 0;
if (scp->state == DN_RUN)
@@ -885,9 +884,8 @@ static int dn_wait_run(struct sock *sk, long *timeo)
err = -ETIMEDOUT;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
out:
if (err == 0) {
sk->sk_socket->state = SS_CONNECTED;
@@ -1032,16 +1030,16 @@ static void dn_user_copy(struct sk_buff *skb, struct optdata_dn *opt)
static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
{
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct sk_buff *skb = NULL;
int err = 0;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ add_wait_queue(sk_sleep(sk), &wait);
for(;;) {
release_sock(sk);
skb = skb_dequeue(&sk->sk_receive_queue);
if (skb == NULL) {
- *timeo = schedule_timeout(*timeo);
+ *timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, *timeo);
skb = skb_dequeue(&sk->sk_receive_queue);
}
lock_sock(sk);
@@ -1056,9 +1054,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
err = -EAGAIN;
if (!*timeo)
break;
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
- finish_wait(sk_sleep(sk), &wait);
+ remove_wait_queue(sk_sleep(sk), &wait);
return skb == NULL ? ERR_PTR(err) : skb;
}
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index ffbba1e71551..532085da8d8f 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1808,6 +1808,7 @@ void dsa_slave_setup_tagger(struct net_device *slave)
struct dsa_slave_priv *p = netdev_priv(slave);
const struct dsa_port *cpu_dp = dp->cpu_dp;
struct net_device *master = cpu_dp->master;
+ const struct dsa_switch *ds = dp->ds;
slave->needed_headroom = cpu_dp->tag_ops->needed_headroom;
slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom;
@@ -1819,6 +1820,14 @@ void dsa_slave_setup_tagger(struct net_device *slave)
slave->needed_tailroom += master->needed_tailroom;
p->xmit = cpu_dp->tag_ops->xmit;
+
+ slave->features = master->vlan_features | NETIF_F_HW_TC;
+ if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
+ slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+ slave->hw_features |= NETIF_F_HW_TC;
+ slave->features |= NETIF_F_LLTX;
+ if (slave->needed_tailroom)
+ slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST);
}
static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
@@ -1881,11 +1890,6 @@ int dsa_slave_create(struct dsa_port *port)
if (slave_dev == NULL)
return -ENOMEM;
- slave_dev->features = master->vlan_features | NETIF_F_HW_TC;
- if (ds->ops->port_vlan_add && ds->ops->port_vlan_del)
- slave_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
- slave_dev->hw_features |= NETIF_F_HW_TC;
- slave_dev->features |= NETIF_F_LLTX;
slave_dev->ethtool_ops = &dsa_slave_ethtool_ops;
if (!is_zero_ether_addr(port->mac))
ether_addr_copy(slave_dev->dev_addr, port->mac);
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index 53565f48934c..a201ccf2435d 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -53,6 +53,9 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
u8 *tag;
u8 *addr;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
@@ -114,6 +117,9 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
u8 *addr;
u16 val;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
@@ -164,6 +170,9 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
u8 *addr;
u8 *tag;
+ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))
+ return NULL;
+
/* Tag encoding */
tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
addr = skb_mac_header(skb);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0dca00745ac3..be75b409445c 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -390,7 +390,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
- skb_reset_network_header(skb);
+ skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0);
err = IP_ECN_decapsulate(iph, skb);
if (unlikely(err)) {
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index f26916a62f25..d3e9386b493e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -503,7 +503,7 @@ static int __init tcp_bpf_v4_build_proto(void)
tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV4], &tcp_prot);
return 0;
}
-core_initcall(tcp_bpf_v4_build_proto);
+late_initcall(tcp_bpf_v4_build_proto);
static int tcp_bpf_assert_proto_ops(struct proto *ops)
{
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 47c32604d38f..25fa4c01a17f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -507,8 +507,18 @@ void tcp_fastopen_active_disable(struct sock *sk)
{
struct net *net = sock_net(sk);
+ if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+ return;
+
+ /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
+ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies);
+
+ /* Paired with smp_rmb() in tcp_fastopen_active_should_disable().
+ * We want net->ipv4.tfo_active_disable_stamp to be updated first.
+ */
+ smp_mb__before_atomic();
atomic_inc(&net->ipv4.tfo_active_disable_times);
- net->ipv4.tfo_active_disable_stamp = jiffies;
+
NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE);
}
@@ -519,17 +529,27 @@ void tcp_fastopen_active_disable(struct sock *sk)
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
- int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
unsigned long timeout;
+ int tfo_da_times;
int multiplier;
+ if (!tfo_bh_timeout)
+ return false;
+
+ tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
if (!tfo_da_times)
return false;
+ /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */
+ smp_rmb();
+
/* Limit timeout to max: 2^6 * initial timeout */
multiplier = 1 << min(tfo_da_times - 1, 6);
- timeout = multiplier * tfo_bh_timeout * HZ;
- if (time_before(jiffies, sock_net(sk)->ipv4.tfo_active_disable_stamp + timeout))
+
+ /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */
+ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) +
+ multiplier * tfo_bh_timeout * HZ;
+ if (time_before(jiffies, timeout))
return true;
/* Mark check bit so we can check for successful active TFO
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b9dc2d6197be..a692626c19e4 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2965,7 +2965,7 @@ static int __net_init tcp_sk_init(struct net *net)
net->ipv4.sysctl_tcp_comp_sack_nr = 44;
net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE;
spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock);
- net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60;
+ net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0;
atomic_set(&net->ipv4.tfo_active_disable_times, 0);
/* Reno is always built in */
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 62cd4cd52e84..1a742b710e54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -645,10 +645,12 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb, u32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -659,18 +661,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
iph->saddr, uh->dest, skb->dev->ifindex, 0,
udptable, NULL);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk)
sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));
@@ -707,15 +719,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udp_encap_needed_key)) {
- sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
+ sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index 45b8782aec0c..9f5a5cdc38e6 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -134,7 +134,7 @@ static int __init udp_bpf_v4_build_proto(void)
udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV4], &udp_prot);
return 0;
}
-core_initcall(udp_bpf_v4_build_proto);
+late_initcall(udp_bpf_v4_build_proto);
int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
{
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 01bea76e3891..8e6ca9ad6812 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -74,7 +74,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
if (likely(nskb)) {
if (skb->sk)
- skb_set_owner_w(skb, skb->sk);
+ skb_set_owner_w(nskb, skb->sk);
consume_skb(skb);
} else {
kfree_skb(skb);
@@ -549,9 +549,10 @@ int ip6_forward(struct sk_buff *skb)
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
- if (proxied > 0)
+ if (proxied > 0) {
+ hdr->hop_limit--;
return ip6_input(skb);
- else if (proxied < 0) {
+ } else if (proxied < 0) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 7b756a7dc036..b6ddf23d3833 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3769,7 +3769,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
err = PTR_ERR(rt->fib6_metrics);
/* Do not leave garbage there. */
rt->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
- goto out;
+ goto out_free;
}
if (cfg->fc_flags & RTF_ADDRCONF)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 0cc7ba531b34..c5e15e94bb00 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -502,12 +502,14 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
+ struct sock *sk,
struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, __be32 info)
{
+ int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
- struct sock *sk;
+ struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
@@ -518,18 +520,28 @@ static struct sock *__udp6_lib_err_encap(struct net *net,
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
+ if (sk) {
+ up = udp_sk(sk);
+
+ lookup = READ_ONCE(up->encap_err_lookup);
+ if (lookup && lookup(sk, skb))
+ sk = NULL;
+
+ goto out;
+ }
+
sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
&hdr->saddr, uh->dest,
inet6_iif(skb), 0, udptable, skb);
if (sk) {
- int (*lookup)(struct sock *sk, struct sk_buff *skb);
- struct udp_sock *up = udp_sk(sk);
+ up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
+out:
if (!sk) {
sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
offset, info));
@@ -558,16 +570,17 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
+
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
- sk = ERR_PTR(-ENOENT);
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
- udptable, skb,
+ udptable, sk, skb,
opt, type, code, info);
if (!sk)
return 0;
- }
+ } else
+ sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 7180979114e4..ac5cadd02cfa 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -98,8 +98,16 @@ static inline u8 llc_ui_header_len(struct sock *sk, struct sockaddr_llc *addr)
{
u8 rc = LLC_PDU_LEN_U;
- if (addr->sllc_test || addr->sllc_xid)
+ if (addr->sllc_test)
rc = LLC_PDU_LEN_U;
+ else if (addr->sllc_xid)
+ /* We need to expand header to sizeof(struct llc_xid_info)
+ * since llc_pdu_init_as_xid_cmd() sets 4,5,6 bytes of LLC header
+ * as XID PDU. In llc_ui_sendmsg() we reserved header size and then
+ * filled all other space with user data. If we won't reserve this
+ * bytes, llc_pdu_init_as_xid_cmd() will overwrite user data
+ */
+ rc = LLC_PDU_LEN_U_XID;
else if (sk->sk_type == SOCK_STREAM)
rc = LLC_PDU_LEN_I;
return rc;
diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index b554f26c68ee..79d1cef8f15a 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -79,7 +79,7 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
struct llc_sap_state_ev *ev = llc_sap_ev(skb);
int rc;
- llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
+ llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap,
ev->daddr.lsap, LLC_PDU_CMD);
llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 84cc7733ea66..4e6f11e63df3 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -152,6 +152,8 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
struct vif_params *params)
{
struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+ struct ieee80211_local *local = sdata->local;
+ struct sta_info *sta;
int ret;
ret = ieee80211_if_change_type(sdata, type);
@@ -162,7 +164,24 @@ static int ieee80211_change_iface(struct wiphy *wiphy,
RCU_INIT_POINTER(sdata->u.vlan.sta, NULL);
ieee80211_check_fast_rx_iface(sdata);
} else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) {
+ struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+
+ if (params->use_4addr == ifmgd->use_4addr)
+ return 0;
+
sdata->u.mgd.use_4addr = params->use_4addr;
+ if (!ifmgd->associated)
+ return 0;
+
+ mutex_lock(&local->sta_mtx);
+ sta = sta_info_get(sdata, ifmgd->bssid);
+ if (sta)
+ drv_sta_set_4addr(local, sdata, &sta->sta,
+ params->use_4addr);
+ mutex_unlock(&local->sta_mtx);
+
+ if (params->use_4addr)
+ ieee80211_send_4addr_nullfunc(local, sdata);
}
if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 22549b95d1aa..30ce6d2ec7ce 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2201,6 +2201,8 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t);
void ieee80211_send_nullfunc(struct ieee80211_local *local,
struct ieee80211_sub_if_data *sdata,
bool powersave);
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata);
void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a00f11a33699..c0ea3b1aa9e1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1095,8 +1095,8 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
ieee80211_tx_skb(sdata, skb);
}
-static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
- struct ieee80211_sub_if_data *sdata)
+void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
+ struct ieee80211_sub_if_data *sdata)
{
struct sk_buff *skb;
struct ieee80211_hdr *nullfunc;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 771921c057e8..2563473b5cf1 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -730,7 +730,8 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local,
* Need to make a copy and possibly remove radiotap header
* and FCS from the original.
