summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers4
-rw-r--r--Documentation/admin-guide/media/vivid.rst2
-rw-r--r--Documentation/arm64/booting.rst8
-rw-r--r--Documentation/arm64/cpu-feature-registers.rst38
-rw-r--r--Documentation/core-api/kernel-api.rst6
-rw-r--r--Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml4
-rw-r--r--Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml3
-rw-r--r--Documentation/driver-api/basics.rst3
-rw-r--r--Documentation/driver-api/driver-model/devres.rst1
-rw-r--r--Documentation/kbuild/reproducible-builds.rst10
-rw-r--r--Documentation/kernel-hacking/hacking.rst2
-rw-r--r--Documentation/process/2.Process.rst15
-rw-r--r--Documentation/process/howto.rst2
-rw-r--r--Documentation/process/maintainer-netdev.rst10
-rw-r--r--Documentation/trace/histogram.rst2
-rw-r--r--Documentation/translations/it_IT/process/howto.rst2
-rw-r--r--Documentation/translations/ja_JP/howto.rst2
-rw-r--r--Documentation/translations/ko_KR/howto.rst2
-rw-r--r--Documentation/translations/zh_CN/process/howto.rst2
-rw-r--r--Documentation/translations/zh_TW/process/howto.rst2
-rw-r--r--Documentation/virt/kvm/devices/vm.rst3
-rw-r--r--MAINTAINERS78
-rw-r--r--Makefile4
-rw-r--r--arch/arc/boot/dts/axc003.dtsi4
-rw-r--r--arch/arc/boot/dts/axc003_idu.dtsi4
-rw-r--r--arch/arc/boot/dts/axs10x_mb.dtsi4
-rw-r--r--arch/arc/boot/dts/hsdk.dts4
-rw-r--r--arch/arc/boot/dts/vdk_axs10x_mb.dtsi2
-rw-r--r--arch/arc/configs/axs101_defconfig4
-rw-r--r--arch/arc/configs/axs103_defconfig4
-rw-r--r--arch/arc/configs/axs103_smp_defconfig4
-rw-r--r--arch/arc/configs/haps_hs_defconfig1
-rw-r--r--arch/arc/configs/haps_hs_smp_defconfig1
-rw-r--r--arch/arc/configs/hsdk_defconfig1
-rw-r--r--arch/arc/configs/nsim_700_defconfig1
-rw-r--r--arch/arc/configs/nsimosci_defconfig1
-rw-r--r--arch/arc/configs/nsimosci_hs_defconfig1
-rw-r--r--arch/arc/configs/nsimosci_hs_smp_defconfig6
-rw-r--r--arch/arc/configs/tb10x_defconfig7
-rw-r--r--arch/arc/configs/vdk_hs38_defconfig3
-rw-r--r--arch/arc/configs/vdk_hs38_smp_defconfig1
-rw-r--r--arch/arc/include/asm/bitops.h4
-rw-r--r--arch/arc/include/asm/entry-compact.h2
-rw-r--r--arch/arc/include/asm/io.h2
-rw-r--r--arch/arc/include/asm/pgtable-levels.h2
-rw-r--r--arch/arc/kernel/smp.c2
-rw-r--r--arch/arc/mm/cache.c4
-rw-r--r--arch/arc/mm/ioremap.c2
-rw-r--r--arch/arm/boot/dts/imx6q-yapp4-crux.dts4
-rw-r--r--arch/arm/boot/dts/imx6qdl-gw5910.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6qdl-gw5913.dtsi2
-rw-r--r--arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts4
-rw-r--r--arch/arm/boot/dts/ste-href.dtsi8
-rw-r--r--arch/arm/boot/dts/ste-snowball.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-codina.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-gavini.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-golden.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-janice.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-kyle.dts8
-rw-r--r--arch/arm/boot/dts/ste-ux500-samsung-skomer.dts8
-rw-r--r--arch/arm64/boot/dts/arm/juno-base.dtsi14
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi18
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts16
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm.dtsi8
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mn.dtsi4
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi20
-rw-r--r--arch/arm64/boot/dts/freescale/imx93.dtsi11
-rw-r--r--arch/arm64/include/asm/efi.h8
-rw-r--r--arch/arm64/kernel/cpufeature.c42
-rw-r--r--arch/arm64/kernel/efi-rt-wrapper.S33
-rw-r--r--arch/arm64/kernel/efi.c26
-rw-r--r--arch/arm64/kernel/entry-common.c3
-rw-r--r--arch/arm64/kvm/arm.c5
-rw-r--r--arch/arm64/kvm/hyp/exception.c3
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h20
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c26
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c8
-rw-r--r--arch/arm64/kvm/irq.h16
-rw-r--r--arch/arm64/kvm/mmu.c2
-rw-r--r--arch/arm64/mm/fault.c4
-rw-r--r--arch/loongarch/include/asm/processor.h2
-rw-r--r--arch/loongarch/include/asm/ptrace.h4
-rw-r--r--arch/loongarch/kernel/head.S3
-rw-r--r--arch/loongarch/kernel/process.c4
-rw-r--r--arch/loongarch/kernel/switch.S2
-rw-r--r--arch/loongarch/net/bpf_jit.c31
-rw-r--r--arch/parisc/include/asm/hardware.h12
-rw-r--r--arch/parisc/include/uapi/asm/pdc.h36
-rw-r--r--arch/parisc/kernel/drivers.c14
-rw-r--r--arch/powerpc/Kconfig3
-rw-r--r--arch/powerpc/include/asm/book3s/64/tlbflush-hash.h6
-rw-r--r--arch/powerpc/include/asm/syscalls.h7
-rw-r--r--arch/powerpc/kernel/exceptions-64e.S7
-rw-r--r--arch/powerpc/kernel/exceptions-64s.S14
-rw-r--r--arch/powerpc/kernel/interrupt.c14
-rw-r--r--arch/powerpc/kernel/interrupt_64.S13
-rw-r--r--arch/powerpc/kernel/sys_ppc32.c13
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl7
-rw-r--r--arch/powerpc/kvm/Kconfig4
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_hv.c2
-rw-r--r--arch/powerpc/kvm/book3s_64_mmu_radix.c2
-rw-r--r--arch/powerpc/kvm/irq.h22
-rw-r--r--arch/powerpc/kvm/powerpc.c18
-rw-r--r--arch/powerpc/lib/vmx-helper.c12
-rw-r--r--arch/powerpc/mm/book3s64/hash_native.c67
-rw-r--r--arch/powerpc/mm/book3s64/hash_pgtable.c8
-rw-r--r--arch/powerpc/mm/book3s64/hash_utils.c12
-rw-r--r--arch/powerpc/platforms/pseries/lparcfg.c11
-rw-r--r--arch/powerpc/platforms/pseries/vas.c83
-rw-r--r--arch/powerpc/platforms/pseries/vas.h6
-rw-r--r--arch/riscv/Kconfig17
-rw-r--r--arch/riscv/Makefile6
-rw-r--r--arch/riscv/include/asm/jump_label.h8
-rw-r--r--arch/riscv/include/asm/vdso/processor.h2
-rw-r--r--arch/riscv/kernel/cpu.c3
-rw-r--r--arch/riscv/mm/kasan_init.c7
-rw-r--r--arch/s390/boot/vmlinux.lds.S13
-rw-r--r--arch/s390/include/asm/futex.h3
-rw-r--r--arch/s390/kernel/perf_pai_ext.c1
-rw-r--r--arch/s390/kvm/irq.h19
-rw-r--r--arch/s390/kvm/kvm-s390.c31
-rw-r--r--arch/s390/kvm/kvm-s390.h1
-rw-r--r--arch/s390/kvm/pci.c2
-rw-r--r--arch/s390/lib/uaccess.c6
-rw-r--r--arch/s390/pci/pci_mmio.c8
-rw-r--r--arch/x86/coco/tdx/tdx.c25
-rw-r--r--arch/x86/crypto/polyval-clmulni_glue.c19
-rw-r--r--arch/x86/events/amd/ibs.c2
-rw-r--r--arch/x86/events/intel/core.c1
-rw-r--r--arch/x86/events/intel/ds.c18
-rw-r--r--arch/x86/events/intel/lbr.c6
-rw-r--r--arch/x86/events/rapl.c10
-rw-r--r--arch/x86/include/asm/cpufeatures.h3
-rw-r--r--arch/x86/include/asm/hyperv-tlfs.h37
-rw-r--r--arch/x86/include/asm/intel-family.h11
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h148
-rw-r--r--arch/x86/include/asm/perf_event.h6
-rw-r--r--arch/x86/include/asm/spec-ctrl.h10
-rw-r--r--arch/x86/include/asm/string_64.h11
-rw-r--r--arch/x86/include/asm/svm.h100
-rw-r--r--arch/x86/include/asm/syscall_wrapper.h2
-rw-r--r--arch/x86/include/asm/uaccess.h13
-rw-r--r--arch/x86/include/uapi/asm/kvm.h5
-rw-r--r--arch/x86/kernel/asm-offsets.c6
-rw-r--r--arch/x86/kernel/cpu/bugs.c15
-rw-r--r--arch/x86/kernel/kvm.c2
-rw-r--r--arch/x86/kvm/.gitignore2
-rw-r--r--arch/x86/kvm/Kconfig11
-rw-r--r--arch/x86/kvm/Makefile18
-rw-r--r--arch/x86/kvm/cpuid.c42
-rw-r--r--arch/x86/kvm/debugfs.c7
-rw-r--r--arch/x86/kvm/emulate.c459
-rw-r--r--arch/x86/kvm/hyperv.c353
-rw-r--r--arch/x86/kvm/hyperv.h64
-rw-r--r--arch/x86/kvm/irq.c5
-rw-r--r--arch/x86/kvm/kvm-asm-offsets.c29
-rw-r--r--arch/x86/kvm/kvm_cache_regs.h5
-rw-r--r--arch/x86/kvm/kvm_emulate.h48
-rw-r--r--arch/x86/kvm/lapic.c8
-rw-r--r--arch/x86/kvm/lapic.h2
-rw-r--r--arch/x86/kvm/mmu/mmu.c176
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h33
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h6
-rw-r--r--arch/x86/kvm/mmu/spte.c12
-rw-r--r--arch/x86/kvm/mmu/spte.h19
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c114
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h2
-rw-r--r--arch/x86/kvm/pmu.c92
-rw-r--r--arch/x86/kvm/pmu.h6
-rw-r--r--arch/x86/kvm/reverse_cpuid.h25
-rw-r--r--arch/x86/kvm/smm.c649
-rw-r--r--arch/x86/kvm/smm.h168
-rw-r--r--arch/x86/kvm/svm/hyperv.c18
-rw-r--r--arch/x86/kvm/svm/hyperv.h50
-rw-r--r--arch/x86/kvm/svm/nested.c64
-rw-r--r--arch/x86/kvm/svm/pmu.c11
-rw-r--r--arch/x86/kvm/svm/sev.c8
-rw-r--r--arch/x86/kvm/svm/svm.c174
-rw-r--r--arch/x86/kvm/svm/svm.h16
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.c8
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.h25
-rw-r--r--arch/x86/kvm/svm/svm_ops.h5
-rw-r--r--arch/x86/kvm/svm/vmenter.S260
-rw-r--r--arch/x86/kvm/trace.h36
-rw-r--r--arch/x86/kvm/vmx/capabilities.h37
-rw-r--r--arch/x86/kvm/vmx/hyperv.c (renamed from arch/x86/kvm/vmx/evmcs.c)45
-rw-r--r--arch/x86/kvm/vmx/hyperv.h (renamed from arch/x86/kvm/vmx/evmcs.h)12
-rw-r--r--arch/x86/kvm/vmx/nested.c48
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c15
-rw-r--r--arch/x86/kvm/vmx/vmcs12.h5
-rw-r--r--arch/x86/kvm/vmx/vmenter.S2
-rw-r--r--arch/x86/kvm/vmx/vmx.c74
-rw-r--r--arch/x86/kvm/vmx/vmx_ops.h2
-rw-r--r--arch/x86/kvm/x86.c523
-rw-r--r--arch/x86/kvm/x86.h1
-rw-r--r--arch/x86/kvm/xen.c98
-rw-r--r--arch/x86/mm/pat/set_memory.c4
-rw-r--r--arch/x86/net/bpf_jit_comp.c13
-rw-r--r--arch/x86/purgatory/Makefile1
-rw-r--r--arch/x86/xen/pmu.c2
-rw-r--r--arch/x86/xen/setup.c23
-rw-r--r--block/blk-mq.c12
-rw-r--r--block/genhd.c13
-rw-r--r--drivers/acpi/acpi_pcc.c2
-rw-r--r--drivers/acpi/numa/srat.c1
-rw-r--r--drivers/acpi/resource.c7
-rw-r--r--drivers/acpi/scan.c1
-rw-r--r--drivers/acpi/video_detect.c12
-rw-r--r--drivers/acpi/x86/utils.c6
-rw-r--r--drivers/ata/pata_legacy.c5
-rw-r--r--drivers/ata/pata_palmld.c4
-rw-r--r--drivers/base/power/domain.c4
-rw-r--r--drivers/base/property.c4
-rw-r--r--drivers/block/Kconfig6
-rw-r--r--drivers/block/rbd.c4
-rw-r--r--drivers/block/ublk_drv.c115
-rw-r--r--drivers/bluetooth/virtio_bt.c2
-rw-r--r--drivers/char/random.c4
-rw-r--r--drivers/clk/clk-renesas-pcie.c65
-rw-r--r--drivers/clk/clk.c6
-rw-r--r--drivers/clk/mediatek/clk-mt8195-topckgen.c4
-rw-r--r--drivers/clk/qcom/gcc-sc7280.c1
-rw-r--r--drivers/clk/qcom/gpucc-sc7280.c1
-rw-r--r--drivers/clk/renesas/r8a779g0-cpg-mssr.c13
-rw-r--r--drivers/clk/sifive/Kconfig4
-rw-r--r--drivers/counter/104-quad-8.c64
-rw-r--r--drivers/counter/microchip-tcb-capture.c18
-rw-r--r--drivers/counter/ti-ecap-capture.c7
-rw-r--r--drivers/cpufreq/intel_pstate.c133
-rw-r--r--drivers/cxl/core/mbox.c2
-rw-r--r--drivers/cxl/core/pmem.c2
-rw-r--r--drivers/cxl/core/port.c11
-rw-r--r--drivers/cxl/core/region.c113
-rw-r--r--drivers/cxl/cxl.h4
-rw-r--r--drivers/cxl/pmem.c105
-rw-r--r--drivers/firmware/arm_scmi/bus.c11
-rw-r--r--drivers/firmware/arm_scmi/common.h5
-rw-r--r--drivers/firmware/arm_scmi/driver.c41
-rw-r--r--drivers/firmware/arm_scmi/mailbox.c2
-rw-r--r--drivers/firmware/arm_scmi/optee.c2
-rw-r--r--drivers/firmware/arm_scmi/shmem.c31
-rw-r--r--drivers/firmware/arm_scmi/smc.c2
-rw-r--r--drivers/firmware/arm_scmi/virtio.c26
-rw-r--r--drivers/firmware/efi/efi.c2
-rw-r--r--drivers/firmware/efi/libstub/random.c7
-rw-r--r--drivers/firmware/efi/tpm.c2
-rw-r--r--drivers/firmware/efi/vars.c68
-rw-r--r--drivers/gpio/gpio-tegra.c60
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c7
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c33
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c21
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mes_v11_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c28
-rw-r--r--drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h764
-rw-r--r--drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm6
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_crat.c106
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_migrate.c4
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c3
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c50
-rw-r--r--drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c11
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc.h1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c12
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c10
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c7
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c15
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h3
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c2
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h111
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h2
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c7
-rw-r--r--drivers/gpu/drm/bridge/parade-ps8640.c25
-rw-r--r--drivers/gpu/drm/drm_format_helper.c66
-rw-r--r--drivers/gpu/drm/i915/Makefile1
-rw-r--r--drivers/gpu/drm/i915/display/intel_ddi.c68
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_core.h8
-rw-r--r--drivers/gpu/drm/i915/display/intel_display_power_well.c7
-rw-r--r--drivers/gpu/drm/i915/display/intel_dkl_phy.c109
-rw-r--r--drivers/gpu/drm/i915/display/intel_dkl_phy.h24
-rw-r--r--drivers/gpu/drm/i915/display/intel_dp.c4
-rw-r--r--drivers/gpu/drm/i915/display/intel_dpll_mgr.c59
-rw-r--r--drivers/gpu/drm/i915/display/intel_lvds.c3
-rw-r--r--drivers/gpu/drm/i915/display/intel_panel.c4
-rw-r--r--drivers/gpu/drm/i915/display/intel_panel.h2
-rw-r--r--drivers/gpu/drm/i915/display/intel_sdvo.c64
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_internal.c19
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_shmem.c2
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_ttm.c4
-rw-r--r--drivers/gpu/drm/i915/gem/i915_gem_userptr.c2
-rw-r--r--drivers/gpu/drm/i915/gt/intel_workarounds.c4
-rw-r--r--drivers/gpu/drm/i915/i915_driver.c1
-rw-r--r--drivers/gpu/drm/i915/i915_reg.h3
-rw-r--r--drivers/gpu/drm/i915/i915_scatterlist.h34
-rw-r--r--drivers/gpu/drm/i915/intel_runtime_pm.c11
-rw-r--r--drivers/gpu/drm/imx/Kconfig1
-rw-r--r--drivers/gpu/drm/imx/imx-tve.c5
-rw-r--r--drivers/gpu/drm/msm/Kconfig2
-rw-r--r--drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c14
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_device.c10
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.c7
-rw-r--r--drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c5
-rw-r--r--drivers/gpu/drm/msm/dp/dp_ctrl.c13
-rw-r--r--drivers/gpu/drm/msm/dp/dp_display.c23
-rw-r--r--drivers/gpu/drm/msm/dp/dp_drm.c34
-rw-r--r--drivers/gpu/drm/msm/dp/dp_parser.c6
-rw-r--r--drivers/gpu/drm/msm/dp/dp_parser.h5
-rw-r--r--drivers/gpu/drm/msm/dsi/dsi.c6
-rw-r--r--drivers/gpu/drm/msm/hdmi/hdmi.c7
-rw-r--r--drivers/gpu/drm/msm/msm_drv.c1
-rw-r--r--drivers/gpu/drm/msm/msm_gem_submit.c9
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.c2
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.h4
-rw-r--r--drivers/gpu/drm/msm/msm_ringbuffer.c3
-rw-r--r--drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c26
-rw-r--r--drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c3
-rw-r--r--drivers/gpu/drm/rockchip/rockchip_drm_gem.c5
-rw-r--r--drivers/gpu/drm/rockchip/rockchip_drm_vop2.c10
-rw-r--r--drivers/gpu/drm/scheduler/sched_entity.c6
-rw-r--r--drivers/hwmon/pmbus/pmbus.h1
-rw-r--r--drivers/hwmon/scmi-hwmon.c116
-rw-r--r--drivers/hwtracing/coresight/coresight-core.c7
-rw-r--r--drivers/hwtracing/coresight/coresight-cti-core.c10
-rw-r--r--drivers/i2c/busses/i2c-i801.c1
-rw-r--r--drivers/i2c/busses/i2c-piix4.c1
-rw-r--r--drivers/i2c/busses/i2c-tegra.c16
-rw-r--r--drivers/iio/accel/adxl367.c23
-rw-r--r--drivers/iio/accel/adxl372.c23
-rw-r--r--drivers/iio/accel/bmc150-accel-core.c23
-rw-r--r--drivers/iio/adc/at91-sama5d2_adc.c23
-rw-r--r--drivers/iio/adc/mcp3911.c13
-rw-r--r--drivers/iio/adc/stm32-adc.c11
-rw-r--r--drivers/iio/light/tsl2583.c2
-rw-r--r--drivers/iio/temperature/ltc2983.c13
-rw-r--r--drivers/infiniband/core/cma.c2
-rw-r--r--drivers/infiniband/core/device.c10
-rw-r--r--drivers/infiniband/core/nldev.c2
-rw-r--r--drivers/infiniband/hw/efa/efa_main.c4
-rw-r--r--drivers/infiniband/hw/hfi1/pio.c3
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.c15
-rw-r--r--drivers/infiniband/hw/hns/hns_roce_hw_v2.h2
-rw-r--r--drivers/infiniband/hw/qedr/main.c9
-rw-r--r--drivers/infiniband/sw/rxe/rxe_resp.c4
-rw-r--r--drivers/isdn/hardware/mISDN/netjet.c2
-rw-r--r--drivers/isdn/mISDN/core.c5
-rw-r--r--drivers/leds/simple/simatic-ipc-leds-gpio.c12
-rw-r--r--drivers/media/test-drivers/vivid/vivid-core.c38
-rw-r--r--drivers/media/test-drivers/vivid/vivid-core.h2
-rw-r--r--drivers/media/test-drivers/vivid/vivid-osd.c2
-rw-r--r--drivers/media/test-drivers/vivid/vivid-vid-cap.c35
-rw-r--r--drivers/media/v4l2-core/v4l2-dv-timings.c14
-rw-r--r--drivers/misc/sgi-gru/grumain.c6
-rw-r--r--drivers/misc/sgi-gru/grutables.h14
-rw-r--r--drivers/mmc/core/block.c44
-rw-r--r--drivers/mmc/core/queue.c8
-rw-r--r--drivers/mmc/core/sdio_bus.c3
-rw-r--r--drivers/mmc/host/Kconfig3
-rw-r--r--drivers/mmc/host/sdhci-esdhc-imx.c14
-rw-r--r--drivers/mmc/host/sdhci-pci-core.c14
-rw-r--r--drivers/mtd/mtdcore.c2
-rw-r--r--drivers/mtd/nand/raw/intel-nand-controller.c23
-rw-r--r--drivers/mtd/nand/raw/marvell_nand.c2
-rw-r--r--drivers/mtd/nand/raw/tegra_nand.c4
-rw-r--r--drivers/mtd/parsers/bcm47xxpart.c4
-rw-r--r--drivers/mtd/spi-nor/core.c4
-rw-r--r--drivers/net/can/mscan/mpc5xxx_can.c8
-rw-r--r--drivers/net/can/rcar/rcar_canfd.c24
-rw-r--r--drivers/net/can/spi/mcp251x.c5
-rw-r--r--drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c4
-rw-r--r--drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c4
-rw-r--r--drivers/net/dsa/dsa_loop.c25
-rw-r--r--drivers/net/ethernet/adi/adin1110.c38
-rw-r--r--drivers/net/ethernet/amd/xgbe/xgbe-pci.c5
-rw-r--r--drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c58
-rw-r--r--drivers/net/ethernet/amd/xgbe/xgbe.h26
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_macsec.c96
-rw-r--r--drivers/net/ethernet/aquantia/atlantic/aq_nic.h2
-rw-r--r--drivers/net/ethernet/broadcom/bcm4908_enet.c12
-rw-r--r--drivers/net/ethernet/broadcom/bcmsysport.c3
-rw-r--r--drivers/net/ethernet/cadence/macb_main.c1
-rw-r--r--drivers/net/ethernet/freescale/dpaa/dpaa_eth.c4
-rw-r--r--drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c2
-rw-r--r--drivers/net/ethernet/freescale/enetc/enetc.c5
-rw-r--r--drivers/net/ethernet/freescale/fec_main.c50
-rw-r--r--drivers/net/ethernet/freescale/fman/mac.c12
-rw-r--r--drivers/net/ethernet/freescale/fman/mac.h2
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_debugfs.c18
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c2
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c2
-rw-r--r--drivers/net/ethernet/huawei/hinic/hinic_sriov.c1
-rw-r--r--drivers/net/ethernet/ibm/ehea/ehea_main.c1
-rw-r--r--drivers/net/ethernet/ibm/ibmvnic.c16
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_ethtool.c100
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_type.h4
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c43
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h1
-rw-r--r--drivers/net/ethernet/lantiq_etop.c1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/cmd.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h9
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c27
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c78
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tx.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c17
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c7
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c6
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/main.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c3
-rw-r--r--drivers/net/ethernet/micrel/ksz884x.c2
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c10
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c50
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_main.c4
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_main.h2
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_regs.h15
-rw-r--r--drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c6
-rw-r--r--drivers/net/ethernet/netronome/nfp/nfp_main.c38
-rw-r--r--drivers/net/ethernet/sfc/efx.c8
-rw-r--r--drivers/net/ethernet/socionext/netsec.c2
-rw-r--r--drivers/net/ethernet/socionext/sni_ave.c6
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c7
-rw-r--r--drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c6
-rw-r--r--drivers/net/ethernet/xilinx/xilinx_emaclite.c2
-rw-r--r--drivers/net/ipa/data/ipa_data-v3.5.1.c4
-rw-r--r--drivers/net/ipa/ipa_main.c3
-rw-r--r--drivers/net/ipa/reg/ipa_reg-v3.1.c96
-rw-r--r--drivers/net/netdevsim/bus.c9
-rw-r--r--drivers/net/netdevsim/dev.c31
-rw-r--r--drivers/net/phy/mdio_bus.c2
-rw-r--r--drivers/net/tun.c3
-rw-r--r--drivers/nfc/fdp/fdp.c10
-rw-r--r--drivers/nfc/nfcmrvl/i2c.c7
-rw-r--r--drivers/nfc/nxp-nci/core.c7
-rw-r--r--drivers/nfc/s3fwrn5/core.c8
-rw-r--r--drivers/nfc/virtual_ncidev.c3
-rw-r--r--drivers/nvme/host/multipath.c1
-rw-r--r--drivers/nvme/host/tcp.c13
-rw-r--r--drivers/parisc/iosapic.c1
-rw-r--r--drivers/parisc/pdc_stable.c34
-rw-r--r--drivers/pinctrl/pinctrl-ingenic.c4
-rw-r--r--drivers/pinctrl/pinctrl-ocelot.c17
-rw-r--r--drivers/pinctrl/pinctrl-zynqmp.c9
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm.c21
-rw-r--r--drivers/platform/loongarch/loongson-laptop.c24
-rw-r--r--drivers/platform/x86/amd/pmc.c7
-rw-r--r--drivers/platform/x86/asus-nb-wmi.c9
-rw-r--r--drivers/platform/x86/intel/pmc/core.c2
-rw-r--r--drivers/platform/x86/thinkpad_acpi.c4
-rw-r--r--drivers/rtc/rtc-cmos.c14
-rw-r--r--drivers/s390/cio/css.c8
-rw-r--r--drivers/s390/crypto/vfio_ap_private.h2
-rw-r--r--drivers/scsi/lpfc/lpfc_bsg.c4
-rw-r--r--drivers/scsi/lpfc/lpfc_ct.c2
-rw-r--r--drivers/scsi/megaraid/megaraid_sas_base.c27
-rw-r--r--drivers/scsi/mpi3mr/Kconfig1
-rw-r--r--drivers/scsi/mpt3sas/mpt3sas_base.c2
-rw-r--r--drivers/scsi/pm8001/pm8001_init.c1
-rw-r--r--drivers/scsi/qla2xxx/qla_attr.c30
-rw-r--r--drivers/soc/imx/imx93-pd.c17
-rw-r--r--drivers/spi/spi-aspeed-smc.c6
-rw-r--r--drivers/spi/spi-gxp.c2
-rw-r--r--drivers/spi/spi-intel.c2
-rw-r--r--drivers/spi/spi-mpc52xx.c2
-rw-r--r--drivers/spi/spi-qup.c2
-rw-r--r--drivers/spi/spi-tegra210-quad.c5
-rw-r--r--drivers/target/target_core_device.c19
-rw-r--r--drivers/target/target_core_iblock.c19
-rw-r--r--drivers/target/target_core_internal.h1
-rw-r--r--drivers/target/target_core_pr.c33
-rw-r--r--drivers/target/target_core_transport.c3
-rw-r--r--drivers/tty/serial/8250/8250_parisc.c (renamed from drivers/tty/serial/8250/8250_gsc.c)0
-rw-r--r--drivers/tty/serial/8250/Kconfig4
-rw-r--r--drivers/tty/serial/8250/Makefile2
-rw-r--r--drivers/ufs/core/ufshcd.c4
-rw-r--r--drivers/ufs/core/ufshpb.c6
-rw-r--r--drivers/ufs/host/ufs-qcom-ice.c1
-rw-r--r--drivers/usb/dwc3/core.c49
-rw-r--r--drivers/usb/dwc3/drd.c50
-rw-r--r--drivers/usb/dwc3/dwc3-st.c2
-rw-r--r--drivers/usb/dwc3/gadget.c20
-rw-r--r--drivers/usb/gadget/function/uvc_queue.c8
-rw-r--r--drivers/usb/gadget/function/uvc_video.c25
-rw-r--r--drivers/usb/gadget/udc/aspeed-vhub/dev.c1
-rw-r--r--drivers/usb/gadget/udc/bdc/bdc_udc.c1
-rw-r--r--drivers/usb/host/xhci-mem.c20
-rw-r--r--drivers/usb/host/xhci-pci.c44
-rw-r--r--drivers/usb/host/xhci.c10
-rw-r--r--drivers/usb/host/xhci.h1
-rw-r--r--drivers/usb/misc/sisusbvga/sisusb_struct.h2
-rw-r--r--drivers/usb/typec/ucsi/ucsi.c42
-rw-r--r--drivers/usb/typec/ucsi/ucsi_acpi.c10
-rw-r--r--drivers/video/aperture.c5
-rw-r--r--drivers/video/fbdev/cyber2000fb.c2
-rw-r--r--drivers/video/fbdev/da8xx-fb.c3
-rw-r--r--drivers/video/fbdev/gbefb.c4
-rw-r--r--drivers/video/fbdev/sis/sis_accel.c2
-rw-r--r--drivers/video/fbdev/sis/vstruct.h2
-rw-r--r--drivers/video/fbdev/sm501fb.c2
-rw-r--r--drivers/video/fbdev/smscufx.c55
-rw-r--r--drivers/video/fbdev/stifb.c3
-rw-r--r--drivers/video/fbdev/xilinxfb.c8
-rw-r--r--drivers/watchdog/exar_wdt.c4
-rw-r--r--drivers/watchdog/sp805_wdt.c2
-rw-r--r--fs/binfmt_elf.c3
-rw-r--r--fs/btrfs/backref.c54
-rw-r--r--fs/btrfs/ctree.h5
-rw-r--r--fs/btrfs/disk-io.c10
-rw-r--r--fs/btrfs/disk-io.h2
-rw-r--r--fs/btrfs/export.c2
-rw-r--r--fs/btrfs/export.h2
-rw-r--r--fs/btrfs/extent-tree.c25
-rw-r--r--fs/btrfs/file.c29
-rw-r--r--fs/btrfs/inode.c16
-rw-r--r--fs/btrfs/raid56.c18
-rw-r--r--fs/btrfs/send.c24
-rw-r--r--fs/btrfs/super.c16
-rw-r--r--fs/btrfs/tests/qgroup-tests.c36
-rw-r--r--fs/btrfs/volumes.c12
-rw-r--r--fs/btrfs/volumes.h2
-rw-r--r--fs/cifs/cifsfs.c26
-rw-r--r--fs/cifs/connect.c1
-rw-r--r--fs/cifs/file.c13
-rw-r--r--fs/cifs/inode.c5
-rw-r--r--fs/cifs/misc.c6
-rw-r--r--fs/cifs/smb2misc.c81
-rw-r--r--fs/cifs/smb2ops.c30
-rw-r--r--fs/cifs/smb2transport.c19
-rw-r--r--fs/crypto/keyring.c17
-rw-r--r--fs/exec.c6
-rw-r--r--fs/ext4/fast_commit.c5
-rw-r--r--fs/ext4/ioctl.c3
-rw-r--r--fs/ext4/migrate.c3
-rw-r--r--fs/ext4/namei.c10
-rw-r--r--fs/ext4/resize.c5
-rw-r--r--fs/ext4/super.c6
-rw-r--r--fs/fuse/file.c4
-rw-r--r--fs/fuse/readdir.c10
-rw-r--r--fs/nfs/client.c4
-rw-r--r--fs/nfs/delegation.c36
-rw-r--r--fs/nfs/dir.c5
-rw-r--r--fs/nfs/dns_resolve.c7
-rw-r--r--fs/nfs/dns_resolve.h2
-rw-r--r--fs/nfs/fs_context.c14
-rw-r--r--fs/nfs/internal.h14
-rw-r--r--fs/nfs/mount_clnt.c4
-rw-r--r--fs/nfs/namespace.c2
-rw-r--r--fs/nfs/nfs3client.c4
-rw-r--r--fs/nfs/nfs42proc.c3
-rw-r--r--fs/nfs/nfs4_fs.h2
-rw-r--r--fs/nfs/nfs4client.c19
-rw-r--r--fs/nfs/nfs4namespace.c16
-rw-r--r--fs/nfs/nfs4proc.c10
-rw-r--r--fs/nfs/nfs4state.c2
-rw-r--r--fs/nfs/pnfs_nfs.c6
-rw-r--r--fs/nfs/super.c5
-rw-r--r--fs/nfsd/filecache.c5
-rw-r--r--fs/squashfs/file.c23
-rw-r--r--fs/squashfs/page_actor.c3
-rw-r--r--fs/squashfs/page_actor.h6
-rw-r--r--fs/super.c3
-rw-r--r--fs/xfs/libxfs/xfs_ag.h15
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c6
-rw-r--r--fs/xfs/libxfs/xfs_dir2_leaf.c9
-rw-r--r--fs/xfs/libxfs/xfs_format.h22
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h60
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c286
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h40
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c15
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c9
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c4
-rw-r--r--fs/xfs/libxfs/xfs_types.h30
-rw-r--r--fs/xfs/scrub/alloc.c4
-rw-r--r--fs/xfs/scrub/ialloc.c5
-rw-r--r--fs/xfs/scrub/refcount.c72
-rw-r--r--fs/xfs/xfs_attr_item.c67
-rw-r--r--fs/xfs/xfs_bmap_item.c54
-rw-r--r--fs/xfs/xfs_error.c9
-rw-r--r--fs/xfs/xfs_extfree_item.c94
-rw-r--r--fs/xfs/xfs_extfree_item.h16
-rw-r--r--fs/xfs/xfs_file.c7
-rw-r--r--fs/xfs/xfs_inode.c2
-rw-r--r--fs/xfs/xfs_log_recover.c10
-rw-r--r--fs/xfs/xfs_ondisk.h23
-rw-r--r--fs/xfs/xfs_refcount_item.c57
-rw-r--r--fs/xfs/xfs_rmap_item.c70
-rw-r--r--fs/xfs/xfs_super.c12
-rw-r--r--fs/xfs/xfs_sysfs.h7
-rw-r--r--fs/xfs/xfs_trace.h48
-rw-r--r--fs/xfs/xfs_trans_ail.c3
-rw-r--r--include/asm-generic/compat.h2
-rw-r--r--include/asm-generic/hyperv-tlfs.h5
-rw-r--r--include/asm-generic/mshyperv.h11
-rw-r--r--include/linux/blk-mq.h3
-rw-r--r--include/linux/bpf.h14
-rw-r--r--include/linux/build_bug.h9
-rw-r--r--include/linux/counter.h5
-rw-r--r--include/linux/efi.h2
-rw-r--r--include/linux/fb.h2
-rw-r--r--include/linux/fortify-string.h30
-rw-r--r--include/linux/fscrypt.h4
-rw-r--r--include/linux/kmsan_string.h21
-rw-r--r--include/linux/kvm_host.h45
-rw-r--r--include/linux/mlx5/driver.h2
-rw-r--r--include/linux/mm.h1
-rw-r--r--include/linux/overflow.h38
-rw-r--r--include/linux/spi/spi-mem.h2
-rw-r--r--include/linux/userfaultfd_k.h6
-rw-r--r--include/net/genetlink.h10
-rw-r--r--include/net/netlink.h48
-rw-r--r--include/net/sock.h9
-rw-r--r--include/sound/control.h1
-rw-r--r--include/sound/simple_card_utils.h1
-rw-r--r--include/uapi/drm/amdgpu_drm.h2
-rw-r--r--include/uapi/linux/kvm.h3
-rw-r--r--include/uapi/linux/perf_event.h2
-rw-r--r--include/uapi/linux/videodev2.h3
-rw-r--r--io_uring/io_uring.c11
-rw-r--r--io_uring/io_uring.h13
-rw-r--r--ipc/msg.c4
-rw-r--r--kernel/bpf/btf.c5
-rw-r--r--kernel/bpf/dispatcher.c6
-rw-r--r--kernel/bpf/memalloc.c18
-rw-r--r--kernel/bpf/verifier.c1
-rw-r--r--kernel/events/core.c1
-rw-r--r--kernel/events/hw_breakpoint_test.c4
-rw-r--r--kernel/kprobes.c5
-rw-r--r--kernel/power/hibernate.c2
-rw-r--r--kernel/rcu/tree.c10
-rw-r--r--kernel/trace/fprobe.c5
-rw-r--r--kernel/trace/ftrace.c16
-rw-r--r--kernel/trace/kprobe_event_gen_test.c18
-rw-r--r--kernel/trace/ring_buffer.c11
-rw-r--r--lib/Kconfig.debug3
-rw-r--r--lib/kunit/string-stream.c4
-rw-r--r--lib/kunit/test.c2
-rw-r--r--lib/maple_tree.c4
-rw-r--r--lib/nlattr.c41
-rw-r--r--lib/overflow_kunit.c47
-rw-r--r--lib/test_rhashtable.c58
-rw-r--r--mm/gup.c33
-rw-r--r--mm/huge_memory.c2
-rw-r--r--mm/hugetlb.c5
-rw-r--r--mm/kmemleak.c61
-rw-r--r--mm/kmsan/instrumentation.c1
-rw-r--r--mm/kmsan/shadow.c1
-rw-r--r--mm/madvise.c12
-rw-r--r--mm/memory-tiers.c8
-rw-r--r--mm/migrate.c7
-rw-r--r--mm/mmap.c3
-rw-r--r--mm/page_alloc.c1
-rw-r--r--mm/page_isolation.c2
-rw-r--r--mm/shmem.c17
-rw-r--r--mm/userfaultfd.c25
-rw-r--r--net/bluetooth/hci_conn.c18
-rw-r--r--net/bluetooth/iso.c14
-rw-r--r--net/bluetooth/l2cap_core.c86
-rw-r--r--net/bridge/br_netlink.c2
-rw-r--r--net/bridge/br_sysfs_br.c2
-rw-r--r--net/can/j1939/transport.c4
-rw-r--r--net/core/neighbour.c2
-rw-r--r--net/core/net_namespace.c7
-rw-r--r--net/core/skbuff.c2
-rw-r--r--net/dsa/dsa2.c13
-rw-r--r--net/ethtool/eeprom.c2
-rw-r--r--net/ethtool/pse-pd.c2
-rw-r--r--net/ieee802154/socket.c4
-rw-r--r--net/ipv4/af_inet.c2
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/nexthop.c2
-rw-r--r--net/ipv4/tcp_bpf.c4
-rw-r--r--net/ipv4/tcp_input.c3
-rw-r--r--net/ipv4/tcp_ipv4.c4
-rw-r--r--net/ipv4/tcp_ulp.c3
-rw-r--r--net/ipv4/udp_bpf.c4
-rw-r--r--net/ipv6/ip6_gre.c12
-rw-r--r--net/ipv6/ip6_tunnel.c11
-rw-r--r--net/ipv6/route.c14
-rw-r--r--net/ipv6/sit.c8
-rw-r--r--net/ipv6/udp.c1
-rw-r--r--net/kcm/kcmsock.c25
-rw-r--r--net/mac802154/rx.c5
-rw-r--r--net/mptcp/protocol.c182
-rw-r--r--net/mptcp/protocol.h5
-rw-r--r--net/mptcp/subflow.c7
-rw-r--r--net/netfilter/ipset/ip_set_hash_gen.h30
-rw-r--r--net/netfilter/ipvs/ip_vs_app.c10
-rw-r--r--net/netfilter/ipvs/ip_vs_conn.c30
-rw-r--r--net/netfilter/nf_nat_core.c11
-rw-r--r--net/netfilter/nf_tables_api.c8
-rw-r--r--net/netfilter/nft_payload.c6
-rw-r--r--net/netlink/genetlink.c25
-rw-r--r--net/openvswitch/datapath.c4
-rw-r--r--net/rose/rose_link.c3
-rw-r--r--net/sched/sch_red.c4
-rw-r--r--net/smc/af_smc.c6
-rw-r--r--net/sunrpc/auth_gss/auth_gss.c2
-rw-r--r--net/sunrpc/sysfs.c12
-rw-r--r--net/tipc/topsrv.c16
-rw-r--r--net/unix/unix_bpf.c8
-rw-r--r--net/vmw_vsock/af_vsock.c7
-rw-r--r--scripts/Makefile.modpost2
-rw-r--r--scripts/kconfig/menu.c23
-rw-r--r--security/commoncap.c6
-rw-r--r--sound/aoa/soundbus/i2sbus/core.c7
-rw-r--r--sound/core/control.c23
-rw-r--r--sound/pci/ac97/ac97_codec.c33
-rw-r--r--sound/pci/au88x0/au88x0.h6
-rw-r--r--sound/pci/au88x0/au88x0_core.c2
-rw-r--r--sound/pci/ca0106/ca0106_mixer.c2
-rw-r--r--sound/pci/emu10k1/emumixer.c2
-rw-r--r--sound/pci/hda/patch_realtek.c12
-rw-r--r--sound/pci/rme9652/hdsp.c26
-rw-r--r--sound/pci/rme9652/rme9652.c22
-rw-r--r--sound/soc/amd/yc/acp6x-mach.c21
-rw-r--r--sound/soc/codecs/Kconfig1
-rw-r--r--sound/soc/codecs/cx2072x.h2
-rw-r--r--sound/soc/codecs/jz4725b.c34
-rw-r--r--sound/soc/codecs/mt6660.c8
-rw-r--r--sound/soc/codecs/rt1019.c20
-rw-r--r--sound/soc/codecs/rt1019.h6
-rw-r--r--sound/soc/codecs/rt1308-sdw.c17
-rw-r--r--sound/soc/codecs/rt1308-sdw.h3
-rw-r--r--sound/soc/codecs/rt1308.h5
-rw-r--r--sound/soc/codecs/rt5682s.c15
-rw-r--r--sound/soc/codecs/rt5682s.h1
-rw-r--r--sound/soc/codecs/tlv320adc3xxx.c2
-rw-r--r--sound/soc/codecs/wm5102.c7
-rw-r--r--sound/soc/codecs/wm5110.c7
-rw-r--r--sound/soc/codecs/wm8962.c54
-rw-r--r--sound/soc/codecs/wm8997.c7
-rw-r--r--sound/soc/generic/audio-graph-card.c2
-rw-r--r--sound/soc/generic/simple-card-utils.c15
-rw-r--r--sound/soc/generic/simple-card.c3
-rw-r--r--sound/soc/intel/boards/sof_rt5682.c12
-rw-r--r--sound/soc/intel/boards/sof_sdw.c11
-rw-r--r--sound/soc/intel/skylake/skl.c8
-rw-r--r--sound/soc/qcom/Kconfig1
-rw-r--r--sound/soc/qcom/lpass-cpu.c10
-rw-r--r--sound/soc/soc-component.c6
-rw-r--r--sound/soc/sof/intel/hda-codec.c8
-rw-r--r--sound/soc/sof/intel/pci-mtl.c2
-rw-r--r--sound/soc/sof/intel/pci-tgl.c30
-rw-r--r--sound/soc/sof/ipc4-mtrace.c20
-rw-r--r--sound/synth/emux/emux.c7
-rw-r--r--sound/usb/implicit.c2
-rw-r--r--sound/usb/mixer.c2
-rw-r--r--tools/arch/arm64/include/asm/cputype.h4
-rw-r--r--tools/arch/x86/include/asm/atomic.h7
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h2
-rw-r--r--tools/arch/x86/lib/memcpy_64.S2
-rw-r--r--tools/build/Makefile.feature1
-rw-r--r--tools/build/feature/Makefile4
-rw-r--r--tools/build/feature/test-libbpf-bpf_program__set_insns.c8
-rw-r--r--tools/iio/iio_utils.c4
-rw-r--r--tools/include/asm-generic/atomic-gcc.h12
-rw-r--r--tools/include/nolibc/string.h17
-rw-r--r--tools/include/uapi/linux/in.h22
-rw-r--r--tools/include/uapi/linux/perf_event.h27
-rw-r--r--tools/include/uapi/linux/stat.h4
-rw-r--r--tools/include/uapi/sound/asound.h16
-rwxr-xr-xtools/kvm/kvm_stat/kvm_stat98
-rw-r--r--tools/perf/Documentation/arm-coresight.txt (renamed from tools/perf/Documentation/perf-arm-coresight.txt)0
-rw-r--r--tools/perf/Makefile.config5
-rw-r--r--tools/perf/arch/powerpc/entry/syscalls/syscall.tbl16
-rw-r--r--tools/perf/builtin-record.c41
-rwxr-xr-xtools/perf/check-headers.sh2
-rw-r--r--tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json6
-rw-r--r--tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json72
-rw-r--r--tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json (renamed from tools/perf/pmu-events/arch/s390/cf_z16/pai.json)0
-rwxr-xr-xtools/perf/tests/shell/test_intel_pt.sh6
-rw-r--r--tools/perf/trace/beauty/statx.c1
-rw-r--r--tools/perf/util/auxtrace.c10
-rw-r--r--tools/perf/util/bpf-event.c5
-rw-r--r--tools/perf/util/bpf-loader.c18
-rw-r--r--tools/perf/util/include/linux/linkage.h13
-rw-r--r--tools/power/pm-graph/README12
-rw-r--r--tools/power/pm-graph/sleepgraph.83
-rwxr-xr-xtools/power/pm-graph/sleepgraph.py225
-rw-r--r--tools/testing/cxl/test/cxl.c301
-rw-r--r--tools/testing/selftests/Makefile1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf.c13
-rw-r--r--tools/testing/selftests/bpf/progs/user_ringbuf_success.c4
-rw-r--r--tools/testing/selftests/drivers/net/bonding/Makefile4
-rwxr-xr-xtools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh2
l---------tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh1
-rwxr-xr-xtools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh4
-rw-r--r--tools/testing/selftests/drivers/net/team/Makefile4
-rwxr-xr-xtools/testing/selftests/drivers/net/team/dev_addr_lists.sh6
l---------tools/testing/selftests/drivers/net/team/lag_lib.sh1
l---------tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh1
-rw-r--r--tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc2
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc2
-rw-r--r--tools/testing/selftests/futex/functional/Makefile6
-rw-r--r--tools/testing/selftests/intel_pstate/Makefile6
-rw-r--r--tools/testing/selftests/kexec/Makefile6
-rw-r--r--tools/testing/selftests/kvm/.gitignore8
-rw-r--r--tools/testing/selftests/kvm/Makefile14
-rw-r--r--tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c3
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c29
-rw-r--r--tools/testing/selftests/kvm/aarch64/debug-exceptions.c32
-rw-r--r--tools/testing/selftests/kvm/aarch64/hypercalls.c3
-rw-r--r--tools/testing/selftests/kvm/aarch64/psci_test.c1
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_init.c2
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_irq.c10
-rw-r--r--tools/testing/selftests/kvm/access_tracking_perf_test.c22
-rw-r--r--tools/testing/selftests/kvm/demand_paging_test.c24
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c130
-rw-r--r--tools/testing/selftests/kvm/dirty_log_test.c3
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util_base.h29
-rw-r--r--tools/testing/selftests/kvm/include/memstress.h72
-rw-r--r--tools/testing/selftests/kvm/include/perf_test_util.h63
-rw-r--r--tools/testing/selftests/kvm/include/test_util.h25
-rw-r--r--tools/testing/selftests/kvm/include/ucall_common.h10
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/evmcs.h48
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/hyperv.h103
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h452
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm.h26
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/svm_util.h14
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/vmx.h25
-rw-r--r--tools/testing/selftests/kvm/kvm_page_table_test.c6
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c18
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/ucall.c102
-rw-r--r--tools/testing/selftests/kvm/lib/elf.c2
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c94
-rw-r--r--tools/testing/selftests/kvm/lib/memstress.c (renamed from tools/testing/selftests/kvm/lib/perf_test_util.c)133
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/ucall.c42
-rw-r--r--tools/testing/selftests/kvm/lib/s390x/ucall.c39
-rw-r--r--tools/testing/selftests/kvm/lib/test_util.c36
-rw-r--r--tools/testing/selftests/kvm/lib/ucall_common.c103
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/hyperv.c46
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/memstress.c (renamed from tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c)37
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c236
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/ucall.c39
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/vmx.c56
-rw-r--r--tools/testing/selftests/kvm/max_guest_memory_test.c21
-rw-r--r--tools/testing/selftests/kvm/memslot_modification_stress_test.c38
-rw-r--r--tools/testing/selftests/kvm/memslot_perf_test.c28
-rw-r--r--tools/testing/selftests/kvm/rseq_test.c4
-rw-r--r--tools/testing/selftests/kvm/s390x/memop.c2
-rw-r--r--tools/testing/selftests/kvm/s390x/resets.c2
-rw-r--r--tools/testing/selftests/kvm/s390x/sync_regs_test.c3
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c5
-rw-r--r--tools/testing/selftests/kvm/steal_time.c1
-rw-r--r--tools/testing/selftests/kvm/system_counter_offset_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/amx_test.c101
-rw-r--r--tools/testing/selftests/kvm/x86_64/cpuid_test.c11
-rw-r--r--tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/emulator_error_test.c193
-rw-r--r--tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c45
-rw-r--r--tools/testing/selftests/kvm/x86_64/flds_emulation.h55
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c (renamed from tools/testing/selftests/kvm/x86_64/evmcs_test.c)96
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_features.c25
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_ipi.c314
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c99
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c690
-rw-r--r--tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c5
-rw-r--r--tools/testing/selftests/kvm/x86_64/platform_info_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c77
-rw-r--r--tools/testing/selftests/kvm/x86_64/set_sregs_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c111
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c67
-rw-r--r--tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/sync_regs_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c73
-rw-r--r--tools/testing/selftests/kvm/x86_64/userspace_io_test.c3
-rw-r--r--tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c88
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c19
-rw-r--r--tools/testing/selftests/kvm/x86_64/xapic_state_test.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c142
-rw-r--r--tools/testing/selftests/landlock/Makefile7
-rw-r--r--tools/testing/selftests/lib.mk4
-rwxr-xr-xtools/testing/selftests/memory-hotplug/mem-on-off-test.sh1
-rw-r--r--tools/testing/selftests/net/openvswitch/Makefile13
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh218
-rw-r--r--tools/testing/selftests/net/openvswitch/ovs-dpctl.py351
-rw-r--r--tools/testing/selftests/pidfd/Makefile2
-rw-r--r--tools/testing/selftests/pidfd/pidfd_test.c4
-rw-r--r--tools/testing/selftests/pidfd/pidfd_wait.c12
-rw-r--r--virt/kvm/irqchip.c3
-rw-r--r--virt/kvm/kvm_main.c54
-rw-r--r--virt/kvm/kvm_mm.h4
-rw-r--r--virt/kvm/pfncache.c71
907 files changed, 14109 insertions, 6850 deletions
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers b/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
index 45985e411f13..721a05b90109 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-memory-tiers
@@ -10,7 +10,7 @@ Description: A collection of all the memory tiers allocated.
What: /sys/devices/virtual/memory_tiering/memory_tierN/
- /sys/devices/virtual/memory_tiering/memory_tierN/nodes
+ /sys/devices/virtual/memory_tiering/memory_tierN/nodelist
Date: August 2022
Contact: Linux memory management mailing list <linux-mm@kvack.org>
Description: Directory with details of a specific memory tier
@@ -21,5 +21,5 @@ Description: Directory with details of a specific memory tier
A smaller value of N implies a higher (faster) memory tier in the
hierarchy.
- nodes: NUMA nodes that are part of this memory tier.
+ nodelist: NUMA nodes that are part of this memory tier.
diff --git a/Documentation/admin-guide/media/vivid.rst b/Documentation/admin-guide/media/vivid.rst
index 4f680dc9661c..abd90ed31090 100644
--- a/Documentation/admin-guide/media/vivid.rst
+++ b/Documentation/admin-guide/media/vivid.rst
@@ -1318,7 +1318,7 @@ instance. This setup would require the following commands:
$ v4l2-ctl -d2 -i2
$ v4l2-ctl -d2 -c horizontal_movement=4
$ v4l2-ctl -d1 --overlay=1
- $ v4l2-ctl -d1 -c loop_video=1
+ $ v4l2-ctl -d0 -c loop_video=1
$ v4l2-ctl -d2 --stream-mmap --overlay=1
And from another console:
diff --git a/Documentation/arm64/booting.rst b/Documentation/arm64/booting.rst
index 8aefa1001ae5..8c324ad638de 100644
--- a/Documentation/arm64/booting.rst
+++ b/Documentation/arm64/booting.rst
@@ -340,6 +340,14 @@ Before jumping into the kernel, the following conditions must be met:
- SMCR_EL2.LEN must be initialised to the same value for all CPUs the
kernel will execute on.
+ - HWFGRTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+
+ - HWFGWTR_EL2.nTPIDR2_EL0 (bit 55) must be initialised to 0b01.
+
+ - HWFGRTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+
+ - HWFGWTR_EL2.nSMPRI_EL1 (bit 54) must be initialised to 0b01.
+
For CPUs with the Scalable Matrix Extension FA64 feature (FEAT_SME_FA64)
- If EL3 is present:
diff --git a/Documentation/arm64/cpu-feature-registers.rst b/Documentation/arm64/cpu-feature-registers.rst
index 04ba83e1965f..c7adc7897df6 100644
--- a/Documentation/arm64/cpu-feature-registers.rst
+++ b/Documentation/arm64/cpu-feature-registers.rst
@@ -92,7 +92,7 @@ operation if the source belongs to the supported system register space.
The infrastructure emulates only the following system register space::
- Op0=3, Op1=0, CRn=0, CRm=0,4,5,6,7
+ Op0=3, Op1=0, CRn=0, CRm=0,2,3,4,5,6,7
(See Table C5-6 'System instruction encodings for non-Debug System
register accesses' in ARMv8 ARM DDI 0487A.h, for the list of
@@ -293,6 +293,42 @@ infrastructure:
| WFXT | [3-0] | y |
+------------------------------+---------+---------+
+ 10) MVFR0_EL1 - AArch32 Media and VFP Feature Register 0
+
+ +------------------------------+---------+---------+
+ | Name | bits | visible |
+ +------------------------------+---------+---------+
+ | FPDP | [11-8] | y |
+ +------------------------------+---------+---------+
+
+ 11) MVFR1_EL1 - AArch32 Media and VFP Feature Register 1
+
+ +------------------------------+---------+---------+
+ | Name | bits | visible |
+ +------------------------------+---------+---------+
+ | SIMDFMAC | [31-28] | y |
+ +------------------------------+---------+---------+
+ | SIMDSP | [19-16] | y |
+ +------------------------------+---------+---------+
+ | SIMDInt | [15-12] | y |
+ +------------------------------+---------+---------+
+ | SIMDLS | [11-8] | y |
+ +------------------------------+---------+---------+
+
+ 12) ID_ISAR5_EL1 - AArch32 Instruction Set Attribute Register 5
+
+ +------------------------------+---------+---------+
+ | Name | bits | visible |
+ +------------------------------+---------+---------+
+ | CRC32 | [19-16] | y |
+ +------------------------------+---------+---------+
+ | SHA2 | [15-12] | y |
+ +------------------------------+---------+---------+
+ | SHA1 | [11-8] | y |
+ +------------------------------+---------+---------+
+ | AES | [7-4] | y |
+ +------------------------------+---------+---------+
+
Appendix I: Example
-------------------
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 0793c400d4b0..06f4ab122697 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -118,6 +118,12 @@ Text Searching
CRC and Math Functions in Linux
===============================
+Arithmetic Overflow Checking
+----------------------------
+
+.. kernel-doc:: include/linux/overflow.h
+ :internal:
+
CRC Functions
-------------
diff --git a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
index 1e2b9b627b12..2722dc7bb03d 100644
--- a/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/xlnx,zynqmp-pinctrl.yaml
@@ -274,10 +274,6 @@ patternProperties:
slew-rate:
enum: [0, 1]
- output-enable:
- description:
- This will internally disable the tri-state for MIO pins.
-
drive-strength:
description:
Selects the drive strength for MIO pins, in mA.
diff --git a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml
index 58022ae7d5dd..dfdb8dfb6b65 100644
--- a/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml
+++ b/Documentation/devicetree/bindings/power/fsl,imx-gpcv2.yaml
@@ -81,6 +81,9 @@ properties:
power-supply: true
+ power-domains:
+ maxItems: 1
+
resets:
description: |
A number of phandles to resets that need to be asserted during
diff --git a/Documentation/driver-api/basics.rst b/Documentation/driver-api/basics.rst
index 3e2dae954898..4b4d8e28d3be 100644
--- a/Documentation/driver-api/basics.rst
+++ b/Documentation/driver-api/basics.rst
@@ -107,9 +107,6 @@ Kernel utility functions
.. kernel-doc:: kernel/panic.c
:export:
-.. kernel-doc:: include/linux/overflow.h
- :internal:
-
Device Resource Management
--------------------------
diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 687adb58048e..56082265e8e5 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -279,6 +279,7 @@ GPIO
devm_gpio_request_one()
I2C
+ devm_i2c_add_adapter()
devm_i2c_new_dummy_device()
IIO
diff --git a/Documentation/kbuild/reproducible-builds.rst b/Documentation/kbuild/reproducible-builds.rst
index 071f0151a7a4..f2dcc39044e6 100644
--- a/Documentation/kbuild/reproducible-builds.rst
+++ b/Documentation/kbuild/reproducible-builds.rst
@@ -119,6 +119,16 @@ To avoid this, you can make the vDSO different for different
kernel versions by including an arbitrary string of "salt" in it.
This is specified by the Kconfig symbol ``CONFIG_BUILD_SALT``.
+Git
+---
+
+Uncommitted changes or different commit ids in git can also lead
+to different compilation results. For example, after executing
+``git reset HEAD^``, even if the code is the same, the
+``include/config/kernel.release`` generated during compilation
+will be different, which will eventually lead to binary differences.
+See ``scripts/setlocalversion`` for details.
+
.. _KBUILD_BUILD_TIMESTAMP: kbuild.html#kbuild-build-timestamp
.. _KBUILD_BUILD_USER and KBUILD_BUILD_HOST: kbuild.html#kbuild-build-user-kbuild-build-host
.. _KCFLAGS: kbuild.html#kcflags
diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst
index 9a1f020c8449..1717348a4404 100644
--- a/Documentation/kernel-hacking/hacking.rst
+++ b/Documentation/kernel-hacking/hacking.rst
@@ -120,7 +120,7 @@ You can tell you are in a softirq (or tasklet) using the
.. warning::
Beware that this will return a false positive if a
- :ref:`botton half lock <local_bh_disable>` is held.
+ :ref:`bottom half lock <local_bh_disable>` is held.
Some Basic Rules
================
diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst
index e05fb1b8f8b6..6a919cffcbfd 100644
--- a/Documentation/process/2.Process.rst
+++ b/Documentation/process/2.Process.rst
@@ -126,17 +126,10 @@ than one development cycle past their initial release. So, for example, the
5.2.21 was the final stable update of the 5.2 release.
Some kernels are designated "long term" kernels; they will receive support
-for a longer period. As of this writing, the current long term kernels
-and their maintainers are:
-
- ====== ================================ =======================
- 3.16 Ben Hutchings (very long-term kernel)
- 4.4 Greg Kroah-Hartman & Sasha Levin (very long-term kernel)
- 4.9 Greg Kroah-Hartman & Sasha Levin
- 4.14 Greg Kroah-Hartman & Sasha Levin
- 4.19 Greg Kroah-Hartman & Sasha Levin
- 5.4 Greg Kroah-Hartman & Sasha Levin
- ====== ================================ =======================
+for a longer period. Please refer to the following link for the list of active
+long term kernel versions and their maintainers:
+
+ https://www.kernel.org/category/releases.html
The selection of a kernel for long-term support is purely a matter of a
maintainer having the need and the time to maintain that release. There
diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst
index bd15c393ba3c..cb6abcb2b6d0 100644
--- a/Documentation/process/howto.rst
+++ b/Documentation/process/howto.rst
@@ -36,7 +36,7 @@ experience, the following books are good for, if anything, reference:
- "C: A Reference Manual" by Harbison and Steele [Prentice Hall]
The kernel is written using GNU C and the GNU toolchain. While it
-adheres to the ISO C89 standard, it uses a number of extensions that are
+adheres to the ISO C11 standard, it uses a number of extensions that are
not featured in the standard. The kernel is a freestanding C
environment, with no reliance on the standard C library, so some
portions of the C standard are not supported. Arbitrary long long
diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index d14007081595..1fa5ab8754d3 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -319,3 +319,13 @@ unpatched tree to confirm infrastructure didn't mangle it.
Finally, go back and read
:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
to be sure you are not repeating some common mistake documented there.
+
+My company uses peer feedback in employee performance reviews. Can I ask netdev maintainers for feedback?
+---------------------------------------------------------------------------------------------------------
+
+Yes, especially if you spend significant amount of time reviewing code
+and go out of your way to improve shared infrastructure.
+
+The feedback must be requested by you, the contributor, and will always
+be shared with you (even if you request for it to be submitted to your
+manager).
diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst
index c1b685a38f6b..87bd772836c0 100644
--- a/Documentation/trace/histogram.rst
+++ b/Documentation/trace/histogram.rst
@@ -39,7 +39,7 @@ Documentation written by Tom Zanussi
will use the event's kernel stacktrace as the key. The keywords
'keys' or 'key' can be used to specify keys, and the keywords
'values', 'vals', or 'val' can be used to specify values. Compound
- keys consisting of up to two fields can be specified by the 'keys'
+ keys consisting of up to three fields can be specified by the 'keys'
keyword. Hashing a compound key produces a unique entry in the
table for each unique combination of component keys, and can be
useful for providing more fine-grained summaries of event data.
diff --git a/Documentation/translations/it_IT/process/howto.rst b/Documentation/translations/it_IT/process/howto.rst
index 15c08aea1dfe..052f1b3610cb 100644
--- a/Documentation/translations/it_IT/process/howto.rst
+++ b/Documentation/translations/it_IT/process/howto.rst
@@ -44,7 +44,7 @@ altro, utili riferimenti:
- "C: A Reference Manual" di Harbison and Steele [Prentice Hall]
Il kernel è stato scritto usando GNU C e la toolchain GNU.
-Sebbene si attenga allo standard ISO C89, esso utilizza una serie di
+Sebbene si attenga allo standard ISO C11, esso utilizza una serie di
estensioni che non sono previste in questo standard. Il kernel è un
ambiente C indipendente, che non ha alcuna dipendenza dalle librerie
C standard, così alcune parti del C standard non sono supportate.
diff --git a/Documentation/translations/ja_JP/howto.rst b/Documentation/translations/ja_JP/howto.rst
index b47a682d8ded..b8eeb45a02d4 100644
--- a/Documentation/translations/ja_JP/howto.rst
+++ b/Documentation/translations/ja_JP/howto.rst
@@ -65,7 +65,7 @@ Linux カーネル開発のやり方
- 『新・詳説 C 言語 H&S リファレンス』 (サミュエル P ハービソン/ガイ L スティール共著 斉藤 信男監訳)[ソフトバンク]
カーネルは GNU C と GNU ツールチェインを使って書かれています。カーネル
-は ISO C89 仕様に準拠して書く一方で、標準には無い言語拡張を多く使って
+は ISO C11 仕様に準拠して書く一方で、標準には無い言語拡張を多く使って
います。カーネルは標準 C ライブラリに依存しない、C 言語非依存環境です。
そのため、C の標準の中で使えないものもあります。特に任意の long long
の除算や浮動小数点は使えません。カーネルがツールチェインや C 言語拡張
diff --git a/Documentation/translations/ko_KR/howto.rst b/Documentation/translations/ko_KR/howto.rst
index df53fafd1b10..969e91a95bb0 100644
--- a/Documentation/translations/ko_KR/howto.rst
+++ b/Documentation/translations/ko_KR/howto.rst
@@ -62,7 +62,7 @@ Documentation/process/howto.rst
- "Practical C Programming" by Steve Oualline [O'Reilly]
- "C: A Reference Manual" by Harbison and Steele [Prentice Hall]
-커널은 GNU C와 GNU 툴체인을 사용하여 작성되었다. 이 툴들은 ISO C89 표준을
+커널은 GNU C와 GNU 툴체인을 사용하여 작성되었다. 이 툴들은 ISO C11 표준을
따르는 반면 표준에 있지 않은 많은 확장기능도 가지고 있다. 커널은 표준 C
라이브러리와는 관계없이 freestanding C 환경이어서 C 표준의 일부는
지원되지 않는다. 임의의 long long 나누기나 floating point는 지원되지 않는다.
diff --git a/Documentation/translations/zh_CN/process/howto.rst b/Documentation/translations/zh_CN/process/howto.rst
index 5bf953146929..888978a62db3 100644
--- a/Documentation/translations/zh_CN/process/howto.rst
+++ b/Documentation/translations/zh_CN/process/howto.rst
@@ -45,7 +45,7 @@ Linux内核大部分是由C语言写成的,一些体系结构相关的代码
- "C: A Reference Manual" by Harbison and Steele [Prentice Hall]
《C语言参考手册(原书第5版)》(邱仲潘 等译)[机械工业出版社]
-Linux内核使用GNU C和GNU工具链开发。虽然它遵循ISO C89标准,但也用到了一些
+Linux内核使用GNU C和GNU工具链开发。虽然它遵循ISO C11标准,但也用到了一些
标准中没有定义的扩展。内核是自给自足的C环境,不依赖于标准C库的支持,所以
并不支持C标准中的部分定义。比如long long类型的大数除法和浮点运算就不允许
使用。有时候确实很难弄清楚内核对工具链的要求和它所使用的扩展,不幸的是目
diff --git a/Documentation/translations/zh_TW/process/howto.rst b/Documentation/translations/zh_TW/process/howto.rst
index 86b0d4c6d6f9..8fb8edcaee66 100644
--- a/Documentation/translations/zh_TW/process/howto.rst
+++ b/Documentation/translations/zh_TW/process/howto.rst
@@ -48,7 +48,7 @@ Linux內核大部分是由C語言寫成的,一些體系結構相關的代碼
- "C: A Reference Manual" by Harbison and Steele [Prentice Hall]
《C語言參考手冊(原書第5版)》(邱仲潘 等譯)[機械工業出版社]
-Linux內核使用GNU C和GNU工具鏈開發。雖然它遵循ISO C89標準,但也用到了一些
+Linux內核使用GNU C和GNU工具鏈開發。雖然它遵循ISO C11標準,但也用到了一些
標準中沒有定義的擴展。內核是自給自足的C環境,不依賴於標準C庫的支持,所以
並不支持C標準中的部分定義。比如long long類型的大數除法和浮點運算就不允許
使用。有時候確實很難弄清楚內核對工具鏈的要求和它所使用的擴展,不幸的是目
diff --git a/Documentation/virt/kvm/devices/vm.rst b/Documentation/virt/kvm/devices/vm.rst
index 0aa5b1cfd700..60acc39e0e93 100644
--- a/Documentation/virt/kvm/devices/vm.rst
+++ b/Documentation/virt/kvm/devices/vm.rst
@@ -215,6 +215,7 @@ KVM_S390_VM_TOD_EXT).
:Parameters: address of a buffer in user space to store the data (u8) to
:Returns: -EFAULT if the given address is not accessible from kernel space;
-EINVAL if setting the TOD clock extension to != 0 is not supported
+ -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
3.2. ATTRIBUTE: KVM_S390_VM_TOD_LOW
-----------------------------------
@@ -224,6 +225,7 @@ the POP (u64).
:Parameters: address of a buffer in user space to store the data (u64) to
:Returns: -EFAULT if the given address is not accessible from kernel space
+ -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
3.3. ATTRIBUTE: KVM_S390_VM_TOD_EXT
-----------------------------------
@@ -237,6 +239,7 @@ it, it is stored as 0 and not allowed to be set to a value != 0.
(kvm_s390_vm_tod_clock) to
:Returns: -EFAULT if the given address is not accessible from kernel space;
-EINVAL if setting the TOD clock extension to != 0 is not supported
+ -EOPNOTSUPP for a PV guest (TOD managed by the ultravisor)
4. GROUP: KVM_S390_VM_CRYPTO
============================
diff --git a/MAINTAINERS b/MAINTAINERS
index e04d944005ba..89672a59c0c3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3984,7 +3984,7 @@ M: Rafał Miłecki <rafal@milecki.pl>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: Documentation/devicetree/bindings/arm/bcm/brcm,bcmbca.yaml
F: arch/arm64/boot/dts/broadcom/bcmbca/*
N: bcmbca
@@ -4009,7 +4009,7 @@ R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
F: drivers/pci/controller/pcie-brcmstb.c
F: drivers/staging/vc04_services
@@ -4023,7 +4023,7 @@ M: Ray Jui <rjui@broadcom.com>
M: Scott Branden <sbranden@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
S: Maintained
-T: git git://github.com/broadcom/mach-bcm
+T: git https://github.com/broadcom/mach-bcm
F: arch/arm/mach-bcm/
N: bcm281*
N: bcm113*
@@ -4088,7 +4088,7 @@ M: Florian Fainelli <f.fainelli@gmail.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: Documentation/devicetree/bindings/pci/brcm,stb-pcie.yaml
F: arch/arm/boot/dts/bcm7*.dts*
F: arch/arm/include/asm/hardware/cache-b15-rac.h
@@ -4101,6 +4101,7 @@ N: bcm7038
N: bcm7120
BROADCOM BDC DRIVER
+M: Justin Chen <justinpopo6@gmail.com>
M: Al Cooper <alcooperx@gmail.com>
L: linux-usb@vger.kernel.org
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
@@ -4120,7 +4121,7 @@ M: Florian Fainelli <f.fainelli@gmail.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-mips@vger.kernel.org
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: arch/mips/bmips/*
F: arch/mips/boot/dts/brcm/bcm*.dts*
F: arch/mips/include/asm/mach-bmips/*
@@ -4207,6 +4208,7 @@ F: Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml
F: drivers/tty/serial/8250/8250_bcm7271.c
BROADCOM BRCMSTB USB EHCI DRIVER
+M: Justin Chen <justinpopo6@gmail.com>
M: Al Cooper <alcooperx@gmail.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-usb@vger.kernel.org
@@ -4223,6 +4225,7 @@ F: Documentation/devicetree/bindings/usb/brcm,usb-pinmap.yaml
F: drivers/usb/misc/brcmstb-usb-pinmap.c
BROADCOM BRCMSTB USB2 and USB3 PHY DRIVER
+M: Justin Chen <justinpopo6@gmail.com>
M: Al Cooper <alcooperx@gmail.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-kernel@vger.kernel.org
@@ -4259,7 +4262,7 @@ M: Scott Branden <sbranden@broadcom.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: arch/arm64/boot/dts/broadcom/northstar2/*
F: arch/arm64/boot/dts/broadcom/stingray/*
F: drivers/clk/bcm/clk-ns*
@@ -4329,7 +4332,7 @@ M: Florian Fainelli <f.fainelli@gmail.com>
R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
L: linux-pm@vger.kernel.org
S: Maintained
-T: git git://github.com/broadcom/stblinux.git
+T: git https://github.com/broadcom/stblinux.git
F: drivers/soc/bcm/bcm63xx/bcm-pmb.c
F: include/dt-bindings/soc/bcm-pmb.h
@@ -5038,7 +5041,7 @@ F: drivers/scsi/snic/
CISCO VIC ETHERNET NIC DRIVER
M: Christian Benvenuti <benve@cisco.com>
-M: Govindarajulu Varadarajan <_govind@gmx.com>
+M: Satish Kharat <satishkh@cisco.com>
S: Supported
F: drivers/net/ethernet/cisco/enic/
@@ -9214,7 +9217,7 @@ W: https://www.hisilicon.com
F: drivers/i2c/busses/i2c-hisi.c
HISILICON LPC BUS DRIVER
-M: john.garry@huawei.com
+M: Jay Fang <f.fangjian@huawei.com>
S: Maintained
W: http://www.hisilicon.com
F: Documentation/devicetree/bindings/arm/hisilicon/low-pin-count.yaml
@@ -9775,7 +9778,10 @@ S: Supported
F: drivers/pci/hotplug/rpaphp*
IBM Power SRIOV Virtual NIC Device Driver
-M: Dany Madden <drt@linux.ibm.com>
+M: Haren Myneni <haren@linux.ibm.com>
+M: Rick Lindsley <ricklind@linux.ibm.com>
+R: Nick Child <nnac123@linux.ibm.com>
+R: Dany Madden <danymadden@us.ibm.com>
R: Thomas Falcon <tlfalcon@linux.ibm.com>
L: netdev@vger.kernel.org
S: Supported
@@ -11245,7 +11251,7 @@ L: kvm@vger.kernel.org
L: kvm-riscv@lists.infradead.org
L: linux-riscv@lists.infradead.org
S: Maintained
-T: git git://github.com/kvm-riscv/linux.git
+T: git https://github.com/kvm-riscv/linux.git
F: arch/riscv/include/asm/kvm*
F: arch/riscv/include/uapi/asm/kvm*
F: arch/riscv/kvm/
@@ -11258,7 +11264,6 @@ M: Claudio Imbrenda <imbrenda@linux.ibm.com>
R: David Hildenbrand <david@redhat.com>
L: kvm@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux.git
F: Documentation/virt/kvm/s390*
F: arch/s390/include/asm/gmap.h
@@ -11319,6 +11324,16 @@ F: arch/x86/kvm/svm/hyperv.*
F: arch/x86/kvm/svm/svm_onhyperv.*
F: arch/x86/kvm/vmx/evmcs.*
+KVM X86 Xen (KVM/Xen)
+M: David Woodhouse <dwmw2@infradead.org>
+M: Paul Durrant <paul@xen.org>
+M: Sean Christopherson <seanjc@google.com>
+M: Paolo Bonzini <pbonzini@redhat.com>
+L: kvm@vger.kernel.org
+S: Supported
+T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
+F: arch/x86/kvm/xen.*
+
KERNFS
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
M: Tejun Heo <tj@kernel.org>
@@ -14524,7 +14539,7 @@ L: linux-nilfs@vger.kernel.org
S: Supported
W: https://nilfs.sourceforge.io/
W: https://nilfs.osdn.jp/
-T: git git://github.com/konis/nilfs2.git
+T: git https://github.com/konis/nilfs2.git
F: Documentation/filesystems/nilfs2.rst
F: fs/nilfs2/
F: include/trace/events/nilfs2.h
@@ -15436,6 +15451,7 @@ S: Maintained
W: http://openvswitch.org
F: include/uapi/linux/openvswitch.h
F: net/openvswitch/
+F: tools/testing/selftests/net/openvswitch/
OPERATING PERFORMANCE POINTS (OPP)
M: Viresh Kumar <vireshk@kernel.org>
@@ -15627,7 +15643,7 @@ F: drivers/input/serio/gscps2.c
F: drivers/input/serio/hp_sdc*
F: drivers/parisc/
F: drivers/parport/parport_gsc.*
-F: drivers/tty/serial/8250/8250_gsc.c
+F: drivers/tty/serial/8250/8250_parisc.c
F: drivers/video/console/sti*
F: drivers/video/fbdev/sti*
F: drivers/video/logo/logo_parisc*
@@ -16675,6 +16691,7 @@ F: Documentation/driver-api/ptp.rst
F: drivers/net/phy/dp83640*
F: drivers/ptp/*
F: include/linux/ptp_cl*
+K: (?:\b|_)ptp(?:\b|_)
PTP VIRTUAL CLOCK SUPPORT
M: Yangbo Lu <yangbo.lu@nxp.com>
@@ -17811,7 +17828,7 @@ S: Odd Fixes
F: drivers/tty/serial/rp2.*
ROHM BD99954 CHARGER IC
-R: Matti Vaittinen <mazziesaccount@gmail.com>
+M: Matti Vaittinen <mazziesaccount@gmail.com>
S: Supported
F: drivers/power/supply/bd99954-charger.c
F: drivers/power/supply/bd99954-charger.h
@@ -17834,7 +17851,7 @@ F: drivers/regulator/bd9571mwv-regulator.c
F: include/linux/mfd/bd9571mwv.h
ROHM POWER MANAGEMENT IC DEVICE DRIVERS
-R: Matti Vaittinen <mazziesaccount@gmail.com>
+M: Matti Vaittinen <mazziesaccount@gmail.com>
S: Supported
F: drivers/clk/clk-bd718x7.c
F: drivers/gpio/gpio-bd71815.c
@@ -17996,7 +18013,6 @@ R: Christian Borntraeger <borntraeger@linux.ibm.com>
R: Sven Schnelle <svens@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git
F: Documentation/driver-api/s390-drivers.rst
F: Documentation/s390/
@@ -18008,7 +18024,6 @@ M: Vineeth Vijayan <vneethv@linux.ibm.com>
M: Peter Oberparleiter <oberpar@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/cio/
S390 DASD DRIVER
@@ -18016,7 +18031,6 @@ M: Stefan Haberland <sth@linux.ibm.com>
M: Jan Hoeppner <hoeppner@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: block/partitions/ibm.c
F: drivers/s390/block/dasd*
F: include/linux/dasd_mod.h
@@ -18026,7 +18040,6 @@ M: Matthew Rosato <mjrosato@linux.ibm.com>
M: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/iommu/s390-iommu.c
S390 IUCV NETWORK LAYER
@@ -18035,7 +18048,6 @@ M: Wenjia Zhang <wenjia@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: netdev@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/net/*iucv*
F: include/net/iucv/
F: net/iucv/
@@ -18046,7 +18058,6 @@ M: Wenjia Zhang <wenjia@linux.ibm.com>
L: linux-s390@vger.kernel.org
L: netdev@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/net/
S390 PCI SUBSYSTEM
@@ -18054,7 +18065,6 @@ M: Niklas Schnelle <schnelle@linux.ibm.com>
M: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: arch/s390/pci/
F: drivers/pci/hotplug/s390_pci_hpc.c
F: Documentation/s390/pci.rst
@@ -18065,7 +18075,6 @@ M: Halil Pasic <pasic@linux.ibm.com>
M: Jason Herne <jjherne@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: Documentation/s390/vfio-ap*
F: drivers/s390/crypto/vfio_ap*
@@ -18094,7 +18103,6 @@ S390 ZCRYPT DRIVER
M: Harald Freudenberger <freude@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/crypto/
S390 ZFCP DRIVER
@@ -18102,7 +18110,6 @@ M: Steffen Maier <maier@linux.ibm.com>
M: Benjamin Block <bblock@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: drivers/s390/scsi/zfcp_*
S3C ADC BATTERY DRIVER
@@ -18674,7 +18681,6 @@ M: Wenjia Zhang <wenjia@linux.ibm.com>
M: Jan Karcher <jaka@linux.ibm.com>
L: linux-s390@vger.kernel.org
S: Supported
-W: http://www.ibm.com/developerworks/linux/linux390/
F: net/smc/
SHARP GP2AP002A00F/GP2AP002S00F SENSOR DRIVER
@@ -18785,7 +18791,7 @@ M: Palmer Dabbelt <palmer@dabbelt.com>
M: Paul Walmsley <paul.walmsley@sifive.com>
L: linux-riscv@lists.infradead.org
S: Supported
-T: git git://github.com/sifive/riscv-linux.git
+T: git https://github.com/sifive/riscv-linux.git
N: sifive
K: [^@]sifive
@@ -21189,15 +21195,6 @@ S: Maintained
F: Documentation/usb/ehci.rst
F: drivers/usb/host/ehci*
-USB GADGET/PERIPHERAL SUBSYSTEM
-M: Felipe Balbi <balbi@kernel.org>
-L: linux-usb@vger.kernel.org
-S: Maintained
-W: http://www.linux-usb.org/gadget
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-F: drivers/usb/gadget/
-F: include/linux/usb/gadget*
-
USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
M: Jiri Kosina <jikos@kernel.org>
M: Benjamin Tissoires <benjamin.tissoires@redhat.com>
@@ -21304,13 +21301,6 @@ W: https://github.com/petkan/pegasus
T: git https://github.com/petkan/pegasus.git
F: drivers/net/usb/pegasus.*
-USB PHY LAYER
-M: Felipe Balbi <balbi@kernel.org>
-L: linux-usb@vger.kernel.org
-S: Maintained
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
-F: drivers/usb/phy/
-
USB PRINTER DRIVER (usblp)
M: Pete Zaitcev <zaitcev@redhat.com>
L: linux-usb@vger.kernel.org
diff --git a/Makefile b/Makefile
index d148a55bfd0f..ac2ec990422d 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 1
SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
NAME = Hurr durr I'ma ninja sloth
# *DOCUMENTATION*
@@ -1218,7 +1218,7 @@ quiet_cmd_ar_vmlinux.a = AR $@
cmd_ar_vmlinux.a = \
rm -f $@; \
$(AR) cDPrST $@ $(KBUILD_VMLINUX_OBJS); \
- $(AR) mPiT $$($(AR) t $@ | head -n1) $@ $$($(AR) t $@ | grep -F --file=$(srctree)/scripts/head-object-list.txt)
+ $(AR) mPiT $$($(AR) t $@ | sed -n 1p) $@ $$($(AR) t $@ | grep -F -f $(srctree)/scripts/head-object-list.txt)
targets += vmlinux.a
vmlinux.a: $(KBUILD_VMLINUX_OBJS) scripts/head-object-list.txt autoksyms_recursive FORCE
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index cd1edcf4f95e..3434c8131ecd 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -103,11 +103,11 @@
dma-coherent;
};
- ehci@40000 {
+ usb@40000 {
dma-coherent;
};
- ohci@60000 {
+ usb@60000 {
dma-coherent;
};
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 70779386ca79..67556f4b7057 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -110,11 +110,11 @@
dma-coherent;
};
- ehci@40000 {
+ usb@40000 {
dma-coherent;
};
- ohci@60000 {
+ usb@60000 {
dma-coherent;
};
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 99d3e7175bf7..b64435385304 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -87,13 +87,13 @@
mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */
};
- ehci@40000 {
+ usb@40000 {
compatible = "generic-ehci";
reg = < 0x40000 0x100 >;
interrupts = < 8 >;
};
- ohci@60000 {
+ usb@60000 {
compatible = "generic-ohci";
reg = < 0x60000 0x100 >;
interrupts = < 8 >;
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index f48ba03e9b5e..6691f4255077 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -234,7 +234,7 @@
};
};
- ohci@60000 {
+ usb@60000 {
compatible = "snps,hsdk-v1.0-ohci", "generic-ohci";
reg = <0x60000 0x100>;
interrupts = <15>;
@@ -242,7 +242,7 @@
dma-coherent;
};
- ehci@40000 {
+ usb@40000 {
compatible = "snps,hsdk-v1.0-ehci", "generic-ehci";
reg = <0x40000 0x100>;
interrupts = <15>;
diff --git a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
index cbb179770293..90a412026e64 100644
--- a/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/vdk_axs10x_mb.dtsi
@@ -46,7 +46,7 @@
clock-names = "stmmaceth";
};
- ehci@40000 {
+ usb@40000 {
compatible = "generic-ehci";
reg = < 0x40000 0x100 >;
interrupts = < 8 >;
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index e31a8ebc3ecc..81764160451f 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -35,9 +35,6 @@ CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
CONFIG_DEVTMPFS=y
# CONFIG_STANDALONE is not set
@@ -99,7 +96,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_SOFTLOCKUP_DETECTOR=y
CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index e0e8567f0d75..d5181275490e 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -34,9 +34,6 @@ CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
CONFIG_DEVTMPFS=y
# CONFIG_STANDALONE is not set
@@ -97,7 +94,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_SOFTLOCKUP_DETECTOR=y
CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index fcbc952bc75b..2f336d99a8cf 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -35,9 +35,6 @@ CONFIG_IP_PNP=y
CONFIG_IP_PNP_DHCP=y
CONFIG_IP_PNP_BOOTP=y
CONFIG_IP_PNP_RARP=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
CONFIG_DEVTMPFS=y
# CONFIG_STANDALONE is not set
@@ -100,7 +97,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_SOFTLOCKUP_DETECTOR=y
CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index d87ad7e88d62..899b2fd5c71d 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y
CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_DEBUG_MEMORY_INIT=y
# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index 8d82cdb7f86a..0d32aac8069f 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -59,6 +59,5 @@ CONFIG_EXT2_FS_XATTR=y
CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_SOFTLOCKUP_DETECTOR=y
# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index f856b03e0fb5..d18378d2c2a6 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -85,7 +85,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_SOFTLOCKUP_DETECTOR=y
CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index a1ce12bf5b16..3e9829775992 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -56,5 +56,4 @@ CONFIG_EXT2_FS_XATTR=y
CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
-# CONFIG_ENABLE_MUST_CHECK is not set
# CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index ca10f4a2c823..502c87f351c8 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -65,4 +65,3 @@ CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 31b6ec3683c6..f721cc3997d0 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -63,4 +63,3 @@ CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index 41a0037f48a5..1419fc946a08 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -26,9 +26,6 @@ CONFIG_UNIX=y
CONFIG_UNIX_DIAG=y
CONFIG_NET_KEY=y
CONFIG_INET=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
CONFIG_DEVTMPFS=y
@@ -37,7 +34,6 @@ CONFIG_DEVTMPFS=y
# CONFIG_BLK_DEV is not set
CONFIG_NETDEVICES=y
# CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
CONFIG_EZCHIP_NPS_MANAGEMENT_ENET=y
# CONFIG_NET_VENDOR_INTEL is not set
@@ -74,5 +70,5 @@ CONFIG_TMPFS=y
# CONFIG_MISC_FILESYSTEMS is not set
CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_FTRACE=y
+# CONFIG_NET_VENDOR_CADENCE is not set
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 4a94d1684ed6..6f0d2be9d926 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -35,15 +35,11 @@ CONFIG_PACKET=y
CONFIG_UNIX=y
CONFIG_INET=y
CONFIG_IP_MULTICAST=y
-# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
-# CONFIG_INET_XFRM_MODE_TUNNEL is not set
-# CONFIG_INET_XFRM_MODE_BEET is not set
# CONFIG_INET_DIAG is not set
# CONFIG_IPV6 is not set
# CONFIG_WIRELESS is not set
CONFIG_DEVTMPFS=y
CONFIG_NETDEVICES=y
-# CONFIG_NET_CADENCE is not set
# CONFIG_NET_VENDOR_BROADCOM is not set
# CONFIG_NET_VENDOR_INTEL is not set
# CONFIG_NET_VENDOR_MARVELL is not set
@@ -94,12 +90,11 @@ CONFIG_DEBUG_INFO_DWARF_TOOLCHAIN_DEFAULT=y
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_FS=y
CONFIG_HEADERS_INSTALL=y
-CONFIG_HEADERS_CHECK=y
CONFIG_DEBUG_SECTION_MISMATCH=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_DEBUG_STACKOVERFLOW=y
CONFIG_DETECT_HUNG_TASK=y
CONFIG_SCHEDSTATS=y
-CONFIG_TIMER_STATS=y
# CONFIG_CRYPTO_HW is not set
+# CONFIG_NET_VENDOR_CADENCE is not set
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index 0c3b21416819..d3ef189c75f8 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -58,8 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y
# CONFIG_HW_RANDOM is not set
# CONFIG_HWMON is not set
CONFIG_FB=y
-CONFIG_ARCPGU_RGB888=y
-CONFIG_ARCPGU_DISPTYPE=0
# CONFIG_VGA_CONSOLE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
@@ -87,7 +85,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_SHIRQ=y
CONFIG_SOFTLOCKUP_DETECTOR=y
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index f9ad9d3ee702..944b347025fd 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -91,7 +91,6 @@ CONFIG_NFS_FS=y
CONFIG_NFS_V3_ACL=y
CONFIG_NLS_CODEPAGE_437=y
CONFIG_NLS_ISO8859_1=y
-# CONFIG_ENABLE_MUST_CHECK is not set
CONFIG_STRIP_ASM_SYMS=y
CONFIG_DEBUG_SHIRQ=y
CONFIG_SOFTLOCKUP_DETECTOR=y
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index bdb7e190a294..f5a936496f06 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -82,7 +82,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x)
/*
* __fls: Similar to fls, but zero based (0-31)
*/
-static inline __attribute__ ((const)) int __fls(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __fls(unsigned long x)
{
if (!x)
return 0;
@@ -131,7 +131,7 @@ static inline __attribute__ ((const)) int fls(unsigned int x)
/*
* __fls: Similar to fls, but zero based (0-31). Also 0 if no bit set
*/
-static inline __attribute__ ((const)) int __fls(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __fls(unsigned long x)
{
/* FLS insn has exactly same semantics as the API */
return __builtin_arc_fls(x);
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index 5aab4f93ab8a..67ff06e15cea 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -21,7 +21,7 @@
* r25 contains the kernel current task ptr
* - Defined Stack Switching Macro to be reused in all intr/excp hdlrs
* - Shaved off 11 instructions from RESTORE_ALL_INT1 by using the
- * address Write back load ld.ab instead of seperate ld/add instn
+ * address Write back load ld.ab instead of separate ld/add instn
*
* Amit Bhor, Sameer Dhavale: Codito Technologies 2004
*/
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index 8f777d6441a5..80347382a380 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -32,7 +32,7 @@ static inline void ioport_unmap(void __iomem *addr)
{
}
-extern void iounmap(const void __iomem *addr);
+extern void iounmap(const volatile void __iomem *addr);
/*
* io{read,write}{16,32}be() macros
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
index 64ca25d199be..ef68758b69f7 100644
--- a/arch/arc/include/asm/pgtable-levels.h
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -161,7 +161,7 @@
#define pmd_pfn(pmd) ((pmd_val(pmd) & PAGE_MASK) >> PAGE_SHIFT)
#define pmd_page(pmd) virt_to_page(pmd_page_vaddr(pmd))
#define set_pmd(pmdp, pmd) (*(pmdp) = pmd)
-#define pmd_pgtable(pmd) ((pgtable_t) pmd_page_vaddr(pmd))
+#define pmd_pgtable(pmd) ((pgtable_t) pmd_page(pmd))
/*
* 4th level paging: pte
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index ab9e75e90f72..ad93fe6e4b77 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -385,7 +385,7 @@ irqreturn_t do_IPI(int irq, void *dev_id)
* API called by platform code to hookup arch-common ISR to their IPI IRQ
*
* Note: If IPI is provided by platform (vs. say ARC MCIP), their intc setup/map
- * function needs to call call irq_set_percpu_devid() for IPI IRQ, otherwise
+ * function needs to call irq_set_percpu_devid() for IPI IRQ, otherwise
* request_percpu_irq() below will fail
*/
static DEFINE_PER_CPU(int, ipi_dev);
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 5446967ea98d..55c6de138eae 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -750,7 +750,7 @@ static inline void arc_slc_enable(void)
* -In SMP, if hardware caches are coherent
*
* There's a corollary case, where kernel READs from a userspace mapped page.
- * If the U-mapping is not congruent to to K-mapping, former needs flushing.
+ * If the U-mapping is not congruent to K-mapping, former needs flushing.
*/
void flush_dcache_page(struct page *page)
{
@@ -910,7 +910,7 @@ EXPORT_SYMBOL(flush_icache_range);
* @vaddr is typically user vaddr (breakpoint) or kernel vaddr (vmalloc)
* However in one instance, when called by kprobe (for a breakpt in
* builtin kernel code) @vaddr will be paddr only, meaning CDU operation will
- * use a paddr to index the cache (despite VIPT). This is fine since since a
+ * use a paddr to index the cache (despite VIPT). This is fine since a
* builtin kernel page will not have any virtual mappings.
* kprobe on loadable module will be kernel vaddr.
*/
diff --git a/arch/arc/mm/ioremap.c b/arch/arc/mm/ioremap.c
index 0ee75aca6e10..712c2311daef 100644
--- a/arch/arc/mm/ioremap.c
+++ b/arch/arc/mm/ioremap.c
@@ -94,7 +94,7 @@ void __iomem *ioremap_prot(phys_addr_t paddr, unsigned long size,
EXPORT_SYMBOL(ioremap_prot);
-void iounmap(const void __iomem *addr)
+void iounmap(const volatile void __iomem *addr)
{
/* weird double cast to handle phys_addr_t > 32 bits */
if (arc_uncached_addr_space((phys_addr_t)(u32)addr))
diff --git a/arch/arm/boot/dts/imx6q-yapp4-crux.dts b/arch/arm/boot/dts/imx6q-yapp4-crux.dts
index 15f4824a5142..bddf3822ebf7 100644
--- a/arch/arm/boot/dts/imx6q-yapp4-crux.dts
+++ b/arch/arm/boot/dts/imx6q-yapp4-crux.dts
@@ -33,6 +33,10 @@
status = "okay";
};
+&reg_pu {
+ regulator-always-on;
+};
+
&reg_usb_h1_vbus {
status = "okay";
};
diff --git a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi
index 68e5ab2e27e2..6bb4855d13ce 100644
--- a/arch/arm/boot/dts/imx6qdl-gw5910.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw5910.dtsi
@@ -29,7 +29,7 @@
user-pb {
label = "user_pb";
- gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>;
+ gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>;
linux,code = <BTN_0>;
};
diff --git a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi
index 8e23cec7149e..696427b487f0 100644
--- a/arch/arm/boot/dts/imx6qdl-gw5913.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw5913.dtsi
@@ -26,7 +26,7 @@
user-pb {
label = "user_pb";
- gpios = <&gsc_gpio 0 GPIO_ACTIVE_LOW>;
+ gpios = <&gsc_gpio 2 GPIO_ACTIVE_LOW>;
linux,code = <BTN_0>;
};
diff --git a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts
index cea165f2161a..afaf4a6759d4 100644
--- a/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts
+++ b/arch/arm/boot/dts/imx6qp-yapp4-crux-plus.dts
@@ -33,6 +33,10 @@
status = "okay";
};
+&reg_pu {
+ regulator-always-on;
+};
+
&reg_usb_h1_vbus {
status = "okay";
};
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index fbaa0ce46427..8f1bb78fc1e4 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -24,6 +24,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 1c9094f24893..e2f0cdacba7d 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -28,6 +28,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts
index d6940e0afa86..27a3ab7e25e1 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-codina-tmo.dts
@@ -44,6 +44,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
index 5f41256d7f4b..b88f0c07873d 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-codina.dts
@@ -57,6 +57,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
index 806da3fc33cd..7231bc745200 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-gavini.dts
@@ -30,6 +30,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
index b0dce91aff4b..9604695edf53 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-golden.dts
@@ -35,6 +35,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts
index ed5c79c3d04b..69387e8754a9 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-janice.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-janice.dts
@@ -30,6 +30,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts
index c57676faf181..167846df3104 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-kyle.dts
@@ -34,6 +34,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts
index 81b341a5ae45..93e5f5ed888d 100644
--- a/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts
+++ b/arch/arm/boot/dts/ste-ux500-samsung-skomer.dts
@@ -30,6 +30,14 @@
polling-delay = <0>;
polling-delay-passive = <0>;
thermal-sensors = <&bat_therm>;
+
+ trips {
+ battery-crit-hi {
+ temperature = <70000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
};
diff --git a/arch/arm64/boot/dts/arm/juno-base.dtsi b/arch/arm64/boot/dts/arm/juno-base.dtsi
index 2f27619d8abd..8b4d280b1e7e 100644
--- a/arch/arm64/boot/dts/arm/juno-base.dtsi
+++ b/arch/arm64/boot/dts/arm/juno-base.dtsi
@@ -751,12 +751,26 @@
polling-delay = <1000>;
polling-delay-passive = <100>;
thermal-sensors = <&scpi_sensors0 0>;
+ trips {
+ pmic_crit0: trip0 {
+ temperature = <90000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
soc {
polling-delay = <1000>;
polling-delay-passive = <100>;
thermal-sensors = <&scpi_sensors0 3>;
+ trips {
+ soc_crit0: trip0 {
+ temperature = <80000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
};
big_cluster_thermal_zone: big-cluster {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
index 421d879013d7..260d045dbd9a 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1088a.dtsi
@@ -779,6 +779,9 @@
little-endian;
#address-cells = <1>;
#size-cells = <0>;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(1)>;
status = "disabled";
};
@@ -788,6 +791,9 @@
little-endian;
#address-cells = <1>;
#size-cells = <0>;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(1)>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index f1b9cc8714dc..348d9e3a9125 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -532,6 +532,9 @@
little-endian;
#address-cells = <1>;
#size-cells = <0>;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(2)>;
status = "disabled";
};
@@ -541,6 +544,9 @@
little-endian;
#address-cells = <1>;
#size-cells = <0>;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(2)>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 6680fb2a6dc9..8c76d86cb756 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -1385,6 +1385,9 @@
#address-cells = <1>;
#size-cells = <0>;
little-endian;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(2)>;
status = "disabled";
};
@@ -1395,6 +1398,9 @@
little-endian;
#address-cells = <1>;
#size-cells = <0>;
+ clock-frequency = <2500000>;
+ clocks = <&clockgen QORIQ_CLK_PLATFORM_PLL
+ QORIQ_CLK_PLL_DIV(2)>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
index 82a1c4488378..10370d1a6c6d 100644
--- a/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8-ss-conn.dtsi
@@ -38,9 +38,9 @@ conn_subsys: bus@5b000000 {
interrupts = <GIC_SPI 232 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b010000 0x10000>;
clocks = <&sdhc0_lpcg IMX_LPCG_CLK_4>,
- <&sdhc0_lpcg IMX_LPCG_CLK_5>,
- <&sdhc0_lpcg IMX_LPCG_CLK_0>;
- clock-names = "ipg", "per", "ahb";
+ <&sdhc0_lpcg IMX_LPCG_CLK_0>,
+ <&sdhc0_lpcg IMX_LPCG_CLK_5>;
+ clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_0>;
status = "disabled";
};
@@ -49,9 +49,9 @@ conn_subsys: bus@5b000000 {
interrupts = <GIC_SPI 233 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b020000 0x10000>;
clocks = <&sdhc1_lpcg IMX_LPCG_CLK_4>,
- <&sdhc1_lpcg IMX_LPCG_CLK_5>,
- <&sdhc1_lpcg IMX_LPCG_CLK_0>;
- clock-names = "ipg", "per", "ahb";
+ <&sdhc1_lpcg IMX_LPCG_CLK_0>,
+ <&sdhc1_lpcg IMX_LPCG_CLK_5>;
+ clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_1>;
fsl,tuning-start-tap = <20>;
fsl,tuning-step = <2>;
@@ -62,9 +62,9 @@ conn_subsys: bus@5b000000 {
interrupts = <GIC_SPI 234 IRQ_TYPE_LEVEL_HIGH>;
reg = <0x5b030000 0x10000>;
clocks = <&sdhc2_lpcg IMX_LPCG_CLK_4>,
- <&sdhc2_lpcg IMX_LPCG_CLK_5>,
- <&sdhc2_lpcg IMX_LPCG_CLK_0>;
- clock-names = "ipg", "per", "ahb";
+ <&sdhc2_lpcg IMX_LPCG_CLK_0>,
+ <&sdhc2_lpcg IMX_LPCG_CLK_5>;
+ clock-names = "ipg", "ahb", "per";
power-domains = <&pd IMX_SC_R_SDHC_2>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
index 32f6f2f50c10..43e89859c044 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mm-mx8menlo.dts
@@ -250,21 +250,21 @@
/* SODIMM 96 */
MX8MM_IOMUXC_SAI1_RXD2_GPIO4_IO4 0x1c4
/* CPLD_D[7] */
- MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x1c4
+ MX8MM_IOMUXC_SAI1_RXD3_GPIO4_IO5 0x184
/* CPLD_D[6] */
- MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x1c4
+ MX8MM_IOMUXC_SAI1_RXFS_GPIO4_IO0 0x184
/* CPLD_D[5] */
- MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x1c4
+ MX8MM_IOMUXC_SAI1_TXC_GPIO4_IO11 0x184
/* CPLD_D[4] */
- MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x1c4
+ MX8MM_IOMUXC_SAI1_TXD0_GPIO4_IO12 0x184
/* CPLD_D[3] */
- MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x1c4
+ MX8MM_IOMUXC_SAI1_TXD1_GPIO4_IO13 0x184
/* CPLD_D[2] */
- MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x1c4
+ MX8MM_IOMUXC_SAI1_TXD2_GPIO4_IO14 0x184
/* CPLD_D[1] */
- MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x1c4
+ MX8MM_IOMUXC_SAI1_TXD3_GPIO4_IO15 0x184
/* CPLD_D[0] */
- MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x1c4
+ MX8MM_IOMUXC_SAI1_TXD4_GPIO4_IO16 0x184
/* KBD_intK */
MX8MM_IOMUXC_SAI2_MCLK_GPIO4_IO27 0x1c4
/* DISP_reset */
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index afb90f59c83c..dabd94dc30c4 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -276,6 +276,7 @@
assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>;
assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>;
clock-names = "main_clk";
+ power-domains = <&pgc_otg1>;
};
usbphynop2: usbphynop2 {
@@ -285,6 +286,7 @@
assigned-clocks = <&clk IMX8MM_CLK_USB_PHY_REF>;
assigned-clock-parents = <&clk IMX8MM_SYS_PLL1_100M>;
clock-names = "main_clk";
+ power-domains = <&pgc_otg2>;
};
soc: soc@0 {
@@ -674,13 +676,11 @@
pgc_otg1: power-domain@2 {
#power-domain-cells = <0>;
reg = <IMX8MM_POWER_DOMAIN_OTG1>;
- power-domains = <&pgc_hsiomix>;
};
pgc_otg2: power-domain@3 {
#power-domain-cells = <0>;
reg = <IMX8MM_POWER_DOMAIN_OTG2>;
- power-domains = <&pgc_hsiomix>;
};
pgc_gpumix: power-domain@4 {
@@ -1186,7 +1186,7 @@
assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>;
phys = <&usbphynop1>;
fsl,usbmisc = <&usbmisc1 0>;
- power-domains = <&pgc_otg1>;
+ power-domains = <&pgc_hsiomix>;
status = "disabled";
};
@@ -1206,7 +1206,7 @@
assigned-clock-parents = <&clk IMX8MM_SYS_PLL2_500M>;
phys = <&usbphynop2>;
fsl,usbmisc = <&usbmisc2 0>;
- power-domains = <&pgc_otg2>;
+ power-domains = <&pgc_hsiomix>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index cb2836bfbd95..ad0b99adf691 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -662,7 +662,6 @@
pgc_otg1: power-domain@1 {
#power-domain-cells = <0>;
reg = <IMX8MN_POWER_DOMAIN_OTG1>;
- power-domains = <&pgc_hsiomix>;
};
pgc_gpumix: power-domain@2 {
@@ -1076,7 +1075,7 @@
assigned-clock-parents = <&clk IMX8MN_SYS_PLL2_500M>;
phys = <&usbphynop1>;
fsl,usbmisc = <&usbmisc1 0>;
- power-domains = <&pgc_otg1>;
+ power-domains = <&pgc_hsiomix>;
status = "disabled";
};
@@ -1175,5 +1174,6 @@
assigned-clocks = <&clk IMX8MN_CLK_USB_PHY_REF>;
assigned-clock-parents = <&clk IMX8MN_SYS_PLL1_100M>;
clock-names = "main_clk";
+ power-domains = <&pgc_otg1>;
};
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
index 7b712d1888ea..5dcd1de586b5 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin.dtsi
@@ -354,16 +354,6 @@
"SODIMM_82",
"SODIMM_70",
"SODIMM_72";
-
- ctrl-sleep-moci-hog {
- gpio-hog;
- /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */
- gpios = <29 GPIO_ACTIVE_HIGH>;
- line-name = "CTRL_SLEEP_MOCI#";
- output-high;
- pinctrl-names = "default";
- pinctrl-0 = <&pinctrl_ctrl_sleep_moci>;
- };
};
&gpio3 {
@@ -432,6 +422,16 @@
"SODIMM_256",
"SODIMM_48",
"SODIMM_44";
+
+ ctrl-sleep-moci-hog {
+ gpio-hog;
+ /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */
+ gpios = <29 GPIO_ACTIVE_HIGH>;
+ line-name = "CTRL_SLEEP_MOCI#";
+ output-high;
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_ctrl_sleep_moci>;
+ };
};
/* On-module I2C */
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index 3a5713bb4880..0247866fc86b 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -451,7 +451,7 @@
clocks = <&clk IMX93_CLK_GPIO2_GATE>,
<&clk IMX93_CLK_GPIO2_GATE>;
clock-names = "gpio", "port";
- gpio-ranges = <&iomuxc 0 32 32>;
+ gpio-ranges = <&iomuxc 0 4 30>;
};
gpio3: gpio@43820080 {
@@ -465,7 +465,8 @@
clocks = <&clk IMX93_CLK_GPIO3_GATE>,
<&clk IMX93_CLK_GPIO3_GATE>;
clock-names = "gpio", "port";
- gpio-ranges = <&iomuxc 0 64 32>;
+ gpio-ranges = <&iomuxc 0 84 8>, <&iomuxc 8 66 18>,
+ <&iomuxc 26 34 2>, <&iomuxc 28 0 4>;
};
gpio4: gpio@43830080 {
@@ -479,7 +480,7 @@
clocks = <&clk IMX93_CLK_GPIO4_GATE>,
<&clk IMX93_CLK_GPIO4_GATE>;
clock-names = "gpio", "port";
- gpio-ranges = <&iomuxc 0 96 32>;
+ gpio-ranges = <&iomuxc 0 38 28>, <&iomuxc 28 36 2>;
};
gpio1: gpio@47400080 {
@@ -493,7 +494,7 @@
clocks = <&clk IMX93_CLK_GPIO1_GATE>,
<&clk IMX93_CLK_GPIO1_GATE>;
clock-names = "gpio", "port";
- gpio-ranges = <&iomuxc 0 0 32>;
+ gpio-ranges = <&iomuxc 0 92 16>;
};
s4muap: mailbox@47520000 {
@@ -501,7 +502,7 @@
reg = <0x47520000 0x10000>;
interrupts = <GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
- interrupt-names = "txirq", "rxirq";
+ interrupt-names = "tx", "rx";
#mbox-cells = <2>;
};
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 439e2bc5d5d8..d6cf535d8352 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -14,8 +14,16 @@
#ifdef CONFIG_EFI
extern void efi_init(void);
+
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg);
#else
#define efi_init()
+
+static inline
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
+{
+ return false;
+}
#endif
int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6062454a9067..b3f37e2209ad 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -428,6 +428,30 @@ static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
ARM64_FTR_END,
};
+static const struct arm64_ftr_bits ftr_mvfr0[] = {
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPROUND_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSHVEC_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSQRT_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDIVIDE_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPTRAP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPDP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_FPSP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR0_SIMD_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
+static const struct arm64_ftr_bits ftr_mvfr1[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDFMAC_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPHP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDHP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDSP_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDINT_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_SIMDLS_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPDNAN_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR1_FPFTZ_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_mvfr2[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_FPMISC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, MVFR2_SIMDMISC_SHIFT, 4, 0),
@@ -458,10 +482,10 @@ static const struct arm64_ftr_bits ftr_id_isar0[] = {
static const struct arm64_ftr_bits ftr_id_isar5[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_RDM_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_CRC32_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA2_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SHA1_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_AES_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR5_SEVL_SHIFT, 4, 0),
ARM64_FTR_END,
};
@@ -574,7 +598,7 @@ static const struct arm64_ftr_bits ftr_smcr[] = {
* Common ftr bits for a 32bit register with all hidden, strict
* attributes, with 4bit feature fields and a default safe value of
* 0. Covers the following 32bit registers:
- * id_isar[1-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
+ * id_isar[1-3], id_mmfr[1-3]
*/
static const struct arm64_ftr_bits ftr_generic_32bits[] = {
ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
@@ -645,8 +669,8 @@ static const struct __ftr_reg_entry {
ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6),
/* Op1 = 0, CRn = 0, CRm = 3 */
- ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits),
- ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_generic_32bits),
+ ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_mvfr0),
+ ARM64_FTR_REG(SYS_MVFR1_EL1, ftr_mvfr1),
ARM64_FTR_REG(SYS_MVFR2_EL1, ftr_mvfr2),
ARM64_FTR_REG(SYS_ID_PFR2_EL1, ftr_id_pfr2),
ARM64_FTR_REG(SYS_ID_DFR1_EL1, ftr_id_dfr1),
@@ -3339,7 +3363,7 @@ static void __maybe_unused cpu_enable_cnp(struct arm64_cpu_capabilities const *c
/*
* We emulate only the following system register space.
- * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 4 - 7]
+ * Op0 = 0x3, CRn = 0x0, Op1 = 0x0, CRm = [0, 2 - 7]
* See Table C5-6 System instruction encodings for System register accesses,
* ARMv8 ARM(ARM DDI 0487A.f) for more details.
*/
@@ -3349,7 +3373,7 @@ static inline bool __attribute_const__ is_emulated(u32 id)
sys_reg_CRn(id) == 0x0 &&
sys_reg_Op1(id) == 0x0 &&
(sys_reg_CRm(id) == 0 ||
- ((sys_reg_CRm(id) >= 4) && (sys_reg_CRm(id) <= 7))));
+ ((sys_reg_CRm(id) >= 2) && (sys_reg_CRm(id) <= 7))));
}
/*
diff --git a/arch/arm64/kernel/efi-rt-wrapper.S b/arch/arm64/kernel/efi-rt-wrapper.S
index 75691a2641c1..67babd5f04c2 100644
--- a/arch/arm64/kernel/efi-rt-wrapper.S
+++ b/arch/arm64/kernel/efi-rt-wrapper.S
@@ -6,7 +6,7 @@
#include <linux/linkage.h>
SYM_FUNC_START(__efi_rt_asm_wrapper)
- stp x29, x30, [sp, #-32]!
+ stp x29, x30, [sp, #-112]!
mov x29, sp
/*
@@ -17,6 +17,20 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
stp x1, x18, [sp, #16]
/*
+ * Preserve all callee saved registers and record the stack pointer
+ * value in a per-CPU variable so we can recover from synchronous
+ * exceptions occurring while running the firmware routines.
+ */
+ stp x19, x20, [sp, #32]
+ stp x21, x22, [sp, #48]
+ stp x23, x24, [sp, #64]
+ stp x25, x26, [sp, #80]
+ stp x27, x28, [sp, #96]
+
+ adr_this_cpu x8, __efi_rt_asm_recover_sp, x9
+ str x29, [x8]
+
+ /*
* We are lucky enough that no EFI runtime services take more than
* 5 arguments, so all are passed in registers rather than via the
* stack.
@@ -31,7 +45,7 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
ldp x1, x2, [sp, #16]
cmp x2, x18
- ldp x29, x30, [sp], #32
+ ldp x29, x30, [sp], #112
b.ne 0f
ret
0:
@@ -45,3 +59,18 @@ SYM_FUNC_START(__efi_rt_asm_wrapper)
mov x18, x2
b efi_handle_corrupted_x18 // tail call
SYM_FUNC_END(__efi_rt_asm_wrapper)
+
+SYM_FUNC_START(__efi_rt_asm_recover)
+ ldr_this_cpu x8, __efi_rt_asm_recover_sp, x9
+ mov sp, x8
+
+ ldp x0, x18, [sp, #16]
+ ldp x19, x20, [sp, #32]
+ ldp x21, x22, [sp, #48]
+ ldp x23, x24, [sp, #64]
+ ldp x25, x26, [sp, #80]
+ ldp x27, x28, [sp, #96]
+ ldp x29, x30, [sp], #112
+
+ b efi_handle_runtime_exception
+SYM_FUNC_END(__efi_rt_asm_recover)
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index e1be6c429810..8d36e66a6e64 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -9,6 +9,7 @@
#include <linux/efi.h>
#include <linux/init.h>
+#include <linux/percpu.h>
#include <asm/efi.h>
@@ -128,3 +129,28 @@ asmlinkage efi_status_t efi_handle_corrupted_x18(efi_status_t s, const char *f)
pr_err_ratelimited(FW_BUG "register x18 corrupted by EFI %s\n", f);
return s;
}
+
+asmlinkage DEFINE_PER_CPU(u64, __efi_rt_asm_recover_sp);
+
+asmlinkage efi_status_t __efi_rt_asm_recover(void);
+
+asmlinkage efi_status_t efi_handle_runtime_exception(const char *f)
+{
+ pr_err(FW_BUG "Synchronous exception occurred in EFI runtime service %s()\n", f);
+ clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ return EFI_ABORTED;
+}
+
+bool efi_runtime_fixup_exception(struct pt_regs *regs, const char *msg)
+{
+ /* Check whether the exception occurred while running the firmware */
+ if (current_work() != &efi_rts_work.work || regs->pc >= TASK_SIZE_64)
+ return false;
+
+ pr_err(FW_BUG "Unable to handle %s in EFI runtime service\n", msg);
+ add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
+ dump_stack();
+
+ regs->pc = (u64)__efi_rt_asm_recover;
+ return true;
+}
diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 9173fad279af..27369fa1c032 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -329,7 +329,8 @@ static void cortex_a76_erratum_1463225_svc_handler(void)
__this_cpu_write(__in_cortex_a76_erratum_1463225_wa, 0);
}
-static bool cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
+static __always_inline bool
+cortex_a76_erratum_1463225_debug_handler(struct pt_regs *regs)
{
if (!__this_cpu_read(__in_cortex_a76_erratum_1463225_wa))
return false;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 94d33e296e10..7b107fa540fa 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2130,6 +2130,11 @@ struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
return NULL;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return irqchip_in_kernel(kvm);
+}
+
bool kvm_arch_has_irq_bypass(void)
{
return true;
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index b7557b25ed56..791d3de76771 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -13,6 +13,7 @@
#include <hyp/adjust_pc.h>
#include <linux/kvm_host.h>
#include <asm/kvm_emulate.h>
+#include <asm/kvm_mmu.h>
#if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__)
#error Hypervisor code only!
@@ -115,7 +116,7 @@ static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode,
new |= (old & PSR_C_BIT);
new |= (old & PSR_V_BIT);
- if (kvm_has_mte(vcpu->kvm))
+ if (kvm_has_mte(kern_hyp_va(vcpu->kvm)))
new |= PSR_TCO_BIT;
new |= (old & PSR_DIT_BIT);
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index 6cbbb6c02f66..3330d1b76bdd 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -87,6 +87,17 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu)
vcpu->arch.mdcr_el2_host = read_sysreg(mdcr_el2);
write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2);
+
+ if (cpus_have_final_cap(ARM64_SME)) {
+ sysreg_clear_set_s(SYS_HFGRTR_EL2,
+ HFGxTR_EL2_nSMPRI_EL1_MASK |
+ HFGxTR_EL2_nTPIDR2_EL0_MASK,
+ 0);
+ sysreg_clear_set_s(SYS_HFGWTR_EL2,
+ HFGxTR_EL2_nSMPRI_EL1_MASK |
+ HFGxTR_EL2_nTPIDR2_EL0_MASK,
+ 0);
+ }
}
static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
@@ -96,6 +107,15 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu)
write_sysreg(0, hstr_el2);
if (kvm_arm_support_pmu_v3())
write_sysreg(0, pmuserenr_el0);
+
+ if (cpus_have_final_cap(ARM64_SME)) {
+ sysreg_clear_set_s(SYS_HFGRTR_EL2, 0,
+ HFGxTR_EL2_nSMPRI_EL1_MASK |
+ HFGxTR_EL2_nTPIDR2_EL0_MASK);
+ sysreg_clear_set_s(SYS_HFGWTR_EL2, 0,
+ HFGxTR_EL2_nSMPRI_EL1_MASK |
+ HFGxTR_EL2_nTPIDR2_EL0_MASK);
+ }
}
static inline void ___activate_traps(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 1e78acf9662e..07f9dc9848ef 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -516,7 +516,7 @@ static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
if (!kvm_pte_valid(pte))
return PKVM_NOPAGE;
- return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte));
+ return pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
}
static int __hyp_check_page_state_range(u64 addr, u64 size,
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 8e9d49a964be..c2cb46ca4fb6 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -55,18 +55,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
write_sysreg(val, cptr_el2);
write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2);
- if (cpus_have_final_cap(ARM64_SME)) {
- val = read_sysreg_s(SYS_HFGRTR_EL2);
- val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
- HFGxTR_EL2_nSMPRI_EL1_MASK);
- write_sysreg_s(val, SYS_HFGRTR_EL2);
-
- val = read_sysreg_s(SYS_HFGWTR_EL2);
- val &= ~(HFGxTR_EL2_nTPIDR2_EL0_MASK |
- HFGxTR_EL2_nSMPRI_EL1_MASK);
- write_sysreg_s(val, SYS_HFGWTR_EL2);
- }
-
if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) {
struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt;
@@ -110,20 +98,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2);
- if (cpus_have_final_cap(ARM64_SME)) {
- u64 val;
-
- val = read_sysreg_s(SYS_HFGRTR_EL2);
- val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
- HFGxTR_EL2_nSMPRI_EL1_MASK;
- write_sysreg_s(val, SYS_HFGRTR_EL2);
-
- val = read_sysreg_s(SYS_HFGWTR_EL2);
- val |= HFGxTR_EL2_nTPIDR2_EL0_MASK |
- HFGxTR_EL2_nSMPRI_EL1_MASK;
- write_sysreg_s(val, SYS_HFGWTR_EL2);
- }
-
cptr = CPTR_EL2_DEFAULT;
if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED))
cptr |= CPTR_EL2_TZ;
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 7acb87eaa092..1a97391fedd2 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -63,10 +63,6 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
__activate_traps_fpsimd32(vcpu);
}
- if (cpus_have_final_cap(ARM64_SME))
- write_sysreg(read_sysreg(sctlr_el2) & ~SCTLR_ELx_ENTP2,
- sctlr_el2);
-
write_sysreg(val, cpacr_el1);
write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
@@ -88,10 +84,6 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
*/
asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
- if (cpus_have_final_cap(ARM64_SME))
- write_sysreg(read_sysreg(sctlr_el2) | SCTLR_ELx_ENTP2,
- sctlr_el2);
-
write_sysreg(CPACR_EL1_DEFAULT, cpacr_el1);
if (!arm64_kernel_unmapped_at_el0())
diff --git a/arch/arm64/kvm/irq.h b/arch/arm64/kvm/irq.h
deleted file mode 100644
index 0d257de42c10..000000000000
--- a/arch/arm64/kvm/irq.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * irq.h: in kernel interrupt controller related definitions
- * Copyright (c) 2016 Red Hat, Inc.
- *
- * This header is included by irqchip.c. However, on ARM, interrupt
- * controller declarations are located in include/kvm/arm_vgic.h since
- * they are mostly shared between arm and arm64.
- */
-
-#ifndef __IRQ_H
-#define __IRQ_H
-
-#include <kvm/arm_vgic.h>
-
-#endif
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 60ee3d9f01f8..f154d4a7fae0 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -1239,7 +1239,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
*/
smp_rmb();
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
write_fault, &writable, NULL);
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5b391490e045..3e9cf9826417 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -30,6 +30,7 @@
#include <asm/bug.h>
#include <asm/cmpxchg.h>
#include <asm/cpufeature.h>
+#include <asm/efi.h>
#include <asm/exception.h>
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
@@ -391,6 +392,9 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr,
msg = "paging request";
}
+ if (efi_runtime_fixup_exception(regs, msg))
+ return;
+
die_kernel_fault(msg, addr, esr, regs);
}
diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h
index 6954dc5d24e9..7184f1dc61f2 100644
--- a/arch/loongarch/include/asm/processor.h
+++ b/arch/loongarch/include/asm/processor.h
@@ -191,7 +191,7 @@ static inline void flush_thread(void)
unsigned long __get_wchan(struct task_struct *p);
#define __KSTK_TOS(tsk) ((unsigned long)task_stack_page(tsk) + \
- THREAD_SIZE - 32 - sizeof(struct pt_regs))
+ THREAD_SIZE - sizeof(struct pt_regs))
#define task_pt_regs(tsk) ((struct pt_regs *)__KSTK_TOS(tsk))
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->csr_era)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[3])
diff --git a/arch/loongarch/include/asm/ptrace.h b/arch/loongarch/include/asm/ptrace.h
index 17838c6b7ccd..59c4608de91d 100644
--- a/arch/loongarch/include/asm/ptrace.h
+++ b/arch/loongarch/include/asm/ptrace.h
@@ -29,7 +29,7 @@ struct pt_regs {
unsigned long csr_euen;
unsigned long csr_ecfg;
unsigned long csr_estat;
- unsigned long __last[0];
+ unsigned long __last[];
} __aligned(8);
static inline int regs_irqs_disabled(struct pt_regs *regs)
@@ -133,7 +133,7 @@ static inline void die_if_kernel(const char *str, struct pt_regs *regs)
#define current_pt_regs() \
({ \
unsigned long sp = (unsigned long)__builtin_frame_address(0); \
- (struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1 - 32) - 1; \
+ (struct pt_regs *)((sp | (THREAD_SIZE - 1)) + 1) - 1; \
})
/* Helpers for working with the user stack pointer */
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index 97425779ce9f..84970e266658 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -84,10 +84,9 @@ SYM_CODE_START(kernel_entry) # kernel entry point
la.pcrel tp, init_thread_union
/* Set the SP after an empty pt_regs. */
- PTR_LI sp, (_THREAD_SIZE - 32 - PT_SIZE)
+ PTR_LI sp, (_THREAD_SIZE - PT_SIZE)
PTR_ADD sp, sp, tp
set_saved_sp sp, t0, t1
- PTR_ADDI sp, sp, -4 * SZREG # init stack pointer
bl start_kernel
ASM_BUG()
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 1256e3582475..2526b68f1c0f 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -129,7 +129,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
unsigned long clone_flags = args->flags;
struct pt_regs *childregs, *regs = current_pt_regs();
- childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
+ childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
/* set up new TSS. */
childregs = (struct pt_regs *) childksp - 1;
@@ -236,7 +236,7 @@ bool in_task_stack(unsigned long stack, struct task_struct *task,
struct stack_info *info)
{
unsigned long begin = (unsigned long)task_stack_page(task);
- unsigned long end = begin + THREAD_SIZE - 32;
+ unsigned long end = begin + THREAD_SIZE;
if (stack < begin || stack >= end)
return false;
diff --git a/arch/loongarch/kernel/switch.S b/arch/loongarch/kernel/switch.S
index 43ebbc3990f7..202a163cb32f 100644
--- a/arch/loongarch/kernel/switch.S
+++ b/arch/loongarch/kernel/switch.S
@@ -26,7 +26,7 @@ SYM_FUNC_START(__switch_to)
move tp, a2
cpu_restore_nonscratch a1
- li.w t0, _THREAD_SIZE - 32
+ li.w t0, _THREAD_SIZE
PTR_ADD t0, t0, tp
set_saved_sp t0, t1, t2
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 43f0a98efe38..bdcd0c7719a9 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -279,6 +279,7 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
const u8 t1 = LOONGARCH_GPR_T1;
const u8 t2 = LOONGARCH_GPR_T2;
const u8 t3 = LOONGARCH_GPR_T3;
+ const u8 r0 = regmap[BPF_REG_0];
const u8 src = regmap[insn->src_reg];
const u8 dst = regmap[insn->dst_reg];
const s16 off = insn->off;
@@ -359,8 +360,6 @@ static void emit_atomic(const struct bpf_insn *insn, struct jit_ctx *ctx)
break;
/* r0 = atomic_cmpxchg(dst + off, r0, src); */
case BPF_CMPXCHG:
- u8 r0 = regmap[BPF_REG_0];
-
move_reg(ctx, t2, r0);
if (isdw) {
emit_insn(ctx, lld, r0, t1, 0);
@@ -390,8 +389,11 @@ static bool is_signed_bpf_cond(u8 cond)
static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool extra_pass)
{
- const bool is32 = BPF_CLASS(insn->code) == BPF_ALU ||
- BPF_CLASS(insn->code) == BPF_JMP32;
+ u8 tm = -1;
+ u64 func_addr;
+ bool func_addr_fixed;
+ int i = insn - ctx->prog->insnsi;
+ int ret, jmp_offset;
const u8 code = insn->code;
const u8 cond = BPF_OP(code);
const u8 t1 = LOONGARCH_GPR_T1;
@@ -400,8 +402,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
const u8 dst = regmap[insn->dst_reg];
const s16 off = insn->off;
const s32 imm = insn->imm;
- int jmp_offset;
- int i = insn - ctx->prog->insnsi;
+ const u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
+ const bool is32 = BPF_CLASS(insn->code) == BPF_ALU || BPF_CLASS(insn->code) == BPF_JMP32;
switch (code) {
/* dst = src */
@@ -724,24 +726,23 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
case BPF_JMP32 | BPF_JSGE | BPF_K:
case BPF_JMP32 | BPF_JSLT | BPF_K:
case BPF_JMP32 | BPF_JSLE | BPF_K:
- u8 t7 = -1;
jmp_offset = bpf2la_offset(i, off, ctx);
if (imm) {
move_imm(ctx, t1, imm, false);
- t7 = t1;
+ tm = t1;
} else {
/* If imm is 0, simply use zero register. */
- t7 = LOONGARCH_GPR_ZERO;
+ tm = LOONGARCH_GPR_ZERO;
}
move_reg(ctx, t2, dst);
if (is_signed_bpf_cond(BPF_OP(code))) {
- emit_sext_32(ctx, t7, is32);
+ emit_sext_32(ctx, tm, is32);
emit_sext_32(ctx, t2, is32);
} else {
- emit_zext_32(ctx, t7, is32);
+ emit_zext_32(ctx, tm, is32);
emit_zext_32(ctx, t2, is32);
}
- if (emit_cond_jmp(ctx, cond, t2, t7, jmp_offset) < 0)
+ if (emit_cond_jmp(ctx, cond, t2, tm, jmp_offset) < 0)
goto toofar;
break;
@@ -775,10 +776,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
/* function call */
case BPF_JMP | BPF_CALL:
- int ret;
- u64 func_addr;
- bool func_addr_fixed;
-
mark_call(ctx);
ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass,
&func_addr, &func_addr_fixed);
@@ -811,8 +808,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
/* dst = imm64 */
case BPF_LD | BPF_IMM | BPF_DW:
- u64 imm64 = (u64)(insn + 1)->imm << 32 | (u32)insn->imm;
-
move_imm(ctx, dst, imm64, is32);
return 1;
diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h
index 9d3d7737c58b..a005ebc54779 100644
--- a/arch/parisc/include/asm/hardware.h
+++ b/arch/parisc/include/asm/hardware.h
@@ -10,12 +10,12 @@
#define SVERSION_ANY_ID PA_SVERSION_ANY_ID
struct hp_hardware {
- unsigned short hw_type:5; /* HPHW_xxx */
- unsigned short hversion;
- unsigned long sversion:28;
- unsigned short opt;
- const char name[80]; /* The hardware description */
-};
+ unsigned int hw_type:8; /* HPHW_xxx */
+ unsigned int hversion:12;
+ unsigned int sversion:12;
+ unsigned char opt;
+ unsigned char name[59]; /* The hardware description */
+} __packed;
struct parisc_device;
diff --git a/arch/parisc/include/uapi/asm/pdc.h b/arch/parisc/include/uapi/asm/pdc.h
index e794e143ec5f..7a90070136e8 100644
--- a/arch/parisc/include/uapi/asm/pdc.h
+++ b/arch/parisc/include/uapi/asm/pdc.h
@@ -363,20 +363,25 @@
#if !defined(__ASSEMBLY__)
-/* flags of the device_path */
+/* flags for hardware_path */
#define PF_AUTOBOOT 0x80
#define PF_AUTOSEARCH 0x40
#define PF_TIMER 0x0F
-struct device_path { /* page 1-69 */
- unsigned char flags; /* flags see above! */
- unsigned char bc[6]; /* bus converter routing info */
- unsigned char mod;
- unsigned int layers[6];/* device-specific layer-info */
-} __attribute__((aligned(8))) ;
+struct hardware_path {
+ unsigned char flags; /* see bit definitions below */
+ signed char bc[6]; /* Bus Converter routing info to a specific */
+ /* I/O adaptor (< 0 means none, > 63 resvd) */
+ signed char mod; /* fixed field of specified module */
+};
+
+struct pdc_module_path { /* page 1-69 */
+ struct hardware_path path;
+ unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */
+} __attribute__((aligned(8)));
struct pz_device {
- struct device_path dp; /* see above */
+ struct pdc_module_path dp; /* see above */
/* struct iomod *hpa; */
unsigned int hpa; /* HPA base address */
/* char *spa; */
@@ -611,21 +616,6 @@ struct pdc_initiator { /* PDC_INITIATOR */
int mode;
};
-struct hardware_path {
- char flags; /* see bit definitions below */
- char bc[6]; /* Bus Converter routing info to a specific */
- /* I/O adaptor (< 0 means none, > 63 resvd) */
- char mod; /* fixed field of specified module */
-};
-
-/*
- * Device path specifications used by PDC.
- */
-struct pdc_module_path {
- struct hardware_path path;
- unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */
-};
-
/* Only used on some pre-PA2.0 boxes */
struct pdc_memory_map { /* PDC_MEMORY_MAP */
unsigned long hpa; /* mod's register set address */
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index d126e78e101a..e7ee0c0c91d3 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -882,15 +882,13 @@ void __init walk_central_bus(void)
&root);
}
-static void print_parisc_device(struct parisc_device *dev)
+static __init void print_parisc_device(struct parisc_device *dev)
{
- char hw_path[64];
- static int count;
+ static int count __initdata;
- print_pa_hwpath(dev, hw_path);
- pr_info("%d. %s at %pap [%s] { %d, 0x%x, 0x%.3x, 0x%.5x }",
- ++count, dev->name, &(dev->hpa.start), hw_path, dev->id.hw_type,
- dev->id.hversion_rev, dev->id.hversion, dev->id.sversion);
+ pr_info("%d. %s at %pap { type:%d, hv:%#x, sv:%#x, rev:%#x }",
+ ++count, dev->name, &(dev->hpa.start), dev->id.hw_type,
+ dev->id.hversion, dev->id.sversion, dev->id.hversion_rev);
if (dev->num_addrs) {
int k;
@@ -1079,7 +1077,7 @@ static __init int qemu_print_iodc_data(struct device *lin_dev, void *data)
-static int print_one_device(struct device * dev, void * data)
+static __init int print_one_device(struct device * dev, void * data)
{
struct parisc_device * pdev = to_parisc_device(dev);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 699df27b0e2f..2ca5418457ed 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -147,6 +147,7 @@ config PPC
select ARCH_MIGHT_HAVE_PC_SERIO
select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
+ select ARCH_SPLIT_ARG64 if PPC32
select ARCH_STACKWALK
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_DEBUG_PAGEALLOC if PPC_BOOK3S || PPC_8xx || 40x
@@ -285,7 +286,7 @@ config PPC
#
config PPC_LONG_DOUBLE_128
- depends on PPC64
+ depends on PPC64 && ALTIVEC
def_bool $(success,test "$(shell,echo __LONG_DOUBLE_128__ | $(CC) -E -P -)" = 1)
config PPC_BARRIER_NOSPEC
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
index fab8332fe1ad..751921f6db46 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h
@@ -32,6 +32,11 @@ static inline void arch_enter_lazy_mmu_mode(void)
if (radix_enabled())
return;
+ /*
+ * apply_to_page_range can call us this preempt enabled when
+ * operating on kernel page tables.
+ */
+ preempt_disable();
batch = this_cpu_ptr(&ppc64_tlb_batch);
batch->active = 1;
}
@@ -47,6 +52,7 @@ static inline void arch_leave_lazy_mmu_mode(void)
if (batch->index)
__flush_tlb_pending(batch);
batch->active = 0;
+ preempt_enable();
}
#define arch_flush_lazy_mmu_mode() do {} while (0)
diff --git a/arch/powerpc/include/asm/syscalls.h b/arch/powerpc/include/asm/syscalls.h
index a1142496cd58..6d51b007b59e 100644
--- a/arch/powerpc/include/asm/syscalls.h
+++ b/arch/powerpc/include/asm/syscalls.h
@@ -104,6 +104,13 @@ long sys_ppc_ftruncate64(unsigned int fd, u32 reg4,
unsigned long len1, unsigned long len2);
long sys_ppc32_fadvise64(int fd, u32 unused, u32 offset1, u32 offset2,
size_t len, int advice);
+long sys_ppc_sync_file_range2(int fd, unsigned int flags,
+ unsigned int offset1,
+ unsigned int offset2,
+ unsigned int nbytes1,
+ unsigned int nbytes2);
+long sys_ppc_fallocate(int fd, int mode, u32 offset1, u32 offset2,
+ u32 len1, u32 len2);
#endif
#ifdef CONFIG_COMPAT
long compat_sys_mmap2(unsigned long addr, size_t len,
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 930e36099015..2f68fb2ee4fc 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -813,6 +813,13 @@ kernel_dbg_exc:
EXCEPTION_COMMON(0x260)
CHECK_NAPPING()
addi r3,r1,STACK_FRAME_OVERHEAD
+ /*
+ * XXX: Returning from performance_monitor_exception taken as a
+ * soft-NMI (Linux irqs disabled) may be risky to use interrupt_return
+ * and could cause bugs in return or elsewhere. That case should just
+ * restore registers and return. There is a workaround for one known
+ * problem in interrupt_exit_kernel_prepare().
+ */
bl performance_monitor_exception
b interrupt_return
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 5381a43e50fe..651c36b056bd 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -2357,9 +2357,21 @@ EXC_VIRT_END(performance_monitor, 0x4f00, 0x20)
EXC_COMMON_BEGIN(performance_monitor_common)
GEN_COMMON performance_monitor
addi r3,r1,STACK_FRAME_OVERHEAD
- bl performance_monitor_exception
+ lbz r4,PACAIRQSOFTMASK(r13)
+ cmpdi r4,IRQS_ENABLED
+ bne 1f
+ bl performance_monitor_exception_async
b interrupt_return_srr
+1:
+ bl performance_monitor_exception_nmi
+ /* Clear MSR_RI before setting SRR0 and SRR1. */
+ li r9,0
+ mtmsrd r9,1
+ kuap_kernel_restore r9, r10
+
+ EXCEPTION_RESTORE_REGS hsrr=0
+ RFI_TO_KERNEL
/**
* Interrupt 0xf20 - Vector Unavailable Interrupt.
diff --git a/arch/powerpc/kernel/interrupt.c b/arch/powerpc/kernel/interrupt.c
index f9db0a172401..fc6631a80527 100644
--- a/arch/powerpc/kernel/interrupt.c
+++ b/arch/powerpc/kernel/interrupt.c
@@ -374,10 +374,18 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs)
if (regs_is_unrecoverable(regs))
unrecoverable_exception(regs);
/*
- * CT_WARN_ON comes here via program_check_exception,
- * so avoid recursion.
+ * CT_WARN_ON comes here via program_check_exception, so avoid
+ * recursion.
+ *
+ * Skip the assertion on PMIs on 64e to work around a problem caused
+ * by NMI PMIs incorrectly taking this interrupt return path, it's
+ * possible for this to hit after interrupt exit to user switches
+ * context to user. See also the comment in the performance monitor
+ * handler in exceptions-64e.S
*/
- if (TRAP(regs) != INTERRUPT_PROGRAM)
+ if (!IS_ENABLED(CONFIG_PPC_BOOK3E_64) &&
+ TRAP(regs) != INTERRUPT_PROGRAM &&
+ TRAP(regs) != INTERRUPT_PERFMON)
CT_WARN_ON(ct_state() == CONTEXT_USER);
kuap = kuap_get_and_assert_locked();
diff --git a/arch/powerpc/kernel/interrupt_64.S b/arch/powerpc/kernel/interrupt_64.S
index 978a173eb339..a019ed6fc839 100644
--- a/arch/powerpc/kernel/interrupt_64.S
+++ b/arch/powerpc/kernel/interrupt_64.S
@@ -532,15 +532,24 @@ _ASM_NOKPROBE_SYMBOL(interrupt_return_\srr\()_kernel)
* Returning to soft-disabled context.
* Check if a MUST_HARD_MASK interrupt has become pending, in which
* case we need to disable MSR[EE] in the return context.
+ *
+ * The MSR[EE] check catches among other things the short incoherency
+ * in hard_irq_disable() between clearing MSR[EE] and setting
+ * PACA_IRQ_HARD_DIS.
*/
ld r12,_MSR(r1)
andi. r10,r12,MSR_EE
beq .Lfast_kernel_interrupt_return_\srr\() // EE already disabled
lbz r11,PACAIRQHAPPENED(r13)
andi. r10,r11,PACA_IRQ_MUST_HARD_MASK
- beq .Lfast_kernel_interrupt_return_\srr\() // No HARD_MASK pending
+ bne 1f // HARD_MASK is pending
+ // No HARD_MASK pending, clear possible HARD_DIS set by interrupt
+ andi. r11,r11,(~PACA_IRQ_HARD_DIS)@l
+ stb r11,PACAIRQHAPPENED(r13)
+ b .Lfast_kernel_interrupt_return_\srr\()
+
- /* Must clear MSR_EE from _MSR */
+1: /* Must clear MSR_EE from _MSR */
#ifdef CONFIG_PPC_BOOK3S
li r10,0
/* Clear valid before changing _MSR */
diff --git a/arch/powerpc/kernel/sys_ppc32.c b/arch/powerpc/kernel/sys_ppc32.c
index 1ab4a4d95aba..d451a8229223 100644
--- a/arch/powerpc/kernel/sys_ppc32.c
+++ b/arch/powerpc/kernel/sys_ppc32.c
@@ -112,7 +112,7 @@ PPC32_SYSCALL_DEFINE6(ppc32_fadvise64,
advice);
}
-COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
+PPC32_SYSCALL_DEFINE6(ppc_sync_file_range2,
int, fd, unsigned int, flags,
unsigned int, offset1, unsigned int, offset2,
unsigned int, nbytes1, unsigned int, nbytes2)
@@ -122,3 +122,14 @@ COMPAT_SYSCALL_DEFINE6(ppc_sync_file_range2,
return ksys_sync_file_range(fd, offset, nbytes, flags);
}
+
+#ifdef CONFIG_PPC32
+SYSCALL_DEFINE6(ppc_fallocate,
+ int, fd, int, mode,
+ u32, offset1, u32, offset2, u32, len1, u32, len2)
+{
+ return ksys_fallocate(fd, mode,
+ merge_64(offset1, offset2),
+ merge_64(len1, len2));
+}
+#endif
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index e9e0df4f9a61..a0be127475b1 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -394,8 +394,11 @@
305 common signalfd sys_signalfd compat_sys_signalfd
306 common timerfd_create sys_timerfd_create
307 common eventfd sys_eventfd
-308 common sync_file_range2 sys_sync_file_range2 compat_sys_ppc_sync_file_range2
-309 nospu fallocate sys_fallocate compat_sys_fallocate
+308 32 sync_file_range2 sys_ppc_sync_file_range2 compat_sys_ppc_sync_file_range2
+308 64 sync_file_range2 sys_sync_file_range2
+308 spu sync_file_range2 sys_sync_file_range2
+309 32 fallocate sys_ppc_fallocate compat_sys_fallocate
+309 64 fallocate sys_fallocate
310 nospu subpage_prot sys_subpage_prot
311 32 timerfd_settime sys_timerfd_settime32
311 64 timerfd_settime sys_timerfd_settime
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 61cdd782d3c5..a9f57dad6d91 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -51,6 +51,7 @@ config KVM_BOOK3S_HV_POSSIBLE
config KVM_BOOK3S_32
tristate "KVM support for PowerPC book3s_32 processors"
depends on PPC_BOOK3S_32 && !SMP && !PTE_64BIT
+ depends on !CONTEXT_TRACKING_USER
select KVM
select KVM_BOOK3S_32_HANDLER
select KVM_BOOK3S_PR_POSSIBLE
@@ -105,6 +106,7 @@ config KVM_BOOK3S_64_HV
config KVM_BOOK3S_64_PR
tristate "KVM support without using hypervisor mode in host"
depends on KVM_BOOK3S_64
+ depends on !CONTEXT_TRACKING_USER
select KVM_BOOK3S_PR_POSSIBLE
help
Support running guest kernels in virtual machines on processors
@@ -190,6 +192,7 @@ config KVM_EXIT_TIMING
config KVM_E500V2
bool "KVM support for PowerPC E500v2 processors"
depends on PPC_E500 && !PPC_E500MC
+ depends on !CONTEXT_TRACKING_USER
select KVM
select KVM_MMIO
select MMU_NOTIFIER
@@ -205,6 +208,7 @@ config KVM_E500V2
config KVM_E500MC
bool "KVM support for PowerPC E500MC/E5500/E6500 processors"
depends on PPC_E500MC
+ depends on !CONTEXT_TRACKING_USER
select KVM
select KVM_MMIO
select KVM_BOOKE_HV
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index e9744b41a226..4939f57b6f6a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -598,7 +598,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_vcpu *vcpu,
write_ok = true;
} else {
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, &write_ok, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 5d5e12f3bf86..9d3743ca16d5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -846,7 +846,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
unsigned long pfn;
/* Call KVM generic code to do the slow-path check */
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+ pfn = __gfn_to_pfn_memslot(memslot, gfn, false, false, NULL,
writing, upgrade_p, NULL);
if (is_error_noslot_pfn(pfn))
return -EFAULT;
diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h
deleted file mode 100644
index e6463f866abc..000000000000
--- a/arch/powerpc/kvm/irq.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __IRQ_H
-#define __IRQ_H
-
-#include <linux/kvm_host.h>
-
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
- int ret = 0;
-
-#ifdef CONFIG_KVM_MPIC
- ret = ret || (kvm->arch.mpic != NULL);
-#endif
-#ifdef CONFIG_KVM_XICS
- ret = ret || (kvm->arch.xics != NULL);
- ret = ret || (kvm->arch.xive != NULL);
-#endif
- smp_rmb();
- return ret;
-}
-
-#endif
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index b850b0efa201..04494a4fb37a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -36,7 +36,6 @@
#include <asm/setup.h>
#include "timing.h"
-#include "irq.h"
#include "../mm/mmu_decl.h"
#define CREATE_TRACE_POINTS
@@ -2165,10 +2164,25 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
return 0;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ int ret = 0;
+
+#ifdef CONFIG_KVM_MPIC
+ ret = ret || (kvm->arch.mpic != NULL);
+#endif
+#ifdef CONFIG_KVM_XICS
+ ret = ret || (kvm->arch.xics != NULL);
+ ret = ret || (kvm->arch.xive != NULL);
+#endif
+ smp_rmb();
+ return ret;
+}
+
int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
bool line_status)
{
- if (!irqchip_in_kernel(kvm))
+ if (!kvm_arch_irqchip_in_kernel(kvm))
return -ENXIO;
irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
diff --git a/arch/powerpc/lib/vmx-helper.c b/arch/powerpc/lib/vmx-helper.c
index f76a50291fd7..d491da8d1838 100644
--- a/arch/powerpc/lib/vmx-helper.c
+++ b/arch/powerpc/lib/vmx-helper.c
@@ -36,7 +36,17 @@ int exit_vmx_usercopy(void)
{
disable_kernel_altivec();
pagefault_enable();
- preempt_enable();
+ preempt_enable_no_resched();
+ /*
+ * Must never explicitly call schedule (including preempt_enable())
+ * while in a kuap-unlocked user copy, because the AMR register will
+ * not be saved and restored across context switch. However preempt
+ * kernels need to be preempted as soon as possible if need_resched is
+ * set and we are preemptible. The hack here is to schedule a
+ * decrementer to fire here and reschedule for us if necessary.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT) && need_resched())
+ set_dec(1);
return 0;
}
diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c
index 623a7b7ab38b..9342e79870df 100644
--- a/arch/powerpc/mm/book3s64/hash_native.c
+++ b/arch/powerpc/mm/book3s64/hash_native.c
@@ -43,6 +43,29 @@
static DEFINE_RAW_SPINLOCK(native_tlbie_lock);
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map hpte_lock_map =
+ STATIC_LOCKDEP_MAP_INIT("hpte_lock", &hpte_lock_map);
+
+static void acquire_hpte_lock(void)
+{
+ lock_map_acquire(&hpte_lock_map);
+}
+
+static void release_hpte_lock(void)
+{
+ lock_map_release(&hpte_lock_map);
+}
+#else
+static void acquire_hpte_lock(void)
+{
+}
+
+static void release_hpte_lock(void)
+{
+}
+#endif
+
static inline unsigned long ___tlbie(unsigned long vpn, int psize,
int apsize, int ssize)
{
@@ -220,6 +243,7 @@ static inline void native_lock_hpte(struct hash_pte *hptep)
{
unsigned long *word = (unsigned long *)&hptep->v;
+ acquire_hpte_lock();
while (1) {
if (!test_and_set_bit_lock(HPTE_LOCK_BIT, word))
break;
@@ -234,6 +258,7 @@ static inline void native_unlock_hpte(struct hash_pte *hptep)
{
unsigned long *word = (unsigned long *)&hptep->v;
+ release_hpte_lock();
clear_bit_unlock(HPTE_LOCK_BIT, word);
}
@@ -243,8 +268,11 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
{
struct hash_pte *hptep = htab_address + hpte_group;
unsigned long hpte_v, hpte_r;
+ unsigned long flags;
int i;
+ local_irq_save(flags);
+
if (!(vflags & HPTE_V_BOLTED)) {
DBG_LOW(" insert(group=%lx, vpn=%016lx, pa=%016lx,"
" rflags=%lx, vflags=%lx, psize=%d)\n",
@@ -263,8 +291,10 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
hptep++;
}
- if (i == HPTES_PER_GROUP)
+ if (i == HPTES_PER_GROUP) {
+ local_irq_restore(flags);
return -1;
+ }
hpte_v = hpte_encode_v(vpn, psize, apsize, ssize) | vflags | HPTE_V_VALID;
hpte_r = hpte_encode_r(pa, psize, apsize) | rflags;
@@ -286,10 +316,13 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn,
* Now set the first dword including the valid bit
* NOTE: this also unlocks the hpte
*/
+ release_hpte_lock();
hptep->v = cpu_to_be64(hpte_v);
__asm__ __volatile__ ("ptesync" : : : "memory");
+ local_irq_restore(flags);
+
return i | (!!(vflags & HPTE_V_SECONDARY) << 3);
}
@@ -327,6 +360,7 @@ static long native_hpte_remove(unsigned long hpte_group)
return -1;
/* Invalidate the hpte. NOTE: this also unlocks it */
+ release_hpte_lock();
hptep->v = 0;
return i;
@@ -339,6 +373,9 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
struct hash_pte *hptep = htab_address + slot;
unsigned long hpte_v, want_v;
int ret = 0, local = 0;
+ unsigned long irqflags;
+
+ local_irq_save(irqflags);
want_v = hpte_encode_avpn(vpn, bpsize, ssize);
@@ -382,6 +419,8 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
if (!(flags & HPTE_NOHPTE_UPDATE))
tlbie(vpn, bpsize, apsize, ssize, local);
+ local_irq_restore(irqflags);
+
return ret;
}
@@ -445,6 +484,9 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
unsigned long vsid;
long slot;
struct hash_pte *hptep;
+ unsigned long flags;
+
+ local_irq_save(flags);
vsid = get_kernel_vsid(ea, ssize);
vpn = hpt_vpn(ea, vsid, ssize);
@@ -463,6 +505,8 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
* actual page size will be same.
*/
tlbie(vpn, psize, psize, ssize, 0);
+
+ local_irq_restore(flags);
}
/*
@@ -476,6 +520,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
unsigned long vsid;
long slot;
struct hash_pte *hptep;
+ unsigned long flags;
+
+ local_irq_save(flags);
vsid = get_kernel_vsid(ea, ssize);
vpn = hpt_vpn(ea, vsid, ssize);
@@ -493,6 +540,9 @@ static int native_hpte_removebolted(unsigned long ea, int psize, int ssize)
/* Invalidate the TLB */
tlbie(vpn, psize, psize, ssize, 0);
+
+ local_irq_restore(flags);
+
return 0;
}
@@ -517,10 +567,11 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
/* recheck with locks held */
hpte_v = hpte_get_old_v(hptep);
- if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID))
+ if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
/* Invalidate the hpte. NOTE: this also unlocks it */
+ release_hpte_lock();
hptep->v = 0;
- else
+ } else
native_unlock_hpte(hptep);
}
/*
@@ -580,10 +631,8 @@ static void native_hugepage_invalidate(unsigned long vsid,
hpte_v = hpte_get_old_v(hptep);
if (HPTE_V_COMPARE(hpte_v, want_v) && (hpte_v & HPTE_V_VALID)) {
- /*
- * Invalidate the hpte. NOTE: this also unlocks it
- */
-
+ /* Invalidate the hpte. NOTE: this also unlocks it */
+ release_hpte_lock();
hptep->v = 0;
} else
native_unlock_hpte(hptep);
@@ -765,8 +814,10 @@ static void native_flush_hash_range(unsigned long number, int local)
if (!HPTE_V_COMPARE(hpte_v, want_v) || !(hpte_v & HPTE_V_VALID))
native_unlock_hpte(hptep);
- else
+ else {
+ release_hpte_lock();
hptep->v = 0;
+ }
} pte_iterate_hashed_end();
}
diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
index 747492edb75a..51f48984abca 100644
--- a/arch/powerpc/mm/book3s64/hash_pgtable.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -404,7 +404,8 @@ EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
struct change_memory_parms {
unsigned long start, end, newpp;
- unsigned int step, nr_cpus, master_cpu;
+ unsigned int step, nr_cpus;
+ atomic_t master_cpu;
atomic_t cpu_counter;
};
@@ -478,7 +479,8 @@ static int change_memory_range_fn(void *data)
{
struct change_memory_parms *parms = data;
- if (parms->master_cpu != smp_processor_id())
+ // First CPU goes through, all others wait.
+ if (atomic_xchg(&parms->master_cpu, 1) == 1)
return chmem_secondary_loop(parms);
// Wait for all but one CPU (this one) to call-in
@@ -516,7 +518,7 @@ static bool hash__change_memory_range(unsigned long start, unsigned long end,
chmem_parms.end = end;
chmem_parms.step = step;
chmem_parms.newpp = newpp;
- chmem_parms.master_cpu = smp_processor_id();
+ atomic_set(&chmem_parms.master_cpu, 0);
cpus_read_lock();
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index df008edf7be0..6df4c6d38b66 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1981,7 +1981,7 @@ repeat:
}
#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
-static DEFINE_SPINLOCK(linear_map_hash_lock);
+static DEFINE_RAW_SPINLOCK(linear_map_hash_lock);
static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
{
@@ -2005,10 +2005,10 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
mmu_linear_psize, mmu_kernel_ssize);
BUG_ON (ret < 0);
- spin_lock(&linear_map_hash_lock);
+ raw_spin_lock(&linear_map_hash_lock);
BUG_ON(linear_map_hash_slots[lmi] & 0x80);
linear_map_hash_slots[lmi] = ret | 0x80;
- spin_unlock(&linear_map_hash_lock);
+ raw_spin_unlock(&linear_map_hash_lock);
}
static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
@@ -2018,14 +2018,14 @@ static void kernel_unmap_linear_page(unsigned long vaddr, unsigned long lmi)
unsigned long vpn = hpt_vpn(vaddr, vsid, mmu_kernel_ssize);
hash = hpt_hash(vpn, PAGE_SHIFT, mmu_kernel_ssize);
- spin_lock(&linear_map_hash_lock);
+ raw_spin_lock(&linear_map_hash_lock);
if (!(linear_map_hash_slots[lmi] & 0x80)) {
- spin_unlock(&linear_map_hash_lock);
+ raw_spin_unlock(&linear_map_hash_lock);
return;
}
hidx = linear_map_hash_slots[lmi] & 0x7f;
linear_map_hash_slots[lmi] = 0;
- spin_unlock(&linear_map_hash_lock);
+ raw_spin_unlock(&linear_map_hash_lock);
if (hidx & _PTEIDX_SECONDARY)
hash = ~hash;
slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index 507dc0b5987d..63fd925ccbb8 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -35,6 +35,7 @@
#include <asm/drmem.h>
#include "pseries.h"
+#include "vas.h" /* pseries_vas_dlpar_cpu() */
/*
* This isn't a module but we expose that to userspace
@@ -748,6 +749,16 @@ static ssize_t lparcfg_write(struct file *file, const char __user * buf,
return -EINVAL;
retval = update_ppp(new_entitled_ptr, NULL);
+
+ if (retval == H_SUCCESS || retval == H_CONSTRAINED) {
+ /*
+ * The hypervisor assigns VAS resources based
+ * on entitled capacity for shared mode.
+ * Reconfig VAS windows based on DLPAR CPU events.
+ */
+ if (pseries_vas_dlpar_cpu() != 0)
+ retval = H_HARDWARE;
+ }
} else if (!strcmp(kbuf, "capacity_weight")) {
char *endp;
*new_weight_ptr = (u8) simple_strtoul(tmp, &endp, 10);
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c
index 0e0524cbe20c..4ad6e510d405 100644
--- a/arch/powerpc/platforms/pseries/vas.c
+++ b/arch/powerpc/platforms/pseries/vas.c
@@ -200,17 +200,42 @@ static irqreturn_t pseries_vas_fault_thread_fn(int irq, void *data)
struct vas_user_win_ref *tsk_ref;
int rc;
- rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
- if (!rc) {
- tsk_ref = &txwin->vas_win.task_ref;
- vas_dump_crb(&crb);
- vas_update_csb(&crb, tsk_ref);
+ while (atomic_read(&txwin->pending_faults)) {
+ rc = h_get_nx_fault(txwin->vas_win.winid, (u64)virt_to_phys(&crb));
+ if (!rc) {
+ tsk_ref = &txwin->vas_win.task_ref;
+ vas_dump_crb(&crb);
+ vas_update_csb(&crb, tsk_ref);
+ }
+ atomic_dec(&txwin->pending_faults);
}
return IRQ_HANDLED;
}
/*
+ * irq_default_primary_handler() can be used only with IRQF_ONESHOT
+ * which disables IRQ before executing the thread handler and enables
+ * it after. But this disabling interrupt sets the VAS IRQ OFF
+ * state in the hypervisor. If the NX generates fault interrupt
+ * during this window, the hypervisor will not deliver this
+ * interrupt to the LPAR. So use VAS specific IRQ handler instead
+ * of calling the default primary handler.
+ */
+static irqreturn_t pseries_vas_irq_handler(int irq, void *data)
+{
+ struct pseries_vas_window *txwin = data;
+
+ /*
+ * The thread hanlder will process this interrupt if it is
+ * already running.
+ */
+ atomic_inc(&txwin->pending_faults);
+
+ return IRQ_WAKE_THREAD;
+}
+
+/*
* Allocate window and setup IRQ mapping.
*/
static int allocate_setup_window(struct pseries_vas_window *txwin,
@@ -240,8 +265,9 @@ static int allocate_setup_window(struct pseries_vas_window *txwin,
goto out_irq;
}
- rc = request_threaded_irq(txwin->fault_virq, NULL,
- pseries_vas_fault_thread_fn, IRQF_ONESHOT,
+ rc = request_threaded_irq(txwin->fault_virq,
+ pseries_vas_irq_handler,
+ pseries_vas_fault_thread_fn, 0,
txwin->name, txwin);
if (rc) {
pr_err("VAS-Window[%d]: Request IRQ(%u) failed with %d\n",
@@ -826,6 +852,25 @@ int vas_reconfig_capabilties(u8 type, int new_nr_creds)
mutex_unlock(&vas_pseries_mutex);
return rc;
}
+
+int pseries_vas_dlpar_cpu(void)
+{
+ int new_nr_creds, rc;
+
+ rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
+ vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
+ (u64)virt_to_phys(&hv_cop_caps));
+ if (!rc) {
+ new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
+ rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE, new_nr_creds);
+ }
+
+ if (rc)
+ pr_err("Failed reconfig VAS capabilities with DLPAR\n");
+
+ return rc;
+}
+
/*
* Total number of default credits available (target_credits)
* in LPAR depends on number of cores configured. It varies based on
@@ -840,7 +885,15 @@ static int pseries_vas_notifier(struct notifier_block *nb,
struct of_reconfig_data *rd = data;
struct device_node *dn = rd->dn;
const __be32 *intserv = NULL;
- int new_nr_creds, len, rc = 0;
+ int len;
+
+ /*
+ * For shared CPU partition, the hypervisor assigns total credits
+ * based on entitled core capacity. So updating VAS windows will
+ * be called from lparcfg_write().
+ */
+ if (is_shared_processor())
+ return NOTIFY_OK;
if ((action == OF_RECONFIG_ATTACH_NODE) ||
(action == OF_RECONFIG_DETACH_NODE))
@@ -852,19 +905,7 @@ static int pseries_vas_notifier(struct notifier_block *nb,
if (!intserv)
return NOTIFY_OK;
- rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES,
- vascaps[VAS_GZIP_DEF_FEAT_TYPE].feat,
- (u64)virt_to_phys(&hv_cop_caps));
- if (!rc) {
- new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds);
- rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE,
- new_nr_creds);
- }
-
- if (rc)
- pr_err("Failed reconfig VAS capabilities with DLPAR\n");
-
- return rc;
+ return pseries_vas_dlpar_cpu();
}
static struct notifier_block pseries_vas_nb = {
diff --git a/arch/powerpc/platforms/pseries/vas.h b/arch/powerpc/platforms/pseries/vas.h
index 333ffa2f9f42..7115043ec488 100644
--- a/arch/powerpc/platforms/pseries/vas.h
+++ b/arch/powerpc/platforms/pseries/vas.h
@@ -132,6 +132,7 @@ struct pseries_vas_window {
u64 flags;
char *name;
int fault_virq;
+ atomic_t pending_faults; /* Number of pending faults */
};
int sysfs_add_vas_caps(struct vas_cop_feat_caps *caps);
@@ -140,10 +141,15 @@ int __init sysfs_pseries_vas_init(struct vas_all_caps *vas_caps);
#ifdef CONFIG_PPC_VAS
int vas_migration_handler(int action);
+int pseries_vas_dlpar_cpu(void);
#else
static inline int vas_migration_handler(int action)
{
return 0;
}
+static inline int pseries_vas_dlpar_cpu(void)
+{
+ return 0;
+}
#endif
#endif /* _VAS_H */
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 6b48a3ae9843..fa78595a6089 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -411,14 +411,16 @@ config RISCV_ISA_SVPBMT
If you don't know what to do here, say Y.
-config CC_HAS_ZICBOM
+config TOOLCHAIN_HAS_ZICBOM
bool
- default y if 64BIT && $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
- default y if 32BIT && $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+ default y
+ depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zicbom)
+ depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zicbom)
+ depends on LLD_VERSION >= 150000 || LD_VERSION >= 23800
config RISCV_ISA_ZICBOM
bool "Zicbom extension support for non-coherent DMA operation"
- depends on CC_HAS_ZICBOM
+ depends on TOOLCHAIN_HAS_ZICBOM
depends on !XIP_KERNEL && MMU
select RISCV_DMA_NONCOHERENT
select RISCV_ALTERNATIVE
@@ -433,6 +435,13 @@ config RISCV_ISA_ZICBOM
If you don't know what to do here, say Y.
+config TOOLCHAIN_HAS_ZIHINTPAUSE
+ bool
+ default y
+ depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zihintpause)
+ depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zihintpause)
+ depends on LLD_VERSION >= 150000 || LD_VERSION >= 23600
+
config FPU
bool "FPU support"
default y
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 1c8ec656e916..0d13b597cb55 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -59,12 +59,10 @@ toolchain-need-zicsr-zifencei := $(call cc-option-yn, -march=$(riscv-march-y)_zi
riscv-march-$(toolchain-need-zicsr-zifencei) := $(riscv-march-y)_zicsr_zifencei
# Check if the toolchain supports Zicbom extension
-toolchain-supports-zicbom := $(call cc-option-yn, -march=$(riscv-march-y)_zicbom)
-riscv-march-$(toolchain-supports-zicbom) := $(riscv-march-y)_zicbom
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZICBOM) := $(riscv-march-y)_zicbom
# Check if the toolchain supports Zihintpause extension
-toolchain-supports-zihintpause := $(call cc-option-yn, -march=$(riscv-march-y)_zihintpause)
-riscv-march-$(toolchain-supports-zihintpause) := $(riscv-march-y)_zihintpause
+riscv-march-$(CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE) := $(riscv-march-y)_zihintpause
KBUILD_CFLAGS += -march=$(subst fd,,$(riscv-march-y))
KBUILD_AFLAGS += -march=$(riscv-march-y)
diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 38af2ec7b9bf..6d58bbb5da46 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -14,8 +14,8 @@
#define JUMP_LABEL_NOP_SIZE 4
-static __always_inline bool arch_static_branch(struct static_key *key,
- bool branch)
+static __always_inline bool arch_static_branch(struct static_key * const key,
+ const bool branch)
{
asm_volatile_goto(
" .option push \n\t"
@@ -35,8 +35,8 @@ label:
return true;
}
-static __always_inline bool arch_static_branch_jump(struct static_key *key,
- bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key * const key,
+ const bool branch)
{
asm_volatile_goto(
" .option push \n\t"
diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h
index 1e4f8b4aef79..fa70cfe507aa 100644
--- a/arch/riscv/include/asm/vdso/processor.h
+++ b/arch/riscv/include/asm/vdso/processor.h
@@ -21,7 +21,7 @@ static inline void cpu_relax(void)
* Reduce instruction retirement.
* This assumes the PC changes.
*/
-#ifdef __riscv_zihintpause
+#ifdef CONFIG_TOOLCHAIN_HAS_ZIHINTPAUSE
__asm__ __volatile__ ("pause");
#else
/* Encoding of the pause instruction */
diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c
index fa427bdcf773..852ecccd8920 100644
--- a/arch/riscv/kernel/cpu.c
+++ b/arch/riscv/kernel/cpu.c
@@ -213,6 +213,9 @@ static void print_mmu(struct seq_file *f)
static void *c_start(struct seq_file *m, loff_t *pos)
{
+ if (*pos == nr_cpu_ids)
+ return NULL;
+
*pos = cpumask_next(*pos - 1, cpu_online_mask);
if ((*pos) < nr_cpu_ids)
return (void *)(uintptr_t)(1 + *pos);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index a22e418dbd82..e1226709490f 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -113,6 +113,8 @@ static void __init kasan_populate_pud(pgd_t *pgd,
base_pud = pt_ops.get_pud_virt(pfn_to_phys(_pgd_pfn(*pgd)));
} else if (pgd_none(*pgd)) {
base_pud = memblock_alloc(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE);
+ memcpy(base_pud, (void *)kasan_early_shadow_pud,
+ sizeof(pud_t) * PTRS_PER_PUD);
} else {
base_pud = (pud_t *)pgd_page_vaddr(*pgd);
if (base_pud == lm_alias(kasan_early_shadow_pud)) {
@@ -173,8 +175,11 @@ static void __init kasan_populate_p4d(pgd_t *pgd,
base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(*pgd)));
} else {
base_p4d = (p4d_t *)pgd_page_vaddr(*pgd);
- if (base_p4d == lm_alias(kasan_early_shadow_p4d))
+ if (base_p4d == lm_alias(kasan_early_shadow_p4d)) {
base_p4d = memblock_alloc(PTRS_PER_PUD * sizeof(p4d_t), PAGE_SIZE);
+ memcpy(base_p4d, (void *)kasan_early_shadow_p4d,
+ sizeof(p4d_t) * PTRS_PER_P4D);
+ }
}
p4dp = base_p4d + p4d_index(vaddr);
diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
index af5c6860e0a1..fa9d33b01b85 100644
--- a/arch/s390/boot/vmlinux.lds.S
+++ b/arch/s390/boot/vmlinux.lds.S
@@ -102,8 +102,17 @@ SECTIONS
_compressed_start = .;
*(.vmlinux.bin.compressed)
_compressed_end = .;
- FILL(0xff);
- . = ALIGN(4096);
+ }
+
+#define SB_TRAILER_SIZE 32
+ /* Trailer needed for Secure Boot */
+ . += SB_TRAILER_SIZE; /* make sure .sb.trailer does not overwrite the previous section */
+ . = ALIGN(4096) - SB_TRAILER_SIZE;
+ .sb.trailer : {
+ QUAD(0)
+ QUAD(0)
+ QUAD(0)
+ QUAD(0x000000207a49504c)
}
_end = .;
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index e08c882dccaa..eaeaeb3ff0be 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -17,7 +17,8 @@
"3: jl 1b\n" \
" lhi %0,0\n" \
"4: sacf 768\n" \
- EX_TABLE(0b,4b) EX_TABLE(2b,4b) EX_TABLE(3b,4b) \
+ EX_TABLE(0b,4b) EX_TABLE(1b,4b) \
+ EX_TABLE(2b,4b) EX_TABLE(3b,4b) \
: "=d" (ret), "=&d" (oldval), "=&d" (newval), \
"=m" (*uaddr) \
: "0" (-EFAULT), "d" (oparg), "a" (uaddr), \
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index d5c7c1e30c17..74b53c531e0c 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -459,6 +459,7 @@ static int paiext_push_sample(void)
raw.frag.data = cpump->save;
raw.size = raw.frag.size;
data.raw = &raw;
+ data.sample_flags |= PERF_SAMPLE_RAW;
}
overflow = perf_event_overflow(event, &data, &regs);
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
deleted file mode 100644
index 484608c71dd0..000000000000
--- a/arch/s390/kvm/irq.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * s390 irqchip routines
- *
- * Copyright IBM Corp. 2014
- *
- * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
- */
-#ifndef __KVM_IRQ_H
-#define __KVM_IRQ_H
-
-#include <linux/kvm_host.h>
-
-static inline int irqchip_in_kernel(struct kvm *kvm)
-{
- return 1;
-}
-
-#endif
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8a0c884bf737..e4890e04b210 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1218,6 +1218,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm,
return 0;
}
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
+
static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_tod_clock gtod;
@@ -1227,7 +1229,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
return -EINVAL;
- kvm_s390_set_tod_clock(kvm, &gtod);
+ __kvm_s390_set_tod_clock(kvm, &gtod);
VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
gtod.epoch_idx, gtod.tod);
@@ -1258,7 +1260,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
sizeof(gtod.tod)))
return -EFAULT;
- kvm_s390_set_tod_clock(kvm, &gtod);
+ __kvm_s390_set_tod_clock(kvm, &gtod);
VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
return 0;
}
@@ -1270,6 +1272,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
if (attr->flags)
return -EINVAL;
+ mutex_lock(&kvm->lock);
+ /*
+ * For protected guests, the TOD is managed by the ultravisor, so trying
+ * to change it will never bring the expected results.
+ */
+ if (kvm_s390_pv_is_protected(kvm)) {
+ ret = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+
switch (attr->attr) {
case KVM_S390_VM_TOD_EXT:
ret = kvm_s390_set_tod_ext(kvm, attr);
@@ -1284,6 +1296,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
ret = -ENXIO;
break;
}
+
+out_unlock:
+ mutex_unlock(&kvm->lock);
return ret;
}
@@ -4425,13 +4440,6 @@ static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_t
preempt_enable();
}
-void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
-{
- mutex_lock(&kvm->lock);
- __kvm_s390_set_tod_clock(kvm, gtod);
- mutex_unlock(&kvm->lock);
-}
-
int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
{
if (!mutex_trylock(&kvm->lock))
@@ -5608,6 +5616,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return true;
+}
+
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 826754937ae4..d48588c207d8 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -367,7 +367,6 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu);
int kvm_s390_handle_sigp_pei(struct kvm_vcpu *vcpu);
/* implemented in kvm-s390.c */
-void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable);
int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long addr);
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index c50c1645c0ae..ded1af2ddae9 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -126,7 +126,7 @@ int kvm_s390_pci_aen_init(u8 nisc)
return -EPERM;
mutex_lock(&aift->aift_lock);
- aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev),
+ aift->kzdev = kcalloc(ZPCI_NR_DEVICES, sizeof(struct kvm_zdev *),
GFP_KERNEL);
if (!aift->kzdev) {
rc = -ENOMEM;
diff --git a/arch/s390/lib/uaccess.c b/arch/s390/lib/uaccess.c
index 58033dfcb6d4..720036fb1924 100644
--- a/arch/s390/lib/uaccess.c
+++ b/arch/s390/lib/uaccess.c
@@ -157,7 +157,7 @@ unsigned long __clear_user(void __user *to, unsigned long size)
asm volatile(
" lr 0,%[spec]\n"
"0: mvcos 0(%1),0(%4),%0\n"
- " jz 4f\n"
+ "6: jz 4f\n"
"1: algr %0,%2\n"
" slgr %1,%2\n"
" j 0b\n"
@@ -167,11 +167,11 @@ unsigned long __clear_user(void __user *to, unsigned long size)
" clgr %0,%3\n" /* copy crosses next page boundary? */
" jnh 5f\n"
"3: mvcos 0(%1),0(%4),%3\n"
- " slgr %0,%3\n"
+ "7: slgr %0,%3\n"
" j 5f\n"
"4: slgr %0,%0\n"
"5:\n"
- EX_TABLE(0b,2b) EX_TABLE(3b,5b)
+ EX_TABLE(0b,2b) EX_TABLE(6b,2b) EX_TABLE(3b,5b) EX_TABLE(7b,5b)
: "+a" (size), "+a" (to), "+a" (tmp1), "=a" (tmp2)
: "a" (empty_zero_page), [spec] "d" (spec.val)
: "cc", "memory", "0");
diff --git a/arch/s390/pci/pci_mmio.c b/arch/s390/pci/pci_mmio.c
index 080c88620723..588089332931 100644
--- a/arch/s390/pci/pci_mmio.c
+++ b/arch/s390/pci/pci_mmio.c
@@ -64,7 +64,7 @@ static inline int __pcistg_mio_inuser(
asm volatile (
" sacf 256\n"
"0: llgc %[tmp],0(%[src])\n"
- " sllg %[val],%[val],8\n"
+ "4: sllg %[val],%[val],8\n"
" aghi %[src],1\n"
" ogr %[val],%[tmp]\n"
" brctg %[cnt],0b\n"
@@ -72,7 +72,7 @@ static inline int __pcistg_mio_inuser(
"2: ipm %[cc]\n"
" srl %[cc],28\n"
"3: sacf 768\n"
- EX_TABLE(0b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
+ EX_TABLE(0b, 3b) EX_TABLE(4b, 3b) EX_TABLE(1b, 3b) EX_TABLE(2b, 3b)
:
[src] "+a" (src), [cnt] "+d" (cnt),
[val] "+d" (val), [tmp] "=d" (tmp),
@@ -215,10 +215,10 @@ static inline int __pcilg_mio_inuser(
"2: ahi %[shift],-8\n"
" srlg %[tmp],%[val],0(%[shift])\n"
"3: stc %[tmp],0(%[dst])\n"
- " aghi %[dst],1\n"
+ "5: aghi %[dst],1\n"
" brctg %[cnt],2b\n"
"4: sacf 768\n"
- EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b)
+ EX_TABLE(0b, 4b) EX_TABLE(1b, 4b) EX_TABLE(3b, 4b) EX_TABLE(5b, 4b)
:
[ioaddr_len] "+&d" (ioaddr_len.pair),
[cc] "+d" (cc), [val] "=d" (val),
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 928dcf7a20d9..b8998cf0508a 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -34,6 +34,8 @@
#define VE_GET_PORT_NUM(e) ((e) >> 16)
#define VE_IS_IO_STRING(e) ((e) & BIT(4))
+#define ATTR_SEPT_VE_DISABLE BIT(28)
+
/*
* Wrapper for standard use of __tdx_hypercall with no output aside from
* return code.