*/
- skb = skb_copy_expand(*origskb, needed_headroom, 0, GFP_ATOMIC);
+ skb = skb_copy_expand(*origskb, needed_headroom + NET_SKB_PAD,
+ 0, GFP_ATOMIC);
if (!skb)
return NULL;
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e96981144358..8509778ff31f 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1147,6 +1147,29 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
return queued;
}
+static void
+ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
+ struct sta_info *sta,
+ struct sk_buff *skb)
+{
+ struct rate_control_ref *ref = sdata->local->rate_ctrl;
+ u16 tid;
+
+ if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
+ return;
+
+ if (!sta || !sta->sta.ht_cap.ht_supported ||
+ !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
+ skb->protocol == sdata->control_port_protocol)
+ return;
+
+ tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
+ if (likely(sta->ampdu_mlme.tid_tx[tid]))
+ return;
+
+ ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
+}
+
/*
* initialises @tx
* pass %NULL for the station if unknown, a valid pointer if known
@@ -1160,6 +1183,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
struct ieee80211_local *local = sdata->local;
struct ieee80211_hdr *hdr;
struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ bool aggr_check = false;
int tid;
memset(tx, 0, sizeof(*tx));
@@ -1188,8 +1212,10 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
} else if (tx->sdata->control_port_protocol == tx->skb->protocol) {
tx->sta = sta_info_get_bss(sdata, hdr->addr1);
}
- if (!tx->sta && !is_multicast_ether_addr(hdr->addr1))
+ if (!tx->sta && !is_multicast_ether_addr(hdr->addr1)) {
tx->sta = sta_info_get(sdata, hdr->addr1);
+ aggr_check = true;
+ }
}
if (tx->sta && ieee80211_is_data_qos(hdr->frame_control) &&
@@ -1199,8 +1225,12 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
struct tid_ampdu_tx *tid_tx;
tid = ieee80211_get_tid(hdr);
-
tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ if (!tid_tx && aggr_check) {
+ ieee80211_aggr_check(sdata, tx->sta, skb);
+ tid_tx = rcu_dereference(tx->sta->ampdu_mlme.tid_tx[tid]);
+ }
+
if (tid_tx) {
bool queued;
@@ -4120,29 +4150,6 @@ void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac)
}
EXPORT_SYMBOL(ieee80211_txq_schedule_start);
-static void
-ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
- struct sta_info *sta,
- struct sk_buff *skb)
-{
- struct rate_control_ref *ref = sdata->local->rate_ctrl;
- u16 tid;
-
- if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
- return;
-
- if (!sta || !sta->sta.ht_cap.ht_supported ||
- !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
- skb->protocol == sdata->control_port_protocol)
- return;
-
- tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
- if (likely(sta->ampdu_mlme.tid_tx[tid]))
- return;
-
- ieee80211_start_tx_ba_session(&sta->sta, tid, 0);
-}
-
void __ieee80211_subif_start_xmit(struct sk_buff *skb,
struct net_device *dev,
u32 info_flags,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 83c52df85870..5c03e5106751 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -670,8 +670,13 @@ bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
return false;
tstamp = nf_conn_tstamp_find(ct);
- if (tstamp && tstamp->stop == 0)
+ if (tstamp) {
+ s32 timeout = ct->timeout - nfct_time_stamp;
+
tstamp->stop = ktime_get_real_ns();
+ if (timeout < 0)
+ tstamp->stop -= jiffies_to_nsecs(-timeout);
+ }
if (nf_conntrack_event_report(IPCT_DESTROY, ct,
portid, report) < 0) {
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 1e50908b1b7e..551976e4284c 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -331,7 +331,11 @@ EXPORT_SYMBOL_GPL(flow_offload_add);
void flow_offload_refresh(struct nf_flowtable *flow_table,
struct flow_offload *flow)
{
- flow->timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ u32 timeout;
+
+ timeout = nf_flowtable_time_stamp + flow_offload_get_timeout(flow);
+ if (READ_ONCE(flow->timeout) != timeout)
+ WRITE_ONCE(flow->timeout, timeout);
if (likely(!nf_flowtable_hw_offload(flow_table)))
return;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index de182d1f7c4e..081437dd75b7 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8445,6 +8445,16 @@ static int nf_tables_commit_audit_alloc(struct list_head *adl,
return 0;
}
+static void nf_tables_commit_audit_free(struct list_head *adl)
+{
+ struct nft_audit_data *adp, *adn;
+
+ list_for_each_entry_safe(adp, adn, adl, list) {
+ list_del(&adp->list);
+ kfree(adp);
+ }
+}
+
static void nf_tables_commit_audit_collect(struct list_head *adl,
struct nft_table *table, u32 op)
{
@@ -8509,6 +8519,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
ret = nf_tables_commit_audit_alloc(&adl, trans->ctx.table);
if (ret) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
if (trans->msg_type == NFT_MSG_NEWRULE ||
@@ -8518,6 +8529,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
ret = nf_tables_commit_chain_prepare(net, chain);
if (ret < 0) {
nf_tables_commit_chain_prepare_cancel(net);
+ nf_tables_commit_audit_free(&adl);
return ret;
}
}
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index 50b4e3c9347a..202f57d17bab 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -174,7 +174,9 @@ static const struct nf_hook_entries *
nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev)
{
const struct nf_hook_entries *hook_head = NULL;
+#ifdef CONFIG_NETFILTER_INGRESS
struct net_device *netdev;
+#endif
switch (pf) {
case NFPROTO_IPV4:
diff --git a/net/netfilter/nft_last.c b/net/netfilter/nft_last.c
index 8088b99f2ee3..304e33cbed9b 100644
--- a/net/netfilter/nft_last.c
+++ b/net/netfilter/nft_last.c
@@ -48,24 +48,30 @@ static void nft_last_eval(const struct nft_expr *expr,
{
struct nft_last_priv *priv = nft_expr_priv(expr);
- priv->last_jiffies = jiffies;
- priv->last_set = 1;
+ if (READ_ONCE(priv->last_jiffies) != jiffies)
+ WRITE_ONCE(priv->last_jiffies, jiffies);
+ if (READ_ONCE(priv->last_set) == 0)
+ WRITE_ONCE(priv->last_set, 1);
}
static int nft_last_dump(struct sk_buff *skb, const struct nft_expr *expr)
{
struct nft_last_priv *priv = nft_expr_priv(expr);
+ unsigned long last_jiffies = READ_ONCE(priv->last_jiffies);
+ u32 last_set = READ_ONCE(priv->last_set);
__be64 msecs;
- if (time_before(jiffies, priv->last_jiffies))
- priv->last_set = 0;
+ if (time_before(jiffies, last_jiffies)) {
+ WRITE_ONCE(priv->last_set, 0);
+ last_set = 0;
+ }
- if (priv->last_set)
- msecs = nf_jiffies64_to_msecs(jiffies - priv->last_jiffies);
+ if (last_set)
+ msecs = nf_jiffies64_to_msecs(jiffies - last_jiffies);
else
msecs = 0;
- if (nla_put_be32(skb, NFTA_LAST_SET, htonl(priv->last_set)) ||
+ if (nla_put_be32(skb, NFTA_LAST_SET, htonl(last_set)) ||
nla_put_be64(skb, NFTA_LAST_MSECS, msecs, NFTA_LAST_PAD))
goto nla_put_failure;
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index 0840c635b752..be1595d6979d 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -201,7 +201,9 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
alen = sizeof_field(struct nf_nat_range, min_addr.ip6);
break;
default:
- return -EAFNOSUPPORT;
+ if (tb[NFTA_NAT_REG_ADDR_MIN])
+ return -EAFNOSUPPORT;
+ break;
}
priv->family = family;
diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c
index 9115f8a7dd45..a8da88db7893 100644
--- a/net/netrom/nr_timer.c
+++ b/net/netrom/nr_timer.c
@@ -121,11 +121,9 @@ static void nr_heartbeat_expiry(struct timer_list *t)
is accepted() it isn't 'dead' so doesn't get removed. */
if (sock_flag(sk, SOCK_DESTROY) ||
(sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) {
- sock_hold(sk);
bh_unlock_sock(sk);
nr_destroy_socket(sk);
- sock_put(sk);
- return;
+ goto out;
}
break;
@@ -146,6 +144,8 @@ static void nr_heartbeat_expiry(struct timer_list *t)
nr_start_heartbeat(sk);
bh_unlock_sock(sk);
+out:
+ sock_put(sk);
}
static void nr_t2timer_expiry(struct timer_list *t)
@@ -159,6 +159,7 @@ static void nr_t2timer_expiry(struct timer_list *t)
nr_enquiry_response(sk);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t4timer_expiry(struct timer_list *t)
@@ -169,6 +170,7 @@ static void nr_t4timer_expiry(struct timer_list *t)
bh_lock_sock(sk);
nr_sk(sk)->condition &= ~NR_COND_PEER_RX_BUSY;
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_idletimer_expiry(struct timer_list *t)
@@ -197,6 +199,7 @@ static void nr_idletimer_expiry(struct timer_list *t)
sock_set_flag(sk, SOCK_DEAD);
}
bh_unlock_sock(sk);
+ sock_put(sk);
}
static void nr_t1timer_expiry(struct timer_list *t)
@@ -209,8 +212,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_1:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_CONNREQ);
@@ -220,8 +222,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_2:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_write_internal(sk, NR_DISCREQ);
@@ -231,8 +232,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
case NR_STATE_3:
if (nr->n2count == nr->n2) {
nr_disconnect(sk, ETIMEDOUT);
- bh_unlock_sock(sk);
- return;
+ goto out;
} else {
nr->n2count++;
nr_requeue_frames(sk);
@@ -241,5 +241,7 @@ static void nr_t1timer_expiry(struct timer_list *t)
}
nr_start_t1timer(sk);
+out:
bh_unlock_sock(sk);
+ sock_put(sk);
}
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index e6f4a6202f82..171b7f3be6ef 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -518,8 +518,10 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
if (!ipc)
goto err;
- if (sock_queue_rcv_skb(&ipc->sk, skb))
+ if (sock_queue_rcv_skb(&ipc->sk, skb)) {
+ qrtr_port_put(ipc);
goto err;
+ }
qrtr_port_put(ipc);
}
@@ -839,6 +841,8 @@ static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb,
ipc = qrtr_port_lookup(to->sq_port);
if (!ipc || &ipc->sk == skb->sk) { /* do not send to self */
+ if (ipc)
+ qrtr_port_put(ipc);
kfree_skb(skb);
return -ENODEV;
}
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 81a1c67335be..8d17a543cc9f 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -6,6 +6,7 @@
*/
#include <linux/module.h>
+#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
@@ -33,6 +34,13 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
tcf_lastuse_update(&d->tcf_tm);
bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
+ action = READ_ONCE(d->tcf_action);
+ if (unlikely(action == TC_ACT_SHOT))