@@ -98,10 +100,11 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9,
panic("TDCALL %lld failed (Buggy TDX module!)\n", fn);
}
-static u64 get_cc_mask(void)
+static void tdx_parse_tdinfo(u64 *cc_mask)
{
struct tdx_module_output out;
unsigned int gpa_width;
+ u64 td_attr;
/*
* TDINFO TDX module call is used to get the TD execution environment
@@ -109,19 +112,27 @@ static u64 get_cc_mask(void)
* information, etc. More details about the ABI can be found in TDX
* Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL
* [TDG.VP.INFO].
+ */
+ tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
+
+ /*
+ * The highest bit of a guest physical address is the "sharing" bit.
+ * Set it for shared pages and clear it for private pages.
*
* The GPA width that comes out of this call is critical. TDX guests
* can not meaningfully run without it.
*/
- tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out);
-
gpa_width = out.rcx & GENMASK(5, 0);
+ *cc_mask = BIT_ULL(gpa_width - 1);
/*
- * The highest bit of a guest physical address is the "sharing" bit.
- * Set it for shared pages and clear it for private pages.
+ * The kernel can not handle #VE's when accessing normal kernel
+ * memory. Ensure that no #VE will be delivered for accesses to
+ * TD-private memory. Only VMM-shared memory (MMIO) will #VE.
*/
- return BIT_ULL(gpa_width - 1);
+ td_attr = out.rdx;
+ if (!(td_attr & ATTR_SEPT_VE_DISABLE))
+ panic("TD misconfiguration: SEPT_VE_DISABLE attibute must be set.\n");
}
/*
@@ -758,7 +769,7 @@ void __init tdx_early_init(void)
setup_force_cpu_cap(X86_FEATURE_TDX_GUEST);
cc_set_vendor(CC_VENDOR_INTEL);
- cc_mask = get_cc_mask();
+ tdx_parse_tdinfo(&cc_mask);
cc_set_mask(cc_mask);
/*
diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c
index b7664d018851..8fa58b0f3cb3 100644
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -27,13 +27,17 @@
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
+#define POLYVAL_ALIGN 16
+#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
+#define POLYVAL_ALIGN_EXTRA ((POLYVAL_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1))
+#define POLYVAL_CTX_SIZE (sizeof(struct polyval_tfm_ctx) + POLYVAL_ALIGN_EXTRA)
#define NUM_KEY_POWERS 8
struct polyval_tfm_ctx {
/*
* These powers must be in the order h^8, ..., h^1.
*/
- u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE];
+ u8 key_powers[NUM_KEY_POWERS][POLYVAL_BLOCK_SIZE] POLYVAL_ALIGN_ATTR;
};
struct polyval_desc_ctx {
@@ -45,6 +49,11 @@ asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator);
asmlinkage void clmul_polyval_mul(u8 *op1, const u8 *op2);
+static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
+{
+ return PTR_ALIGN(crypto_shash_ctx(tfm), POLYVAL_ALIGN);
+}
+
static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator)
{
@@ -72,7 +81,7 @@ static void internal_polyval_mul(u8 *op1, const u8 *op2)
static int polyval_x86_setkey(struct crypto_shash *tfm,
const u8 *key, unsigned int keylen)
{
- struct polyval_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+ struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(tfm);
int i;
if (keylen != POLYVAL_BLOCK_SIZE)
@@ -102,7 +111,7 @@ static int polyval_x86_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
- const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+ const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
u8 *pos;
unsigned int nblocks;
unsigned int n;
@@ -143,7 +152,7 @@ static int polyval_x86_update(struct shash_desc *desc,
static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
- const struct polyval_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+ const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
if (dctx->bytes) {
internal_polyval_mul(dctx->buffer,
@@ -167,7 +176,7 @@ static struct shash_alg polyval_alg = {
.cra_driver_name = "polyval-clmulni",
.cra_priority = 200,
.cra_blocksize = POLYVAL_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct polyval_tfm_ctx),
+ .cra_ctxsize = POLYVAL_CTX_SIZE,
.cra_module = THIS_MODULE,
},
};
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 3271735f0070..4cb710efbdd9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2,
/* Extension Memory */
if (ibs_caps & IBS_CAPS_ZEN4 &&
ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) {
- data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM;
+ data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL;
if (op_data2->rmt_node) {
data_src->mem_remote = PERF_MEM_REMOTE_REMOTE;
/* IBS doesn't provide Remote socket detail */
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a646a5f9a235..1b92bf05fd65 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4911,6 +4911,7 @@ static const struct x86_cpu_desc isolation_ucodes[] = {
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 5, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 6, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 7, 0x00000000),
+ INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_X, 11, 0x00000000),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE_L, 3, 0x0000007c),
INTEL_CPU_DESC(INTEL_FAM6_SKYLAKE, 3, 0x0000007c),
INTEL_CPU_DESC(INTEL_FAM6_KABYLAKE, 9, 0x0000004e),
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7839507b3844..446d2833efa7 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -982,8 +982,13 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */
INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */
@@ -1004,8 +1009,13 @@ struct event_constraint intel_spr_pebs_event_constraints[] = {
INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe),
INTEL_PLD_CONSTRAINT(0x1cd, 0xfe),
INTEL_PSD_CONSTRAINT(0x2cd, 0x1),
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf),
- INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf),
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */
+ INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */
INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf),
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 8259d725054d..4dbde69c423b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1603,10 +1603,8 @@ clear_arch_lbr:
* x86_perf_get_lbr - get the LBR records information
*
* @lbr: the caller's memory to store the LBR records information
- *
- * Returns: 0 indicates the LBR info has been successfully obtained
*/
-int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
int lbr_fmt = x86_pmu.intel_cap.lbr_format;
@@ -1614,8 +1612,6 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
lbr->from = x86_pmu.lbr_from;
lbr->to = x86_pmu.lbr_to;
lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
-
- return 0;
}
EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 77e3a47af5ad..a829492bca4c 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -619,12 +619,8 @@ static int rapl_check_hw_unit(struct rapl_model *rm)
case RAPL_UNIT_QUIRK_INTEL_HSW:
rapl_hw_unit[PERF_RAPL_RAM] = 16;
break;
- /*
- * SPR shares the same DRAM domain energy unit as HSW, plus it
- * also has a fixed energy unit for Psys domain.
- */
+ /* SPR uses a fixed energy unit for Psys domain. */
case RAPL_UNIT_QUIRK_INTEL_SPR:
- rapl_hw_unit[PERF_RAPL_RAM] = 16;
rapl_hw_unit[PERF_RAPL_PSYS] = 0;
break;
default:
@@ -806,7 +802,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &model_skl),
X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &model_spr),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &model_skl),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &model_skl),
{},
};
MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index b71f4f2ecdd5..1419c4e04d45 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -308,6 +308,9 @@
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
+#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */
+#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */
+#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 3089ec352743..e3efaf6e6b62 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -61,6 +61,8 @@
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
/* Support for debug MSRs available */
#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11)
+/* Support for extended gva ranges for flush hypercalls available */
+#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14)
/*
* Support for returning hypercall output block via XMM
* registers is available
@@ -598,6 +600,41 @@ struct hv_enlightened_vmcs {
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF
+/*
+ * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by
+ * pairing it with architecturally impossible exit reasons. Bit 28 is set only
+ * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit
+ * is pending. I.e. it will never be set by hardware for non-SMI exits (there
+ * are only three), nor will it ever be set unless the VMM is an STM.
+ */
+#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031
+
+/*
+ * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose
+ * SVM enlightenments to guests.
+ */
+struct hv_vmcb_enlightenments {
+ struct __packed hv_enlightenments_control {
+ u32 nested_flush_hypercall:1;
+ u32 msr_bitmap:1;
+ u32 enlightened_npt_tlb: 1;
+ u32 reserved:29;
+ } __packed hv_enlightenments_control;
+ u32 hv_vp_id;
+ u64 hv_vm_id;
+ u64 partition_assist_page;
+ u64 reserved;
+} __packed;
+
+/*
+ * Hyper-V uses the software reserved clean bit in VMCB.
+ */
+#define HV_VMCB_NESTED_ENLIGHTENMENTS 31
+
+/* Synthetic VM-Exit */
+#define HV_SVM_EXITCODE_ENL 0xf0000000
+#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1)
+
struct hv_partition_assist_pg {
u32 tlb_lock_count;
};
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5d75fe229342..347707d459c6 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -107,6 +107,11 @@
#define INTEL_FAM6_SAPPHIRERAPIDS_X 0x8F /* Golden Cove */
+#define INTEL_FAM6_EMERALDRAPIDS_X 0xCF
+
+#define INTEL_FAM6_GRANITERAPIDS_X 0xAD
+#define INTEL_FAM6_GRANITERAPIDS_D 0xAE
+
#define INTEL_FAM6_ALDERLAKE 0x97 /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_L 0x9A /* Golden Cove / Gracemont */
#define INTEL_FAM6_ALDERLAKE_N 0xBE
@@ -118,7 +123,7 @@
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
-/* "Small Core" Processors (Atom) */
+/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_FAM6_ATOM_BONNELL 0x1C /* Diamondville, Pineview */
#define INTEL_FAM6_ATOM_BONNELL_MID 0x26 /* Silverthorne, Lincroft */
@@ -145,6 +150,10 @@
#define INTEL_FAM6_ATOM_TREMONT 0x96 /* Elkhart Lake */
#define INTEL_FAM6_ATOM_TREMONT_L 0x9C /* Jasper Lake */
+#define INTEL_FAM6_SIERRAFOREST_X 0xAF
+
+#define INTEL_FAM6_GRANDRIDGE 0xB6
+
/* Xeon Phi */
#define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 82ba4a564e58..abccd51dcfca 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -110,10 +110,12 @@ KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt)
KVM_X86_OP_OPTIONAL(set_hv_timer)
KVM_X86_OP_OPTIONAL(cancel_hv_timer)
KVM_X86_OP(setup_mce)
+#ifdef CONFIG_KVM_SMM
KVM_X86_OP(smi_allowed)
KVM_X86_OP(enter_smm)
KVM_X86_OP(leave_smm)
KVM_X86_OP(enable_smi_window)
+#endif
KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
@@ -123,7 +125,7 @@ KVM_X86_OP_OPTIONAL(guest_memory_reclaimed)
KVM_X86_OP(get_msr_feature)
KVM_X86_OP(can_emulate_instruction)
KVM_X86_OP(apic_init_signal_blocked)
-KVM_X86_OP_OPTIONAL(enable_direct_tlbflush)
+KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush)
KVM_X86_OP_OPTIONAL(migrate_timers)
KVM_X86_OP(msr_filter_changed)
KVM_X86_OP(complete_emulated_msr)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7551b6f9c31c..d1013c4f673c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
#include <linux/clocksource.h>
#include <linux/irqbypass.h>
#include <linux/hyperv.h>
+#include <linux/kfifo.h>
#include <asm/apic.h>
#include <asm/pvclock-abi.h>
@@ -81,7 +82,9 @@
#define KVM_REQ_NMI KVM_ARCH_REQ(9)
#define KVM_REQ_PMU KVM_ARCH_REQ(10)
#define KVM_REQ_PMI KVM_ARCH_REQ(11)
+#ifdef CONFIG_KVM_SMM
#define KVM_REQ_SMI KVM_ARCH_REQ(12)
+#endif
#define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13)
#define KVM_REQ_MCLOCK_INPROGRESS \
KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
@@ -108,6 +111,8 @@
KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \
KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
+#define KVM_REQ_HV_TLB_FLUSH \
+ KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -204,6 +209,7 @@ typedef enum exit_fastpath_completion fastpath_t;
struct x86_emulate_ctxt;
struct x86_exception;
+union kvm_smram;
enum x86_intercept;
enum x86_intercept_stage;
@@ -253,16 +259,16 @@ enum x86_intercept_stage;
#define PFERR_GUEST_PAGE_BIT 33
#define PFERR_IMPLICIT_ACCESS_BIT 48
-#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
-#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
-#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
-#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
-#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
-#define PFERR_PK_MASK (1U << PFERR_PK_BIT)
-#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT)
-#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT)
-#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT)
-#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT)
+#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
+#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
+#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
+#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
+#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
#define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \
PFERR_WRITE_MASK | \
@@ -488,20 +494,27 @@ enum pmc_type {
struct kvm_pmc {
enum pmc_type type;
u8 idx;
+ bool is_paused;
+ bool intr;
u64 counter;
+ u64 prev_counter;
u64 eventsel;
struct perf_event *perf_event;
struct kvm_vcpu *vcpu;
/*
+ * only for creating or reusing perf_event,
* eventsel value for general purpose counters,
* ctrl value for fixed counters.
*/
u64 current_config;
- bool is_paused;
- bool intr;
};
+/* More counters may conflict with other existing Architectural MSRs */
+#define KVM_INTEL_PMC_MAX_GENERIC 8
+#define MSR_ARCH_PERFMON_PERFCTR_MAX (MSR_ARCH_PERFMON_PERFCTR0 + KVM_INTEL_PMC_MAX_GENERIC - 1)
+#define MSR_ARCH_PERFMON_EVENTSEL_MAX (MSR_ARCH_PERFMON_EVENTSEL0 + KVM_INTEL_PMC_MAX_GENERIC - 1)
#define KVM_PMC_MAX_FIXED 3
+#define KVM_AMD_PMC_MAX_GENERIC 6
struct kvm_pmu {
unsigned nr_arch_gp_counters;
unsigned nr_arch_fixed_counters;
@@ -516,10 +529,19 @@ struct kvm_pmu {
u64 reserved_bits;
u64 raw_event_mask;
u8 version;
- struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
+ struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
struct irq_work irq_work;
- DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+
+ /*
+ * Overlay the bitmap with a 64-bit atomic so that all bits can be
+ * set in a single access, e.g. to reprogram all counters when the PMU
+ * filter changes.
+ */
+ union {
+ DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+ atomic64_t __reprogram_pmi;
+ };
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
@@ -597,6 +619,29 @@ struct kvm_vcpu_hv_synic {
bool dont_zero_synic_pages;
};
+/* The maximum number of entries on the TLB flush fifo. */
+#define KVM_HV_TLB_FLUSH_FIFO_SIZE (16)
+/*
+ * Note: the following 'magic' entry is made up by KVM to avoid putting
+ * anything besides GVA on the TLB flush fifo. It is theoretically possible
+ * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000
+ * which will look identical. KVM's action to 'flush everything' instead of
+ * flushing these particular addresses is, however, fully legitimate as
+ * flushing more than requested is always OK.
+ */
+#define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1)
+
+enum hv_tlb_flush_fifos {
+ HV_L1_TLB_FLUSH_FIFO,
+ HV_L2_TLB_FLUSH_FIFO,
+ HV_NR_TLB_FLUSH_FIFOS,
+};
+
+struct kvm_vcpu_hv_tlb_flush_fifo {
+ spinlock_t write_lock;
+ DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE);
+};
+
/* Hyper-V per vcpu emulation context */
struct kvm_vcpu_hv {
struct kvm_vcpu *vcpu;
@@ -618,6 +663,19 @@ struct kvm_vcpu_hv {
u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */
u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */
} cpuid_cache;
+
+ struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
+
+ /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+
+ struct hv_vp_assist_page vp_assist_page;
+
+ struct {
+ u64 pa_page_gpa;
+ u64 vm_id;
+ u32 vp_id;
+ } nested;
};
/* Xen HVM per vcpu emulation context */
@@ -1151,7 +1209,18 @@ struct kvm_arch {
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
struct list_head active_mmu_pages;
struct list_head zapped_obsolete_pages;
- struct list_head lpage_disallowed_mmu_pages;
+ /*
+ * A list of kvm_mmu_page structs that, if zapped, could possibly be
+ * replaced by an NX huge page. A shadow page is on this list if its
+ * existence disallows an NX huge page (nx_huge_page_disallowed is set)
+ * and there are no other conditions that prevent a huge page, e.g.
+ * the backing host page is huge, dirtly logging is not enabled for its
+ * memslot, etc... Note, zapping shadow pages on this list doesn't
+ * guarantee an NX huge page will be created in its stead, e.g. if the
+ * guest attempts to execute from the region then KVM obviously can't
+ * create an NX huge page (without hanging the guest).
+ */
+ struct list_head possible_nx_huge_pages;
struct kvm_page_track_notifier_node mmu_sp_tracker;
struct kvm_page_track_notifier_head track_notifier_head;
/*
@@ -1267,7 +1336,7 @@ struct kvm_arch {
bool sgx_provisioning_allowed;
struct kvm_pmu_event_filter __rcu *pmu_event_filter;
- struct task_struct *nx_lpage_recovery_thread;
+ struct task_struct *nx_huge_page_recovery_thread;
#ifdef CONFIG_X86_64
/*
@@ -1279,6 +1348,9 @@ struct kvm_arch {
*/
bool tdp_mmu_enabled;
+ /* The number of TDP MMU pages across all roots. */
+ atomic64_t tdp_mmu_pages;
+
/*
* List of kvm_mmu_page structs being used as roots.
* All kvm_mmu_page structs in the list should have
@@ -1300,20 +1372,12 @@ struct kvm_arch {
struct list_head tdp_mmu_roots;
/*
- * List of kvm_mmu_page structs not being used as roots.
- * All kvm_mmu_page structs in the list should have
- * tdp_mmu_page set and a tdp_mmu_root_count of 0.
- */
- struct list_head tdp_mmu_pages;
-
- /*
* Protects accesses to the following fields when the MMU lock
* is held in read mode:
* - tdp_mmu_roots (above)
- * - tdp_mmu_pages (above)
* - the link field of kvm_mmu_page structs used by the TDP MMU
- * - lpage_disallowed_mmu_pages
- * - the lpage_disallowed_link field of kvm_mmu_page structs used
+ * - possible_nx_huge_pages;
+ * - the possible_nx_huge_page_link field of kvm_mmu_page structs used
* by the TDP MMU
* It is acceptable, but not necessary, to acquire this lock when
* the thread holds the MMU lock in write mode.
@@ -1607,10 +1671,12 @@ struct kvm_x86_ops {
void (*setup_mce)(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_KVM_SMM
int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
- int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
+ int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+ int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
void (*enable_smi_window)(struct kvm_vcpu *vcpu);
+#endif
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
@@ -1625,7 +1691,7 @@ struct kvm_x86_ops {
void *insn, int insn_len);
bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
- int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
+ int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu);
void (*migrate_timers)(struct kvm_vcpu *vcpu);
void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
@@ -1658,6 +1724,7 @@ struct kvm_x86_nested_ops {
int (*enable_evmcs)(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu);
+ void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_init_ops {
@@ -1839,6 +1906,7 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu);
int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
@@ -1904,8 +1972,6 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu,
void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu);
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
-gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
- struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception);
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
@@ -1989,14 +2055,18 @@ enum {
#define HF_NMI_MASK (1 << 3)
#define HF_IRET_MASK (1 << 4)
#define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
+
+#ifdef CONFIG_KVM_SMM
#define HF_SMM_MASK (1 << 6)
#define HF_SMM_INSIDE_NMI_MASK (1 << 7)
-#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
-#define KVM_ADDRESS_SPACE_NUM 2
-
-#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
-#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+# define KVM_ADDRESS_SPACE_NUM 2
+# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+#else
+# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0)
+#endif
#define KVM_ARCH_WANT_MMU_NOTIFIER
@@ -2084,12 +2154,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#endif
}
-#define put_smstate(type, buf, offset, val) \
- *(type *)((buf) + (offset) - 0x7e00) = val
-
-#define GET_SMSTATE(type, buf, offset) \
- (*(type *)((buf) + (offset) - 0x7e00))
-
int kvm_cpu_dirty_log_size(void);
int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 9ac46dbe57d4..5d0f6891ae61 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -543,12 +543,12 @@ static inline void perf_check_microcode(void) { }
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL)
extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
-extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
+extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr);
#else
struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data);
-static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
+static inline void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
{
- return -1;
+ memset(lbr, 0, sizeof(*lbr));
}
#endif
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 5393babc0598..cb0386fc4dc3 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -13,7 +13,7 @@
* Takes the guest view of SPEC_CTRL MSR as a parameter and also
* the guest's version of VIRT_SPEC_CTRL, if emulated.
*/
-extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool guest);
+extern void x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool guest);
/**
* x86_spec_ctrl_set_guest - Set speculation control registers for the guest
@@ -24,9 +24,9 @@ extern void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bo
* Avoids writing to the MSR if the content/bits are the same
*/
static inline
-void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+void x86_spec_ctrl_set_guest(u64 guest_virt_spec_ctrl)
{
- x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, true);
+ x86_virt_spec_ctrl(guest_virt_spec_ctrl, true);
}
/**
@@ -38,9 +38,9 @@ void x86_spec_ctrl_set_guest(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
* Avoids writing to the MSR if the content/bits are the same
*/
static inline
-void x86_spec_ctrl_restore_host(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl)
+void x86_spec_ctrl_restore_host(u64 guest_virt_spec_ctrl)
{
- x86_virt_spec_ctrl(guest_spec_ctrl, guest_virt_spec_ctrl, false);
+ x86_virt_spec_ctrl(guest_virt_spec_ctrl, false);
}
/* AMD specific Speculative Store Bypass MSR data */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index 3b87d889b6e1..888731ccf1f6 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -10,10 +10,13 @@
/* Even with __builtin_ the compiler may decide to use the out of line
function. */
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
+#include <linux/kmsan_string.h>
+#endif
+
#define __HAVE_ARCH_MEMCPY 1
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
#undef memcpy
-void *__msan_memcpy(void *dst, const void *src, size_t size);
#define memcpy __msan_memcpy
#else
extern void *memcpy(void *to, const void *from, size_t len);
@@ -21,7 +24,7 @@ extern void *memcpy(void *to, const void *from, size_t len);
extern void *__memcpy(void *to, const void *from, size_t len);
#define __HAVE_ARCH_MEMSET
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
extern void *__msan_memset(void *s, int c, size_t n);
#undef memset
#define memset __msan_memset
@@ -67,7 +70,7 @@ static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
}
#define __HAVE_ARCH_MEMMOVE
-#if defined(__SANITIZE_MEMORY__)
+#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY)
#undef memmove
void *__msan_memmove(void *dest, const void *src, size_t len);
#define memmove __msan_memmove
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 0361626841bc..cb1ee53ad3b1 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -5,6 +5,8 @@
#include <uapi/asm/svm.h>
#include <uapi/asm/kvm.h>
+#include <asm/hyperv-tlfs.h>
+
/*
* 32-bit intercept words in the VMCB Control Area, starting
* at Byte offset 000h.
@@ -161,7 +163,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
* Offset 0x3e0, 32 bytes reserved
* for use by hypervisor/software.
*/
- u8 reserved_sw[32];
+ union {
+ struct hv_vmcb_enlightenments hv_enlightenments;
+ u8 reserved_sw[32];
+ };
};
@@ -293,12 +298,13 @@ struct vmcb_save_area {
struct vmcb_seg ldtr;
struct vmcb_seg idtr;
struct vmcb_seg tr;
- u8 reserved_1[42];
+ /* Reserved fields are named following their struct offset */
+ u8 reserved_0xa0[42];
u8 vmpl;
u8 cpl;
- u8 reserved_2[4];
+ u8 reserved_0xcc[4];
u64 efer;
- u8 reserved_3[112];
+ u8 reserved_0xd8[112];
u64 cr4;
u64 cr3;
u64 cr0;
@@ -306,7 +312,7 @@ struct vmcb_save_area {
u64 dr6;
u64 rflags;
u64 rip;
- u8 reserved_4[88];
+ u8 reserved_0x180[88];
u64 rsp;
u64 s_cet;
u64 ssp;
@@ -321,14 +327,14 @@ struct vmcb_save_area {
u64 sysenter_esp;
u64 sysenter_eip;
u64 cr2;
- u8 reserved_5[32];
+ u8 reserved_0x248[32];
u64 g_pat;
u64 dbgctl;
u64 br_from;
u64 br_to;
u64 last_excp_from;
u64 last_excp_to;
- u8 reserved_6[72];
+ u8 reserved_0x298[72];
u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */
} __packed;
@@ -349,12 +355,12 @@ struct sev_es_save_area {
u64 vmpl2_ssp;
u64 vmpl3_ssp;
u64 u_cet;
- u8 reserved_1[2];
+ u8 reserved_0xc8[2];
u8 vmpl;
u8 cpl;
- u8 reserved_2[4];
+ u8 reserved_0xcc[4];
u64 efer;
- u8 reserved_3[104];
+ u8 reserved_0xd8[104];
u64 xss;
u64 cr4;
u64 cr3;
@@ -371,7 +377,7 @@ struct sev_es_save_area {
u64 dr1_addr_mask;
u64 dr2_addr_mask;
u64 dr3_addr_mask;
- u8 reserved_4[24];
+ u8 reserved_0x1c0[24];
u64 rsp;
u64 s_cet;
u64 ssp;
@@ -386,21 +392,21 @@ struct sev_es_save_area {
u64 sysenter_esp;
u64 sysenter_eip;
u64 cr2;
- u8 reserved_5[32];
+ u8 reserved_0x248[32];
u64 g_pat;
u64 dbgctl;
u64 br_from;
u64 br_to;
u64 last_excp_from;
u64 last_excp_to;
- u8 reserved_7[80];
+ u8 reserved_0x298[80];
u32 pkru;
- u8 reserved_8[20];
- u64 reserved_9; /* rax already available at 0x01f8 */
+ u32 tsc_aux;
+ u8 reserved_0x2f0[24];
u64 rcx;
u64 rdx;
u64 rbx;
- u64 reserved_10; /* rsp already available at 0x01d8 */
+ u64 reserved_0x320; /* rsp already available at 0x01d8 */
u64 rbp;
u64 rsi;
u64 rdi;
@@ -412,7 +418,7 @@ struct sev_es_save_area {
u64 r13;
u64 r14;
u64 r15;
- u8 reserved_11[16];
+ u8 reserved_0x380[16];
u64 guest_exit_info_1;
u64 guest_exit_info_2;
u64 guest_exit_int_info;
@@ -425,7 +431,7 @@ struct sev_es_save_area {
u64 pcpu_id;
u64 event_inj;
u64 xcr0;
- u8 reserved_12[16];
+ u8 reserved_0x3f0[16];
/* Floating point area */
u64 x87_dp;
@@ -443,23 +449,23 @@ struct sev_es_save_area {
} __packed;
struct ghcb_save_area {
- u8 reserved_1[203];
+ u8 reserved_0x0[203];
u8 cpl;
- u8 reserved_2[116];
+ u8 reserved_0xcc[116];
u64 xss;
- u8 reserved_3[24];
+ u8 reserved_0x148[24];
u64 dr7;
- u8 reserved_4[16];
+ u8 reserved_0x168[16];
u64 rip;
- u8 reserved_5[88];
+ u8 reserved_0x180[88];
u64 rsp;
- u8 reserved_6[24];
+ u8 reserved_0x1e0[24];
u64 rax;
- u8 reserved_7[264];
+ u8 reserved_0x200[264];
u64 rcx;
u64 rdx;
u64 rbx;
- u8 reserved_8[8];
+ u8 reserved_0x320[8];
u64 rbp;
u64 rsi;
u64 rdi;
@@ -471,12 +477,12 @@ struct ghcb_save_area {
u64 r13;
u64 r14;
u64 r15;
- u8 reserved_9[16];
+ u8 reserved_0x380[16];
u64 sw_exit_code;
u64 sw_exit_info_1;
u64 sw_exit_info_2;
u64 sw_scratch;
- u8 reserved_10[56];
+ u8 reserved_0x3b0[56];
u64 xcr0;
u8 valid_bitmap[16];
u64 x87_state_gpa;
@@ -490,7 +496,7 @@ struct ghcb {
u8 shared_buffer[GHCB_SHARED_BUF_SIZE];
- u8 reserved_1[10];
+ u8 reserved_0xff0[10];
u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */
u32 ghcb_usage;
} __packed;
@@ -502,6 +508,9 @@ struct ghcb {
#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024
#define EXPECTED_GHCB_SIZE PAGE_SIZE
+#define BUILD_BUG_RESERVED_OFFSET(x, y) \
+ ASSERT_STRUCT_OFFSET(struct x, reserved ## _ ## y, y)
+
static inline void __unused_size_checks(void)
{
BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE);
@@ -509,6 +518,39 @@ static inline void __unused_size_checks(void)
BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE);
BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE);
+
+ /* Check offsets of reserved fields */
+
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248);
+ BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298);
+
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xd8);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380);
+ BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0);
+
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x0);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0xcc);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x148);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x168);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x180);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x1e0);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x200);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x320);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x380);
+ BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x3b0);
+
+ BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0);
}
struct vmcb {
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index 59358d1bf880..fd2669b1cb2d 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -6,7 +6,7 @@
#ifndef _ASM_X86_SYSCALL_WRAPPER_H
#define _ASM_X86_SYSCALL_WRAPPER_H
-struct pt_regs;
+#include <asm/ptrace.h>
extern long __x64_sys_ni_syscall(const struct pt_regs *regs);
extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bc614cfe21b..1cc756eafa44 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -254,24 +254,25 @@ extern void __put_user_nocheck_8(void);
#define __put_user_size(x, ptr, size, label) \
do { \
__typeof__(*(ptr)) __x = (x); /* eval x once */ \
- __chk_user_ptr(ptr); \
+ __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \
+ __chk_user_ptr(__ptr); \
switch (size) { \
case 1: \
- __put_user_goto(__x, ptr, "b", "iq", label); \
+ __put_user_goto(__x, __ptr, "b", "iq", label); \
break; \
case 2: \
- __put_user_goto(__x, ptr, "w", "ir", label); \
+ __put_user_goto(__x, __ptr, "w", "ir", label); \
break; \
case 4: \
- __put_user_goto(__x, ptr, "l", "ir", label); \
+ __put_user_goto(__x, __ptr, "l", "ir", label); \
break; \
case 8: \
- __put_user_goto_u64(__x, ptr, label); \
+ __put_user_goto_u64(__x, __ptr, label); \
break; \
default: \
__put_user_bad(); \
} \
- instrument_put_user(__x, ptr, size); \
+ instrument_put_user(__x, __ptr, size); \
} while (0)
#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 46de10a809ec..c6df6b16a088 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -214,6 +214,8 @@ struct kvm_msr_list {
struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_READ (1 << 0)
#define KVM_MSR_FILTER_WRITE (1 << 1)
+#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \
+ KVM_MSR_FILTER_WRITE)
__u32 flags;
__u32 nmsrs; /* number of msrs in bitmap */
__u32 base; /* MSR index the bitmap starts at */
@@ -222,8 +224,11 @@ struct kvm_msr_filter_range {
#define KVM_MSR_FILTER_MAX_RANGES 16
struct kvm_msr_filter {
+#ifndef __KERNEL__
#define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0)
+#endif
#define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0)
+#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY)
__u32 flags;
struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
};
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index cb50589a7102..437308004ef2 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -19,7 +19,6 @@
#include <asm/suspend.h>
#include <asm/tlbflush.h>
#include <asm/tdx.h>
-#include "../kvm/vmx/vmx.h"
#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -108,9 +107,4 @@ static void __used common(void)
OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
-
- if (IS_ENABLED(CONFIG_KVM_INTEL)) {
- BLANK();
- OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl);
- }
}
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index da7c361f47e0..3e3230cccaa7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -196,22 +196,15 @@ void __init check_bugs(void)
}
/*
- * NOTE: This function is *only* called for SVM. VMX spec_ctrl handling is
- * done in vmenter.S.
+ * NOTE: This function is *only* called for SVM, since Intel uses
+ * MSR_IA32_SPEC_CTRL for SSBD.
*/
void
-x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
+x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool setguest)
{
- u64 msrval, guestval = guest_spec_ctrl, hostval = spec_ctrl_current();
+ u64 guestval, hostval;
struct thread_info *ti = current_thread_info();
- if (static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) {
- if (hostval != guestval) {
- msrval = setguest ? guestval : hostval;
- wrmsrl(MSR_IA32_SPEC_CTRL, msrval);
- }
- }
-
/*
* If SSBD is not handled in MSR_SPEC_CTRL on AMD, update
* MSR_AMD64_L2_CFG or MSR_VIRT_SPEC_CTRL if supported.
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d4e48b4a438b..cf886f86038a 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -349,7 +349,7 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val)
static void kvm_guest_cpu_init(void)
{
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) {
- u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason));
+ u64 pa;
WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled));
diff --git a/arch/x86/kvm/.gitignore b/arch/x86/kvm/.gitignore
new file mode 100644
index 000000000000..615d6ff35c00
--- /dev/null
+++ b/arch/x86/kvm/.gitignore
@@ -0,0 +1,2 @@
+/kvm-asm-offsets.s
+/kvm-asm-offsets.h
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 67be7f217e37..fbeaa9ddef59 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -118,6 +118,17 @@ config KVM_AMD_SEV
Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
with Encrypted State (SEV-ES) on AMD processors.
+config KVM_SMM
+ bool "System Management Mode emulation"
+ default y
+ depends on KVM
+ help
+ Provides support for KVM to emulate System Management Mode (SMM)
+ in virtual machines. This can be used by the virtual machine
+ firmware to implement UEFI secure boot.
+
+ If unsure, say Y.
+
config KVM_XEN
bool "Support for Xen hypercall interface"
depends on KVM
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 30f244b64523..80e3fe184d17 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -20,12 +20,14 @@ endif
kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
kvm-$(CONFIG_KVM_XEN) += xen.o
+kvm-$(CONFIG_KVM_SMM) += smm.o
kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
- vmx/evmcs.o vmx/nested.o vmx/posted_intr.o
+ vmx/hyperv.o vmx/nested.o vmx/posted_intr.o
kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o
-kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o
+kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \
+ svm/sev.o svm/hyperv.o
ifdef CONFIG_HYPERV
kvm-amd-y += svm/svm_onhyperv.o
@@ -34,3 +36,15 @@ endif
obj-$(CONFIG_KVM) += kvm.o
obj-$(CONFIG_KVM_INTEL) += kvm-intel.o
obj-$(CONFIG_KVM_AMD) += kvm-amd.o
+
+AFLAGS_svm/vmenter.o := -iquote $(obj)
+$(obj)/svm/vmenter.o: $(obj)/kvm-asm-offsets.h
+
+AFLAGS_vmx/vmenter.o := -iquote $(obj)
+$(obj)/vmx/vmenter.o: $(obj)/kvm-asm-offsets.h
+
+$(obj)/kvm-asm-offsets.h: $(obj)/kvm-asm-offsets.s FORCE
+ $(call filechk,offsets,__KVM_ASM_OFFSETS_H__)
+
+targets += kvm-asm-offsets.s
+clean-files += kvm-asm-offsets.h
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 7065462378e2..723502181a3a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -62,10 +62,16 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
* This one is tied to SSB in the user API, and not
* visible in /proc/cpuinfo.
*/
-#define KVM_X86_FEATURE_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
+#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */
#define F feature_bit
-#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0)
+
+/* Scattered Flag - For features that are scattered by cpufeatures.h. */
+#define SF(name) \
+({ \
+ BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \
+ (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \
+})
/*
* Magic value used by KVM when querying userspace-provided CPUID entries and
@@ -543,9 +549,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf)
}
static __always_inline
-void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask)
+void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask)
{
- /* Use kvm_cpu_cap_mask for non-scattered leafs. */
+ /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */
BUILD_BUG_ON(leaf < NCAPINTS);
kvm_cpu_caps[leaf] = mask;
@@ -555,7 +561,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask)
static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask)
{
- /* Use kvm_cpu_cap_init_scattered for scattered leafs. */
+ /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */
BUILD_BUG_ON(leaf >= NCAPINTS);
kvm_cpu_caps[leaf] &= mask;
@@ -657,14 +663,19 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD);
kvm_cpu_cap_mask(CPUID_7_1_EAX,
- F(AVX_VNNI) | F(AVX512_BF16)
+ F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) |
+ F(AVX_IFMA)
+ );
+
+ kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX,
+ F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI)
);
kvm_cpu_cap_mask(CPUID_D_1_EAX,
F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd
);
- kvm_cpu_cap_init_scattered(CPUID_12_EAX,
+ kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX,
SF(SGX1) | SF(SGX2)
);
@@ -694,7 +705,7 @@ void kvm_set_cpu_caps(void)
F(CLZERO) | F(XSAVEERPTR) |
F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) |
- __feature_bit(KVM_X86_FEATURE_PSFD)
+ __feature_bit(KVM_X86_FEATURE_AMD_PSFD)
);
/*
@@ -913,9 +924,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
goto out;
cpuid_entry_override(entry, CPUID_7_1_EAX);
+ cpuid_entry_override(entry, CPUID_7_1_EDX);
entry->ebx = 0;
entry->ecx = 0;
- entry->edx = 0;
}
break;
case 0xa: { /* Architectural Performance Monitoring */
@@ -1133,11 +1144,13 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = max(entry->eax, 0x80000021);
break;
case 0x80000001:
+ entry->ebx &= ~GENMASK(27, 16);
cpuid_entry_override(entry, CPUID_8000_0001_EDX);
cpuid_entry_override(entry, CPUID_8000_0001_ECX);
break;
case 0x80000006:
- /* L2 cache and TLB: pass through host info. */
+ /* Drop reserved bits, pass host L2 cache and TLB info. */
+ entry->edx &= ~GENMASK(17, 16);
break;
case 0x80000007: /* Advanced power management */
/* invariant TSC is CPUID.80000007H:EDX[8] */
@@ -1167,6 +1180,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
g_phys_as = phys_as;
entry->eax = g_phys_as | (virt_as << 8);
+ entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8));
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
break;
@@ -1186,6 +1200,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->ecx = entry->edx = 0;
break;
case 0x8000001a:
+ entry->eax &= GENMASK(2, 0);
+ entry->ebx = entry->ecx = entry->edx = 0;
+ break;
case 0x8000001e:
break;
case 0x8000001F:
@@ -1193,7 +1210,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
} else {
cpuid_entry_override(entry, CPUID_8000_001F_EAX);
-
+ /* Clear NumVMPL since KVM does not support VMPL. */
+ entry->ebx &= ~GENMASK(31, 12);
/*
* Enumerate '0' for "PA bits reduction", the adjusted
* MAXPHYADDR is enumerated directly (see 0x80000008).
@@ -1331,7 +1349,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
if (sanity_check_entries(entries, cpuid->nent, type))
return -EINVAL;
- array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL);
+ array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL);
if (!array.entries)
return -ENOMEM;
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index cfed36aba2f7..c1390357126a 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -158,11 +158,16 @@ out:
static int kvm_mmu_rmaps_stat_open(struct inode *inode, struct file *file)
{
struct kvm *kvm = inode->i_private;
+ int r;
if (!kvm_get_kvm_safe(kvm))
return -ENOENT;
- return single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+ r = single_open(file, kvm_mmu_rmaps_stat_show, kvm);
+ if (r < 0)
+ kvm_put_kvm(kvm);
+
+ return r;
}
static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 3b27622d4642..5cc3efa0e21c 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -242,37 +242,6 @@ enum x86_transfer_type {
X86_TRANSFER_TASK_SWITCH,
};
-static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
- nr &= NR_EMULATOR_GPRS - 1;
-
- if (!(ctxt->regs_valid & (1 << nr))) {
- ctxt->regs_valid |= 1 << nr;
- ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
- }
- return ctxt->_regs[nr];
-}
-
-static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
- nr &= NR_EMULATOR_GPRS - 1;
-
- BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
- BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
-
- ctxt->regs_valid |= 1 << nr;
- ctxt->regs_dirty |= 1 << nr;
- return &ctxt->_regs[nr];
-}
-
-static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
-{
- reg_read(ctxt, nr);
- return reg_write(ctxt, nr);
-}
-
static void writeback_registers(struct x86_emulate_ctxt *ctxt)
{
unsigned long dirty = ctxt->regs_dirty;
@@ -791,8 +760,7 @@ static int linearize(struct x86_emulate_ctxt *ctxt,
ctxt->mode, linear);
}
-static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
- enum x86emul_mode mode)
+static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst)
{
ulong linear;
int rc;
@@ -802,41 +770,71 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
if (ctxt->op_bytes != sizeof(unsigned long))
addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
- rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+ rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear);
if (rc == X86EMUL_CONTINUE)
ctxt->_eip = addr.ea;
return rc;
}
+static inline int emulator_recalc_and_set_mode(struct x86_emulate_ctxt *ctxt)
+{
+ u64 efer;
+ struct desc_struct cs;
+ u16 selector;
+ u32 base3;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+
+ if (!(ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PE)) {
+ /* Real mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_REAL;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (ctxt->eflags & X86_EFLAGS_VM) {
+ /* Protected/VM86 mode. cpu must not have long mode active */
+ if (efer & EFER_LMA)
+ return X86EMUL_UNHANDLEABLE;
+ ctxt->mode = X86EMUL_MODE_VM86;
+ return X86EMUL_CONTINUE;
+ }
+
+ if (!ctxt->ops->get_segment(ctxt, &selector, &cs, &base3, VCPU_SREG_CS))
+ return X86EMUL_UNHANDLEABLE;
+
+ if (efer & EFER_LMA) {
+ if (cs.l) {
+ /* Proper long mode */
+ ctxt->mode = X86EMUL_MODE_PROT64;
+ } else if (cs.d) {
+ /* 32 bit compatibility mode*/
+ ctxt->mode = X86EMUL_MODE_PROT32;
+ } else {
+ ctxt->mode = X86EMUL_MODE_PROT16;
+ }
+ } else {
+ /* Legacy 32 bit / 16 bit mode */
+ ctxt->mode = cs.d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- return assign_eip(ctxt, dst, ctxt->mode);
+ return assign_eip(ctxt, dst);
}
-static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
- const struct desc_struct *cs_desc)
+static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst)
{
- enum x86emul_mode mode = ctxt->mode;
- int rc;
+ int rc = emulator_recalc_and_set_mode(ctxt);
-#ifdef CONFIG_X86_64
- if (ctxt->mode >= X86EMUL_MODE_PROT16) {
- if (cs_desc->l) {
- u64 efer = 0;
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
- ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
- if (efer & EFER_LMA)
- mode = X86EMUL_MODE_PROT64;
- } else
- mode = X86EMUL_MODE_PROT32; /* temporary value */
- }
-#endif
- if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
- mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
- rc = assign_eip(ctxt, dst, mode);
- if (rc == X86EMUL_CONTINUE)
- ctxt->mode = mode;
- return rc;
+ return assign_eip(ctxt, dst);
}
static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
@@ -2172,7 +2170,7 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2250,7 +2248,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, eip, &new_desc);
+ rc = assign_eip_far(ctxt, eip);
/* Error handling is not implemented. */
if (rc != X86EMUL_CONTINUE)
return X86EMUL_UNHANDLEABLE;
@@ -2309,335 +2307,15 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
return rc;
}
-static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
-{
-#ifdef CONFIG_X86_64
- return ctxt->ops->guest_has_long_mode(ctxt);
-#else
- return false;
-#endif
-}
-
-static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
-{
- desc->g = (flags >> 23) & 1;
- desc->d = (flags >> 22) & 1;
- desc->l = (flags >> 21) & 1;
- desc->avl = (flags >> 20) & 1;
- desc->p = (flags >> 15) & 1;
- desc->dpl = (flags >> 13) & 3;
- desc->s = (flags >> 12) & 1;
- desc->type = (flags >> 8) & 15;
-}
-
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
-{
- struct desc_struct desc;
- int offset;
- u16 selector;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
- return X86EMUL_CONTINUE;
-}
-
-#ifdef CONFIG_X86_64
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
- int n)
-{
- struct desc_struct desc;
- int offset;
- u16 selector;
- u32 base3;
-
- offset = 0x7e00 + n * 16;
-
- selector = GET_SMSTATE(u16, smstate, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
- base3 = GET_SMSTATE(u32, smstate, offset + 12);
-
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
- return X86EMUL_CONTINUE;
-}
-#endif
-
-static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
- u64 cr0, u64 cr3, u64 cr4)
-{
- int bad;
- u64 pcid;
-
- /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
- pcid = 0;
- if (cr4 & X86_CR4_PCIDE) {
- pcid = cr3 & 0xfff;
- cr3 &= ~0xfff;
- }
-
- bad = ctxt->ops->set_cr(ctxt, 3, cr3);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- /*
- * First enable PAE, long mode needs it before CR0.PG = 1 is set.
- * Then enable protected mode. However, PCID cannot be enabled
- * if EFER.LMA=0, so set it separately.
- */
- bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- bad = ctxt->ops->set_cr(ctxt, 0, cr0);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
-
- if (cr4 & X86_CR4_PCIDE) {
- bad = ctxt->ops->set_cr(ctxt, 4, cr4);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
- if (pcid) {
- bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid);
- if (bad)
- return X86EMUL_UNHANDLEABLE;
- }
-
- }
-
- return X86EMUL_CONTINUE;
-}
-
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
-{
- struct desc_struct desc;
- struct desc_ptr dt;
- u16 selector;
- u32 val, cr0, cr3, cr4;
- int i;
-
- cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
-
- for (i = 0; i < NR_EMULATOR_GPRS; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
-
- val = GET_SMSTATE(u32, smstate, 0x7fcc);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
- return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u32, smstate, 0x7fc8);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
- return X86EMUL_UNHANDLEABLE;
-
- selector = GET_SMSTATE(u32, smstate, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
-
- selector = GET_SMSTATE(u32, smstate, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
- ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
-
- dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
- ctxt->ops->set_gdt(ctxt, &dt);
-
- dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
- dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
- ctxt->ops->set_idt(ctxt, &dt);
-
- for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
-
- cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
-
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
-
- return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
-}
-
-#ifdef CONFIG_X86_64
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
-{
- struct desc_struct desc;
- struct desc_ptr dt;
- u64 val, cr0, cr3, cr4;
- u32 base3;
- u16 selector;
- int i, r;
-
- for (i = 0; i < NR_EMULATOR_GPRS; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
-
- ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
-
- val = GET_SMSTATE(u64, smstate, 0x7f68);
-
- if (ctxt->ops->set_dr(ctxt, 6, val))
- return X86EMUL_UNHANDLEABLE;
-
- val = GET_SMSTATE(u64, smstate, 0x7f60);
-
- if (ctxt->ops->set_dr(ctxt, 7, val))
- return X86EMUL_UNHANDLEABLE;
-
- cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
- cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
- cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
- val = GET_SMSTATE(u64, smstate, 0x7ed0);
-
- if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
- return X86EMUL_UNHANDLEABLE;
-
- selector = GET_SMSTATE(u32, smstate, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
- base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
-
- dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
- ctxt->ops->set_idt(ctxt, &dt);
-
- selector = GET_SMSTATE(u32, smstate, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
- base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
- ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
-
- dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
- dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
- ctxt->ops->set_gdt(ctxt, &dt);
-
- r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
- if (r != X86EMUL_CONTINUE)
- return r;
-
- for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smstate, i);
- if (r != X86EMUL_CONTINUE)
- return r;
- }
-
- return X86EMUL_CONTINUE;
-}
-#endif
-
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
- unsigned long cr0, cr4, efer;
- char buf[512];
- u64 smbase;
- int ret;
-
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
- smbase = ctxt->ops->get_smbase(ctxt);
-
- ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
- if (ret != X86EMUL_CONTINUE)
- return X86EMUL_UNHANDLEABLE;
-
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
-
- ctxt->ops->exiting_smm(ctxt);
-
- /*
- * Get back to real mode, to prepare a safe state in which to load
- * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
- * supports long mode.
- */
- if (emulator_has_longmode(ctxt)) {
- struct desc_struct cs_desc;
-
- /* Zero CR4.PCIDE before CR0.PG. */
- cr4 = ctxt->ops->get_cr(ctxt, 4);
- if (cr4 & X86_CR4_PCIDE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
-
- /* A 32-bit code segment is required to clear EFER.LMA. */
- memset(&cs_desc, 0, sizeof(cs_desc));
- cs_desc.type = 0xb;
- cs_desc.s = cs_desc.g = cs_desc.p = 1;
- ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS);
- }
-
- /* For the 64-bit case, this will clear EFER.LMA. */
- cr0 = ctxt->ops->get_cr(ctxt, 0);
- if (cr0 & X86_CR0_PE)
- ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
-
- if (emulator_has_longmode(ctxt)) {
- /* Clear CR4.PAE before clearing EFER.LME. */
- cr4 = ctxt->ops->get_cr(ctxt, 4);
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
- }
-
- /*
- * Give leave_smm() a chance to make ISA-specific changes to the vCPU
- * state (e.g. enter guest mode) before loading state from the SMM
- * state-save area.
- */
- if (ctxt->ops->leave_smm(ctxt, buf))
- goto emulate_shutdown;
-
-#ifdef CONFIG_X86_64
- if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, buf);
- else
-#endif
- ret = rsm_load_state_32(ctxt, buf);
-
- if (ret != X86EMUL_CONTINUE)
- goto emulate_shutdown;
-
- /*
- * Note, the ctxt->ops callbacks are responsible for handling side
- * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID
- * runtime updates, etc... If that changes, e.g. this flow is moved
- * out of the emulator to make it look more like enter_smm(), then
- * those side effects need to be explicitly handled for both success
- * and shutdown.
- */
- return X86EMUL_CONTINUE;
+ if (ctxt->ops->leave_smm(ctxt))
+ ctxt->ops->triple_fault(ctxt);
-emulate_shutdown:
- ctxt->ops->triple_fault(ctxt);
- return X86EMUL_CONTINUE;
+ return emulator_recalc_and_set_mode(ctxt);
}
static void
@@ -2876,6 +2554,7 @@ static int em_sysexit(struct x86_emulate_ctxt *ctxt)
ops->set_segment(ctxt, ss_sel, &ss, 0, VCPU_SREG_SS);
ctxt->_eip = rdx;
+ ctxt->mode = usermode;
*reg_write(ctxt, VCPU_REGS_RSP) = rcx;
return X86EMUL_CONTINUE;
@@ -3469,7 +3148,7 @@ static int em_call_far(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
+ rc = assign_eip_far(ctxt, ctxt->src.val);
if (rc != X86EMUL_CONTINUE)
goto fail;
@@ -3611,11 +3290,25 @@ static int em_movbe(struct x86_emulate_ctxt *ctxt)
static int em_cr_write(struct x86_emulate_ctxt *ctxt)
{
- if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val))
+ int cr_num = ctxt->modrm_reg;
+ int r;
+
+ if (ctxt->ops->set_cr(ctxt, cr_num, ctxt->src.val))
return emulate_gp(ctxt, 0);
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
+
+ if (cr_num == 0) {
+ /*
+ * CR0 write might have updated CR0.PE and/or CR0.PG
+ * which can affect the cpu's execution mode.
+ */
+ r = emulator_recalc_and_set_mode(ctxt);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+ }
+
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 0adf4a437e85..2c7f2a26421e 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -23,22 +23,25 @@
#include "ioapic.h"
#include "cpuid.h"
#include "hyperv.h"
+#include "mmu.h"
#include "xen.h"
#include <linux/cpu.h>
#include <linux/kvm_host.h>
#include <linux/highmem.h>
#include <linux/sched/cputime.h>
+#include <linux/spinlock.h>
#include <linux/eventfd.h>
#include <asm/apicdef.h>
+#include <asm/mshyperv.h>
#include <trace/events/kvm.h>
#include "trace.h"
#include "irq.h"
#include "fpu.h"
-#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64)
+#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK)
static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer,
bool vcpu_kick);
@@ -897,13 +900,15 @@ bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled);
-bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
- struct hv_vp_assist_page *assist_page)
+int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu)
{
- if (!kvm_hv_assist_page_enabled(vcpu))
- return false;
- return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
- assist_page, sizeof(*assist_page));
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (!hv_vcpu || !kvm_hv_assist_page_enabled(vcpu))
+ return -EFAULT;
+
+ return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data,
+ &hv_vcpu->vp_assist_page, sizeof(struct hv_vp_assist_page));
}
EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page);
@@ -954,6 +959,11 @@ int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu)
hv_vcpu->vp_index = vcpu->vcpu_idx;
+ for (i = 0; i < HV_NR_TLB_FLUSH_FIFOS; i++) {
+ INIT_KFIFO(hv_vcpu->tlb_flush_fifo[i].entries);
+ spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock);
+ }
+
return 0;
}
@@ -1736,6 +1746,28 @@ static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks,
}
}
+static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[])
+{
+ int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK;
+ unsigned long sbank;
+
+ if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask))
+ return false;
+
+ /*
+ * The index into the sparse bank is the number of preceding bits in
+ * the valid mask. Optimize for VMs with <64 vCPUs by skipping the
+ * fancy math if there can't possibly be preceding bits.
+ */
+ if (valid_bit_nr)
+ sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0));
+ else
+ sbank = 0;
+
+ return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK,
+ (unsigned long *)&sparse_banks[sbank]);
+}
+
struct kvm_hv_hcall {
u64 param;
u64 ingpa;
@@ -1749,57 +1781,173 @@ struct kvm_hv_hcall {
sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS];
};
-static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
- int consumed_xmm_halves,
- u64 *sparse_banks, gpa_t offset)
-{
- u16 var_cnt;
- int i;
-
- if (hc->var_cnt > 64)
- return -EINVAL;
- /* Ignore banks that cannot possibly contain a legal VP index. */
- var_cnt = min_t(u16, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS);
+static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc,
+ u16 orig_cnt, u16 cnt_cap, u64 *data,
+ int consumed_xmm_halves, gpa_t offset)
+{
+ /*
+ * Preserve the original count when ignoring entries via a "cap", KVM
+ * still needs to validate the guest input (though the non-XMM path
+ * punts on the checks).
+ */
+ u16 cnt = min(orig_cnt, cnt_cap);
+ int i, j;
if (hc->fast) {
/*
* Each XMM holds two sparse banks, but do not count halves that
* have already been consumed for hypercall parameters.
*/
- if (hc->var_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
+ if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves)
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- for (i = 0; i < var_cnt; i++) {
- int j = i + consumed_xmm_halves;
+
+ for (i = 0; i < cnt; i++) {
+ j = i + consumed_xmm_halves;
if (j % 2)
- sparse_banks[i] = sse128_hi(hc->xmm[j / 2]);
+ data[i] = sse128_hi(hc->xmm[j / 2]);
else
- sparse_banks[i] = sse128_lo(hc->xmm[j / 2]);
+ data[i] = sse128_lo(hc->xmm[j / 2]);
}
return 0;
}
- return kvm_read_guest(kvm, hc->ingpa + offset, sparse_banks,
- var_cnt * sizeof(*sparse_banks));
+ return kvm_read_guest(kvm, hc->ingpa + offset, data,
+ cnt * sizeof(*data));
+}
+
+static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc,
+ u64 *sparse_banks, int consumed_xmm_halves,
+ gpa_t offset)
+{
+ if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS)
+ return -EINVAL;
+
+ /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */
+ return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS,
+ sparse_banks, consumed_xmm_halves, offset);
+}
+
+static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[],
+ int consumed_xmm_halves, gpa_t offset)
+{
+ return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt,
+ entries, consumed_xmm_halves, offset);
+}
+
+static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu,
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo,
+ u64 *entries, int count)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 flush_all_entry = KVM_HV_TLB_FLUSHALL_ENTRY;
+
+ if (!hv_vcpu)
+ return;
+
+ spin_lock(&tlb_flush_fifo->write_lock);
+
+ /*
+ * All entries should fit on the fifo leaving one free for 'flush all'
+ * entry in case another request comes in. In case there's not enough
+ * space, just put 'flush all' entry there.
+ */
+ if (count && entries && count < kfifo_avail(&tlb_flush_fifo->entries)) {
+ WARN_ON(kfifo_in(&tlb_flush_fifo->entries, entries, count) != count);
+ goto out_unlock;
+ }
+
+ /*
+ * Note: full fifo always contains 'flush all' entry, no need to check the
+ * return value.
+ */
+ kfifo_in(&tlb_flush_fifo->entries, &flush_all_entry, 1);
+
+out_unlock:
+ spin_unlock(&tlb_flush_fifo->write_lock);
+}
+
+int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE];
+ int i, j, count;
+ gva_t gva;
+
+ if (!tdp_enabled || !hv_vcpu)
+ return -EINVAL;
+
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu));
+
+ count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE);
+
+ for (i = 0; i < count; i++) {
+ if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
+ goto out_flush_all;
+
+ /*
+ * Lower 12 bits of 'address' encode the number of additional
+ * pages to flush.
+ */
+ gva = entries[i] & PAGE_MASK;
+ for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++)
+ static_call(kvm_x86_flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE);
+
+ ++vcpu->stat.tlb_flush;
+ }
+ return 0;
+
+out_flush_all:
+ kfifo_reset_out(&tlb_flush_fifo->entries);
+
+ /* Fall back to full flush. */
+ return -ENOSPC;
}
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
+ /*
+ * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
+ * entries on the TLB flush fifo. The last entry, however, needs to be
+ * always left free for 'flush all' entry which gets placed when
+ * there is not enough space to put all the requested entries.
+ */
+ u64 __tlb_flush_entries[KVM_HV_TLB_FLUSH_FIFO_SIZE - 1];
+ u64 *tlb_flush_entries;
u64 valid_bank_mask;
- u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
+ struct kvm_vcpu *v;
+ unsigned long i;
bool all_cpus;
+ int consumed_xmm_halves = 0;
+ gpa_t data_offset;
/*
- * The Hyper-V TLFS doesn't allow more than 64 sparse banks, e.g. the
- * valid mask is a u64. Fail the build if KVM's max allowed number of
- * vCPUs (>4096) would exceed this limit, KVM will additional changes
- * for Hyper-V support to avoid setting the guest up to fail.
+ * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS
+ * sparse banks. Fail the build if KVM's max allowed number of
+ * vCPUs (>4096) exceeds this limit.
*/
- BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > 64);
+ BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > HV_MAX_SPARSE_VCPU_BANKS);
+
+ /*
+ * 'Slow' hypercall's first parameter is the address in guest's memory
+ * where hypercall parameters are placed. This is either a GPA or a
+ * nested GPA when KVM is handling the call from L2 ('direct' TLB
+ * flush). Translate the address here so the memory can be uniformly
+ * read with kvm_read_guest().
+ */
+ if (!hc->fast && is_guest_mode(vcpu)) {
+ hc->ingpa = translate_nested_gpa(vcpu, hc->ingpa, 0, NULL);
+ if (unlikely(hc->ingpa == INVALID_GPA))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST ||
hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) {
@@ -1807,14 +1955,17 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
flush.address_space = hc->ingpa;
flush.flags = hc->outgpa;
flush.processor_mask = sse128_lo(hc->xmm[0]);
+ consumed_xmm_halves = 1;
} else {
if (unlikely(kvm_read_guest(kvm, hc->ingpa,
&flush, sizeof(flush))))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ data_offset = sizeof(flush);
}
trace_kvm_hv_flush_tlb(flush.processor_mask,
- flush.address_space, flush.flags);
+ flush.address_space, flush.flags,
+ is_guest_mode(vcpu));
valid_bank_mask = BIT_ULL(0);
sparse_banks[0] = flush.processor_mask;
@@ -1834,16 +1985,18 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
flush_ex.flags = hc->outgpa;
memcpy(&flush_ex.hv_vp_set,
&hc->xmm[0], sizeof(hc->xmm[0]));
+ consumed_xmm_halves = 2;
} else {
if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex,
sizeof(flush_ex))))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ data_offset = sizeof(flush_ex);
}
trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask,
flush_ex.hv_vp_set.format,
flush_ex.address_space,
- flush_ex.flags);
+ flush_ex.flags, is_guest_mode(vcpu));
valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask;
all_cpus = flush_ex.hv_vp_set.format !=
@@ -1852,29 +2005,95 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
if (hc->var_cnt != hweight64(valid_bank_mask))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- if (all_cpus)
- goto do_flush;
+ if (!all_cpus) {
+ if (!hc->var_cnt)
+ goto ret_success;
- if (!hc->var_cnt)
- goto ret_success;
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks,
+ consumed_xmm_halves, data_offset))
+ return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ }
- if (kvm_get_sparse_vp_set(kvm, hc, 2, sparse_banks,
- offsetof(struct hv_tlb_flush_ex,
- hv_vp_set.bank_contents)))
+ /*
+ * Hyper-V TLFS doesn't explicitly forbid non-empty sparse vCPU
+ * banks (and, thus, non-zero 'var_cnt') for the 'all vCPUs'
+ * case (HV_GENERIC_SET_ALL). Always adjust data_offset and
+ * consumed_xmm_halves to make sure TLB flush entries are read
+ * from the correct offset.
+ */
+ data_offset += hc->var_cnt * sizeof(sparse_banks[0]);
+ consumed_xmm_halves += hc->var_cnt;
+ }
+
+ if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
+ hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX ||
+ hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) {
+ tlb_flush_entries = NULL;
+ } else {
+ if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries,
+ consumed_xmm_halves, data_offset))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
+ tlb_flush_entries = __tlb_flush_entries;
}
-do_flush:
/*
* vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
* analyze it here, flush TLB regardless of the specified address space.
*/
- if (all_cpus) {
- kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST);
- } else {
+ if (all_cpus && !is_guest_mode(vcpu)) {
+ kvm_for_each_vcpu(i, v, kvm) {
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH);
+ } else if (!is_guest_mode(vcpu)) {
sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
- kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, vcpu_mask);
+ for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) {
+ v = kvm_get_vcpu(kvm, i);
+ if (!v)
+ continue;
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
+ } else {
+ struct kvm_vcpu_hv *hv_v;
+
+ bitmap_zero(vcpu_mask, KVM_MAX_VCPUS);
+
+ kvm_for_each_vcpu(i, v, kvm) {
+ hv_v = to_hv_vcpu(v);
+
+ /*
+ * The following check races with nested vCPUs entering/exiting
+ * and/or migrating between L1's vCPUs, however the only case when
+ * KVM *must* flush the TLB is when the target L2 vCPU keeps
+ * running on the same L1 vCPU from the moment of the request until
+ * kvm_hv_flush_tlb() returns. TLB is fully flushed in all other
+ * cases, e.g. when the target L2 vCPU migrates to a different L1
+ * vCPU or when the corresponding L1 vCPU temporary switches to a
+ * different L2 vCPU while the request is being processed.
+ */
+ if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id)
+ continue;
+
+ if (!all_cpus &&
+ !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask,
+ sparse_banks))
+ continue;
+
+ __set_bit(i, vcpu_mask);
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, true);
+ hv_tlb_flush_enqueue(v, tlb_flush_fifo,
+ tlb_flush_entries, hc->rep_cnt);
+ }
+
+ kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask);
}
ret_success:
@@ -1883,8 +2102,8 @@ ret_success:
((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET);
}
-static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
- unsigned long *vcpu_bitmap)
+static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector,
+ u64 *sparse_banks, u64 valid_bank_mask)
{
struct kvm_lapic_irq irq = {
.delivery_mode = APIC_DM_FIXED,
@@ -1894,7 +2113,9 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
unsigned long i;
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
+ if (sparse_banks &&
+ !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu),
+ valid_bank_mask, sparse_banks))
continue;
/* We fail only when APIC is disabled */
@@ -1904,12 +2125,12 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector,
static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_send_ipi_ex send_ipi_ex;
struct hv_send_ipi send_ipi;
- DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
u64 valid_bank_mask;
- u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS];
u32 vector;
bool all_cpus;
@@ -1959,7 +2180,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
if (!hc->var_cnt)
goto ret_success;
- if (kvm_get_sparse_vp_set(kvm, hc, 1, sparse_banks,
+ if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1,
offsetof(struct hv_send_ipi_ex,
vp_set.bank_contents)))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
@@ -1969,13 +2190,10 @@ check_and_send_ipi:
if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
return HV_STATUS_INVALID_HYPERCALL_INPUT;
- if (all_cpus) {
- kvm_send_ipi_to_many(kvm, vector, NULL);
- } else {
- sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask);
-
- kvm_send_ipi_to_many(kvm, vector, vcpu_mask);
- }
+ if (all_cpus)
+ kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0);
+ else
+ kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask);
ret_success:
return HV_STATUS_SUCCESS;
@@ -2062,10 +2280,25 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result)
{
+ u32 tlb_lock_count = 0;
+ int ret;
+
+ if (hv_result_success(result) && is_guest_mode(vcpu) &&
+ kvm_hv_is_tlb_flush_hcall(vcpu) &&
+ kvm_read_guest(vcpu->kvm, to_hv_vcpu(vcpu)->nested.pa_page_gpa,
+ &tlb_lock_count, sizeof(tlb_lock_count)))
+ result = HV_STATUS_INVALID_HYPERCALL_INPUT;
+
trace_kvm_hv_hypercall_done(result);
kvm_hv_hypercall_set_result(vcpu, result);
++vcpu->stat.hypercalls;
- return kvm_skip_emulated_instruction(vcpu);
+
+ ret = kvm_skip_emulated_instruction(vcpu);
+
+ if (tlb_lock_count)
+ kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu);
+
+ return ret;
}
static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
@@ -2502,6 +2735,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
ent->ebx |= HV_DEBUGGING;
ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE;
ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE;
+ ent->edx |= HV_FEATURE_EXT_GVA_RANGES_FLUSH;
/*
* Direct Synthetic timers only make sense with in-kernel
@@ -2545,6 +2779,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_NESTED_FEATURES:
ent->eax = evmcs_ver;
+ ent->eax |= HV_X64_NESTED_DIRECT_FLUSH;
ent->eax |= HV_X64_NESTED_MSR_BITMAP;
ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL;
break;
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 1030b1b50552..9f96414a31c5 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -22,6 +22,7 @@
#define __ARCH_X86_KVM_HYPERV_H__
#include <linux/kvm_host.h>
+#include "x86.h"
/* "Hv#1" signature */
#define HYPERV_CPUID_SIGNATURE_EAX 0x31237648
@@ -107,8 +108,7 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu);
bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu);
-bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu,
- struct hv_vp_assist_page *assist_page);
+int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu);
static inline struct kvm_vcpu_hv_stimer *to_hv_stimer(struct kvm_vcpu *vcpu,
int timer_index)
@@ -151,4 +151,64 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries);
+static inline struct kvm_vcpu_hv_tlb_flush_fifo *kvm_hv_get_tlb_flush_fifo(struct kvm_vcpu *vcpu,
+ bool is_guest_mode)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ int i = is_guest_mode ? HV_L2_TLB_FLUSH_FIFO :
+ HV_L1_TLB_FLUSH_FIFO;
+
+ return &hv_vcpu->tlb_flush_fifo[i];
+}
+
+static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
+
+ if (!to_hv_vcpu(vcpu) || !kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu))
+ return;
+
+ tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu));
+
+ kfifo_reset_out(&tlb_flush_fifo->entries);
+}
+
+static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ return hv_vcpu &&
+ (hv_vcpu->cpuid_cache.nested_eax & HV_X64_NESTED_DIRECT_FLUSH);
+}
+
+static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ u16 code;
+
+ if (!hv_vcpu)
+ return false;
+
+ code = is_64_bit_hypercall(vcpu) ? kvm_rcx_read(vcpu) :
+ kvm_rax_read(vcpu);
+
+ return (code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE ||
+ code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST ||
+ code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX ||
+ code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX);
+}
+
+static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu)
+{
+ if (!to_hv_vcpu(vcpu))
+ return 0;
+
+ if (!kvm_hv_assist_page_enabled(vcpu))
+ return 0;
+
+ return kvm_hv_get_assist_page(vcpu);
+}
+
+int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu);
+
#endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index f371f1292ca3..d8d50558f165 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -165,3 +165,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
}
+
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return irqchip_in_kernel(kvm);
+}
diff --git a/arch/x86/kvm/kvm-asm-offsets.c b/arch/x86/kvm/kvm-asm-offsets.c
new file mode 100644
index 000000000000..24a710d37323
--- /dev/null
+++ b/arch/x86/kvm/kvm-asm-offsets.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generate definitions needed by assembly language modules.
+ * This code generates raw asm output which is post-processed to extract
+ * and format the required data.
+ */
+#define COMPILE_OFFSETS
+
+#include <linux/kbuild.h>
+#include "vmx/vmx.h"
+#include "svm/svm.h"
+
+static void __used common(void)
+{
+ if (IS_ENABLED(CONFIG_KVM_AMD)) {
+ BLANK();
+ OFFSET(SVM_vcpu_arch_regs, vcpu_svm, vcpu.arch.regs);
+ OFFSET(SVM_current_vmcb, vcpu_svm, current_vmcb);
+ OFFSET(SVM_spec_ctrl, vcpu_svm, spec_ctrl);
+ OFFSET(SVM_vmcb01, vcpu_svm, vmcb01);
+ OFFSET(KVM_VMCB_pa, kvm_vmcb_info, pa);
+ OFFSET(SD_save_area_pa, svm_cpu_data, save_area_pa);
+ }
+
+ if (IS_ENABLED(CONFIG_KVM_INTEL)) {
+ BLANK();
+ OFFSET(VMX_spec_ctrl, vcpu_vmx, spec_ctrl);
+ }
+}
diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h
index 3febc342360c..c09174f73a34 100644
--- a/arch/x86/kvm/kvm_cache_regs.h
+++ b/arch/x86/kvm/kvm_cache_regs.h
@@ -200,9 +200,4 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu)
return vcpu->arch.hflags & HF_GUEST_MASK;
}
-static inline bool is_smm(struct kvm_vcpu *vcpu)
-{
- return vcpu->arch.hflags & HF_SMM_MASK;
-}
-
#endif
diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
index 89246446d6aa..2d9662be8333 100644
--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
@@ -117,16 +117,6 @@ struct x86_emulate_ops {
struct x86_exception *fault, bool system);
/*
- * read_phys: Read bytes of standard (non-emulated/special) memory.
- * Used for descriptor reading.
- * @addr: [IN ] Physical address from which to read.
- * @val: [OUT] Value read from memory.
- * @bytes: [IN ] Number of bytes to read from memory.
- */
- int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr,
- void *val, unsigned int bytes);
-
- /*
* write_std: Write bytes of standard (non-emulated/special) memory.
* Used for descriptor writing.
* @addr: [IN ] Linear address to which to write.
@@ -209,11 +199,8 @@ struct x86_emulate_ops {
int (*cpl)(struct x86_emulate_ctxt *ctxt);
void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
- u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt);
- void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase);
int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
- int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc);
int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata);
@@ -234,8 +221,7 @@ struct x86_emulate_ops {
void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
- void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
- int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate);
+ int (*leave_smm)(struct x86_emulate_ctxt *ctxt);
void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
};
@@ -292,7 +278,6 @@ enum x86emul_mode {
/* These match some of the HF_* flags defined in kvm_host.h */
#define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */
#define X86EMUL_SMM_MASK (1 << 6)
-#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7)
/*
* fastop functions are declared as taking a never-defined fastop parameter,
@@ -526,4 +511,35 @@ void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt);
+static inline ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+ nr &= NR_EMULATOR_GPRS - 1;
+
+ if (!(ctxt->regs_valid & (1 << nr))) {
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr);
+ }
+ return ctxt->_regs[nr];
+}
+
+static inline ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt))
+ nr &= NR_EMULATOR_GPRS - 1;
+
+ BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+ BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS);
+
+ ctxt->regs_valid |= 1 << nr;
+ ctxt->regs_dirty |= 1 << nr;
+ return &ctxt->_regs[nr];
+}
+
+static inline ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr)
+{
+ reg_read(ctxt, nr);
+ return reg_write(ctxt, nr);
+}
+
#endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index d7639d126e6c..1bb63746e991 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -42,6 +42,7 @@
#include "x86.h"
#include "cpuid.h"
#include "hyperv.h"
+#include "smm.h"
#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
@@ -1170,9 +1171,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
break;
case APIC_DM_SMI:
- result = 1;
- kvm_make_request(KVM_REQ_SMI, vcpu);
- kvm_vcpu_kick(vcpu);
+ if (!kvm_inject_smi(vcpu)) {
+ kvm_vcpu_kick(vcpu);
+ result = 1;
+ }
break;
case APIC_DM_NMI:
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index a5ac4a5a5179..28e3769066e2 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -7,7 +7,7 @@
#include <linux/kvm_host.h>
#include "hyperv.h"
-#include "kvm_cache_regs.h"
+#include "smm.h"
#define KVM_APIC_INIT 0
#define KVM_APIC_SIPI 1
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 6f81539061d6..4736d7849c60 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -22,6 +22,7 @@
#include "tdp_mmu.h"
#include "x86.h"
#include "kvm_cache_regs.h"
+#include "smm.h"
#include "kvm_emulate.h"
#include "cpuid.h"
#include "spte.h"
@@ -802,15 +803,31 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_flush_remote_tlbs_with_address(kvm, gfn, 1);
}
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
- if (sp->lpage_disallowed)
+ /*
+ * If it's possible to replace the shadow page with an NX huge page,
+ * i.e. if the shadow page is the only thing currently preventing KVM
+ * from using a huge page, add the shadow page to the list of "to be
+ * zapped for NX recovery" pages. Note, the shadow page can already be
+ * on the list if KVM is reusing an existing shadow page, i.e. if KVM
+ * links a shadow page at multiple points.
+ */
+ if (!list_empty(&sp->possible_nx_huge_page_link))
return;
++kvm->stat.nx_lpage_splits;
- list_add_tail(&sp->lpage_disallowed_link,
- &kvm->arch.lpage_disallowed_mmu_pages);
- sp->lpage_disallowed = true;
+ list_add_tail(&sp->possible_nx_huge_page_link,
+ &kvm->arch.possible_nx_huge_pages);
+}
+
+static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp,
+ bool nx_huge_page_possible)
+{
+ sp->nx_huge_page_disallowed = true;
+
+ if (nx_huge_page_possible)
+ track_possible_nx_huge_page(kvm, sp);
}
static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
@@ -830,11 +847,20 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
kvm_mmu_gfn_allow_lpage(slot, gfn);
}
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
+ if (list_empty(&sp->possible_nx_huge_page_link))
+ return;
+
--kvm->stat.nx_lpage_splits;
- sp->lpage_disallowed = false;
- list_del(&sp->lpage_disallowed_link);
+ list_del_init(&sp->possible_nx_huge_page_link);
+}
+
+static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+ sp->nx_huge_page_disallowed = false;
+
+ untrack_possible_nx_huge_page(kvm, sp);
}
static struct kvm_memory_slot *
@@ -1645,7 +1671,7 @@ static int is_empty_shadow_page(u64 *spt)
u64 *pos;
u64 *end;
- for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++)
+ for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++)
if (is_shadow_present_pte(*pos)) {
printk(KERN_ERR "%s: %p %llx\n", __func__,
pos, *pos);
@@ -1793,7 +1819,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp,
continue;
}
- child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(ent);
if (child->unsync_children) {
if (mmu_pages_add(pvec, child, i))
@@ -1894,7 +1920,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
if (sp->role.invalid)
return true;
- /* TDP MMU pages due not use the MMU generation. */
+ /* TDP MMU pages do not use the MMU generation. */
return !sp->tdp_mmu_page &&
unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
}
@@ -2129,6 +2155,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm,
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+ INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
/*
* active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages()
* depends on valid pages being added to the head of the list. See
@@ -2350,7 +2378,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep,
* so we should update the spte at this point to get
* a new sp with the correct access.
*/
- child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(*sptep);
if (child->role.access == direct_access)
return;
@@ -2371,7 +2399,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
if (is_last_spte(pte, sp->role.level)) {
drop_spte(kvm, spte);
} else {
- child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(pte);
drop_parent_pte(child, spte);
/*
@@ -2486,8 +2514,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
zapped_root = !is_obsolete_sp(kvm, sp);
}
- if (sp->lpage_disallowed)
- unaccount_huge_nx_page(kvm, sp);
+ if (sp->nx_huge_page_disallowed)
+ unaccount_nx_huge_page(kvm, sp);
sp->role.invalid = 1;
@@ -2810,7 +2838,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
struct kvm_mmu_page *child;
u64 pte = *sptep;
- child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK);
+ child = spte_to_child_sp(pte);
drop_parent_pte(child, sptep);
flush = true;
} else if (pfn != spte_to_pfn(*sptep)) {
@@ -3084,7 +3112,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
if (cur_level > PG_LEVEL_4K &&
cur_level == fault->goal_level &&
is_shadow_present_pte(spte) &&
- !is_large_pte(spte)) {
+ !is_large_pte(spte) &&
+ spte_to_child_sp(spte)->nx_huge_page_disallowed) {
/*
* A small SPTE exists for this pfn, but FNAME(fetch)
* and __direct_map would like to create a large PTE
@@ -3126,9 +3155,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
continue;
link_shadow_page(vcpu, it.sptep, sp);
- if (fault->is_tdp && fault->huge_page_disallowed &&
- fault->req_level >= it.level)
- account_huge_nx_page(vcpu->kvm, sp);
+ if (fault->huge_page_disallowed)
+ account_nx_huge_page(vcpu->kvm, sp,
+ fault->req_level >= it.level);
}
if (WARN_ON_ONCE(it.level != fault->goal_level))
@@ -3148,8 +3177,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk);
}
-static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
+static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
{
+ if (is_sigpending_pfn(pfn)) {
+ kvm_handle_signal_exit(vcpu);
+ return -EINTR;
+ }
+
/*
* Do not cache the mmio info caused by writing the readonly gfn
* into the spte otherwise read access on readonly gfn also can
@@ -3171,7 +3205,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau
{
/* The pfn is invalid, report the error! */
if (unlikely(is_error_pfn(fault->pfn)))
- return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
+ return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn);
if (unlikely(!fault->slot)) {
gva_t gva = fault->is_tdp ? 0 : fault->addr;
@@ -3422,7 +3456,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa,
if (!VALID_PAGE(*root_hpa))
return;
- sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK);
+ /*
+ * The "root" may be a special root, e.g. a PAE entry, treat it as a
+ * SPTE to ensure any non-PA bits are dropped.
+ */
+ sp = spte_to_child_sp(*root_hpa);
if (WARN_ON(!sp))
return;
@@ -3907,8 +3945,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu)
hpa_t root = vcpu->arch.mmu->pae_root[i];
if (IS_VALID_PAE_ROOT(root)) {
- root &= SPTE_BASE_ADDR_MASK;
- sp = to_shadow_page(root);
+ sp = spte_to_child_sp(root);
mmu_sync_children(vcpu, sp, true);
}
}
@@ -4169,7 +4206,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
async = false;
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async,
fault->write, &fault->map_writable,
&fault->hva);
if (!async)
@@ -4186,7 +4223,12 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
}
}
- fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL,
+ /*
+ * Allow gup to bail on pending non-fatal signals when it's also allowed
+ * to wait for IO. Note, gup always bails if it is unable to quickly
+ * get a page and a fatal signal, i.e. SIGKILL, is pending.
+ */
+ fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL,
fault->write, &fault->map_writable,
&fault->hva);
return RET_PF_CONTINUE;
@@ -5971,7 +6013,7 @@ int kvm_mmu_init_vm(struct kvm *kvm)
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
- INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
+ INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
r = kvm_mmu_init_tdp_mmu(kvm);
@@ -6656,7 +6698,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
kvm_mmu_zap_all_fast(kvm);
mutex_unlock(&kvm->slots_lock);
- wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
}
mutex_unlock(&kvm_lock);
}
@@ -6788,7 +6830,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
mutex_lock(&kvm_lock);
list_for_each_entry(kvm, &vm_list, vm_list)
- wake_up_process(kvm->arch.nx_lpage_recovery_thread);
+ wake_up_process(kvm->arch.nx_huge_page_recovery_thread);
mutex_unlock(&kvm_lock);
}
@@ -6796,9 +6838,10 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel
return err;
}
-static void kvm_recover_nx_lpages(struct kvm *kvm)
+static void kvm_recover_nx_huge_pages(struct kvm *kvm)
{
unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits;
+ struct kvm_memory_slot *slot;
int rcu_idx;
struct kvm_mmu_page *sp;
unsigned int ratio;
@@ -6819,24 +6862,55 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
ratio = READ_ONCE(nx_huge_pages_recovery_ratio);
to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0;
for ( ; to_zap; --to_zap) {
- if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages))
+ if (list_empty(&kvm->arch.possible_nx_huge_pages))
break;
/*
* We use a separate list instead of just using active_mmu_pages
- * because the number of lpage_disallowed pages is expected to
- * be relatively small compared to the total.
+ * because the number of shadow pages that be replaced with an
+ * NX huge page is expected to be relatively small compared to
+ * the total number of shadow pages. And because the TDP MMU
+ * doesn't use active_mmu_pages.
*/
- sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages,
+ sp = list_first_entry(&kvm->arch.possible_nx_huge_pages,
struct kvm_mmu_page,
- lpage_disallowed_link);
- WARN_ON_ONCE(!sp->lpage_disallowed);
- if (is_tdp_mmu_page(sp)) {
+ possible_nx_huge_page_link);
+ WARN_ON_ONCE(!sp->nx_huge_page_disallowed);
+ WARN_ON_ONCE(!sp->role.direct);
+
+ /*
+ * Unaccount and do not attempt to recover any NX Huge Pages
+ * that are being dirty tracked, as they would just be faulted
+ * back in as 4KiB pages. The NX Huge Pages in this slot will be
+ * recovered, along with all the other huge pages in the slot,
+ * when dirty logging is disabled.
+ *
+ * Since gfn_to_memslot() is relatively expensive, it helps to
+ * skip it if it the test cannot possibly return true. On the
+ * other hand, if any memslot has logging enabled, chances are
+ * good that all of them do, in which case unaccount_nx_huge_page()
+ * is much cheaper than zapping the page.
+ *
+ * If a memslot update is in progress, reading an incorrect value
+ * of kvm->nr_memslots_dirty_logging is not a problem: if it is
+ * becoming zero, gfn_to_memslot() will be done unnecessarily; if
+ * it is becoming nonzero, the page will be zapped unnecessarily.
+ * Either way, this only affects efficiency in racy situations,
+ * and not correctness.