+ goto drop;
+
+ if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
+ return action;
+
/* XXX: if you are going to edit more fields beyond ethernet header
* (example when you add IP header replacement or vlan swap)
* then MAX_EDIT_LEN needs to change appropriately
@@ -41,10 +49,6 @@ static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
if (unlikely(err)) /* best policy is to drop on the floor */
goto drop;
- action = READ_ONCE(d->tcf_action);
- if (unlikely(action == TC_ACT_SHOT))
- goto drop;
-
p = rcu_dereference_bh(d->skbmod_p);
flags = p->flags;
if (flags & SKBMOD_F_DMAC)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d73b5c5514a9..e3e79e9bd706 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2904,7 +2904,7 @@ replay:
break;
case RTM_GETCHAIN:
err = tc_chain_notify(chain, skb, n->nlmsg_seq,
- n->nlmsg_seq, n->nlmsg_type, true);
+ n->nlmsg_flags, n->nlmsg_type, true);
if (err < 0)
NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
break;
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 5b274534264c..e9a8a2c86bbd 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -278,6 +278,8 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r,
TCA_TCINDEX_POLICE);
}
+static void tcindex_free_perfect_hash(struct tcindex_data *cp);
+
static void tcindex_partial_destroy_work(struct work_struct *work)
{
struct tcindex_data *p = container_of(to_rcu_work(work),
@@ -285,7 +287,8 @@ static void tcindex_partial_destroy_work(struct work_struct *work)
rwork);
rtnl_lock();
- kfree(p->perfect);
+ if (p->perfect)
+ tcindex_free_perfect_hash(p);
kfree(p);
rtnl_unlock();
}
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 6f8319b828b0..fe74c5f95630 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -860,6 +860,8 @@ int sctp_auth_set_key(struct sctp_endpoint *ep,
if (replace) {
list_del_init(&shkey->key_list);
sctp_auth_shkey_release(shkey);
+ if (asoc && asoc->active_key_id == auth_key->sca_keynumber)
+ sctp_auth_asoc_init_active_key(asoc, GFP_KERNEL);
}
list_add(&cur_key->key_list, sh_keys);
diff --git a/net/sctp/input.c b/net/sctp/input.c
index eb3c2a34a31c..5ef86fdb1176 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -1203,7 +1203,7 @@ static struct sctp_association *__sctp_rcv_asconf_lookup(
if (unlikely(!af))
return NULL;
- if (af->from_addr_param(&paddr, param, peer_port, 0))
+ if (!af->from_addr_param(&paddr, param, peer_port, 0))
return NULL;
return __sctp_lookup_association(net, laddr, &paddr, transportp);
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index e48dd909dee5..470dbdc27d58 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -100,8 +100,9 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
list_for_each_entry_safe(addr, temp,
&net->sctp.local_addr_list, list) {
if (addr->a.sa.sa_family == AF_INET6 &&
- ipv6_addr_equal(&addr->a.v6.sin6_addr,
- &ifa->addr)) {
+ ipv6_addr_equal(&addr->a.v6.sin6_addr,
+ &ifa->addr) &&
+ addr->a.v6.sin6_scope_id == ifa->idev->dev->ifindex) {
sctp_addr_wq_mgmt(net, addr, SCTP_ADDR_DEL);
found = 1;
addr->valid = 0;
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 9032ce60d50e..4dfb5ea82b05 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -104,8 +104,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
if (asoc->param_flags & SPP_PMTUD_ENABLE)
sctp_assoc_sync_pmtu(asoc);
} else if (!sctp_transport_pl_enabled(tp) &&
- !sctp_transport_pmtu_check(tp)) {
- if (asoc->param_flags & SPP_PMTUD_ENABLE)
+ asoc->param_flags & SPP_PMTUD_ENABLE) {
+ if (!sctp_transport_pmtu_check(tp))
sctp_assoc_sync_pmtu(asoc);
}
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 09a8f23ec709..32df65f68c12 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1109,12 +1109,12 @@ enum sctp_disposition sctp_sf_send_probe(struct net *net,
if (!sctp_transport_pl_enabled(transport))
return SCTP_DISPOSITION_CONSUME;
- sctp_transport_pl_send(transport);
-
- reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
- if (!reply)
- return SCTP_DISPOSITION_NOMEM;
- sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ if (sctp_transport_pl_send(transport)) {
+ reply = sctp_make_heartbeat(asoc, transport, transport->pl.probe_size);
+ if (!reply)
+ return SCTP_DISPOSITION_NOMEM;
+ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(reply));
+ }
sctp_add_cmd_sf(commands, SCTP_CMD_PROBE_TIMER_UPDATE,
SCTP_TRANSPORT(transport));
@@ -1274,8 +1274,7 @@ enum sctp_disposition sctp_sf_backbeat_8_3(struct net *net,
!sctp_transport_pl_enabled(link))
return SCTP_DISPOSITION_DISCARD;
- sctp_transport_pl_recv(link);
- if (link->pl.state == SCTP_PL_COMPLETE)
+ if (sctp_transport_pl_recv(link))
return SCTP_DISPOSITION_CONSUME;
return sctp_sf_send_probe(net, ep, asoc, type, link, commands);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index e64e01f61b11..6b937bfd4751 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4577,6 +4577,10 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
}
if (optlen > 0) {
+ /* Trim it to the biggest size sctp sockopt may need if necessary */
+ optlen = min_t(unsigned int, optlen,
+ PAGE_ALIGN(USHRT_MAX +
+ sizeof(__u16) * sizeof(struct sctp_reset_streams)));
kopt = memdup_sockptr(optval, optlen);
if (IS_ERR(kopt))
return PTR_ERR(kopt);
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 397a6244dd97..a3d3ca6dd63d 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -258,16 +258,13 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
sctp_transport_pl_update(transport);
}
-void sctp_transport_pl_send(struct sctp_transport *t)
+bool sctp_transport_pl_send(struct sctp_transport *t)
{
- pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
- __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
-
- if (t->pl.probe_count < SCTP_MAX_PROBES) {
- t->pl.probe_count++;
- return;
- }
+ if (t->pl.probe_count < SCTP_MAX_PROBES)
+ goto out;
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
+ t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
if (t->pl.probe_size == SCTP_BASE_PLPMTU) { /* BASE_PLPMTU Confirmation Failed */
t->pl.state = SCTP_PL_ERROR; /* Base -> Error */
@@ -299,14 +296,27 @@ void sctp_transport_pl_send(struct sctp_transport *t)
sctp_assoc_sync_pmtu(t->asoc);
}
}
- t->pl.probe_count = 1;
+
+out:
+ if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count < 30 &&
+ !t->pl.probe_count && t->pl.last_rtx_chunks == t->asoc->rtx_data_chunks) {
+ t->pl.raise_count++;
+ return false;
+ }
+
+ pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
+ __func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+
+ t->pl.probe_count++;
+ return true;
}
-void sctp_transport_pl_recv(struct sctp_transport *t)
+bool sctp_transport_pl_recv(struct sctp_transport *t)
{
pr_debug("%s: PLPMTUD: transport: %p, state: %d, pmtu: %d, size: %d, high: %d\n",
__func__, t, t->pl.state, t->pl.pmtu, t->pl.probe_size, t->pl.probe_high);
+ t->pl.last_rtx_chunks = t->asoc->rtx_data_chunks;
t->pl.pmtu = t->pl.probe_size;
t->pl.probe_count = 0;
if (t->pl.state == SCTP_PL_BASE) {
@@ -323,7 +333,7 @@ void sctp_transport_pl_recv(struct sctp_transport *t)
if (!t->pl.probe_high) {
t->pl.probe_size = min(t->pl.probe_size + SCTP_PL_BIG_STEP,
SCTP_MAX_PLPMTU);
- return;
+ return false;
}
t->pl.probe_size += SCTP_PL_MIN_STEP;
if (t->pl.probe_size >= t->pl.probe_high) {
@@ -335,14 +345,13 @@ void sctp_transport_pl_recv(struct sctp_transport *t)
t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
sctp_assoc_sync_pmtu(t->asoc);
}
- } else if (t->pl.state == SCTP_PL_COMPLETE) {
- t->pl.raise_count++;
- if (t->pl.raise_count == 30) {
- /* Raise probe_size again after 30 * interval in Search Complete */
- t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
- t->pl.probe_size += SCTP_PL_MIN_STEP;
- }
+ } else if (t->pl.state == SCTP_PL_COMPLETE && t->pl.raise_count == 30) {
+ /* Raise probe_size again after 30 * interval in Search Complete */
+ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
+ t->pl.probe_size += SCTP_PL_MIN_STEP;
}
+
+ return t->pl.state == SCTP_PL_COMPLETE;
}
static bool sctp_transport_pl_toobig(struct sctp_transport *t, u32 pmtu)
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index e5c43d4d5a75..c9391d38de85 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -898,16 +898,10 @@ static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
if (unlikely(!aead))
return -ENOKEY;
- /* Cow skb data if needed */
- if (likely(!skb_cloned(skb) &&
- (!skb_is_nonlinear(skb) || !skb_has_frag_list(skb)))) {
- nsg = 1 + skb_shinfo(skb)->nr_frags;
- } else {
- nsg = skb_cow_data(skb, 0, &unused);
- if (unlikely(nsg < 0)) {
- pr_err("RX: skb_cow_data() returned %d\n", nsg);
- return nsg;
- }
+ nsg = skb_cow_data(skb, 0, &unused);
+ if (unlikely(nsg < 0)) {
+ pr_err("RX: skb_cow_data() returned %d\n", nsg);
+ return nsg;
}
/* Allocate memory for the AEAD operation */
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 34a97ea36cc8..75b99b7eda22 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -158,6 +158,7 @@ static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack);
+static int tipc_wait_for_connect(struct socket *sock, long *timeo_p);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
@@ -1515,8 +1516,13 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
rc = 0;
}
- if (unlikely(syn && !rc))
+ if (unlikely(syn && !rc)) {
tipc_set_sk_state(sk, TIPC_CONNECTING);
+ if (timeout) {
+ timeout = msecs_to_jiffies(timeout);
+ tipc_wait_for_connect(sock, &timeout);
+ }
+ }
return rc ? rc : dlen;
}
@@ -1564,7 +1570,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
return -EMSGSIZE;
/* Handle implicit connection setup */
- if (unlikely(dest)) {
+ if (unlikely(dest && sk->sk_state == TIPC_OPEN)) {
rc = __tipc_sendmsg(sock, m, dlen);
if (dlen && dlen == rc) {
tsk->peer_caps = tipc_node_get_capabilities(net, dnode);
@@ -2646,7 +2652,7 @@ static int tipc_listen(struct socket *sock, int len)
static int tipc_wait_for_accept(struct socket *sock, long timeo)
{
struct sock *sk = sock->sk;
- DEFINE_WAIT(wait);
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
int err;
/* True wake-one mechanism for incoming connections: only
@@ -2655,12 +2661,12 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
* anymore, the common case will execute the loop only once.
*/
for (;;) {
- prepare_to_wait_exclusive(sk_sleep(sk), &wait,
- TASK_INTERRUPTIBLE);
if (timeo && skb_queue_empty(&sk->sk_receive_queue)) {
+ add_wait_queue(sk_sleep(sk), &wait);
release_sock(sk);
- timeo = schedule_timeout(timeo);
+ timeo = wait_woken(&wait, TASK_INTERRUPTIBLE, timeo);
lock_sock(sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
}
err = 0;
if (!skb_queue_empty(&sk->sk_receive_queue))
@@ -2672,7 +2678,6 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
if (signal_pending(current))
break;
}
- finish_wait(sk_sleep(sk), &wait);
return err;
}
@@ -2689,9 +2694,10 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
bool kern)
{
struct sock *new_sk, *sk = sock->sk;
- struct sk_buff *buf;
struct tipc_sock *new_tsock;
+ struct msghdr m = {NULL,};
struct tipc_msg *msg;
+ struct sk_buff *buf;
long timeo;
int res;
@@ -2737,19 +2743,17 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
}
/*
- * Respond to 'SYN-' by discarding it & returning 'ACK'-.
- * Respond to 'SYN+' by queuing it on new socket.
+ * Respond to 'SYN-' by discarding it & returning 'ACK'.
+ * Respond to 'SYN+' by queuing it on new socket & returning 'ACK'.
*/
if (!msg_data_sz(msg)) {
- struct msghdr m = {NULL,};
-
tsk_advance_rx_queue(sk);
- __tipc_sendstream(new_sock, &m, 0);
} else {
__skb_dequeue(&sk->sk_receive_queue);
__skb_queue_head(&new_sk->sk_receive_queue, buf);
skb_set_owner_r(buf, new_sk);
}
+ __tipc_sendstream(new_sock, &m, 0);
release_sock(new_sk);
exit:
release_sock(sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 23c92ad15c61..ba7ced947e51 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1526,6 +1526,53 @@ out:
return err;
}
+static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+
+ /*
+ * Garbage collection of unix sockets starts by selecting a set of
+ * candidate sockets which have reference only from being in flight
+ * (total_refs == inflight_refs). This condition is checked once during
+ * the candidate collection phase, and candidates are marked as such, so
+ * that non-candidates can later be ignored. While inflight_refs is
+ * protected by unix_gc_lock, total_refs (file count) is not, hence this
+ * is an instantaneous decision.
+ *
+ * Once a candidate, however, the socket must not be reinstalled into a
+ * file descriptor while the garbage collection is in progress.
+ *
+ * If the above conditions are met, then the directed graph of
+ * candidates (*) does not change while unix_gc_lock is held.
+ *
+ * Any operations that changes the file count through file descriptors
+ * (dup, close, sendmsg) does not change the graph since candidates are
+ * not installed in fds.
+ *
+ * Dequeing a candidate via recvmsg would install it into an fd, but
+ * that takes unix_gc_lock to decrement the inflight count, so it's
+ * serialized with garbage collection.
+ *
+ * MSG_PEEK is special in that it does not change the inflight count,
+ * yet does install the socket into an fd. The following lock/unlock
+ * pair is to ensure serialization with garbage collection. It must be
+ * done between incrementing the file count and installing the file into
+ * an fd.
+ *
+ * If garbage collection starts after the barrier provided by the
+ * lock/unlock, then it will see the elevated refcount and not mark this
+ * as a candidate. If a garbage collection is already in progress
+ * before the file count was incremented, then the lock/unlock pair will
+ * ensure that garbage collection is finished before progressing to
+ * installing the fd.
+ *
+ * (*) A -> B where B is on the queue of A or B is on the queue of C
+ * which is on the queue of listening socket A.
+ */
+ spin_lock(&unix_gc_lock);
+ spin_unlock(&unix_gc_lock);
+}
+
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
@@ -2175,7 +2222,7 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
sk_peek_offset_fwd(sk, size);
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
}
err = (flags & MSG_TRUNC) ? skb->len - skip : size;
@@ -2418,7 +2465,7 @@ unlock:
/* It is questionable, see note in unix_dgram_recvmsg.
*/
if (UNIXCB(skb).fp)
- scm.fp = scm_fp_dup(UNIXCB(skb).fp);
+ unix_peek_fds(&scm, skb);
sk_peek_offset_fwd(sk, chunk);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 50eb405b0690..16c88beea48b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2351,7 +2351,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
goto nla_put_failure;
for (band = state->band_start;
- band < NUM_NL80211_BANDS; band++) {
+ band < (state->split ?
+ NUM_NL80211_BANDS :
+ NL80211_BAND_60GHZ + 1);
+ band++) {
struct ieee80211_supported_band *sband;
/* omit higher bands for ancient software */
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index f03c7ac8e184..7897b1478c3c 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1754,16 +1754,14 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
* be grouped with this beacon for updates ...
*/
if (!cfg80211_combine_bsses(rdev, new)) {
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
}
if (rdev->bss_entries >= bss_entries_limit &&
!cfg80211_bss_expire_oldest(rdev)) {
- if (!list_empty(&new->hidden_list))
- list_del(&new->hidden_list);
- kfree(new);
+ bss_ref_put(rdev, new);
goto drop;
}
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 14e32825c339..6a2971a7e6a1 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -246,12 +246,18 @@ static bool hw_support_mmap(struct snd_pcm_substream *substream)
if (!(substream->runtime->hw.info & SNDRV_PCM_INFO_MMAP))
return false;
- if (substream->ops->mmap ||
- (substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV &&
- substream->dma_buffer.dev.type != SNDRV_DMA_TYPE_DEV_UC))
+ if (substream->ops->mmap)
return true;
- return dma_can_mmap(substream->dma_buffer.dev.dev);
+ switch (substream->dma_buffer.dev.type) {
+ case SNDRV_DMA_TYPE_UNKNOWN:
+ return false;
+ case SNDRV_DMA_TYPE_CONTINUOUS:
+ case SNDRV_DMA_TYPE_VMALLOC:
+ return true;
+ default:
+ return dma_can_mmap(substream->dma_buffer.dev.dev);
+ }
}
static int constrain_mask_params(struct snd_pcm_substream *substream,
@@ -3063,9 +3069,14 @@ static int snd_pcm_ioctl_sync_ptr_compat(struct snd_pcm_substream *substream,
boundary = 0x7fffffff;
snd_pcm_stream_lock_irq(substream);
/* FIXME: we should consider the boundary for the sync from app */
- if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL))
- control->appl_ptr = scontrol.appl_ptr;
- else
+ if (!(sflags & SNDRV_PCM_SYNC_PTR_APPL)) {
+ err = pcm_lib_apply_appl_ptr(substream,
+ scontrol.appl_ptr);
+ if (err < 0) {
+ snd_pcm_stream_unlock_irq(substream);
+ return err;
+ }
+ } else
scontrol.appl_ptr = control->appl_ptr % boundary;
if (!(sflags & SNDRV_PCM_SYNC_PTR_AVAIL_MIN))
control->avail_min = scontrol.avail_min;
@@ -3664,6 +3675,8 @@ static vm_fault_t snd_pcm_mmap_data_fault(struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
if (substream->ops->page)
page = substream->ops->page(substream, offset);
+ else if (!snd_pcm_get_dma_buf(substream))
+ page = virt_to_page(runtime->dma_area + offset);
else
page = snd_sgbuf_get_page(snd_pcm_get_dma_buf(substream), offset);
if (!page)
diff --git a/sound/hda/intel-dsp-config.c b/sound/hda/intel-dsp-config.c
index d8be146793ee..c9d0ba353463 100644
--- a/sound/hda/intel-dsp-config.c
+++ b/sound/hda/intel-dsp-config.c
@@ -319,6 +319,10 @@ static const struct config_entry config_table[] = {
.flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
.device = 0x4b55,
},
+ {
+ .flags = FLAG_SOF | FLAG_SOF_ONLY_IF_DMIC,
+ .device = 0x4b58,
+ },
#endif
/* Alder Lake */
diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c
index 5bbe6695689d..7ad8c5f7b664 100644
--- a/sound/isa/sb/sb16_csp.c
+++ b/sound/isa/sb/sb16_csp.c
@@ -816,6 +816,7 @@ static int snd_sb_csp_start(struct snd_sb_csp * p, int sample_width, int channel
mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7);
+ spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
spin_lock(&p->chip->reg_lock);
set_mode_register(p->chip, 0xc0); /* c0 = STOP */
@@ -855,6 +856,7 @@ static int snd_sb_csp_start(struct snd_sb_csp * p, int sample_width, int channel
spin_unlock(&p->chip->reg_lock);
/* restore PCM volume */
+ spin_lock_irqsave(&p->chip->mixer_lock, flags);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR);
spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
@@ -880,6 +882,7 @@ static int snd_sb_csp_stop(struct snd_sb_csp * p)
mixR = snd_sbmixer_read(p->chip, SB_DSP4_PCM_DEV + 1);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL & 0x7);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR & 0x7);
+ spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
spin_lock(&p->chip->reg_lock);
if (p->running & SNDRV_SB_CSP_ST_QSOUND) {
@@ -894,6 +897,7 @@ static int snd_sb_csp_stop(struct snd_sb_csp * p)
spin_unlock(&p->chip->reg_lock);
/* restore PCM volume */
+ spin_lock_irqsave(&p->chip->mixer_lock, flags);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV, mixL);
snd_sbmixer_write(p->chip, SB_DSP4_PCM_DEV + 1, mixR);
spin_unlock_irqrestore(&p->chip->mixer_lock, flags);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 4b2cc8cb55c4..e143e69d8184 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -1940,6 +1940,8 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
static const struct snd_pci_quirk force_connect_list[] = {
SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
+ SND_PCI_QUIRK(0x1462, 0xec94, "MS-7C94", 1),
+ SND_PCI_QUIRK(0x8086, 0x2081, "Intel NUC 10", 1),
{}
};
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1389cfd5e0db..caaf0e8aac11 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8626,6 +8626,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
SND_PCI_QUIRK(0x17aa, 0x3818, "Lenovo C940", ALC298_FIXUP_LENOVO_SPK_VOLUME),
SND_PCI_QUIRK(0x17aa, 0x3827, "Ideapad S740", ALC285_FIXUP_IDEAPAD_S740_COEF),
SND_PCI_QUIRK(0x17aa, 0x3843, "Yoga 9i", ALC287_FIXUP_IDEAPAD_BASS_SPK_AMP),
diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index 84e3906abd4f..9449fb40a956 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -576,6 +576,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = {
| SND_SOC_DAIFMT_CBM_CFM,
.init = cz_rt5682_init,
.dpcm_playback = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_play_ops,
SND_SOC_DAILINK_REG(designware1, rt5682, platform),
},
@@ -585,6 +586,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = {
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_cap_ops,
SND_SOC_DAILINK_REG(designware2, rt5682, platform),
},
@@ -594,6 +596,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = {
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_playback = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_max_play_ops,
SND_SOC_DAILINK_REG(designware3, mx, platform),
},
@@ -604,6 +607,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = {
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_dmic0_cap_ops,
SND_SOC_DAILINK_REG(designware3, adau, platform),
},
@@ -614,6 +618,7 @@ static struct snd_soc_dai_link cz_dai_5682_98357[] = {
.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
| SND_SOC_DAIFMT_CBM_CFM,
.dpcm_capture = 1,
+ .stop_dma_first = 1,
.ops = &cz_rt5682_dmic1_cap_ops,
SND_SOC_DAILINK_REG(designware2, adau, platform),
},
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 7ebae3f09435..a3b784ed4f70 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1325,7 +1325,7 @@ config SND_SOC_SSM2305
high-efficiency mono Class-D audio power amplifiers.