+ */
+ slot = NULL;
+ if (atomic_read(&kvm->nr_memslots_dirty_logging)) {
+ slot = gfn_to_memslot(kvm, sp->gfn);
+ WARN_ON_ONCE(!slot);
+ }
+
+ if (slot && kvm_slot_dirty_track_enabled(slot))
+ unaccount_nx_huge_page(kvm, sp);
+ else if (is_tdp_mmu_page(sp))
flush |= kvm_tdp_mmu_zap_sp(kvm, sp);
- } else {
+ else
kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
- WARN_ON_ONCE(sp->lpage_disallowed);
- }
+ WARN_ON_ONCE(sp->nx_huge_page_disallowed);
if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) {
kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
@@ -6856,7 +6930,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
srcu_read_unlock(&kvm->srcu, rcu_idx);
}
-static long get_nx_lpage_recovery_timeout(u64 start_time)
+static long get_nx_huge_page_recovery_timeout(u64 start_time)
{
bool enabled;
uint period;
@@ -6867,19 +6941,19 @@ static long get_nx_lpage_recovery_timeout(u64 start_time)
: MAX_SCHEDULE_TIMEOUT;
}
-static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
+static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data)
{
u64 start_time;
long remaining_time;
while (true) {
start_time = get_jiffies_64();
- remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ remaining_time = get_nx_huge_page_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
while (!kthread_should_stop() && remaining_time > 0) {
schedule_timeout(remaining_time);
- remaining_time = get_nx_lpage_recovery_timeout(start_time);
+ remaining_time = get_nx_huge_page_recovery_timeout(start_time);
set_current_state(TASK_INTERRUPTIBLE);
}
@@ -6888,7 +6962,7 @@ static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data)
if (kthread_should_stop())
return 0;
- kvm_recover_nx_lpages(kvm);
+ kvm_recover_nx_huge_pages(kvm);
}
}
@@ -6896,17 +6970,17 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
{
int err;
- err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0,
+ err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0,
"kvm-nx-lpage-recovery",
- &kvm->arch.nx_lpage_recovery_thread);
+ &kvm->arch.nx_huge_page_recovery_thread);
if (!err)
- kthread_unpark(kvm->arch.nx_lpage_recovery_thread);
+ kthread_unpark(kvm->arch.nx_huge_page_recovery_thread);
return err;
}
void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
{
- if (kvm->arch.nx_lpage_recovery_thread)
- kthread_stop(kvm->arch.nx_lpage_recovery_thread);
+ if (kvm->arch.nx_huge_page_recovery_thread)
+ kthread_stop(kvm->arch.nx_huge_page_recovery_thread);
}
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 582def531d4d..dbaf6755c5a7 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -57,7 +57,13 @@ struct kvm_mmu_page {
bool tdp_mmu_page;
bool unsync;
u8 mmu_valid_gen;
- bool lpage_disallowed; /* Can't be replaced by an equiv large page */
+
+ /*
+ * The shadow page can't be replaced by an equivalent huge page
+ * because it is being used to map an executable page in the guest
+ * and the NX huge page mitigation is enabled.
+ */
+ bool nx_huge_page_disallowed;
/*
* The following two entries are used to key the shadow page in the
@@ -100,7 +106,14 @@ struct kvm_mmu_page {
};
};
- struct list_head lpage_disallowed_link;
+ /*
+ * Tracks shadow pages that, if zapped, would allow KVM to create an NX
+ * huge page. A shadow page will have nx_huge_page_disallowed set but
+ * not be on the list if a huge page is disallowed for other reasons,
+ * e.g. because KVM is shadowing a PTE at the same gfn, the memslot
+ * isn't properly aligned, etc...
+ */
+ struct list_head possible_nx_huge_page_link;
#ifdef CONFIG_X86_32
/*
* Used out of the mmu-lock to avoid reading spte values while an
@@ -120,18 +133,6 @@ struct kvm_mmu_page {
extern struct kmem_cache *mmu_page_header_cache;
-static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
-{
- struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
-
- return (struct kvm_mmu_page *)page_private(page);
-}
-
-static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
-{
- return to_shadow_page(__pa(sptep));
-}
-
static inline int kvm_mmu_role_as_id(union kvm_mmu_page_role role)
{
return role.smm ? 1 : 0;
@@ -315,7 +316,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_
void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
-void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
-void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
+void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp);
#endif /* __KVM_X86_MMU_INTERNAL_H */
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5ab5f94dcb6f..0f6455072055 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -713,9 +713,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
continue;
link_shadow_page(vcpu, it.sptep, sp);
- if (fault->huge_page_disallowed &&
- fault->req_level >= it.level)
- account_huge_nx_page(vcpu->kvm, sp);
+ if (fault->huge_page_disallowed)
+ account_nx_huge_page(vcpu->kvm, sp,
+ fault->req_level >= it.level);
}
if (WARN_ON_ONCE(it.level != fault->goal_level))
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 2e08b2a45361..c0fd7e049b4e 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -161,6 +161,18 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (!prefetch)
spte |= spte_shadow_accessed_mask(spte);
+ /*
+ * For simplicity, enforce the NX huge page mitigation even if not
+ * strictly necessary. KVM could ignore the mitigation if paging is
+ * disabled in the guest, as the guest doesn't have an page tables to
+ * abuse. But to safely ignore the mitigation, KVM would have to
+ * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG
+ * is toggled on, and that's a net negative for performance when TDP is
+ * enabled. When TDP is disabled, KVM will always switch to a new MMU
+ * when CR0.PG is toggled, but leveraging that to ignore the mitigation
+ * would tie make_spte() further to vCPU/MMU state, and add complexity
+ * just to optimize a mode that is anything but performance critical.
+ */
if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) &&
is_nx_huge_page_enabled(vcpu->kvm)) {
pte_access &= ~ACC_EXEC_MASK;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7670c13ce251..1f03701b943a 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -188,7 +188,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
* should not modify the SPTE.
*
* Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on
- * bot AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
+ * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF
* vulnerability. Use only low bits to avoid 64-bit immediates.
*
* Only used by the TDP MMU.
@@ -219,6 +219,23 @@ static inline int spte_index(u64 *sptep)
*/
extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
+{
+ struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT);
+
+ return (struct kvm_mmu_page *)page_private(page);
+}
+
+static inline struct kvm_mmu_page *spte_to_child_sp(u64 spte)
+{
+ return to_shadow_page(spte & SPTE_BASE_ADDR_MASK);
+}
+
+static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep)
+{
+ return to_shadow_page(__pa(sptep));
+}
+
static inline bool is_mmio_spte(u64 spte)
{
return (spte & shadow_mmio_mask) == shadow_mmio_value &&
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 672f0432d777..771210ce5181 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -29,7 +29,6 @@ int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
kvm->arch.tdp_mmu_enabled = true;
INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
- INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages);
kvm->arch.tdp_mmu_zap_wq = wq;
return 1;
}
@@ -54,7 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
/* Also waits for any queued work items. */
destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
- WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages));
+ WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
@@ -284,6 +283,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu)
static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep,
gfn_t gfn, union kvm_mmu_page_role role)
{
+ INIT_LIST_HEAD(&sp->possible_nx_huge_page_link);
+
set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
sp->role = role;
@@ -375,11 +376,13 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn,
static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, +1);
+ atomic64_inc(&kvm->arch.tdp_mmu_pages);
}
static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp)
{
kvm_account_pgtable_pages((void *)sp->spt, -1);
+ atomic64_dec(&kvm->arch.tdp_mmu_pages);
}
/**
@@ -395,14 +398,17 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp,
bool shared)
{
tdp_unaccount_mmu_page(kvm, sp);
+
+ if (!sp->nx_huge_page_disallowed)
+ return;
+
if (shared)
spin_lock(&kvm->arch.tdp_mmu_pages_lock);
else
lockdep_assert_held_write(&kvm->mmu_lock);
- list_del(&sp->link);
- if (sp->lpage_disallowed)
- unaccount_huge_nx_page(kvm, sp);
+ sp->nx_huge_page_disallowed = false;
+ untrack_possible_nx_huge_page(kvm, sp);
if (shared)
spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
@@ -1116,16 +1122,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
* @kvm: kvm instance
* @iter: a tdp_iter instance currently on the SPTE that should be set
* @sp: The new TDP page table to install.
- * @account_nx: True if this page table is being installed to split a
- * non-executable huge page.
* @shared: This operation is running under the MMU lock in read mode.
*
* Returns: 0 if the new page table was installed. Non-0 if the page table
* could not be installed (e.g. the atomic compare-exchange failed).
*/
static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
- struct kvm_mmu_page *sp, bool account_nx,
- bool shared)
+ struct kvm_mmu_page *sp, bool shared)
{
u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled());
int ret = 0;
@@ -1138,16 +1141,14 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
tdp_mmu_set_spte(kvm, iter, spte);
}
- spin_lock(&kvm->arch.tdp_mmu_pages_lock);
- list_add(&sp->link, &kvm->arch.tdp_mmu_pages);
- if (account_nx)
- account_huge_nx_page(kvm, sp);
- spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
tdp_account_mmu_page(kvm, sp);
return 0;
}
+static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
+ struct kvm_mmu_page *sp, bool shared);
+
/*
* Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing
* page tables and SPTEs to translate the faulting guest physical address.
@@ -1155,9 +1156,10 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter,
int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
struct kvm_mmu *mmu = vcpu->arch.mmu;
+ struct kvm *kvm = vcpu->kvm;
struct tdp_iter iter;
struct kvm_mmu_page *sp;
- int ret;
+ int ret = RET_PF_RETRY;
kvm_mmu_hugepage_adjust(vcpu, fault);
@@ -1166,6 +1168,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
rcu_read_lock();
tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) {
+ int r;
+
if (fault->nx_huge_page_workaround_enabled)
disallowed_hugepage_adjust(fault, iter.old_spte, iter.level);
@@ -1173,57 +1177,52 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
break;
/*
- * If there is an SPTE mapping a large page at a higher level
- * than the target, that SPTE must be cleared and replaced
- * with a non-leaf SPTE.
+ * If SPTE has been frozen by another thread, just give up and
+ * retry, avoiding unnecessary page table allocation and free.
*/
- if (is_shadow_present_pte(iter.old_spte) &&
- is_large_pte(iter.old_spte)) {
- if (tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter))
- break;
+ if (is_removed_spte(iter.old_spte))
+ goto retry;
- /*
- * The iter must explicitly re-read the spte here
- * because the new value informs the !present
- * path below.
- */
- iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep);
- }
+ /* Step down into the lower level page table if it exists. */
+ if (is_shadow_present_pte(iter.old_spte) &&
+ !is_large_pte(iter.old_spte))
+ continue;
- if (!is_shadow_present_pte(iter.old_spte)) {
- bool account_nx = fault->huge_page_disallowed &&
- fault->req_level >= iter.level;
+ /*
+ * The SPTE is either non-present or points to a huge page that
+ * needs to be split.
+ */
+ sp = tdp_mmu_alloc_sp(vcpu);
+ tdp_mmu_init_child_sp(sp, &iter);
- /*
- * If SPTE has been frozen by another thread, just
- * give up and retry, avoiding unnecessary page table
- * allocation and free.
- */
- if (is_removed_spte(iter.old_spte))
- break;
+ sp->nx_huge_page_disallowed = fault->huge_page_disallowed;
- sp = tdp_mmu_alloc_sp(vcpu);
- tdp_mmu_init_child_sp(sp, &iter);
+ if (is_shadow_present_pte(iter.old_spte))
+ r = tdp_mmu_split_huge_page(kvm, &iter, sp, true);
+ else
+ r = tdp_mmu_link_sp(kvm, &iter, sp, true);
- if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) {
- tdp_mmu_free_sp(sp);
- break;
- }
+ /*
+ * Also force the guest to retry the access if the upper level SPTEs
+ * aren't in place.
+ */
+ if (r) {
+ tdp_mmu_free_sp(sp);
+ goto retry;
}
- }
- /*
- * Force the guest to retry the access if the upper level SPTEs aren't
- * in place, or if the target leaf SPTE is frozen by another CPU.
- */
- if (iter.level != fault->goal_level || is_removed_spte(iter.old_spte)) {
- rcu_read_unlock();
- return RET_PF_RETRY;
+ if (fault->huge_page_disallowed &&
+ fault->req_level >= iter.level) {
+ spin_lock(&kvm->arch.tdp_mmu_pages_lock);
+ track_possible_nx_huge_page(kvm, sp);
+ spin_unlock(&kvm->arch.tdp_mmu_pages_lock);
+ }
}
ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter);
- rcu_read_unlock();
+retry:
+ rcu_read_unlock();
return ret;
}
@@ -1472,6 +1471,7 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm,
return sp;
}
+/* Note, the caller is responsible for initializing @sp. */
static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
struct kvm_mmu_page *sp, bool shared)
{
@@ -1479,8 +1479,6 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
const int level = iter->level;
int ret, i;
- tdp_mmu_init_child_sp(sp, iter);
-
/*
* No need for atomics when writing to sp->spt since the page table has
* not been linked in yet and thus is not reachable from any other CPU.
@@ -1496,7 +1494,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter,
* correctness standpoint since the translation will be the same either
* way.
*/
- ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared);
+ ret = tdp_mmu_link_sp(kvm, iter, sp, shared);
if (ret)
goto out;
@@ -1556,6 +1554,8 @@ retry:
continue;
}
+ tdp_mmu_init_child_sp(sp, &iter);
+
if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared))
goto retry;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index c163f7cc23ca..d3714200b932 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -5,6 +5,8 @@
#include <linux/kvm_host.h>
+#include "spte.h"
+
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
__must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index d9b9a0f0db17..684393c22105 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -56,7 +56,7 @@ static const struct x86_cpu_id vmx_icl_pebs_cpu[] = {
* code. Each pmc, stored in kvm_pmc.idx field, is unique across
* all perf counters (both gp and fixed). The mapping relationship
* between pmc and perf counters is as the following:
- * * Intel: [0 .. INTEL_PMC_MAX_GENERIC-1] <=> gp counters
+ * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters
* [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed
* * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H
* and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters
@@ -101,10 +101,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
bool skip_pmi = false;
- /* Ignore counters that have been reprogrammed already. */
- if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi))
- return;
-
if (pmc->perf_event && pmc->perf_event->attr.precise_ip) {
if (!in_pmi) {
/*
@@ -122,7 +118,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
} else {
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
}
- kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
if (!pmc->intr || skip_pmi)
return;
@@ -147,12 +142,22 @@ static void kvm_perf_overflow(struct perf_event *perf_event,
{
struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+ /*
+ * Ignore overflow events for counters that are scheduled to be
+ * reprogrammed, e.g. if a PMI for the previous event races with KVM's
+ * handling of a related guest WRMSR.
+ */
+ if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi))
+ return;
+
__kvm_perf_overflow(pmc, true);
+
+ kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
}
-static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
- u64 config, bool exclude_user,
- bool exclude_kernel, bool intr)
+static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config,
+ bool exclude_user, bool exclude_kernel,
+ bool intr)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
struct perf_event *event;
@@ -204,14 +209,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type,
if (IS_ERR(event)) {
pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n",
PTR_ERR(event), pmc->idx);
- return;
+ return PTR_ERR(event);
}
pmc->perf_event = event;
pmc_to_pmu(pmc)->event_count++;
- clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
pmc->is_paused = false;
pmc->intr = intr || pebs;
+ return 0;
}
static void pmc_pause_counter(struct kvm_pmc *pmc)
@@ -245,7 +250,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc)
perf_event_enable(pmc->perf_event);
pmc->is_paused = false;
- clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
return true;
}
@@ -293,7 +297,7 @@ out:
return allow_event;
}
-void reprogram_counter(struct kvm_pmc *pmc)
+static void reprogram_counter(struct kvm_pmc *pmc)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
u64 eventsel = pmc->eventsel;
@@ -303,10 +307,13 @@ void reprogram_counter(struct kvm_pmc *pmc)
pmc_pause_counter(pmc);
if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc))
- return;
+ goto reprogram_complete;
if (!check_pmu_event_filter(pmc))
- return;
+ goto reprogram_complete;
+
+ if (pmc->counter < pmc->prev_counter)
+ __kvm_perf_overflow(pmc, false);
if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
printk_once("kvm pmu: pin control bit is ignored\n");
@@ -324,18 +331,29 @@ void reprogram_counter(struct kvm_pmc *pmc)
}
if (pmc->current_config == new_config && pmc_resume_counter(pmc))
- return;
+ goto reprogram_complete;
pmc_release_perf_event(pmc);
pmc->current_config = new_config;
- pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
- (eventsel & pmu->raw_event_mask),
- !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
- !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
- eventsel & ARCH_PERFMON_EVENTSEL_INT);
+
+ /*
+ * If reprogramming fails, e.g. due to contention, leave the counter's
+ * regprogram bit set, i.e. opportunistically try again on the next PMU
+ * refresh. Don't make a new request as doing so can stall the guest
+ * if reprogramming repeatedly fails.
+ */
+ if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW,
+ (eventsel & pmu->raw_event_mask),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_USR),
+ !(eventsel & ARCH_PERFMON_EVENTSEL_OS),
+ eventsel & ARCH_PERFMON_EVENTSEL_INT))
+ return;
+
+reprogram_complete:
+ clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi);
+ pmc->prev_counter = 0;
}
-EXPORT_SYMBOL_GPL(reprogram_counter);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
{
@@ -345,10 +363,11 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) {
struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit);
- if (unlikely(!pmc || !pmc->perf_event)) {
+ if (unlikely(!pmc)) {
clear_bit(bit, pmu->reprogram_pmi);
continue;
}
+
reprogram_counter(pmc);
}
@@ -522,14 +541,9 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
static void kvm_pmu_incr_counter(struct kvm_pmc *pmc)
{
- u64 prev_count;
-
- prev_count = pmc->counter;
+ pmc->prev_counter = pmc->counter;
pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc);
-
- reprogram_counter(pmc);
- if (pmc->counter < prev_count)
- __kvm_perf_overflow(pmc, false);
+ kvm_pmu_request_counter_reprogam(pmc);
}
static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
@@ -542,12 +556,15 @@ static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc,
static inline bool cpl_is_matched(struct kvm_pmc *pmc)
{
bool select_os, select_user;
- u64 config = pmc->current_config;
+ u64 config;
if (pmc_is_gp(pmc)) {
+ config = pmc->eventsel;
select_os = config & ARCH_PERFMON_EVENTSEL_OS;
select_user = config & ARCH_PERFMON_EVENTSEL_USR;
} else {
+ config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl,
+ pmc->idx - INTEL_PMC_IDX_FIXED);
select_os = config & 0x1;
select_user = config & 0x2;
}
@@ -577,6 +594,8 @@ EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);
int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
{
struct kvm_pmu_event_filter tmp, *filter;
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
size_t size;
int r;
@@ -613,9 +632,18 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
mutex_lock(&kvm->lock);
filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
mutex_is_locked(&kvm->lock));
+ synchronize_srcu_expedited(&kvm->srcu);
+
+ BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) >
+ sizeof(((struct kvm_pmu *)0)->__reprogram_pmi));
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ atomic64_set(&vcpu_to_pmu(vcpu)->__reprogram_pmi, -1ull);
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_PMU);
+
mutex_unlock(&kvm->lock);
- synchronize_srcu_expedited(&kvm->srcu);
r = 0;
cleanup:
kfree(filter);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 5cc5721f260b..85ff3c0588ba 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -183,7 +183,11 @@ static inline void kvm_init_pmu_capability(void)
KVM_PMC_MAX_FIXED);
}
-void reprogram_counter(struct kvm_pmc *pmc);
+static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc)
+{
+ set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi);
+ kvm_make_request(KVM_REQ_PMU, pmc->vcpu);
+}
void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index a19d473d0184..203fdad07bae 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -7,23 +7,41 @@
#include <asm/cpufeatures.h>
/*
- * Hardware-defined CPUID leafs that are scattered in the kernel, but need to
- * be directly used by KVM. Note, these word values conflict with the kernel's
- * "bug" caps, but KVM doesn't use those.
+ * Hardware-defined CPUID leafs that are either scattered by the kernel or are
+ * unknown to the kernel, but need to be directly used by KVM. Note, these
+ * word values conflict with the kernel's "bug" caps, but KVM doesn't use those.
*/
enum kvm_only_cpuid_leafs {
CPUID_12_EAX = NCAPINTS,
+ CPUID_7_1_EDX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
};
+/*
+ * Define a KVM-only feature flag.
+ *
+ * For features that are scattered by cpufeatures.h, __feature_translate() also
+ * needs to be updated to translate the kernel-defined feature into the
+ * KVM-defined feature.
+ *
+ * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h,
+ * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so
+ * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is
+ * needed in this case.
+ */
#define KVM_X86_FEATURE(w, f) ((w)*32 + (f))
/* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */
#define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0)
#define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1)
+/* Intel-defined sub-features, CPUID level 0x00000007:1 (EDX) */
+#define X86_FEATURE_AVX_VNNI_INT8 KVM_X86_FEATURE(CPUID_7_1_EDX, 4)
+#define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5)
+#define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14)
+
struct cpuid_reg {
u32 function;
u32 index;
@@ -48,6 +66,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_7_1_EAX] = { 7, 1, CPUID_EAX},
[CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX},
[CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX},
+ [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX},
};
/*
diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c
new file mode 100644
index 000000000000..a9c1c2af8d94
--- /dev/null
+++ b/arch/x86/kvm/smm.c
@@ -0,0 +1,649 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/kvm_host.h>
+#include "x86.h"
+#include "kvm_cache_regs.h"
+#include "kvm_emulate.h"
+#include "smm.h"
+#include "cpuid.h"
+#include "trace.h"
+
+#define CHECK_SMRAM32_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00)
+
+#define CHECK_SMRAM64_OFFSET(field, offset) \
+ ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00)
+
+static void check_smram_offsets(void)
+{
+ /* 32 bit SMRAM image */
+ CHECK_SMRAM32_OFFSET(reserved1, 0xFE00);
+ CHECK_SMRAM32_OFFSET(smbase, 0xFEF8);
+ CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC);
+ CHECK_SMRAM32_OFFSET(io_inst_restart, 0xFF00);
+ CHECK_SMRAM32_OFFSET(auto_hlt_restart, 0xFF02);
+ CHECK_SMRAM32_OFFSET(io_restart_rdi, 0xFF04);
+ CHECK_SMRAM32_OFFSET(io_restart_rcx, 0xFF08);
+ CHECK_SMRAM32_OFFSET(io_restart_rsi, 0xFF0C);
+ CHECK_SMRAM32_OFFSET(io_restart_rip, 0xFF10);
+ CHECK_SMRAM32_OFFSET(cr4, 0xFF14);
+ CHECK_SMRAM32_OFFSET(reserved2, 0xFF18);
+ CHECK_SMRAM32_OFFSET(int_shadow, 0xFF1A);
+ CHECK_SMRAM32_OFFSET(reserved3, 0xFF1B);
+ CHECK_SMRAM32_OFFSET(ds, 0xFF2C);
+ CHECK_SMRAM32_OFFSET(fs, 0xFF38);
+ CHECK_SMRAM32_OFFSET(gs, 0xFF44);
+ CHECK_SMRAM32_OFFSET(idtr, 0xFF50);
+ CHECK_SMRAM32_OFFSET(tr, 0xFF5C);
+ CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C);
+ CHECK_SMRAM32_OFFSET(ldtr, 0xFF78);
+ CHECK_SMRAM32_OFFSET(es, 0xFF84);
+ CHECK_SMRAM32_OFFSET(cs, 0xFF90);
+ CHECK_SMRAM32_OFFSET(ss, 0xFF9C);
+ CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8);
+ CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC);
+ CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0);
+ CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4);
+ CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8);
+ CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC);
+ CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0);
+ CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4);
+ CHECK_SMRAM32_OFFSET(dr7, 0xFFC8);
+ CHECK_SMRAM32_OFFSET(dr6, 0xFFCC);
+ CHECK_SMRAM32_OFFSET(gprs, 0xFFD0);
+ CHECK_SMRAM32_OFFSET(eip, 0xFFF0);
+ CHECK_SMRAM32_OFFSET(eflags, 0xFFF4);
+ CHECK_SMRAM32_OFFSET(cr3, 0xFFF8);
+ CHECK_SMRAM32_OFFSET(cr0, 0xFFFC);
+
+ /* 64 bit SMRAM image */
+ CHECK_SMRAM64_OFFSET(es, 0xFE00);
+ CHECK_SMRAM64_OFFSET(cs, 0xFE10);
+ CHECK_SMRAM64_OFFSET(ss, 0xFE20);
+ CHECK_SMRAM64_OFFSET(ds, 0xFE30);
+ CHECK_SMRAM64_OFFSET(fs, 0xFE40);
+ CHECK_SMRAM64_OFFSET(gs, 0xFE50);
+ CHECK_SMRAM64_OFFSET(gdtr, 0xFE60);
+ CHECK_SMRAM64_OFFSET(ldtr, 0xFE70);
+ CHECK_SMRAM64_OFFSET(idtr, 0xFE80);
+ CHECK_SMRAM64_OFFSET(tr, 0xFE90);
+ CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0);
+ CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8);
+ CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0);
+ CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8);
+ CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0);
+ CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4);
+ CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8);
+ CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9);
+ CHECK_SMRAM64_OFFSET(amd_nmi_mask, 0xFECA);
+ CHECK_SMRAM64_OFFSET(int_shadow, 0xFECB);
+ CHECK_SMRAM64_OFFSET(reserved2, 0xFECC);
+ CHECK_SMRAM64_OFFSET(efer, 0xFED0);
+ CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8);
+ CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0);
+ CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8);
+ CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0);
+ CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC);
+ CHECK_SMRAM64_OFFSET(smbase, 0xFF00);
+ CHECK_SMRAM64_OFFSET(reserved4, 0xFF04);
+ CHECK_SMRAM64_OFFSET(ssp, 0xFF18);
+ CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20);
+ CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28);
+ CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30);
+ CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38);
+ CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40);
+ CHECK_SMRAM64_OFFSET(cr4, 0xFF48);
+ CHECK_SMRAM64_OFFSET(cr3, 0xFF50);
+ CHECK_SMRAM64_OFFSET(cr0, 0xFF58);
+ CHECK_SMRAM64_OFFSET(dr7, 0xFF60);
+ CHECK_SMRAM64_OFFSET(dr6, 0xFF68);
+ CHECK_SMRAM64_OFFSET(rflags, 0xFF70);
+ CHECK_SMRAM64_OFFSET(rip, 0xFF78);
+ CHECK_SMRAM64_OFFSET(gprs, 0xFF80);
+
+ BUILD_BUG_ON(sizeof(union kvm_smram) != 512);
+}
+
+#undef CHECK_SMRAM64_OFFSET
+#undef CHECK_SMRAM32_OFFSET
+
+
+void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
+{
+ BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
+
+ trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm);
+
+ if (entering_smm) {
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ } else {
+ vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK);
+
+ /* Process a latched INIT or SMI, if any. */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+ /*
+ * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
+ * on SMM exit we still need to reload them from
+ * guest memory
+ */
+ vcpu->arch.pdptrs_from_userspace = false;
+ }
+
+ kvm_mmu_reset_context(vcpu);
+}
+
+void process_smi(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.smi_pending = true;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
+static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
+{
+ u32 flags = 0;
+ flags |= seg->g << 23;
+ flags |= seg->db << 22;
+ flags |= seg->l << 21;
+ flags |= seg->avl << 20;
+ flags |= seg->present << 15;
+ flags |= seg->dpl << 13;
+ flags |= seg->s << 12;
+ flags |= seg->type << 8;
+ return flags;
+}
+
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_32 *state,
+ u32 *selector, int n)
+{
+ struct kvm_segment seg;
+
+ kvm_get_segment(vcpu, &seg, n);
+ *selector = seg.selector;
+ state->base = seg.base;
+ state->limit = seg.limit;
+ state->flags = enter_smm_get_segment_flags(&seg);
+}
+
+#ifdef CONFIG_X86_64
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu,
+ struct kvm_smm_seg_state_64 *state,
+ int n)
+{
+ struct kvm_segment seg;
+
+ kvm_get_segment(vcpu, &seg, n);
+ state->selector = seg.selector;
+ state->attributes = enter_smm_get_segment_flags(&seg) >> 8;
+ state->limit = seg.limit;
+ state->base = seg.base;
+}
+#endif
+
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu,
+ struct kvm_smram_state_32 *smram)
+{
+ struct desc_ptr dt;
+ unsigned long val;
+ int i;
+
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->eflags = kvm_get_rflags(vcpu);
+ smram->eip = kvm_rip_read(vcpu);
+
+ for (i = 0; i < 8; i++)
+ smram->gprs[i] = kvm_register_read_raw(vcpu, i);
+
+ kvm_get_dr(vcpu, 6, &val);
+ smram->dr6 = (u32)val;
+ kvm_get_dr(vcpu, 7, &val);
+ smram->dr7 = (u32)val;
+
+ enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
+ enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
+
+ static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ smram->gdtr.base = dt.address;
+ smram->gdtr.limit = dt.size;
+
+ static_call(kvm_x86_get_idt)(vcpu, &dt);
+ smram->idtr.base = dt.address;
+ smram->idtr.limit = dt.size;
+
+ enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES);
+ enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS);
+ enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS);
+
+ enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS);
+ enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS);
+ enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS);
+
+ smram->cr4 = kvm_read_cr4(vcpu);
+ smram->smm_revision = 0x00020000;
+ smram->smbase = vcpu->arch.smbase;
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+}
+
+#ifdef CONFIG_X86_64
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu,
+ struct kvm_smram_state_64 *smram)
+{
+ struct desc_ptr dt;
+ unsigned long val;
+ int i;
+
+ for (i = 0; i < 16; i++)
+ smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i);
+
+ smram->rip = kvm_rip_read(vcpu);
+ smram->rflags = kvm_get_rflags(vcpu);
+
+
+ kvm_get_dr(vcpu, 6, &val);
+ smram->dr6 = val;
+ kvm_get_dr(vcpu, 7, &val);
+ smram->dr7 = val;
+
+ smram->cr0 = kvm_read_cr0(vcpu);
+ smram->cr3 = kvm_read_cr3(vcpu);
+ smram->cr4 = kvm_read_cr4(vcpu);
+
+ smram->smbase = vcpu->arch.smbase;
+ smram->smm_revison = 0x00020064;
+
+ smram->efer = vcpu->arch.efer;
+
+ enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
+
+ static_call(kvm_x86_get_idt)(vcpu, &dt);
+ smram->idtr.limit = dt.size;
+ smram->idtr.base = dt.address;
+
+ enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
+
+ static_call(kvm_x86_get_gdt)(vcpu, &dt);
+ smram->gdtr.limit = dt.size;
+ smram->gdtr.base = dt.address;
+
+ enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES);
+ enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS);
+ enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS);
+ enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+ enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+ enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+ smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+}
+#endif
+
+void enter_smm(struct kvm_vcpu *vcpu)
+{
+ struct kvm_segment cs, ds;
+ struct desc_ptr dt;
+ unsigned long cr0;
+ union kvm_smram smram;
+
+ check_smram_offsets();
+
+ memset(smram.bytes, 0, sizeof(smram.bytes));
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ enter_smm_save_state_64(vcpu, &smram.smram64);
+ else
+#endif
+ enter_smm_save_state_32(vcpu, &smram.smram32);
+
+ /*
+ * Give enter_smm() a chance to make ISA-specific changes to the vCPU
+ * state (e.g. leave guest mode) after we've saved the state into the
+ * SMM state-save area.
+ *
+ * Kill the VM in the unlikely case of failure, because the VM
+ * can be in undefined state in this case.
+ */
+ if (static_call(kvm_x86_enter_smm)(vcpu, &smram))
+ goto error;
+
+ kvm_smm_changed(vcpu, true);
+
+ if (kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram)))
+ goto error;
+
+ if (static_call(kvm_x86_get_nmi_mask)(vcpu))
+ vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
+ else
+ static_call(kvm_x86_set_nmi_mask)(vcpu, true);
+
+ kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ kvm_rip_write(vcpu, 0x8000);
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
+ cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
+ static_call(kvm_x86_set_cr0)(vcpu, cr0);
+ vcpu->arch.cr0 = cr0;
+
+ static_call(kvm_x86_set_cr4)(vcpu, 0);
+
+ /* Undocumented: IDT limit is set to zero on entry to SMM. */
+ dt.address = dt.size = 0;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ if (WARN_ON_ONCE(kvm_set_dr(vcpu, 7, DR7_FIXED_1)))
+ goto error;
+
+ cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
+ cs.base = vcpu->arch.smbase;
+
+ ds.selector = 0;
+ ds.base = 0;
+
+ cs.limit = ds.limit = 0xffffffff;
+ cs.type = ds.type = 0x3;
+ cs.dpl = ds.dpl = 0;
+ cs.db = ds.db = 0;
+ cs.s = ds.s = 1;
+ cs.l = ds.l = 0;
+ cs.g = ds.g = 1;
+ cs.avl = ds.avl = 0;
+ cs.present = ds.present = 1;
+ cs.unusable = ds.unusable = 0;
+ cs.padding = ds.padding = 0;
+
+ kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
+ kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ if (static_call(kvm_x86_set_efer)(vcpu, 0))
+ goto error;
+#endif
+
+ kvm_update_cpuid_runtime(vcpu);
+ kvm_mmu_reset_context(vcpu);
+ return;
+error:
+ kvm_vm_dead(vcpu->kvm);
+}
+
+static void rsm_set_desc_flags(struct kvm_segment *desc, u32 flags)
+{
+ desc->g = (flags >> 23) & 1;
+ desc->db = (flags >> 22) & 1;
+ desc->l = (flags >> 21) & 1;
+ desc->avl = (flags >> 20) & 1;
+ desc->present = (flags >> 15) & 1;
+ desc->dpl = (flags >> 13) & 3;
+ desc->s = (flags >> 12) & 1;
+ desc->type = (flags >> 8) & 15;
+
+ desc->unusable = !desc->present;
+ desc->padding = 0;
+}
+
+static int rsm_load_seg_32(struct kvm_vcpu *vcpu,
+ const struct kvm_smm_seg_state_32 *state,
+ u16 selector, int n)
+{
+ struct kvm_segment desc;
+
+ desc.selector = selector;
+ desc.base = state->base;
+ desc.limit = state->limit;
+ rsm_set_desc_flags(&desc, state->flags);
+ kvm_set_segment(vcpu, &desc, n);
+ return X86EMUL_CONTINUE;
+}
+
+#ifdef CONFIG_X86_64
+
+static int rsm_load_seg_64(struct kvm_vcpu *vcpu,
+ const struct kvm_smm_seg_state_64 *state,
+ int n)
+{
+ struct kvm_segment desc;
+
+ desc.selector = state->selector;
+ rsm_set_desc_flags(&desc, state->attributes << 8);
+ desc.limit = state->limit;
+ desc.base = state->base;
+ kvm_set_segment(vcpu, &desc, n);
+ return X86EMUL_CONTINUE;
+}
+#endif
+
+static int rsm_enter_protected_mode(struct kvm_vcpu *vcpu,
+ u64 cr0, u64 cr3, u64 cr4)
+{
+ int bad;
+ u64 pcid;
+
+ /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */
+ pcid = 0;
+ if (cr4 & X86_CR4_PCIDE) {
+ pcid = cr3 & 0xfff;
+ cr3 &= ~0xfff;
+ }
+
+ bad = kvm_set_cr3(vcpu, cr3);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ /*
+ * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+ * Then enable protected mode. However, PCID cannot be enabled
+ * if EFER.LMA=0, so set it separately.
+ */
+ bad = kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ bad = kvm_set_cr0(vcpu, cr0);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+
+ if (cr4 & X86_CR4_PCIDE) {
+ bad = kvm_set_cr4(vcpu, cr4);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ if (pcid) {
+ bad = kvm_set_cr3(vcpu, cr3 | pcid);
+ if (bad)
+ return X86EMUL_UNHANDLEABLE;
+ }
+
+ }
+
+ return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smram_state_32 *smstate)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct desc_ptr dt;
+ int i, r;
+
+ ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED;
+ ctxt->_eip = smstate->eip;
+
+ for (i = 0; i < 8; i++)
+ *reg_write(ctxt, i) = smstate->gprs[i];
+
+ if (kvm_set_dr(vcpu, 6, smstate->dr6))
+ return X86EMUL_UNHANDLEABLE;
+ if (kvm_set_dr(vcpu, 7, smstate->dr7))
+ return X86EMUL_UNHANDLEABLE;
+
+ rsm_load_seg_32(vcpu, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR);
+ rsm_load_seg_32(vcpu, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR);
+
+ dt.address = smstate->gdtr.base;
+ dt.size = smstate->gdtr.limit;
+ static_call(kvm_x86_set_gdt)(vcpu, &dt);
+
+ dt.address = smstate->idtr.base;
+ dt.size = smstate->idtr.limit;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ rsm_load_seg_32(vcpu, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
+ rsm_load_seg_32(vcpu, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
+ rsm_load_seg_32(vcpu, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS);
+
+ rsm_load_seg_32(vcpu, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS);
+ rsm_load_seg_32(vcpu, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS);
+ rsm_load_seg_32(vcpu, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS);
+
+ vcpu->arch.smbase = smstate->smbase;
+
+ r = rsm_enter_protected_mode(vcpu, smstate->cr0,
+ smstate->cr3, smstate->cr4);
+
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return r;
+}
+
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const struct kvm_smram_state_64 *smstate)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ struct desc_ptr dt;
+ int i, r;
+
+ for (i = 0; i < 16; i++)
+ *reg_write(ctxt, i) = smstate->gprs[15 - i];
+
+ ctxt->_eip = smstate->rip;
+ ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED;
+
+ if (kvm_set_dr(vcpu, 6, smstate->dr6))
+ return X86EMUL_UNHANDLEABLE;
+ if (kvm_set_dr(vcpu, 7, smstate->dr7))
+ return X86EMUL_UNHANDLEABLE;
+
+ vcpu->arch.smbase = smstate->smbase;
+
+ if (kvm_set_msr(vcpu, MSR_EFER, smstate->efer & ~EFER_LMA))
+ return X86EMUL_UNHANDLEABLE;
+
+ rsm_load_seg_64(vcpu, &smstate->tr, VCPU_SREG_TR);
+
+ dt.size = smstate->idtr.limit;
+ dt.address = smstate->idtr.base;
+ static_call(kvm_x86_set_idt)(vcpu, &dt);
+
+ rsm_load_seg_64(vcpu, &smstate->ldtr, VCPU_SREG_LDTR);
+
+ dt.size = smstate->gdtr.limit;
+ dt.address = smstate->gdtr.base;
+ static_call(kvm_x86_set_gdt)(vcpu, &dt);
+
+ r = rsm_enter_protected_mode(vcpu, smstate->cr0, smstate->cr3, smstate->cr4);
+ if (r != X86EMUL_CONTINUE)
+ return r;
+
+ rsm_load_seg_64(vcpu, &smstate->es, VCPU_SREG_ES);
+ rsm_load_seg_64(vcpu, &smstate->cs, VCPU_SREG_CS);
+ rsm_load_seg_64(vcpu, &smstate->ss, VCPU_SREG_SS);
+ rsm_load_seg_64(vcpu, &smstate->ds, VCPU_SREG_DS);
+ rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS);
+ rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS);
+
+ static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+ ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ return X86EMUL_CONTINUE;
+}
+#endif
+
+int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
+{
+ struct kvm_vcpu *vcpu = ctxt->vcpu;
+ unsigned long cr0;
+ union kvm_smram smram;
+ u64 smbase;
+ int ret;
+
+ smbase = vcpu->arch.smbase;
+
+ ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfe00, smram.bytes, sizeof(smram));
+ if (ret < 0)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK) == 0)
+ static_call(kvm_x86_set_nmi_mask)(vcpu, false);
+
+ kvm_smm_changed(vcpu, false);
+
+ /*
+ * Get back to real mode, to prepare a safe state in which to load
+ * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
+ * supports long mode.
+ */
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+ struct kvm_segment cs_desc;
+ unsigned long cr4;
+
+ /* Zero CR4.PCIDE before CR0.PG. */
+ cr4 = kvm_read_cr4(vcpu);
+ if (cr4 & X86_CR4_PCIDE)
+ kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE);
+
+ /* A 32-bit code segment is required to clear EFER.LMA. */
+ memset(&cs_desc, 0, sizeof(cs_desc));
+ cs_desc.type = 0xb;
+ cs_desc.s = cs_desc.g = cs_desc.present = 1;
+ kvm_set_segment(vcpu, &cs_desc, VCPU_SREG_CS);
+ }
+#endif
+
+ /* For the 64-bit case, this will clear EFER.LMA. */
+ cr0 = kvm_read_cr0(vcpu);
+ if (cr0 & X86_CR0_PE)
+ kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
+ unsigned long cr4, efer;
+
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = kvm_read_cr4(vcpu);
+ if (cr4 & X86_CR4_PAE)
+ kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PAE);
+
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ kvm_set_msr(vcpu, MSR_EFER, efer);
+ }
+#endif
+
+ /*
+ * Give leave_smm() a chance to make ISA-specific changes to the vCPU
+ * state (e.g. enter guest mode) before loading state from the SMM
+ * state-save area.
+ */
+ if (static_call(kvm_x86_leave_smm)(vcpu, &smram))
+ return X86EMUL_UNHANDLEABLE;
+
+#ifdef CONFIG_X86_64
+ if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return rsm_load_state_64(ctxt, &smram.smram64);
+ else
+#endif
+ return rsm_load_state_32(ctxt, &smram.smram32);
+}
diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h
new file mode 100644
index 000000000000..a1cf2ac5bd78
--- /dev/null
+++ b/arch/x86/kvm/smm.h
@@ -0,0 +1,168 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_KVM_SMM_H
+#define ASM_KVM_SMM_H
+
+#include <linux/build_bug.h>
+
+#ifdef CONFIG_KVM_SMM
+
+
+/*
+ * 32 bit KVM's emulated SMM layout. Based on Intel P6 layout
+ * (https://www.sandpile.org/x86/smm.htm).
+ */
+
+struct kvm_smm_seg_state_32 {
+ u32 flags;
+ u32 limit;
+ u32 base;
+} __packed;
+
+struct kvm_smram_state_32 {
+ u32 reserved1[62];
+ u32 smbase;
+ u32 smm_revision;
+ u16 io_inst_restart;
+ u16 auto_hlt_restart;
+ u32 io_restart_rdi;
+ u32 io_restart_rcx;
+ u32 io_restart_rsi;
+ u32 io_restart_rip;
+ u32 cr4;
+
+ /* A20M#, CPL, shutdown and other reserved/undocumented fields */
+ u16 reserved2;
+ u8 int_shadow; /* KVM extension */
+ u8 reserved3[17];
+
+ struct kvm_smm_seg_state_32 ds;
+ struct kvm_smm_seg_state_32 fs;
+ struct kvm_smm_seg_state_32 gs;
+ struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */
+ struct kvm_smm_seg_state_32 tr;
+ u32 reserved;
+ struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */
+ struct kvm_smm_seg_state_32 ldtr;
+ struct kvm_smm_seg_state_32 es;
+ struct kvm_smm_seg_state_32 cs;
+ struct kvm_smm_seg_state_32 ss;
+
+ u32 es_sel;
+ u32 cs_sel;
+ u32 ss_sel;
+ u32 ds_sel;
+ u32 fs_sel;
+ u32 gs_sel;
+ u32 ldtr_sel;
+ u32 tr_sel;
+
+ u32 dr7;
+ u32 dr6;
+ u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */
+ u32 eip;
+ u32 eflags;
+ u32 cr3;
+ u32 cr0;
+} __packed;
+
+
+/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */
+
+struct kvm_smm_seg_state_64 {
+ u16 selector;
+ u16 attributes;
+ u32 limit;
+ u64 base;
+};
+
+struct kvm_smram_state_64 {
+
+ struct kvm_smm_seg_state_64 es;
+ struct kvm_smm_seg_state_64 cs;
+ struct kvm_smm_seg_state_64 ss;
+ struct kvm_smm_seg_state_64 ds;
+ struct kvm_smm_seg_state_64 fs;
+ struct kvm_smm_seg_state_64 gs;
+ struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 ldtr;
+ struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/
+ struct kvm_smm_seg_state_64 tr;
+
+ /* I/O restart and auto halt restart are not implemented by KVM */
+ u64 io_restart_rip;
+ u64 io_restart_rcx;
+ u64 io_restart_rsi;
+ u64 io_restart_rdi;
+ u32 io_restart_dword;
+ u32 reserved1;
+ u8 io_inst_restart;
+ u8 auto_hlt_restart;
+ u8 amd_nmi_mask; /* Documented in AMD BKDG as NMI mask, not used by KVM */
+ u8 int_shadow;
+ u32 reserved2;
+
+ u64 efer;
+
+ /*
+ * Two fields below are implemented on AMD only, to store
+ * SVM guest vmcb address if the #SMI was received while in the guest mode.
+ */
+ u64 svm_guest_flag;
+ u64 svm_guest_vmcb_gpa;
+ u64 svm_guest_virtual_int; /* unknown purpose, not implemented */
+
+ u32 reserved3[3];
+ u32 smm_revison;
+ u32 smbase;
+ u32 reserved4[5];
+
+ /* ssp and svm_* fields below are not implemented by KVM */
+ u64 ssp;
+ u64 svm_guest_pat;
+ u64 svm_host_efer;
+ u64 svm_host_cr4;
+ u64 svm_host_cr3;
+ u64 svm_host_cr0;
+
+ u64 cr4;
+ u64 cr3;
+ u64 cr0;
+ u64 dr7;
+ u64 dr6;
+ u64 rflags;
+ u64 rip;
+ u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+};
+
+union kvm_smram {
+ struct kvm_smram_state_64 smram64;
+ struct kvm_smram_state_32 smram32;
+ u8 bytes[512];
+};
+
+static inline int kvm_inject_smi(struct kvm_vcpu *vcpu)
+{
+ kvm_make_request(KVM_REQ_SMI, vcpu);
+ return 0;
+}
+
+static inline bool is_smm(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.hflags & HF_SMM_MASK;
+}
+
+void kvm_smm_changed(struct kvm_vcpu *vcpu, bool in_smm);
+void enter_smm(struct kvm_vcpu *vcpu);
+int emulator_leave_smm(struct x86_emulate_ctxt *ctxt);
+void process_smi(struct kvm_vcpu *vcpu);
+#else
+static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) { return -ENOTTY; }
+static inline bool is_smm(struct kvm_vcpu *vcpu) { return false; }
+
+/*
+ * emulator_leave_smm is used as a function pointer, so the
+ * stub is defined in x86.c.
+ */
+#endif
+
+#endif
diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c
new file mode 100644
index 000000000000..088f6429b24c
--- /dev/null
+++ b/arch/x86/kvm/svm/hyperv.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD SVM specific code for Hyper-V on KVM.
+ *
+ * Copyright 2022 Red Hat, Inc. and/or its affiliates.
+ */
+#include "hyperv.h"
+
+void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL;
+ svm->vmcb->control.exit_code_hi = 0;
+ svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH;
+ svm->vmcb->control.exit_info_2 = 0;
+ nested_svm_vmexit(svm);
+}
diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h
index 7d6d97968fb9..02f4784b5d44 100644
--- a/arch/x86/kvm/svm/hyperv.h
+++ b/arch/x86/kvm/svm/hyperv.h
@@ -9,27 +9,37 @@
#include <asm/mshyperv.h>
#include "../hyperv.h"
+#include "svm.h"
-/*
- * Hyper-V uses the software reserved 32 bytes in VMCB
- * control area to expose SVM enlightenments to guests.
- */
-struct hv_enlightenments {
- struct __packed hv_enlightenments_control {
- u32 nested_flush_hypercall:1;
- u32 msr_bitmap:1;
- u32 enlightened_npt_tlb: 1;
- u32 reserved:29;
- } __packed hv_enlightenments_control;
- u32 hv_vp_id;
- u64 hv_vm_id;
- u64 partition_assist_page;
- u64 reserved;
-} __packed;
+static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
-/*
- * Hyper-V uses the software reserved clean bit in VMCB
- */
-#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW
+ if (!hv_vcpu)
+ return;
+
+ hv_vcpu->nested.pa_page_gpa = hve->partition_assist_page;
+ hv_vcpu->nested.vm_id = hve->hv_vm_id;
+ hv_vcpu->nested.vp_id = hve->hv_vp_id;
+}
+
+static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+
+ if (!hv_vcpu)
+ return false;
+
+ if (!hve->hv_enlightenments_control.nested_flush_hypercall)
+ return false;
+
+ return hv_vcpu->vp_assist_page.nested_control.features.directhypercall;
+}
+
+void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
#endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 4c620999d230..bc9cd7086fa9 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -25,6 +25,7 @@
#include "trace.h"
#include "mmu.h"
#include "x86.h"
+#include "smm.h"
#include "cpuid.h"
#include "lapic.h"
#include "svm.h"
@@ -149,8 +150,12 @@ void recalc_intercepts(struct vcpu_svm *svm)
vmcb_clr_intercept(c, INTERCEPT_VINTR);
}
- /* We don't want to see VMMCALLs from a nested guest */
- vmcb_clr_intercept(c, INTERCEPT_VMMCALL);
+ /*
+ * We want to see VMMCALLs from a nested guest only when Hyper-V L2 TLB
+ * flush feature is enabled.
+ */
+ if (!nested_svm_l2_tlb_flush_enabled(&svm->vcpu))
+ vmcb_clr_intercept(c, INTERCEPT_VMMCALL);
for (i = 0; i < MAX_INTERCEPT; i++)
c->intercepts[i] |= g->intercepts[i];
@@ -179,8 +184,7 @@ void recalc_intercepts(struct vcpu_svm *svm)
*/
static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
{
- struct hv_enlightenments *hve =
- (struct hv_enlightenments *)svm->nested.ctl.reserved_sw;
+ struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
int i;
/*
@@ -194,7 +198,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
if (!svm->nested.force_msr_bitmap_recalc &&
kvm_hv_hypercall_enabled(&svm->vcpu) &&
hve->hv_enlightenments_control.msr_bitmap &&
- (svm->nested.ctl.clean & BIT(VMCB_HV_NESTED_ENLIGHTENMENTS)))
+ (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
goto set_msrpm_base_pa;
if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
@@ -369,8 +373,8 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu,
/* Hyper-V extensions (Enlightened VMCB) */
if (kvm_hv_hypercall_enabled(vcpu)) {
to->clean = from->clean;
- memcpy(to->reserved_sw, from->reserved_sw,
- sizeof(struct hv_enlightenments));
+ memcpy(&to->hv_enlightenments, &from->hv_enlightenments,
+ sizeof(to->hv_enlightenments));
}
}
@@ -474,6 +478,15 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm,
static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu)
{
/*
+ * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+ * L2's VP_ID upon request from the guest. Make sure we check for
+ * pending entries in the right FIFO upon L1/L2 transition as these
+ * requests are put by other vCPUs asynchronously.
+ */
+ if (to_hv_vcpu(vcpu) && npt_enabled)
+ kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+
+ /*
* TODO: optimize unconditional TLB flush/MMU sync. A partial list of
* things to fix before this can be conditional:
*
@@ -800,6 +813,8 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa,
if (kvm_vcpu_apicv_active(vcpu))
kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
+ nested_svm_hv_update_vm_vp_ids(vcpu);
+
return 0;
}
@@ -822,6 +837,13 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
return 1;
}
+ /* This fails when VP assist page is enabled but the supplied GPA is bogus */
+ ret = kvm_hv_verify_vp_assist(vcpu);
+ if (ret) {
+ kvm_inject_gp(vcpu, 0);
+ return ret;
+ }
+
vmcb12_gpa = svm->vmcb->save.rax;
ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map);
if (ret == -EINVAL) {
@@ -1091,6 +1113,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
static void nested_svm_triple_fault(struct kvm_vcpu *vcpu)
{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN))
+ return;
+
+ kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN);
}
@@ -1125,6 +1153,9 @@ void svm_free_nested(struct vcpu_svm *svm)
if (!svm->nested.initialized)
return;
+ if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr))
+ svm_switch_vmcb(svm, &svm->vmcb01);
+
svm_vcpu_free_msrpm(svm->nested.msrpm);
svm->nested.msrpm = NULL;
@@ -1143,9 +1174,6 @@ void svm_free_nested(struct vcpu_svm *svm)
svm->nested.initialized = false;
}
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
void svm_leave_nested(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1377,6 +1405,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
return 0;
}
+#ifdef CONFIG_KVM_SMM
if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) {
if (block_nested_events)
return -EBUSY;
@@ -1385,6 +1414,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
nested_svm_simple_vmexit(svm, SVM_EXIT_SMI);
return 0;
}
+#endif
if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) {
if (block_nested_events)
@@ -1411,6 +1441,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu)
int nested_svm_exit_special(struct vcpu_svm *svm)
{
u32 exit_code = svm->vmcb->control.exit_code;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
switch (exit_code) {
case SVM_EXIT_INTR:
@@ -1429,6 +1460,13 @@ int nested_svm_exit_special(struct vcpu_svm *svm)
return NESTED_EXIT_HOST;
break;
}
+ case SVM_EXIT_VMMCALL:
+ /* Hyper-V L2 TLB flush hypercall is handled by L0 */
+ if (guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
+ nested_svm_l2_tlb_flush_enabled(vcpu) &&
+ kvm_hv_is_tlb_flush_hcall(vcpu))
+ return NESTED_EXIT_HOST;
+ break;
default:
break;
}
@@ -1479,7 +1517,7 @@ static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst,
dst->virt_ext = from->virt_ext;
dst->pause_filter_count = from->pause_filter_count;
dst->pause_filter_thresh = from->pause_filter_thresh;
- /* 'clean' and 'reserved_sw' are not changed by KVM */
+ /* 'clean' and 'hv_enlightenments' are not changed by KVM */
}
static int svm_get_nested_state(struct kvm_vcpu *vcpu,
@@ -1709,6 +1747,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
return false;
}
+ if (kvm_hv_verify_vp_assist(vcpu))
+ return false;
+
return true;
}
@@ -1720,4 +1761,5 @@ struct kvm_x86_nested_ops svm_nested_ops = {
.get_nested_state_pages = svm_get_nested_state_pages,
.get_state = svm_get_nested_state,
.set_state = svm_set_nested_state,
+ .hv_inject_synthetic_vmexit_post_tlb_flush = svm_hv_inject_synthetic_vmexit_post_tlb_flush,
};
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index b68956299fa8..0e313fbae055 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -159,7 +159,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
data &= ~pmu->reserved_bits;
if (data != pmc->eventsel) {
pmc->eventsel = data;
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
return 0;
}
@@ -192,9 +192,10 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
int i;
- BUILD_BUG_ON(AMD64_NUM_COUNTERS_CORE > INTEL_PMC_MAX_GENERIC);
+ BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > AMD64_NUM_COUNTERS_CORE);
+ BUILD_BUG_ON(KVM_AMD_PMC_MAX_GENERIC > INTEL_PMC_MAX_GENERIC);
- for (i = 0; i < AMD64_NUM_COUNTERS_CORE ; i++) {
+ for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC ; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
pmu->gp_counters[i].idx = i;
@@ -207,11 +208,11 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
int i;
- for (i = 0; i < AMD64_NUM_COUNTERS_CORE; i++) {
+ for (i = 0; i < KVM_AMD_PMC_MAX_GENERIC; i++) {
struct kvm_pmc *pmc = &pmu->gp_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = pmc->eventsel = 0;
+ pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
}
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 28064060413a..69dbf17f0d6a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -196,7 +196,7 @@ static void sev_asid_free(struct kvm_sev_info *sev)
__set_bit(sev->asid, sev_reclaim_asid_bitmap);
for_each_possible_cpu(cpu) {
- sd = per_cpu(svm_data, cpu);
+ sd = per_cpu_ptr(&svm_data, cpu);
sd->sev_vmcbs[sev->asid] = NULL;
}
@@ -605,7 +605,7 @@ static int sev_es_sync_vmsa(struct vcpu_svm *svm)
save->dr6 = svm->vcpu.arch.dr6;
pr_debug("Virtual Machine Save Area (VMSA):\n");
- print_hex_dump(KERN_CONT, "", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
+ print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, save, sizeof(*save), false);
return 0;
}
@@ -2600,7 +2600,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm)
void pre_sev_run(struct vcpu_svm *svm, int cpu)
{
- struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
int asid = sev_get_asid(svm->vcpu.kvm);
/* Assign the asid allocated with this SEV guest */
@@ -2648,7 +2648,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len)
ghcb_scratch_beg = control->ghcb_gpa +
offsetof(struct ghcb, shared_buffer);
ghcb_scratch_end = control->ghcb_gpa +
- offsetof(struct ghcb, reserved_1);
+ offsetof(struct ghcb, reserved_0xff0);
/*
* If the scratch area begins within the GHCB, it must be
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 58f0077d9357..91352d692845 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -6,6 +6,7 @@
#include "mmu.h"
#include "kvm_cache_regs.h"
#include "x86.h"
+#include "smm.h"
#include "cpuid.h"
#include "pmu.h"
@@ -245,7 +246,7 @@ struct kvm_ldttss_desc {
u32 zero1;
} __attribute__((packed));
-DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
+DEFINE_PER_CPU(struct svm_cpu_data, svm_data);
/*
* Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via
@@ -346,12 +347,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
return 0;
}
-static int is_external_interrupt(u32 info)
-{
- info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID;
- return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR);
-}
-
static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -581,12 +576,7 @@ static int svm_hardware_enable(void)
pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me);
return -EINVAL;
}
- sd = per_cpu(svm_data, me);
- if (!sd) {
- pr_err("%s: svm_data is NULL on %d\n", __func__, me);
- return -EINVAL;
- }
-
+ sd = per_cpu_ptr(&svm_data, me);
sd->asid_generation = 1;
sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
sd->next_asid = sd->max_asid + 1;
@@ -597,7 +587,7 @@ static int svm_hardware_enable(void)
wrmsrl(MSR_EFER, efer | EFER_SVME);
- wrmsrl(MSR_VM_HSAVE_PA, __sme_page_pa(sd->save_area));
+ wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa);
if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
/*
@@ -646,42 +636,37 @@ static int svm_hardware_enable(void)
static void svm_cpu_uninit(int cpu)
{
- struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
- if (!sd)
+ if (!sd->save_area)
return;
- per_cpu(svm_data, cpu) = NULL;
kfree(sd->sev_vmcbs);
__free_page(sd->save_area);
- kfree(sd);
+ sd->save_area_pa = 0;
+ sd->save_area = NULL;
}
static int svm_cpu_init(int cpu)
{
- struct svm_cpu_data *sd;
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
int ret = -ENOMEM;
- sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
- if (!sd)
- return ret;
- sd->cpu = cpu;
+ memset(sd, 0, sizeof(struct svm_cpu_data));
sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!sd->save_area)
- goto free_cpu_data;
+ return ret;
ret = sev_cpu_init(sd);
if (ret)
goto free_save_area;
- per_cpu(svm_data, cpu) = sd;
-
+ sd->save_area_pa = __sme_page_pa(sd->save_area);
return 0;
free_save_area:
__free_page(sd->save_area);
-free_cpu_data:
- kfree(sd);
+ sd->save_area = NULL;
return ret;
}
@@ -730,6 +715,15 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
u32 offset;
u32 *msrpm;
+ /*
+ * For non-nested case:
+ * If the L01 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ *
+ * For nested case:
+ * If the L02 MSR bitmap does not intercept the MSR, then we need to
+ * save it.
+ */
msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
to_svm(vcpu)->msrpm;
@@ -1425,7 +1419,7 @@ static void svm_clear_current_vmcb(struct vmcb *vmcb)
int i;
for_each_online_cpu(i)
- cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL);
+ cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL);
}
static void svm_vcpu_free(struct kvm_vcpu *vcpu)
@@ -1439,6 +1433,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
*/
svm_clear_current_vmcb(svm->vmcb);
+ svm_leave_nested(vcpu);
svm_free_nested(svm);
sev_free_vcpu(vcpu);
@@ -1450,7 +1445,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
if (sev_es_guest(vcpu->kvm))
sev_es_unmap_ghcb(svm);
@@ -1462,7 +1457,7 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
* Save additional host state that will be restored on VMEXIT (sev-es)
* or subsequent vmload of host save area.
*/
- vmsave(__sme_page_pa(sd->save_area));
+ vmsave(sd->save_area_pa);
if (sev_es_guest(vcpu->kvm)) {
struct sev_es_save_area *hostsa;
hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
@@ -1487,7 +1482,7 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
if (sd->current_vmcb != svm->vmcb) {
sd->current_vmcb = svm->vmcb;
@@ -2714,8 +2709,6 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr)
if (boot_cpu_has(X86_FEATURE_LFENCE_RDTSC))
msr->data |= MSR_F10H_DECFG_LFENCE_SERIALIZE;
break;
- case MSR_IA32_PERF_CAPABILITIES:
- return 0;
default:
return KVM_MSR_RET_INVALID;
}
@@ -3426,15 +3419,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
return 0;
}
- if (is_external_interrupt(svm->vmcb->control.exit_int_info) &&
- exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR &&
- exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH &&
- exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI)
- printk(KERN_ERR "%s: unexpected exit_int_info 0x%x "
- "exit_code 0x%x\n",
- __func__, svm->vmcb->control.exit_int_info,
- exit_code);
-
if (exit_fastpath != EXIT_FASTPATH_NONE)
return 1;
@@ -3443,7 +3427,7 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
static void reload_tss(struct kvm_vcpu *vcpu)
{
- struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
sd->tss_desc->type = 9; /* available 32/64-bit TSS */
load_TR_desc();
@@ -3451,7 +3435,7 @@ static void reload_tss(struct kvm_vcpu *vcpu)
static void pre_svm_run(struct kvm_vcpu *vcpu)
{
- struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
+ struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu);
struct vcpu_svm *svm = to_svm(vcpu);
/*
@@ -3739,6 +3723,13 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
/*
+ * Unlike VMX, SVM doesn't provide a way to flush only NPT TLB entries.
+ * A TLB flush for the current ASID flushes both "host" and "guest" TLB
+ * entries, and thus is a superset of Hyper-V's fine grained flushing.
+ */
+ kvm_hv_vcpu_purge_flush_tlb(vcpu);
+
+ /*
* Flush only the current ASID even if the TLB flush was invoked via
* kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all
* ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and
@@ -3911,30 +3902,16 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
return EXIT_FASTPATH_NONE;
}
-static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted)
{
struct vcpu_svm *svm = to_svm(vcpu);
- unsigned long vmcb_pa = svm->current_vmcb->pa;
guest_state_enter_irqoff();
- if (sev_es_guest(vcpu->kvm)) {
- __svm_sev_es_vcpu_run(vmcb_pa);
- } else {
- struct svm_cpu_data *sd = per_cpu(svm_data, vcpu->cpu);
-
- /*
- * Use a single vmcb (vmcb01 because it's always valid) for
- * context switching guest state via VMLOAD/VMSAVE, that way
- * the state doesn't need to be copied between vmcb01 and
- * vmcb02 when switching vmcbs for nested virtualization.
- */
- vmload(svm->vmcb01.pa);
- __svm_vcpu_run(vmcb_pa, (unsigned long *)&vcpu->arch.regs);
- vmsave(svm->vmcb01.pa);
-
- vmload(__sme_page_pa(sd->save_area));
- }
+ if (sev_es_guest(vcpu->kvm))
+ __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted);
+ else
+ __svm_vcpu_run(svm, spec_ctrl_intercepted);
guest_state_exit_irqoff();
}
@@ -3942,6 +3919,7 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu)
static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
trace_kvm_entry(vcpu);
@@ -3998,34 +3976,15 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
* being speculatively taken.
*/
if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL))
- x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
+ x86_spec_ctrl_set_guest(svm->virt_spec_ctrl);
- svm_vcpu_enter_exit(vcpu);
-
- /*
- * We do not use IBRS in the kernel. If this vCPU has used the
- * SPEC_CTRL MSR it may have left it on; save the value and
- * turn it off. This is much more efficient than blindly adding
- * it to the atomic save/restore list. Especially as the former
- * (Saving guest MSRs on vmexit) doesn't even exist in KVM.
- *
- * For non-nested case:
- * If the L01 MSR bitmap does not intercept the MSR, then we need to
- * save it.
- *
- * For nested case:
- * If the L02 MSR bitmap does not intercept the MSR, then we need to
- * save it.
- */
- if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL) &&
- unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL)))
- svm->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL);
+ svm_vcpu_enter_exit(vcpu, spec_ctrl_intercepted);
if (!sev_es_guest(vcpu->kvm))
reload_tss(vcpu);
if (!static_cpu_has(X86_FEATURE_V_SPEC_CTRL))
- x86_spec_ctrl_restore_host(svm->spec_ctrl, svm->virt_spec_ctrl);
+ x86_spec_ctrl_restore_host(svm->virt_spec_ctrl);
if (!sev_es_guest(vcpu->kvm)) {
vcpu->arch.cr2 = svm->vmcb->save.cr2;
@@ -4149,6 +4108,8 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
return false;
case MSR_IA32_SMBASE:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ return false;
/* SEV-ES guests do not support SMM, so report false */
if (kvm && sev_es_guest(kvm))
return false;
@@ -4405,6 +4366,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu)
vcpu->arch.mcg_cap &= 0x1ff;
}
+#ifdef CONFIG_KVM_SMM
bool svm_smi_blocked(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -4432,7 +4394,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return 1;
}
-static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map_save;
@@ -4441,10 +4403,16 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
if (!is_guest_mode(vcpu))
return 0;
- /* FED8h - SVM Guest */
- put_smstate(u64, smstate, 0x7ed8, 1);
- /* FEE0h - SVM Guest VMCB Physical Address */
- put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+ /*
+ * 32-bit SMRAM format doesn't preserve EFER and SVM state. Userspace is
+ * responsible for ensuring nested SVM and SMIs are mutually exclusive.
+ */
+
+ if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ return 1;
+
+ smram->smram64.svm_guest_flag = 1;
+ smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
@@ -4466,8 +4434,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
* that, see svm_prepare_switch_to_guest()) which must be
* preserved.
*/
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
- &map_save) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save))
return 1;
BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
@@ -4479,34 +4446,33 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct kvm_host_map map, map_save;
- u64 saved_efer, vmcb12_gpa;
struct vmcb *vmcb12;
int ret;
+ const struct kvm_smram_state_64 *smram64 = &smram->smram64;
+
if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
return 0;
/* Non-zero if SMI arrived while vCPU was in guest mode. */
- if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+ if (!smram64->svm_guest_flag)
return 0;
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
return 1;
- saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
- if (!(saved_efer & EFER_SVME))
+ if (!(smram64->efer & EFER_SVME))
return 1;
- vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram64->svm_guest_vmcb_gpa), &map))
return 1;
ret = 1;
- if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL)
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save))
goto unmap_map;
if (svm_allocate_nested(svm))
@@ -4528,7 +4494,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
vmcb12 = map.hva;
nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+ ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false);
if (ret)
goto unmap_save;
@@ -4554,6 +4520,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu)
/* We must be in SMM; RSM will cause a vmexit anyway. */
}
}
+#endif
static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
void *insn, int insn_len)
@@ -4829,10 +4796,12 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.pi_update_irte = avic_pi_update_irte,
.setup_mce = svm_setup_mce,
+#ifdef CONFIG_KVM_SMM
.smi_allowed = svm_smi_allowed,
.enter_smm = svm_enter_smm,
.leave_smm = svm_leave_smm,
.enable_smi_window = svm_enable_smi_window,
+#endif
.mem_enc_ioctl = sev_mem_enc_ioctl,
.mem_enc_register_region = sev_mem_enc_register_region,
@@ -4898,6 +4867,7 @@ static __init void svm_set_cpu_caps(void)
{
kvm_set_cpu_caps();
+ kvm_caps.supported_perf_cap = 0;
kvm_caps.supported_xss = 0;
/* CPUID 0x80000001 and 0x8000000A (SVM features) */
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 6a7686bf6900..4826e6cc611b 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -151,7 +151,10 @@ struct vmcb_ctrl_area_cached {
u64 nested_cr3;
u64 virt_ext;
u32 clean;
- u8 reserved_sw[32];
+ union {
+ struct hv_vmcb_enlightenments hv_enlightenments;
+ u8 reserved_sw[32];
+ };
};
struct svm_nested_state {
@@ -209,7 +212,6 @@ struct vcpu_svm {
struct vmcb *vmcb;
struct kvm_vmcb_info vmcb01;
struct kvm_vmcb_info *current_vmcb;
- struct svm_cpu_data *svm_data;
u32 asid;
u32 sysenter_esp_hi;
u32 sysenter_eip_hi;
@@ -281,8 +283,6 @@ struct vcpu_svm {
};
struct svm_cpu_data {
- int cpu;
-
u64 asid_generation;
u32 max_asid;
u32 next_asid;
@@ -290,13 +290,15 @@ struct svm_cpu_data {
struct kvm_ldttss_desc *tss_desc;
struct page *save_area;
+ unsigned long save_area_pa;
+
struct vmcb *current_vmcb;
/* index = sev_asid, value = vmcb pointer */
struct vmcb **sev_vmcbs;
};
-DECLARE_PER_CPU(struct svm_cpu_data *, svm_data);
+DECLARE_PER_CPU(struct svm_cpu_data, svm_data);
void recalc_intercepts(struct vcpu_svm *svm);
@@ -683,7 +685,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm);
/* vmenter.S */
-void __svm_sev_es_vcpu_run(unsigned long vmcb_pa);
-void __svm_vcpu_run(unsigned long vmcb_pa, unsigned long *regs);
+void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
+void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted);
#endif
diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c
index 8cdc62c74a96..26a89d0da93e 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.c
+++ b/arch/x86/kvm/svm/svm_onhyperv.c
@@ -14,9 +14,9 @@
#include "kvm_onhyperv.h"
#include "svm_onhyperv.h"
-int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu)
+int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
{
- struct hv_enlightenments *hve;
+ struct hv_vmcb_enlightenments *hve;
struct hv_partition_assist_pg **p_hv_pa_pg =
&to_kvm_hv(vcpu->kvm)->hv_pa_pg;
@@ -26,13 +26,13 @@ int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu)
if (!*p_hv_pa_pg)
return -ENOMEM;
- hve = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw;
+ hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
hve->partition_assist_page = __pa(*p_hv_pa_pg);
hve->hv_vm_id = (unsigned long)vcpu->kvm;
if (!hve->hv_enlightenments_control.nested_flush_hypercall) {
hve->hv_enlightenments_control.nested_flush_hypercall = 1;
- vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
+ vmcb_mark_dirty(to_svm(vcpu)->vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
}
return 0;
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index e2fc59380465..45faf84476ce 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -13,12 +13,14 @@
static struct kvm_x86_ops svm_x86_ops;
-int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu);
+int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu);
static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
{
- struct hv_enlightenments *hve =
- (struct hv_enlightenments *)vmcb->control.reserved_sw;
+ struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
+
+ BUILD_BUG_ON(sizeof(vmcb->control.hv_enlightenments) !=
+ sizeof(vmcb->control.reserved_sw));
if (npt_enabled &&
ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB)
@@ -51,8 +53,8 @@ static inline void svm_hv_hardware_setup(void)
vp_ap->nested_control.features.directhypercall = 1;
}
- svm_x86_ops.enable_direct_tlbflush =
- svm_hv_enable_direct_tlbflush;
+ svm_x86_ops.enable_l2_tlb_flush =
+ svm_hv_enable_l2_tlb_flush;
}
}
@@ -60,23 +62,20 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments(
struct kvm_vcpu *vcpu)
{
struct vmcb *vmcb = to_svm(vcpu)->vmcb;
- struct hv_enlightenments *hve =
- (struct hv_enlightenments *)vmcb->control.reserved_sw;
+ struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
if (hve->hv_enlightenments_control.msr_bitmap)
- vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
+ vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
}
-static inline void svm_hv_update_vp_id(struct vmcb *vmcb,
- struct kvm_vcpu *vcpu)
+static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu)
{
- struct hv_enlightenments *hve =
- (struct hv_enlightenments *)vmcb->control.reserved_sw;
+ struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
u32 vp_index = kvm_hv_get_vpindex(vcpu);
if (hve->hv_vp_id != vp_index) {
hve->hv_vp_id = vp_index;
- vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS);
+ vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS);
}
}
#else
diff --git a/arch/x86/kvm/svm/svm_ops.h b/arch/x86/kvm/svm/svm_ops.h
index 9430d6437c9f..36c8af87a707 100644
--- a/arch/x86/kvm/svm/svm_ops.h
+++ b/arch/x86/kvm/svm/svm_ops.h
@@ -61,9 +61,4 @@ static __always_inline void vmsave(unsigned long pa)
svm_asm1(vmsave, "a" (pa), "memory");
}
-static __always_inline void vmload(unsigned long pa)
-{
- svm_asm1(vmload, "a" (pa), "memory");
-}
-
#endif /* __KVM_X86_SVM_OPS_H */
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 723f8534986c..34367dc203f2 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -4,35 +4,97 @@
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/nospec-branch.h>
+#include "kvm-asm-offsets.h"
#define WORD_SIZE (BITS_PER_LONG / 8)
/* Intentionally omit RAX as it's context switched by hardware */
-#define VCPU_RCX __VCPU_REGS_RCX * WORD_SIZE
-#define VCPU_RDX __VCPU_REGS_RDX * WORD_SIZE
-#define VCPU_RBX __VCPU_REGS_RBX * WORD_SIZE
+#define VCPU_RCX (SVM_vcpu_arch_regs + __VCPU_REGS_RCX * WORD_SIZE)
+#define VCPU_RDX (SVM_vcpu_arch_regs + __VCPU_REGS_RDX * WORD_SIZE)
+#define VCPU_RBX (SVM_vcpu_arch_regs + __VCPU_REGS_RBX * WORD_SIZE)
/* Intentionally omit RSP as it's context switched by hardware */
-#define VCPU_RBP __VCPU_REGS_RBP * WORD_SIZE
-#define VCPU_RSI __VCPU_REGS_RSI * WORD_SIZE
-#define VCPU_RDI __VCPU_REGS_RDI * WORD_SIZE
+#define VCPU_RBP (SVM_vcpu_arch_regs + __VCPU_REGS_RBP * WORD_SIZE)
+#define VCPU_RSI (SVM_vcpu_arch_regs + __VCPU_REGS_RSI * WORD_SIZE)
+#define VCPU_RDI (SVM_vcpu_arch_regs + __VCPU_REGS_RDI * WORD_SIZE)
#ifdef CONFIG_X86_64
-#define VCPU_R8 __VCPU_REGS_R8 * WORD_SIZE
-#define VCPU_R9 __VCPU_REGS_R9 * WORD_SIZE
-#define VCPU_R10 __VCPU_REGS_R10 * WORD_SIZE
-#define VCPU_R11 __VCPU_REGS_R11 * WORD_SIZE
-#define VCPU_R12 __VCPU_REGS_R12 * WORD_SIZE
-#define VCPU_R13 __VCPU_REGS_R13 * WORD_SIZE
-#define VCPU_R14 __VCPU_REGS_R14 * WORD_SIZE
-#define VCPU_R15 __VCPU_REGS_R15 * WORD_SIZE
+#define VCPU_R8 (SVM_vcpu_arch_regs + __VCPU_REGS_R8 * WORD_SIZE)
+#define VCPU_R9 (SVM_vcpu_arch_regs + __VCPU_REGS_R9 * WORD_SIZE)
+#define VCPU_R10 (SVM_vcpu_arch_regs + __VCPU_REGS_R10 * WORD_SIZE)
+#define VCPU_R11 (SVM_vcpu_arch_regs + __VCPU_REGS_R11 * WORD_SIZE)
+#define VCPU_R12 (SVM_vcpu_arch_regs + __VCPU_REGS_R12 * WORD_SIZE)
+#define VCPU_R13 (SVM_vcpu_arch_regs + __VCPU_REGS_R13 * WORD_SIZE)
+#define VCPU_R14 (SVM_vcpu_arch_regs + __VCPU_REGS_R14 * WORD_SIZE)
+#define VCPU_R15 (SVM_vcpu_arch_regs + __VCPU_REGS_R15 * WORD_SIZE)
#endif
+#define SVM_vmcb01_pa (SVM_vmcb01 + KVM_VMCB_pa)
+
.section .noinstr.text, "ax"
+.macro RESTORE_GUEST_SPEC_CTRL
+ /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
+ ALTERNATIVE_2 "", \
+ "jmp 800f", X86_FEATURE_MSR_SPEC_CTRL, \
+ "", X86_FEATURE_V_SPEC_CTRL
+801:
+.endm
+.macro RESTORE_GUEST_SPEC_CTRL_BODY
+800:
+ /*
+ * SPEC_CTRL handling: if the guest's SPEC_CTRL value differs from the
+ * host's, write the MSR. This is kept out-of-line so that the common
+ * case does not have to jump.
+ *
+ * IMPORTANT: To avoid RSB underflow attacks and any other nastiness,
+ * there must not be any returns or indirect branches between this code
+ * and vmentry.
+ */
+ movl SVM_spec_ctrl(%_ASM_DI), %eax
+ cmp PER_CPU_VAR(x86_spec_ctrl_current), %eax
+ je 801b
+ mov $MSR_IA32_SPEC_CTRL, %ecx
+ xor %edx, %edx
+ wrmsr
+ jmp 801b
+.endm
+
+.macro RESTORE_HOST_SPEC_CTRL
+ /* No need to do anything if SPEC_CTRL is unset or V_SPEC_CTRL is set */
+ ALTERNATIVE_2 "", \
+ "jmp 900f", X86_FEATURE_MSR_SPEC_CTRL, \
+ "", X86_FEATURE_V_SPEC_CTRL
+901:
+.endm
+.macro RESTORE_HOST_SPEC_CTRL_BODY
+900:
+ /* Same for after vmexit. */
+ mov $MSR_IA32_SPEC_CTRL, %ecx
+
+ /*
+ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL,
+ * if it was not intercepted during guest execution.
+ */
+ cmpb $0, (%_ASM_SP)
+ jnz 998f
+ rdmsr
+ movl %eax, SVM_spec_ctrl(%_ASM_DI)
+998:
+
+ /* Now restore the host value of the MSR if different from the guest's. */
+ movl PER_CPU_VAR(x86_spec_ctrl_current), %eax
+ cmp SVM_spec_ctrl(%_ASM_DI), %eax
+ je 901b
+ xor %edx, %edx
+ wrmsr
+ jmp 901b
+.endm
+
+
/**
* __svm_vcpu_run - Run a vCPU via a transition to SVM guest mode
- * @vmcb_pa: unsigned long
- * @regs: unsigned long * (to guest registers)
+ * @svm: struct vcpu_svm *
+ * @spec_ctrl_intercepted: bool
*/
SYM_FUNC_START(__svm_vcpu_run)
push %_ASM_BP
@@ -47,49 +109,71 @@ SYM_FUNC_START(__svm_vcpu_run)
#endif
push %_ASM_BX
- /* Save @regs. */
+ /*
+ * Save variables needed after vmexit on the stack, in inverse
+ * order compared to when they are needed.
+ */
+
+ /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */
push %_ASM_ARG2
- /* Save @vmcb. */
+ /* Needed to restore access to percpu variables. */
+ __ASM_SIZE(push) PER_CPU_VAR(svm_data + SD_save_area_pa)
+
+ /* Finally save @svm. */
push %_ASM_ARG1
- /* Move @regs to RAX. */
- mov %_ASM_ARG2, %_ASM_AX
+.ifnc _ASM_ARG1, _ASM_DI
+ /*
+ * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
+ * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
+ */
+ mov %_ASM_ARG1, %_ASM_DI
+.endif
+
+ /* Clobbers RAX, RCX, RDX. */
+ RESTORE_GUEST_SPEC_CTRL
+
+ /*
+ * Use a single vmcb (vmcb01 because it's always valid) for
+ * context switching guest state via VMLOAD/VMSAVE, that way
+ * the state doesn't need to be copied between vmcb01 and
+ * vmcb02 when switching vmcbs for nested virtualization.
+ */
+ mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+1: vmload %_ASM_AX
+2:
+
+ /* Get svm->current_vmcb->pa into RAX. */
+ mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
+ mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
/* Load guest registers. */
- mov VCPU_RCX(%_ASM_AX), %_ASM_CX
- mov VCPU_RDX(%_ASM_AX), %_ASM_DX
- mov VCPU_RBX(%_ASM_AX), %_ASM_BX
- mov VCPU_RBP(%_ASM_AX), %_ASM_BP
- mov VCPU_RSI(%_ASM_AX), %_ASM_SI
- mov VCPU_RDI(%_ASM_AX), %_ASM_DI
+ mov VCPU_RCX(%_ASM_DI), %_ASM_CX
+ mov VCPU_RDX(%_ASM_DI), %_ASM_DX
+ mov VCPU_RBX(%_ASM_DI), %_ASM_BX
+ mov VCPU_RBP(%_ASM_DI), %_ASM_BP
+ mov VCPU_RSI(%_ASM_DI), %_ASM_SI
#ifdef CONFIG_X86_64
- mov VCPU_R8 (%_ASM_AX), %r8
- mov VCPU_R9 (%_ASM_AX), %r9
- mov VCPU_R10(%_ASM_AX), %r10
- mov VCPU_R11(%_ASM_AX), %r11
- mov VCPU_R12(%_ASM_AX), %r12
- mov VCPU_R13(%_ASM_AX), %r13
- mov VCPU_R14(%_ASM_AX), %r14
- mov VCPU_R15(%_ASM_AX), %r15
+ mov VCPU_R8 (%_ASM_DI), %r8
+ mov VCPU_R9 (%_ASM_DI), %r9
+ mov VCPU_R10(%_ASM_DI), %r10
+ mov VCPU_R11(%_ASM_DI), %r11
+ mov VCPU_R12(%_ASM_DI), %r12
+ mov VCPU_R13(%_ASM_DI), %r13
+ mov VCPU_R14(%_ASM_DI), %r14
+ mov VCPU_R15(%_ASM_DI), %r15
#endif
-
- /* "POP" @vmcb to RAX. */
- pop %_ASM_AX
+ mov VCPU_RDI(%_ASM_DI), %_ASM_DI
/* Enter guest mode */
sti
-1: vmrun %_ASM_AX
-
-2: cli
-
-#ifdef CONFIG_RETPOLINE
- /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
- FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
-#endif
+3: vmrun %_ASM_AX
+4:
+ cli
- /* "POP" @regs to RAX. */
+ /* Pop @svm to RAX while it's the only available register. */
pop %_ASM_AX
/* Save all guest registers. */
@@ -110,6 +194,26 @@ SYM_FUNC_START(__svm_vcpu_run)
mov %r15, VCPU_R15(%_ASM_AX)
#endif
+ /* @svm can stay in RDI from now on. */
+ mov %_ASM_AX, %_ASM_DI
+
+ mov SVM_vmcb01_pa(%_ASM_DI), %_ASM_AX
+5: vmsave %_ASM_AX
+6:
+
+ /* Restores GSBASE among other things, allowing access to percpu data. */
+ pop %_ASM_AX
+7: vmload %_ASM_AX
+8:
+
+#ifdef CONFIG_RETPOLINE
+ /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
+ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
+#endif
+
+ /* Clobbers RAX, RCX, RDX. */
+ RESTORE_HOST_SPEC_CTRL
+
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
* untrained as soon as we exit the VM and are back to the
@@ -145,6 +249,9 @@ SYM_FUNC_START(__svm_vcpu_run)
xor %r15d, %r15d
#endif
+ /* "Pop" @spec_ctrl_intercepted. */
+ pop %_ASM_BX
+
pop %_ASM_BX
#ifdef CONFIG_X86_64
@@ -159,17 +266,33 @@ SYM_FUNC_START(__svm_vcpu_run)
pop %_ASM_BP
RET
-3: cmpb $0, kvm_rebooting
+ RESTORE_GUEST_SPEC_CTRL_BODY
+ RESTORE_HOST_SPEC_CTRL_BODY
+
+10: cmpb $0, kvm_rebooting
jne 2b
ud2
+30: cmpb $0, kvm_rebooting
+ jne 4b
+ ud2
+50: cmpb $0, kvm_rebooting
+ jne 6b
+ ud2
+70: cmpb $0, kvm_rebooting
+ jne 8b
+ ud2
- _ASM_EXTABLE(1b, 3b)
+ _ASM_EXTABLE(1b, 10b)
+ _ASM_EXTABLE(3b, 30b)
+ _ASM_EXTABLE(5b, 50b)
+ _ASM_EXTABLE(7b, 70b)
SYM_FUNC_END(__svm_vcpu_run)
/**
* __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode
- * @vmcb_pa: unsigned long
+ * @svm: struct vcpu_svm *
+ * @spec_ctrl_intercepted: bool
*/
SYM_FUNC_START(__svm_sev_es_vcpu_run)
push %_ASM_BP
@@ -184,8 +307,31 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
#endif
push %_ASM_BX
- /* Move @vmcb to RAX. */
- mov %_ASM_ARG1, %_ASM_AX
+ /*
+ * Save variables needed after vmexit on the stack, in inverse
+ * order compared to when they are needed.
+ */
+
+ /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */
+ push %_ASM_ARG2
+
+ /* Save @svm. */
+ push %_ASM_ARG1
+
+.ifnc _ASM_ARG1, _ASM_DI
+ /*
+ * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX
+ * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL.
+ */
+ mov %_ASM_ARG1, %_ASM_DI
+.endif
+
+ /* Clobbers RAX, RCX, RDX. */
+ RESTORE_GUEST_SPEC_CTRL
+
+ /* Get svm->current_vmcb->pa into RAX. */
+ mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX
+ mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX
/* Enter guest mode */
sti
@@ -194,11 +340,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
2: cli
+ /* Pop @svm to RDI, guest registers have been saved already. */
+ pop %_ASM_DI
+
#ifdef CONFIG_RETPOLINE
/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE
#endif
+ /* Clobbers RAX, RCX, RDX. */
+ RESTORE_HOST_SPEC_CTRL
+
/*
* Mitigate RETBleed for AMD/Hygon Zen uarch. RET should be
* untrained as soon as we exit the VM and are back to the
@@ -208,6 +360,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
*/
UNTRAIN_RET
+ /* "Pop" @spec_ctrl_intercepted. */
+ pop %_ASM_BX
+
pop %_ASM_BX
#ifdef CONFIG_X86_64
@@ -222,6 +377,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
pop %_ASM_BP
RET
+ RESTORE_GUEST_SPEC_CTRL_BODY
+ RESTORE_HOST_SPEC_CTRL_BODY
+
3: cmpb $0, kvm_rebooting
jne 2b
ud2
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index bc25589ad588..83843379813e 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -113,12 +113,13 @@ TRACE_EVENT(kvm_hv_hypercall_done,
* Tracepoint for Xen hypercall.
*/
TRACE_EVENT(kvm_xen_hypercall,
- TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1,
- unsigned long a2, unsigned long a3, unsigned long a4,
- unsigned long a5),
- TP_ARGS(nr, a0, a1, a2, a3, a4, a5),
+ TP_PROTO(u8 cpl, unsigned long nr,
+ unsigned long a0, unsigned long a1, unsigned long a2,
+ unsigned long a3, unsigned long a4, unsigned long a5),
+ TP_ARGS(cpl, nr, a0, a1, a2, a3, a4, a5),
TP_STRUCT__entry(
+ __field(u8, cpl)
__field(unsigned long, nr)
__field(unsigned long, a0)
__field(unsigned long, a1)
@@ -129,6 +130,7 @@ TRACE_EVENT(kvm_xen_hypercall,
),
TP_fast_assign(
+ __entry->cpl = cpl;
__entry->nr = nr;
__entry->a0 = a0;
__entry->a1 = a1;
@@ -138,8 +140,9 @@ TRACE_EVENT(kvm_xen_hypercall,
__entry->a4 = a5;
),
- TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx",
- __entry->nr, __entry->a0, __entry->a1, __entry->a2,
+ TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx",
+ __entry->cpl, __entry->nr,
+ __entry->a0, __entry->a1, __entry->a2,
__entry->a3, __entry->a4, __entry->a5)
);
@@ -1547,38 +1550,41 @@ TRACE_EVENT(kvm_hv_timer_state,
* Tracepoint for kvm_hv_flush_tlb.
*/
TRACE_EVENT(kvm_hv_flush_tlb,
- TP_PROTO(u64 processor_mask, u64 address_space, u64 flags),
- TP_ARGS(processor_mask, address_space, flags),
+ TP_PROTO(u64 processor_mask, u64 address_space, u64 flags, bool guest_mode),
+ TP_ARGS(processor_mask, address_space, flags, guest_mode),
TP_STRUCT__entry(
__field(u64, processor_mask)
__field(u64, address_space)
__field(u64, flags)
+ __field(bool, guest_mode)
),
TP_fast_assign(
__entry->processor_mask = processor_mask;
__entry->address_space = address_space;
__entry->flags = flags;
+ __entry->guest_mode = guest_mode;
),
- TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx",
+ TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx %s",
__entry->processor_mask, __entry->address_space,
- __entry->flags)
+ __entry->flags, __entry->guest_mode ? "(L2)" : "")
);
/*
* Tracepoint for kvm_hv_flush_tlb_ex.
*/
TRACE_EVENT(kvm_hv_flush_tlb_ex,
- TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags),
- TP_ARGS(valid_bank_mask, format, address_space, flags),
+ TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags, bool guest_mode),
+ TP_ARGS(valid_bank_mask, format, address_space, flags, guest_mode),
TP_STRUCT__entry(
__field(u64, valid_bank_mask)
__field(u64, format)
__field(u64, address_space)
__field(u64, flags)
+ __field(bool, guest_mode)
),
TP_fast_assign(
@@ -1586,12 +1592,14 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex,
__entry->format = format;
__entry->address_space = address_space;
__entry->flags = flags;
+ __entry->guest_mode = guest_mode;
),
TP_printk("valid_bank_mask 0x%llx format 0x%llx "
- "address_space 0x%llx flags 0x%llx",
+ "address_space 0x%llx flags 0x%llx %s",
__entry->valid_bank_mask, __entry->format,
- __entry->address_space, __entry->flags)
+ __entry->address_space, __entry->flags,
+ __entry->guest_mode ? "(L2)" : "")
);
/*
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 87c4e46daf37..cd2ac9536c99 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -24,8 +24,6 @@ extern int __read_mostly pt_mode;
#define PMU_CAP_FW_WRITES (1ULL << 13)
#define PMU_CAP_LBR_FMT 0x3f
-#define DEBUGCTLMSR_LBR_MASK (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI)
-
struct nested_vmx_msrs {
/*
* We only store the "true" versions of the VMX capability MSRs. We
@@ -397,41 +395,6 @@ static inline bool vmx_pebs_supported(void)
return boot_cpu_has(X86_FEATURE_PEBS) && kvm_pmu_cap.pebs_ept;
}
-static inline u64 vmx_get_perf_capabilities(void)
-{
- u64 perf_cap = PMU_CAP_FW_WRITES;
- u64 host_perf_cap = 0;
-
- if (!enable_pmu)
- return 0;
-
- if (boot_cpu_has(X86_FEATURE_PDCM))
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
-
- perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
-
- if (vmx_pebs_supported()) {
- perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
- if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
- perf_cap &= ~PERF_CAP_PEBS_BASELINE;
- }
-
- return perf_cap;
-}
-
-static inline u64 vmx_supported_debugctl(void)
-{
- u64 debugctl = 0;
-
- if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
- debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
-
- if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
- debugctl |= DEBUGCTLMSR_LBR_MASK;
-
- return debugctl;
-}
-
static inline bool cpu_has_notify_vmexit(void)
{
return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/hyperv.c
index d8b23c96d627..ae03d1fe0355 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/hyperv.c
@@ -3,9 +3,9 @@
#include <linux/errno.h>
#include <linux/smp.h>
-#include "../hyperv.h"
#include "../cpuid.h"
-#include "evmcs.h"
+#include "hyperv.h"
+#include "nested.h"
#include "vmcs.h"
#include "vmx.h"
#include "trace.h"
@@ -322,24 +322,17 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = {
};
const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1);
-bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa)
+u64 nested_get_evmptr(struct kvm_vcpu *vcpu)
{
- struct hv_vp_assist_page assist_page;
-
- *evmcs_gpa = -1ull;
-
- if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page)))
- return false;
-
- if (unlikely(!assist_page.enlighten_vmentry))
- return false;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
- if (unlikely(!evmptr_is_valid(assist_page.current_nested_vmcs)))
- return false;
+ if (unlikely(kvm_hv_get_assist_page(vcpu)))
+ return EVMPTR_INVALID;
- *evmcs_gpa = assist_page.current_nested_vmcs;
+ if (unlikely(!hv_vcpu->vp_assist_page.enlighten_vmentry))
+ return EVMPTR_INVALID;
- return true;
+ return hv_vcpu->vp_assist_page.current_nested_vmcs;
}
uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
@@ -507,3 +500,23 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
return 0;
}
+
+bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+
+ if (!hv_vcpu || !evmcs)
+ return false;
+
+ if (!evmcs->hv_enlightenments_control.nested_flush_hypercall)
+ return false;
+
+ return hv_vcpu->vp_assist_page.nested_control.features.directhypercall;
+}
+
+void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu)
+{
+ nested_vmx_vmexit(vcpu, HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH, 0, 0);
+}
diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/hyperv.h
index 6f746ef3c038..571e7929d14e 100644
--- a/arch/x86/kvm/vmx/evmcs.h
+++ b/arch/x86/kvm/vmx/hyperv.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __KVM_X86_VMX_EVMCS_H
-#define __KVM_X86_VMX_EVMCS_H
+#ifndef __KVM_X86_VMX_HYPERV_H
+#define __KVM_X86_VMX_HYPERV_H
#include <linux/jump_label.h>
@@ -8,6 +8,8 @@
#include <asm/mshyperv.h>
#include <asm/vmx.h>
+#include "../hyperv.h"
+
#include "capabilities.h"
#include "vmcs.h"
#include "vmcs12.h"
@@ -235,11 +237,13 @@ enum nested_evmptrld_status {
EVMPTRLD_ERROR,
};
-bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa);
+u64 nested_get_evmptr(struct kvm_vcpu *vcpu);
uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu);
int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version);
void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
int nested_evmcs_check_controls(struct vmcs12 *vmcs12);
+bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu);
+void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu);
-#endif /* __KVM_X86_VMX_EVMCS_H */
+#endif /* __KVM_X86_VMX_HYPERV_H */
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0c62352dda6a..b28be793de29 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -7,7 +7,6 @@
#include <asm/mmu_context.h>
#include "cpuid.h"
-#include "evmcs.h"
#include "hyperv.h"
#include "mmu.h"
#include "nested.h"
@@ -16,6 +15,7 @@
#include "trace.h"
#include "vmx.h"
#include "x86.h"
+#include "smm.h"
static bool __read_mostly enable_shadow_vmcs = 1;
module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
@@ -225,6 +225,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx)
static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
{
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) {
@@ -233,6 +234,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu)
}
vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
+
+ if (hv_vcpu) {
+ hv_vcpu->nested.pa_page_gpa = INVALID_GPA;
+ hv_vcpu->nested.vm_id = 0;
+ hv_vcpu->nested.vp_id = 0;
+ }
}
static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
@@ -1126,6 +1133,15 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
struct vcpu_vmx *vmx = to_vmx(vcpu);
/*
+ * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or
+ * L2's VP_ID upon request from the guest. Make sure we check for
+ * pending entries in the right FIFO upon L1/L2 transition as these
+ * requests are put by other vCPUs asynchronously.
+ */
+ if (to_hv_vcpu(vcpu) && enable_ept)
+ kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu);
+
+ /*
* If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
* for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a
* full TLB flush from the guest's perspective. This is required even
@@ -1557,12 +1573,20 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields
{
struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12;
struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs;
+ struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu);
/* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */
vmcs12->tpr_threshold = evmcs->tpr_threshold;
vmcs12->guest_rip = evmcs->guest_rip;
if (unlikely(!(hv_clean_fields &
+ HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) {
+ hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page;
+ hv_vcpu->nested.vm_id = evmcs->hv_vm_id;
+ hv_vcpu->nested.vp_id = evmcs->hv_vp_id;
+ }
+
+ if (unlikely(!(hv_clean_fields &
HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) {
vmcs12->guest_rsp = evmcs->guest_rsp;
vmcs12->guest_rflags = evmcs->guest_rflags;
@@ -1977,7 +2001,8 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
if (likely(!guest_cpuid_has_evmcs(vcpu)))
return EVMPTRLD_DISABLED;
- if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) {
+ evmcs_gpa = nested_get_evmptr(vcpu);
+ if (!evmptr_is_valid(evmcs_gpa)) {
nested_release_evmcs(vcpu);
return EVMPTRLD_DISABLED;
}
@@ -3251,6 +3276,12 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
+ /*
+ * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy
+ * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory
+ * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post
+ * migration.
+ */
if (!nested_get_evmcs_page(vcpu)) {
pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
__func__);
@@ -4854,6 +4885,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu)
{
+ kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu);
nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
}
@@ -5205,7 +5237,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 zero = 0;
gpa_t vmptr;
- u64 evmcs_gpa;
int r;
if (!nested_vmx_check_permission(vcpu))
@@ -5231,7 +5262,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu)
* vmx->nested.hv_evmcs but this shouldn't be a problem.
*/
if (likely(!guest_cpuid_has_evmcs(vcpu) ||
- !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) {
+ !evmptr_is_valid(nested_get_evmptr(vcpu)))) {
if (vmptr == vmx->nested.current_vmptr)
nested_release_vmcs12(vcpu);
@@ -6128,6 +6159,11 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
* Handle L2's bus locks in L0 directly.
*/
return true;
+ case EXIT_REASON_VMCALL:
+ /* Hyper-V L2 TLB flush hypercall is handled by L0 */
+ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) &&
+ nested_evmcs_l2_tlb_flush_enabled(vcpu) &&
+ kvm_hv_is_tlb_flush_hcall(vcpu);
default:
break;
}
@@ -6440,9 +6476,6 @@ out:
return kvm_state.size;
}
-/*
- * Forcibly leave nested mode in order to be able to reset the VCPU later on.
- */
void vmx_leave_nested(struct kvm_vcpu *vcpu)
{
if (is_guest_mode(vcpu)) {
@@ -6982,4 +7015,5 @@ struct kvm_x86_nested_ops vmx_nested_ops = {
.write_log_dirty = nested_vmx_write_pml_buffer,
.enable_evmcs = nested_enable_evmcs,
.get_evmcs_version = nested_get_evmcs_version,
+ .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush,
};
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 25b70a85bef5..e5cec07ca8d9 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -52,7 +52,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i);
__set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use);
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
}
@@ -76,7 +76,7 @@ static void reprogram_counters(struct kvm_pmu *pmu, u64 diff)
for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) {
pmc = intel_pmc_idx_to_pmc(pmu, bit);
if (pmc)
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
}
}
@@ -477,7 +477,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
reserved_bits ^= HSW_IN_TX_CHECKPOINTED;
if (!(data & reserved_bits)) {
pmc->eventsel = data;
- reprogram_counter(pmc);
+ kvm_pmu_request_counter_reprogam(pmc);
return 0;
}
} else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false))
@@ -617,7 +617,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
- for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+ for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
pmu->gp_counters[i].idx = i;
@@ -631,7 +631,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
pmu->fixed_counters[i].current_config = 0;
}
- vcpu->arch.perf_capabilities = vmx_get_perf_capabilities();
lbr_desc->records.nr = 0;
lbr_desc->event = NULL;
lbr_desc->msr_passthrough = false;
@@ -643,18 +642,18 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
struct kvm_pmc *pmc = NULL;
int i;
- for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
+ for (i = 0; i < KVM_INTEL_PMC_MAX_GENERIC; i++) {
pmc = &pmu->gp_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = pmc->eventsel = 0;
+ pmc->counter = pmc->prev_counter = pmc->eventsel = 0;
}
for (i = 0; i < KVM_PMC_MAX_FIXED; i++) {
pmc = &pmu->fixed_counters[i];
pmc_stop_counter(pmc);
- pmc->counter = 0;
+ pmc->counter = pmc->prev_counter = 0;
}
pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0;
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 746129ddd5ae..01936013428b 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -208,9 +208,8 @@ struct __packed vmcs12 {
/*
* For save/restore compatibility, the vmcs12 field offsets must not change.
*/
-#define CHECK_OFFSET(field, loc) \
- BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \
- "Offset of " #field " in struct vmcs12 has changed.")
+#define CHECK_OFFSET(field, loc) \
+ ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
static inline void vmx_check_vmcs12_offsets(void)
{
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index 8477d8bdd69c..0b5db4de4d09 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -1,12 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
#include <asm/asm.h>
-#include <asm/asm-offsets.h>
#include <asm/bitsperlong.h>
#include <asm/kvm_vcpu_regs.h>
#include <asm/nospec-branch.h>
#include <asm/percpu.h>
#include <asm/segment.h>
+#include "kvm-asm-offsets.h"
#include "run_flags.h"
#define WORD_SIZE (BITS_PER_LONG / 8)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9dba04b6b019..cea8c07f5229 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -51,7 +51,6 @@
#include "capabilities.h"
#include "cpuid.h"
-#include "evmcs.h"
#include "hyperv.h"
#include "kvm_onhyperv.h"
#include "irq.h"
@@ -66,6 +65,7 @@
#include "vmcs12.h"
#include "vmx.h"
#include "x86.h"
+#include "smm.h"
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
@@ -526,7 +526,7 @@ static unsigned long host_idt_base;
static bool __read_mostly enlightened_vmcs = true;
module_param(enlightened_vmcs, bool, 0444);
-static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu)
+static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
{
struct hv_enlightened_vmcs *evmcs;
struct hv_partition_assist_pg **p_hv_pa_pg =
@@ -1849,9 +1849,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
if (!nested)
return 1;
return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
- case MSR_IA32_PERF_CAPABILITIES:
- msr->data = vmx_get_perf_capabilities();
- return 0;
default:
return KVM_MSR_RET_INVALID;
}
@@ -2021,15 +2018,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
+static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
- u64 debugctl = vmx_supported_debugctl();
+ u64 debugctl = 0;
- if (!intel_pmu_lbr_is_enabled(vcpu))
- debugctl &= ~DEBUGCTLMSR_LBR_MASK;
+ if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+ (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
+ debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
- if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
- debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+ if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) &&
+ (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
+ debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
return debugctl;
}
@@ -2103,7 +2102,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
case MSR_IA32_DEBUGCTLMSR: {
- u64 invalid = data & ~vcpu_supported_debugctl(vcpu);
+ u64 invalid;
+
+ invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
if (report_ignored_msrs)
vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n",
@@ -2338,14 +2339,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
if (data & PMU_CAP_LBR_FMT) {
if ((data & PMU_CAP_LBR_FMT) !=
- (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT))
+ (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT))
return 1;
if (!cpuid_model_is_consistent(vcpu))
return 1;
}
if (data & PERF_CAP_PEBS_FORMAT) {
if ((data & PERF_CAP_PEBS_MASK) !=
- (vmx_get_perf_capabilities() & PERF_CAP_PEBS_MASK))
+ (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK))
return 1;
if (!guest_cpuid_has(vcpu, X86_FEATURE_DS))
return 1;
@@ -6840,6 +6841,8 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
{
switch (index) {
case MSR_IA32_SMBASE:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ return false;
/*
* We cannot do SMM unless we can run the guest in big
* real mode.
@@ -7665,6 +7668,31 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vmx_update_exception_bitmap(vcpu);
}
+static u64 vmx_get_perf_capabilities(void)
+{
+ u64 perf_cap = PMU_CAP_FW_WRITES;
+ struct x86_pmu_lbr lbr;
+ u64 host_perf_cap = 0;
+
+ if (!enable_pmu)
+ return 0;
+
+ if (boot_cpu_has(X86_FEATURE_PDCM))
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+
+ x86_perf_get_lbr(&lbr);
+ if (lbr.nr)
+ perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+
+ if (vmx_pebs_supported()) {
+ perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
+ if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
+ perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+ }
+
+ return perf_cap;
+}
+
static __init void vmx_set_cpu_caps(void)
{
kvm_set_cpu_caps();
@@ -7687,6 +7715,7 @@ static __init void vmx_set_cpu_caps(void)
if (!enable_pmu)
kvm_cpu_cap_clear(X86_FEATURE_PDCM);
+ kvm_caps.supported_perf_cap = vmx_get_perf_capabilities();
if (!enable_sgx) {
kvm_cpu_cap_clear(X86_FEATURE_SGX);
@@ -7902,6 +7931,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu)
~FEAT_CTL_LMCE_ENABLED;
}
+#ifdef CONFIG_KVM_SMM
static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
{
/* we need a nested vmexit to enter SMM, postpone if run is pending */
@@ -7910,7 +7940,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
return !is_smm(vcpu);
}
-static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7931,7 +7961,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7956,6 +7986,7 @@ static void vmx_enable_smi_window(struct kvm_vcpu *vcpu)
{
/* RSM will cause a vmexit anyway. */
}
+#endif
static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
{
@@ -8123,10 +8154,12 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
.setup_mce = vmx_setup_mce,
+#ifdef CONFIG_KVM_SMM
.smi_allowed = vmx_smi_allowed,
.enter_smm = vmx_enter_smm,
.leave_smm = vmx_leave_smm,
.enable_smi_window = vmx_enable_smi_window,
+#endif
.can_emulate_instruction = vmx_can_emulate_instruction,
.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
@@ -8263,6 +8296,11 @@ static __init int hardware_setup(void)
if (!cpu_has_virtual_nmis())
enable_vnmi = 0;
+#ifdef CONFIG_X86_SGX_KVM
+ if (!cpu_has_vmx_encls_vmexit())
+ enable_sgx = false;
+#endif
+
/*
* set_apic_access_page_addr() is used to reload apic access
* page upon invalidation. No need to do anything if not
@@ -8481,8 +8519,8 @@ static int __init vmx_init(void)
}
if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH)
- vmx_x86_ops.enable_direct_tlbflush
- = hv_enable_direct_tlbflush;
+ vmx_x86_ops.enable_l2_tlb_flush
+ = hv_enable_l2_tlb_flush;
} else {
enlightened_vmcs = false;
diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h
index ec268df83ed6..f6f23c7397dc 100644
--- a/arch/x86/kvm/vmx/vmx_ops.h
+++ b/arch/x86/kvm/vmx/vmx_ops.h
@@ -6,7 +6,7 @@
#include <asm/vmx.h>
-#include "evmcs.h"
+#include "hyperv.h"
#include "vmcs.h"
#include "../x86.h"
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9cf1ba865562..72ac6bf05c8b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -30,6 +30,7 @@
#include "hyperv.h"
#include "lapic.h"
#include "xen.h"
+#include "smm.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
@@ -119,8 +120,6 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
static void update_cr8_intercept(struct kvm_vcpu *vcpu);
static void process_nmi(struct kvm_vcpu *vcpu);
-static void process_smi(struct kvm_vcpu *vcpu);
-static void enter_smm(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
static void store_regs(struct kvm_vcpu *vcpu);
static int sync_regs(struct kvm_vcpu *vcpu);
@@ -628,6 +627,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto
ex->payload = payload;
}
+/* Forcibly leave the nested mode in cases like a vCPU reset */
+static void kvm_leave_nested(struct kvm_vcpu *vcpu)
+{
+ kvm_x86_ops.nested_ops->leave_nested(vcpu);
+}
+
static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
unsigned nr, bool has_error, u32 error_code,
bool has_payload, unsigned long payload, bool reinject)
@@ -1438,32 +1443,27 @@ static const u32 msrs_to_save_all[] = {
MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
MSR_CORE_PERF_GLOBAL_CTRL, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
+ MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
+
+ /* This part of MSRs should match KVM_INTEL_PMC_MAX_GENERIC. */
MSR_ARCH_PERFMON_PERFCTR0, MSR_ARCH_PERFMON_PERFCTR1,
MSR_ARCH_PERFMON_PERFCTR0 + 2, MSR_ARCH_PERFMON_PERFCTR0 + 3,
MSR_ARCH_PERFMON_PERFCTR0 + 4, MSR_ARCH_PERFMON_PERFCTR0 + 5,
MSR_ARCH_PERFMON_PERFCTR0 + 6, MSR_ARCH_PERFMON_PERFCTR0 + 7,
- MSR_ARCH_PERFMON_PERFCTR0 + 8, MSR_ARCH_PERFMON_PERFCTR0 + 9,
- MSR_ARCH_PERFMON_PERFCTR0 + 10, MSR_ARCH_PERFMON_PERFCTR0 + 11,
- MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
- MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
- MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
MSR_ARCH_PERFMON_EVENTSEL0 + 6, MSR_ARCH_PERFMON_EVENTSEL0 + 7,
- MSR_ARCH_PERFMON_EVENTSEL0 + 8, MSR_ARCH_PERFMON_EVENTSEL0 + 9,
- MSR_ARCH_PERFMON_EVENTSEL0 + 10, MSR_ARCH_PERFMON_EVENTSEL0 + 11,
- MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
- MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
- MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
- MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
MSR_K7_EVNTSEL0, MSR_K7_EVNTSEL1, MSR_K7_EVNTSEL2, MSR_K7_EVNTSEL3,
MSR_K7_PERFCTR0, MSR_K7_PERFCTR1, MSR_K7_PERFCTR2, MSR_K7_PERFCTR3,
+
+ /* This part of MSRs should match KVM_AMD_PMC_MAX_GENERIC. */
MSR_F15H_PERF_CTL0, MSR_F15H_PERF_CTL1, MSR_F15H_PERF_CTL2,
MSR_F15H_PERF_CTL3, MSR_F15H_PERF_CTL4, MSR_F15H_PERF_CTL5,
MSR_F15H_PERF_CTR0, MSR_F15H_PERF_CTR1, MSR_F15H_PERF_CTR2,
MSR_F15H_PERF_CTR3, MSR_F15H_PERF_CTR4, MSR_F15H_PERF_CTR5,
+
MSR_IA32_XFD, MSR_IA32_XFD_ERR,
};
@@ -1653,6 +1653,9 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
case MSR_IA32_ARCH_CAPABILITIES:
msr->data = kvm_get_arch_capabilities();
break;
+ case MSR_IA32_PERF_CAPABILITIES:
+ msr->data = kvm_caps.supported_perf_cap;
+ break;
case MSR_IA32_UCODE_REV:
rdmsrl_safe(msr->index, &msr->data);
break;
@@ -2315,11 +2318,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
/* we verify if the enable bit is set... */
if (system_time & 1) {
- kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
- KVM_HOST_USES_PFN, system_time & ~1ULL,
- sizeof(struct pvclock_vcpu_time_info));
+ kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
+ KVM_HOST_USES_PFN, system_time & ~1ULL,
+ sizeof(struct pvclock_vcpu_time_info));
} else {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
}
return;
@@ -3388,7 +3391,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data)
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time);
vcpu->arch.time = 0;
}
@@ -3396,6 +3399,9 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu)
{
++vcpu->stat.tlb_flush;
static_call(kvm_x86_flush_tlb_all)(vcpu);
+
+ /* Flushing all ASIDs flushes the current ASID... */
+ kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
}
static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
@@ -3414,6 +3420,12 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu)
}
static_call(kvm_x86_flush_tlb_guest)(vcpu);
+
+ /*
+ * Flushing all "guest" TLB is always a superset of Hyper-V's fine
+ * grained flushing.
+ */
+ kvm_hv_vcpu_purge_flush_tlb(vcpu);
}
@@ -3565,20 +3577,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vcpu->arch.arch_capabilities = data;
break;
- case MSR_IA32_PERF_CAPABILITIES: {
- struct kvm_msr_entry msr_ent = {.index = msr, .data = 0};
-
+ case MSR_IA32_PERF_CAPABILITIES:
if (!msr_info->host_initiated)
return 1;
- if (kvm_get_msr_feature(&msr_ent))
- return 1;
- if (data & ~msr_ent.data)
+ if (data & ~kvm_caps.supported_perf_cap)
return 1;
vcpu->arch.perf_capabilities = data;
kvm_pmu_refresh(vcpu);
return 0;
- }
case MSR_EFER:
return set_efer(vcpu, msr_info);
case MSR_K7_HWCR:
@@ -3650,7 +3657,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
break;
}
case MSR_IA32_SMBASE:
- if (!msr_info->host_initiated)
+ if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
return 1;
vcpu->arch.smbase = data;
break;
@@ -4066,7 +4073,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vcpu->arch.ia32_misc_enable_msr;
break;
case MSR_IA32_SMBASE:
- if (!msr_info->host_initiated)
+ if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated)
return 1;
msr_info->data = vcpu->arch.smbase;
break;
@@ -4440,6 +4447,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r |= KVM_X86_DISABLE_EXITS_MWAIT;
break;
case KVM_CAP_X86_SMM:
+ if (!IS_ENABLED(CONFIG_KVM_SMM))
+ break;
+
/* SMBASE is usually relocated above 1M on modern chipsets,
* and SMM handlers might indeed rely on 4G segment limits,
* so do not report SMM to be available if real mode is
@@ -4480,7 +4490,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0;
break;
case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
- r = kvm_x86_ops.enable_direct_tlbflush != NULL;
+ r = kvm_x86_ops.enable_l2_tlb_flush != NULL;
break;
case KVM_CAP_HYPERV_ENLIGHTENED_VMCS:
r = kvm_x86_ops.nested_ops->enable_evmcs != NULL;
@@ -4896,13 +4906,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu)
return 0;
}
-static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu)
-{
- kvm_make_request(KVM_REQ_SMI, vcpu);
-
- return 0;
-}
-
static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu,
struct kvm_tpr_access_ctl *tac)
{
@@ -5038,8 +5041,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
process_nmi(vcpu);
+#ifdef CONFIG_KVM_SMM
if (kvm_check_request(KVM_REQ_SMI, vcpu))
process_smi(vcpu);
+#endif
/*
* KVM's ABI only allows for one exception to be migrated. Luckily,
@@ -5067,16 +5072,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
ex->pending && ex->has_payload)
kvm_deliver_exception_payload(vcpu, ex);
+ memset(events, 0, sizeof(*events));
+
/*
* The API doesn't provide the instruction length for software
* exceptions, so don't report them. As long as the guest RIP
* isn't advanced, we should expect to encounter the exception
* again.
*/
- if (kvm_exception_is_soft(ex->vector)) {
- events->exception.injected = 0;
- events->exception.pending = 0;
- } else {
+ if (!kvm_exception_is_soft(ex->vector)) {
events->exception.injected = ex->injected;
events->exception.pending = ex->pending;
/*
@@ -5096,20 +5100,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->interrupt.injected =
vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft;
events->interrupt.nr = vcpu->arch.interrupt.nr;
- events->interrupt.soft = 0;
events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending != 0;
events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu);
- events->nmi.pad = 0;
- events->sipi_vector = 0; /* never valid when reporting to user space */
+ /* events->sipi_vector is never valid when reporting to user space */
+#ifdef CONFIG_KVM_SMM
events->smi.smm = is_smm(vcpu);
events->smi.pending = vcpu->arch.smi_pending;
events->smi.smm_inside_nmi =
!!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK);
+#endif
events->smi.latched_init = kvm_lapic_latched_init(vcpu);
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
@@ -5121,12 +5125,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu);
events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
}
-
- memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm);
-
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
@@ -5199,8 +5199,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+#ifdef CONFIG_KVM_SMM
if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
- kvm_x86_ops.nested_ops->leave_nested(vcpu);
+ kvm_leave_nested(vcpu);
kvm_smm_changed(vcpu, events->smi.smm);
}
@@ -5213,6 +5214,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK;
}
+#else
+ if (events->smi.smm || events->smi.pending ||
+ events->smi.smm_inside_nmi)
+ return -EINVAL;
+#endif
+
if (lapic_in_kernel(vcpu)) {
if (events->smi.latched_init)
set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events);
@@ -5496,10 +5503,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
}
return r;
case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
- if (!kvm_x86_ops.enable_direct_tlbflush)
+ if (!kvm_x86_ops.enable_l2_tlb_flush)
return -ENOTTY;
- return static_call(kvm_x86_enable_direct_tlbflush)(vcpu);
+ return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu);
case KVM_CAP_HYPERV_ENFORCE_CPUID:
return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]);
@@ -5579,7 +5586,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
break;
}
case KVM_SMI: {
- r = kvm_vcpu_ioctl_smi(vcpu);
+ r = kvm_inject_smi(vcpu);
break;
}
case KVM_SET_CPUID: {
@@ -6238,9 +6245,7 @@ split_irqchip_unlock:
break;
case KVM_CAP_X86_USER_SPACE_MSR:
r = -EINVAL;
- if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL |
- KVM_MSR_EXIT_REASON_UNKNOWN |
- KVM_MSR_EXIT_REASON_FILTER))
+ if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK)
break;
kvm->arch.user_space_msr_mask = cap->args[0];
r = 0;
@@ -6417,7 +6422,7 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter,
if (!user_range->nmsrs)
return 0;
- if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE))
+ if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK)
return -EINVAL;
if (!user_range->flags)
@@ -6451,7 +6456,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm,
int r = 0;
u32 i;
- if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY)
+ if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK)
return -EINVAL;
for (i = 0; i < ARRAY_SIZE(filter->ranges); i++)
@@ -7041,14 +7046,14 @@ static void kvm_init_msr_list(void)
intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
continue;
break;
- case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+ case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR_MAX:
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
- min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+ min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
continue;
break;
- case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+ case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL_MAX:
if (msrs_to_save_all[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
- min(INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
+ min(KVM_INTEL_PMC_MAX_GENERIC, kvm_pmu_cap.num_counters_gp))
continue;
break;
case MSR_IA32_XFD:
@@ -7124,8 +7129,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v)
return handled;
}
-static void kvm_set_segment(struct kvm_vcpu *vcpu,
- struct kvm_segment *var, int seg)
+void kvm_set_segment(struct kvm_vcpu *vcpu,
+ struct kvm_segment *var, int seg)
{
static_call(kvm_x86_set_segment)(vcpu, var, seg);
}
@@ -7161,16 +7166,6 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
}
EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read);
- gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
- struct x86_exception *exception)
-{
- struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
-
- u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0;
- access |= PFERR_FETCH_MASK;
- return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception);
-}
-
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
struct x86_exception *exception)
{
@@ -7283,15 +7278,6 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
}
-static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
- unsigned long addr, void *val, unsigned int bytes)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes);
-
- return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
-}
-
static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
struct kvm_vcpu *vcpu, u64 access,
struct x86_exception *exception)
@@ -8083,26 +8069,6 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt,
return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata);
}
-static int emulator_set_msr(struct x86_emulate_ctxt *ctxt,
- u32 msr_index, u64 data)
-{
- return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
-}
-
-static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- return vcpu->arch.smbase;
-}
-
-static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- vcpu->arch.smbase = smbase;
-}
-
static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt,
u32 pmc)
{
@@ -8177,18 +8143,13 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
return emul_to_vcpu(ctxt)->arch.hflags;
}
-static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
-{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- kvm_smm_changed(vcpu, false);
-}
-
-static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
- const char *smstate)
+#ifndef CONFIG_KVM_SMM
+static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
{
- return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+ WARN_ON_ONCE(1);
+ return X86EMUL_UNHANDLEABLE;
}
+#endif
static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
{
@@ -8214,7 +8175,6 @@ static const struct x86_emulate_ops emulate_ops = {
.write_gpr = emulator_write_gpr,
.read_std = emulator_read_std,
.write_std = emulator_write_std,
- .read_phys = kvm_read_guest_phys_system,
.fetch = kvm_fetch_guest_virt,
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
@@ -8234,11 +8194,8 @@ static const struct x86_emulate_ops emulate_ops = {
.cpl = emulator_get_cpl,
.get_dr = emulator_get_dr,
.set_dr = emulator_set_dr,
- .get_smbase = emulator_get_smbase,
- .set_smbase = emulator_set_smbase,
.set_msr_with_filter = emulator_set_msr_with_filter,
.get_msr_with_filter = emulator_get_msr_with_filter,
- .set_msr = emulator_set_msr,
.get_msr = emulator_get_msr,
.check_pmc = emulator_check_pmc,
.read_pmc = emulator_read_pmc,
@@ -8253,7 +8210,6 @@ static const struct x86_emulate_ops emulate_ops = {
.guest_has_rdpid = emulator_guest_has_rdpid,
.set_nmi_mask = emulator_set_nmi_mask,
.get_hflags = emulator_get_hflags,
- .exiting_smm = emulator_exiting_smm,
.leave_smm = emulator_leave_smm,
.triple_fault = emulator_triple_fault,
.set_xcr = emulator_set_xcr,
@@ -8326,8 +8282,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
cs_db ? X86EMUL_MODE_PROT32 :
X86EMUL_MODE_PROT16;
BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
- BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
- BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
ctxt->interruptibility = 0;
ctxt->have_exception = false;
@@ -8586,29 +8540,6 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
static int complete_emulated_pio(struct kvm_vcpu *vcpu);
-static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm)
-{
- trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm);
-
- if (entering_smm) {
- vcpu->arch.hflags |= HF_SMM_MASK;
- } else {
- vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK);
-
- /* Process a latched INIT or SMI, if any. */
- kvm_make_request(KVM_REQ_EVENT, vcpu);
-
- /*
- * Even if KVM_SET_SREGS2 loaded PDPTRs out of band,
- * on SMM exit we still need to reload them from
- * guest memory
- */
- vcpu->arch.pdptrs_from_userspace = false;
- }
-
- kvm_mmu_reset_context(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -9810,7 +9741,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
int kvm_check_nested_events(struct kvm_vcpu *vcpu)
{
- if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+ if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
kvm_x86_ops.nested_ops->triple_fault(vcpu);
return 1;
}
@@ -9998,6 +9929,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
* in order to make progress and get back here for another iteration.
* The kvm_x86_ops hooks communicate this by returning -EBUSY.
*/
+#ifdef CONFIG_KVM_SMM
if (vcpu->arch.smi_pending) {
r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY;
if (r < 0)
@@ -10010,6 +9942,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
} else
static_call(kvm_x86_enable_smi_window)(vcpu);
}
+#endif
if (vcpu->arch.nmi_pending) {
r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY;
@@ -10044,7 +9977,20 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
kvm_x86_ops.nested_ops->has_events(vcpu))
*req_immediate_exit = true;
- WARN_ON(kvm_is_exception_pending(vcpu));
+ /*
+ * KVM must never queue a new exception while injecting an event; KVM
+ * is done emulating and should only propagate the to-be-injected event
+ * to the VMCS/VMCB. Queueing a new exception can put the vCPU into an
+ * infinite loop as KVM will bail from VM-Enter to inject the pending
+ * exception and start the cycle all over.
+ *
+ * Exempt triple faults as they have special handling and won't put the
+ * vCPU into an infinite loop. Triple fault can be queued when running
+ * VMX without unrestricted guest, as that requires KVM to emulate Real
+ * Mode events (see kvm_inject_realmode_interrupt()).
+ */
+ WARN_ON_ONCE(vcpu->arch.exception.pending ||
+ vcpu->arch.exception_vmexit.pending);
return 0;
out:
@@ -10072,246 +10018,6 @@ static void process_nmi(struct kvm_vcpu *vcpu)
kvm_make_request(KVM_REQ_EVENT, vcpu);
}
-static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
-{
- u32 flags = 0;
- flags |= seg->g << 23;
- flags |= seg->db << 22;
- flags |= seg->l << 21;
- flags |= seg->avl << 20;
- flags |= seg->present << 15;
- flags |= seg->dpl << 13;
- flags |= seg->s << 12;
- flags |= seg->type << 8;
- return flags;
-}
-
-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
-{
- struct kvm_segment seg;
- int offset;
-
- kvm_get_segment(vcpu, &seg, n);
- put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
-
- if (n < 3)
- offset = 0x7f84 + n * 12;
- else
- offset = 0x7f2c + (n - 3) * 12;
-
- put_smstate(u32, buf, offset + 8, seg.base);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
-{
- struct kvm_segment seg;
- int offset;
- u16 flags;
-
- kvm_get_segment(vcpu, &seg, n);
- offset = 0x7e00 + n * 16;
-
- flags = enter_smm_get_segment_flags(&seg) >> 8;
- put_smstate(u16, buf, offset, seg.selector);
- put_smstate(u16, buf, offset + 2, flags);
- put_smstate(u32, buf, offset + 4, seg.limit);
- put_smstate(u64, buf, offset + 8, seg.base);
-}
-#endif
-
-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
-{
- struct desc_ptr dt;
- struct kvm_segment seg;
- unsigned long val;
- int i;
-
- put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
- put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
- put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
- put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
-
- for (i = 0; i < 8; i++)
- put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
-
- kvm_get_dr(vcpu, 6, &val);
- put_smstate(u32, buf, 0x7fcc, (u32)val);
- kvm_get_dr(vcpu, 7, &val);
- put_smstate(u32, buf, 0x7fc8, (u32)val);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u32, buf, 0x7fc4, seg.selector);
- put_smstate(u32, buf, 0x7f64, seg.base);
- put_smstate(u32, buf, 0x7f60, seg.limit);
- put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u32, buf, 0x7fc0, seg.selector);
- put_smstate(u32, buf, 0x7f80, seg.base);
- put_smstate(u32, buf, 0x7f7c, seg.limit);
- put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
-
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f74, dt.address);
- put_smstate(u32, buf, 0x7f70, dt.size);
-
- static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7f58, dt.address);
- put_smstate(u32, buf, 0x7f54, dt.size);
-
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_32(vcpu, buf, i);
-
- put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
-
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020000);
- put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
-}
-
-#ifdef CONFIG_X86_64
-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
-{
- struct desc_ptr dt;
- struct kvm_segment seg;
- unsigned long val;
- int i;
-
- for (i = 0; i < 16; i++)
- put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
-
- put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
- put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
-
- kvm_get_dr(vcpu, 6, &val);
- put_smstate(u64, buf, 0x7f68, val);
- kvm_get_dr(vcpu, 7, &val);
- put_smstate(u64, buf, 0x7f60, val);
-
- put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
- put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
- put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
-
- put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
-
- /* revision id */
- put_smstate(u32, buf, 0x7efc, 0x00020064);
-
- put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
- put_smstate(u16, buf, 0x7e90, seg.selector);
- put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e94, seg.limit);
- put_smstate(u64, buf, 0x7e98, seg.base);
-
- static_call(kvm_x86_get_idt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e84, dt.size);
- put_smstate(u64, buf, 0x7e88, dt.address);
-
- kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
- put_smstate(u16, buf, 0x7e70, seg.selector);
- put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
- put_smstate(u32, buf, 0x7e74, seg.limit);
- put_smstate(u64, buf, 0x7e78, seg.base);
-
- static_call(kvm_x86_get_gdt)(vcpu, &dt);
- put_smstate(u32, buf, 0x7e64, dt.size);
- put_smstate(u64, buf, 0x7e68, dt.address);
-
- for (i = 0; i < 6; i++)
- enter_smm_save_seg_64(vcpu, buf, i);
-}
-#endif
-
-static void enter_smm(struct kvm_vcpu *vcpu)
-{
- struct kvm_segment cs, ds;
- struct desc_ptr dt;
- unsigned long cr0;
- char buf[512];
-
- memset(buf, 0, 512);
-#ifdef CONFIG_X86_64
- if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- enter_smm_save_state_64(vcpu, buf);
- else
-#endif
- enter_smm_save_state_32(vcpu, buf);
-
- /*
- * Give enter_smm() a chance to make ISA-specific changes to the vCPU
- * state (e.g. leave guest mode) after we've saved the state into the
- * SMM state-save area.
- */
- static_call(kvm_x86_enter_smm)(vcpu, buf);
-
- kvm_smm_changed(vcpu, true);
- kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
-
- if (static_call(kvm_x86_get_nmi_mask)(vcpu))
- vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
- else
- static_call(kvm_x86_set_nmi_mask)(vcpu, true);
-
- kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
- kvm_rip_write(vcpu, 0x8000);
-
- cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
- static_call(kvm_x86_set_cr0)(vcpu, cr0);
- vcpu->arch.cr0 = cr0;
-
- static_call(kvm_x86_set_cr4)(vcpu, 0);
-
- /* Undocumented: IDT limit is set to zero on entry to SMM. */
- dt.address = dt.size = 0;
- static_call(kvm_x86_set_idt)(vcpu, &dt);
-
- kvm_set_dr(vcpu, 7, DR7_FIXED_1);
-
- cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
- cs.base = vcpu->arch.smbase;
-
- ds.selector = 0;
- ds.base = 0;
-
- cs.limit = ds.limit = 0xffffffff;
- cs.type = ds.type = 0x3;
- cs.dpl = ds.dpl = 0;
- cs.db = ds.db = 0;
- cs.s = ds.s = 1;
- cs.l = ds.l = 0;
- cs.g = ds.g = 1;
- cs.avl = ds.avl = 0;
- cs.present = ds.present = 1;
- cs.unusable = ds.unusable = 0;
- cs.padding = ds.padding = 0;
-
- kvm_set_segment(vcpu, &cs, VCPU_SREG_CS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_DS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_ES);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_FS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
- kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
-
-#ifdef CONFIG_X86_64
- if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
- static_call(kvm_x86_set_efer)(vcpu, 0);
-#endif
-
- kvm_update_cpuid_runtime(vcpu);
- kvm_mmu_reset_context(vcpu);
-}
-
-static void process_smi(struct kvm_vcpu *vcpu)
-{
- vcpu->arch.smi_pending = true;
- kvm_make_request(KVM_REQ_EVENT, vcpu);
-}
-
void kvm_make_scan_ioapic_request_mask(struct kvm *kvm,
unsigned long *vcpu_bitmap)
{
@@ -10391,7 +10097,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
kvm->arch.apicv_inhibit_reasons = new;
if (new) {
unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
+ int idx = srcu_read_lock(&kvm->srcu);
+
kvm_zap_gfn_range(kvm, gfn, gfn+1);
+ srcu_read_unlock(&kvm->srcu, idx);
}
} else {
kvm->arch.apicv_inhibit_reasons = new;
@@ -10536,28 +10245,42 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_mmu_sync_roots(vcpu);
if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu))
kvm_mmu_load_pgd(vcpu);
- if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) {
+
+ /*
+ * Note, the order matters here, as flushing "all" TLB entries
+ * also flushes the "current" TLB entries, i.e. servicing the
+ * flush "all" will clear any request to flush "current".
+ */
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
kvm_vcpu_flush_tlb_all(vcpu);
- /* Flushing all ASIDs flushes the current ASID... */
- kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
- }
kvm_service_local_tlb_flush_requests(vcpu);
+ /*
+ * Fall back to a "full" guest flush if Hyper-V's precise
+ * flushing fails. Note, Hyper-V's flushing is per-vCPU, but
+ * the flushes are considered "remote" and not "local" because
+ * the requests can be initiated from other vCPUs.
+ */
+ if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) &&
+ kvm_hv_vcpu_flush_tlb(vcpu))
+ kvm_vcpu_flush_tlb_guest(vcpu);
+
if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
goto out;
}
- if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
- if (is_guest_mode(vcpu)) {
+ if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
+ if (is_guest_mode(vcpu))
kvm_x86_ops.nested_ops->triple_fault(vcpu);
- } else {
+
+ if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
vcpu->mmio_needed = 0;
r = 0;
- goto out;
}
+ goto out;
}
if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
/* Page is swapped out. Do synthetic halt */
@@ -10567,8 +10290,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
}
if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
record_steal_time(vcpu);
+#ifdef CONFIG_KVM_SMM
if (kvm_check_request(KVM_REQ_SMI, vcpu))
process_smi(vcpu);
+#endif
if (kvm_check_request(KVM_REQ_NMI, vcpu))
process_nmi(vcpu);
if (kvm_check_request(KVM_REQ_PMU, vcpu))
@@ -11816,6 +11541,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.regs_avail = ~0;
vcpu->arch.regs_dirty = ~0;
+ kvm_gpc_init(&vcpu->arch.pv_time);
+
if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
@@ -11880,6 +11607,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
kvm_async_pf_hash_reset(vcpu);
+
+ vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
kvm_pmu_init(vcpu);
vcpu->arch.pending_external_vector = -1;
@@ -11984,8 +11713,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
WARN_ON_ONCE(!init_event &&
(old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu)));
+ /*
+ * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's
+ * possible to INIT the vCPU while L2 is active. Force the vCPU back
+ * into L1 as EFER.SVME is cleared on INIT (along with all other EFER
+ * bits), i.e. virtualization is disabled.
+ */
+ if (is_guest_mode(vcpu))
+ kvm_leave_nested(vcpu);
+
kvm_lapic_reset(vcpu, init_event);
+ WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu));
vcpu->arch.hflags = 0;
vcpu->arch.smi_pending = 0;
@@ -12879,10 +12618,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
static_call(kvm_x86_nmi_allowed)(vcpu, false)))
return true;
+#ifdef CONFIG_KVM_SMM
if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
(vcpu->arch.smi_pending &&
static_call(kvm_x86_smi_allowed)(vcpu, false)))
return true;
+#endif
if (kvm_arch_interrupt_allowed(vcpu) &&
(kvm_cpu_has_interrupt(vcpu) ||
@@ -12923,7 +12664,9 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
return true;
if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+#ifdef CONFIG_KVM_SMM
kvm_test_request(KVM_REQ_SMI, vcpu) ||
+#endif
kvm_test_request(KVM_REQ_EVENT, vcpu))
return true;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 829d3134c1eb..9de72586f406 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -27,6 +27,7 @@ struct kvm_caps {
u64 supported_mce_cap;
u64 supported_xcr0;
u64 supported_xss;
+ u64 supported_perf_cap;
};
void kvm_spurious_fault(void);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 93c628d3e3a9..4b8e9628fbf5 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -42,13 +42,13 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn)
int idx = srcu_read_lock(&kvm->srcu);
if (gfn == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(kvm, gpc);
+ kvm_gpc_deactivate(kvm, gpc);
goto out;
}
do {
- ret = kvm_gfn_to_pfn_cache_init(kvm, gpc, NULL, KVM_HOST_USES_PFN,
- gpa, PAGE_SIZE);
+ ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa,
+ PAGE_SIZE);
if (ret)
goto out;
@@ -554,15 +554,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
offsetof(struct compat_vcpu_info, time));
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.vcpu_info_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct vcpu_info));
+ r = kvm_gpc_activate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_info_cache, NULL,
+ KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct vcpu_info));
if (!r)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -570,16 +570,16 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO:
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_time_info_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct pvclock_vcpu_time_info));
+ r = kvm_gpc_activate(vcpu->kvm,
+ &vcpu->arch.xen.vcpu_time_info_cache,
+ NULL, KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct pvclock_vcpu_time_info));
if (!r)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
break;
@@ -590,16 +590,15 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data)
break;
}
if (data->u.gpa == GPA_INVALID) {
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache);
+ kvm_gpc_deactivate(vcpu->kvm,
+ &vcpu->arch.xen.runstate_cache);
r = 0;
break;
}
- r = kvm_gfn_to_pfn_cache_init(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache,
- NULL, KVM_HOST_USES_PFN, data->u.gpa,
- sizeof(struct vcpu_runstate_info));
+ r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache,
+ NULL, KVM_HOST_USES_PFN, data->u.gpa,
+ sizeof(struct vcpu_runstate_info));
break;
case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT:
@@ -955,6 +954,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu)
return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result);
}
+static inline int max_evtchn_port(struct kvm *kvm)
+{
+ if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
+ return EVTCHN_2L_NR_CHANNELS;
+ else
+ return COMPAT_EVTCHN_2L_NR_CHANNELS;
+}
+
static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports,
evtchn_port_t *ports)
{
@@ -1043,6 +1050,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
*r = -EFAULT;
goto out;
}
+ if (ports[i] >= max_evtchn_port(vcpu->kvm)) {
+ *r = -EINVAL;
+ goto out;
+ }
}
if (sched_poll.nr_ports == 1)
@@ -1216,6 +1227,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
bool longmode;
u64 input, params[6], r = -ENOSYS;
bool handled = false;
+ u8 cpl;
input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX);
@@ -1243,9 +1255,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
params[5] = (u64)kvm_r9_read(vcpu);
}
#endif
- trace_kvm_xen_hypercall(input, params[0], params[1], params[2],
+ cpl = static_call(kvm_x86_get_cpl)(vcpu);
+ trace_kvm_xen_hypercall(cpl, input, params[0], params[1], params[2],
params[3], params[4], params[5]);
+ /*
+ * Only allow hypercall acceleration for CPL0. The rare hypercalls that
+ * are permitted in guest userspace can be handled by the VMM.
+ */
+ if (unlikely(cpl > 0))
+ goto handle_in_userspace;
+
switch (input) {
case __HYPERVISOR_xen_version:
if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) {
@@ -1280,10 +1300,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
if (handled)
return kvm_xen_hypercall_set_result(vcpu, r);
+handle_in_userspace:
vcpu->run->exit_reason = KVM_EXIT_XEN;
vcpu->run->xen.type = KVM_EXIT_XEN_HCALL;
vcpu->run->xen.u.hcall.longmode = longmode;
- vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu);
+ vcpu->run->xen.u.hcall.cpl = cpl;
vcpu->run->xen.u.hcall.input = input;
vcpu->run->xen.u.hcall.params[0] = params[0];
vcpu->run->xen.u.hcall.params[1] = params[1];
@@ -1298,14 +1319,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu)
return 0;
}
-static inline int max_evtchn_port(struct kvm *kvm)
-{
- if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode)
- return EVTCHN_2L_NR_CHANNELS;
- else
- return COMPAT_EVTCHN_2L_NR_CHANNELS;
-}
-
static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port)
{
int poll_evtchn = vcpu->arch.xen.poll_evtchn;
@@ -1667,18 +1680,18 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
case EVTCHNSTAT_ipi:
/* IPI must map back to the same port# */
if (data->u.evtchn.deliver.port.port != data->u.evtchn.send_port)
- goto out; /* -EINVAL */
+ goto out_noeventfd; /* -EINVAL */
break;
case EVTCHNSTAT_interdomain:
if (data->u.evtchn.deliver.port.port) {
if (data->u.evtchn.deliver.port.port >= max_evtchn_port(kvm))
- goto out; /* -EINVAL */
+ goto out_noeventfd; /* -EINVAL */
} else {
eventfd = eventfd_ctx_fdget(data->u.evtchn.deliver.eventfd.fd);
if (IS_ERR(eventfd)) {
ret = PTR_ERR(eventfd);
- goto out;
+ goto out_noeventfd;
}
}
break;
@@ -1718,6 +1731,7 @@ static int kvm_xen_eventfd_assign(struct kvm *kvm,
out:
if (eventfd)
eventfd_ctx_put(eventfd);
+out_noeventfd:
kfree(evtchnfd);
return ret;
}
@@ -1816,7 +1830,12 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu)
{
vcpu->arch.xen.vcpu_id = vcpu->vcpu_idx;
vcpu->arch.xen.poll_evtchn = 0;
+
timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0);
+
+ kvm_gpc_init(&vcpu->arch.xen.runstate_cache);
+ kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache);
}
void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
@@ -1824,18 +1843,17 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu)
if (kvm_xen_timer_enabled(vcpu))
kvm_xen_stop_timer(vcpu);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.runstate_cache);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_info_cache);
- kvm_gfn_to_pfn_cache_destroy(vcpu->kvm,
- &vcpu->arch.xen.vcpu_time_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache);
+ kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache);
+
del_timer_sync(&vcpu->arch.xen.poll_timer);
}
void kvm_xen_init_vm(struct kvm *kvm)
{
idr_init(&kvm->arch.xen.evtchn_ports);
+ kvm_gpc_init(&kvm->arch.xen.shinfo_cache);
}
void kvm_xen_destroy_vm(struct kvm *kvm)
@@ -1843,7 +1861,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm)
struct evtchnfd *evtchnfd;
int i;
- kvm_gfn_to_pfn_cache_destroy(kvm, &kvm->arch.xen.shinfo_cache);
+ kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache);
idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) {
if (!evtchnfd->deliver.port.port)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 97342c42dda8..2e5a045731de 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -587,6 +587,10 @@ static inline pgprot_t verify_rwx(pgprot_t old, pgprot_t new, unsigned long star
{
unsigned long end;
+ /* Kernel text is rw at boot up */
+ if (system_state == SYSTEM_BOOTING)
+ return new;
+
/*
* 32-bit has some unfixable W+X issues, like EFI code
* and writeable data being in the same page. Disable
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 99620428ad78..00127abd89ee 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -11,6 +11,7 @@
#include <linux/bpf.h>
#include <linux/memory.h>
#include <linux/sort.h>
+#include <linux/init.h>
#include <asm/extable.h>
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
@@ -388,6 +389,18 @@ out:
return ret;
}
+int __init bpf_arch_init_dispatcher_early(void *ip)
+{
+ const u8 *nop_insn = x86_nops[5];
+
+ if (is_endbr(*(u32 *)ip))
+ ip += ENDBR_INSN_SIZE;
+
+ if (memcmp(ip, nop_insn, X86_PATCH_SIZE))
+ text_poke_early(ip, nop_insn, X86_PATCH_SIZE);
+ return 0;
+}
+
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 58a200dc762d..17f09dc26381 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -26,6 +26,7 @@ GCOV_PROFILE := n
KASAN_SANITIZE := n
UBSAN_SANITIZE := n
KCSAN_SANITIZE := n
+KMSAN_SANITIZE := n
KCOV_INSTRUMENT := n
# These are adjustments to the compiler flags used for objects that
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index 68aff1382872..246d67dab510 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -302,7 +302,7 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
bool *emul)
{
- int type, index;
+ int type, index = 0;
if (is_amd_pmu_msr(msr))
*emul = xen_amd_pmu_emulate(msr, val, is_read);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index cfa99e8f054b..4f4309500559 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -910,17 +910,9 @@ static int register_callback(unsigned type, const void *func)
void xen_enable_sysenter(void)
{
- int ret;
- unsigned sysenter_feature;
-
- sysenter_feature = X86_FEATURE_SYSENTER32;
-
- if (!boot_cpu_has(sysenter_feature))
- return;
-
- ret = register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat);
- if(ret != 0)
- setup_clear_cpu_cap(sysenter_feature);
+ if (cpu_feature_enabled(X86_FEATURE_SYSENTER32) &&
+ register_callback(CALLBACKTYPE_sysenter, xen_entry_SYSENTER_compat))
+ setup_clear_cpu_cap(X86_FEATURE_SYSENTER32);
}
void xen_enable_syscall(void)
@@ -934,12 +926,9 @@ void xen_enable_syscall(void)
mechanism for syscalls. */
}
- if (boot_cpu_has(X86_FEATURE_SYSCALL32)) {
- ret = register_callback(CALLBACKTYPE_syscall32,
- xen_entry_SYSCALL_compat);
- if (ret != 0)
- setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
- }
+ if (cpu_feature_enabled(X86_FEATURE_SYSCALL32) &&
+ register_callback(CALLBACKTYPE_syscall32, xen_entry_SYSCALL_compat))
+ setup_clear_cpu_cap(X86_FEATURE_SYSCALL32);
}
static void __init xen_pvmmu_arch_setup(void)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 33292c01875d..6a789cda68a5 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -611,6 +611,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
.nr_tags = 1,
};
u64 alloc_time_ns = 0;
+ struct request *rq;
unsigned int cpu;
unsigned int tag;
int ret;
@@ -660,8 +661,12 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
tag = blk_mq_get_tag(&data);
if (tag == BLK_MQ_NO_TAG)
goto out_queue_exit;
- return blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
+ rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag,
alloc_time_ns);
+ rq->__data_len = 0;
+ rq->__sector = (sector_t) -1;
+ rq->bio = rq->biotail = NULL;
+ return rq;
out_queue_exit:
blk_queue_exit(q);
@@ -1257,6 +1262,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
(!blk_queue_nomerges(rq->q) &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_mq_flush_plug_list(plug, false);
+ last = NULL;
trace_block_plug(rq->q);
}
@@ -4188,9 +4194,7 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
return 0;
err_hctxs:
- xa_destroy(&q->hctx_table);
- q->nr_hw_queues = 0;
- blk_mq_sysfs_deinit(q);
+ blk_mq_release(q);
err_poll:
blk_stat_free_callback(q->poll_cb);
q->poll_cb = NULL;
diff --git a/block/genhd.c b/block/genhd.c
index 17b33c62423d..0f9769db2de8 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -410,9 +410,10 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
* Otherwise just allocate the device numbers for both the whole device
* and all partitions from the extended dev_t space.
*/
+ ret = -EINVAL;
if (disk->major) {
if (WARN_ON(!disk->minors))
- return -EINVAL;
+ goto out_exit_elevator;
if (disk->minors > DISK_MAX_PARTS) {
pr_err("block: can't allocate more than %d partitions\n",
@@ -420,14 +421,14 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
disk->minors = DISK_MAX_PARTS;
}
if (disk->first_minor + disk->minors > MINORMASK + 1)
- return -EINVAL;
+ goto out_exit_elevator;
} else {
if (WARN_ON(disk->minors))
- return -EINVAL;
+ goto out_exit_elevator;
ret = blk_alloc_ext_minor();
if (ret < 0)
- return ret;
+ goto out_exit_elevator;
disk->major = BLOCK_EXT_MAJOR;
disk->first_minor = ret;
}
@@ -526,6 +527,7 @@ out_unregister_bdi:
bdi_unregister(disk->bdi);
out_unregister_queue:
blk_unregister_queue(disk);
+ rq_qos_exit(disk->queue);
out_put_slave_dir:
kobject_put(disk->slave_dir);
out_put_holder_dir:
@@ -540,6 +542,9 @@ out_device_del:
out_free_ext_minor:
if (disk->major == BLOCK_EXT_MAJOR)
blk_free_ext_minor(disk->first_minor);
+out_exit_elevator:
+ if (disk->queue->elevator)
+ elevator_exit(disk->queue);
return ret;
}
EXPORT_SYMBOL(device_add_disk);
diff --git a/drivers/acpi/acpi_pcc.c b/drivers/acpi/acpi_pcc.c
index ee4ce5ba1fb2..3e252be047b8 100644
--- a/drivers/acpi/acpi_pcc.c
+++ b/drivers/acpi/acpi_pcc.c
@@ -27,7 +27,7 @@
* Arbitrary retries in case the remote processor is slow to respond
* to PCC commands
*/
-#define PCC_CMD_WAIT_RETRIES_NUM 500
+#define PCC_CMD_WAIT_RETRIES_NUM 500ULL
struct pcc_data {
struct pcc_mbox_chan *pcc_chan;
diff --git a/drivers/acpi/numa/srat.c b/drivers/acpi/numa/srat.c
index 3b818ab186be..1f4fc5f8a819 100644
--- a/drivers/acpi/numa/srat.c
+++ b/drivers/acpi/numa/srat.c
@@ -327,6 +327,7 @@ static int __init acpi_parse_cfmws(union acpi_subtable_headers *header,
pr_warn("ACPI NUMA: Failed to add memblk for CFMWS node %d [mem %#llx-%#llx]\n",
node, start, end);
}
+ node_set(node, numa_nodes_parsed);
/* Set the next available fake_pxm value */
(*fake_pxm)++;
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 78c2804164c6..f27914aedbd5 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -425,6 +425,13 @@ static const struct dmi_system_id asus_laptop[] = {
DMI_MATCH(DMI_BOARD_NAME, "S5402ZA"),
},
},
+ {
+ .ident = "Asus Vivobook S5602ZA",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"),
+ },
+ },
{ }
};
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 024cc373a197..b47e93a24a9a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -789,6 +789,7 @@ static bool acpi_info_matches_ids(struct acpi_device_info *info,
static const char * const acpi_ignore_dep_ids[] = {
"PNP0D80", /* Windows-compatible System Power Management Controller */
"INT33BD", /* Intel Baytrail Mailbox Device */
+ "LATT2021", /* Lattice FW Update Client Driver */
NULL
};
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 0d9064a9804c..9cd8797d12bb 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -668,6 +668,11 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
{ },
};
+static bool google_cros_ec_present(void)
+{
+ return acpi_dev_found("GOOG0004");
+}
+
/*
* Determine which type of backlight interface to use on this system,
* First check cmdline, then dmi quirks, then do autodetect.
@@ -730,6 +735,13 @@ static enum acpi_backlight_type __acpi_video_get_backlight_type(bool native)
return acpi_backlight_video;
}
+ /*
+ * Chromebooks that don't have backlight handle in ACPI table
+ * are supposed to use native backlight if it's available.
+ */
+ if (google_cros_ec_present() && native_available)
+ return acpi_backlight_native;
+
/* No ACPI video (old hw), use vendor specific fw methods. */
return acpi_backlight_vendor;
}
diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index f8a2cbdc0ce2..d7d3f1669d4c 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -219,6 +219,12 @@ static const struct dmi_system_id force_storage_d3_dmi[] = {
DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 14 7425 2-in-1"),
}
},
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 16 5625"),
+ }
+ },
{}
};
diff --git a/drivers/ata/pata_legacy.c b/drivers/ata/pata_legacy.c
index 0a8bf09a5c19..03c580625c2c 100644
--- a/drivers/ata/pata_legacy.c
+++ b/drivers/ata/pata_legacy.c
@@ -315,9 +315,10 @@ static void pdc20230_set_piomode(struct ata_port *ap, struct ata_device *adev)
outb(inb(0x1F4) & 0x07, 0x1F4);
rt = inb(0x1F3);
- rt &= 0x07 << (3 * adev->devno);
+ rt &= ~(0x07 << (3 * !adev->devno));
if (pio)
- rt |= (1 + 3 * pio) << (3 * adev->devno);
+ rt |= (1 + 3 * pio) << (3 * !adev->devno);
+ outb(rt, 0x1F3);
udelay(100);
outb(inb(0x1F2) | 0x01, 0x1F2);
diff --git a/drivers/ata/pata_palmld.c b/drivers/ata/pata_palmld.c
index 400e65190904..51caa2a427dd 100644
--- a/drivers/ata/pata_palmld.c
+++ b/drivers/ata/pata_palmld.c
@@ -63,8 +63,8 @@ static int palmld_pata_probe(struct platform_device *pdev)
/* remap drive's physical memory address */
mem = devm_platform_ioremap_resource(pdev, 0);
- if (!mem)
- return -ENOMEM;
+ if (IS_ERR(mem))
+ return PTR_ERR(mem);
/* request and activate power and reset GPIOs */
lda->power = devm_gpiod_get(dev, "power", GPIOD_OUT_HIGH);
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index ead135c7044c..6471b559230e 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2952,6 +2952,10 @@ static int genpd_iterate_idle_states(struct device_node *dn,
np = it.node;
if (!of_match_node(idle_state_match, np))
continue;
+
+ if (!of_device_is_available(np))
+ continue;
+
if (states) {
ret = genpd_parse_state(&states[i], np);
if (ret) {
diff --git a/drivers/base/property.c b/drivers/base/property.c
index 4d6278a84868..2a5a37fcd998 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -229,7 +229,7 @@ EXPORT_SYMBOL_GPL(device_property_read_string);
* Find a given string in a string array and if it is found return the
* index back.
*
- * Return: %0 if the property was found (success),
+ * Return: index, starting from %0, if the property was found (success),
* %-EINVAL if given arguments are not valid,
* %-ENODATA if the property does not have a value,
* %-EPROTO if the property is not an array of strings,
@@ -450,7 +450,7 @@ EXPORT_SYMBOL_GPL(fwnode_property_read_string);
* Find a given string in a string array and if it is found return the
* index back.
*
- * Return: %0 if the property was found (success),
+ * Return: index, starting from %0, if the property was found (success),
* %-EINVAL if given arguments are not valid,
* %-ENODATA if the property does not have a value,
* %-EPROTO if the property is not an array of strings,
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index db1b4b202646..a41145d52de9 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -408,6 +408,12 @@ config BLK_DEV_UBLK
definition isn't finalized yet, and might change according to future
requirement, so mark is as experimental now.
+ Say Y if you want to get better performance because task_work_add()
+ can be used in IO path for replacing io_uring cmd, which will become
+ shared between IO tasks and ubq daemon, meantime task_work_add() can
+ can handle batch more effectively, but task_work_add() isn't exported
+ for module, so ublk has to be built to kernel.
+
source "drivers/block/rnbd/Kconfig"
endif # BLK_DEV
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index f9e39301c4af..04453f4a319c 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -7222,8 +7222,10 @@ static int __init rbd_sysfs_init(void)
int ret;
ret = device_register(&rbd_root_dev);
- if (ret < 0)
+ if (ret < 0) {
+ put_device(&rbd_root_dev);
return ret;
+ }
ret = bus_register(&rbd_bus_type);
if (ret < 0)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 5afce6ffaadf..f96cb01e9604 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -57,11 +57,14 @@
#define UBLK_PARAM_TYPE_ALL (UBLK_PARAM_TYPE_BASIC | UBLK_PARAM_TYPE_DISCARD)
struct ublk_rq_data {
- struct callback_head work;
+ union {
+ struct callback_head work;
+ struct llist_node node;
+ };
};
struct ublk_uring_cmd_pdu {
- struct request *req;
+ struct ublk_queue *ubq;
};
/*
@@ -119,6 +122,8 @@ struct ublk_queue {
struct task_struct *ubq_daemon;
char *io_cmd_buf;
+ struct llist_head io_cmds;
+
unsigned long io_addr; /* mapped vm address */
unsigned int max_io_sz;
bool force_abort;
@@ -764,8 +769,12 @@ static inline void __ublk_rq_task_work(struct request *req)
static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd)
{
struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
+ struct ublk_queue *ubq = pdu->ubq;
+ struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds);
+ struct ublk_rq_data *data;
- __ublk_rq_task_work(pdu->req);
+ llist_for_each_entry(data, io_cmds, node)
+ __ublk_rq_task_work(blk_mq_rq_from_pdu(data));
}
static void ublk_rq_task_work_fn(struct callback_head *work)
@@ -777,6 +786,54 @@ static void ublk_rq_task_work_fn(struct callback_head *work)
__ublk_rq_task_work(req);
}
+static void ublk_submit_cmd(struct ublk_queue *ubq, const struct request *rq)
+{
+ struct ublk_io *io = &ubq->ios[rq->tag];
+
+ /*
+ * If the check pass, we know that this is a re-issued request aborted
+ * previously in monitor_work because the ubq_daemon(cmd's task) is
+ * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore
+ * because this ioucmd's io_uring context may be freed now if no inflight
+ * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work.
+ *
+ * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing
+ * the tag). Then the request is re-started(allocating the tag) and we are here.
+ * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED
+ * guarantees that here is a re-issued request aborted previously.
+ */
+ if (unlikely(io->flags & UBLK_IO_FLAG_ABORTED)) {
+ struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds);
+ struct ublk_rq_data *data;
+
+ llist_for_each_entry(data, io_cmds, node)
+ __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data));
+ } else {
+ struct io_uring_cmd *cmd = io->cmd;
+ struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
+
+ pdu->ubq = ubq;
+ io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
+ }
+}
+
+static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq,
+ bool last)
+{
+ struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);
+
+ if (ublk_can_use_task_work(ubq)) {
+ enum task_work_notify_mode notify_mode = last ?
+ TWA_SIGNAL_NO_IPI : TWA_NONE;
+
+ if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
+ __ublk_abort_rq(ubq, rq);
+ } else {
+ if (llist_add(&data->node, &ubq->io_cmds))
+ ublk_submit_cmd(ubq, rq);
+ }
+}
+
static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
const struct blk_mq_queue_data *bd)
{
@@ -788,6 +845,7 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
res = ublk_setup_iod(ubq, rq);
if (unlikely(res != BLK_STS_OK))
return BLK_STS_IOERR;
+
/* With recovery feature enabled, force_abort is set in
* ublk_stop_dev() before calling del_gendisk(). We have to
* abort all requeued and new rqs here to let del_gendisk()
@@ -803,41 +861,11 @@ static blk_status_t ublk_queue_rq(struct blk_mq_hw_ctx *hctx,
blk_mq_start_request(bd->rq);
if (unlikely(ubq_daemon_is_dying(ubq))) {
- fail:
__ublk_abort_rq(ubq, rq);
return BLK_STS_OK;
}
- if (ublk_can_use_task_work(ubq)) {
- struct ublk_rq_data *data = blk_mq_rq_to_pdu(rq);
- enum task_work_notify_mode notify_mode = bd->last ?
- TWA_SIGNAL_NO_IPI : TWA_NONE;
-
- if (task_work_add(ubq->ubq_daemon, &data->work, notify_mode))
- goto fail;
- } else {
- struct ublk_io *io = &ubq->ios[rq->tag];
- struct io_uring_cmd *cmd = io->cmd;
- struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
-
- /*
- * If the check pass, we know that this is a re-issued request aborted
- * previously in monitor_work because the ubq_daemon(cmd's task) is
- * PF_EXITING. We cannot call io_uring_cmd_complete_in_task() anymore
- * because this ioucmd's io_uring context may be freed now if no inflight
- * ioucmd exists. Otherwise we may cause null-deref in ctx->fallback_work.
- *
- * Note: monitor_work sets UBLK_IO_FLAG_ABORTED and ends this request(releasing
- * the tag). Then the request is re-started(allocating the tag) and we are here.
- * Since releasing/allocating a tag implies smp_mb(), finding UBLK_IO_FLAG_ABORTED
- * guarantees that here is a re-issued request aborted previously.
- */
- if ((io->flags & UBLK_IO_FLAG_ABORTED))
- goto fail;
-
- pdu->req = rq;
- io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
- }
+ ublk_queue_cmd(ubq, rq, bd->last);
return BLK_STS_OK;
}
@@ -1164,22 +1192,12 @@ static void ublk_mark_io_ready(struct ublk_device *ub, struct ublk_queue *ubq)
}
static void ublk_handle_need_get_data(struct ublk_device *ub, int q_id,
- int tag, struct io_uring_cmd *cmd)
+ int tag)
{
struct ublk_queue *ubq = ublk_get_queue(ub, q_id);
struct request *req = blk_mq_tag_to_rq(ub->tag_set.tags[q_id], tag);
- if (ublk_can_use_task_work(ubq)) {
- struct ublk_rq_data *data = blk_mq_rq_to_pdu(req);
-
- /* should not fail since we call it just in ubq->ubq_daemon */
- task_work_add(ubq->ubq_daemon, &data->work, TWA_SIGNAL_NO_IPI);
- } else {
- struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
-
- pdu->req = req;
- io_uring_cmd_complete_in_task(cmd, ublk_rq_task_work_cb);
- }
+ ublk_queue_cmd(ubq, req, true);
}
static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
@@ -1267,7 +1285,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags)
io->addr = ub_cmd->addr;
io->cmd = cmd;
io->flags |= UBLK_IO_FLAG_ACTIVE;
- ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag, cmd);
+ ublk_handle_need_get_data(ub, ub_cmd->q_id, ub_cmd->tag);
break;
default:
goto out;
@@ -1658,6 +1676,9 @@ static int ublk_ctrl_add_dev(struct io_uring_cmd *cmd)
*/
ub->dev_info.flags &= UBLK_F_ALL;
+ if (!IS_BUILTIN(CONFIG_BLK_DEV_UBLK))
+ ub->dev_info.flags |= UBLK_F_URING_CMD_COMP_IN_TASK;
+
/* We are not ready to support zero copy */
ub->dev_info.flags &= ~UBLK_F_SUPPORT_ZERO_COPY;
diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c
index 67c21263f9e0..fd281d439505 100644
--- a/drivers/bluetooth/virtio_bt.c
+++ b/drivers/bluetooth/virtio_bt.c
@@ -219,7 +219,7 @@ static void virtbt_rx_work(struct work_struct *work)
if (!skb)
return;
- skb->len = len;
+ skb_put(skb, len);
virtbt_rx_handle(vbt, skb);
if (virtbt_add_inbuf(vbt) < 0)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 2fe28eeb2f38..69754155300e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -791,13 +791,13 @@ void __init random_init_early(const char *command_line)
#endif
for (i = 0, arch_bits = sizeof(entropy) * 8; i < ARRAY_SIZE(entropy);) {
- longs = arch_get_random_seed_longs(entropy, ARRAY_SIZE(entropy) - i);
+ longs = arch_get_random_seed_longs_early(entropy, ARRAY_SIZE(entropy) - i);
if (longs) {
_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
i += longs;
continue;
}
- longs = arch_get_random_longs(entropy, ARRAY_SIZE(entropy) - i);
+ longs = arch_get_random_longs_early(entropy, ARRAY_SIZE(entropy) - i);
if (longs) {
_mix_pool_bytes(entropy, sizeof(*entropy) * longs);
i += longs;
diff --git a/drivers/clk/clk-renesas-pcie.c b/drivers/clk/clk-renesas-pcie.c
index 4f5df1fc74b4..e6247141d0c0 100644
--- a/drivers/clk/clk-renesas-pcie.c
+++ b/drivers/clk/clk-renesas-pcie.c
@@ -90,13 +90,66 @@ static const struct regmap_access_table rs9_writeable_table = {
.n_yes_ranges = ARRAY_SIZE(rs9_writeable_ranges),
};
+static int rs9_regmap_i2c_write(void *context,
+ unsigned int reg, unsigned int val)
+{
+ struct i2c_client *i2c = context;
+ const u8 data[3] = { reg, 1, val };
+ const int count = ARRAY_SIZE(data);
+ int ret;
+
+ ret = i2c_master_send(i2c, data, count);
+ if (ret == count)
+ return 0;
+ else if (ret < 0)
+ return ret;
+ else
+ return -EIO;
+}
+
+static int rs9_regmap_i2c_read(void *context,
+ unsigned int reg, unsigned int *val)
+{
+ struct i2c_client *i2c = context;
+ struct i2c_msg xfer[2];
+ u8 txdata = reg;
+ u8 rxdata[2];
+ int ret;
+
+ xfer[0].addr = i2c->addr;
+ xfer[0].flags = 0;
+ xfer[0].len = 1;
+ xfer[0].buf = (void *)&txdata;
+
+ xfer[1].addr = i2c->addr;
+ xfer[1].flags = I2C_M_RD;
+ xfer[1].len = 2;
+ xfer[1].buf = (void *)rxdata;
+
+ ret = i2c_transfer(i2c->adapter, xfer, 2);
+ if (ret < 0)
+ return ret;
+ if (ret != 2)
+ return -EIO;
+
+ /*
+ * Byte 0 is transfer length, which is always 1 due
+ * to BCP register programming to 1 in rs9_probe(),
+ * ignore it and use data from Byte 1.
+ */
+ *val = rxdata[1];
+ return 0;
+}
+
static const struct regmap_config rs9_regmap_config = {
.reg_bits = 8,
.val_bits = 8,
- .cache_type = REGCACHE_FLAT,
- .max_register = 0x8,
+ .cache_type = REGCACHE_NONE,
+ .max_register = RS9_REG_BCP,
.rd_table = &rs9_readable_table,
.wr_table = &rs9_writeable_table,
+ .reg_write = rs9_regmap_i2c_write,
+ .reg_read = rs9_regmap_i2c_read,
};
static int rs9_get_output_config(struct rs9_driver_data *rs9, int idx)
@@ -242,11 +295,17 @@ static int rs9_probe(struct i2c_client *client)
return ret;
}
- rs9->regmap = devm_regmap_init_i2c(client, &rs9_regmap_config);
+ rs9->regmap = devm_regmap_init(&client->dev, NULL,
+ client, &rs9_regmap_config);
if (IS_ERR(rs9->regmap))
return dev_err_probe(&client->dev, PTR_ERR(rs9->regmap),
"Failed to allocate register map\n");
+ /* Always read back 1 Byte via I2C */
+ ret = regmap_write(rs9->regmap, RS9_REG_BCP, 1);
+ if (ret < 0)
+ return ret;
+
/* Register clock */
for (i = 0; i < rs9->chip_info->num_clks; i++) {
snprintf(name, 5, "DIF%d", i);
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index c3c3f8c07258..57b83665e5c3 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -1459,10 +1459,14 @@ static void clk_core_init_rate_req(struct clk_core * const core,
{
struct clk_core *parent;
- if (WARN_ON(!core || !req))
+ if (WARN_ON(!req))
return;
memset(req, 0, sizeof(*req));
+ req->max_rate = ULONG_MAX;
+
+ if (!core)
+ return;
req->rate = rate;
clk_core_get_boundaries(core, &req->min_rate, &req->max_rate);
diff --git a/drivers/clk/mediatek/clk-mt8195-topckgen.c b/drivers/clk/mediatek/clk-mt8195-topckgen.c
index 8cbab5ca2e58..1e016329c1d2 100644
--- a/drivers/clk/mediatek/clk-mt8195-topckgen.c
+++ b/drivers/clk/mediatek/clk-mt8195-topckgen.c
@@ -1270,8 +1270,10 @@ static int clk_mt8195_topck_probe(struct platform_device *pdev)
hw = devm_clk_hw_register_mux(&pdev->dev, "mfg_ck_fast_ref", mfg_fast_parents,
ARRAY_SIZE(mfg_fast_parents), CLK_SET_RATE_PARENT,
(base + 0x250), 8, 1, 0, &mt8195_clk_lock);
- if (IS_ERR(hw))
+ if (IS_ERR(hw)) {
+ r = PTR_ERR(hw);
goto unregister_muxes;
+ }
top_clk_data->hws[CLK_TOP_MFG_CK_FAST_REF] = hw;
r = clk_mt8195_reg_mfg_mux_notifier(&pdev->dev,
diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c
index 8afb7575e712..46d41ebce2b0 100644
--- a/drivers/clk/qcom/gcc-sc7280.c
+++ b/drivers/clk/qcom/gcc-sc7280.c
@@ -3467,6 +3467,7 @@ static int gcc_sc7280_probe(struct platform_device *pdev)
regmap_update_bits(regmap, 0x28004, BIT(0), BIT(0));
regmap_update_bits(regmap, 0x28014, BIT(0), BIT(0));
regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0));
+ regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13));
ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks,
ARRAY_SIZE(gcc_dfs_clocks));
diff --git a/drivers/clk/qcom/gpucc-sc7280.c b/drivers/clk/qcom/gpucc-sc7280.c
index 9a832f2bcf49..1490cd45a654 100644
--- a/drivers/clk/qcom/gpucc-sc7280.c
+++ b/drivers/clk/qcom/gpucc-sc7280.c
@@ -463,6 +463,7 @@ static int gpu_cc_sc7280_probe(struct platform_device *pdev)
*/
regmap_update_bits(regmap, 0x1170, BIT(0), BIT(0));
regmap_update_bits(regmap, 0x1098, BIT(0), BIT(0));
+ regmap_update_bits(regmap, 0x1098, BIT(13), BIT(13));
return qcom_cc_really_probe(pdev, &gpu_cc_sc7280_desc, regmap);
}
diff --git a/drivers/clk/renesas/r8a779g0-cpg-mssr.c b/drivers/clk/renesas/r8a779g0-cpg-mssr.c
index 9641122133b5..d5b325e3c539 100644
--- a/drivers/clk/renesas/r8a779g0-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a779g0-cpg-mssr.c
@@ -47,6 +47,7 @@ enum clk_ids {
CLK_S0_VIO,
CLK_S0_VC,
CLK_S0_HSC,
+ CLK_SASYNCPER,
CLK_SV_VIP,
CLK_SV_IR,
CLK_SDSRC,
@@ -84,6 +85,7 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = {
DEF_FIXED(".s0_vio", CLK_S0_VIO, CLK_PLL1_DIV2, 2, 1),
DEF_FIXED(".s0_vc", CLK_S0_VC, CLK_PLL1_DIV2, 2, 1),
DEF_FIXED(".s0_hsc", CLK_S0_HSC, CLK_PLL1_DIV2, 2, 1),
+ DEF_FIXED(".sasyncper", CLK_SASYNCPER, CLK_PLL5_DIV4, 3, 1),
DEF_FIXED(".sv_vip", CLK_SV_VIP, CLK_PLL1, 5, 1),
DEF_FIXED(".sv_ir", CLK_SV_IR, CLK_PLL1, 5, 1),
DEF_BASE(".sdsrc", CLK_SDSRC, CLK_TYPE_GEN4_SDSRC, CLK_PLL5),
@@ -128,6 +130,9 @@ static const struct cpg_core_clk r8a779g0_core_clks[] __initconst = {
DEF_FIXED("s0d4_hsc", R8A779G0_CLK_S0D4_HSC, CLK_S0_HSC, 4, 1),
DEF_FIXED("cl16m_hsc", R8A779G0_CLK_CL16M_HSC, CLK_S0_HSC, 48, 1),
DEF_FIXED("s0d2_cc", R8A779G0_CLK_S0D2_CC, CLK_S0, 2, 1),
+ DEF_FIXED("sasyncperd1",R8A779G0_CLK_SASYNCPERD1, CLK_SASYNCPER,1, 1),
+ DEF_FIXED("sasyncperd2",R8A779G0_CLK_SASYNCPERD2, CLK_SASYNCPER,2, 1),
+ DEF_FIXED("sasyncperd4",R8A779G0_CLK_SASYNCPERD4, CLK_SASYNCPER,4, 1),
DEF_FIXED("svd1_ir", R8A779G0_CLK_SVD1_IR, CLK_SV_IR, 1, 1),
DEF_FIXED("svd2_ir", R8A779G0_CLK_SVD2_IR, CLK_SV_IR, 2, 1),
DEF_FIXED("svd1_vip", R8A779G0_CLK_SVD1_VIP, CLK_SV_VIP, 1, 1),
@@ -153,10 +158,10 @@ static const struct mssr_mod_clk r8a779g0_mod_clks[] __initconst = {
DEF_MOD("avb0", 211, R8A779G0_CLK_S0D4_HSC),
DEF_MOD("avb1", 212, R8A779G0_CLK_S0D4_HSC),
DEF_MOD("avb2", 213, R8A779G0_CLK_S0D4_HSC),
- DEF_MOD("hscif0", 514, R8A779G0_CLK_S0D3_PER),
- DEF_MOD("hscif1", 515, R8A779G0_CLK_S0D3_PER),
- DEF_MOD("hscif2", 516, R8A779G0_CLK_S0D3_PER),
- DEF_MOD("hscif3", 517, R8A779G0_CLK_S0D3_PER),
+ DEF_MOD("hscif0", 514, R8A779G0_CLK_SASYNCPERD1),
+ DEF_MOD("hscif1", 515, R8A779G0_CLK_SASYNCPERD1),
+ DEF_MOD("hscif2", 516, R8A779G0_CLK_SASYNCPERD1),
+ DEF_MOD("hscif3", 517, R8A779G0_CLK_SASYNCPERD1),
DEF_MOD("i2c0", 518, R8A779G0_CLK_S0D6_PER),
DEF_MOD("i2c1", 519, R8A779G0_CLK_S0D6_PER),
DEF_MOD("i2c2", 520, R8A779G0_CLK_S0D6_PER),
diff --git a/drivers/clk/sifive/Kconfig b/drivers/clk/sifive/Kconfig
index 9132c3c4aa86..b7fde0aadfcb 100644
--- a/drivers/clk/sifive/Kconfig
+++ b/drivers/clk/sifive/Kconfig
@@ -2,7 +2,8 @@
menuconfig CLK_SIFIVE
bool "SiFive SoC driver support"
- depends on RISCV || COMPILE_TEST
+ depends on SOC_SIFIVE || COMPILE_TEST
+ default SOC_SIFIVE
help
SoC drivers for SiFive Linux-capable SoCs.