config SND_SOC_SSM2518
- tristate
+ tristate "Analog Devices SSM2518 Class-D Amplifier"
depends on I2C
config SND_SOC_SSM2602
@@ -1557,6 +1557,7 @@ config SND_SOC_WCD934X
Qualcomm SoCs like SDM845.
config SND_SOC_WCD938X
+ depends on SND_SOC_WCD938X_SDW
tristate
config SND_SOC_WCD938X_SDW
@@ -1813,11 +1814,6 @@ config SND_SOC_ZL38060
which consists of a Digital Signal Processor (DSP), several Digital
Audio Interfaces (DAIs), analog outputs, and a block of 14 GPIOs.
-config SND_SOC_ZX_AUD96P22
- tristate "ZTE ZX AUD96P22 CODEC"
- depends on I2C
- select REGMAP_I2C
-
# Amp
config SND_SOC_LM4857
tristate
diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c
index 3000bc128b5b..38356ea2bd6e 100644
--- a/sound/soc/codecs/rt5631.c
+++ b/sound/soc/codecs/rt5631.c
@@ -1695,6 +1695,8 @@ static const struct regmap_config rt5631_regmap_config = {
.reg_defaults = rt5631_reg,
.num_reg_defaults = ARRAY_SIZE(rt5631_reg),
.cache_type = REGCACHE_RBTREE,
+ .use_single_read = true,
+ .use_single_write = true,
};
static int rt5631_i2c_probe(struct i2c_client *i2c,
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index e4c91571abae..abcd6f483788 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -973,10 +973,14 @@ int rt5682_headset_detect(struct snd_soc_component *component, int jack_insert)
rt5682_enable_push_button_irq(component, false);
snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
- if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS"))
+ if (!snd_soc_dapm_get_pin_status(dapm, "MICBIAS") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL1") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL2B"))
snd_soc_component_update_bits(component,
RT5682_PWR_ANLG_1, RT5682_PWR_MB, 0);
- if (!snd_soc_dapm_get_pin_status(dapm, "Vref2"))
+ if (!snd_soc_dapm_get_pin_status(dapm, "Vref2") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL1") &&
+ !snd_soc_dapm_get_pin_status(dapm, "PLL2B"))
snd_soc_component_update_bits(component,
RT5682_PWR_ANLG_1, RT5682_PWR_VREF2, 0);
snd_soc_component_update_bits(component, RT5682_PWR_ANLG_3,
diff --git a/sound/soc/codecs/tlv320aic31xx.c b/sound/soc/codecs/tlv320aic31xx.c
index 51870d50f419..b504d63385b3 100644
--- a/sound/soc/codecs/tlv320aic31xx.c
+++ b/sound/soc/codecs/tlv320aic31xx.c
@@ -1604,6 +1604,8 @@ static int aic31xx_i2c_probe(struct i2c_client *i2c,
ret);
return ret;
}
+ regcache_cache_only(aic31xx->regmap, true);
+
aic31xx->dev = &i2c->dev;
aic31xx->irq = i2c->irq;
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 81952984613d..2513922a0292 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -151,8 +151,8 @@ struct aic31xx_pdata {
#define AIC31XX_WORD_LEN_24BITS 0x02
#define AIC31XX_WORD_LEN_32BITS 0x03
#define AIC31XX_IFACE1_MASTER_MASK GENMASK(3, 2)
-#define AIC31XX_BCLK_MASTER BIT(2)
-#define AIC31XX_WCLK_MASTER BIT(3)
+#define AIC31XX_BCLK_MASTER BIT(3)
+#define AIC31XX_WCLK_MASTER BIT(2)
/* AIC31XX_DATA_OFFSET */
#define AIC31XX_DATA_OFFSET_MASK GENMASK(7, 0)
diff --git a/sound/soc/codecs/tlv320aic32x4.c b/sound/soc/codecs/tlv320aic32x4.c
index c63b717040ed..dcd8aeb45cb3 100644
--- a/sound/soc/codecs/tlv320aic32x4.c
+++ b/sound/soc/codecs/tlv320aic32x4.c
@@ -250,8 +250,8 @@ static DECLARE_TLV_DB_SCALE(tlv_pcm, -6350, 50, 0);
static DECLARE_TLV_DB_SCALE(tlv_driver_gain, -600, 100, 0);
/* -12dB min, 0.5dB steps */
static DECLARE_TLV_DB_SCALE(tlv_adc_vol, -1200, 50, 0);
-
-static DECLARE_TLV_DB_LINEAR(tlv_spk_vol, TLV_DB_GAIN_MUTE, 0);
+/* -6dB min, 1dB steps */
+static DECLARE_TLV_DB_SCALE(tlv_tas_driver_gain, -5850, 50, 0);
static DECLARE_TLV_DB_SCALE(tlv_amp_vol, 0, 600, 1);
static const char * const lo_cm_text[] = {
@@ -1063,21 +1063,20 @@ static const struct snd_soc_component_driver soc_component_dev_aic32x4 = {
};
static const struct snd_kcontrol_new aic32x4_tas2505_snd_controls[] = {
- SOC_DOUBLE_R_S_TLV("PCM Playback Volume", AIC32X4_LDACVOL,
- AIC32X4_LDACVOL, 0, -0x7f, 0x30, 7, 0, tlv_pcm),
+ SOC_SINGLE_S8_TLV("PCM Playback Volume",
+ AIC32X4_LDACVOL, -0x7f, 0x30, tlv_pcm),
SOC_ENUM("DAC Playback PowerTune Switch", l_ptm_enum),
- SOC_DOUBLE_R_S_TLV("HP Driver Playback Volume", AIC32X4_HPLGAIN,
- AIC32X4_HPLGAIN, 0, -0x6, 0x1d, 5, 0,
- tlv_driver_gain),
- SOC_DOUBLE_R("HP DAC Playback Switch", AIC32X4_HPLGAIN,
- AIC32X4_HPLGAIN, 6, 0x01, 1),
- SOC_SINGLE("Auto-mute Switch", AIC32X4_DACMUTE, 4, 7, 0),
+ SOC_SINGLE_TLV("HP Driver Gain Volume",
+ AIC32X4_HPLGAIN, 0, 0x74, 1, tlv_tas_driver_gain),
+ SOC_SINGLE("HP DAC Playback Switch", AIC32X4_HPLGAIN, 6, 1, 1),
- SOC_SINGLE_RANGE_TLV("Speaker Driver Playback Volume", TAS2505_SPKVOL1,
- 0, 0, 117, 1, tlv_spk_vol),
- SOC_SINGLE_TLV("Speaker Amplifier Playback Volume", TAS2505_SPKVOL2,
- 4, 5, 0, tlv_amp_vol),
+ SOC_SINGLE_TLV("Speaker Driver Playback Volume",
+ TAS2505_SPKVOL1, 0, 0x74, 1, tlv_tas_driver_gain),
+ SOC_SINGLE_TLV("Speaker Amplifier Playback Volume",
+ TAS2505_SPKVOL2, 4, 5, 0, tlv_amp_vol),
+
+ SOC_SINGLE("Auto-mute Switch", AIC32X4_DACMUTE, 4, 7, 0),
};
static const struct snd_kcontrol_new hp_output_mixer_controls[] = {
diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c
index 78b76eceff8f..2fcc97370be2 100644
--- a/sound/soc/codecs/wcd938x.c
+++ b/sound/soc/codecs/wcd938x.c
@@ -3317,13 +3317,6 @@ static int wcd938x_soc_codec_probe(struct snd_soc_component *component)
(WCD938X_DIGITAL_INTR_LEVEL_0 + i), 0);
}
- ret = wcd938x_irq_init(wcd938x, component->dev);
- if (ret) {
- dev_err(component->dev, "%s: IRQ init failed: %d\n",
- __func__, ret);
- return ret;
- }
-
wcd938x->hphr_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip,
WCD938X_IRQ_HPHR_PDM_WD_INT);
wcd938x->hphl_pdm_wd_int = regmap_irq_get_virq(wcd938x->irq_chip,
@@ -3553,7 +3546,6 @@ static int wcd938x_bind(struct device *dev)
}
wcd938x->sdw_priv[AIF1_PB] = dev_get_drvdata(wcd938x->rxdev);
wcd938x->sdw_priv[AIF1_PB]->wcd938x = wcd938x;
- wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq;
wcd938x->txdev = wcd938x_sdw_device_get(wcd938x->txnode);
if (!wcd938x->txdev) {
@@ -3562,7 +3554,6 @@ static int wcd938x_bind(struct device *dev)
}
wcd938x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd938x->txdev);
wcd938x->sdw_priv[AIF1_CAP]->wcd938x = wcd938x;
- wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq;
wcd938x->tx_sdw_dev = dev_to_sdw_dev(wcd938x->txdev);
if (!wcd938x->tx_sdw_dev) {
dev_err(dev, "could not get txslave with matching of dev\n");
@@ -3595,6 +3586,15 @@ static int wcd938x_bind(struct device *dev)
return PTR_ERR(wcd938x->regmap);
}
+ ret = wcd938x_irq_init(wcd938x, dev);
+ if (ret) {
+ dev_err(dev, "%s: IRQ init failed: %d\n", __func__, ret);
+ return ret;
+ }
+
+ wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq;
+ wcd938x->sdw_priv[AIF1_CAP]->slave_irq = wcd938x->virq;
+
ret = wcd938x_set_micbias_data(wcd938x);
if (ret < 0) {
dev_err(dev, "%s: bad micbias pdata\n", __func__);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 37aa020f23f6..549d98241dae 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -282,6 +282,7 @@
/*
* HALO_CCM_CORE_CONTROL
*/
+#define HALO_CORE_RESET 0x00000200
#define HALO_CORE_EN 0x00000001
/*
@@ -1213,7 +1214,7 @@ static int wm_coeff_tlv_get(struct snd_kcontrol *kctl,