@@ -10,6 +11,7 @@ if CLK_SIFIVE
config CLK_SIFIVE_PRCI
bool "PRCI driver for SiFive SoCs"
+ default SOC_SIFIVE
select RESET_CONTROLLER
select RESET_SIMPLE
select CLK_ANALOGBITS_WRPLL_CLN28HPC
diff --git a/drivers/counter/104-quad-8.c b/drivers/counter/104-quad-8.c
index 77a863b7eefe..deed4afadb29 100644
--- a/drivers/counter/104-quad-8.c
+++ b/drivers/counter/104-quad-8.c
@@ -232,34 +232,45 @@ static const enum counter_function quad8_count_functions_list[] = {
COUNTER_FUNCTION_QUADRATURE_X4,
};
+static int quad8_function_get(const struct quad8 *const priv, const size_t id,
+ enum counter_function *const function)
+{
+ if (!priv->quadrature_mode[id]) {
+ *function = COUNTER_FUNCTION_PULSE_DIRECTION;
+ return 0;
+ }
+
+ switch (priv->quadrature_scale[id]) {
+ case 0:
+ *function = COUNTER_FUNCTION_QUADRATURE_X1_A;
+ return 0;
+ case 1:
+ *function = COUNTER_FUNCTION_QUADRATURE_X2_A;
+ return 0;
+ case 2:
+ *function = COUNTER_FUNCTION_QUADRATURE_X4;
+ return 0;
+ default:
+ /* should never reach this path */
+ return -EINVAL;
+ }
+}
+
static int quad8_function_read(struct counter_device *counter,
struct counter_count *count,
enum counter_function *function)
{
struct quad8 *const priv = counter_priv(counter);
- const int id = count->id;
unsigned long irqflags;
+ int retval;
spin_lock_irqsave(&priv->lock, irqflags);
- if (priv->quadrature_mode[id])
- switch (priv->quadrature_scale[id]) {
- case 0:
- *function = COUNTER_FUNCTION_QUADRATURE_X1_A;
- break;
- case 1:
- *function = COUNTER_FUNCTION_QUADRATURE_X2_A;
- break;
- case 2:
- *function = COUNTER_FUNCTION_QUADRATURE_X4;
- break;
- }
- else
- *function = COUNTER_FUNCTION_PULSE_DIRECTION;
+ retval = quad8_function_get(priv, count->id, function);
spin_unlock_irqrestore(&priv->lock, irqflags);
- return 0;
+ return retval;
}
static int quad8_function_write(struct counter_device *counter,
@@ -359,6 +370,7 @@ static int quad8_action_read(struct counter_device *counter,
enum counter_synapse_action *action)
{
struct quad8 *const priv = counter_priv(counter);
+ unsigned long irqflags;
int err;
enum counter_function function;
const size_t signal_a_id = count->synapses[0].signal->id;
@@ -374,9 +386,21 @@ static int quad8_action_read(struct counter_device *counter,
return 0;
}
- err = quad8_function_read(counter, count, &function);
- if (err)
+ spin_lock_irqsave(&priv->lock, irqflags);
+
+ /* Get Count function and direction atomically */
+ err = quad8_function_get(priv, count->id, &function);
+ if (err) {
+ spin_unlock_irqrestore(&priv->lock, irqflags);
+ return err;
+ }
+ err = quad8_direction_read(counter, count, &direction);
+ if (err) {
+ spin_unlock_irqrestore(&priv->lock, irqflags);
return err;
+ }
+
+ spin_unlock_irqrestore(&priv->lock, irqflags);
/* Default action mode */
*action = COUNTER_SYNAPSE_ACTION_NONE;
@@ -389,10 +413,6 @@ static int quad8_action_read(struct counter_device *counter,
return 0;
case COUNTER_FUNCTION_QUADRATURE_X1_A:
if (synapse->signal->id == signal_a_id) {
- err = quad8_direction_read(counter, count, &direction);
- if (err)
- return err;
-
if (direction == COUNTER_COUNT_DIRECTION_FORWARD)
*action = COUNTER_SYNAPSE_ACTION_RISING_EDGE;
else
diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c
index f9dee15d9777..e2d1dc6ca668 100644
--- a/drivers/counter/microchip-tcb-capture.c
+++ b/drivers/counter/microchip-tcb-capture.c
@@ -28,7 +28,6 @@ struct mchp_tc_data {
int qdec_mode;
int num_channels;
int channel[2];
- bool trig_inverted;
};
static const enum counter_function mchp_tc_count_functions[] = {
@@ -153,7 +152,7 @@ static int mchp_tc_count_signal_read(struct counter_device *counter,
regmap_read(priv->regmap, ATMEL_TC_REG(priv->channel[0], SR), &sr);
- if (priv->trig_inverted)
+ if (signal->id == 1)
sigstatus = (sr & ATMEL_TC_MTIOB);
else
sigstatus = (sr & ATMEL_TC_MTIOA);
@@ -171,6 +170,17 @@ static int mchp_tc_count_action_read(struct counter_device *counter,
struct mchp_tc_data *const priv = counter_priv(counter);
u32 cmr;
+ if (priv->qdec_mode) {
+ *action = COUNTER_SYNAPSE_ACTION_BOTH_EDGES;
+ return 0;
+ }
+
+ /* Only TIOA signal is evaluated in non-QDEC mode */
+ if (synapse->signal->id != 0) {
+ *action = COUNTER_SYNAPSE_ACTION_NONE;
+ return 0;
+ }
+
regmap_read(priv->regmap, ATMEL_TC_REG(priv->channel[0], CMR), &cmr);
switch (cmr & ATMEL_TC_ETRGEDG) {
@@ -199,8 +209,8 @@ static int mchp_tc_count_action_write(struct counter_device *counter,
struct mchp_tc_data *const priv = counter_priv(counter);
u32 edge = ATMEL_TC_ETRGEDG_NONE;
- /* QDEC mode is rising edge only */
- if (priv->qdec_mode)
+ /* QDEC mode is rising edge only; only TIOA handled in non-QDEC mode */
+ if (priv->qdec_mode || synapse->signal->id != 0)
return -EINVAL;
switch (action) {
diff --git a/drivers/counter/ti-ecap-capture.c b/drivers/counter/ti-ecap-capture.c
index af10de30aba5..fb1cb1774674 100644
--- a/drivers/counter/ti-ecap-capture.c
+++ b/drivers/counter/ti-ecap-capture.c
@@ -377,7 +377,8 @@ static const enum counter_signal_polarity ecap_cnt_pol_avail[] = {
COUNTER_SIGNAL_POLARITY_NEGATIVE,
};
-static DEFINE_COUNTER_ARRAY_POLARITY(ecap_cnt_pol_array, ecap_cnt_pol_avail, ECAP_NB_CEVT);
+static DEFINE_COUNTER_AVAILABLE(ecap_cnt_pol_available, ecap_cnt_pol_avail);
+static DEFINE_COUNTER_ARRAY_POLARITY(ecap_cnt_pol_array, ecap_cnt_pol_available, ECAP_NB_CEVT);
static struct counter_comp ecap_cnt_signal_ext[] = {
COUNTER_COMP_ARRAY_POLARITY(ecap_cnt_pol_read, ecap_cnt_pol_write, ecap_cnt_pol_array),
@@ -479,8 +480,8 @@ static int ecap_cnt_probe(struct platform_device *pdev)
int ret;
counter_dev = devm_counter_alloc(dev, sizeof(*ecap_dev));
- if (IS_ERR(counter_dev))
- return PTR_ERR(counter_dev);
+ if (!counter_dev)
+ return -ENOMEM;
counter_dev->name = ECAP_DRV_NAME;
counter_dev->parent = dev;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index fc3ebeb0bbe5..6ff73c30769f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -27,6 +27,7 @@
#include <linux/pm_qos.h>
#include <trace/events/power.h>
+#include <asm/cpu.h>
#include <asm/div64.h>
#include <asm/msr.h>
#include <asm/cpu_device_id.h>
@@ -280,10 +281,10 @@ static struct cpudata **all_cpu_data;
* structure is used to store those callbacks.
*/
struct pstate_funcs {
- int (*get_max)(void);
- int (*get_max_physical)(void);
- int (*get_min)(void);
- int (*get_turbo)(void);
+ int (*get_max)(int cpu);
+ int (*get_max_physical)(int cpu);
+ int (*get_min)(int cpu);
+ int (*get_turbo)(int cpu);
int (*get_scaling)(void);
int (*get_cpu_scaling)(int cpu);
int (*get_aperf_mperf_shift)(void);
@@ -398,16 +399,6 @@ static int intel_pstate_get_cppc_guaranteed(int cpu)
return cppc_perf.nominal_perf;
}
-
-static u32 intel_pstate_cppc_nominal(int cpu)
-{
- u64 nominal_perf;
-
- if (cppc_get_nominal_perf(cpu, &nominal_perf))
- return 0;
-
- return nominal_perf;
-}
#else /* CONFIG_ACPI_CPPC_LIB */
static inline void intel_pstate_set_itmt_prio(int cpu)
{
@@ -531,35 +522,18 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
{
int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
- int perf_ctl_turbo = pstate_funcs.get_turbo();
- int turbo_freq = perf_ctl_turbo * perf_ctl_scaling;
+ int perf_ctl_turbo = pstate_funcs.get_turbo(cpu->cpu);
int scaling = cpu->pstate.scaling;
pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
- pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, pstate_funcs.get_max());
pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);
- /*
- * If the product of the HWP performance scaling factor and the HWP_CAP
- * highest performance is greater than the maximum turbo frequency
- * corresponding to the pstate_funcs.get_turbo() return value, the
- * scaling factor is too high, so recompute it to make the HWP_CAP
- * highest performance correspond to the maximum turbo frequency.
- */
- cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling;
- if (turbo_freq < cpu->pstate.turbo_freq) {
- cpu->pstate.turbo_freq = turbo_freq;
- scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate);
- cpu->pstate.scaling = scaling;
-
- pr_debug("CPU%d: refined HWP-to-frequency scaling factor: %d\n",
- cpu->cpu, scaling);
- }
-
+ cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling,
+ perf_ctl_scaling);
cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
perf_ctl_scaling);
@@ -1740,7 +1714,7 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
intel_pstate_update_epp_defaults(cpudata);
}
-static int atom_get_min_pstate(void)
+static int atom_get_min_pstate(int not_used)
{
u64 value;
@@ -1748,7 +1722,7 @@ static int atom_get_min_pstate(void)
return (value >> 8) & 0x7F;
}
-static int atom_get_max_pstate(void)
+static int atom_get_max_pstate(int not_used)
{
u64 value;
@@ -1756,7 +1730,7 @@ static int atom_get_max_pstate(void)
return (value >> 16) & 0x7F;
}
-static int atom_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(int not_used)
{
u64 value;
@@ -1834,23 +1808,23 @@ static void atom_get_vid(struct cpudata *cpudata)
cpudata->vid.turbo = value & 0x7f;
}
-static int core_get_min_pstate(void)
+static int core_get_min_pstate(int cpu)
{
u64 value;
- rdmsrl(MSR_PLATFORM_INFO, value);
+ rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
return (value >> 40) & 0xFF;
}
-static int core_get_max_pstate_physical(void)
+static int core_get_max_pstate_physical(int cpu)
{
u64 value;
- rdmsrl(MSR_PLATFORM_INFO, value);
+ rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &value);
return (value >> 8) & 0xFF;
}
-static int core_get_tdp_ratio(u64 plat_info)
+static int core_get_tdp_ratio(int cpu, u64 plat_info)
{
/* Check how many TDP levels present */
if (plat_info & 0x600000000) {
@@ -1860,13 +1834,13 @@ static int core_get_tdp_ratio(u64 plat_info)
int err;
/* Get the TDP level (0, 1, 2) to get ratios */
- err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+ err = rdmsrl_safe_on_cpu(cpu, MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
if (err)
return err;
/* TDP MSR are continuous starting at 0x648 */
tdp_msr = MSR_CONFIG_TDP_NOMINAL + (tdp_ctrl & 0x03);
- err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+ err = rdmsrl_safe_on_cpu(cpu, tdp_msr, &tdp_ratio);
if (err)
return err;
@@ -1883,7 +1857,7 @@ static int core_get_tdp_ratio(u64 plat_info)
return -ENXIO;
}
-static int core_get_max_pstate(void)
+static int core_get_max_pstate(int cpu)
{
u64 tar;
u64 plat_info;
@@ -1891,10 +1865,10 @@ static int core_get_max_pstate(void)
int tdp_ratio;
int err;
- rdmsrl(MSR_PLATFORM_INFO, plat_info);
+ rdmsrl_on_cpu(cpu, MSR_PLATFORM_INFO, &plat_info);
max_pstate = (plat_info >> 8) & 0xFF;
- tdp_ratio = core_get_tdp_ratio(plat_info);
+ tdp_ratio = core_get_tdp_ratio(cpu, plat_info);
if (tdp_ratio <= 0)
return max_pstate;
@@ -1903,7 +1877,7 @@ static int core_get_max_pstate(void)
return tdp_ratio;
}
- err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
+ err = rdmsrl_safe_on_cpu(cpu, MSR_TURBO_ACTIVATION_RATIO, &tar);
if (!err) {
int tar_levels;
@@ -1918,13 +1892,13 @@ static int core_get_max_pstate(void)
return max_pstate;
}
-static int core_get_turbo_pstate(void)
+static int core_get_turbo_pstate(int cpu)
{
u64 value;
int nont, ret;
- rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
- nont = core_get_max_pstate();
+ rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+ nont = core_get_max_pstate(cpu);
ret = (value) & 255;
if (ret <= nont)
ret = nont;
@@ -1952,50 +1926,37 @@ static int knl_get_aperf_mperf_shift(void)
return 10;
}
-static int knl_get_turbo_pstate(void)
+static int knl_get_turbo_pstate(int cpu)
{
u64 value;
int nont, ret;
- rdmsrl(MSR_TURBO_RATIO_LIMIT, value);
- nont = core_get_max_pstate();
+ rdmsrl_on_cpu(cpu, MSR_TURBO_RATIO_LIMIT, &value);
+ nont = core_get_max_pstate(cpu);
ret = (((value) >> 8) & 0xFF);
if (ret <= nont)
ret = nont;
return ret;
}
-#ifdef CONFIG_ACPI_CPPC_LIB
-static u32 hybrid_ref_perf;
-
-static int hybrid_get_cpu_scaling(int cpu)
+static void hybrid_get_type(void *data)
{
- return DIV_ROUND_UP(core_get_scaling() * hybrid_ref_perf,
- intel_pstate_cppc_nominal(cpu));
+ u8 *cpu_type = data;
+
+ *cpu_type = get_this_hybrid_cpu_type();
}
-static void intel_pstate_cppc_set_cpu_scaling(void)
+static int hybrid_get_cpu_scaling(int cpu)
{
- u32 min_nominal_perf = U32_MAX;
- int cpu;
+ u8 cpu_type = 0;
- for_each_present_cpu(cpu) {
- u32 nominal_perf = intel_pstate_cppc_nominal(cpu);
+ smp_call_function_single(cpu, hybrid_get_type, &cpu_type, 1);
+ /* P-cores have a smaller perf level-to-freqency scaling factor. */
+ if (cpu_type == 0x40)
+ return 78741;
- if (nominal_perf && nominal_perf < min_nominal_perf)
- min_nominal_perf = nominal_perf;
- }
-
- if (min_nominal_perf < U32_MAX) {
- hybrid_ref_perf = min_nominal_perf;
- pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
- }
+ return core_get_scaling();
}
-#else
-static inline void intel_pstate_cppc_set_cpu_scaling(void)
-{
-}
-#endif /* CONFIG_ACPI_CPPC_LIB */
static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
{
@@ -2025,10 +1986,10 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu)
static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
{
- int perf_ctl_max_phys = pstate_funcs.get_max_physical();
+ int perf_ctl_max_phys = pstate_funcs.get_max_physical(cpu->cpu);
int perf_ctl_scaling = pstate_funcs.get_scaling();
- cpu->pstate.min_pstate = pstate_funcs.get_min();
+ cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu);
cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;
@@ -2044,8 +2005,8 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
}
} else {
cpu->pstate.scaling = perf_ctl_scaling;
- cpu->pstate.max_pstate = pstate_funcs.get_max();
- cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
+ cpu->pstate.max_pstate = pstate_funcs.get_max(cpu->cpu);
+ cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(cpu->cpu);
}
if (cpu->pstate.scaling == perf_ctl_scaling) {
@@ -3221,9 +3182,9 @@ static unsigned int force_load __initdata;
static int __init intel_pstate_msrs_not_valid(void)
{
- if (!pstate_funcs.get_max() ||
- !pstate_funcs.get_min() ||
- !pstate_funcs.get_turbo())
+ if (!pstate_funcs.get_max(0) ||
+ !pstate_funcs.get_min(0) ||
+ !pstate_funcs.get_turbo(0))
return -ENODEV;
return 0;
@@ -3450,7 +3411,7 @@ static int __init intel_pstate_init(void)
default_driver = &intel_pstate;
if (boot_cpu_has(X86_FEATURE_HYBRID_CPU))
- intel_pstate_cppc_set_cpu_scaling();
+ pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
goto hwp_cpu_matched;
}
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 16176b9278b4..0c90f13870a4 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -174,7 +174,7 @@ int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in,
};
int rc;
- if (out_size > cxlds->payload_size)
+ if (in_size > cxlds->payload_size || out_size > cxlds->payload_size)
return -E2BIG;
rc = cxlds->mbox_send(cxlds, &mbox_cmd);
diff --git a/drivers/cxl/core/pmem.c b/drivers/cxl/core/pmem.c
index 1d12a8206444..36aa5070d902 100644
--- a/drivers/cxl/core/pmem.c
+++ b/drivers/cxl/core/pmem.c
@@ -188,6 +188,7 @@ static void cxl_nvdimm_release(struct device *dev)
{
struct cxl_nvdimm *cxl_nvd = to_cxl_nvdimm(dev);
+ xa_destroy(&cxl_nvd->pmem_regions);
kfree(cxl_nvd);
}
@@ -230,6 +231,7 @@ static struct cxl_nvdimm *cxl_nvdimm_alloc(struct cxl_memdev *cxlmd)
dev = &cxl_nvd->dev;
cxl_nvd->cxlmd = cxlmd;
+ xa_init(&cxl_nvd->pmem_regions);
device_initialize(dev);
lockdep_set_class(&dev->mutex, &cxl_nvdimm_key);
device_set_pm_not_required(dev);
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index bffde862de0b..e7556864ea80 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -811,6 +811,7 @@ static struct cxl_dport *find_dport(struct cxl_port *port, int id)
static int add_dport(struct cxl_port *port, struct cxl_dport *new)
{
struct cxl_dport *dup;
+ int rc;
device_lock_assert(&port->dev);
dup = find_dport(port, new->port_id);
@@ -821,8 +822,14 @@ static int add_dport(struct cxl_port *port, struct cxl_dport *new)
dev_name(dup->dport));
return -EBUSY;
}
- return xa_insert(&port->dports, (unsigned long)new->dport, new,
- GFP_KERNEL);
+
+ rc = xa_insert(&port->dports, (unsigned long)new->dport, new,
+ GFP_KERNEL);
+ if (rc)
+ return rc;
+
+ port->nr_dports++;
+ return 0;
}
/*
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 401148016978..f9ae5ad284ff 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -174,7 +174,8 @@ static int cxl_region_decode_commit(struct cxl_region *cxlr)
iter = to_cxl_port(iter->dev.parent)) {
cxl_rr = cxl_rr_load(iter, cxlr);
cxld = cxl_rr->decoder;
- rc = cxld->commit(cxld);
+ if (cxld->commit)
+ rc = cxld->commit(cxld);
if (rc)
break;
}
@@ -657,6 +658,9 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
xa_for_each(&port->regions, index, iter) {
struct cxl_region_params *ip = &iter->region->params;
+ if (!ip->res)
+ continue;
+
if (ip->res->start > p->res->start) {
dev_dbg(&cxlr->dev,
"%s: HPA order violation %s:%pr vs %pr\n",
@@ -686,18 +690,27 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
return cxl_rr;
}
-static void free_region_ref(struct cxl_region_ref *cxl_rr)
+static void cxl_rr_free_decoder(struct cxl_region_ref *cxl_rr)
{
- struct cxl_port *port = cxl_rr->port;
struct cxl_region *cxlr = cxl_rr->region;
struct cxl_decoder *cxld = cxl_rr->decoder;
+ if (!cxld)
+ return;
+
dev_WARN_ONCE(&cxlr->dev, cxld->region != cxlr, "region mismatch\n");
if (cxld->region == cxlr) {
cxld->region = NULL;
put_device(&cxlr->dev);
}
+}
+static void free_region_ref(struct cxl_region_ref *cxl_rr)
+{
+ struct cxl_port *port = cxl_rr->port;
+ struct cxl_region *cxlr = cxl_rr->region;
+
+ cxl_rr_free_decoder(cxl_rr);
xa_erase(&port->regions, (unsigned long)cxlr);
xa_destroy(&cxl_rr->endpoints);
kfree(cxl_rr);
@@ -728,6 +741,33 @@ static int cxl_rr_ep_add(struct cxl_region_ref *cxl_rr,
return 0;
}
+static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
+ struct cxl_endpoint_decoder *cxled,
+ struct cxl_region_ref *cxl_rr)
+{
+ struct cxl_decoder *cxld;
+
+ if (port == cxled_to_port(cxled))
+ cxld = &cxled->cxld;
+ else
+ cxld = cxl_region_find_decoder(port, cxlr);
+ if (!cxld) {
+ dev_dbg(&cxlr->dev, "%s: no decoder available\n",
+ dev_name(&port->dev));
+ return -EBUSY;
+ }
+
+ if (cxld->region) {
+ dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n",
+ dev_name(&port->dev), dev_name(&cxld->dev),
+ dev_name(&cxld->region->dev));
+ return -EBUSY;
+ }
+
+ cxl_rr->decoder = cxld;
+ return 0;
+}
+
/**
* cxl_port_attach_region() - track a region's interest in a port by endpoint
* @port: port to add a new region reference 'struct cxl_region_ref'
@@ -794,12 +834,6 @@ static int cxl_port_attach_region(struct cxl_port *port,
cxl_rr->nr_targets++;
nr_targets_inc = true;
}
-
- /*
- * The decoder for @cxlr was allocated when the region was first
- * attached to @port.
- */
- cxld = cxl_rr->decoder;
} else {
cxl_rr = alloc_region_ref(port, cxlr);
if (IS_ERR(cxl_rr)) {
@@ -810,26 +844,11 @@ static int cxl_port_attach_region(struct cxl_port *port,
}
nr_targets_inc = true;
- if (port == cxled_to_port(cxled))
- cxld = &cxled->cxld;
- else
- cxld = cxl_region_find_decoder(port, cxlr);
- if (!cxld) {
- dev_dbg(&cxlr->dev, "%s: no decoder available\n",
- dev_name(&port->dev));
- goto out_erase;
- }
-
- if (cxld->region) {
- dev_dbg(&cxlr->dev, "%s: %s already attached to %s\n",
- dev_name(&port->dev), dev_name(&cxld->dev),
- dev_name(&cxld->region->dev));
- rc = -EBUSY;
+ rc = cxl_rr_alloc_decoder(port, cxlr, cxled, cxl_rr);
+ if (rc)
goto out_erase;
- }
-
- cxl_rr->decoder = cxld;
}
+ cxld = cxl_rr->decoder;
rc = cxl_rr_ep_add(cxl_rr, cxled);
if (rc) {
@@ -971,7 +990,14 @@ static int cxl_port_setup_targets(struct cxl_port *port,
if (cxl_rr->nr_targets_set) {
int i, distance;
- distance = p->nr_targets / cxl_rr->nr_targets;
+ /*
+ * Passthrough ports impose no distance requirements between
+ * peers
+ */
+ if (port->nr_dports == 1)
+ distance = 0;
+ else
+ distance = p->nr_targets / cxl_rr->nr_targets;
for (i = 0; i < cxl_rr->nr_targets_set; i++)
if (ep->dport == cxlsd->target[i]) {
rc = check_last_peer(cxled, ep, cxl_rr,
@@ -1508,9 +1534,24 @@ static const struct attribute_group *region_groups[] = {
static void cxl_region_release(struct device *dev)
{
+ struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(dev->parent);
struct cxl_region *cxlr = to_cxl_region(dev);
+ int id = atomic_read(&cxlrd->region_id);
+
+ /*
+ * Try to reuse the recently idled id rather than the cached
+ * next id to prevent the region id space from increasing
+ * unnecessarily.
+ */
+ if (cxlr->id < id)
+ if (atomic_try_cmpxchg(&cxlrd->region_id, &id, cxlr->id)) {
+ memregion_free(id);
+ goto out;
+ }
memregion_free(cxlr->id);
+out:
+ put_device(dev->parent);
kfree(cxlr);
}
@@ -1538,8 +1579,19 @@ static struct cxl_region *to_cxl_region(struct device *dev)
static void unregister_region(void *dev)
{
struct cxl_region *cxlr = to_cxl_region(dev);
+ struct cxl_region_params *p = &cxlr->params;
+ int i;
device_del(dev);
+
+ /*
+ * Now that region sysfs is shutdown, the parameter block is now
+ * read-only, so no need to hold the region rwsem to access the
+ * region parameters.
+ */
+ for (i = 0; i < p->interleave_ways; i++)
+ detach_target(cxlr, i);
+
cxl_region_iomem_release(cxlr);
put_device(dev);
}
@@ -1561,6 +1613,11 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i
device_initialize(dev);
lockdep_set_class(&dev->mutex, &cxl_region_key);
dev->parent = &cxlrd->cxlsd.cxld.dev;
+ /*
+ * Keep root decoder pinned through cxl_region_release to fixup
+ * region id allocations
+ */
+ get_device(dev->parent);
device_set_pm_not_required(dev);
dev->bus = &cxl_bus_type;
dev->type = &cxl_region_type;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index f680450f0b16..ac75554b5d76 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -423,7 +423,7 @@ struct cxl_nvdimm {
struct device dev;
struct cxl_memdev *cxlmd;
struct cxl_nvdimm_bridge *bridge;
- struct cxl_pmem_region *region;
+ struct xarray pmem_regions;
};
struct cxl_pmem_region_mapping {
@@ -457,6 +457,7 @@ struct cxl_pmem_region {
* @regions: cxl_region_ref instances, regions mapped by this port
* @parent_dport: dport that points to this port in the parent
* @decoder_ida: allocator for decoder ids
+ * @nr_dports: number of entries in @dports
* @hdm_end: track last allocated HDM decoder instance for allocation ordering
* @commit_end: cursor to track highest committed decoder for commit ordering
* @component_reg_phys: component register capability base address (optional)
@@ -475,6 +476,7 @@ struct cxl_port {
struct xarray regions;
struct cxl_dport *parent_dport;
struct ida decoder_ida;
+ int nr_dports;
int hdm_end;
int commit_end;
resource_size_t component_reg_phys;
diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c
index 7dc0a2fa1a6b..4c627d67281a 100644
--- a/drivers/cxl/pmem.c
+++ b/drivers/cxl/pmem.c
@@ -30,17 +30,20 @@ static void unregister_nvdimm(void *nvdimm)
struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm);
struct cxl_nvdimm_bridge *cxl_nvb = cxl_nvd->bridge;
struct cxl_pmem_region *cxlr_pmem;
+ unsigned long index;
device_lock(&cxl_nvb->dev);
- cxlr_pmem = cxl_nvd->region;
dev_set_drvdata(&cxl_nvd->dev, NULL);
- cxl_nvd->region = NULL;
- device_unlock(&cxl_nvb->dev);
+ xa_for_each(&cxl_nvd->pmem_regions, index, cxlr_pmem) {
+ get_device(&cxlr_pmem->dev);
+ device_unlock(&cxl_nvb->dev);
- if (cxlr_pmem) {
device_release_driver(&cxlr_pmem->dev);
put_device(&cxlr_pmem->dev);
+
+ device_lock(&cxl_nvb->dev);
}
+ device_unlock(&cxl_nvb->dev);
nvdimm_delete(nvdimm);
cxl_nvd->bridge = NULL;
@@ -107,7 +110,7 @@ static int cxl_pmem_get_config_size(struct cxl_dev_state *cxlds,
*cmd = (struct nd_cmd_get_config_size) {
.config_size = cxlds->lsa_size,
- .max_xfer = cxlds->payload_size,
+ .max_xfer = cxlds->payload_size - sizeof(struct cxl_mbox_set_lsa),
};
return 0;
@@ -148,7 +151,7 @@ static int cxl_pmem_set_config_data(struct cxl_dev_state *cxlds,
return -EINVAL;
/* 4-byte status follows the input data in the payload */
- if (struct_size(cmd, in_buf, cmd->in_length) + 4 > buf_len)
+ if (size_add(struct_size(cmd, in_buf, cmd->in_length), 4) > buf_len)
return -EINVAL;
set_lsa =
@@ -366,25 +369,49 @@ static int match_cxl_nvdimm(struct device *dev, void *data)
static void unregister_nvdimm_region(void *nd_region)
{
- struct cxl_nvdimm_bridge *cxl_nvb;
- struct cxl_pmem_region *cxlr_pmem;
+ nvdimm_region_delete(nd_region);
+}
+
+static int cxl_nvdimm_add_region(struct cxl_nvdimm *cxl_nvd,
+ struct cxl_pmem_region *cxlr_pmem)
+{
+ int rc;
+
+ rc = xa_insert(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem,
+ cxlr_pmem, GFP_KERNEL);
+ if (rc)
+ return rc;
+
+ get_device(&cxlr_pmem->dev);
+ return 0;
+}
+
+static void cxl_nvdimm_del_region(struct cxl_nvdimm *cxl_nvd,
+ struct cxl_pmem_region *cxlr_pmem)
+{
+ /*
+ * It is possible this is called without a corresponding
+ * cxl_nvdimm_add_region for @cxlr_pmem
+ */
+ cxlr_pmem = xa_erase(&cxl_nvd->pmem_regions, (unsigned long)cxlr_pmem);
+ if (cxlr_pmem)
+ put_device(&cxlr_pmem->dev);
+}
+
+static void release_mappings(void *data)
+{
int i;
+ struct cxl_pmem_region *cxlr_pmem = data;
+ struct cxl_nvdimm_bridge *cxl_nvb = cxlr_pmem->bridge;
- cxlr_pmem = nd_region_provider_data(nd_region);
- cxl_nvb = cxlr_pmem->bridge;
device_lock(&cxl_nvb->dev);
for (i = 0; i < cxlr_pmem->nr_mappings; i++) {
struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i];
struct cxl_nvdimm *cxl_nvd = m->cxl_nvd;
- if (cxl_nvd->region) {
- put_device(&cxlr_pmem->dev);
- cxl_nvd->region = NULL;
- }
+ cxl_nvdimm_del_region(cxl_nvd, cxlr_pmem);
}
device_unlock(&cxl_nvb->dev);
-
- nvdimm_region_delete(nd_region);
}
static void cxlr_pmem_remove_resource(void *res)
@@ -422,7 +449,7 @@ static int cxl_pmem_region_probe(struct device *dev)
if (!cxl_nvb->nvdimm_bus) {
dev_dbg(dev, "nvdimm bus not found\n");
rc = -ENXIO;
- goto err;
+ goto out_nvb;
}
memset(&mappings, 0, sizeof(mappings));
@@ -431,7 +458,7 @@ static int cxl_pmem_region_probe(struct device *dev)
res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL);
if (!res) {
rc = -ENOMEM;
- goto err;
+ goto out_nvb;
}
res->name = "Persistent Memory";
@@ -442,11 +469,11 @@ static int cxl_pmem_region_probe(struct device *dev)
rc = insert_resource(&iomem_resource, res);
if (rc)
- goto err;
+ goto out_nvb;
rc = devm_add_action_or_reset(dev, cxlr_pmem_remove_resource, res);
if (rc)
- goto err;
+ goto out_nvb;
ndr_desc.res = res;
ndr_desc.provider_data = cxlr_pmem;
@@ -462,7 +489,7 @@ static int cxl_pmem_region_probe(struct device *dev)
nd_set = devm_kzalloc(dev, sizeof(*nd_set), GFP_KERNEL);
if (!nd_set) {
rc = -ENOMEM;
- goto err;
+ goto out_nvb;
}
ndr_desc.memregion = cxlr->id;
@@ -472,9 +499,13 @@ static int cxl_pmem_region_probe(struct device *dev)
info = kmalloc_array(cxlr_pmem->nr_mappings, sizeof(*info), GFP_KERNEL);
if (!info) {
rc = -ENOMEM;
- goto err;
+ goto out_nvb;
}
+ rc = devm_add_action_or_reset(dev, release_mappings, cxlr_pmem);
+ if (rc)
+ goto out_nvd;
+
for (i = 0; i < cxlr_pmem->nr_mappings; i++) {
struct cxl_pmem_region_mapping *m = &cxlr_pmem->mapping[i];
struct cxl_memdev *cxlmd = m->cxlmd;
@@ -486,7 +517,7 @@ static int cxl_pmem_region_probe(struct device *dev)
dev_dbg(dev, "[%d]: %s: no cxl_nvdimm found\n", i,
dev_name(&cxlmd->dev));
rc = -ENODEV;
- goto err;
+ goto out_nvd;
}
/* safe to drop ref now with bridge lock held */
@@ -498,10 +529,17 @@ static int cxl_pmem_region_probe(struct device *dev)
dev_dbg(dev, "[%d]: %s: no nvdimm found\n", i,
dev_name(&cxlmd->dev));
rc = -ENODEV;
- goto err;
+ goto out_nvd;
}
- cxl_nvd->region = cxlr_pmem;
- get_device(&cxlr_pmem->dev);
+
+ /*
+ * Pin the region per nvdimm device as those may be released
+ * out-of-order with respect to the region, and a single nvdimm
+ * maybe associated with multiple regions
+ */
+ rc = cxl_nvdimm_add_region(cxl_nvd, cxlr_pmem);
+ if (rc)
+ goto out_nvd;
m->cxl_nvd = cxl_nvd;
mappings[i] = (struct nd_mapping_desc) {
.nvdimm = nvdimm,
@@ -527,27 +565,18 @@ static int cxl_pmem_region_probe(struct device *dev)
nvdimm_pmem_region_create(cxl_nvb->nvdimm_bus, &ndr_desc);
if (!cxlr_pmem->nd_region) {
rc = -ENOMEM;
- goto err;
+ goto out_nvd;
}
rc = devm_add_action_or_reset(dev, unregister_nvdimm_region,
cxlr_pmem->nd_region);
-out:
+out_nvd:
kfree(info);
+out_nvb:
device_unlock(&cxl_nvb->dev);
put_device(&cxl_nvb->dev);
return rc;
-
-err:
- dev_dbg(dev, "failed to create nvdimm region\n");
- for (i--; i >= 0; i--) {
- nvdimm = mappings[i].nvdimm;
- cxl_nvd = nvdimm_provider_data(nvdimm);
- put_device(&cxl_nvd->region->dev);
- cxl_nvd->region = NULL;
- }
- goto out;
}
static struct cxl_driver cxl_pmem_region_driver = {
diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c
index d4e23101448a..35bb70724d44 100644
--- a/drivers/firmware/arm_scmi/bus.c
+++ b/drivers/firmware/arm_scmi/bus.c
@@ -216,9 +216,20 @@ void scmi_device_destroy(struct scmi_device *scmi_dev)
device_unregister(&scmi_dev->dev);
}
+void scmi_device_link_add(struct device *consumer, struct device *supplier)
+{
+ struct device_link *link;
+
+ link = device_link_add(consumer, supplier, DL_FLAG_AUTOREMOVE_CONSUMER);
+
+ WARN_ON(!link);
+}
+
void scmi_set_handle(struct scmi_device *scmi_dev)
{
scmi_dev->handle = scmi_handle_get(&scmi_dev->dev);
+ if (scmi_dev->handle)
+ scmi_device_link_add(&scmi_dev->dev, scmi_dev->handle->dev);
}
int scmi_protocol_register(const struct scmi_protocol *proto)
diff --git a/drivers/firmware/arm_scmi/common.h b/drivers/firmware/arm_scmi/common.h
index 61aba7447c32..a1c0154c31c6 100644
--- a/drivers/firmware/arm_scmi/common.h
+++ b/drivers/firmware/arm_scmi/common.h
@@ -97,6 +97,7 @@ static inline void unpack_scmi_header(u32 msg_hdr, struct scmi_msg_hdr *hdr)
struct scmi_revision_info *
scmi_revision_area_get(const struct scmi_protocol_handle *ph);
int scmi_handle_put(const struct scmi_handle *handle);
+void scmi_device_link_add(struct device *consumer, struct device *supplier);
struct scmi_handle *scmi_handle_get(struct device *dev);
void scmi_set_handle(struct scmi_device *scmi_dev);
void scmi_setup_protocol_implemented(const struct scmi_protocol_handle *ph,
@@ -117,6 +118,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id);
*
* @dev: Reference to device in the SCMI hierarchy corresponding to this
* channel
+ * @rx_timeout_ms: The configured RX timeout in milliseconds.
* @handle: Pointer to SCMI entity handle
* @no_completion_irq: Flag to indicate that this channel has no completion
* interrupt mechanism for synchronous commands.
@@ -126,6 +128,7 @@ void scmi_protocol_release(const struct scmi_handle *handle, u8 protocol_id);
*/
struct scmi_chan_info {
struct device *dev;
+ unsigned int rx_timeout_ms;
struct scmi_handle *handle;
bool no_completion_irq;
void *transport_info;
@@ -232,7 +235,7 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id);
struct scmi_shared_mem;
void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem,
- struct scmi_xfer *xfer);
+ struct scmi_xfer *xfer, struct scmi_chan_info *cinfo);
u32 shmem_read_header(struct scmi_shared_mem __iomem *shmem);
void shmem_fetch_response(struct scmi_shared_mem __iomem *shmem,
struct scmi_xfer *xfer);
diff --git a/drivers/firmware/arm_scmi/driver.c b/drivers/firmware/arm_scmi/driver.c
index 609ebedee9cb..f818d00bb2c6 100644
--- a/drivers/firmware/arm_scmi/driver.c
+++ b/drivers/firmware/arm_scmi/driver.c
@@ -2013,6 +2013,7 @@ static int scmi_chan_setup(struct scmi_info *info, struct device *dev,
return -ENOMEM;
cinfo->dev = dev;
+ cinfo->rx_timeout_ms = info->desc->max_rx_timeout_ms;
ret = info->desc->ops->chan_setup(cinfo, info->dev, tx);
if (ret)
@@ -2044,8 +2045,12 @@ scmi_txrx_setup(struct scmi_info *info, struct device *dev, int prot_id)
{
int ret = scmi_chan_setup(info, dev, prot_id, true);
- if (!ret) /* Rx is optional, hence no error check */
- scmi_chan_setup(info, dev, prot_id, false);
+ if (!ret) {
+ /* Rx is optional, report only memory errors */
+ ret = scmi_chan_setup(info, dev, prot_id, false);
+ if (ret && ret != -ENOMEM)
+ ret = 0;
+ }
return ret;
}
@@ -2273,10 +2278,16 @@ int scmi_protocol_device_request(const struct scmi_device_id *id_table)
sdev = scmi_get_protocol_device(child, info,
id_table->protocol_id,
id_table->name);
- /* Set handle if not already set: device existed */
- if (sdev && !sdev->handle)
- sdev->handle =
- scmi_handle_get_from_info_unlocked(info);
+ if (sdev) {
+ /* Set handle if not already set: device existed */
+ if (!sdev->handle)
+ sdev->handle =
+ scmi_handle_get_from_info_unlocked(info);
+ /* Relink consumer and suppliers */
+ if (sdev->handle)
+ scmi_device_link_add(&sdev->dev,
+ sdev->handle->dev);
+ }
} else {
dev_err(info->dev,
"Failed. SCMI protocol %d not active.\n",
@@ -2475,20 +2486,17 @@ void scmi_free_channel(struct scmi_chan_info *cinfo, struct idr *idr, int id)
static int scmi_remove(struct platform_device *pdev)
{
- int ret = 0, id;
+ int ret, id;
struct scmi_info *info = platform_get_drvdata(pdev);
struct device_node *child;
mutex_lock(&scmi_list_mutex);
if (info->users)
- ret = -EBUSY;
- else
- list_del(&info->node);
+ dev_warn(&pdev->dev,
+ "Still active SCMI users will be forcibly unbound.\n");
+ list_del(&info->node);
mutex_unlock(&scmi_list_mutex);
- if (ret)
- return ret;
-
scmi_notification_exit(&info->handle);
mutex_lock(&info->protocols_mtx);
@@ -2500,7 +2508,11 @@ static int scmi_remove(struct platform_device *pdev)
idr_destroy(&info->active_protocols);
/* Safe to free channels since no more users */
- return scmi_cleanup_txrx_channels(info);
+ ret = scmi_cleanup_txrx_channels(info);
+ if (ret)
+ dev_warn(&pdev->dev, "Failed to cleanup SCMI channels.\n");
+
+ return 0;
}
static ssize_t protocol_version_show(struct device *dev,
@@ -2571,6 +2583,7 @@ MODULE_DEVICE_TABLE(of, scmi_of_match);
static struct platform_driver scmi_driver = {
.driver = {
.name = "arm-scmi",
+ .suppress_bind_attrs = true,
.of_match_table = scmi_of_match,
.dev_groups = versions_groups,
},
diff --git a/drivers/firmware/arm_scmi/mailbox.c b/drivers/firmware/arm_scmi/mailbox.c
index 08ff4d110beb..1e40cb035044 100644
--- a/drivers/firmware/arm_scmi/mailbox.c
+++ b/drivers/firmware/arm_scmi/mailbox.c
@@ -36,7 +36,7 @@ static void tx_prepare(struct mbox_client *cl, void *m)
{
struct scmi_mailbox *smbox = client_to_scmi_mailbox(cl);
- shmem_tx_prepare(smbox->shmem, m);
+ shmem_tx_prepare(smbox->shmem, m, smbox->cinfo);
}
static void rx_callback(struct mbox_client *cl, void *m)
diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c
index f42dad997ac9..2a7aeab40e54 100644
--- a/drivers/firmware/arm_scmi/optee.c
+++ b/drivers/firmware/arm_scmi/optee.c
@@ -498,7 +498,7 @@ static int scmi_optee_send_message(struct scmi_chan_info *cinfo,
msg_tx_prepare(channel->req.msg, xfer);
ret = invoke_process_msg_channel(channel, msg_command_size(xfer));
} else {
- shmem_tx_prepare(channel->req.shmem, xfer);
+ shmem_tx_prepare(channel->req.shmem, xfer, cinfo);
ret = invoke_process_smt_channel(channel);
}
diff --git a/drivers/firmware/arm_scmi/shmem.c b/drivers/firmware/arm_scmi/shmem.c
index 0e3eaea5d852..1dfe534b8518 100644
--- a/drivers/firmware/arm_scmi/shmem.c
+++ b/drivers/firmware/arm_scmi/shmem.c
@@ -5,10 +5,13 @@
* Copyright (C) 2019 ARM Ltd.
*/
+#include <linux/ktime.h>
#include <linux/io.h>
#include <linux/processor.h>
#include <linux/types.h>
+#include <asm-generic/bug.h>
+
#include "common.h"
/*
@@ -30,16 +33,36 @@ struct scmi_shared_mem {
};
void shmem_tx_prepare(struct scmi_shared_mem __iomem *shmem,
- struct scmi_xfer *xfer)
+ struct scmi_xfer *xfer, struct scmi_chan_info *cinfo)
{
+ ktime_t stop;
+
/*
* Ideally channel must be free by now unless OS timeout last
* request and platform continued to process the same, wait
* until it releases the shared memory, otherwise we may endup
- * overwriting its response with new message payload or vice-versa
+ * overwriting its response with new message payload or vice-versa.
+ * Giving up anyway after twice the expected channel timeout so as
+ * not to bail-out on intermittent issues where the platform is
+ * occasionally a bit slower to answer.
+ *
+ * Note that after a timeout is detected we bail-out and carry on but
+ * the transport functionality is probably permanently compromised:
+ * this is just to ease debugging and avoid complete hangs on boot
+ * due to a misbehaving SCMI firmware.
*/
- spin_until_cond(ioread32(&shmem->channel_status) &
- SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE);
+ stop = ktime_add_ms(ktime_get(), 2 * cinfo->rx_timeout_ms);
+ spin_until_cond((ioread32(&shmem->channel_status) &
+ SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE) ||
+ ktime_after(ktime_get(), stop));
+ if (!(ioread32(&shmem->channel_status) &
+ SCMI_SHMEM_CHAN_STAT_CHANNEL_FREE)) {
+ WARN_ON_ONCE(1);
+ dev_err(cinfo->dev,
+ "Timeout waiting for a free TX channel !\n");
+ return;
+ }
+
/* Mark channel busy + clear error */
iowrite32(0x0, &shmem->channel_status);
iowrite32(xfer->hdr.poll_completion ? 0 : SCMI_SHMEM_FLAG_INTR_ENABLED,
diff --git a/drivers/firmware/arm_scmi/smc.c b/drivers/firmware/arm_scmi/smc.c
index 745acfdd0b3d..87a7b13cf868 100644
--- a/drivers/firmware/arm_scmi/smc.c
+++ b/drivers/firmware/arm_scmi/smc.c
@@ -188,7 +188,7 @@ static int smc_send_message(struct scmi_chan_info *cinfo,
*/
smc_channel_lock_acquire(scmi_info, xfer);
- shmem_tx_prepare(scmi_info->shmem, xfer);
+ shmem_tx_prepare(scmi_info->shmem, xfer, cinfo);
arm_smccc_1_1_invoke(scmi_info->func_id, 0, 0, 0, 0, 0, 0, 0, &res);
diff --git a/drivers/firmware/arm_scmi/virtio.c b/drivers/firmware/arm_scmi/virtio.c
index 14709dbc96a1..33c9b81a55cd 100644
--- a/drivers/firmware/arm_scmi/virtio.c
+++ b/drivers/firmware/arm_scmi/virtio.c
@@ -148,7 +148,6 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch)
{
unsigned long flags;
DECLARE_COMPLETION_ONSTACK(vioch_shutdown_done);
- void *deferred_wq = NULL;
/*
* Prepare to wait for the last release if not already released
@@ -162,16 +161,11 @@ static void scmi_vio_channel_cleanup_sync(struct scmi_vio_channel *vioch)
vioch->shutdown_done = &vioch_shutdown_done;
virtio_break_device(vioch->vqueue->vdev);
- if (!vioch->is_rx && vioch->deferred_tx_wq) {
- deferred_wq = vioch->deferred_tx_wq;
+ if (!vioch->is_rx && vioch->deferred_tx_wq)
/* Cannot be kicked anymore after this...*/
vioch->deferred_tx_wq = NULL;
- }
spin_unlock_irqrestore(&vioch->lock, flags);
- if (deferred_wq)
- destroy_workqueue(deferred_wq);
-
scmi_vio_channel_release(vioch);
/* Let any possibly concurrent RX path release the channel */
@@ -416,6 +410,11 @@ static bool virtio_chan_available(struct device *dev, int idx)
return vioch && !vioch->cinfo;
}
+static void scmi_destroy_tx_workqueue(void *deferred_tx_wq)
+{
+ destroy_workqueue(deferred_tx_wq);
+}
+
static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
bool tx)
{
@@ -430,6 +429,8 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
/* Setup a deferred worker for polling. */
if (tx && !vioch->deferred_tx_wq) {
+ int ret;
+
vioch->deferred_tx_wq =
alloc_workqueue(dev_name(&scmi_vdev->dev),
WQ_UNBOUND | WQ_FREEZABLE | WQ_SYSFS,
@@ -437,6 +438,11 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
if (!vioch->deferred_tx_wq)
return -ENOMEM;
+ ret = devm_add_action_or_reset(dev, scmi_destroy_tx_workqueue,
+ vioch->deferred_tx_wq);
+ if (ret)
+ return ret;
+
INIT_WORK(&vioch->deferred_tx_work,
scmi_vio_deferred_tx_worker);
}
@@ -444,12 +450,12 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
for (i = 0; i < vioch->max_msg; i++) {
struct scmi_vio_msg *msg;
- msg = devm_kzalloc(cinfo->dev, sizeof(*msg), GFP_KERNEL);
+ msg = devm_kzalloc(dev, sizeof(*msg), GFP_KERNEL);
if (!msg)
return -ENOMEM;
if (tx) {
- msg->request = devm_kzalloc(cinfo->dev,
+ msg->request = devm_kzalloc(dev,
VIRTIO_SCMI_MAX_PDU_SIZE,
GFP_KERNEL);
if (!msg->request)
@@ -458,7 +464,7 @@ static int virtio_chan_setup(struct scmi_chan_info *cinfo, struct device *dev,
refcount_set(&msg->users, 1);
}
- msg->input = devm_kzalloc(cinfo->dev, VIRTIO_SCMI_MAX_PDU_SIZE,
+ msg->input = devm_kzalloc(dev, VIRTIO_SCMI_MAX_PDU_SIZE,
GFP_KERNEL);
if (!msg->input)
return -ENOMEM;
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 3ecdc43a3f2b..a46df5d1d094 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -611,7 +611,7 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
seed = early_memremap(efi_rng_seed, sizeof(*seed));
if (seed != NULL) {
- size = READ_ONCE(seed->size);
+ size = min(seed->size, EFI_RANDOM_SEED_SIZE);
early_memunmap(seed, sizeof(*seed));
} else {
pr_err("Could not map UEFI random seed!\n");
diff --git a/drivers/firmware/efi/libstub/random.c b/drivers/firmware/efi/libstub/random.c
index 24aa37535372..33ab56769595 100644
--- a/drivers/firmware/efi/libstub/random.c
+++ b/drivers/firmware/efi/libstub/random.c
@@ -75,7 +75,12 @@ efi_status_t efi_random_get_seed(void)
if (status != EFI_SUCCESS)
return status;
- status = efi_bs_call(allocate_pool, EFI_RUNTIME_SERVICES_DATA,
+ /*
+ * Use EFI_ACPI_RECLAIM_MEMORY here so that it is guaranteed that the
+ * allocation will survive a kexec reboot (although we refresh the seed
+ * beforehand)
+ */
+ status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY,
sizeof(*seed) + EFI_RANDOM_SEED_SIZE,
(void **)&seed);
if (status != EFI_SUCCESS)
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index 8f665678e9e3..e8d69bd548f3 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -97,7 +97,7 @@ int __init efi_tpm_eventlog_init(void)
goto out_calc;
}
- memblock_reserve((unsigned long)final_tbl,
+ memblock_reserve(efi.tpm_final_log,
tbl_size + sizeof(*final_tbl));
efi_tpm_final_log_size = tbl_size;
diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c
index 433b61587139..0ba9f18312f5 100644
--- a/drivers/firmware/efi/vars.c
+++ b/drivers/firmware/efi/vars.c
@@ -21,29 +21,22 @@ static struct efivars *__efivars;
static DEFINE_SEMAPHORE(efivars_lock);
-static efi_status_t check_var_size(u32 attributes, unsigned long size)
-{
- const struct efivar_operations *fops;
-
- fops = __efivars->ops;
-
- if (!fops->query_variable_store)
- return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES;
-
- return fops->query_variable_store(attributes, size, false);
-}
-
-static
-efi_status_t check_var_size_nonblocking(u32 attributes, unsigned long size)
+static efi_status_t check_var_size(bool nonblocking, u32 attributes,
+ unsigned long size)
{
const struct efivar_operations *fops;
+ efi_status_t status;
fops = __efivars->ops;
if (!fops->query_variable_store)
+ status = EFI_UNSUPPORTED;
+ else
+ status = fops->query_variable_store(attributes, size,
+ nonblocking);
+ if (status == EFI_UNSUPPORTED)
return (size <= SZ_64K) ? EFI_SUCCESS : EFI_OUT_OF_RESOURCES;
-
- return fops->query_variable_store(attributes, size, true);
+ return status;
}
/**
@@ -196,26 +189,6 @@ efi_status_t efivar_get_next_variable(unsigned long *name_size,
EXPORT_SYMBOL_NS_GPL(efivar_get_next_variable, EFIVAR);
/*
- * efivar_set_variable_blocking() - local helper function for set_variable
- *
- * Must be called with efivars_lock held.
- */
-static efi_status_t
-efivar_set_variable_blocking(efi_char16_t *name, efi_guid_t *vendor,
- u32 attr, unsigned long data_size, void *data)
-{
- efi_status_t status;
-
- if (data_size > 0) {
- status = check_var_size(attr, data_size +
- ucs2_strsize(name, 1024));
- if (status != EFI_SUCCESS)
- return status;
- }
- return __efivars->ops->set_variable(name, vendor, attr, data_size, data);
-}
-
-/*
* efivar_set_variable_locked() - set a variable identified by name/vendor
*
* Must be called with efivars_lock held. If @nonblocking is set, it will use
@@ -228,23 +201,21 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor,
efi_set_variable_t *setvar;
efi_status_t status;
- if (!nonblocking)
- return efivar_set_variable_blocking(name, vendor, attr,
- data_size, data);
+ if (data_size > 0) {
+ status = check_var_size(nonblocking, attr,
+ data_size + ucs2_strsize(name, 1024));
+ if (status != EFI_SUCCESS)
+ return status;
+ }
/*
* If no _nonblocking variant exists, the ordinary one
* is assumed to be non-blocking.
*/
- setvar = __efivars->ops->set_variable_nonblocking ?:
- __efivars->ops->set_variable;
+ setvar = __efivars->ops->set_variable_nonblocking;
+ if (!setvar || !nonblocking)
+ setvar = __efivars->ops->set_variable;
- if (data_size > 0) {
- status = check_var_size_nonblocking(attr, data_size +
- ucs2_strsize(name, 1024));
- if (status != EFI_SUCCESS)
- return status;
- }
return setvar(name, vendor, attr, data_size, data);
}
EXPORT_SYMBOL_NS_GPL(efivar_set_variable_locked, EFIVAR);
@@ -264,7 +235,8 @@ efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor,
if (efivar_lock())
return EFI_ABORTED;
- status = efivar_set_variable_blocking(name, vendor, attr, data_size, data);
+ status = efivar_set_variable_locked(name, vendor, attr, data_size,
+ data, false);
efivar_unlock();
return status;
}
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index e4fb4cb38a0f..5b265a6fd3c1 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -18,6 +18,7 @@
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/module.h>
+#include <linux/seq_file.h>
#include <linux/irqdomain.h>
#include <linux/irqchip/chained_irq.h>
#include <linux/pinctrl/consumer.h>
@@ -94,7 +95,6 @@ struct tegra_gpio_info {
struct tegra_gpio_bank *bank_info;
const struct tegra_gpio_soc_config *soc;
struct gpio_chip gc;
- struct irq_chip ic;
u32 bank_count;
unsigned int *irqs;
};
@@ -288,6 +288,7 @@ static void tegra_gpio_irq_mask(struct irq_data *d)
unsigned int gpio = d->hwirq;
tegra_gpio_mask_write(tgi, GPIO_MSK_INT_ENB(tgi, gpio), gpio, 0);
+ gpiochip_disable_irq(chip, gpio);
}
static void tegra_gpio_irq_unmask(struct irq_data *d)
@@ -296,6 +297,7 @@ static void tegra_gpio_irq_unmask(struct irq_data *d)
struct tegra_gpio_info *tgi = gpiochip_get_data(chip);
unsigned int gpio = d->hwirq;
+ gpiochip_enable_irq(chip, gpio);
tegra_gpio_mask_write(tgi, GPIO_MSK_INT_ENB(tgi, gpio), gpio, 1);
}
@@ -598,10 +600,47 @@ static void tegra_gpio_irq_release_resources(struct irq_data *d)
tegra_gpio_enable(tgi, d->hwirq);
}
+static void tegra_gpio_irq_print_chip(struct irq_data *d, struct seq_file *s)
+{
+ struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+
+ seq_printf(s, dev_name(chip->parent));
+}
+
+static const struct irq_chip tegra_gpio_irq_chip = {
+ .irq_shutdown = tegra_gpio_irq_shutdown,
+ .irq_ack = tegra_gpio_irq_ack,
+ .irq_mask = tegra_gpio_irq_mask,
+ .irq_unmask = tegra_gpio_irq_unmask,
+ .irq_set_type = tegra_gpio_irq_set_type,
+#ifdef CONFIG_PM_SLEEP
+ .irq_set_wake = tegra_gpio_irq_set_wake,
+#endif
+ .irq_print_chip = tegra_gpio_irq_print_chip,
+ .irq_request_resources = tegra_gpio_irq_request_resources,
+ .irq_release_resources = tegra_gpio_irq_release_resources,
+ .flags = IRQCHIP_IMMUTABLE,
+};
+
+static const struct irq_chip tegra210_gpio_irq_chip = {
+ .irq_shutdown = tegra_gpio_irq_shutdown,
+ .irq_ack = tegra_gpio_irq_ack,
+ .irq_mask = tegra_gpio_irq_mask,
+ .irq_unmask = tegra_gpio_irq_unmask,
+ .irq_set_affinity = tegra_gpio_irq_set_affinity,
+ .irq_set_type = tegra_gpio_irq_set_type,
+#ifdef CONFIG_PM_SLEEP
+ .irq_set_wake = tegra_gpio_irq_set_wake,
+#endif
+ .irq_print_chip = tegra_gpio_irq_print_chip,
+ .irq_request_resources = tegra_gpio_irq_request_resources,
+ .irq_release_resources = tegra_gpio_irq_release_resources,
+ .flags = IRQCHIP_IMMUTABLE,
+};
+
#ifdef CONFIG_DEBUG_FS
#include <linux/debugfs.h>
-#include <linux/seq_file.h>
static int tegra_dbg_gpio_show(struct seq_file *s, void *unused)
{
@@ -689,18 +728,6 @@ static int tegra_gpio_probe(struct platform_device *pdev)
tgi->gc.ngpio = tgi->bank_count * 32;
tgi->gc.parent = &pdev->dev;
- tgi->ic.name = "GPIO";
- tgi->ic.irq_ack = tegra_gpio_irq_ack;
- tgi->ic.irq_mask = tegra_gpio_irq_mask;
- tgi->ic.irq_unmask = tegra_gpio_irq_unmask;
- tgi->ic.irq_set_type = tegra_gpio_irq_set_type;
- tgi->ic.irq_shutdown = tegra_gpio_irq_shutdown;
-#ifdef CONFIG_PM_SLEEP
- tgi->ic.irq_set_wake = tegra_gpio_irq_set_wake;
-#endif
- tgi->ic.irq_request_resources = tegra_gpio_irq_request_resources;
- tgi->ic.irq_release_resources = tegra_gpio_irq_release_resources;
-
platform_set_drvdata(pdev, tgi);
if (tgi->soc->debounce_supported)
@@ -733,7 +760,6 @@ static int tegra_gpio_probe(struct platform_device *pdev)
}
irq = &tgi->gc.irq;
- irq->chip = &tgi->ic;
irq->fwnode = of_node_to_fwnode(pdev->dev.of_node);
irq->child_to_parent_hwirq = tegra_gpio_child_to_parent_hwirq;
irq->populate_parent_alloc_arg = tegra_gpio_populate_parent_fwspec;
@@ -752,7 +778,9 @@ static int tegra_gpio_probe(struct platform_device *pdev)
if (!irq->parent_domain)
return -EPROBE_DEFER;
- tgi->ic.irq_set_affinity = tegra_gpio_irq_set_affinity;
+ gpio_irq_chip_set_chip(irq, &tegra210_gpio_irq_chip);
+ } else {
+ gpio_irq_chip_set_chip(irq, &tegra_gpio_irq_chip);
}
tgi->regs = devm_platform_ioremap_resource(pdev, 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 0561812aa0a4..5d9a34601a1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -706,6 +706,13 @@ err:
void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle)
{
+ /* Temporary workaround to fix issues observed in some
+ * compute applications when GFXOFF is enabled on GFX11.
+ */
+ if (IP_VERSION_MAJ(adev->ip_versions[GC_HWIP][0]) == 11) {
+ pr_debug("GFXOFF is %s\n", idle ? "enabled" : "disabled");
+ amdgpu_gfx_off_ctrl(adev, idle);
+ }
amdgpu_dpm_switch_power_profile(adev,
PP_SMC_POWER_PROFILE_COMPUTE,
!idle);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 978d3970b5cc..84f44f7e4111 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -510,13 +510,13 @@ kfd_mem_dmamap_userptr(struct kgd_mem *mem,
struct ttm_tt *ttm = bo->tbo.ttm;
int ret;
+ if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
+ return -EINVAL;
+
ttm->sg = kmalloc(sizeof(*ttm->sg), GFP_KERNEL);
if (unlikely(!ttm->sg))
return -ENOMEM;
- if (WARN_ON(ttm->num_pages != src_ttm->num_pages))
- return -EINVAL;
-
/* Same sequence as in amdgpu_ttm_tt_pin_userptr */
ret = sg_alloc_table_from_pages(ttm->sg, src_ttm->pages,
ttm->num_pages, 0,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index f6d9d5da53cd..d2139ac12159 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -326,7 +326,10 @@ static int amdgpu_ctx_init(struct amdgpu_ctx_mgr *mgr, int32_t priority,
if (r)
return r;
- ctx->stable_pstate = current_stable_pstate;
+ if (mgr->adev->pm.stable_pstate_ctx)
+ ctx->stable_pstate = mgr->adev->pm.stable_pstate_ctx->stable_pstate;
+ else
+ ctx->stable_pstate = current_stable_pstate;
return 0;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e0445e8cc342..64510898eedd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3210,6 +3210,15 @@ static int amdgpu_device_ip_resume_phase2(struct amdgpu_device *adev)
return r;
}
adev->ip_blocks[i].status.hw = true;
+
+ if (adev->in_s0ix && adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
+ /* disable gfxoff for IP resume. The gfxoff will be re-enabled in
+ * amdgpu_device_resume() after IP resume.
+ */
+ amdgpu_gfx_off_ctrl(adev, false);
+ DRM_DEBUG("will disable gfxoff for re-initializing other blocks\n");
+ }
+
}
return 0;
@@ -4051,15 +4060,18 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
* at suspend time.
*
*/
-static void amdgpu_device_evict_resources(struct amdgpu_device *adev)
+static int amdgpu_device_evict_resources(struct amdgpu_device *adev)
{
+ int ret;
+
/* No need to evict vram on APUs for suspend to ram or s2idle */
if ((adev->in_s3 || adev->in_s0ix) && (adev->flags & AMD_IS_APU))
- return;
+ return 0;
- if (amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM))
+ ret = amdgpu_ttm_evict_resources(adev, TTM_PL_VRAM);
+ if (ret)
DRM_WARN("evicting device resources failed\n");
-
+ return ret;
}
/*
@@ -4109,7 +4121,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool fbcon)
if (!adev->in_s0ix)
amdgpu_amdkfd_suspend(adev, adev->in_runpm);
- amdgpu_device_evict_resources(adev);
+ r = amdgpu_device_evict_resources(adev);
+ if (r)
+ return r;
amdgpu_fence_driver_hw_fini(adev);
@@ -4185,6 +4199,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool fbcon)
/* Make sure IB tests flushed */
flush_delayed_work(&adev->delayed_init_work);
+ if (adev->in_s0ix) {
+ /* re-enable gfxoff after IP resume. This re-enables gfxoff after
+ * it was disabled for IP resume in amdgpu_device_ip_resume_phase2().
+ */
+ amdgpu_gfx_off_ctrl(adev, true);
+ DRM_DEBUG("will enable gfxoff for the mission mode\n");
+ }
if (fbcon)
drm_fb_helper_set_suspend_unlocked(adev_to_drm(adev)->fb_helper, false);
@@ -5381,7 +5402,7 @@ skip_hw_reset:
drm_sched_start(&ring->sched, !tmp_adev->asic_reset_res);
}
- if (adev->enable_mes)
+ if (adev->enable_mes && adev->ip_versions[GC_HWIP][0] != IP_VERSION(11, 0, 3))
amdgpu_mes_self_test(tmp_adev);
if (!drm_drv_uses_atomic_modeset(adev_to_drm(tmp_adev)) && !job_signaled) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 3c9fecdd6b2f..bf2d50c8c92a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2201,7 +2201,8 @@ amdgpu_pci_remove(struct pci_dev *pdev)
pm_runtime_forbid(dev->dev);
}
- if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2)) {
+ if (adev->ip_versions[MP1_HWIP][0] == IP_VERSION(13, 0, 2) &&
+ !amdgpu_sriov_vf(adev)) {
bool need_to_reset_gpu = false;
if (adev->gmc.xgmi.num_physical_nodes > 1) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index fe23e09eec98..4e42dcb1950f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -337,11 +337,17 @@ static int amdgpu_firmware_info(struct drm_amdgpu_info_firmware *fw_info,
fw_info->feature = adev->psp.cap_feature_version;
break;
case AMDGPU_INFO_FW_MES_KIQ:
- fw_info->ver = adev->mes.ucode_fw_version[0];
- fw_info->feature = 0;
+ fw_info->ver = adev->mes.kiq_version & AMDGPU_MES_VERSION_MASK;
+ fw_info->feature = (adev->mes.kiq_version & AMDGPU_MES_FEAT_VERSION_MASK)
+ >> AMDGPU_MES_FEAT_VERSION_SHIFT;
break;
case AMDGPU_INFO_FW_MES:
- fw_info->ver = adev->mes.ucode_fw_version[1];
+ fw_info->ver = adev->mes.sched_version & AMDGPU_MES_VERSION_MASK;
+ fw_info->feature = (adev->mes.sched_version & AMDGPU_MES_FEAT_VERSION_MASK)
+ >> AMDGPU_MES_FEAT_VERSION_SHIFT;
+ break;
+ case AMDGPU_INFO_FW_IMU:
+ fw_info->ver = adev->gfx.imu_fw_version;
fw_info->feature = 0;
break;
default:
@@ -1520,6 +1526,15 @@ static int amdgpu_debugfs_firmware_info_show(struct seq_file *m, void *unused)
fw_info.feature, fw_info.ver);
}
+ /* IMU */
+ query_fw.fw_type = AMDGPU_INFO_FW_IMU;
+ query_fw.index = 0;
+ ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
+ if (ret)
+ return ret;
+ seq_printf(m, "IMU feature version: %u, firmware version: 0x%08x\n",
+ fw_info.feature, fw_info.ver);
+
/* PSP SOS */
query_fw.fw_type = AMDGPU_INFO_FW_SOS;
ret = amdgpu_firmware_info(&fw_info, &query_fw, adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index dd0bc649a57d..5cb62e6249c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -698,6 +698,7 @@ FW_VERSION_ATTR(rlc_srlg_fw_version, 0444, gfx.rlc_srlg_fw_version);
FW_VERSION_ATTR(rlc_srls_fw_version, 0444, gfx.rlc_srls_fw_version);
FW_VERSION_ATTR(mec_fw_version, 0444, gfx.mec_fw_version);
FW_VERSION_ATTR(mec2_fw_version, 0444, gfx.mec2_fw_version);
+FW_VERSION_ATTR(imu_fw_version, 0444, gfx.imu_fw_version);
FW_VERSION_ATTR(sos_fw_version, 0444, psp.sos.fw_version);
FW_VERSION_ATTR(asd_fw_version, 0444, psp.asd_context.bin_desc.fw_version);
FW_VERSION_ATTR(ta_ras_fw_version, 0444, psp.ras_context.context.bin_desc.fw_version);
@@ -719,7 +720,8 @@ static struct attribute *fw_attrs[] = {
&dev_attr_ta_ras_fw_version.attr, &dev_attr_ta_xgmi_fw_version.attr,
&dev_attr_smc_fw_version.attr, &dev_attr_sdma_fw_version.attr,
&dev_attr_sdma2_fw_version.attr, &dev_attr_vcn_fw_version.attr,
- &dev_attr_dmcu_fw_version.attr, NULL
+ &dev_attr_dmcu_fw_version.attr, &dev_attr_imu_fw_version.attr,
+ NULL
};
static const struct attribute_group fw_attr_group = {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 9c765b04aae3..c73abe54d974 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -547,6 +547,7 @@ static void amdgpu_virt_populate_vf2pf_ucode_info(struct amdgpu_device *adev)
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_RLC_SRLS, adev->gfx.rlc_srls_fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC, adev->gfx.mec_fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_MEC2, adev->gfx.mec2_fw_version);
+ POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_IMU, adev->gfx.imu_fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_SOS, adev->psp.sos.fw_version);
POPULATE_UCODE_INFO(vf2pf_info, AMD_SRIOV_UCODE_ID_ASD,
adev->psp.asd_context.bin_desc.fw_version);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
index f4b5301ea2a0..500a1dc4fe02 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vkms.c
@@ -500,6 +500,8 @@ static int amdgpu_vkms_sw_init(void *handle)
adev_to_drm(adev)->mode_config.fb_base = adev->gmc.aper_base;
+ adev_to_drm(adev)->mode_config.fb_modifiers_not_supported = true;
+
r = amdgpu_display_modeset_create_props(adev);
if (r)
return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
index e78e4c27b62a..6c97148ca0ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
@@ -70,6 +70,7 @@ enum amd_sriov_ucode_engine_id {
AMD_SRIOV_UCODE_ID_RLC_SRLS,
AMD_SRIOV_UCODE_ID_MEC,
AMD_SRIOV_UCODE_ID_MEC2,
+ AMD_SRIOV_UCODE_ID_IMU,
AMD_SRIOV_UCODE_ID_SOS,
AMD_SRIOV_UCODE_ID_ASD,
AMD_SRIOV_UCODE_ID_TA_RAS,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 671ca5a0f208..0fecc5bf45bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -5051,6 +5051,7 @@ static int gfx_v11_0_set_powergating_state(void *handle,
switch (adev->ip_versions[GC_HWIP][0]) {
case IP_VERSION(11, 0, 0):
case IP_VERSION(11, 0, 2):
+ case IP_VERSION(11, 0, 3):
amdgpu_gfx_off_ctrl(adev, enable);
break;
case IP_VERSION(11, 0, 1):
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index fef7d020bc5f..f141fadd2d86 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -98,7 +98,14 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
struct amdgpu_device *adev = mes->adev;
struct amdgpu_ring *ring = &mes->ring;
unsigned long flags;
+ signed long timeout = adev->usec_timeout;
+ if (amdgpu_emu_mode) {
+ timeout *= 100;
+ } else if (amdgpu_sriov_vf(adev)) {
+ /* Worst case in sriov where all other 15 VF timeout, each VF needs about 600ms */
+ timeout = 15 * 600 * 1000;
+ }
BUG_ON(size % 4 != 0);
spin_lock_irqsave(&mes->ring_lock, flags);
@@ -118,7 +125,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
DRM_DEBUG("MES msg=%d was emitted\n", x_pkt->header.opcode);
r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq,
- adev->usec_timeout * (amdgpu_emu_mode ? 100 : 1));
+ timeout);
if (r < 1) {
DRM_ERROR("MES failed to response msg=%d\n",
x_pkt->header.opcode);
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 4d304f22889e..998b5d17b271 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -32,8 +32,6 @@
#include "gc/gc_10_1_0_offset.h"
#include "soc15_common.h"
-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid 0x064d
-#define mmMM_ATC_L2_MISC_CG_Sienna_Cichlid_BASE_IDX 0
#define mmDAGB0_CNTL_MISC2_Sienna_Cichlid 0x0070
#define mmDAGB0_CNTL_MISC2_Sienna_Cichlid_BASE_IDX 0
@@ -574,7 +572,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
case IP_VERSION(2, 1, 0):
case IP_VERSION(2, 1, 1):
case IP_VERSION(2, 1, 2):
- def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
def1 = data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
break;
default:
@@ -608,8 +605,6 @@ static void mmhub_v2_0_update_medium_grain_clock_gating(struct amdgpu_device *ad
case IP_VERSION(2, 1, 0):
case IP_VERSION(2, 1, 1):
case IP_VERSION(2, 1, 2):
- if (def != data)
- WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
if (def1 != data1)
WREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid, data1);
break;
@@ -634,8 +629,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
case IP_VERSION(2, 1, 0):
case IP_VERSION(2, 1, 1):
case IP_VERSION(2, 1, 2):
- def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
- break;
+ /* There is no ATCL2 in MMHUB for 2.1.x */
+ return;
default:
def = data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG);
break;
@@ -646,18 +641,8 @@ static void mmhub_v2_0_update_medium_grain_light_sleep(struct amdgpu_device *ade
else
data &= ~MM_ATC_L2_MISC_CG__MEM_LS_ENABLE_MASK;
- if (def != data) {
- switch (adev->ip_versions[MMHUB_HWIP][0]) {
- case IP_VERSION(2, 1, 0):
- case IP_VERSION(2, 1, 1):
- case IP_VERSION(2, 1, 2):
- WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid, data);
- break;
- default:
- WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
- break;
- }
- }
+ if (def != data)
+ WREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG, data);
}
static int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
@@ -695,7 +680,10 @@ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
case IP_VERSION(2, 1, 0):
case IP_VERSION(2, 1, 1):
case IP_VERSION(2, 1, 2):
- data = RREG32_SOC15(MMHUB, 0, mmMM_ATC_L2_MISC_CG_Sienna_Cichlid);
+ /* There is no ATCL2 in MMHUB for 2.1.x. Keep the status
+ * based on DAGB
+ */
+ data = MM_ATC_L2_MISC_CG__ENABLE_MASK;
data1 = RREG32_SOC15(MMHUB, 0, mmDAGB0_CNTL_MISC2_Sienna_Cichlid);
break;
default:
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index c7118843db05..0c4c5499bb5c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -2495,442 +2495,444 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
0xbf9f0000, 0x00000000,
};
static const uint32_t cwsr_trap_gfx11_hex[] = {
- 0xbfa00001, 0xbfa0021e,
+ 0xbfa00001, 0xbfa00221,
0xb0804006, 0xb8f8f802,
0x9178ff78, 0x00020006,
- 0xb8fbf803, 0xbf0d9f6d,
- 0xbfa20006, 0x8b6eff78,
- 0x00002000, 0xbfa10009,
- 0x8b6eff6d, 0x00ff0000,
- 0xbfa2001e, 0x8b6eff7b,
- 0x00000400, 0xbfa20041,
- 0xbf830010, 0xb8fbf803,
- 0xbfa0fffa, 0x8b6eff7b,
- 0x00000900, 0xbfa20015,
- 0x8b6eff7b, 0x000071ff,
- 0xbfa10008, 0x8b6fff7b,
- 0x00007080, 0xbfa10001,
- 0xbeee1287, 0xb8eff801,
- 0x846e8c6e, 0x8b6e6f6e,
- 0xbfa2000a, 0x8b6eff6d,
- 0x00ff0000, 0xbfa20007,
- 0xb8eef801, 0x8b6eff6e,
- 0x00000800, 0xbfa20003,
+ 0xb8fbf803, 0xbf0d9e6d,
+ 0xbfa10001, 0xbfbd0000,
+ 0xbf0d9f6d, 0xbfa20006,
+ 0x8b6eff78, 0x00002000,
+ 0xbfa10009, 0x8b6eff6d,
+ 0x00ff0000, 0xbfa2001e,
0x8b6eff7b, 0x00000400,
- 0xbfa20026, 0xbefa4d82,
- 0xbf89fc07, 0x84fa887a,
- 0xf4005bbd, 0xf8000010,
- 0xbf89fc07, 0x846e976e,
- 0x9177ff77, 0x00800000,
- 0x8c776e77, 0xf4045bbd,
- 0xf8000000, 0xbf89fc07,
- 0xf4045ebd, 0xf8000008,
- 0xbf89fc07, 0x8bee6e6e,
- 0xbfa10001, 0xbe80486e,
- 0x8b6eff6d, 0x01ff0000,
- 0xbfa20005, 0x8c78ff78,
- 0x00002000, 0x80ec886c,
- 0x82ed806d, 0xbfa00005,
- 0x8b6eff6d, 0x01000000,
- 0xbfa20002, 0x806c846c,
- 0x826d806d, 0x8b6dff6d,
- 0x0000ffff, 0x8bfe7e7e,
- 0x8bea6a6a, 0xb978f802,
- 0xbe804a6c, 0x8b6dff6d,
- 0x0000ffff, 0xbefa0080,
- 0xb97a0283, 0xbeee007e,
- 0xbeef007f, 0xbefe0180,
- 0xbefe4d84, 0xbf89fc07,
- 0x8b7aff7f, 0x04000000,
- 0x847a857a, 0x8c6d7a6d,
- 0xbefa007e, 0x8b7bff7f,
- 0x0000ffff, 0xbefe00c1,
- 0xbeff00c1, 0xdca6c000,
- 0x007a0000, 0x7e000280,
- 0xbefe007a, 0xbeff007b,
- 0xb8fb02dc, 0x847b997b,
- 0xb8fa3b05, 0x807a817a,
- 0xbf0d997b, 0xbfa20002,
- 0x847a897a, 0xbfa00001,
- 0x847a8a7a, 0xb8fb1e06,
- 0x847b8a7b, 0x807a7b7a,
+ 0xbfa20041, 0xbf830010,
+ 0xb8fbf803, 0xbfa0fffa,
+ 0x8b6eff7b, 0x00000900,
+ 0xbfa20015, 0x8b6eff7b,
+ 0x000071ff, 0xbfa10008,
+ 0x8b6fff7b, 0x00007080,
+ 0xbfa10001, 0xbeee1287,
+ 0xb8eff801, 0x846e8c6e,
+ 0x8b6e6f6e, 0xbfa2000a,
+ 0x8b6eff6d, 0x00ff0000,
+ 0xbfa20007, 0xb8eef801,
+ 0x8b6eff6e, 0x00000800,
+ 0xbfa20003, 0x8b6eff7b,
+ 0x00000400, 0xbfa20026,
+ 0xbefa4d82, 0xbf89fc07,
+ 0x84fa887a, 0xf4005bbd,
+ 0xf8000010, 0xbf89fc07,
+ 0x846e976e, 0x9177ff77,
+ 0x00800000, 0x8c776e77,
+ 0xf4045bbd, 0xf8000000,
+ 0xbf89fc07, 0xf4045ebd,
+ 0xf8000008, 0xbf89fc07,
+ 0x8bee6e6e, 0xbfa10001,
+ 0xbe80486e, 0x8b6eff6d,
+ 0x01ff0000, 0xbfa20005,
+ 0x8c78ff78, 0x00002000,
+ 0x80ec886c, 0x82ed806d,
+ 0xbfa00005, 0x8b6eff6d,
+ 0x01000000, 0xbfa20002,
+ 0x806c846c, 0x826d806d,
+ 0x8b6dff6d, 0x0000ffff,
+ 0x8bfe7e7e, 0x8bea6a6a,
+ 0xb978f802, 0xbe804a6c,
+ 0x8b6dff6d, 0x0000ffff,
+ 0xbefa0080, 0xb97a0283,
+ 0xbeee007e, 0xbeef007f,
+ 0xbefe0180, 0xbefe4d84,
+ 0xbf89fc07, 0x8b7aff7f,
+ 0x04000000, 0x847a857a,
+ 0x8c6d7a6d, 0xbefa007e,
0x8b7bff7f, 0x0000ffff,
- 0x807aff7a, 0x00000200,
- 0x807a7e7a, 0x827b807b,
- 0xd7610000, 0x00010870,
- 0xd7610000, 0x00010a71,
- 0xd7610000, 0x00010c72,
- 0xd7610000, 0x00010e73,
- 0xd7610000, 0x00011074,
- 0xd7610000, 0x00011275,
- 0xd7610000, 0x00011476,
- 0xd7610000, 0x00011677,
- 0xd7610000, 0x00011a79,
- 0xd7610000, 0x00011c7e,
- 0xd7610000, 0x00011e7f,
- 0xbefe00ff, 0x00003fff,
- 0xbeff0080, 0xdca6c040,
- 0x007a0000, 0xd760007a,
- 0x00011d00, 0xd760007b,
- 0x00011f00, 0xbefe007a,
- 0xbeff007b, 0xbef4007e,
- 0x8b75ff7f, 0x0000ffff,
- 0x8c75ff75, 0x00040000,
- 0xbef60080, 0xbef700ff,
- 0x10807fac, 0xbef1007d,
- 0xbef00080, 0xb8f302dc,
- 0x84739973, 0xbefe00c1,
- 0x857d9973, 0x8b7d817d,
- 0xbf06817d, 0xbfa20002,
- 0xbeff0080, 0xbfa00002,
- 0xbeff00c1, 0xbfa00009,
+ 0xbefe00c1, 0xbeff00c1,
+ 0xdca6c000, 0x007a0000,
+ 0x7e000280, 0xbefe007a,
+ 0xbeff007b, 0xb8fb02dc,
+ 0x847b997b, 0xb8fa3b05,
+ 0x807a817a, 0xbf0d997b,
+ 0xbfa20002, 0x847a897a,
+ 0xbfa00001, 0x847a8a7a,
+ 0xb8fb1e06, 0x847b8a7b,
+ 0x807a7b7a, 0x8b7bff7f,
+ 0x0000ffff, 0x807aff7a,
+ 0x00000200, 0x807a7e7a,
+ 0x827b807b, 0xd7610000,
+ 0x00010870, 0xd7610000,
+ 0x00010a71, 0xd7610000,
+ 0x00010c72, 0xd7610000,
+ 0x00010e73, 0xd7610000,
+ 0x00011074, 0xd7610000,
+ 0x00011275, 0xd7610000,
+ 0x00011476, 0xd7610000,
+ 0x00011677, 0xd7610000,
+ 0x00011a79, 0xd7610000,
+ 0x00011c7e, 0xd7610000,
+ 0x00011e7f, 0xbefe00ff,
+ 0x00003fff, 0xbeff0080,
+ 0xdca6c040, 0x007a0000,
+ 0xd760007a, 0x00011d00,
+ 0xd760007b, 0x00011f00,
+ 0xbefe007a, 0xbeff007b,
+ 0xbef4007e, 0x8b75ff7f,
+ 0x0000ffff, 0x8c75ff75,
+ 0x00040000, 0xbef60080,
+ 0xbef700ff, 0x10807fac,
+ 0xbef1007d, 0xbef00080,
+ 0xb8f302dc, 0x84739973,
+ 0xbefe00c1, 0x857d9973,
+ 0x8b7d817d, 0xbf06817d,
+ 0xbfa20002, 0xbeff0080,
+ 0xbfa00002, 0xbeff00c1,
+ 0xbfa00009, 0xbef600ff,
+ 0x01000000, 0xe0685080,
+ 0x701d0100, 0xe0685100,
+ 0x701d0200, 0xe0685180,
+ 0x701d0300, 0xbfa00008,
0xbef600ff, 0x01000000,
- 0xe0685080, 0x701d0100,
- 0xe0685100, 0x701d0200,
- 0xe0685180, 0x701d0300,
- 0xbfa00008, 0xbef600ff,
- 0x01000000, 0xe0685100,
- 0x701d0100, 0xe0685200,
- 0x701d0200, 0xe0685300,
- 0x701d0300, 0xb8f03b05,
- 0x80708170, 0xbf0d9973,
- 0xbfa20002, 0x84708970,
- 0xbfa00001, 0x84708a70,
- 0xb8fa1e06, 0x847a8a7a,
- 0x80707a70, 0x8070ff70,
- 0x00000200, 0xbef600ff,
- 0x01000000, 0x7e000280,
- 0x7e020280, 0x7e040280,
- 0xbefd0080, 0xd7610002,
- 0x0000fa71, 0x807d817d,
- 0xd7610002, 0x0000fa6c,
- 0x807d817d, 0x917aff6d,
- 0x80000000, 0xd7610002,
- 0x0000fa7a, 0x807d817d,
- 0xd7610002, 0x0000fa6e,
- 0x807d817d, 0xd7610002,
- 0x0000fa6f, 0x807d817d,
- 0xd7610002, 0x0000fa78,
- 0x807d817d, 0xb8faf803,
- 0xd7610002, 0x0000fa7a,
- 0x807d817d, 0xd7610002,
- 0x0000fa7b, 0x807d817d,
- 0xb8f1f801, 0xd7610002,
- 0x0000fa71, 0x807d817d,
- 0xb8f1f814, 0xd7610002,
- 0x0000fa71, 0x807d817d,
- 0xb8f1f815, 0xd7610002,
- 0x0000fa71, 0x807d817d,
- 0xbefe00ff, 0x0000ffff,
- 0xbeff0080, 0xe0685000,
- 0x701d0200, 0xbefe00c1,
+ 0xe0685100, 0x701d0100,
+ 0xe0685200, 0x701d0200,
+ 0xe0685300, 0x701d0300,
0xb8f03b05, 0x80708170,
0xbf0d9973, 0xbfa20002,
0x84708970, 0xbfa00001,
0x84708a70, 0xb8fa1e06,
0x847a8a7a, 0x80707a70,
+ 0x8070ff70, 0x00000200,
0xbef600ff, 0x01000000,
- 0xbef90080, 0xbefd0080,
- 0xbf800000, 0xbe804100,
- 0xbe824102, 0xbe844104,
- 0xbe864106, 0xbe884108,
- 0xbe8a410a, 0xbe8c410c,
- 0xbe8e410e, 0xd7610002,
- 0x0000f200, 0x80798179,
- 0xd7610002, 0x0000f201,
+ 0x7e000280, 0x7e020280,
+ 0x7e040280, 0xbefd0080,
+ 0xd7610002, 0x0000fa71,
+ 0x807d817d, 0xd7610002,
+ 0x0000fa6c, 0x807d817d,
+ 0x917aff6d, 0x80000000,
+ 0xd7610002, 0x0000fa7a,
+ 0x807d817d, 0xd7610002,
+ 0x0000fa6e, 0x807d817d,
+ 0xd7610002, 0x0000fa6f,
+ 0x807d817d, 0xd7610002,
+ 0x0000fa78, 0x807d817d,
+ 0xb8faf803, 0xd7610002,
+ 0x0000fa7a, 0x807d817d,
+ 0xd7610002, 0x0000fa7b,
+ 0x807d817d, 0xb8f1f801,
+ 0xd7610002, 0x0000fa71,
+ 0x807d817d, 0xb8f1f814,
+ 0xd7610002, 0x0000fa71,
+ 0x807d817d, 0xb8f1f815,
+ 0xd7610002, 0x0000fa71,
+ 0x807d817d, 0xbefe00ff,
+ 0x0000ffff, 0xbeff0080,
+ 0xe0685000, 0x701d0200,
+ 0xbefe00c1, 0xb8f03b05,
+ 0x80708170, 0xbf0d9973,
+ 0xbfa20002, 0x84708970,
+ 0xbfa00001, 0x84708a70,
+ 0xb8fa1e06, 0x847a8a7a,
+ 0x80707a70, 0xbef600ff,
+ 0x01000000, 0xbef90080,
+ 0xbefd0080, 0xbf800000,
+ 0xbe804100, 0xbe824102,
+ 0xbe844104, 0xbe864106,
+ 0xbe884108, 0xbe8a410a,
+ 0xbe8c410c, 0xbe8e410e,
+ 0xd7610002, 0x0000f200,
0x80798179, 0xd7610002,
- 0x0000f202, 0x80798179,
- 0xd7610002, 0x0000f203,
+ 0x0000f201, 0x80798179,
+ 0xd7610002, 0x0000f202,
0x80798179, 0xd7610002,
- 0x0000f204, 0x80798179,
- 0xd7610002, 0x0000f205,
+ 0x0000f203, 0x80798179,
+ 0xd7610002, 0x0000f204,
0x80798179, 0xd7610002,
- 0x0000f206, 0x80798179,
- 0xd7610002, 0x0000f207,
+ 0x0000f205, 0x80798179,
+ 0xd7610002, 0x0000f206,
0x80798179, 0xd7610002,
- 0x0000f208, 0x80798179,
- 0xd7610002, 0x0000f209,
+ 0x0000f207, 0x80798179,
+ 0xd7610002, 0x0000f208,
0x80798179, 0xd7610002,
- 0x0000f20a, 0x80798179,
- 0xd7610002, 0x0000f20b,
+ 0x0000f209, 0x80798179,
+ 0xd7610002, 0x0000f20a,
0x80798179, 0xd7610002,
- 0x0000f20c, 0x80798179,
- 0xd7610002, 0x0000f20d,
+ 0x0000f20b, 0x80798179,
+ 0xd7610002, 0x0000f20c,
0x80798179, 0xd7610002,
- 0x0000f20e, 0x80798179,
- 0xd7610002, 0x0000f20f,
- 0x80798179, 0xbf06a079,
- 0xbfa10006, 0xe0685000,
- 0x701d0200, 0x8070ff70,
- 0x00000080, 0xbef90080,
- 0x7e040280, 0x807d907d,
- 0xbf0aff7d, 0x00000060,
- 0xbfa2ffbc, 0xbe804100,
- 0xbe824102, 0xbe844104,
- 0xbe864106, 0xbe884108,
- 0xbe8a410a, 0xd7610002,
- 0x0000f200, 0x80798179,
- 0xd7610002, 0x0000f201,
+ 0x0000f20d, 0x80798179,
+ 0xd7610002, 0x0000f20e,
0x80798179, 0xd7610002,
- 0x0000f202, 0x80798179,
- 0xd7610002, 0x0000f203,
+ 0x0000f20f, 0x80798179,
+ 0xbf06a079, 0xbfa10006,
+ 0xe0685000, 0x701d0200,
+ 0x8070ff70, 0x00000080,
+ 0xbef90080, 0x7e040280,
+ 0x807d907d, 0xbf0aff7d,
+ 0x00000060, 0xbfa2ffbc,
+ 0xbe804100, 0xbe824102,
+ 0xbe844104, 0xbe864106,
+ 0xbe884108, 0xbe8a410a,
+ 0xd7610002, 0x0000f200,
0x80798179, 0xd7610002,
- 0x0000f204, 0x80798179,
- 0xd7610002, 0x0000f205,
+ 0x0000f201, 0x80798179,
+ 0xd7610002, 0x0000f202,
0x80798179, 0xd7610002,
- 0x0000f206, 0x80798179,
- 0xd7610002, 0x0000f207,
+ 0x0000f203, 0x80798179,
+ 0xd7610002, 0x0000f204,
0x80798179, 0xd7610002,
- 0x0000f208, 0x80798179,
- 0xd7610002, 0x0000f209,
+ 0x0000f205, 0x80798179,
+ 0xd7610002, 0x0000f206,
0x80798179, 0xd7610002,
- 0x0000f20a, 0x80798179,
- 0xd7610002, 0x0000f20b,
- 0x80798179, 0xe0685000,
- 0x701d0200, 0xbefe00c1,
- 0x857d9973, 0x8b7d817d,
- 0xbf06817d, 0xbfa20002,
- 0xbeff0080, 0xbfa00001,
- 0xbeff00c1, 0xb8fb4306,
- 0x8b7bc17b, 0xbfa10044,
- 0xbfbd0000, 0x8b7aff6d,
- 0x80000000, 0xbfa10040,
- 0x847b867b, 0x847b827b,
- 0xbef6007b, 0xb8f03b05,
- 0x80708170, 0xbf0d9973,
- 0xbfa20002, 0x84708970,
- 0xbfa00001, 0x84708a70,
- 0xb8fa1e06, 0x847a8a7a,
- 0x80707a70, 0x8070ff70,
- 0x00000200, 0x8070ff70,
- 0x00000080, 0xbef600ff,
- 0x01000000, 0xd71f0000,
- 0x000100c1, 0xd7200000,
- 0x000200c1, 0x16000084,
- 0x857d9973, 0x8b7d817d,
- 0xbf06817d, 0xbefd0080,
- 0xbfa20012, 0xbe8300ff,
- 0x00000080, 0xbf800000,
- 0xbf800000, 0xbf800000,
- 0xd8d80000, 0x01000000,
- 0xbf890000, 0xe0685000,
- 0x701d0100, 0x807d037d,
- 0x80700370, 0xd5250000,
- 0x0001ff00, 0x00000080,
- 0xbf0a7b7d, 0xbfa2fff4,
- 0xbfa00011, 0xbe8300ff,
- 0x00000100, 0xbf800000,
- 0xbf800000, 0xbf800000,
- 0xd8d80000, 0x01000000,
- 0xbf890000, 0xe0685000,
- 0x701d0100, 0x807d037d,
- 0x80700370, 0xd5250000,
- 0x0001ff00, 0x00000100,
- 0xbf0a7b7d, 0xbfa2fff4,
+ 0x0000f207, 0x80798179,
+ 0xd7610002, 0x0000f208,
+ 0x80798179, 0xd7610002,
+ 0x0000f209, 0x80798179,
+ 0xd7610002, 0x0000f20a,
+ 0x80798179, 0xd7610002,
+ 0x0000f20b, 0x80798179,
+ 0xe0685000, 0x701d0200,
0xbefe00c1, 0x857d9973,
0x8b7d817d, 0xbf06817d,
- 0xbfa20004, 0xbef000ff,
- 0x00000200, 0xbeff0080,
- 0xbfa00003, 0xbef000ff,
- 0x00000400, 0xbeff00c1,
- 0xb8fb3b05, 0x807b817b,
- 0x847b827b, 0x857d9973,
+ 0xbfa20002, 0xbeff0080,
+ 0xbfa00001, 0xbeff00c1,
+ 0xb8fb4306, 0x8b7bc17b,
+ 0xbfa10044, 0xbfbd0000,
+ 0x8b7aff6d, 0x80000000,
+ 0xbfa10040, 0x847b867b,
+ 0x847b827b, 0xbef6007b,
+ 0xb8f03b05, 0x80708170,
+ 0xbf0d9973, 0xbfa20002,
+ 0x84708970, 0xbfa00001,
+ 0x84708a70, 0xb8fa1e06,
+ 0x847a8a7a, 0x80707a70,
+ 0x8070ff70, 0x00000200,
+ 0x8070ff70, 0x00000080,
+ 0xbef600ff, 0x01000000,
+ 0xd71f0000, 0x000100c1,
+ 0xd7200000, 0x000200c1,
+ 0x16000084, 0x857d9973,
0x8b7d817d, 0xbf06817d,
- 0xbfa20017, 0xbef600ff,
- 0x01000000, 0xbefd0084,
- 0xbf0a7b7d, 0xbfa10037,
- 0x7e008700, 0x7e028701,
- 0x7e048702, 0x7e068703,
- 0xe0685000, 0x701d0000,
- 0xe0685080, 0x701d0100,
- 0xe0685100, 0x701d0200,
- 0xe0685180, 0x701d0300,
- 0x807d847d, 0x8070ff70,
- 0x00000200, 0xbf0a7b7d,
- 0xbfa2ffef, 0xbfa00025,
+ 0xbefd0080, 0xbfa20012,
+ 0xbe8300ff, 0x00000080,
+ 0xbf800000, 0xbf800000,
+ 0xbf800000, 0xd8d80000,
+ 0x01000000, 0xbf890000,
+ 0xe0685000, 0x701d0100,
+ 0x807d037d, 0x80700370,
+ 0xd5250000, 0x0001ff00,
+ 0x00000080, 0xbf0a7b7d,
+ 0xbfa2fff4, 0xbfa00011,
+ 0xbe8300ff, 0x00000100,
+ 0xbf800000, 0xbf800000,
+ 0xbf800000, 0xd8d80000,
+ 0x01000000, 0xbf890000,
+ 0xe0685000, 0x701d0100,
+ 0x807d037d, 0x80700370,
+ 0xd5250000, 0x0001ff00,
+ 0x00000100, 0xbf0a7b7d,
+ 0xbfa2fff4, 0xbefe00c1,
+ 0x857d9973, 0x8b7d817d,
+ 0xbf06817d, 0xbfa20004,
+ 0xbef000ff, 0x00000200,
+ 0xbeff0080, 0xbfa00003,
+ 0xbef000ff, 0x00000400,
+ 0xbeff00c1, 0xb8fb3b05,
+ 0x807b817b, 0x847b827b,
+ 0x857d9973, 0x8b7d817d,
+ 0xbf06817d, 0xbfa20017,
0xbef600ff, 0x01000000,
0xbefd0084, 0xbf0a7b7d,
- 0xbfa10011, 0x7e008700,
+ 0xbfa10037, 0x7e008700,
0x7e028701, 0x7e048702,
0x7e068703, 0xe0685000,
- 0x701d0000, 0xe0685100,
- 0x701d0100, 0xe0685200,
- 0x701d0200, 0xe0685300,
+ 0x701d0000, 0xe0685080,
+ 0x701d0100, 0xe0685100,
+ 0x701d0200, 0xe0685180,
0x701d0300, 0x807d847d,
- 0x8070ff70, 0x00000400,
+ 0x8070ff70, 0x00000200,
0xbf0a7b7d, 0xbfa2ffef,
- 0xb8fb1e06, 0x8b7bc17b,
- 0xbfa1000c, 0x847b837b,
- 0x807b7d7b, 0xbefe00c1,
- 0xbeff0080, 0x7e008700,
+ 0xbfa00025, 0xbef600ff,
+ 0x01000000, 0xbefd0084,
+ 0xbf0a7b7d, 0xbfa10011,
+ 0x7e008700, 0x7e028701,
+ 0x7e048702, 0x7e068703,
0xe0685000, 0x701d0000,
- 0x807d817d, 0x8070ff70,
- 0x00000080, 0xbf0a7b7d,
- 0xbfa2fff8, 0xbfa00146,
- 0xbef4007e, 0x8b75ff7f,
- 0x0000ffff, 0x8c75ff75,
- 0x00040000, 0xbef60080,
- 0xbef700ff, 0x10807fac,
- 0xb8f202dc, 0x84729972,
- 0x8b6eff7f, 0x04000000,
- 0xbfa1003a, 0xbefe00c1,
- 0x857d9972, 0x8b7d817d,
- 0xbf06817d, 0xbfa20002,
- 0xbeff0080, 0xbfa00001,
- 0xbeff00c1, 0xb8ef4306,
- 0x8b6fc16f, 0xbfa1002f,
- 0x846f866f, 0x846f826f,
- 0xbef6006f, 0xb8f83b05,
- 0x80788178, 0xbf0d9972,
- 0xbfa20002, 0x84788978,
- 0xbfa00001, 0x84788a78,
- 0xb8ee1e06, 0x846e8a6e,
- 0x80786e78, 0x8078ff78,
- 0x00000200, 0x8078ff78,
- 0x00000080, 0xbef600ff,
- 0x01000000, 0x857d9972,
- 0x8b7d817d, 0xbf06817d,
- 0xbefd0080, 0xbfa2000c,
- 0xe0500000, 0x781d0000,
- 0xbf8903f7, 0xdac00000,
- 0x00000000, 0x807dff7d,
- 0x00000080, 0x8078ff78,
- 0x00000080, 0xbf0a6f7d,
- 0xbfa2fff5, 0xbfa0000b,
- 0xe0500000, 0x781d0000,
- 0xbf8903f7, 0xdac00000,
- 0x00000000, 0x807dff7d,
- 0x00000100, 0x8078ff78,
- 0x00000100, 0xbf0a6f7d,
- 0xbfa2fff5, 0xbef80080,
+ 0xe0685100, 0x701d0100,
+ 0xe0685200, 0x701d0200,
+ 0xe0685300, 0x701d0300,
+ 0x807d847d, 0x8070ff70,
+ 0x00000400, 0xbf0a7b7d,
+ 0xbfa2ffef, 0xb8fb1e06,
+ 0x8b7bc17b, 0xbfa1000c,
+ 0x847b837b, 0x807b7d7b,
+ 0xbefe00c1, 0xbeff0080,
+ 0x7e008700, 0xe0685000,
+ 0x701d0000, 0x807d817d,
+ 0x8070ff70, 0x00000080,
+ 0xbf0a7b7d, 0xbfa2fff8,
+ 0xbfa00146, 0xbef4007e,
+ 0x8b75ff7f, 0x0000ffff,
+ 0x8c75ff75, 0x00040000,
+ 0xbef60080, 0xbef700ff,
+ 0x10807fac, 0xb8f202dc,
+ 0x84729972, 0x8b6eff7f,
+ 0x04000000, 0xbfa1003a,
0xbefe00c1, 0x857d9972,
0x8b7d817d, 0xbf06817d,
0xbfa20002, 0xbeff0080,
0xbfa00001, 0xbeff00c1,
- 0xb8ef3b05, 0x806f816f,
- 0x846f826f, 0x857d9972,
- 0x8b7d817d, 0xbf06817d,
- 0xbfa20024, 0xbef600ff,
- 0x01000000, 0xbeee0078,
+ 0xb8ef4306, 0x8b6fc16f,
+ 0xbfa1002f, 0x846f866f,
+ 0x846f826f, 0xbef6006f,
+ 0xb8f83b05, 0x80788178,
+ 0xbf0d9972, 0xbfa20002,
+ 0x84788978, 0xbfa00001,
+ 0x84788a78, 0xb8ee1e06,
+ 0x846e8a6e, 0x80786e78,
0x8078ff78, 0x00000200,
- 0xbefd0084, 0xbf0a6f7d,
- 0xbfa10050, 0xe0505000,
- 0x781d0000, 0xe0505080,
- 0x781d0100, 0xe0505100,
- 0x781d0200, 0xe0505180,
- 0x781d0300, 0xbf8903f7,
- 0x7e008500, 0x7e028501,
- 0x7e048502, 0x7e068503,
- 0x807d847d, 0x8078ff78,
- 0x00000200, 0xbf0a6f7d,
- 0xbfa2ffee, 0xe0505000,
- 0x6e1d0000, 0xe0505080,
- 0x6e1d0100, 0xe0505100,
- 0x6e1d0200, 0xe0505180,
- 0x6e1d0300, 0xbf8903f7,
- 0xbfa00034, 0xbef600ff,
- 0x01000000, 0xbeee0078,
- 0x8078ff78, 0x00000400,
- 0xbefd0084, 0xbf0a6f7d,
- 0xbfa10012, 0xe0505000,
- 0x781d0000, 0xe0505100,
- 0x781d0100, 0xe0505200,
- 0x781d0200, 0xe0505300,
- 0x781d0300, 0xbf8903f7,
- 0x7e008500, 0x7e028501,
- 0x7e048502, 0x7e068503,
- 0x807d847d, 0x8078ff78,
- 0x00000400, 0xbf0a6f7d,
- 0xbfa2ffee, 0xb8ef1e06,
- 0x8b6fc16f, 0xbfa1000e,
- 0x846f836f, 0x806f7d6f,
- 0xbefe00c1, 0xbeff0080,
+ 0x8078ff78, 0x00000080,
+ 0xbef600ff, 0x01000000,
+ 0x857d9972, 0x8b7d817d,
+ 0xbf06817d, 0xbefd0080,
+ 0xbfa2000c, 0xe0500000,
+ 0x781d0000, 0xbf8903f7,
+ 0xdac00000, 0x00000000,
+ 0x807dff7d, 0x00000080,
+ 0x8078ff78, 0x00000080,
+ 0xbf0a6f7d, 0xbfa2fff5,
+ 0xbfa0000b, 0xe0500000,
+ 0x781d0000, 0xbf8903f7,
+ 0xdac00000, 0x00000000,
+ 0x807dff7d, 0x00000100,
+ 0x8078ff78, 0x00000100,
+ 0xbf0a6f7d, 0xbfa2fff5,
+ 0xbef80080, 0xbefe00c1,
+ 0x857d9972, 0x8b7d817d,
+ 0xbf06817d, 0xbfa20002,
+ 0xbeff0080, 0xbfa00001,
+ 0xbeff00c1, 0xb8ef3b05,
+ 0x806f816f, 0x846f826f,
+ 0x857d9972, 0x8b7d817d,
+ 0xbf06817d, 0xbfa20024,
+ 0xbef600ff, 0x01000000,
+ 0xbeee0078, 0x8078ff78,
+ 0x00000200, 0xbefd0084,
+ 0xbf0a6f7d, 0xbfa10050,
0xe0505000, 0x781d0000,
+ 0xe0505080, 0x781d0100,
+ 0xe0505100, 0x781d0200,
+ 0xe0505180, 0x781d0300,
0xbf8903f7, 0x7e008500,
- 0x807d817d, 0x8078ff78,
- 0x00000080, 0xbf0a6f7d,
- 0xbfa2fff7, 0xbeff00c1,
+ 0x7e028501, 0x7e048502,
+ 0x7e068503, 0x807d847d,
+ 0x8078ff78, 0x00000200,
+ 0xbf0a6f7d, 0xbfa2ffee,
0xe0505000, 0x6e1d0000,
- 0xe0505100, 0x6e1d0100,
- 0xe0505200, 0x6e1d0200,
- 0xe0505300, 0x6e1d0300,
- 0xbf8903f7, 0xb8f83b05,
- 0x80788178, 0xbf0d9972,
- 0xbfa20002, 0x84788978,
- 0xbfa00001, 0x84788a78,
- 0xb8ee1e06, 0x846e8a6e,
- 0x80786e78, 0x8078ff78,
- 0x00000200, 0x80f8ff78,
- 0x00000050, 0xbef600ff,
- 0x01000000, 0xbefd00ff,
- 0x0000006c, 0x80f89078,
- 0xf428403a, 0xf0000000,
- 0xbf89fc07, 0x80fd847d,
- 0xbf800000, 0xbe804300,
- 0xbe824302, 0x80f8a078,
- 0xf42c403a, 0xf0000000,
- 0xbf89fc07, 0x80fd887d,
- 0xbf800000, 0xbe804300,
- 0xbe824302, 0xbe844304,
- 0xbe864306, 0x80f8c078,
- 0xf430403a, 0xf0000000,
- 0xbf89fc07, 0x80fd907d,
- 0xbf800000, 0xbe804300,
- 0xbe824302, 0xbe844304,
- 0xbe864306, 0xbe884308,
- 0xbe8a430a, 0xbe8c430c,
- 0xbe8e430e, 0xbf06807d,
- 0xbfa1fff0, 0xb980f801,
- 0x00000000, 0xbfbd0000,
+ 0xe0505080, 0x6e1d0100,
+ 0xe0505100, 0x6e1d0200,
+ 0xe0505180, 0x6e1d0300,
+ 0xbf8903f7, 0xbfa00034,
+ 0xbef600ff, 0x01000000,
+ 0xbeee0078, 0x8078ff78,
+ 0x00000400, 0xbefd0084,
+ 0xbf0a6f7d, 0xbfa10012,
+ 0xe0505000, 0x781d0000,
+ 0xe0505100, 0x781d0100,
+ 0xe0505200, 0x781d0200,
+ 0xe0505300, 0x781d0300,
+ 0xbf8903f7, 0x7e008500,
+ 0x7e028501, 0x7e048502,
+ 0x7e068503, 0x807d847d,
+ 0x8078ff78, 0x00000400,
+ 0xbf0a6f7d, 0xbfa2ffee,
+ 0xb8ef1e06, 0x8b6fc16f,
+ 0xbfa1000e, 0x846f836f,
+ 0x806f7d6f, 0xbefe00c1,
+ 0xbeff0080, 0xe0505000,
+ 0x781d0000, 0xbf8903f7,
+ 0x7e008500, 0x807d817d,
+ 0x8078ff78, 0x00000080,
+ 0xbf0a6f7d, 0xbfa2fff7,
+ 0xbeff00c1, 0xe0505000,
+ 0x6e1d0000, 0xe0505100,
+ 0x6e1d0100, 0xe0505200,
+ 0x6e1d0200, 0xe0505300,
+ 0x6e1d0300, 0xbf8903f7,
0xb8f83b05, 0x80788178,
0xbf0d9972, 0xbfa20002,
0x84788978, 0xbfa00001,
0x84788a78, 0xb8ee1e06,
0x846e8a6e, 0x80786e78,
0x8078ff78, 0x00000200,
+ 0x80f8ff78, 0x00000050,
0xbef600ff, 0x01000000,
- 0xf4205bfa, 0xf0000000,
- 0x80788478, 0xf4205b3a,
+ 0xbefd00ff, 0x0000006c,
+ 0x80f89078, 0xf428403a,
+ 0xf0000000, 0xbf89fc07,
+ 0x80fd847d, 0xbf800000,
+ 0xbe804300, 0xbe824302,
+ 0x80f8a078, 0xf42c403a,
+ 0xf0000000, 0xbf89fc07,
+ 0x80fd887d, 0xbf800000,
+ 0xbe804300, 0xbe824302,
+ 0xbe844304, 0xbe864306,
+ 0x80f8c078, 0xf430403a,
+ 0xf0000000, 0xbf89fc07,
+ 0x80fd907d, 0xbf800000,
+ 0xbe804300, 0xbe824302,
+ 0xbe844304, 0xbe864306,
+ 0xbe884308, 0xbe8a430a,
+ 0xbe8c430c, 0xbe8e430e,
+ 0xbf06807d, 0xbfa1fff0,
+ 0xb980f801, 0x00000000,
+ 0xbfbd0000, 0xb8f83b05,
+ 0x80788178, 0xbf0d9972,
+ 0xbfa20002, 0x84788978,
+ 0xbfa00001, 0x84788a78,
+ 0xb8ee1e06, 0x846e8a6e,
+ 0x80786e78, 0x8078ff78,
+ 0x00000200, 0xbef600ff,
+ 0x01000000, 0xf4205bfa,
0xf0000000, 0x80788478,
- 0xf4205b7a, 0xf0000000,
- 0x80788478, 0xf4205c3a,
+ 0xf4205b3a, 0xf0000000,
+ 0x80788478, 0xf4205b7a,
0xf0000000, 0x80788478,
- 0xf4205c7a, 0xf0000000,
- 0x80788478, 0xf4205eba,
+ 0xf4205c3a, 0xf0000000,
+ 0x80788478, 0xf4205c7a,
0xf0000000, 0x80788478,
- 0xf4205efa, 0xf0000000,
- 0x80788478, 0xf4205e7a,
+ 0xf4205eba, 0xf0000000,
+ 0x80788478, 0xf4205efa,
0xf0000000, 0x80788478,
- 0xf4205cfa, 0xf0000000,
- 0x80788478, 0xf4205bba,
+ 0xf4205e7a, 0xf0000000,
+ 0x80788478, 0xf4205cfa,
0xf0000000, 0x80788478,
- 0xbf89fc07, 0xb96ef814,
0xf4205bba, 0xf0000000,
0x80788478, 0xbf89fc07,
- 0xb96ef815, 0xbefd006f,
- 0xbefe0070, 0xbeff0071,
- 0x8b6f7bff, 0x000003ff,
- 0xb96f4803, 0x8b6f7bff,
- 0xfffff800, 0x856f8b6f,
- 0xb96fa2c3, 0xb973f801,
- 0xb8ee3b05, 0x806e816e,
- 0xbf0d9972, 0xbfa20002,
- 0x846e896e, 0xbfa00001,
- 0x846e8a6e, 0xb8ef1e06,
- 0x846f8a6f, 0x806e6f6e,
- 0x806eff6e, 0x00000200,
- 0x806e746e, 0x826f8075,
- 0x8b6fff6f, 0x0000ffff,
- 0xf4085c37, 0xf8000050,
- 0xf4085d37, 0xf8000060,
- 0xf4005e77, 0xf8000074,
- 0xbf89fc07, 0x8b6dff6d,
- 0x0000ffff, 0x8bfe7e7e,
- 0x8bea6a6a, 0xb8eef802,
- 0xbf0d866e, 0xbfa20002,
- 0xb97af802, 0xbe80486c,
- 0xb97af802, 0xbe804a6c,
- 0xbfb00000, 0xbf9f0000,
+ 0xb96ef814, 0xf4205bba,
+ 0xf0000000, 0x80788478,
+ 0xbf89fc07, 0xb96ef815,
+ 0xbefd006f, 0xbefe0070,
+ 0xbeff0071, 0x8b6f7bff,
+ 0x000003ff, 0xb96f4803,
+ 0x8b6f7bff, 0xfffff800,
+ 0x856f8b6f, 0xb96fa2c3,
+ 0xb973f801, 0xb8ee3b05,
+ 0x806e816e, 0xbf0d9972,
+ 0xbfa20002, 0x846e896e,
+ 0xbfa00001, 0x846e8a6e,
+ 0xb8ef1e06, 0x846f8a6f,
+ 0x806e6f6e, 0x806eff6e,
+ 0x00000200, 0x806e746e,
+ 0x826f8075, 0x8b6fff6f,
+ 0x0000ffff, 0xf4085c37,
+ 0xf8000050, 0xf4085d37,
+ 0xf8000060, 0xf4005e77,
+ 0xf8000074, 0xbf89fc07,
+ 0x8b6dff6d, 0x0000ffff,
+ 0x8bfe7e7e, 0x8bea6a6a,
+ 0xb8eef802, 0xbf0d866e,
+ 0xbfa20002, 0xb97af802,
+ 0xbe80486c, 0xb97af802,
+ 0xbe804a6c, 0xbfb00000,
0xbf9f0000, 0xbf9f0000,
0xbf9f0000, 0xbf9f0000,
+ 0xbf9f0000, 0x00000000,
};
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index 0f81670f6f9c..8b92c33c2a7c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -186,6 +186,12 @@ L_SKIP_RESTORE:
s_getreg_b32 s_save_trapsts, hwreg(HW_REG_TRAPSTS)
#if SW_SA_TRAP
+ // If ttmp1[30] is set then issue s_barrier to unblock dependent waves.
+ s_bitcmp1_b32 s_save_pc_hi, 30
+ s_cbranch_scc0 L_TRAP_NO_BARRIER
+ s_barrier
+
+L_TRAP_NO_BARRIER:
// If ttmp1[31] is set then trap may occur early.
// Spin wait until SAVECTX exception is raised.
s_bitcmp1_b32 s_save_pc_hi, 31
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index cd5f8b219bf9..8bfdfd062ff6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -795,6 +795,102 @@ static struct kfd_gpu_cache_info yellow_carp_cache_info[] = {
},
};
+static struct kfd_gpu_cache_info gfx1037_cache_info[] = {
+ {
+ /* TCP L1 Cache per CU */
+ .cache_size = 16,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 1,
+ },
+ {
+ /* Scalar L1 Instruction Cache per SQC */
+ .cache_size = 32,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_INST_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* Scalar L1 Data Cache per SQC */
+ .cache_size = 16,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* GL1 Data Cache per SA */
+ .cache_size = 128,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* L2 Data Cache per GPU (Total Tex Cache) */
+ .cache_size = 256,
+ .cache_level = 2,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+};
+
+static struct kfd_gpu_cache_info gc_10_3_6_cache_info[] = {
+ {
+ /* TCP L1 Cache per CU */
+ .cache_size = 16,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 1,
+ },
+ {
+ /* Scalar L1 Instruction Cache per SQC */
+ .cache_size = 32,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_INST_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* Scalar L1 Data Cache per SQC */
+ .cache_size = 16,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* GL1 Data Cache per SA */
+ .cache_size = 128,
+ .cache_level = 1,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+ {
+ /* L2 Data Cache per GPU (Total Tex Cache) */
+ .cache_size = 256,
+ .cache_level = 2,
+ .flags = (CRAT_CACHE_FLAGS_ENABLED |
+ CRAT_CACHE_FLAGS_DATA_CACHE |
+ CRAT_CACHE_FLAGS_SIMD_CACHE),
+ .num_cu_shared = 2,
+ },
+};
+
static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
struct crat_subtype_computeunit *cu)
{
@@ -1514,11 +1610,17 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
num_of_cache_types = ARRAY_SIZE(beige_goby_cache_info);
break;
case IP_VERSION(10, 3, 3):
- case IP_VERSION(10, 3, 6): /* TODO: Double check these on production silicon */
- case IP_VERSION(10, 3, 7): /* TODO: Double check these on production silicon */
pcache_info = yellow_carp_cache_info;
num_of_cache_types = ARRAY_SIZE(yellow_carp_cache_info);
break;
+ case IP_VERSION(10, 3, 6):
+ pcache_info = gc_10_3_6_cache_info;
+ num_of_cache_types = ARRAY_SIZE(gc_10_3_6_cache_info);
+ break;
+ case IP_VERSION(10, 3, 7):
+ pcache_info = gfx1037_cache_info;
+ num_of_cache_types = ARRAY_SIZE(gfx1037_cache_info);
+ break;
case IP_VERSION(11, 0, 0):
case IP_VERSION(11, 0, 1):
case IP_VERSION(11, 0, 2):
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
index 2797029bd500..22b077ac9a19 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_migrate.c
@@ -973,12 +973,10 @@ out_unlock_prange:
out_unlock_svms:
mutex_unlock(&p->svms.lock);
out_unref_process:
+ pr_debug("CPU fault svms 0x%p address 0x%lx done\n", &p->svms, addr);
kfd_unref_process(p);
out_mmput:
mmput(mm);
-
- pr_debug("CPU fault svms 0x%p address 0x%lx done\n", &p->svms, addr);
-
return r ? VM_FAULT_SIGBUS : 0;
}
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 c053cb79cd06..589bee9acf16 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1549,6 +1549,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
adev->dm.dc->debug.visual_confirm = amdgpu_dc_visual_confirm;
+ /* TODO: Remove after DP2 receiver gets proper support of Cable ID feature */
+ adev->dm.dc->debug.ignore_cable_id = true;
+
r = dm_dmub_hw_init(adev);
if (r) {
DRM_ERROR("DMUB interface failed to initialize: status=%d\n", r);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index dfd3be49eac8..e6854f7270a6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -1369,7 +1369,7 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
{
struct amdgpu_device *adev = drm_to_adev(plane->dev);
const struct drm_format_info *info = drm_format_info(format);
- struct hw_asic_id asic_id = adev->dm.dc->ctx->asic_id;
+ int i;
enum dm_micro_swizzle microtile = modifier_gfx9_swizzle_mode(modifier) & 3;
@@ -1386,49 +1386,13 @@ static bool dm_plane_format_mod_supported(struct drm_plane *plane,
return true;
}
- /* check if swizzle mode is supported by this version of DCN */
- switch (asic_id.chip_family) {
- case FAMILY_SI:
- case FAMILY_CI:
- case FAMILY_KV:
- case FAMILY_CZ:
- case FAMILY_VI:
- /* asics before AI does not have modifier support */
- return false;
- case FAMILY_AI:
- case FAMILY_RV:
- case FAMILY_NV:
- case FAMILY_VGH:
- case FAMILY_YELLOW_CARP:
- case AMDGPU_FAMILY_GC_10_3_6:
- case AMDGPU_FAMILY_GC_10_3_7:
- switch (AMD_FMT_MOD_GET(TILE, modifier)) {
- case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_D_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_S_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_D:
- return true;
- default:
- return false;
- }
- break;
- case AMDGPU_FAMILY_GC_11_0_0:
- case AMDGPU_FAMILY_GC_11_0_1:
- switch (AMD_FMT_MOD_GET(TILE, modifier)) {
- case AMD_FMT_MOD_TILE_GFX11_256K_R_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_R_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_D_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_S_X:
- case AMD_FMT_MOD_TILE_GFX9_64K_D:
- return true;
- default:
- return false;
- }
- break;
- default:
- ASSERT(0); /* Unknown asic */
- break;
+ /* Check that the modifier is on the list of the plane's supported modifiers. */
+ for (i = 0; i < plane->modifier_count; i++) {
+ if (modifier == plane->modifiers[i])
+ break;
}
+ if (i == plane->modifier_count)
+ return false;
/*
* For D swizzle the canonical modifier depends on the bpp, so check
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
index 1c612ccf1944..6f77d8e538ab 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn32/dcn32_clk_mgr.c
@@ -157,6 +157,7 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
unsigned int num_levels;
struct clk_limit_num_entries *num_entries_per_clk = &clk_mgr_base->bw_params->clk_table.num_entries_per_clk;
+ unsigned int i;
memset(&(clk_mgr_base->clks), 0, sizeof(struct dc_clocks));
clk_mgr_base->clks.p_state_change_support = true;
@@ -205,18 +206,17 @@ void dcn32_init_clocks(struct clk_mgr *clk_mgr_base)
clk_mgr->dpm_present = true;
if (clk_mgr_base->ctx->dc->debug.min_disp_clk_khz) {
- unsigned int i;
-
for (i = 0; i < num_levels; i++)
if (clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz
< khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_disp_clk_khz))
clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz
= khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_disp_clk_khz);
}
+ for (i = 0; i < num_levels; i++)
+ if (clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz > 1950)
+ clk_mgr_base->bw_params->clk_table.entries[i].dispclk_mhz = 1950;
if (clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz) {
- unsigned int i;
-
for (i = 0; i < num_levels; i++)
if (clk_mgr_base->bw_params->clk_table.entries[i].dppclk_mhz
< khz_to_mhz_ceil(clk_mgr_base->ctx->dc->debug.min_dpp_clk_khz))
@@ -669,6 +669,9 @@ static void dcn32_get_memclk_states_from_smu(struct clk_mgr *clk_mgr_base)
&clk_mgr_base->bw_params->clk_table.entries[0].memclk_mhz,
&num_entries_per_clk->num_memclk_levels);
+ /* memclk must have at least one level */
+ num_entries_per_clk->num_memclk_levels = num_entries_per_clk->num_memclk_levels ? num_entries_per_clk->num_memclk_levels : 1;
+
dcn32_init_single_clock(clk_mgr, PPCLK_FCLK,
&clk_mgr_base->bw_params->clk_table.entries[0].fclk_mhz,
&num_entries_per_clk->num_fclk_levels);
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index bfc5474c0f4c..737b221ca689 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -852,6 +852,7 @@ struct dc_debug_options {
bool enable_double_buffered_dsc_pg_support;
bool enable_dp_dig_pixel_rate_div_policy;
enum lttpr_mode lttpr_mode_override;
+ unsigned int dsc_delay_factor_wa_x1000;
};
struct gpu_info_soc_bounding_box_v1_0;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
index 4996d2810edb..938dba5249d4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubp.c
@@ -623,6 +623,10 @@ void hubp2_cursor_set_attributes(
hubp->att.size.bits.width = attr->width;
hubp->att.size.bits.height = attr->height;
hubp->att.cur_ctl.bits.mode = attr->color_format;
+
+ hubp->cur_rect.w = attr->width;
+ hubp->cur_rect.h = attr->height;
+
hubp->att.cur_ctl.bits.pitch = hw_pitch;
hubp->att.cur_ctl.bits.line_per_chunk = lpc;
hubp->att.cur_ctl.bits.cur_2x_magnify = attr->attribute_flags.bits.ENABLE_MAGNIFICATION;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index d732b6f031a1..a7e0001a8f46 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -1270,16 +1270,6 @@ void dcn20_pipe_control_lock(
lock,
&hw_locks,
&inst_flags);
- } else if (pipe->stream && pipe->stream->mall_stream_config.type == SUBVP_MAIN) {
- union dmub_inbox0_cmd_lock_hw hw_lock_cmd = { 0 };
- hw_lock_cmd.bits.command_code = DMUB_INBOX0_CMD__HW_LOCK;
- hw_lock_cmd.bits.hw_lock_client = HW_LOCK_CLIENT_DRIVER;
- hw_lock_cmd.bits.lock_pipe = 1;
- hw_lock_cmd.bits.otg_inst = pipe->stream_res.tg->inst;
- hw_lock_cmd.bits.lock = lock;
- if (!lock)
- hw_lock_cmd.bits.should_release = 1;
- dmub_hw_lock_mgr_inbox0_cmd(dc->ctx->dmub_srv, hw_lock_cmd);
} else if (pipe->plane_state != NULL && pipe->plane_state->triplebuffer_flips) {
if (lock)
pipe->stream_res.tg->funcs->triplebuffer_lock(pipe->stream_res.tg);
@@ -1856,7 +1846,7 @@ void dcn20_post_unlock_program_front_end(
for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS*1000
&& hubp->funcs->hubp_is_flip_pending(hubp); j++)
- mdelay(1);
+ udelay(1);
}
}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
index d0ad72caead2..9066c511a052 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn314/dcn314_resource.c
@@ -847,7 +847,7 @@ static const struct resource_caps res_cap_dcn314 = {
.num_ddc = 5,
.num_vmid = 16,
.num_mpc_3dlut = 2,
- .num_dsc = 3,
+ .num_dsc = 4,
};
static const struct dc_plane_cap plane_cap = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
index d51d0c40ae5b..b03a7814e96d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn32/dcn32_resource_helpers.c
@@ -200,7 +200,7 @@ bool dcn32_all_pipes_have_stream_and_plane(struct dc *dc,
struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
if (!pipe->stream)
- return false;
+ continue;
if (!pipe->plane_state)
return false;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
index d680f1c5b69f..45db40c41882 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/dcn20_fpu.c
@@ -1228,6 +1228,7 @@ int dcn20_populate_dml_pipes_from_context(
pipes[pipe_cnt].pipe.src.dcc = false;
pipes[pipe_cnt].pipe.src.dcc_rate = 1;
pipes[pipe_cnt].pipe.dest.synchronized_vblank_all_planes = synchronized_vblank;
+ pipes[pipe_cnt].pipe.dest.synchronize_timings = synchronized_vblank;
pipes[pipe_cnt].pipe.dest.hblank_start = timing->h_total - timing->h_front_porch;
pipes[pipe_cnt].pipe.dest.hblank_end = pipes[pipe_cnt].pipe.dest.hblank_start
- timing->h_addressable
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
index 819de0f11012..f37c9a6b3b7e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
@@ -2359,9 +2359,11 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes)
dcn3_2_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
-
}
+ /* DML DSC delay factor workaround */
+ dcn3_2_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
+
/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
dcn3_2_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
index 5b91660a6496..3d184679f129 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c
@@ -364,10 +364,11 @@ static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerforman
for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k) {
v->DSCDelay[k] = dml32_DSCDelayRequirement(mode_lib->vba.DSCEnabled[k],
mode_lib->vba.ODMCombineEnabled[k], mode_lib->vba.DSCInputBitPerComponent[k],
- mode_lib->vba.OutputBpp[k], mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k],
+ mode_lib->vba.OutputBppPerState[mode_lib->vba.VoltageLevel][k],
+ mode_lib->vba.HActive[k], mode_lib->vba.HTotal[k],
mode_lib->vba.NumberOfDSCSlices[k], mode_lib->vba.OutputFormat[k],
mode_lib->vba.Output[k], mode_lib->vba.PixelClock[k],
- mode_lib->vba.PixelClockBackEnd[k]);
+ mode_lib->vba.PixelClockBackEnd[k], mode_lib->vba.ip.dsc_delay_factor_wa);
}
for (k = 0; k < mode_lib->vba.NumberOfActiveSurfaces; ++k)
@@ -1627,7 +1628,7 @@ static void mode_support_configuration(struct vba_vars_st *v,
&& !mode_lib->vba.MSOOrODMSplitWithNonDPLink
&& !mode_lib->vba.NotEnoughLanesForMSO
&& mode_lib->vba.LinkCapacitySupport[i] == true && !mode_lib->vba.P2IWith420
- && !mode_lib->vba.DSCOnlyIfNecessaryWithBPP
+ //&& !mode_lib->vba.DSCOnlyIfNecessaryWithBPP
&& !mode_lib->vba.DSC422NativeNotSupported
&& !mode_lib->vba.MPCCombineMethodIncompatible
&& mode_lib->vba.ODMCombine2To1SupportCheckOK[i] == true
@@ -2475,7 +2476,8 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
mode_lib->vba.OutputBppPerState[i][k], mode_lib->vba.HActive[k],
mode_lib->vba.HTotal[k], mode_lib->vba.NumberOfDSCSlices[k],
mode_lib->vba.OutputFormat[k], mode_lib->vba.Output[k],
- mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k]);
+ mode_lib->vba.PixelClock[k], mode_lib->vba.PixelClockBackEnd[k],
+ mode_lib->vba.ip.dsc_delay_factor_wa);
}
for (k = 0; k <= mode_lib->vba.NumberOfActiveSurfaces - 1; k++) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
index ad66e241f9ae..968924c491c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.c
@@ -1726,7 +1726,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
enum output_format_class OutputFormat,
enum output_encoder_class Output,
double PixelClock,
- double PixelClockBackEnd)
+ double PixelClockBackEnd,
+ double dsc_delay_factor_wa)
{
unsigned int DSCDelayRequirement_val;
@@ -1746,7 +1747,7 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
}
DSCDelayRequirement_val = DSCDelayRequirement_val + (HTotal - HActive) *
- dml_ceil(DSCDelayRequirement_val / HActive, 1);
+ dml_ceil((double)DSCDelayRequirement_val / HActive, 1);
DSCDelayRequirement_val = DSCDelayRequirement_val * PixelClock / PixelClockBackEnd;
@@ -1764,7 +1765,7 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
dml_print("DML::%s: DSCDelayRequirement_val = %d\n", __func__, DSCDelayRequirement_val);
#endif
- return DSCDelayRequirement_val;
+ return dml_ceil(DSCDelayRequirement_val * dsc_delay_factor_wa, 1);
}
void dml32_CalculateSurfaceSizeInMall(
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
index 55cead0d4237..2c3827546ac7 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_util_32.h
@@ -327,7 +327,8 @@ unsigned int dml32_DSCDelayRequirement(bool DSCEnabled,
enum output_format_class OutputFormat,
enum output_encoder_class Output,
double PixelClock,
- double PixelClockBackEnd);
+ double PixelClockBackEnd,
+ double dsc_delay_factor_wa);
void dml32_CalculateSurfaceSizeInMall(
unsigned int NumberOfActiveSurfaces,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
index a1276f6b9581..395ae8761980 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_rq_dlg_calc_32.c
@@ -291,8 +291,8 @@ void dml32_rq_dlg_get_dlg_reg(struct display_mode_lib *mode_lib,
dml_print("DML_DLG: %s: vready_after_vcount0 = %d\n", __func__, dlg_regs->vready_after_vcount0);
- dst_x_after_scaler = get_dst_x_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx);
- dst_y_after_scaler = get_dst_y_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx);
+ dst_x_after_scaler = dml_ceil(get_dst_x_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx), 1);
+ dst_y_after_scaler = dml_ceil(get_dst_y_after_scaler(mode_lib, e2e_pipe_param, num_pipes, pipe_idx), 1);
// do some adjustment on the dst_after scaler to account for odm combine mode
dml_print("DML_DLG: %s: input dst_x_after_scaler = %d\n", __func__, dst_x_after_scaler);
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
index dd90f241e906..ec0486efab14 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
@@ -29,6 +29,7 @@
#include "dcn321_fpu.h"
#include "dcn32/dcn32_resource.h"
#include "dcn321/dcn321_resource.h"
+#include "dml/dcn32/display_mode_vba_util_32.h"
#define DCN3_2_DEFAULT_DET_SIZE 256
@@ -119,15 +120,15 @@ struct _vcs_dpi_soc_bounding_box_st dcn3_21_soc = {
},
},
.num_states = 1,
- .sr_exit_time_us = 12.36,
- .sr_enter_plus_exit_time_us = 16.72,
+ .sr_exit_time_us = 19.95,
+ .sr_enter_plus_exit_time_us = 24.36,
.sr_exit_z8_time_us = 285.0,
.sr_enter_plus_exit_z8_time_us = 320,
.writeback_latency_us = 12.0,
.round_trip_ping_latency_dcfclk_cycles = 263,
- .urgent_latency_pixel_data_only_us = 4.0,
- .urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
- .urgent_latency_vm_data_only_us = 4.0,
+ .urgent_latency_pixel_data_only_us = 9.35,
+ .urgent_latency_pixel_mixed_with_vm_data_us = 9.35,
+ .urgent_latency_vm_data_only_us = 9.35,
.fclk_change_latency_us = 20,
.usr_retraining_latency_us = 2,
.smn_latency_us = 2,
@@ -538,9 +539,11 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
if (dc->ctx->dc_bios->vram_info.dram_channel_width_bytes)
dcn3_21_soc.dram_channel_width_bytes = dc->ctx->dc_bios->vram_info.dram_channel_width_bytes;
-
}
+ /* DML DSC delay factor workaround */
+ dcn3_21_ip.dsc_delay_factor_wa = dc->debug.dsc_delay_factor_wa_x1000 / 1000.0;
+
/* Override dispclk_dppclk_vco_speed_mhz from Clk Mgr */
dcn3_21_soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
dc->dml.soc.dispclk_dppclk_vco_speed_mhz = dc->clk_mgr->dentist_vco_freq_khz / 1000.0;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index f33a8879b05a..d7be01ac0751 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -364,6 +364,9 @@ struct _vcs_dpi_ip_params_st {
unsigned int max_num_dp2p0_outputs;
unsigned int max_num_dp2p0_streams;
unsigned int VBlankNomDefaultUS;
+
+ /* DM workarounds */
+ double dsc_delay_factor_wa; // TODO: Remove after implementing root cause fix
};
struct _vcs_dpi_display_xfc_params_st {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index 03924aed8d5c..8e6585dab20e 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -625,7 +625,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
mode_lib->vba.skip_dio_check[mode_lib->vba.NumberOfActivePlanes] =
dout->is_virtual;
- if (!dout->dsc_enable)
+ if (dout->dsc_enable)
mode_lib->vba.ForcedOutputLinkBPP[mode_lib->vba.NumberOfActivePlanes] = dout->output_bpp;
else
mode_lib->vba.ForcedOutputLinkBPP[mode_lib->vba.NumberOfActivePlanes] = 0.0;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
index 063f4a737605..b76f0f7e4299 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu13_driver_if_v13_0_0.h
@@ -25,7 +25,7 @@
#define SMU13_DRIVER_IF_V13_0_0_H
//Increment this version if SkuTable_t or BoardTable_t change
-#define PPTABLE_VERSION 0x24
+#define PPTABLE_VERSION 0x26
#define NUM_GFXCLK_DPM_LEVELS 16
#define NUM_SOCCLK_DPM_LEVELS 8
@@ -109,6 +109,22 @@
#define FEATURE_SPARE_63_BIT 63
#define NUM_FEATURES 64
+#define ALLOWED_FEATURE_CTRL_DEFAULT 0xFFFFFFFFFFFFFFFFULL
+#define ALLOWED_FEATURE_CTRL_SCPM ((1 << FEATURE_DPM_GFXCLK_BIT) | \
+ (1 << FEATURE_DPM_GFX_POWER_OPTIMIZER_BIT) | \
+ (1 << FEATURE_DPM_UCLK_BIT) | \
+ (1 << FEATURE_DPM_FCLK_BIT) | \
+ (1 << FEATURE_DPM_SOCCLK_BIT) | \
+ (1 << FEATURE_DPM_MP0CLK_BIT) | \
+ (1 << FEATURE_DPM_LINK_BIT) | \
+ (1 << FEATURE_DPM_DCN_BIT) | \
+ (1 << FEATURE_DS_GFXCLK_BIT) | \
+ (1 << FEATURE_DS_SOCCLK_BIT) | \
+ (1 << FEATURE_DS_FCLK_BIT) | \
+ (1 << FEATURE_DS_LCLK_BIT) | \
+ (1 << FEATURE_DS_DCFCLK_BIT) | \
+ (1 << FEATURE_DS_UCLK_BIT))
+
//For use with feature control messages
typedef enum {
FEATURE_PWR_ALL,
@@ -133,6 +149,7 @@ typedef enum {
#define DEBUG_OVERRIDE_DISABLE_DFLL 0x00000200
#define DEBUG_OVERRIDE_ENABLE_RLC_VF_BRINGUP_MODE 0x00000400
#define DEBUG_OVERRIDE_DFLL_MASTER_MODE 0x00000800
+#define DEBUG_OVERRIDE_ENABLE_PROFILING_MODE 0x00001000
// VR Mapping Bit Defines
#define VR_MAPPING_VR_SELECT_MASK 0x01
@@ -262,15 +279,15 @@ typedef enum {
} I2cControllerPort_e;
typedef enum {
- I2C_CONTROLLER_NAME_VR_GFX = 0,
- I2C_CONTROLLER_NAME_VR_SOC,
- I2C_CONTROLLER_NAME_VR_VMEMP,
- I2C_CONTROLLER_NAME_VR_VDDIO,
- I2C_CONTROLLER_NAME_LIQUID0,
- I2C_CONTROLLER_NAME_LIQUID1,
- I2C_CONTROLLER_NAME_PLX,
- I2C_CONTROLLER_NAME_OTHER,
- I2C_CONTROLLER_NAME_COUNT,
+ I2C_CONTROLLER_NAME_VR_GFX = 0,
+ I2C_CONTROLLER_NAME_VR_SOC,
+ I2C_CONTROLLER_NAME_VR_VMEMP,
+ I2C_CONTROLLER_NAME_VR_VDDIO,
+ I2C_CONTROLLER_NAME_LIQUID0,
+ I2C_CONTROLLER_NAME_LIQUID1,
+ I2C_CONTROLLER_NAME_PLX,
+ I2C_CONTROLLER_NAME_FAN_INTAKE,
+ I2C_CONTROLLER_NAME_COUNT,
} I2cControllerName_e;
typedef enum {
@@ -282,16 +299,17 @@ typedef enum {
I2C_CONTROLLER_THROTTLER_LIQUID0,
I2C_CONTROLLER_THROTTLER_LIQUID1,
I2C_CONTROLLER_THROTTLER_PLX,
+ I2C_CONTROLLER_THROTTLER_FAN_INTAKE,
I2C_CONTROLLER_THROTTLER_INA3221,
I2C_CONTROLLER_THROTTLER_COUNT,
} I2cControllerThrottler_e;
typedef enum {
- I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5,
- I2C_CONTROLLER_PROTOCOL_VR_IR35217,
- I2C_CONTROLLER_PROTOCOL_TMP_TMP102A,
- I2C_CONTROLLER_PROTOCOL_INA3221,
- I2C_CONTROLLER_PROTOCOL_COUNT,
+ I2C_CONTROLLER_PROTOCOL_VR_XPDE132G5,
+ I2C_CONTROLLER_PROTOCOL_VR_IR35217,
+ I2C_CONTROLLER_PROTOCOL_TMP_MAX31875,
+ I2C_CONTROLLER_PROTOCOL_INA3221,
+ I2C_CONTROLLER_PROTOCOL_COUNT,
} I2cControllerProtocol_e;
typedef struct {
@@ -658,13 +676,20 @@ typedef struct {
#define PP_NUM_OD_VF_CURVE_POINTS PP_NUM_RTAVFS_PWL_ZONES + 1
+typedef enum {
+ FAN_MODE_AUTO = 0,
+ FAN_MODE_MANUAL_LINEAR,
+} FanMode_e;
typedef struct {
uint32_t FeatureCtrlMask;
//Voltage control
int16_t VoltageOffsetPerZoneBoundary[PP_NUM_OD_VF_CURVE_POINTS];
- uint16_t reserved[2];
+ uint16_t VddGfxVmax; // in mV
+
+ uint8_t IdlePwrSavingFeaturesCtrl;
+ uint8_t RuntimePwrSavingFeaturesCtrl;
//Frequency changes
int16_t GfxclkFmin; // MHz
@@ -674,7 +699,7 @@ typedef struct {
//PPT
int16_t Ppt; // %
- int16_t reserved1;
+ int16_t Tdc;
//Fan control
uint8_t FanLinearPwmPoints[NUM_OD_FAN_MAX_POINTS];
@@ -701,16 +726,19 @@ typedef struct {
uint32_t FeatureCtrlMask;
int16_t VoltageOffsetPerZoneBoundary;
- uint16_t reserved[2];
+ uint16_t VddGfxVmax; // in mV
+
+ uint8_t IdlePwrSavingFeaturesCtrl;
+ uint8_t RuntimePwrSavingFeaturesCtrl;
- uint16_t GfxclkFmin; // MHz
- uint16_t GfxclkFmax; // MHz
+ int16_t GfxclkFmin; // MHz
+ int16_t GfxclkFmax; // MHz
uint16_t UclkFmin; // MHz
uint16_t UclkFmax; // MHz
//PPT
int16_t Ppt; // %
- int16_t reserved1;
+ int16_t Tdc;
uint8_t FanLinearPwmPoints;
uint8_t FanLinearTempPoints;
@@ -857,7 +885,8 @@ typedef struct {
uint16_t FanStartTempMin;
uint16_t FanStartTempMax;
- uint32_t Spare[12];
+ uint16_t PowerMinPpt0[POWER_SOURCE_COUNT];
+ uint32_t Spare[11];
} MsgLimits_t;
@@ -1041,7 +1070,17 @@ typedef struct {
uint32_t GfxoffSpare[15];
// GFX GPO
- uint32_t GfxGpoSpare[16];
+ uint32_t DfllBtcMasterScalerM;
+ int32_t DfllBtcMasterScalerB;
+ uint32_t DfllBtcSlaveScalerM;
+ int32_t DfllBtcSlaveScalerB;
+
+ uint32_t DfllPccAsWaitCtrl; //GDFLL_AS_WAIT_CTRL_PCC register value to be passed to RLC msg
+ uint32_t DfllPccAsStepCtrl; //GDFLL_AS_STEP_CTRL_PCC register value to be passed to RLC msg
+
+ uint32_t DfllL2FrequencyBoostM; //Unitless (float)
+ uint32_t DfllL2FrequencyBoostB; //In MHz (integer)
+ uint32_t GfxGpoSpare[8];
// GFX DCS
@@ -1114,12 +1153,14 @@ typedef struct {
uint16_t IntakeTempHighIntakeAcousticLimit;
uint16_t IntakeTempAcouticLimitReleaseRate;
- uint16_t FanStalledTempLimitOffset;
+ int16_t FanAbnormalTempLimitOffset;
uint16_t FanStalledTriggerRpm;
- uint16_t FanAbnormalTriggerRpm;
- uint16_t FanPadding;
+ uint16_t FanAbnormalTriggerRpmCoeff;
+ uint16_t FanAbnormalDetectionEnable;
- uint32_t FanSpare[14];
+ uint8_t FanIntakeSensorSupport;
+ uint8_t FanIntakePadding[3];
+ uint32_t FanSpare[13];
// SECTION: VDD_GFX AVFS
@@ -1198,8 +1239,13 @@ typedef struct {
int16_t TotalBoardPowerM;
int16_t TotalBoardPowerB;
+ //PMFW-11158
+ QuadraticInt_t qFeffCoeffGameClock[POWER_SOURCE_COUNT];
+ QuadraticInt_t qFeffCoeffBaseClock[POWER_SOURCE_COUNT];
+ QuadraticInt_t qFeffCoeffBoostClock[POWER_SOURCE_COUNT];
+
// SECTION: Sku Reserved
- uint32_t Spare[61];
+ uint32_t Spare[43];
// Padding for MMHUB - do not modify this
uint32_t MmHubPadding[8];
@@ -1288,8 +1334,11 @@ typedef struct {
uint32_t PostVoltageSetBacoDelay; // in microseconds. Amount of time FW will wait after power good is established or PSI0 command is issued
uint32_t BacoEntryDelay; // in milliseconds. Amount of time FW will wait to trigger BACO entry after receiving entry notification from OS
+ uint8_t FuseWritePowerMuxPresent;
+ uint8_t FuseWritePadding[3];
+
// SECTION: Board Reserved
- uint32_t BoardSpare[64];
+ uint32_t BoardSpare[63];
// SECTION: Structure Padding
@@ -1381,7 +1430,7 @@ typedef struct {
uint16_t AverageTotalBoardPower;
uint16_t AvgTemperature[TEMP_COUNT];
- uint16_t TempPadding;
+ uint16_t AvgTemperatureFanIntake;
uint8_t PcieRate ;
uint8_t PcieWidth ;
@@ -1550,5 +1599,7 @@ typedef struct {
#define IH_INTERRUPT_CONTEXT_ID_AUDIO_D0 0x5
#define IH_INTERRUPT_CONTEXT_ID_AUDIO_D3 0x6
#define IH_INTERRUPT_CONTEXT_ID_THERMAL_THROTTLING 0x7
+#define IH_INTERRUPT_CONTEXT_ID_FAN_ABNORMAL 0x8
+#define IH_INTERRUPT_CONTEXT_ID_FAN_RECOVERY 0x9
#endif
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 8f72202aea8e..80fb583b18d9 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -30,7 +30,7 @@
#define SMU13_DRIVER_IF_VERSION_ALDE 0x08
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_4 0x07
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_5 0x04
-#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0 0x30
+#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10 0x32
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_7 0x2C
#define SMU13_DRIVER_IF_VERSION_SMU_V13_0_10 0x1D
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index c4552ade8d44..43fb102a65f5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -289,7 +289,8 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_ALDE;
break;
case IP_VERSION(13, 0, 0):
- smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0;
+ case IP_VERSION(13, 0, 10):
+ smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_0_10;
break;
case IP_VERSION(13, 0, 7):
smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_7;
@@ -305,9 +306,6 @@ int smu_v13_0_check_fw_version(struct smu_context *smu)
case IP_VERSION(13, 0, 5):
smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_5;
break;
- case IP_VERSION(13, 0, 10):
- smu->smc_driver_if_version = SMU13_DRIVER_IF_VERSION_SMU_V13_0_10;
- break;
default:
dev_err(adev->dev, "smu unsupported IP version: 0x%x.\n",
adev->ip_versions[MP1_HWIP][0]);
@@ -842,6 +840,7 @@ int smu_v13_0_gfx_off_control(struct smu_context *smu, bool enable)
case IP_VERSION(13, 0, 5):
case IP_VERSION(13, 0, 7):
case IP_VERSION(13, 0, 8):
+ case IP_VERSION(13, 0, 10):
if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
return 0;
if (enable)
diff --git a/drivers/gpu/drm/bridge/parade-ps8640.c b/drivers/gpu/drm/bridge/parade-ps8640.c
index d7483c13c569..083337a27966 100644
--- a/drivers/gpu/drm/bridge/parade-ps8640.c
+++ b/drivers/gpu/drm/bridge/parade-ps8640.c
@@ -105,6 +105,7 @@ struct ps8640 {
struct gpio_desc *gpio_powerdown;
struct device_link *link;
bool pre_enabled;
+ bool need_post_hpd_delay;
};
static const struct regmap_config ps8640_regmap_config[] = {
@@ -173,14 +174,31 @@ static int _ps8640_wait_hpd_asserted(struct ps8640 *ps_bridge, unsigned long wai
{
struct regmap *map = ps_bridge->regmap[PAGE2_TOP_CNTL];
int status;
+ int ret;
/*
* Apparently something about the firmware in the chip signals that
* HPD goes high by reporting GPIO9 as high (even though HPD isn't
* actually connected to GPIO9).
*/
- return regmap_read_poll_timeout(map, PAGE2_GPIO_H, status,
- status & PS_GPIO9, wait_us / 10, wait_us);
+ ret = regmap_read_poll_timeout(map, PAGE2_GPIO_H, status,
+ status & PS_GPIO9, wait_us / 10, wait_us);
+
+ /*
+ * The first time we see HPD go high after a reset we delay an extra
+ * 50 ms. The best guess is that the MCU is doing "stuff" during this
+ * time (maybe talking to the panel) and we don't want to interrupt it.
+ *
+ * No locking is done around "need_post_hpd_delay". If we're here we
+ * know we're holding a PM Runtime reference and the only other place
+ * that touches this is PM Runtime resume.
+ */
+ if (!ret && ps_bridge->need_post_hpd_delay) {
+ ps_bridge->need_post_hpd_delay = false;
+ msleep(50);
+ }
+
+ return ret;
}
static int ps8640_wait_hpd_asserted(struct drm_dp_aux *aux, unsigned long wait_us)
@@ -381,6 +399,9 @@ static int __maybe_unused ps8640_resume(struct device *dev)
msleep(50);
gpiod_set_value(ps_bridge->gpio_reset, 0);
+ /* We just reset things, so we need a delay after the first HPD */
+ ps_bridge->need_post_hpd_delay = true;
+
/*
* Mystery 200 ms delay for the "MCU to be ready". It's unclear if
* this is truly necessary since the MCU will already signal that
diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c
index e2f76621453c..3ee59bae9d2f 100644
--- a/drivers/gpu/drm/drm_format_helper.c
+++ b/drivers/gpu/drm/drm_format_helper.c
@@ -807,6 +807,38 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t
return false;
}
+static const uint32_t conv_from_xrgb8888[] = {
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_ARGB8888,
+ DRM_FORMAT_XRGB2101010,
+ DRM_FORMAT_ARGB2101010,
+ DRM_FORMAT_RGB565,
+ DRM_FORMAT_RGB888,
+};
+
+static const uint32_t conv_from_rgb565_888[] = {
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_ARGB8888,
+};
+
+static bool is_conversion_supported(uint32_t from, uint32_t to)
+{
+ switch (from) {
+ case DRM_FORMAT_XRGB8888:
+ case DRM_FORMAT_ARGB8888:
+ return is_listed_fourcc(conv_from_xrgb8888, ARRAY_SIZE(conv_from_xrgb8888), to);
+ case DRM_FORMAT_RGB565:
+ case DRM_FORMAT_RGB888:
+ return is_listed_fourcc(conv_from_rgb565_888, ARRAY_SIZE(conv_from_rgb565_888), to);
+ case DRM_FORMAT_XRGB2101010:
+ return to == DRM_FORMAT_ARGB2101010;
+ case DRM_FORMAT_ARGB2101010:
+ return to == DRM_FORMAT_XRGB2101010;
+ default:
+ return false;
+ }
+}
+
/**
* drm_fb_build_fourcc_list - Filters a list of supported color formats against
* the device's native formats
@@ -827,7 +859,9 @@ static bool is_listed_fourcc(const uint32_t *fourccs, size_t nfourccs, uint32_t
* be handed over to drm_universal_plane_init() et al. Native formats
* will go before emulated formats. Other heuristics might be applied
* to optimize the order. Formats near the beginning of the list are
- * usually preferred over formats near the end of the list.
+ * usually preferred over formats near the end of the list. Formats
+ * without conversion helpers will be skipped. New drivers should only
+ * pass in XRGB8888 and avoid exposing additional emulated formats.
*
* Returns:
* The number of color-formats 4CC codes returned in @fourccs_out.
@@ -839,7 +873,7 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev,
{
u32 *fourccs = fourccs_out;
const u32 *fourccs_end = fourccs_out + nfourccs_out;
- bool found_native = false;
+ uint32_t native_format = 0;
size_t i;
/*
@@ -858,27 +892,19 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev,
drm_dbg_kms(dev, "adding native format %p4cc\n", &fourcc);
- if (!found_native)
- found_native = is_listed_fourcc(driver_fourccs, driver_nfourccs, fourcc);
+ /*
+ * There should only be one native format with the current API.
+ * This API needs to be refactored to correctly support arbitrary
+ * sets of native formats, since it needs to report which native
+ * format to use for each emulated format.
+ */
+ if (!native_format)
+ native_format = fourcc;
*fourccs = fourcc;
++fourccs;
}
/*
- * The plane's atomic_update helper converts the framebuffer's color format
- * to a native format when copying to device memory.
- *
- * If there is not a single format supported by both, device and
- * driver, the native formats are likely not supported by the conversion
- * helpers. Therefore *only* support the native formats and add a
- * conversion helper ASAP.
- */
- if (!found_native) {
- drm_warn(dev, "Format conversion helpers required to add extra formats.\n");
- goto out;
- }
-
- /*
* The extra formats, emulated by the driver, go second.
*/
@@ -890,6 +916,9 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev,
} else if (fourccs == fourccs_end) {
drm_warn(dev, "Ignoring emulated format %p4cc\n", &fourcc);
continue; /* end of available output buffer */
+ } else if (!is_conversion_supported(fourcc, native_format)) {
+ drm_dbg_kms(dev, "Unsupported emulated format %p4cc\n", &fourcc);
+ continue; /* format is not supported for conversion */
}
drm_dbg_kms(dev, "adding emulated format %p4cc\n", &fourcc);
@@ -898,7 +927,6 @@ size_t drm_fb_build_fourcc_list(struct drm_device *dev,
++fourccs;
}
-out:
return fourccs - fourccs_out;
}
EXPORT_SYMBOL(drm_fb_build_fourcc_list);
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index a26edcdadc21..cea00aaca04b 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -282,6 +282,7 @@ i915-y += \
display/intel_ddi.o \
display/intel_ddi_buf_trans.o \
display/intel_display_trace.o \
+ display/intel_dkl_phy.o \
display/intel_dp.o \
display/intel_dp_aux.o \
display/intel_dp_aux_backlight.o \
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index da8472cdc135..69ecf2a3d6c6 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -43,6 +43,7 @@
#include "intel_de.h"
#include "intel_display_power.h"
#include "intel_display_types.h"
+#include "intel_dkl_phy.h"
#include "intel_dp.h"
#include "intel_dp_link_training.h"
#include "intel_dp_mst.h"
@@ -1262,33 +1263,30 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder,
for (ln = 0; ln < 2; ln++) {
int level;
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, ln));
-
- intel_de_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), 0);
+ intel_dkl_phy_write(dev_priv, DKL_TX_PMD_LANE_SUS(tc_port), ln, 0);
level = intel_ddi_level(encoder, crtc_state, 2*ln+0);
- intel_de_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port),
- DKL_TX_PRESHOOT_COEFF_MASK |
- DKL_TX_DE_EMPAHSIS_COEFF_MASK |
- DKL_TX_VSWING_CONTROL_MASK,
- DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
- DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
- DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
+ intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL0(tc_port), ln,
+ DKL_TX_PRESHOOT_COEFF_MASK |
+ DKL_TX_DE_EMPAHSIS_COEFF_MASK |
+ DKL_TX_VSWING_CONTROL_MASK,
+ DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
+ DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
+ DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
level = intel_ddi_level(encoder, crtc_state, 2*ln+1);
- intel_de_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port),
- DKL_TX_PRESHOOT_COEFF_MASK |
- DKL_TX_DE_EMPAHSIS_COEFF_MASK |
- DKL_TX_VSWING_CONTROL_MASK,
- DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
- DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
- DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
+ intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL1(tc_port), ln,
+ DKL_TX_PRESHOOT_COEFF_MASK |
+ DKL_TX_DE_EMPAHSIS_COEFF_MASK |
+ DKL_TX_VSWING_CONTROL_MASK,
+ DKL_TX_PRESHOOT_COEFF(trans->entries[level].dkl.preshoot) |
+ DKL_TX_DE_EMPHASIS_COEFF(trans->entries[level].dkl.de_emphasis) |
+ DKL_TX_VSWING_CONTROL(trans->entries[level].dkl.vswing));
- intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
- DKL_TX_DP20BITMODE, 0);
+ intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln,
+ DKL_TX_DP20BITMODE, 0);
if (IS_ALDERLAKE_P(dev_priv)) {
u32 val;
@@ -1306,10 +1304,10 @@ static void tgl_dkl_phy_set_signal_levels(struct intel_encoder *encoder,
val |= DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2(0);
}
- intel_de_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port),
- DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK |
- DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK,
- val);
+ intel_dkl_phy_rmw(dev_priv, DKL_TX_DPCNTL2(tc_port), ln,
+ DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX1_MASK |
+ DKL_TX_DPCNTL2_CFG_LOADGENSELECT_TX2_MASK,
+ val);
}
}
}
@@ -2019,12 +2017,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
return;
if (DISPLAY_VER(dev_priv) >= 12) {
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x0));
- ln0 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port));
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x1));
- ln1 = intel_de_read(dev_priv, DKL_DP_MODE(tc_port));
+ ln0 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 0);
+ ln1 = intel_dkl_phy_read(dev_priv, DKL_DP_MODE(tc_port), 1);
} else {
ln0 = intel_de_read(dev_priv, MG_DP_MODE(0, tc_port));
ln1 = intel_de_read(dev_priv, MG_DP_MODE(1, tc_port));
@@ -2085,12 +2079,8 @@ icl_program_mg_dp_mode(struct intel_digital_port *dig_port,
}
if (DISPLAY_VER(dev_priv) >= 12) {
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x0));
- intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln0);
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x1));
- intel_de_write(dev_priv, DKL_DP_MODE(tc_port), ln1);
+ intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 0, ln0);
+ intel_dkl_phy_write(dev_priv, DKL_DP_MODE(tc_port), 1, ln1);
} else {
intel_de_write(dev_priv, MG_DP_MODE(0, tc_port), ln0);
intel_de_write(dev_priv, MG_DP_MODE(1, tc_port), ln1);
@@ -3094,10 +3084,8 @@ static void adlp_tbt_to_dp_alt_switch_wa(struct intel_encoder *encoder)
enum tc_port tc_port = intel_port_to_tc(i915, encoder->port);
int ln;
- for (ln = 0; ln < 2; ln++) {
- intel_de_write(i915, HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
- intel_de_rmw(i915, DKL_PCS_DW5(tc_port), DKL_PCS_DW5_CORE_SOFTRESET, 0);
- }
+ for (ln = 0; ln < 2; ln++)
+ intel_dkl_phy_rmw(i915, DKL_PCS_DW5(tc_port), ln, DKL_PCS_DW5_CORE_SOFTRESET, 0);
}
static void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp,
diff --git a/drivers/gpu/drm/i915/display/intel_display_core.h b/drivers/gpu/drm/i915/display/intel_display_core.h
index 96cf994b0ad1..9b51148e8ba5 100644
--- a/drivers/gpu/drm/i915/display/intel_display_core.h
+++ b/drivers/gpu/drm/i915/display/intel_display_core.h
@@ -316,6 +316,14 @@ struct intel_display {
} dbuf;
struct {
+ /*
+ * dkl.phy_lock protects against concurrent access of the
+ * Dekel TypeC PHYs.
+ */
+ spinlock_t phy_lock;
+ } dkl;
+
+ struct {
/* VLV/CHV/BXT/GLK DSI MMIO register base address */
u32 mmio_base;
} dsi;
diff --git a/drivers/gpu/drm/i915/display/intel_display_power_well.c b/drivers/gpu/drm/i915/display/intel_display_power_well.c
index df7ee4969ef1..1d18eee56253 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power_well.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power_well.c
@@ -12,6 +12,7 @@
#include "intel_de.h"
#include "intel_display_power_well.h"
#include "intel_display_types.h"
+#include "intel_dkl_phy.h"
#include "intel_dmc.h"
#include "intel_dpio_phy.h"
#include "intel_dpll.h"
@@ -529,11 +530,9 @@ icl_tc_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
enum tc_port tc_port;
tc_port = TGL_AUX_PW_TO_TC_PORT(i915_power_well_instance(power_well)->hsw.idx);
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x2));
- if (intel_de_wait_for_set(dev_priv, DKL_CMN_UC_DW_27(tc_port),
- DKL_CMN_UC_DW27_UC_HEALTH, 1))
+ if (wait_for(intel_dkl_phy_read(dev_priv, DKL_CMN_UC_DW_27(tc_port), 2) &
+ DKL_CMN_UC_DW27_UC_HEALTH, 1))
drm_warn(&dev_priv->drm,
"Timeout waiting TC uC health\n");
}
diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.c b/drivers/gpu/drm/i915/display/intel_dkl_phy.c
new file mode 100644
index 000000000000..710b030c7ed5
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.c
@@ -0,0 +1,109 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_reg.h"
+
+#include "intel_de.h"
+#include "intel_display.h"
+#include "intel_dkl_phy.h"
+
+static void
+dkl_phy_set_hip_idx(struct drm_i915_private *i915, i915_reg_t reg, int idx)
+{
+ enum tc_port tc_port = DKL_REG_TC_PORT(reg);
+
+ drm_WARN_ON(&i915->drm, tc_port < TC_PORT_1 || tc_port >= I915_MAX_TC_PORTS);
+
+ intel_de_write(i915,
+ HIP_INDEX_REG(tc_port),
+ HIP_INDEX_VAL(tc_port, idx));
+}
+
+/**
+ * intel_dkl_phy_read - read a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @ln: lane instance of @reg
+ *
+ * Read the @reg Dekel PHY register.
+ *
+ * Returns the read value.
+ */
+u32
+intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln)
+{
+ u32 val;
+
+ spin_lock(&i915->display.dkl.phy_lock);
+
+ dkl_phy_set_hip_idx(i915, reg, ln);
+ val = intel_de_read(i915, reg);
+
+ spin_unlock(&i915->display.dkl.phy_lock);
+
+ return val;
+}
+
+/**
+ * intel_dkl_phy_write - write a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @ln: lane instance of @reg
+ * @val: value to write
+ *
+ * Write @val to the @reg Dekel PHY register.
+ */
+void
+intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val)
+{
+ spin_lock(&i915->display.dkl.phy_lock);
+
+ dkl_phy_set_hip_idx(i915, reg, ln);
+ intel_de_write(i915, reg, val);
+
+ spin_unlock(&i915->display.dkl.phy_lock);
+}
+
+/**
+ * intel_dkl_phy_rmw - read-modify-write a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @ln: lane instance of @reg
+ * @clear: mask to clear
+ * @set: mask to set
+ *
+ * Read the @reg Dekel PHY register, clearing then setting the @clear/@set bits in it, and writing
+ * this value back to the register if the value differs from the read one.
+ */
+void
+intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set)
+{
+ spin_lock(&i915->display.dkl.phy_lock);
+
+ dkl_phy_set_hip_idx(i915, reg, ln);
+ intel_de_rmw(i915, reg, clear, set);
+
+ spin_unlock(&i915->display.dkl.phy_lock);
+}
+
+/**
+ * intel_dkl_phy_posting_read - do a posting read from a Dekel PHY register
+ * @i915: i915 device instance
+ * @reg: Dekel PHY register
+ * @ln: lane instance of @reg
+ *
+ * Read the @reg Dekel PHY register without returning the read value.