mutex_lock(&ctl->dsp->pwr_lock);
- ret = wm_coeff_read_ctrl_raw(ctl, ctl->cache, size);
+ ret = wm_coeff_read_ctrl(ctl, ctl->cache, size);
if (!ret && copy_to_user(bytes, ctl->cache, size))
ret = -EFAULT;
@@ -3333,7 +3334,8 @@ static int wm_halo_start_core(struct wm_adsp *dsp)
{
return regmap_update_bits(dsp->regmap,
dsp->base + HALO_CCM_CORE_CONTROL,
- HALO_CORE_EN, HALO_CORE_EN);
+ HALO_CORE_RESET | HALO_CORE_EN,
+ HALO_CORE_RESET | HALO_CORE_EN);
}
static void wm_halo_stop_core(struct wm_adsp *dsp)
diff --git a/sound/soc/intel/boards/sof_sdw_max98373.c b/sound/soc/intel/boards/sof_sdw_max98373.c
index 0e7ed906b341..25daef910aee 100644
--- a/sound/soc/intel/boards/sof_sdw_max98373.c
+++ b/sound/soc/intel/boards/sof_sdw_max98373.c
@@ -55,43 +55,68 @@ static int spk_init(struct snd_soc_pcm_runtime *rtd)
return ret;
}
-static int max98373_sdw_trigger(struct snd_pcm_substream *substream, int cmd)
+static int mx8373_enable_spk_pin(struct snd_pcm_substream *substream, bool enable)
{
+ struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
+ struct snd_soc_dai *codec_dai;
+ struct snd_soc_dai *cpu_dai;
int ret;
+ int j;
- switch (cmd) {
- case SNDRV_PCM_TRIGGER_START:
- case SNDRV_PCM_TRIGGER_RESUME:
- case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
- /* enable max98373 first */
- ret = max_98373_trigger(substream, cmd);
- if (ret < 0)
- break;
-
- ret = sdw_trigger(substream, cmd);
- break;
- case SNDRV_PCM_TRIGGER_STOP:
- case SNDRV_PCM_TRIGGER_SUSPEND:
- case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- ret = sdw_trigger(substream, cmd);
- if (ret < 0)
- break;
-
- ret = max_98373_trigger(substream, cmd);
- break;
- default:
- ret = -EINVAL;
- break;
+ /* set spk pin by playback only */
+ if (substream->stream == SNDRV_PCM_STREAM_CAPTURE)
+ return 0;
+
+ cpu_dai = asoc_rtd_to_cpu(rtd, 0);
+ for_each_rtd_codec_dais(rtd, j, codec_dai) {
+ struct snd_soc_dapm_context *dapm =
+ snd_soc_component_get_dapm(cpu_dai->component);
+ char pin_name[16];
+
+ snprintf(pin_name, ARRAY_SIZE(pin_name), "%s Spk",
+ codec_dai->component->name_prefix);
+
+ if (enable)
+ ret = snd_soc_dapm_enable_pin(dapm, pin_name);
+ else
+ ret = snd_soc_dapm_disable_pin(dapm, pin_name);
+
+ if (!ret)
+ snd_soc_dapm_sync(dapm);
}
- return ret;
+ return 0;
+}
+
+static int mx8373_sdw_prepare(struct snd_pcm_substream *substream)
+{
+ int ret = 0;
+
+ /* according to soc_pcm_prepare dai link prepare is called first */
+ ret = sdw_prepare(substream);
+ if (ret < 0)
+ return ret;
+
+ return mx8373_enable_spk_pin(substream, true);
+}
+
+static int mx8373_sdw_hw_free(struct snd_pcm_substream *substream)
+{
+ int ret = 0;
+
+ /* according to soc_pcm_hw_free dai link free is called first */
+ ret = sdw_hw_free(substream);
+ if (ret < 0)
+ return ret;
+
+ return mx8373_enable_spk_pin(substream, false);
}
static const struct snd_soc_ops max_98373_sdw_ops = {
.startup = sdw_startup,
- .prepare = sdw_prepare,
- .trigger = max98373_sdw_trigger,
- .hw_free = sdw_hw_free,
+ .prepare = mx8373_sdw_prepare,
+ .trigger = sdw_trigger,
+ .hw_free = mx8373_sdw_hw_free,
.shutdown = sdw_shutdown,
};
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 46513bb97904..d1c570ca21ea 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1015,6 +1015,7 @@ out:
static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
{
+ struct snd_soc_pcm_runtime *rtd = asoc_substream_to_rtd(substream);
int ret = -EINVAL, _ret = 0;
int rollback = 0;
@@ -1055,14 +1056,23 @@ start_err:
case SNDRV_PCM_TRIGGER_STOP:
case SNDRV_PCM_TRIGGER_SUSPEND:
case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
- ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
- if (ret < 0)
- break;
+ if (rtd->dai_link->stop_dma_first) {
+ ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
- ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
- if (ret < 0)
- break;
+ ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ } else {
+ ret = snd_soc_pcm_dai_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ ret = snd_soc_pcm_component_trigger(substream, cmd, rollback);
+ if (ret < 0)
+ break;
+ }
ret = snd_soc_link_trigger(substream, cmd, rollback);
break;
}
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index a00262184efa..d04ce84fe7cc 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -89,6 +89,7 @@ static const struct sof_dev_desc adls_desc = {
static const struct sof_dev_desc adl_desc = {
.machines = snd_soc_acpi_intel_adl_machines,
.alt_machines = snd_soc_acpi_intel_adl_sdw_machines,
+ .use_acpi_target_states = true,
.resindex_lpe_base = 0,
.resindex_pcicfg_base = -1,
.resindex_imr_base = -1,
diff --git a/sound/soc/tegra/tegra_pcm.c b/sound/soc/tegra/tegra_pcm.c
index 573374b89b10..d3276b4595af 100644
--- a/sound/soc/tegra/tegra_pcm.c
+++ b/sound/soc/tegra/tegra_pcm.c
@@ -213,19 +213,19 @@ snd_pcm_uframes_t tegra_pcm_pointer(struct snd_soc_component *component,
}
EXPORT_SYMBOL_GPL(tegra_pcm_pointer);
-static int tegra_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream,
+static int tegra_pcm_preallocate_dma_buffer(struct device *dev, struct snd_pcm *pcm, int stream,
size_t size)
{
struct snd_pcm_substream *substream = pcm->streams[stream].substream;
struct snd_dma_buffer *buf = &substream->dma_buffer;
- buf->area = dma_alloc_wc(pcm->card->dev, size, &buf->addr, GFP_KERNEL);
+ buf->area = dma_alloc_wc(dev, size, &buf->addr, GFP_KERNEL);
if (!buf->area)
return -ENOMEM;
buf->private_data = NULL;
buf->dev.type = SNDRV_DMA_TYPE_DEV;
- buf->dev.dev = pcm->card->dev;
+ buf->dev.dev = dev;
buf->bytes = size;
return 0;
@@ -244,31 +244,28 @@ static void tegra_pcm_deallocate_dma_buffer(struct snd_pcm *pcm, int stream)
if (!buf->area)
return;
- dma_free_wc(pcm->card->dev, buf->bytes, buf->area, buf->addr);
+ dma_free_wc(buf->dev.dev, buf->bytes, buf->area, buf->addr);
buf->area = NULL;
}
-static int tegra_pcm_dma_allocate(struct snd_soc_pcm_runtime *rtd,
+static int tegra_pcm_dma_allocate(struct device *dev, struct snd_soc_pcm_runtime *rtd,
size_t size)
{
- struct snd_card *card = rtd->card->snd_card;
struct snd_pcm *pcm = rtd->pcm;
int ret;
- ret = dma_set_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+ ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32));
if (ret < 0)
return ret;
if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
- ret = tegra_pcm_preallocate_dma_buffer(pcm,
- SNDRV_PCM_STREAM_PLAYBACK, size);
+ ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_PLAYBACK, size);
if (ret)
goto err;
}
if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
- ret = tegra_pcm_preallocate_dma_buffer(pcm,
- SNDRV_PCM_STREAM_CAPTURE, size);
+ ret = tegra_pcm_preallocate_dma_buffer(dev, pcm, SNDRV_PCM_STREAM_CAPTURE, size);
if (ret)
goto err_free_play;
}
@@ -284,7 +281,16 @@ err:
int tegra_pcm_construct(struct snd_soc_component *component,
struct snd_soc_pcm_runtime *rtd)
{
- return tegra_pcm_dma_allocate(rtd, tegra_pcm_hardware.buffer_bytes_max);
+ struct device *dev = component->dev;
+
+ /*
+ * Fallback for backwards-compatibility with older device trees that
+ * have the iommus property in the virtual, top-level "sound" node.
+ */
+ if (!of_get_property(dev->of_node, "iommus", NULL))
+ dev = rtd->card->snd_card->dev;
+
+ return tegra_pcm_dma_allocate(dev, rtd, tegra_pcm_hardware.buffer_bytes_max);
}
EXPORT_SYMBOL_GPL(tegra_pcm_construct);
diff --git a/sound/soc/ti/j721e-evm.c b/sound/soc/ti/j721e-evm.c
index a7c0484d44ec..265bbc5a2f96 100644
--- a/sound/soc/ti/j721e-evm.c
+++ b/sound/soc/ti/j721e-evm.c
@@ -197,7 +197,7 @@ static int j721e_configure_refclk(struct j721e_priv *priv,
return ret;
}
- if (priv->hsdiv_rates[domain->parent_clk_id] != scki) {
+ if (domain->parent_clk_id == -1 || priv->hsdiv_rates[domain->parent_clk_id] != scki) {
dev_dbg(priv->dev,
"%s configuration for %u Hz: %s, %dxFS (SCKI: %u Hz)\n",
audio_domain == J721E_AUDIO_DOMAIN_CPB ? "CPB" : "IVI",
@@ -278,23 +278,29 @@ static int j721e_audio_startup(struct snd_pcm_substream *substream)
j721e_rule_rate, &priv->rate_range,
SNDRV_PCM_HW_PARAM_RATE, -1);
- mutex_unlock(&priv->mutex);
if (ret)
- return ret;
+ goto out;
/* Reset TDM slots to 32 */
ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0x3, 0x3, 2, 32);
if (ret && ret != -ENOTSUPP)
- return ret;
+ goto out;
for_each_rtd_codec_dais(rtd, i, codec_dai) {
ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x3, 0x3, 2, 32);
if (ret && ret != -ENOTSUPP)
- return ret;
+ goto out;
}
- return 0;
+ if (ret == -ENOTSUPP)
+ ret = 0;
+out:
+ if (ret)
+ domain->active--;
+ mutex_unlock(&priv->mutex);
+
+ return ret;
}
static int j721e_audio_hw_params(struct snd_pcm_substream *substream,
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 30b3e128e28d..f4cdaf1ba44a 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -3295,7 +3295,15 @@ static void snd_usb_mixer_dump_cval(struct snd_info_buffer *buffer,
{
struct usb_mixer_elem_info *cval = mixer_elem_list_to_info(list);
static const char * const val_types[] = {
- "BOOLEAN", "INV_BOOLEAN", "S8", "U8", "S16", "U16", "S32", "U32",
+ [USB_MIXER_BOOLEAN] = "BOOLEAN",
+ [USB_MIXER_INV_BOOLEAN] = "INV_BOOLEAN",
+ [USB_MIXER_S8] = "S8",
+ [USB_MIXER_U8] = "U8",
+ [USB_MIXER_S16] = "S16",
+ [USB_MIXER_U16] = "U16",
+ [USB_MIXER_S32] = "S32",
+ [USB_MIXER_U32] = "U32",
+ [USB_MIXER_BESPOKEN] = "BESPOKEN",
};
snd_iprintf(buffer, " Info: id=%i, control=%i, cmask=0x%x, "
"channels=%i, type=\"%s\"\n", cval->head.id,
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 8b8bee3c3dd6..e7accd87e063 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1897,6 +1897,9 @@ static const struct registration_quirk registration_quirks[] = {
REG_QUIRK_ENTRY(0x0951, 0x16d8, 2), /* Kingston HyperX AMP */
REG_QUIRK_ENTRY(0x0951, 0x16ed, 2), /* Kingston HyperX Cloud Alpha S */
REG_QUIRK_ENTRY(0x0951, 0x16ea, 2), /* Kingston HyperX Cloud Flight S */
+ REG_QUIRK_ENTRY(0x0ecb, 0x1f46, 2), /* JBL Quantum 600 */
+ REG_QUIRK_ENTRY(0x0ecb, 0x2039, 2), /* JBL Quantum 400 */
+ REG_QUIRK_ENTRY(0x0ecb, 0x203e, 2), /* JBL Quantum 800 */
{ 0 } /* terminator */
};
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 1828bba19020..dc6daa193557 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -222,6 +222,11 @@ int mount_bpffs_for_pin(const char *name)
int err = 0;
file = malloc(strlen(name) + 1);
+ if (!file) {
+ p_err("mem alloc failed");
+ return -1;
+ }
+
strcpy(file, name);
dir = dirname(file);
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 22f8326547eb..bc1f64873c8f 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -2434,6 +2434,22 @@ static int cs_etm__process_event(struct perf_session *session,
return 0;
}
+static void dump_queued_data(struct cs_etm_auxtrace *etm,
+ struct perf_record_auxtrace *event)
+{
+ struct auxtrace_buffer *buf;
+ unsigned int i;
+ /*
+ * Find all buffers with same reference in the queues and dump them.
+ * This is because the queues can contain multiple entries of the same
+ * buffer that were split on aux records.
+ */
+ for (i = 0; i < etm->queues.nr_queues; ++i)
+ list_for_each_entry(buf, &etm->queues.queue_array[i].head, list)
+ if (buf->reference == event->reference)
+ cs_etm__dump_event(etm, buf);
+}
+
static int cs_etm__process_auxtrace_event(struct perf_session *session,
union perf_event *event,
struct perf_tool *tool __maybe_unused)
@@ -2466,7 +2482,8 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session,
cs_etm__dump_event(etm, buffer);
auxtrace_buffer__put_data(buffer);
}
- }
+ } else if (dump_trace)
+ dump_queued_data(etm, &event->auxtrace);
return 0;
}
@@ -3042,7 +3059,6 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
if (dump_trace) {
cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
- return 0;
}
err = cs_etm__synth_events(etm, session);
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 72e7f3616157..8af693d9678c 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -192,8 +192,6 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
if (!(prot & PROT_EXEC))
dso__set_loaded(dso);
}
-
- nsinfo__put(dso->nsinfo);
dso->nsinfo = nsi;
if (build_id__is_defined(bid))
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index a1bd7007a8b4..fc683bc41715 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -742,9 +742,13 @@ struct pmu_events_map *__weak pmu_events_map__find(void)
return perf_pmu__find_map(NULL);
}
-static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
+/*
+ * Suffix must be in form tok_{digits}, or tok{digits}, or same as pmu_name
+ * to be valid.
+ */
+static bool perf_pmu__valid_suffix(const char *pmu_name, char *tok)
{
- char *p;
+ const char *p;
if (strncmp(pmu_name, tok, strlen(tok)))
return false;
@@ -753,12 +757,16 @@ static bool perf_pmu__valid_suffix(char *pmu_name, char *tok)
if (*p == 0)
return true;
- if (*p != '_')
- return false;
+ if (*p == '_')
+ ++p;
- ++p;
- if (*p == 0 || !isdigit(*p))
- return false;
+ /* Ensure we end in a number */
+ while (1) {
+ if (!isdigit(*p))
+ return false;
+ if (*(++p) == 0)
+ break;
+ }
return true;
}
@@ -789,12 +797,19 @@ bool pmu_uncore_alias_match(const char *pmu_name, const char *name)
* match "socket" in "socketX_pmunameY" and then "pmuname" in
* "pmunameY".
*/
- for (; tok; name += strlen(tok), tok = strtok_r(NULL, ",", &tmp)) {
+ while (1) {
+ char *next_tok = strtok_r(NULL, ",", &tmp);
+
name = strstr(name, tok);
- if (!name || !perf_pmu__valid_suffix((char *)name, tok)) {
+ if (!name ||
+ (!next_tok && !perf_pmu__valid_suffix(name, tok))) {
res = false;
goto out;
}
+ if (!next_tok)
+ break;
+ tok = next_tok;
+ name += strlen(tok);
}
res = true;
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a3e593ddfafc..2debba4e8a3a 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1,4 +1,233 @@
{
+ "map access: known scalar += value_ptr unknown vs const",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs unknown",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (ne)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (lt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (gt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
"map access: known scalar += value_ptr from different maps",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 0709af0144c8..98053d3afbda 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0-only
/aarch64/debug-exceptions
/aarch64/get-reg-list
+/aarch64/psci_cpu_on_test
/aarch64/vgic_init
/s390x/memop
/s390x/resets
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 5832f510a16c..5d05801ab816 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
TEST_GEN_PROGS_aarch64 += demand_paging_test
TEST_GEN_PROGS_aarch64 += dirty_log_test
diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
new file mode 100644
index 000000000000..018c269990e1
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * psci_cpu_on_test - Test that the observable state of a vCPU targeted by the
+ * CPU_ON PSCI call matches what the caller requested.
+ *
+ * Copyright (c) 2021 Google LLC.
+ *
+ * This is a regression test for a race between KVM servicing the PSCI call and
+ * userspace reading the vCPUs registers.
+ */
+
+#define _GNU_SOURCE
+
+#include <linux/psci.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+#define VCPU_ID_SOURCE 0
+#define VCPU_ID_TARGET 1
+
+#define CPU_ON_ENTRY_ADDR 0xfeedf00dul
+#define CPU_ON_CONTEXT_ID 0xdeadc0deul
+
+static uint64_t psci_cpu_on(uint64_t target_cpu, uint64_t entry_addr,
+ uint64_t context_id)
+{
+ register uint64_t x0 asm("x0") = PSCI_0_2_FN64_CPU_ON;
+ register uint64_t x1 asm("x1") = target_cpu;
+ register uint64_t x2 asm("x2") = entry_addr;
+ register uint64_t x3 asm("x3") = context_id;
+
+ asm("hvc #0"
+ : "=r"(x0)
+ : "r"(x0), "r"(x1), "r"(x2), "r"(x3)
+ : "memory");
+
+ return x0;
+}
+
+static uint64_t psci_affinity_info(uint64_t target_affinity,
+ uint64_t lowest_affinity_level)
+{
+ register uint64_t x0 asm("x0") = PSCI_0_2_FN64_AFFINITY_INFO;
+ register uint64_t x1 asm("x1") = target_affinity;
+ register uint64_t x2 asm("x2") = lowest_affinity_level;
+
+ asm("hvc #0"
+ : "=r"(x0)
+ : "r"(x0), "r"(x1), "r"(x2)
+ : "memory");
+
+ return x0;
+}
+
+static void guest_main(uint64_t target_cpu)
+{
+ GUEST_ASSERT(!psci_cpu_on(target_cpu, CPU_ON_ENTRY_ADDR, CPU_ON_CONTEXT_ID));
+ uint64_t target_state;
+
+ do {
+ target_state = psci_affinity_info(target_cpu, 0);
+
+ GUEST_ASSERT((target_state == PSCI_0_2_AFFINITY_LEVEL_ON) ||
+ (target_state == PSCI_0_2_AFFINITY_LEVEL_OFF));
+ } while (target_state != PSCI_0_2_AFFINITY_LEVEL_ON);
+
+ GUEST_DONE();
+}
+
+int main(void)
+{
+ uint64_t target_mpidr, obs_pc, obs_x0;
+ struct kvm_vcpu_init init;
+ struct kvm_vm *vm;
+ struct ucall uc;
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+ kvm_vm_elf_load(vm, program_invocation_name);
+ ucall_init(vm, NULL);
+
+ vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);
+ init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2);
+
+ aarch64_vcpu_add_default(vm, VCPU_ID_SOURCE, &init, guest_main);
+
+ /*
+ * make sure the target is already off when executing the test.
+ */
+ init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF);
+ aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main);
+
+ get_reg(vm, VCPU_ID_TARGET, ARM64_SYS_REG(MPIDR_EL1), &target_mpidr);
+ vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
+ vcpu_run(vm, VCPU_ID_SOURCE);
+
+ switch (get_ucall(vm, VCPU_ID_SOURCE, &uc)) {
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0], __FILE__,
+ uc.args[1]);
+ break;
+ default:
+ TEST_FAIL("Unhandled ucall: %lu", uc.cmd);
+ }
+
+ get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.pc), &obs_pc);
+ get_reg(vm, VCPU_ID_TARGET, ARM64_CORE_REG(regs.regs[0]), &obs_x0);
+
+ TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR,
+ "unexpected target cpu pc: %lx (expected: %lx)",
+ obs_pc, CPU_ON_ENTRY_ADDR);
+ TEST_ASSERT(obs_x0 == CPU_ON_CONTEXT_ID,
+ "unexpected target context id: %lx (expected: %lx)",
+ obs_x0, CPU_ON_CONTEXT_ID);
+
+ kvm_vm_free(vm);
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index 27dc5c2e56b9..c0273aefa63d 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -17,6 +17,7 @@
#define CPACR_EL1 3, 0, 1, 0, 2
#define TCR_EL1 3, 0, 2, 0, 2
#define MAIR_EL1 3, 0, 10, 2, 0
+#define MPIDR_EL1 3, 0, 0, 0, 5
#define TTBR0_EL1 3, 0, 2, 0, 0
#define SCTLR_EL1 3, 0, 1, 0, 0
#define VBAR_EL1 3, 0, 12, 0, 0
@@ -40,6 +41,8 @@
(0xfful << (4 * 8)) | \
(0xbbul << (5 * 8)))
+#define MPIDR_HWID_BITMASK (0xff00fffffful)
+
static inline void get_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint64_t *addr)
{
struct kvm_one_reg reg;
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 6365c7fd1262..bd6288302094 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -11,9 +11,11 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include <linux/tcp.h>
+#include <linux/udp.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netinet/in.h>
+#include <netinet/ip.h>
#include <netdb.h>
#include <fcntl.h>
#include <libgen.h>
@@ -27,6 +29,10 @@
#include <time.h>
#include <errno.h>
+#include <linux/xfrm.h>
+#include <linux/ipsec.h>
+#include <linux/pfkeyv2.h>
+
#ifndef IPV6_UNICAST_IF
#define IPV6_UNICAST_IF 76
#endif
@@ -114,6 +120,9 @@ struct sock_args {
struct in_addr in;
struct in6_addr in6;
} expected_raddr;
+
+ /* ESP in UDP encap test */
+ int use_xfrm;
};
static int server_mode;
@@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args)
return 0;
}
+static int config_xfrm_policy(int sd, struct sock_args *args)
+{
+ struct xfrm_userpolicy_info policy = {};
+ int type = UDP_ENCAP_ESPINUDP;
+ int xfrm_af = IP_XFRM_POLICY;
+ int level = SOL_IP;
+
+ if (args->type != SOCK_DGRAM) {
+ log_error("Invalid socket type. Only DGRAM could be used for XFRM\n");
+ return 1;
+ }
+
+ policy.action = XFRM_POLICY_ALLOW;
+ policy.sel.family = args->version;
+ if (args->version == AF_INET6) {
+ xfrm_af = IPV6_XFRM_POLICY;
+ level = SOL_IPV6;
+ }
+
+ policy.dir = XFRM_POLICY_OUT;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ policy.dir = XFRM_POLICY_IN;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) {
+ log_err_errno("Failed to set xfrm encap");
+ return 1;
+ }
+
+ return 0;
+}
+
static int lsock_init(struct sock_args *args)
{
long flags;
@@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args)
if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0)
log_err_errno("Failed to set close-on-exec flag");
+ if (args->use_xfrm && config_xfrm_policy(sd, args)) {
+ log_err_errno("Failed to set xfrm policy");
+ goto err;
+ }
+
out:
return sd;
@@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
return client_status;
}
-#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq"
+#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
static void print_usage(char *prog)
{
@@ -1795,6 +1844,7 @@ static void print_usage(char *prog)
" -D|R datagram (D) / raw (R) socket (default stream)\n"
" -l addr local address to bind to in server mode\n"
" -c addr local address to bind to in client mode\n"
+ " -x configure XFRM policy on socket\n"
"\n"
" -d dev bind socket to given device name\n"
" -I dev bind socket to given device name - server mode\n"
@@ -1966,6 +2016,9 @@ int main(int argc, char *argv[])
case 'q':
quiet = 1;
break;
+ case 'x':
+ args.use_xfrm = 1;
+ break;
default:
print_usage(argv[0]);
return 1;
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 64cd2e23c568..543ad7513a8e 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -118,6 +118,16 @@
# below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
# changes alone won't affect PMTU
#
+# - pmtu_vti4_udp_exception
+# Same as pmtu_vti4_exception, but using ESP-in-UDP
+#
+# - pmtu_vti4_udp_routed_exception
+# Set up vti tunnel on top of veth connected through routing namespace and
+# add xfrm states and policies with ESP-in-UDP encapsulation. Check that
+# route exception is not created if link layer MTU is not exceeded, then
+# lower MTU on second part of routed environment and check that exception
+# is created with the expected PMTU.
+#
# - pmtu_vti6_exception
# Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is
@@ -125,6 +135,13 @@
# decrease and increase MTU of tunnel, checking that route exception PMTU
# changes accordingly
#
+# - pmtu_vti6_udp_exception
+# Same as pmtu_vti6_exception, but using ESP-in-UDP
+#
+# - pmtu_vti6_udp_routed_exception
+# Same as pmtu_vti6_udp_routed_exception but with routing between vti
+# endpoints
+#
# - pmtu_vti4_default_mtu
# Set up vti4 tunnel on top of veth, in two namespaces with matching
# endpoints. Check that MTU assigned to vti interface is the MTU of the
@@ -224,6 +241,10 @@ tests="
pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1
pmtu_vti6_exception vti6: PMTU exceptions 0
pmtu_vti4_exception vti4: PMTU exceptions 0
+ pmtu_vti6_udp_exception vti6: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti4_udp_exception vti4: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti6_udp_routed_exception vti6: PMTU exceptions, routed (ESP-in-UDP) 0
+ pmtu_vti4_udp_routed_exception vti4: PMTU exceptions, routed (ESP-in-UDP) 0
pmtu_vti4_default_mtu vti4: default MTU assignment 0
pmtu_vti6_default_mtu vti6: default MTU assignment 0
pmtu_vti4_link_add_mtu vti4: MTU setting on link creation 0
@@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}"
ns_c="ip netns exec ${NS_C}"
ns_r1="ip netns exec ${NS_R1}"
ns_r2="ip netns exec ${NS_R2}"
-
# Addressing and routing for tests with routers: four network segments, with
# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
@@ -279,7 +299,6 @@ routes="
A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2
B default ${prefix6}:${b_r1}::2
"
-
USE_NH="no"
# ns family nh id destination gateway
nexthops="
@@ -326,6 +345,7 @@ dummy6_mask="64"
err_buf=
tcpdump_pids=
+nettest_pids=
err() {
err_buf="${err_buf}${1}
@@ -548,6 +568,14 @@ setup_vti6() {
setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
}
+setup_vti4routed() {
+ setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
+}
+
+setup_vti6routed() {
+ setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
setup_vxlan_or_geneve() {
type="${1}"
a_addr="${2}"
@@ -619,18 +647,36 @@ setup_xfrm() {
proto=${1}
veth_a_addr="${2}"
veth_b_addr="${3}"
+ encap=${4}
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
}
+setup_nettest_xfrm() {
+ which nettest >/dev/null
+ if [ $? -ne 0 ]; then
+ echo "'nettest' command not found; skipping tests"
+ return 1
+ fi
+
+ [ ${1} -eq 6 ] && proto="-6" || proto=""
+ port=${2}
+
+ run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+
+ run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+}
+
setup_xfrm4() {
setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
}
@@ -639,6 +685,26 @@ setup_xfrm6() {
setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
}
+setup_xfrm4udp() {
+ setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udp() {
+ setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
+setup_xfrm4udprouted() {
+ setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udprouted() {
+ setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
setup_routing_old() {
for i in ${routes}; do
[ "${ns}" = "" ] && ns="${i}" && continue
@@ -823,6 +889,11 @@ cleanup() {
done
tcpdump_pids=
+ for pid in ${nettest_pids}; do
+ kill ${pid}
+ done
+ nettest_pids=
+
for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
ip netns del ${n} 2> /dev/null
done
@@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() {
return ${fail}
}
+test_pmtu_vti4_udp_exception() {
+ setup namespaces veth vti4 xfrm4udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_a ${veth_mtu}
+ mtu "${ns_b}" veth_b ${veth_mtu}
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now exceed link layer MTU by one byte, check that exception is created
+ # with the right PMTU value
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
+}
+
+test_pmtu_vti6_udp_exception() {
+ setup namespaces veth vti6 xfrm6udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+ fail=0
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_a 4000
+ mtu "${ns_b}" veth_b 4000
+ mtu "${ns_a}" vti6_a 5000
+ mtu "${ns_b}" vti6_b 5000
+ run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
+
+ # Decrease tunnel MTU, check for PMTU decrease in route exception
+ mtu "${ns_a}" vti6_a 3000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
+
+ # Increase tunnel MTU, check for PMTU increase in route exception
+ mtu "${ns_a}" vti6_a 9000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
+
+ return ${fail}
+}
+
+test_pmtu_vti4_udp_routed_exception() {
+ setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+}
+
+test_pmtu_vti6_udp_routed_exception() {
+ setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 40))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 48))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ # mtu "${ns_a}" vti6_a ${vti_mtu}
+ # mtu "${ns_b}" vti6_b ${vti_mtu}
+
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr}
+
+ # Check that exception was not created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+
+}
+
test_pmtu_vti4_default_mtu() {
setup namespaces veth vti4 || return $ksft_skip
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index e363bdaff59d..2ea438e6b8b1 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area)
static void anon_allocate_area(void **alloc_area)
{
- if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
- err("posix_memalign() failed");
+ *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (*alloc_area == MAP_FAILED)
+ err("mmap of anonymous memory failed");
}
static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 305956310174..439d3b4cd1a9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -189,16 +189,6 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
return true;
}
-bool kvm_is_transparent_hugepage(kvm_pfn_t pfn)
-{
- struct page *page = pfn_to_page(pfn);
-
- if (!PageTransCompoundMap(page))
- return false;
-
- return is_transparent_hugepage(compound_head(page));
-}
-
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
@@ -2337,7 +2327,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* Get a reference here because callers of *hva_to_pfn* and
* *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
* returned pfn. This is only needed if the VMA has VM_MIXEDMAP
- * set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
+ * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will
* simply do nothing for reserved pfns.
*
* Whoever called remap_pfn_range is also going to call e.g.
@@ -2734,13 +2724,6 @@ void kvm_set_pfn_accessed(kvm_pfn_t pfn)
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
-void kvm_get_pfn(kvm_pfn_t pfn)
-{
- if (!kvm_is_reserved_pfn(pfn))
- get_page(pfn_to_page(pfn));
-}
-EXPORT_SYMBOL_GPL(kvm_get_pfn);
-
static int next_segment(unsigned long len, int offset)
{
if (len > PAGE_SIZE - offset)