+ */
+void
+intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln)
+{
+ spin_lock(&i915->display.dkl.phy_lock);
+
+ dkl_phy_set_hip_idx(i915, reg, ln);
+ intel_de_posting_read(i915, reg);
+
+ spin_unlock(&i915->display.dkl.phy_lock);
+}
diff --git a/drivers/gpu/drm/i915/display/intel_dkl_phy.h b/drivers/gpu/drm/i915/display/intel_dkl_phy.h
new file mode 100644
index 000000000000..260ad121a0b1
--- /dev/null
+++ b/drivers/gpu/drm/i915/display/intel_dkl_phy.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef __INTEL_DKL_PHY_H__
+#define __INTEL_DKL_PHY_H__
+
+#include <linux/types.h>
+
+#include "i915_reg_defs.h"
+
+struct drm_i915_private;
+
+u32
+intel_dkl_phy_read(struct drm_i915_private *i915, i915_reg_t reg, int ln);
+void
+intel_dkl_phy_write(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 val);
+void
+intel_dkl_phy_rmw(struct drm_i915_private *i915, i915_reg_t reg, int ln, u32 clear, u32 set);
+void
+intel_dkl_phy_posting_read(struct drm_i915_private *i915, i915_reg_t reg, int ln);
+
+#endif /* __INTEL_DKL_PHY_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index c9be61d2348e..2b5bc95a8b0d 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -3957,6 +3957,8 @@ intel_dp_handle_hdmi_link_status_change(struct intel_dp *intel_dp)
drm_dp_pcon_hdmi_frl_link_error_count(&intel_dp->aux, &intel_dp->attached_connector->base);
+ intel_dp->frl.is_trained = false;
+
/* Restart FRL training or fall back to TMDS mode */
intel_dp_check_frl_training(intel_dp);
}
@@ -5274,7 +5276,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
encoder->devdata, IS_ERR(edid) ? NULL : edid);
intel_panel_add_edid_fixed_modes(intel_connector,
- intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE,
+ intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE ||
intel_vrr_is_capable(intel_connector));
/* MSO requires information from the EDID */
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index e5fb66a5dd02..64dd603dc69a 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -25,6 +25,7 @@
#include "intel_de.h"
#include "intel_display_types.h"
+#include "intel_dkl_phy.h"
#include "intel_dpio_phy.h"
#include "intel_dpll.h"
#include "intel_dpll_mgr.h"
@@ -3508,15 +3509,12 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
* All registers read here have the same HIP_INDEX_REG even though
* they are on different building blocks
*/
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x2));
-
- hw_state->mg_refclkin_ctl = intel_de_read(dev_priv,
- DKL_REFCLKIN_CTL(tc_port));
+ hw_state->mg_refclkin_ctl = intel_dkl_phy_read(dev_priv,
+ DKL_REFCLKIN_CTL(tc_port), 2);
hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
hw_state->mg_clktop2_hsclkctl =
- intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
+ intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2);
hw_state->mg_clktop2_hsclkctl &=
MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
@@ -3524,32 +3522,32 @@ static bool dkl_pll_get_hw_state(struct drm_i915_private *dev_priv,
MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
hw_state->mg_clktop2_coreclkctl1 =
- intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
+ intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2);
hw_state->mg_clktop2_coreclkctl1 &=
MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
- hw_state->mg_pll_div0 = intel_de_read(dev_priv, DKL_PLL_DIV0(tc_port));
+ hw_state->mg_pll_div0 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV0(tc_port), 2);
val = DKL_PLL_DIV0_MASK;
if (dev_priv->display.vbt.override_afc_startup)
val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
hw_state->mg_pll_div0 &= val;
- hw_state->mg_pll_div1 = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
+ hw_state->mg_pll_div1 = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2);
hw_state->mg_pll_div1 &= (DKL_PLL_DIV1_IREF_TRIM_MASK |
DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
- hw_state->mg_pll_ssc = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port));
+ hw_state->mg_pll_ssc = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2);
hw_state->mg_pll_ssc &= (DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
DKL_PLL_SSC_STEP_LEN_MASK |
DKL_PLL_SSC_STEP_NUM_MASK |
DKL_PLL_SSC_EN);
- hw_state->mg_pll_bias = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port));
+ hw_state->mg_pll_bias = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2);
hw_state->mg_pll_bias &= (DKL_PLL_BIAS_FRAC_EN_H |
DKL_PLL_BIAS_FBDIV_FRAC_MASK);
hw_state->mg_pll_tdc_coldst_bias =
- intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+ intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2);
hw_state->mg_pll_tdc_coldst_bias &= (DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
@@ -3737,61 +3735,58 @@ static void dkl_pll_write(struct drm_i915_private *dev_priv,
* All registers programmed here have the same HIP_INDEX_REG even
* though on different building block
*/
- intel_de_write(dev_priv, HIP_INDEX_REG(tc_port),
- HIP_INDEX_VAL(tc_port, 0x2));
-
/* All the registers are RMW */
- val = intel_de_read(dev_priv, DKL_REFCLKIN_CTL(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2);
val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
val |= hw_state->mg_refclkin_ctl;
- intel_de_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_REFCLKIN_CTL(tc_port), 2, val);
- val = intel_de_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2);
val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
val |= hw_state->mg_clktop2_coreclkctl1;
- intel_de_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_CORECLKCTL1(tc_port), 2, val);
- val = intel_de_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2);
val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
val |= hw_state->mg_clktop2_hsclkctl;
- intel_de_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_CLKTOP2_HSCLKCTL(tc_port), 2, val);
val = DKL_PLL_DIV0_MASK;
if (dev_priv->display.vbt.override_afc_startup)
val |= DKL_PLL_DIV0_AFC_STARTUP_MASK;
- intel_de_rmw(dev_priv, DKL_PLL_DIV0(tc_port), val,
- hw_state->mg_pll_div0);
+ intel_dkl_phy_rmw(dev_priv, DKL_PLL_DIV0(tc_port), 2, val,
+ hw_state->mg_pll_div0);
- val = intel_de_read(dev_priv, DKL_PLL_DIV1(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_PLL_DIV1(tc_port), 2);
val &= ~(DKL_PLL_DIV1_IREF_TRIM_MASK |
DKL_PLL_DIV1_TDC_TARGET_CNT_MASK);
val |= hw_state->mg_pll_div1;
- intel_de_write(dev_priv, DKL_PLL_DIV1(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_PLL_DIV1(tc_port), 2, val);
- val = intel_de_read(dev_priv, DKL_PLL_SSC(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_PLL_SSC(tc_port), 2);
val &= ~(DKL_PLL_SSC_IREF_NDIV_RATIO_MASK |
DKL_PLL_SSC_STEP_LEN_MASK |
DKL_PLL_SSC_STEP_NUM_MASK |
DKL_PLL_SSC_EN);
val |= hw_state->mg_pll_ssc;
- intel_de_write(dev_priv, DKL_PLL_SSC(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_PLL_SSC(tc_port), 2, val);
- val = intel_de_read(dev_priv, DKL_PLL_BIAS(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_PLL_BIAS(tc_port), 2);
val &= ~(DKL_PLL_BIAS_FRAC_EN_H |
DKL_PLL_BIAS_FBDIV_FRAC_MASK);
val |= hw_state->mg_pll_bias;
- intel_de_write(dev_priv, DKL_PLL_BIAS(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_PLL_BIAS(tc_port), 2, val);
- val = intel_de_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+ val = intel_dkl_phy_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2);
val &= ~(DKL_PLL_TDC_SSC_STEP_SIZE_MASK |
DKL_PLL_TDC_FEED_FWD_GAIN_MASK);
val |= hw_state->mg_pll_tdc_coldst_bias;
- intel_de_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), val);
+ intel_dkl_phy_write(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2, val);
- intel_de_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port));
+ intel_dkl_phy_posting_read(dev_priv, DKL_PLL_TDC_COLDST_BIAS(tc_port), 2);
}
static void icl_pll_power_enable(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 9aa38e8141b5..e5352239b2a2 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -972,8 +972,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
/* Try EDID first */
intel_panel_add_edid_fixed_modes(intel_connector,
- intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE,
- false);
+ intel_connector->panel.vbt.drrs_type != DRRS_TYPE_NONE);
/* Failed to get EDID, what about VBT? */
if (!intel_panel_preferred_fixed_mode(intel_connector))
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index a3a3f9fe4342..41cec9dc4223 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -254,10 +254,10 @@ static void intel_panel_destroy_probed_modes(struct intel_connector *connector)
}
void intel_panel_add_edid_fixed_modes(struct intel_connector *connector,
- bool has_drrs, bool has_vrr)
+ bool use_alt_fixed_modes)
{
intel_panel_add_edid_preferred_mode(connector);
- if (intel_panel_preferred_fixed_mode(connector) && (has_drrs || has_vrr))
+ if (intel_panel_preferred_fixed_mode(connector) && use_alt_fixed_modes)
intel_panel_add_edid_alt_fixed_modes(connector);
intel_panel_destroy_probed_modes(connector);
}
diff --git a/drivers/gpu/drm/i915/display/intel_panel.h b/drivers/gpu/drm/i915/display/intel_panel.h
index eff3ffd3d082..5c5b5b7f95b6 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.h
+++ b/drivers/gpu/drm/i915/display/intel_panel.h
@@ -44,7 +44,7 @@ int intel_panel_fitting(struct intel_crtc_state *crtc_state,
int intel_panel_compute_config(struct intel_connector *connector,
struct drm_display_mode *adjusted_mode);
void intel_panel_add_edid_fixed_modes(struct intel_connector *connector,
- bool has_drrs, bool has_vrr);
+ bool use_alt_fixed_modes);
void intel_panel_add_vbt_lfp_fixed_mode(struct intel_connector *connector);
void intel_panel_add_vbt_sdvo_fixed_mode(struct intel_connector *connector);
void intel_panel_add_encoder_fixed_mode(struct intel_connector *connector,
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index f5b744bef18f..774c1dc31a52 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -2747,13 +2747,10 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
if (!intel_sdvo_connector)
return false;
- if (device == 0) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS0;
+ if (device == 0)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS0;
- } else if (device == 1) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_TMDS1;
+ else if (device == 1)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_TMDS1;
- }
intel_connector = &intel_sdvo_connector->base;
connector = &intel_connector->base;
@@ -2808,7 +2805,6 @@ intel_sdvo_tv_init(struct intel_sdvo *intel_sdvo, int type)
encoder->encoder_type = DRM_MODE_ENCODER_TVDAC;
connector->connector_type = DRM_MODE_CONNECTOR_SVIDEO;
- intel_sdvo->controlled_output |= type;
intel_sdvo_connector->output_flag = type;
if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
@@ -2849,13 +2845,10 @@ intel_sdvo_analog_init(struct intel_sdvo *intel_sdvo, int device)
encoder->encoder_type = DRM_MODE_ENCODER_DAC;
connector->connector_type = DRM_MODE_CONNECTOR_VGA;
- if (device == 0) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB0;
+ if (device == 0)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB0;
- } else if (device == 1) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_RGB1;
+ else if (device == 1)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_RGB1;
- }
if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
kfree(intel_sdvo_connector);
@@ -2885,13 +2878,10 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
encoder->encoder_type = DRM_MODE_ENCODER_LVDS;
connector->connector_type = DRM_MODE_CONNECTOR_LVDS;
- if (device == 0) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS0;
+ if (device == 0)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS0;
- } else if (device == 1) {
- intel_sdvo->controlled_output |= SDVO_OUTPUT_LVDS1;
+ else if (device == 1)
intel_sdvo_connector->output_flag = SDVO_OUTPUT_LVDS1;
- }
if (intel_sdvo_connector_init(intel_sdvo_connector, intel_sdvo) < 0) {
kfree(intel_sdvo_connector);
@@ -2910,8 +2900,12 @@ intel_sdvo_lvds_init(struct intel_sdvo *intel_sdvo, int device)
intel_panel_add_vbt_sdvo_fixed_mode(intel_connector);
if (!intel_panel_preferred_fixed_mode(intel_connector)) {
+ mutex_lock(&i915->drm.mode_config.mutex);
+
intel_ddc_get_modes(connector, &intel_sdvo->ddc);
- intel_panel_add_edid_fixed_modes(intel_connector, false, false);
+ intel_panel_add_edid_fixed_modes(intel_connector, false);
+
+ mutex_unlock(&i915->drm.mode_config.mutex);
}
intel_panel_init(intel_connector);
@@ -2926,16 +2920,39 @@ err:
return false;
}
+static u16 intel_sdvo_filter_output_flags(u16 flags)
+{
+ flags &= SDVO_OUTPUT_MASK;
+
+ /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/
+ if (!(flags & SDVO_OUTPUT_TMDS0))
+ flags &= ~SDVO_OUTPUT_TMDS1;
+
+ if (!(flags & SDVO_OUTPUT_RGB0))
+ flags &= ~SDVO_OUTPUT_RGB1;
+
+ if (!(flags & SDVO_OUTPUT_LVDS0))
+ flags &= ~SDVO_OUTPUT_LVDS1;
+
+ return flags;
+}
+
static bool
intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
{
- /* SDVO requires XXX1 function may not exist unless it has XXX0 function.*/
+ struct drm_i915_private *i915 = to_i915(intel_sdvo->base.base.dev);
+
+ flags = intel_sdvo_filter_output_flags(flags);
+
+ intel_sdvo->controlled_output = flags;
+
+ intel_sdvo_select_ddc_bus(i915, intel_sdvo);
if (flags & SDVO_OUTPUT_TMDS0)
if (!intel_sdvo_dvi_init(intel_sdvo, 0))
return false;
- if ((flags & SDVO_TMDS_MASK) == SDVO_TMDS_MASK)
+ if (flags & SDVO_OUTPUT_TMDS1)
if (!intel_sdvo_dvi_init(intel_sdvo, 1))
return false;
@@ -2956,7 +2973,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
if (!intel_sdvo_analog_init(intel_sdvo, 0))
return false;
- if ((flags & SDVO_RGB_MASK) == SDVO_RGB_MASK)
+ if (flags & SDVO_OUTPUT_RGB1)
if (!intel_sdvo_analog_init(intel_sdvo, 1))
return false;
@@ -2964,14 +2981,13 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
if (!intel_sdvo_lvds_init(intel_sdvo, 0))
return false;
- if ((flags & SDVO_LVDS_MASK) == SDVO_LVDS_MASK)
+ if (flags & SDVO_OUTPUT_LVDS1)
if (!intel_sdvo_lvds_init(intel_sdvo, 1))
return false;
- if ((flags & SDVO_OUTPUT_MASK) == 0) {
+ if (flags == 0) {
unsigned char bytes[2];
- intel_sdvo->controlled_output = 0;
memcpy(bytes, &intel_sdvo->caps.output_flags, 2);
DRM_DEBUG_KMS("%s: Unknown SDVO output type (0x%02x%02x)\n",
SDVO_NAME(intel_sdvo),
@@ -3383,8 +3399,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
*/
intel_sdvo->base.cloneable = 0;
- intel_sdvo_select_ddc_bus(dev_priv, intel_sdvo);
-
/* Set the input timing to the screen. Assume always input 0. */
if (!intel_sdvo_set_target_input(intel_sdvo))
goto err_output;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index c698f95af15f..629acb403a2c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -6,7 +6,6 @@
#include <linux/scatterlist.h>
#include <linux/slab.h>
-#include <linux/swiotlb.h>
#include "i915_drv.h"
#include "i915_gem.h"
@@ -38,22 +37,12 @@ static int i915_gem_object_get_pages_internal(struct drm_i915_gem_object *obj)
struct scatterlist *sg;
unsigned int sg_page_sizes;
unsigned int npages;
- int max_order;
+ int max_order = MAX_ORDER;
+ unsigned int max_segment;
gfp_t gfp;
- max_order = MAX_ORDER;
-#ifdef CONFIG_SWIOTLB
- if (is_swiotlb_active(obj->base.dev->dev)) {
- unsigned int max_segment;
-
- max_segment = swiotlb_max_segment();
- if (max_segment) {
- max_segment = max_t(unsigned int, max_segment,
- PAGE_SIZE) >> PAGE_SHIFT;
- max_order = min(max_order, ilog2(max_segment));
- }
- }
-#endif
+ max_segment = i915_sg_segment_size(i915->drm.dev) >> PAGE_SHIFT;
+ max_order = min(max_order, get_order(max_segment));
gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_RECLAIMABLE;
if (IS_I965GM(i915) || IS_I965G(i915)) {
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index f42ca1179f37..11125c32dd35 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -194,7 +194,7 @@ static int shmem_get_pages(struct drm_i915_gem_object *obj)
struct intel_memory_region *mem = obj->mm.region;
struct address_space *mapping = obj->base.filp->f_mapping;
const unsigned long page_count = obj->base.size / PAGE_SIZE;
- unsigned int max_segment = i915_sg_segment_size();
+ unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
struct sg_table *st;
struct sgt_iter sgt_iter;
struct page *page;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index 4f861782c3e8..a4aa9500fa17 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -189,7 +189,7 @@ static int i915_ttm_tt_shmem_populate(struct ttm_device *bdev,
struct drm_i915_private *i915 = container_of(bdev, typeof(*i915), bdev);
struct intel_memory_region *mr = i915->mm.regions[INTEL_MEMORY_SYSTEM];
struct i915_ttm_tt *i915_tt = container_of(ttm, typeof(*i915_tt), ttm);
- const unsigned int max_segment = i915_sg_segment_size();
+ const unsigned int max_segment = i915_sg_segment_size(i915->drm.dev);
const size_t size = (size_t)ttm->num_pages << PAGE_SHIFT;
struct file *filp = i915_tt->filp;
struct sgt_iter sgt_iter;
@@ -538,7 +538,7 @@ static struct i915_refct_sgt *i915_ttm_tt_get_st(struct ttm_tt *ttm)
ret = sg_alloc_table_from_pages_segment(st,
ttm->pages, ttm->num_pages,
0, (unsigned long)ttm->num_pages << PAGE_SHIFT,
- i915_sg_segment_size(), GFP_KERNEL);
+ i915_sg_segment_size(i915_tt->dev), GFP_KERNEL);
if (ret) {
st->sgl = NULL;
return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index d4398948f016..f34e01a7fefb 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -129,7 +129,7 @@ static void i915_gem_object_userptr_drop_ref(struct drm_i915_gem_object *obj)
static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
{
const unsigned long num_pages = obj->base.size >> PAGE_SHIFT;
- unsigned int max_segment = i915_sg_segment_size();
+ unsigned int max_segment = i915_sg_segment_size(obj->base.dev->dev);
struct sg_table *st;
unsigned int sg_page_sizes;
struct page **pvec;
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index 6d2003d598e6..a821e3d405db 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -2293,11 +2293,11 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
}
if (IS_DG1_GRAPHICS_STEP(i915, STEP_A0, STEP_B0) ||
- IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915)) {
+ IS_ROCKETLAKE(i915) || IS_TIGERLAKE(i915) || IS_ALDERLAKE_P(i915)) {
/*
* Wa_1607030317:tgl
* Wa_1607186500:tgl
- * Wa_1607297627:tgl,rkl,dg1[a0]
+ * Wa_1607297627:tgl,rkl,dg1[a0],adlp
*
* On TGL and RKL there are multiple entries for this WA in the
* BSpec; some indicate this is an A0-only WA, others indicate
diff --git a/drivers/gpu/drm/i915/i915_driver.c b/drivers/gpu/drm/i915/i915_driver.c
index c459eb362c47..f2a15d8155f4 100644
--- a/drivers/gpu/drm/i915/i915_driver.c
+++ b/drivers/gpu/drm/i915/i915_driver.c
@@ -353,6 +353,7 @@ static int i915_driver_early_probe(struct drm_i915_private *dev_priv)
mutex_init(&dev_priv->display.wm.wm_mutex);
mutex_init(&dev_priv->display.pps.mutex);
mutex_init(&dev_priv->display.hdcp.comp_mutex);
+ spin_lock_init(&dev_priv->display.dkl.phy_lock);
i915_memcpy_init_early(dev_priv);
intel_runtime_pm_init_early(&dev_priv->runtime_pm);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0b287a59dc2f..da35bb2db26b 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7420,6 +7420,9 @@ enum skl_power_gate {
#define _DKL_PHY5_BASE 0x16C000
#define _DKL_PHY6_BASE 0x16D000
+#define DKL_REG_TC_PORT(__reg) \
+ (TC_PORT_1 + ((__reg).reg - _DKL_PHY1_BASE) / (_DKL_PHY2_BASE - _DKL_PHY1_BASE))
+
/* DEKEL PHY MMIO Address = Phy base + (internal address & ~index_mask) */
#define _DKL_PCS_DW5 0x14
#define DKL_PCS_DW5(tc_port) _MMIO(_PORT(tc_port, _DKL_PHY1_BASE, \
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.h b/drivers/gpu/drm/i915/i915_scatterlist.h
index 9ddb3e743a3e..b0a1db44f895 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.h
+++ b/drivers/gpu/drm/i915/i915_scatterlist.h
@@ -9,7 +9,8 @@
#include <linux/pfn.h>
#include <linux/scatterlist.h>
-#include <linux/swiotlb.h>
+#include <linux/dma-mapping.h>
+#include <xen/xen.h>
#include "i915_gem.h"
@@ -127,19 +128,26 @@ static inline unsigned int i915_sg_dma_sizes(struct scatterlist *sg)
return page_sizes;
}
-static inline unsigned int i915_sg_segment_size(void)
+static inline unsigned int i915_sg_segment_size(struct device *dev)
{
- unsigned int size = swiotlb_max_segment();
-
- if (size == 0)
- size = UINT_MAX;
-
- size = rounddown(size, PAGE_SIZE);
- /* swiotlb_max_segment_size can return 1 byte when it means one page. */
- if (size < PAGE_SIZE)
- size = PAGE_SIZE;
-
- return size;
+ size_t max = min_t(size_t, UINT_MAX, dma_max_mapping_size(dev));
+
+ /*
+ * For Xen PV guests pages aren't contiguous in DMA (machine) address
+ * space. The DMA API takes care of that both in dma_alloc_* (by
+ * calling into the hypervisor to make the pages contiguous) and in
+ * dma_map_* (by bounce buffering). But i915 abuses ignores the
+ * coherency aspects of the DMA API and thus can't cope with bounce
+ * buffering actually happening, so add a hack here to force small
+ * allocations and mappings when running in PV mode on Xen.
+ *
+ * Note this will still break if bounce buffering is required for other
+ * reasons, like confidential computing hypervisors or PCIe root ports
+ * with addressing limitations.
+ */
+ if (xen_pv_domain())
+ max = PAGE_SIZE;
+ return round_down(max, PAGE_SIZE);
}
bool i915_sg_trim(struct sg_table *orig_st);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 6ed5786bcd29..744cca507946 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -591,8 +591,15 @@ void intel_runtime_pm_enable(struct intel_runtime_pm *rpm)
pm_runtime_use_autosuspend(kdev);
}
- /* Enable by default */
- pm_runtime_allow(kdev);
+ /*
+ * FIXME: Temp hammer to keep autosupend disable on lmem supported platforms.
+ * As per PCIe specs 5.3.1.4.1, all iomem read write request over a PCIe
+ * function will be unsupported in case PCIe endpoint function is in D3.
+ * Let's keep i915 autosuspend control 'on' till we fix all known issue
+ * with lmem access in D3.
+ */
+ if (!IS_DGFX(i915))
+ pm_runtime_allow(kdev);
/*
* The core calls the driver load handler with an RPM reference held.
diff --git a/drivers/gpu/drm/imx/Kconfig b/drivers/gpu/drm/imx/Kconfig
index 975de4ff7313..fd5b2471fdf0 100644
--- a/drivers/gpu/drm/imx/Kconfig
+++ b/drivers/gpu/drm/imx/Kconfig
@@ -4,7 +4,6 @@ config DRM_IMX
select DRM_KMS_HELPER
select VIDEOMODE_HELPERS
select DRM_GEM_DMA_HELPER
- select DRM_KMS_HELPER
depends on DRM && (ARCH_MXC || ARCH_MULTIPLATFORM || COMPILE_TEST)
depends on IMX_IPUV3_CORE
help
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 6b34fac3f73a..ab4d1c878fda 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -218,8 +218,9 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector)
return ret;
}
-static int imx_tve_connector_mode_valid(struct drm_connector *connector,
- struct drm_display_mode *mode)
+static enum drm_mode_status
+imx_tve_connector_mode_valid(struct drm_connector *connector,
+ struct drm_display_mode *mode)
{
struct imx_tve *tve = con_to_tve(connector);
unsigned long rate;
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 4e0cbd682725..3c9dfdb0b328 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -155,7 +155,7 @@ config DRM_MSM_HDMI
Compile in support for the HDMI output MSM DRM driver. It can
be a primary or a secondary display on device. Note that this is used
only for the direct HDMI output. If the device outputs HDMI data
- throught some kind of DSI-to-HDMI bridge, this option can be disabled.
+ through some kind of DSI-to-HDMI bridge, this option can be disabled.
config DRM_MSM_HDMI_HDCP
bool "Enable HDMI HDCP support in MSM DRM driver"
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index 55f443328d8e..a5c3d1ed255a 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -91,7 +91,7 @@ struct a6xx_state_memobj {
static void *state_kcalloc(struct a6xx_gpu_state *a6xx_state, int nr, size_t objsize)
{
struct a6xx_state_memobj *obj =
- kzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL);
+ kvzalloc((nr * objsize) + sizeof(*obj), GFP_KERNEL);
if (!obj)
return NULL;
@@ -813,6 +813,9 @@ static struct msm_gpu_state_bo *a6xx_snapshot_gmu_bo(
{
struct msm_gpu_state_bo *snapshot;
+ if (!bo->size)
+ return NULL;
+
snapshot = state_kcalloc(a6xx_state, 1, sizeof(*snapshot));
if (!snapshot)
return NULL;
@@ -1040,8 +1043,13 @@ static void a6xx_gpu_state_destroy(struct kref *kref)
if (a6xx_state->gmu_hfi)
kvfree(a6xx_state->gmu_hfi->data);
- list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node)
- kfree(obj);
+ if (a6xx_state->gmu_debug)
+ kvfree(a6xx_state->gmu_debug->data);
+
+ list_for_each_entry_safe(obj, tmp, &a6xx_state->objs, node) {
+ list_del(&obj->node);
+ kvfree(obj);
+ }
adreno_gpu_state_destroy(state);
kfree(a6xx_state);
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 24b489b6129a..628806423f7d 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -679,6 +679,9 @@ static int adreno_system_suspend(struct device *dev)
struct msm_gpu *gpu = dev_to_gpu(dev);
int remaining, ret;
+ if (!gpu)
+ return 0;
+
suspend_scheduler(gpu);
remaining = wait_event_timeout(gpu->retire_event,
@@ -700,7 +703,12 @@ out:
static int adreno_system_resume(struct device *dev)
{
- resume_scheduler(dev_to_gpu(dev));
+ struct msm_gpu *gpu = dev_to_gpu(dev);
+
+ if (!gpu)
+ return 0;
+
+ resume_scheduler(gpu);
return pm_runtime_force_resume(dev);
}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 382fb7f9e497..5a0e8491cd3a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -729,7 +729,12 @@ static char *adreno_gpu_ascii85_encode(u32 *src, size_t len)
return buf;
}
-/* len is expected to be in bytes */
+/* len is expected to be in bytes
+ *
+ * WARNING: *ptr should be allocated with kvmalloc or friends. It can be free'd
+ * with kvfree() and replaced with a newly kvmalloc'd buffer on the first call
+ * when the unencoded raw data is encoded
+ */
void adreno_show_object(struct drm_printer *p, void **ptr, int len,
bool *encoded)
{
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index 7288041dd86a..7444b75c4215 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -56,8 +56,9 @@ static int mdp4_lvds_connector_get_modes(struct drm_connector *connector)
return ret;
}
-static int mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
- struct drm_display_mode *mode)
+static enum drm_mode_status
+mdp4_lvds_connector_mode_valid(struct drm_connector *connector,
+ struct drm_display_mode *mode)
{
struct mdp4_lvds_connector *mdp4_lvds_connector =
to_mdp4_lvds_connector(connector);
diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
index 3854c9f1f7e9..dd26ca651a05 100644
--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
+++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
@@ -1243,8 +1243,7 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
{
int ret = 0;
const u8 *dpcd = ctrl->panel->dpcd;
- u8 encoding = DP_SET_ANSI_8B10B;
- u8 ssc;
+ u8 encoding[] = { 0, DP_SET_ANSI_8B10B };
u8 assr;
struct dp_link_info link_info = {0};
@@ -1256,13 +1255,11 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
dp_aux_link_configure(ctrl->aux, &link_info);
- if (drm_dp_max_downspread(dpcd)) {
- ssc = DP_SPREAD_AMP_0_5;
- drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, &ssc, 1);
- }
+ if (drm_dp_max_downspread(dpcd))
+ encoding[0] |= DP_SPREAD_AMP_0_5;
- drm_dp_dpcd_write(ctrl->aux, DP_MAIN_LINK_CHANNEL_CODING_SET,
- &encoding, 1);
+ /* config DOWNSPREAD_CTRL and MAIN_LINK_CHANNEL_CODING_SET */
+ drm_dp_dpcd_write(ctrl->aux, DP_DOWNSPREAD_CTRL, encoding, 2);
if (drm_dp_alternate_scrambler_reset_cap(dpcd)) {
assr = DP_ALTERNATE_SCRAMBLER_RESET_ENABLE;
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index bfd0aeff3f0d..a49f6dbbe888 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -1249,7 +1249,7 @@ int dp_display_request_irq(struct msm_dp *dp_display)
return -EINVAL;
}
- rc = devm_request_irq(&dp->pdev->dev, dp->irq,
+ rc = devm_request_irq(dp_display->drm_dev->dev, dp->irq,
dp_display_irq_handler,
IRQF_TRIGGER_HIGH, "dp_display_isr", dp);
if (rc < 0) {
@@ -1528,6 +1528,11 @@ void msm_dp_debugfs_init(struct msm_dp *dp_display, struct drm_minor *minor)
}
}
+static void of_dp_aux_depopulate_bus_void(void *data)
+{
+ of_dp_aux_depopulate_bus(data);
+}
+
static int dp_display_get_next_bridge(struct msm_dp *dp)
{
int rc;
@@ -1552,10 +1557,16 @@ static int dp_display_get_next_bridge(struct msm_dp *dp)
* panel driver is probed asynchronously but is the best we
* can do without a bigger driver reorganization.
*/
- rc = devm_of_dp_aux_populate_ep_devices(dp_priv->aux);
+ rc = of_dp_aux_populate_bus(dp_priv->aux, NULL);
of_node_put(aux_bus);
if (rc)
goto error;
+
+ rc = devm_add_action_or_reset(dp->drm_dev->dev,
+ of_dp_aux_depopulate_bus_void,
+ dp_priv->aux);
+ if (rc)
+ goto error;
} else if (dp->is_edp) {
DRM_ERROR("eDP aux_bus not found\n");
return -ENODEV;
@@ -1568,7 +1579,7 @@ static int dp_display_get_next_bridge(struct msm_dp *dp)
* For DisplayPort interfaces external bridges are optional, so
* silently ignore an error if one is not present (-ENODEV).
*/
- rc = dp_parser_find_next_bridge(dp_priv->parser);
+ rc = devm_dp_parser_find_next_bridge(dp->drm_dev->dev, dp_priv->parser);
if (!dp->is_edp && rc == -ENODEV)
return 0;
@@ -1597,6 +1608,12 @@ int msm_dp_modeset_init(struct msm_dp *dp_display, struct drm_device *dev,
return -EINVAL;
priv = dev->dev_private;
+
+ if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+ DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+ return -ENOSPC;
+ }
+
dp_display->drm_dev = dev;
dp_priv = container_of(dp_display, struct dp_display_private, dp_display);
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index 6df25f7662e7..6db82f9b03af 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -31,6 +31,36 @@ static enum drm_connector_status dp_bridge_detect(struct drm_bridge *bridge)
connector_status_disconnected;
}
+static int dp_bridge_atomic_check(struct drm_bridge *bridge,
+ struct drm_bridge_state *bridge_state,
+ struct drm_crtc_state *crtc_state,
+ struct drm_connector_state *conn_state)
+{
+ struct msm_dp *dp;
+
+ dp = to_dp_bridge(bridge)->dp_display;
+
+ drm_dbg_dp(dp->drm_dev, "is_connected = %s\n",
+ (dp->is_connected) ? "true" : "false");
+
+ /*
+ * There is no protection in the DRM framework to check if the display
+ * pipeline has been already disabled before trying to disable it again.
+ * Hence if the sink is unplugged, the pipeline gets disabled, but the
+ * crtc->active is still true. Any attempt to set the mode or manually
+ * disable this encoder will result in the crash.
+ *
+ * TODO: add support for telling the DRM subsystem that the pipeline is
+ * disabled by the hardware and thus all access to it should be forbidden.
+ * After that this piece of code can be removed.
+ */
+ if (bridge->ops & DRM_BRIDGE_OP_HPD)
+ return (dp->is_connected) ? 0 : -ENOTCONN;
+
+ return 0;
+}
+
+
/**
* dp_bridge_get_modes - callback to add drm modes via drm_mode_probed_add()
* @bridge: Poiner to drm bridge
@@ -61,6 +91,9 @@ static int dp_bridge_get_modes(struct drm_bridge *bridge, struct drm_connector *
}
static const struct drm_bridge_funcs dp_bridge_ops = {
+ .atomic_duplicate_state = drm_atomic_helper_bridge_duplicate_state,
+ .atomic_destroy_state = drm_atomic_helper_bridge_destroy_state,
+ .atomic_reset = drm_atomic_helper_bridge_reset,
.enable = dp_bridge_enable,
.disable = dp_bridge_disable,
.post_disable = dp_bridge_post_disable,
@@ -68,6 +101,7 @@ static const struct drm_bridge_funcs dp_bridge_ops = {
.mode_valid = dp_bridge_mode_valid,
.get_modes = dp_bridge_get_modes,
.detect = dp_bridge_detect,
+ .atomic_check = dp_bridge_atomic_check,
};
struct drm_bridge *dp_bridge_init(struct msm_dp *dp_display, struct drm_device *dev,
diff --git a/drivers/gpu/drm/msm/dp/dp_parser.c b/drivers/gpu/drm/msm/dp/dp_parser.c
index dd732215d55b..dcbe893d66d7 100644
--- a/drivers/gpu/drm/msm/dp/dp_parser.c
+++ b/drivers/gpu/drm/msm/dp/dp_parser.c
@@ -240,12 +240,12 @@ static int dp_parser_clock(struct dp_parser *parser)
return 0;
}
-int dp_parser_find_next_bridge(struct dp_parser *parser)
+int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser)
{
- struct device *dev = &parser->pdev->dev;
+ struct platform_device *pdev = parser->pdev;
struct drm_bridge *bridge;
- bridge = devm_drm_of_get_bridge(dev, dev->of_node, 1, 0);
+ bridge = devm_drm_of_get_bridge(dev, pdev->dev.of_node, 1, 0);
if (IS_ERR(bridge))
return PTR_ERR(bridge);
diff --git a/drivers/gpu/drm/msm/dp/dp_parser.h b/drivers/gpu/drm/msm/dp/dp_parser.h
index 866c1a82bf1a..d30ab773db46 100644
--- a/drivers/gpu/drm/msm/dp/dp_parser.h
+++ b/drivers/gpu/drm/msm/dp/dp_parser.h
@@ -138,8 +138,9 @@ struct dp_parser {
struct dp_parser *dp_parser_get(struct platform_device *pdev);
/**
- * dp_parser_find_next_bridge() - find an additional bridge to DP
+ * devm_dp_parser_find_next_bridge() - find an additional bridge to DP
*
+ * @dev: device to tie bridge lifetime to
* @parser: dp_parser data from client
*
* This function is used to find any additional bridge attached to
@@ -147,6 +148,6 @@ struct dp_parser *dp_parser_get(struct platform_device *pdev);
*
* Return: 0 if able to get the bridge, otherwise negative errno for failure.
*/
-int dp_parser_find_next_bridge(struct dp_parser *parser);
+int devm_dp_parser_find_next_bridge(struct device *dev, struct dp_parser *parser);
#endif
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index 39bbabb5daf6..8a95c744972a 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -218,6 +218,12 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
return -EINVAL;
priv = dev->dev_private;
+
+ if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+ DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+ return -ENOSPC;
+ }
+
msm_dsi->dev = dev;
ret = msm_dsi_host_modeset_init(msm_dsi->host, dev);
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi.c b/drivers/gpu/drm/msm/hdmi/hdmi.c
index 93fe61b86967..f28fb21e3891 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi.c
@@ -300,6 +300,11 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
struct platform_device *pdev = hdmi->pdev;
int ret;
+ if (priv->num_bridges == ARRAY_SIZE(priv->bridges)) {
+ DRM_DEV_ERROR(dev->dev, "too many bridges\n");
+ return -ENOSPC;
+ }
+
hdmi->dev = dev;
hdmi->encoder = encoder;
@@ -339,7 +344,7 @@ int msm_hdmi_modeset_init(struct hdmi *hdmi,
goto fail;
}
- ret = devm_request_irq(&pdev->dev, hdmi->irq,
+ ret = devm_request_irq(dev->dev, hdmi->irq,
msm_hdmi_irq, IRQF_TRIGGER_HIGH,
"hdmi_isr", hdmi);
if (ret < 0) {
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 28034c21f6bc..105b5b48e828 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -247,6 +247,7 @@ static int msm_drm_uninit(struct device *dev)
for (i = 0; i < priv->num_bridges; i++)
drm_bridge_remove(priv->bridges[i]);
+ priv->num_bridges = 0;
pm_runtime_get_sync(dev);
msm_irq_uninstall(ddev);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 5599d93ec0d2..45a3e5cadc7d 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -501,11 +501,11 @@ out:
*/
static void submit_cleanup(struct msm_gem_submit *submit, bool error)
{
- unsigned cleanup_flags = BO_LOCKED | BO_OBJ_PINNED;
+ unsigned cleanup_flags = BO_LOCKED;
unsigned i;
if (error)
- cleanup_flags |= BO_VMA_PINNED;
+ cleanup_flags |= BO_VMA_PINNED | BO_OBJ_PINNED;
for (i = 0; i < submit->nr_bos; i++) {
struct msm_gem_object *msm_obj = submit->bos[i].obj;
@@ -706,7 +706,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
struct msm_drm_private *priv = dev->dev_private;
struct drm_msm_gem_submit *args = data;
struct msm_file_private *ctx = file->driver_priv;
- struct msm_gem_submit *submit = NULL;
+ struct msm_gem_submit *submit;
struct msm_gpu *gpu = priv->gpu;
struct msm_gpu_submitqueue *queue;
struct msm_ringbuffer *ring;
@@ -946,8 +946,7 @@ out_unlock:
put_unused_fd(out_fence_fd);
mutex_unlock(&queue->lock);
out_post_unlock:
- if (submit)
- msm_gem_submit_put(submit);
+ msm_gem_submit_put(submit);
if (!IS_ERR_OR_NULL(post_deps)) {
for (i = 0; i < args->nr_out_syncobjs; ++i) {
kfree(post_deps[i].chain);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 0098ee8438aa..021f4e29b613 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -997,4 +997,6 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
}
msm_devfreq_cleanup(gpu);
+
+ platform_set_drvdata(gpu->pdev, NULL);
}
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index ff911e7305ce..58a72e6b1400 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -280,6 +280,10 @@ struct msm_gpu {
static inline struct msm_gpu *dev_to_gpu(struct device *dev)
{
struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(dev);
+
+ if (!adreno_smmu)
+ return NULL;
+
return container_of(adreno_smmu, struct msm_gpu, adreno_smmu);
}
diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.c b/drivers/gpu/drm/msm/msm_ringbuffer.c
index cad4c3525f0b..57a8e9564540 100644
--- a/drivers/gpu/drm/msm/msm_ringbuffer.c
+++ b/drivers/gpu/drm/msm/msm_ringbuffer.c
@@ -25,7 +25,8 @@ static struct dma_fence *msm_job_run(struct drm_sched_job *job)
msm_gem_lock(obj);
msm_gem_unpin_vma_fenced(submit->bos[i].vma, fctx);
- submit->bos[i].flags &= ~BO_VMA_PINNED;
+ msm_gem_unpin_locked(obj);
+ submit->bos[i].flags &= ~(BO_VMA_PINNED | BO_OBJ_PINNED);
msm_gem_unlock(obj);
}
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
index bf6948125b84..f4df9820b295 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi-rockchip.c
@@ -752,7 +752,7 @@ static void dw_mipi_dsi_rockchip_config(struct dw_mipi_dsi_rockchip *dsi)
static void dw_mipi_dsi_rockchip_set_lcdsel(struct dw_mipi_dsi_rockchip *dsi,
int mux)
{
- if (dsi->cdata->lcdsel_grf_reg < 0)
+ if (dsi->cdata->lcdsel_grf_reg)
regmap_write(dsi->grf_regmap, dsi->cdata->lcdsel_grf_reg,
mux ? dsi->cdata->lcdsel_lit : dsi->cdata->lcdsel_big);
}
@@ -1051,23 +1051,31 @@ static int dw_mipi_dsi_rockchip_host_attach(void *priv_data,
if (ret) {
DRM_DEV_ERROR(dsi->dev, "Failed to register component: %d\n",
ret);
- return ret;
+ goto out;
}
second = dw_mipi_dsi_rockchip_find_second(dsi);
- if (IS_ERR(second))
- return PTR_ERR(second);
+ if (IS_ERR(second)) {
+ ret = PTR_ERR(second);
+ goto out;
+ }
if (second) {
ret = component_add(second, &dw_mipi_dsi_rockchip_ops);
if (ret) {
DRM_DEV_ERROR(second,
"Failed to register component: %d\n",
ret);
- return ret;
+ goto out;
}
}
return 0;
+
+out:
+ mutex_lock(&dsi->usage_mutex);
+ dsi->usage_mode = DW_DSI_USAGE_IDLE;
+ mutex_unlock(&dsi->usage_mutex);
+ return ret;
}
static int dw_mipi_dsi_rockchip_host_detach(void *priv_data,
@@ -1635,7 +1643,6 @@ static const struct rockchip_dw_dsi_chip_data rk3399_chip_data[] = {
static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = {
{
.reg = 0xfe060000,
- .lcdsel_grf_reg = -1,
.lanecfg1_grf_reg = RK3568_GRF_VO_CON2,
.lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI0_SKEWCALHS |
RK3568_DSI0_FORCETXSTOPMODE |
@@ -1645,7 +1652,6 @@ static const struct rockchip_dw_dsi_chip_data rk3568_chip_data[] = {
},
{
.reg = 0xfe070000,
- .lcdsel_grf_reg = -1,
.lanecfg1_grf_reg = RK3568_GRF_VO_CON3,
.lanecfg1 = HIWORD_UPDATE(0, RK3568_DSI1_SKEWCALHS |
RK3568_DSI1_FORCETXSTOPMODE |
@@ -1681,5 +1687,11 @@ struct platform_driver dw_mipi_dsi_rockchip_driver = {
.of_match_table = dw_mipi_dsi_rockchip_dt_ids,
.pm = &dw_mipi_dsi_rockchip_pm_ops,
.name = "dw-mipi-dsi-rockchip",
+ /*
+ * For dual-DSI display, one DSI pokes at the other DSI's
+ * drvdata in dw_mipi_dsi_rockchip_find_second(). This is not
+ * safe for asynchronous probe.
+ */
+ .probe_type = PROBE_FORCE_SYNCHRONOUS,
},
};
diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
index c14f88893868..2f4b8f64cbad 100644
--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
@@ -565,7 +565,8 @@ static int dw_hdmi_rockchip_bind(struct device *dev, struct device *master,
ret = rockchip_hdmi_parse_dt(hdmi);
if (ret) {
- DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n");
+ if (ret != -EPROBE_DEFER)
+ DRM_DEV_ERROR(hdmi->dev, "Unable to parse OF data\n");
return ret;
}
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index 614e97aaac80..da8a69953706 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -364,9 +364,12 @@ rockchip_gem_create_with_handle(struct drm_file *file_priv,
{
struct rockchip_gem_object *rk_obj;
struct drm_gem_object *obj;
+ bool is_framebuffer;
int ret;
- rk_obj = rockchip_gem_create_object(drm, size, false);
+ is_framebuffer = drm->fb_helper && file_priv == drm->fb_helper->client.file;
+
+ rk_obj = rockchip_gem_create_object(drm, size, is_framebuffer);
if (IS_ERR(rk_obj))
return ERR_CAST(rk_obj);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
index aac20be5ac08..105a548d0abe 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
@@ -877,10 +877,14 @@ static void vop2_crtc_atomic_disable(struct drm_crtc *crtc,
{
struct vop2_video_port *vp = to_vop2_video_port(crtc);
struct vop2 *vop2 = vp->vop2;
+ struct drm_crtc_state *old_crtc_state;
int ret;
vop2_lock(vop2);
+ old_crtc_state = drm_atomic_get_old_crtc_state(state, crtc);
+ drm_atomic_helper_disable_planes_on_crtc(old_crtc_state, false);
+
drm_crtc_vblank_off(crtc);
/*
@@ -996,13 +1000,15 @@ static int vop2_plane_atomic_check(struct drm_plane *plane,
static void vop2_plane_atomic_disable(struct drm_plane *plane,
struct drm_atomic_state *state)
{
- struct drm_plane_state *old_pstate = drm_atomic_get_old_plane_state(state, plane);
+ struct drm_plane_state *old_pstate = NULL;
struct vop2_win *win = to_vop2_win(plane);
struct vop2 *vop2 = win->vop2;
drm_dbg(vop2->drm, "%s disable\n", win->data->name);
- if (!old_pstate->crtc)
+ if (state)
+ old_pstate = drm_atomic_get_old_plane_state(state, plane);
+ if (old_pstate && !old_pstate->crtc)
return;
vop2_win_disable(win);
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 6137537aaea4..4b913dbb7d7b 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -207,6 +207,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
finish_cb);
+ dma_fence_put(f);
INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
schedule_work(&job->work);
}
@@ -234,8 +235,10 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
struct drm_sched_fence *s_fence = job->s_fence;
/* Wait for all dependencies to avoid data corruptions */
- while ((f = drm_sched_job_dependency(job, entity)))
+ while ((f = drm_sched_job_dependency(job, entity))) {
dma_fence_wait(f, false);
+ dma_fence_put(f);
+ }
drm_sched_fence_scheduled(s_fence);
dma_fence_set_error(&s_fence->finished, -ESRCH);
@@ -250,6 +253,7 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
continue;
}
+ dma_fence_get(entity->last_scheduled);
r = dma_fence_add_callback(entity->last_scheduled,
&job->finish_cb,
drm_sched_entity_kill_jobs_cb);
diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h
index 7daaf0caf4d3..10fb17879f8e 100644
--- a/drivers/hwmon/pmbus/pmbus.h
+++ b/drivers/hwmon/pmbus/pmbus.h
@@ -467,7 +467,6 @@ extern const struct regulator_ops pmbus_regulator_ops;
#define PMBUS_REGULATOR_STEP(_name, _id, _voltages, _step) \
[_id] = { \
.name = (_name # _id), \
- .supply_name = "vin", \
.id = (_id), \
.of_match = of_match_ptr(_name # _id), \
.regulators_node = of_match_ptr("regulators"), \
diff --git a/drivers/hwmon/scmi-hwmon.c b/drivers/hwmon/scmi-hwmon.c
index b1329a58ce40..e192f0c67146 100644
--- a/drivers/hwmon/scmi-hwmon.c
+++ b/drivers/hwmon/scmi-hwmon.c
@@ -20,6 +20,11 @@ struct scmi_sensors {
const struct scmi_sensor_info **info[hwmon_max];
};
+struct scmi_thermal_sensor {
+ const struct scmi_protocol_handle *ph;
+ const struct scmi_sensor_info *info;
+};
+
static inline u64 __pow10(u8 x)
{
u64 r = 1;
@@ -64,16 +69,14 @@ static int scmi_hwmon_scale(const struct scmi_sensor_info *sensor, u64 *value)
return 0;
}
-static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
- u32 attr, int channel, long *val)
+static int scmi_hwmon_read_scaled_value(const struct scmi_protocol_handle *ph,
+ const struct scmi_sensor_info *sensor,
+ long *val)
{
int ret;
u64 value;
- const struct scmi_sensor_info *sensor;
- struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev);
- sensor = *(scmi_sensors->info[type] + channel);
- ret = sensor_ops->reading_get(scmi_sensors->ph, sensor->id, &value);
+ ret = sensor_ops->reading_get(ph, sensor->id, &value);
if (ret)
return ret;
@@ -84,6 +87,17 @@ static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
return ret;
}
+static int scmi_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long *val)
+{
+ const struct scmi_sensor_info *sensor;
+ struct scmi_sensors *scmi_sensors = dev_get_drvdata(dev);
+
+ sensor = *(scmi_sensors->info[type] + channel);
+
+ return scmi_hwmon_read_scaled_value(scmi_sensors->ph, sensor, val);
+}
+
static int
scmi_hwmon_read_string(struct device *dev, enum hwmon_sensor_types type,
u32 attr, int channel, const char **str)
@@ -122,6 +136,25 @@ static struct hwmon_chip_info scmi_chip_info = {
.info = NULL,
};
+static int scmi_hwmon_thermal_get_temp(struct thermal_zone_device *tz,
+ int *temp)
+{
+ int ret;
+ long value;
+ struct scmi_thermal_sensor *th_sensor = tz->devdata;
+
+ ret = scmi_hwmon_read_scaled_value(th_sensor->ph, th_sensor->info,
+ &value);
+ if (!ret)
+ *temp = value;
+
+ return ret;
+}
+
+static const struct thermal_zone_device_ops scmi_hwmon_thermal_ops = {
+ .get_temp = scmi_hwmon_thermal_get_temp,
+};
+
static int scmi_hwmon_add_chan_info(struct hwmon_channel_info *scmi_hwmon_chan,
struct device *dev, int num,
enum hwmon_sensor_types type, u32 config)
@@ -149,7 +182,6 @@ static enum hwmon_sensor_types scmi_types[] = {
};
static u32 hwmon_attributes[hwmon_max] = {
- [hwmon_chip] = HWMON_C_REGISTER_TZ,
[hwmon_temp] = HWMON_T_INPUT | HWMON_T_LABEL,
[hwmon_in] = HWMON_I_INPUT | HWMON_I_LABEL,
[hwmon_curr] = HWMON_C_INPUT | HWMON_C_LABEL,
@@ -157,6 +189,43 @@ static u32 hwmon_attributes[hwmon_max] = {
[hwmon_energy] = HWMON_E_INPUT | HWMON_E_LABEL,
};
+static int scmi_thermal_sensor_register(struct device *dev,
+ const struct scmi_protocol_handle *ph,
+ const struct scmi_sensor_info *sensor)
+{
+ struct scmi_thermal_sensor *th_sensor;
+ struct thermal_zone_device *tzd;
+
+ th_sensor = devm_kzalloc(dev, sizeof(*th_sensor), GFP_KERNEL);
+ if (!th_sensor)
+ return -ENOMEM;
+
+ th_sensor->ph = ph;
+ th_sensor->info = sensor;
+
+ /*
+ * Try to register a temperature sensor with the Thermal Framework:
+ * skip sensors not defined as part of any thermal zone (-ENODEV) but
+ * report any other errors related to misconfigured zones/sensors.
+ */
+ tzd = devm_thermal_of_zone_register(dev, th_sensor->info->id, th_sensor,
+ &scmi_hwmon_thermal_ops);
+ if (IS_ERR(tzd)) {
+ devm_kfree(dev, th_sensor);
+
+ if (PTR_ERR(tzd) != -ENODEV)
+ return PTR_ERR(tzd);
+
+ dev_dbg(dev, "Sensor '%s' not attached to any thermal zone.\n",
+ sensor->name);
+ } else {
+ dev_dbg(dev, "Sensor '%s' attached to thermal zone ID:%d\n",
+ sensor->name, tzd->id);
+ }
+
+ return 0;
+}
+
static int scmi_hwmon_probe(struct scmi_device *sdev)
{
int i, idx;
@@ -164,7 +233,7 @@ static int scmi_hwmon_probe(struct scmi_device *sdev)
enum hwmon_sensor_types type;
struct scmi_sensors *scmi_sensors;
const struct scmi_sensor_info *sensor;
- int nr_count[hwmon_max] = {0}, nr_types = 0;
+ int nr_count[hwmon_max] = {0}, nr_types = 0, nr_count_temp = 0;
const struct hwmon_chip_info *chip_info;
struct device *hwdev, *dev = &sdev->dev;
struct hwmon_channel_info *scmi_hwmon_chan;
@@ -208,10 +277,8 @@ static int scmi_hwmon_probe(struct scmi_device *sdev)
}
}
- if (nr_count[hwmon_temp]) {
- nr_count[hwmon_chip]++;
- nr_types++;
- }
+ if (nr_count[hwmon_temp])
+ nr_count_temp = nr_count[hwmon_temp];
scmi_hwmon_chan = devm_kcalloc(dev, nr_types, sizeof(*scmi_hwmon_chan),
GFP_KERNEL);
@@ -262,8 +329,31 @@ static int scmi_hwmon_probe(struct scmi_device *sdev)
hwdev = devm_hwmon_device_register_with_info(dev, "scmi_sensors",
scmi_sensors, chip_info,
NULL);
+ if (IS_ERR(hwdev))
+ return PTR_ERR(hwdev);
- return PTR_ERR_OR_ZERO(hwdev);
+ for (i = 0; i < nr_count_temp; i++) {
+ int ret;
+
+ sensor = *(scmi_sensors->info[hwmon_temp] + i);
+ if (!sensor)
+ continue;
+
+ /*
+ * Warn on any misconfiguration related to thermal zones but
+ * bail out of probing only on memory errors.
+ */
+ ret = scmi_thermal_sensor_register(dev, ph, sensor);
+ if (ret) {
+ if (ret == -ENOMEM)
+ return ret;
+ dev_warn(dev,
+ "Thermal zone misconfigured for %s. err=%d\n",
+ sensor->name, ret);
+ }
+ }
+
+ return 0;
}
static const struct scmi_device_id scmi_id_table[] = {
diff --git a/drivers/hwtracing/coresight/coresight-core.c b/drivers/hwtracing/coresight/coresight-core.c
index d5dbc67bacb4..f3068175ca9d 100644
--- a/drivers/hwtracing/coresight/coresight-core.c
+++ b/drivers/hwtracing/coresight/coresight-core.c
@@ -1687,14 +1687,15 @@ struct coresight_device *coresight_register(struct coresight_desc *desc)
ret = coresight_fixup_device_conns(csdev);
if (!ret)
ret = coresight_fixup_orphan_conns(csdev);
- if (!ret && cti_assoc_ops && cti_assoc_ops->add)
- cti_assoc_ops->add(csdev);
out_unlock:
mutex_unlock(&coresight_mutex);
/* Success */
- if (!ret)
+ if (!ret) {
+ if (cti_assoc_ops && cti_assoc_ops->add)
+ cti_assoc_ops->add(csdev);
return csdev;
+ }
/* Unregister the device if needed */
if (registered) {
diff --git a/drivers/hwtracing/coresight/coresight-cti-core.c b/drivers/hwtracing/coresight/coresight-cti-core.c
index 8988b2ed2ea6..c6e8c6542f24 100644
--- a/drivers/hwtracing/coresight/coresight-cti-core.c
+++ b/drivers/hwtracing/coresight/coresight-cti-core.c
@@ -90,11 +90,9 @@ void cti_write_all_hw_regs(struct cti_drvdata *drvdata)
static int cti_enable_hw(struct cti_drvdata *drvdata)
{
struct cti_config *config = &drvdata->config;
- struct device *dev = &drvdata->csdev->dev;
unsigned long flags;
int rc = 0;
- pm_runtime_get_sync(dev->parent);
spin_lock_irqsave(&drvdata->spinlock, flags);
/* no need to do anything if enabled or unpowered*/
@@ -119,7 +117,6 @@ cti_state_unchanged:
/* cannot enable due to error */
cti_err_not_enabled:
spin_unlock_irqrestore(&drvdata->spinlock, flags);
- pm_runtime_put(dev->parent);
return rc;
}
@@ -153,7 +150,6 @@ cti_hp_not_enabled:
static int cti_disable_hw(struct cti_drvdata *drvdata)
{
struct cti_config *config = &drvdata->config;
- struct device *dev = &drvdata->csdev->dev;
struct coresight_device *csdev = drvdata->csdev;
spin_lock(&drvdata->spinlock);
@@ -175,7 +171,6 @@ static int cti_disable_hw(struct cti_drvdata *drvdata)
coresight_disclaim_device_unlocked(csdev);
CS_LOCK(drvdata->base);
spin_unlock(&drvdata->spinlock);
- pm_runtime_put(dev->parent);
return 0;
/* not disabled this call */
@@ -541,7 +536,7 @@ cti_match_fixup_csdev(struct cti_device *ctidev, const char *node_name,
/*
* Search the cti list to add an associated CTI into the supplied CS device
* This will set the association if CTI declared before the CS device.
- * (called from coresight_register() with coresight_mutex locked).
+ * (called from coresight_register() without coresight_mutex locked).
*/
static void cti_add_assoc_to_csdev(struct coresight_device *csdev)
{
@@ -569,7 +564,8 @@ static void cti_add_assoc_to_csdev(struct coresight_device *csdev)
* if we found a matching csdev then update the ECT
* association pointer for the device with this CTI.
*/
- csdev->ect_dev = ect_item->csdev;
+ coresight_set_assoc_ectdev_mutex(csdev->ect_dev,
+ ect_item->csdev);
break;
}
}
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index e06509edc5f3..1fda1eaa6d6a 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -1243,6 +1243,7 @@ static const struct {
*/
{ "Latitude 5480", 0x29 },
{ "Vostro V131", 0x1d },
+ { "Vostro 5568", 0x29 },
};
static void register_dell_lis3lv02d_i2c_device(struct i801_priv *priv)
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 39cb1b7bb865..809fbd014cd6 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -1080,6 +1080,7 @@ static int piix4_probe(struct pci_dev *dev, const struct pci_device_id *id)
"", &piix4_main_adapters[0]);
if (retval < 0)
return retval;
+ piix4_adapter_count = 1;
}
/* Check for auxiliary SMBus on some AMD chipsets */
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 954022c04cc4..3869c258a529 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -284,6 +284,7 @@ struct tegra_i2c_dev {
struct dma_chan *tx_dma_chan;
struct dma_chan *rx_dma_chan;
unsigned int dma_buf_size;
+ struct device *dma_dev;
dma_addr_t dma_phys;
void *dma_buf;
@@ -420,7 +421,7 @@ static int tegra_i2c_dma_submit(struct tegra_i2c_dev *i2c_dev, size_t len)
static void tegra_i2c_release_dma(struct tegra_i2c_dev *i2c_dev)
{
if (i2c_dev->dma_buf) {
- dma_free_coherent(i2c_dev->dev, i2c_dev->dma_buf_size,
+ dma_free_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size,
i2c_dev->dma_buf, i2c_dev->dma_phys);
i2c_dev->dma_buf = NULL;
}
@@ -472,10 +473,13 @@ static int tegra_i2c_init_dma(struct tegra_i2c_dev *i2c_dev)
i2c_dev->tx_dma_chan = chan;
+ WARN_ON(i2c_dev->tx_dma_chan->device != i2c_dev->rx_dma_chan->device);
+ i2c_dev->dma_dev = chan->device->dev;
+
i2c_dev->dma_buf_size = i2c_dev->hw->quirks->max_write_len +
I2C_PACKET_HEADER_SIZE;
- dma_buf = dma_alloc_coherent(i2c_dev->dev, i2c_dev->dma_buf_size,
+ dma_buf = dma_alloc_coherent(i2c_dev->dma_dev, i2c_dev->dma_buf_size,
&dma_phys, GFP_KERNEL | __GFP_NOWARN);
if (!dma_buf) {
dev_err(i2c_dev->dev, "failed to allocate DMA buffer\n");
@@ -1272,7 +1276,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
if (i2c_dev->dma_mode) {
if (i2c_dev->msg_read) {
- dma_sync_single_for_device(i2c_dev->dev,
+ dma_sync_single_for_device(i2c_dev->dma_dev,
i2c_dev->dma_phys,
xfer_size, DMA_FROM_DEVICE);
@@ -1280,7 +1284,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
if (err)
return err;
} else {
- dma_sync_single_for_cpu(i2c_dev->dev,
+ dma_sync_single_for_cpu(i2c_dev->dma_dev,
i2c_dev->dma_phys,
xfer_size, DMA_TO_DEVICE);
}
@@ -1293,7 +1297,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
memcpy(i2c_dev->dma_buf + I2C_PACKET_HEADER_SIZE,
msg->buf, msg->len);
- dma_sync_single_for_device(i2c_dev->dev,
+ dma_sync_single_for_device(i2c_dev->dma_dev,
i2c_dev->dma_phys,
xfer_size, DMA_TO_DEVICE);
@@ -1344,7 +1348,7 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
}
if (i2c_dev->msg_read && i2c_dev->msg_err == I2C_ERR_NONE) {
- dma_sync_single_for_cpu(i2c_dev->dev,
+ dma_sync_single_for_cpu(i2c_dev->dma_dev,
i2c_dev->dma_phys,
xfer_size, DMA_FROM_DEVICE);
diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c
index 47feb375b70b..7c7d78040793 100644
--- a/drivers/iio/accel/adxl367.c
+++ b/drivers/iio/accel/adxl367.c
@@ -1185,17 +1185,30 @@ static ssize_t adxl367_get_fifo_watermark(struct device *dev,
return sysfs_emit(buf, "%d\n", fifo_watermark);
}
-static IIO_CONST_ATTR(hwfifo_watermark_min, "1");
-static IIO_CONST_ATTR(hwfifo_watermark_max,
- __stringify(ADXL367_FIFO_MAX_WATERMARK));
+static ssize_t hwfifo_watermark_min_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", "1");
+}
+
+static ssize_t hwfifo_watermark_max_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", __stringify(ADXL367_FIFO_MAX_WATERMARK));
+}
+
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_min, 0);
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
static IIO_DEVICE_ATTR(hwfifo_watermark, 0444,
adxl367_get_fifo_watermark, NULL, 0);
static IIO_DEVICE_ATTR(hwfifo_enabled, 0444,
adxl367_get_fifo_enabled, NULL, 0);
static const struct attribute *adxl367_fifo_attributes[] = {
- &iio_const_attr_hwfifo_watermark_min.dev_attr.attr,
- &iio_const_attr_hwfifo_watermark_max.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_min.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
&iio_dev_attr_hwfifo_watermark.dev_attr.attr,
&iio_dev_attr_hwfifo_enabled.dev_attr.attr,
NULL,
diff --git a/drivers/iio/accel/adxl372.c b/drivers/iio/accel/adxl372.c
index e3ecbaee61f7..bc53af809d5d 100644
--- a/drivers/iio/accel/adxl372.c
+++ b/drivers/iio/accel/adxl372.c
@@ -998,17 +998,30 @@ static ssize_t adxl372_get_fifo_watermark(struct device *dev,
return sprintf(buf, "%d\n", st->watermark);
}
-static IIO_CONST_ATTR(hwfifo_watermark_min, "1");
-static IIO_CONST_ATTR(hwfifo_watermark_max,
- __stringify(ADXL372_FIFO_SIZE));
+static ssize_t hwfifo_watermark_min_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", "1");
+}
+
+static ssize_t hwfifo_watermark_max_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", __stringify(ADXL372_FIFO_SIZE));
+}
+
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_min, 0);
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
static IIO_DEVICE_ATTR(hwfifo_watermark, 0444,
adxl372_get_fifo_watermark, NULL, 0);
static IIO_DEVICE_ATTR(hwfifo_enabled, 0444,
adxl372_get_fifo_enabled, NULL, 0);
static const struct attribute *adxl372_fifo_attributes[] = {
- &iio_const_attr_hwfifo_watermark_min.dev_attr.attr,
- &iio_const_attr_hwfifo_watermark_max.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_min.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
&iio_dev_attr_hwfifo_watermark.dev_attr.attr,
&iio_dev_attr_hwfifo_enabled.dev_attr.attr,
NULL,
diff --git a/drivers/iio/accel/bmc150-accel-core.c b/drivers/iio/accel/bmc150-accel-core.c
index 57e8a8350cd1..92f8b139acce 100644
--- a/drivers/iio/accel/bmc150-accel-core.c
+++ b/drivers/iio/accel/bmc150-accel-core.c
@@ -925,17 +925,30 @@ static const struct iio_chan_spec_ext_info bmc150_accel_ext_info[] = {
{ }
};
-static IIO_CONST_ATTR(hwfifo_watermark_min, "1");
-static IIO_CONST_ATTR(hwfifo_watermark_max,
- __stringify(BMC150_ACCEL_FIFO_LENGTH));
+static ssize_t hwfifo_watermark_min_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", "1");
+}
+
+static ssize_t hwfifo_watermark_max_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", __stringify(BMC150_ACCEL_FIFO_LENGTH));
+}
+
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_min, 0);
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
static IIO_DEVICE_ATTR(hwfifo_enabled, S_IRUGO,
bmc150_accel_get_fifo_state, NULL, 0);
static IIO_DEVICE_ATTR(hwfifo_watermark, S_IRUGO,
bmc150_accel_get_fifo_watermark, NULL, 0);
static const struct attribute *bmc150_accel_fifo_attributes[] = {
- &iio_const_attr_hwfifo_watermark_min.dev_attr.attr,
- &iio_const_attr_hwfifo_watermark_max.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_min.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
&iio_dev_attr_hwfifo_watermark.dev_attr.attr,
&iio_dev_attr_hwfifo_enabled.dev_attr.attr,
NULL,
diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 4294d6539cdb..33e251552214 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -2193,17 +2193,30 @@ static ssize_t at91_adc_get_watermark(struct device *dev,
return scnprintf(buf, PAGE_SIZE, "%d\n", st->dma_st.watermark);
}
+static ssize_t hwfifo_watermark_min_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", "2");
+}
+
+static ssize_t hwfifo_watermark_max_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ return sysfs_emit(buf, "%s\n", AT91_HWFIFO_MAX_SIZE_STR);
+}
+
static IIO_DEVICE_ATTR(hwfifo_enabled, 0444,
at91_adc_get_fifo_state, NULL, 0);
static IIO_DEVICE_ATTR(hwfifo_watermark, 0444,
at91_adc_get_watermark, NULL, 0);
-
-static IIO_CONST_ATTR(hwfifo_watermark_min, "2");
-static IIO_CONST_ATTR(hwfifo_watermark_max, AT91_HWFIFO_MAX_SIZE_STR);
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_min, 0);
+static IIO_DEVICE_ATTR_RO(hwfifo_watermark_max, 0);
static const struct attribute *at91_adc_fifo_attributes[] = {
- &iio_const_attr_hwfifo_watermark_min.dev_attr.attr,
- &iio_const_attr_hwfifo_watermark_max.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_min.dev_attr.attr,
+ &iio_dev_attr_hwfifo_watermark_max.dev_attr.attr,
&iio_dev_attr_hwfifo_watermark.dev_attr.attr,
&iio_dev_attr_hwfifo_enabled.dev_attr.attr,
NULL,
diff --git a/drivers/iio/adc/mcp3911.c b/drivers/iio/adc/mcp3911.c
index b35fd2c9c3c0..76b334f5ac61 100644
--- a/drivers/iio/adc/mcp3911.c
+++ b/drivers/iio/adc/mcp3911.c
@@ -55,8 +55,9 @@
/* Internal voltage reference in mV */
#define MCP3911_INT_VREF_MV 1200
-#define MCP3911_REG_READ(reg, id) ((((reg) << 1) | ((id) << 5) | (1 << 0)) & 0xff)
-#define MCP3911_REG_WRITE(reg, id) ((((reg) << 1) | ((id) << 5) | (0 << 0)) & 0xff)
+#define MCP3911_REG_READ(reg, id) ((((reg) << 1) | ((id) << 6) | (1 << 0)) & 0xff)
+#define MCP3911_REG_WRITE(reg, id) ((((reg) << 1) | ((id) << 6) | (0 << 0)) & 0xff)
+#define MCP3911_REG_MASK GENMASK(4, 1)
#define MCP3911_NUM_CHANNELS 2
@@ -89,8 +90,8 @@ static int mcp3911_read(struct mcp3911 *adc, u8 reg, u32 *val, u8 len)
be32_to_cpus(val);
*val >>= ((4 - len) * 8);
- dev_dbg(&adc->spi->dev, "reading 0x%x from register 0x%x\n", *val,
- reg >> 1);
+ dev_dbg(&adc->spi->dev, "reading 0x%x from register 0x%lx\n", *val,
+ FIELD_GET(MCP3911_REG_MASK, reg));
return ret;
}
@@ -248,7 +249,7 @@ static int mcp3911_write_raw(struct iio_dev *indio_dev,
break;
case IIO_CHAN_INFO_OVERSAMPLING_RATIO:
- for (int i = 0; i < sizeof(mcp3911_osr_table); i++) {
+ for (int i = 0; i < ARRAY_SIZE(mcp3911_osr_table); i++) {
if (val == mcp3911_osr_table[i]) {
val = FIELD_PREP(MCP3911_CONFIG_OSR, i);
ret = mcp3911_update(adc, MCP3911_REG_CONFIG, MCP3911_CONFIG_OSR,
@@ -496,7 +497,7 @@ static int mcp3911_probe(struct spi_device *spi)
indio_dev->name,
iio_device_id(indio_dev));
if (!adc->trig)
- return PTR_ERR(adc->trig);
+ return -ENOMEM;
adc->trig->ops = &mcp3911_trigger_ops;
iio_trigger_set_drvdata(adc->trig, adc);
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 6256977eb7f7..3cda529f081d 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -2086,18 +2086,19 @@ static int stm32_adc_generic_chan_init(struct iio_dev *indio_dev,
stm32_adc_chan_init_one(indio_dev, &channels[scan_index], val,
vin[1], scan_index, differential);
+ val = 0;
ret = fwnode_property_read_u32(child, "st,min-sample-time-ns", &val);
/* st,min-sample-time-ns is optional */
- if (!ret) {
- stm32_adc_smpr_init(adc, channels[scan_index].channel, val);
- if (differential)
- stm32_adc_smpr_init(adc, vin[1], val);
- } else if (ret != -EINVAL) {
+ if (ret && ret != -EINVAL) {
dev_err(&indio_dev->dev, "Invalid st,min-sample-time-ns property %d\n",
ret);
goto err;
}
+ stm32_adc_smpr_init(adc, channels[scan_index].channel, val);
+ if (differential)
+ stm32_adc_smpr_init(adc, vin[1], val);
+
scan_index++;
}
diff --git a/drivers/iio/light/tsl2583.c b/drivers/iio/light/tsl2583.c
index 0a2ca1a8146d..7bcb5c718922 100644
--- a/drivers/iio/light/tsl2583.c
+++ b/drivers/iio/light/tsl2583.c
@@ -858,7 +858,7 @@ static int tsl2583_probe(struct i2c_client *clientp,
TSL2583_POWER_OFF_DELAY_MS);
pm_runtime_use_autosuspend(&clientp->dev);
- ret = devm_iio_device_register(indio_dev->dev.parent, indio_dev);
+ ret = iio_device_register(indio_dev);
if (ret) {
dev_err(&clientp->dev, "%s: iio registration failed\n",
__func__);
diff --git a/drivers/iio/temperature/ltc2983.c b/drivers/iio/temperature/ltc2983.c
index b652d2b39bcf..a60ccf183687 100644
--- a/drivers/iio/temperature/ltc2983.c
+++ b/drivers/iio/temperature/ltc2983.c
@@ -1385,13 +1385,6 @@ static int ltc2983_setup(struct ltc2983_data *st, bool assign_iio)
return ret;
}
- st->iio_chan = devm_kzalloc(&st->spi->dev,
- st->iio_channels * sizeof(*st->iio_chan),
- GFP_KERNEL);
-
- if (!st->iio_chan)
- return -ENOMEM;
-
ret = regmap_update_bits(st->regmap, LTC2983_GLOBAL_CONFIG_REG,
LTC2983_NOTCH_FREQ_MASK,
LTC2983_NOTCH_FREQ(st->filter_notch_freq));
@@ -1514,6 +1507,12 @@ static int ltc2983_probe(struct spi_device *spi)
gpiod_set_value_cansleep(gpio, 0);
}
+ st->iio_chan = devm_kzalloc(&spi->dev,
+ st->iio_channels * sizeof(*st->iio_chan),
+ GFP_KERNEL);
+ if (!st->iio_chan)
+ return -ENOMEM;
+
ret = ltc2983_setup(st, true);
if (ret)
return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index cc2222b85c88..26d1772179b8 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1556,7 +1556,7 @@ static bool validate_ipv4_net_dev(struct net_device *net_dev,
return false;
memset(&fl4, 0, sizeof(fl4));
- fl4.flowi4_iif = net_dev->ifindex;
+ fl4.flowi4_oif = net_dev->ifindex;
fl4.daddr = daddr;
fl4.saddr = saddr;
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index ae60c73babcc..b69e2c4e4d2a 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2815,10 +2815,18 @@ static int __init ib_core_init(void)
nldev_init();
rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
- roce_gid_mgmt_init();
+ ret = roce_gid_mgmt_init();
+ if (ret) {
+ pr_warn("Couldn't init RoCE GID management\n");
+ goto err_parent;
+ }
return 0;
+err_parent:
+ rdma_nl_unregister(RDMA_NL_LS);
+ nldev_exit();
+ unregister_pernet_device(&rdma_dev_net_ops);
err_compat:
unregister_blocking_lsm_notifier(&ibdev_lsm_nb);
err_sa:
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index b92358f606d0..12dc97067ed2 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -2537,7 +2537,7 @@ void __init nldev_init(void)
rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
}
-void __exit nldev_exit(void)
+void nldev_exit(void)
{
rdma_nl_unregister(RDMA_NL_NLDEV);
}
diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
index 94b94cca4870..15ee92081118 100644
--- a/drivers/infiniband/hw/efa/efa_main.c
+++ b/drivers/infiniband/hw/efa/efa_main.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
/*
- * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
*/
#include <linux/module.h>
@@ -14,10 +14,12 @@
#define PCI_DEV_ID_EFA0_VF 0xefa0
#define PCI_DEV_ID_EFA1_VF 0xefa1
+#define PCI_DEV_ID_EFA2_VF 0xefa2
static const struct pci_device_id efa_pci_tbl[] = {
{ PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA0_VF) },
{ PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA1_VF) },
+ { PCI_VDEVICE(AMAZON, PCI_DEV_ID_EFA2_VF) },
{ }
};
diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c
index 3d42bd2b36bd..51ae58c02b15 100644
--- a/drivers/infiniband/hw/hfi1/pio.c
+++ b/drivers/infiniband/hw/hfi1/pio.c
@@ -913,8 +913,7 @@ void sc_disable(struct send_context *sc)
spin_unlock(&sc->release_lock);
write_seqlock(&sc->waitlock);
- if (!list_empty(&sc->piowait))
- list_move(&sc->piowait, &wake_list);
+ list_splice_init(&sc->piowait, &wake_list);
write_sequnlock(&sc->waitlock);
while (!list_empty(&wake_list)) {
struct iowait *wait;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 1ead35fb031b..1435fe2ea176 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -118,7 +118,6 @@ static const u32 hns_roce_op_code[] = {
HR_OPC_MAP(ATOMIC_CMP_AND_SWP, ATOM_CMP_AND_SWAP),
HR_OPC_MAP(ATOMIC_FETCH_AND_ADD, ATOM_FETCH_AND_ADD),
HR_OPC_MAP(SEND_WITH_INV, SEND_WITH_INV),
- HR_OPC_MAP(LOCAL_INV, LOCAL_INV),
HR_OPC_MAP(MASKED_ATOMIC_CMP_AND_SWP, ATOM_MSK_CMP_AND_SWAP),
HR_OPC_MAP(MASKED_ATOMIC_FETCH_AND_ADD, ATOM_MSK_FETCH_AND_ADD),
HR_OPC_MAP(REG_MR, FAST_REG_PMR),
@@ -559,9 +558,6 @@ static int set_rc_opcode(struct hns_roce_dev *hr_dev,
else
ret = -EOPNOTSUPP;
break;
- case IB_WR_LOCAL_INV:
- hr_reg_enable(rc_sq_wqe, RC_SEND_WQE_SO);
- fallthrough;
case IB_WR_SEND_WITH_INV:
rc_sq_wqe->inv_key = cpu_to_le32(wr->ex.invalidate_rkey);
break;
@@ -2805,8 +2801,12 @@ static int free_mr_modify_qp(struct hns_roce_dev *hr_dev)
static int free_mr_init(struct hns_roce_dev *hr_dev)
{
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
+ struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
int ret;
+ mutex_init(&free_mr->mutex);
+
ret = free_mr_alloc_res(hr_dev);
if (ret)
return ret;
@@ -3222,7 +3222,6 @@ static int hns_roce_v2_write_mtpt(struct hns_roce_dev *hr_dev,
hr_reg_write(mpt_entry, MPT_ST, V2_MPT_ST_VALID);
hr_reg_write(mpt_entry, MPT_PD, mr->pd);
- hr_reg_enable(mpt_entry, MPT_L_INV_EN);
hr_reg_write_bool(mpt_entry, MPT_BIND_EN,
mr->access & IB_ACCESS_MW_BIND);
@@ -3313,7 +3312,6 @@ static int hns_roce_v2_frmr_write_mtpt(struct hns_roce_dev *hr_dev,
hr_reg_enable(mpt_entry, MPT_RA_EN);
hr_reg_enable(mpt_entry, MPT_R_INV_EN);
- hr_reg_enable(mpt_entry, MPT_L_INV_EN);
hr_reg_enable(mpt_entry, MPT_FRE);
hr_reg_clear(mpt_entry, MPT_MR_MW);
@@ -3345,7 +3343,6 @@ static int hns_roce_v2_mw_write_mtpt(void *mb_buf, struct hns_roce_mw *mw)
hr_reg_write(mpt_entry, MPT_PD, mw->pdn);
hr_reg_enable(mpt_entry, MPT_R_INV_EN);
- hr_reg_enable(mpt_entry, MPT_L_INV_EN);
hr_reg_enable(mpt_entry, MPT_LW_EN);
hr_reg_enable(mpt_entry, MPT_MR_MW);
@@ -3794,7 +3791,6 @@ static const u32 wc_send_op_map[] = {
HR_WC_OP_MAP(RDMA_READ, RDMA_READ),
HR_WC_OP_MAP(RDMA_WRITE, RDMA_WRITE),
HR_WC_OP_MAP(RDMA_WRITE_WITH_IMM, RDMA_WRITE),
- HR_WC_OP_MAP(LOCAL_INV, LOCAL_INV),
HR_WC_OP_MAP(ATOM_CMP_AND_SWAP, COMP_SWAP),
HR_WC_OP_MAP(ATOM_FETCH_AND_ADD, FETCH_ADD),
HR_WC_OP_MAP(ATOM_MSK_CMP_AND_SWAP, MASKED_COMP_SWAP),
@@ -3844,9 +3840,6 @@ static void fill_send_wc(struct ib_wc *wc, struct hns_roce_v2_cqe *cqe)
case HNS_ROCE_V2_WQE_OP_RDMA_WRITE_WITH_IMM:
wc->wc_flags |= IB_WC_WITH_IMM;
break;
- case HNS_ROCE_V2_WQE_OP_LOCAL_INV:
- wc->wc_flags |= IB_WC_WITH_INVALIDATE;
- break;
case HNS_ROCE_V2_WQE_OP_ATOM_CMP_AND_SWAP:
case HNS_ROCE_V2_WQE_OP_ATOM_FETCH_AND_ADD:
case HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP:
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index b11579027e82..c7bf2d52c1cd 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -179,7 +179,6 @@ enum {
HNS_ROCE_V2_WQE_OP_ATOM_MSK_CMP_AND_SWAP = 0x8,
HNS_ROCE_V2_WQE_OP_ATOM_MSK_FETCH_AND_ADD = 0x9,
HNS_ROCE_V2_WQE_OP_FAST_REG_PMR = 0xa,
- HNS_ROCE_V2_WQE_OP_LOCAL_INV = 0xb,
HNS_ROCE_V2_WQE_OP_BIND_MW = 0xc,
HNS_ROCE_V2_WQE_OP_MASK = 0x1f,
};
@@ -915,7 +914,6 @@ struct hns_roce_v2_rc_send_wqe {
#define RC_SEND_WQE_OWNER RC_SEND_WQE_FIELD_LOC(7, 7)
#define RC_SEND_WQE_CQE RC_SEND_WQE_FIELD_LOC(8, 8)
#define RC_SEND_WQE_FENCE RC_SEND_WQE_FIELD_LOC(9, 9)
-#define RC_SEND_WQE_SO RC_SEND_WQE_FIELD_LOC(10, 10)
#define RC_SEND_WQE_SE RC_SEND_WQE_FIELD_LOC(11, 11)
#define RC_SEND_WQE_INLINE RC_SEND_WQE_FIELD_LOC(12, 12)
#define RC_SEND_WQE_WQE_INDEX RC_SEND_WQE_FIELD_LOC(30, 15)
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 5152f10d2e6d..ba0c3e4c07d8 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -344,6 +344,10 @@ static int qedr_alloc_resources(struct qedr_dev *dev)
if (IS_IWARP(dev)) {
xa_init(&dev->qps);
dev->iwarp_wq = create_singlethread_workqueue("qedr_iwarpq");
+ if (!dev->iwarp_wq) {
+ rc = -ENOMEM;
+ goto err1;
+ }
}
/* Allocate Status blocks for CNQ */
@@ -351,7 +355,7 @@ static int qedr_alloc_resources(struct qedr_dev *dev)
GFP_KERNEL);
if (!dev->sb_array) {
rc = -ENOMEM;
- goto err1;
+ goto err_destroy_wq;
}
dev->cnq_array = kcalloc(dev->num_cnq,
@@ -402,6 +406,9 @@ err3:
kfree(dev->cnq_array);
err2:
kfree(dev->sb_array);
+err_destroy_wq:
+ if (IS_IWARP(dev))
+ destroy_workqueue(dev->iwarp_wq);
err1:
kfree(dev->sgid_tbl);
return rc;
diff --git a/drivers/infiniband/sw/rxe/rxe_resp.c b/drivers/infiniband/sw/rxe/rxe_resp.c
index ed5a09e86417..693081e813ec 100644
--- a/drivers/infiniband/sw/rxe/rxe_resp.c
+++ b/drivers/infiniband/sw/rxe/rxe_resp.c
@@ -806,8 +806,10 @@ static enum resp_states read_reply(struct rxe_qp *qp,
skb = prepare_ack_packet(qp, &ack_pkt, opcode, payload,
res->cur_psn, AETH_ACK_UNLIMITED);
- if (!skb)
+ if (!skb) {
+ rxe_put(mr);
return RESPST_ERR_RNR;
+ }
rxe_mr_copy(mr, res->read.va, payload_addr(&ack_pkt),
payload, RXE_FROM_MR_OBJ);
diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index a52f275f8263..f8447135a902 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -956,7 +956,7 @@ nj_release(struct tiger_hw *card)
}
if (card->irq > 0)
free_irq(card->irq, card);
- if (card->isac.dch.dev.dev.class)
+ if (device_is_registered(&card->isac.dch.dev.dev))
mISDN_unregister_device(&card->isac.dch.dev);
for (i = 0; i < 2; i++) {
diff --git a/drivers/isdn/mISDN/core.c b/drivers/isdn/mISDN/core.c
index a41b4b264594..7ea0100f218a 100644
--- a/drivers/isdn/mISDN/core.c
+++ b/drivers/isdn/mISDN/core.c
@@ -233,11 +233,12 @@ mISDN_register_device(struct mISDNdevice *dev,
if (debug & DEBUG_CORE)
printk(KERN_DEBUG "mISDN_register %s %d\n",
dev_name(&dev->dev), dev->id);
+ dev->dev.class = &mISDN_class;
+
err = create_stack(dev);
if (err)
goto error1;
- dev->dev.class = &mISDN_class;
dev->dev.platform_data = dev;
dev->dev.parent = parent;
dev_set_drvdata(&dev->dev, dev);
@@ -249,8 +250,8 @@ mISDN_register_device(struct mISDNdevice *dev,
error3:
delete_stack(dev);
- return err;
error1:
+ put_device(&dev->dev);
return err;
}
diff --git a/drivers/leds/simple/simatic-ipc-leds-gpio.c b/drivers/leds/simple/simatic-ipc-leds-gpio.c
index b9eeb8702df0..07f0d79d604d 100644
--- a/drivers/leds/simple/simatic-ipc-leds-gpio.c
+++ b/drivers/leds/simple/simatic-ipc-leds-gpio.c
@@ -20,12 +20,12 @@ static struct gpiod_lookup_table *simatic_ipc_led_gpio_table;
static struct gpiod_lookup_table simatic_ipc_led_gpio_table_127e = {
.dev_id = "leds-gpio",
.table = {
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 52, NULL, 1, GPIO_ACTIVE_LOW),
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 53, NULL, 2, GPIO_ACTIVE_LOW),
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 57, NULL, 3, GPIO_ACTIVE_LOW),
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 58, NULL, 4, GPIO_ACTIVE_LOW),
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 60, NULL, 5, GPIO_ACTIVE_LOW),
- GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 51, NULL, 0, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 52, NULL, 0, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 53, NULL, 1, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 57, NULL, 2, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 58, NULL, 3, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 60, NULL, 4, GPIO_ACTIVE_LOW),
+ GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 51, NULL, 5, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 56, NULL, 6, GPIO_ACTIVE_LOW),
GPIO_LOOKUP_IDX("apollolake-pinctrl.0", 59, NULL, 7, GPIO_ACTIVE_HIGH),
},
diff --git a/drivers/media/test-drivers/vivid/vivid-core.c b/drivers/media/test-drivers/vivid/vivid-core.c
index 04b75666bad4..f28440e6c9f8 100644
--- a/drivers/media/test-drivers/vivid/vivid-core.c
+++ b/drivers/media/test-drivers/vivid/vivid-core.c
@@ -339,6 +339,28 @@ static int vidioc_g_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *a
return vivid_vid_out_g_fbuf(file, fh, a);
}
+/*
+ * Only support the framebuffer of one of the vivid instances.
+ * Anything else is rejected.
+ */
+bool vivid_validate_fb(const struct v4l2_framebuffer *a)
+{
+ struct vivid_dev *dev;
+ int i;
+
+ for (i = 0; i < n_devs; i++) {
+ dev = vivid_devs[i];
+ if (!dev || !dev->video_pbase)
+ continue;
+ if ((unsigned long)a->base == dev->video_pbase &&
+ a->fmt.width <= dev->display_width &&
+ a->fmt.height <= dev->display_height &&
+ a->fmt.bytesperline <= dev->display_byte_stride)
+ return true;
+ }
+ return false;
+}
+
static int vidioc_s_fbuf(struct file *file, void *fh, const struct v4l2_framebuffer *a)
{
struct video_device *vdev = video_devdata(file);
@@ -920,8 +942,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst,
/* how many inputs do we have and of what type? */
dev->num_inputs = num_inputs[inst];
- if (dev->num_inputs < 1)
- dev->num_inputs = 1;
+ if (node_type & 0x20007) {
+ if (dev->num_inputs < 1)
+ dev->num_inputs = 1;
+ } else {
+ dev->num_inputs = 0;
+ }
if (dev->num_inputs >= MAX_INPUTS)
dev->num_inputs = MAX_INPUTS;
for (i = 0; i < dev->num_inputs; i++) {
@@ -938,8 +964,12 @@ static int vivid_detect_feature_set(struct vivid_dev *dev, int inst,
/* how many outputs do we have and of what type? */
dev->num_outputs = num_outputs[inst];
- if (dev->num_outputs < 1)
- dev->num_outputs = 1;
+ if (node_type & 0x40300) {
+ if (dev->num_outputs < 1)
+ dev->num_outputs = 1;
+ } else {
+ dev->num_outputs = 0;
+ }
if (dev->num_outputs >= MAX_OUTPUTS)
dev->num_outputs = MAX_OUTPUTS;
for (i = 0; i < dev->num_outputs; i++) {
diff --git a/drivers/media/test-drivers/vivid/vivid-core.h b/drivers/media/test-drivers/vivid/vivid-core.h
index bfcfb3515901..473f3598db5a 100644
--- a/drivers/media/test-drivers/vivid/vivid-core.h
+++ b/drivers/media/test-drivers/vivid/vivid-core.h
@@ -613,4 +613,6 @@ static inline bool vivid_is_hdmi_out(const struct vivid_dev *dev)
return dev->output_type[dev->output] == HDMI;
}
+bool vivid_validate_fb(const struct v4l2_framebuffer *a);
+
#endif
diff --git a/drivers/media/test-drivers/vivid/vivid-osd.c b/drivers/media/test-drivers/vivid/vivid-osd.c
index fbaec8acc161..ec25edc679b3 100644
--- a/drivers/media/test-drivers/vivid/vivid-osd.c
+++ b/drivers/media/test-drivers/vivid/vivid-osd.c
@@ -357,7 +357,7 @@ int vivid_fb_init(struct vivid_dev *dev)
int ret;
dev->video_buffer_size = MAX_OSD_HEIGHT * MAX_OSD_WIDTH * 2;
- dev->video_vbase = kzalloc(dev->video_buffer_size, GFP_KERNEL | GFP_DMA32);
+ dev->video_vbase = kzalloc(dev->video_buffer_size, GFP_KERNEL);
if (dev->video_vbase == NULL)
return -ENOMEM;
dev->video_pbase = virt_to_phys(dev->video_vbase);
diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
index 86b158eeb2d8..11620eaf941e 100644
--- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
@@ -453,6 +453,12 @@ void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls)
tpg_reset_source(&dev->tpg, dev->src_rect.width, dev->src_rect.height, dev->field_cap);
dev->crop_cap = dev->src_rect;
dev->crop_bounds_cap = dev->src_rect;
+ if (dev->bitmap_cap &&
+ (dev->compose_cap.width != dev->crop_cap.width ||
+ dev->compose_cap.height != dev->crop_cap.height)) {
+ vfree(dev->bitmap_cap);
+ dev->bitmap_cap = NULL;
+ }
dev->compose_cap = dev->crop_cap;
if (V4L2_FIELD_HAS_T_OR_B(dev->field_cap))
dev->compose_cap.height /= 2;
@@ -460,6 +466,14 @@ void vivid_update_format_cap(struct vivid_dev *dev, bool keep_controls)
tpg_s_video_aspect(&dev->tpg, vivid_get_video_aspect(dev));
tpg_s_pixel_aspect(&dev->tpg, vivid_get_pixel_aspect(dev));
tpg_update_mv_step(&dev->tpg);
+
+ /*
+ * We can be called from within s_ctrl, in that case we can't
+ * modify controls. Luckily we don't need to in that case.
+ */
+ if (keep_controls)
+ return;
+
dims[0] = roundup(dev->src_rect.width, PIXEL_ARRAY_DIV);
dims[1] = roundup(dev->src_rect.height, PIXEL_ARRAY_DIV);
v4l2_ctrl_modify_dimensions(dev->pixel_array, dims);
@@ -913,6 +927,8 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
struct vivid_dev *dev = video_drvdata(file);
struct v4l2_rect *crop = &dev->crop_cap;
struct v4l2_rect *compose = &dev->compose_cap;
+ unsigned orig_compose_w = compose->width;
+ unsigned orig_compose_h = compose->height;
unsigned factor = V4L2_FIELD_HAS_T_OR_B(dev->field_cap) ? 2 : 1;
int ret;
@@ -1029,17 +1045,17 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection
s->r.height /= factor;
}
v4l2_rect_map_inside(&s->r, &dev->fmt_cap_rect);
- if (dev->bitmap_cap && (compose->width != s->r.width ||
- compose->height != s->r.height)) {
- vfree(dev->bitmap_cap);
- dev->bitmap_cap = NULL;
- }
*compose = s->r;
break;
default:
return -EINVAL;
}
+ if (dev->bitmap_cap && (compose->width != orig_compose_w ||
+ compose->height != orig_compose_h)) {
+ vfree(dev->bitmap_cap);
+ dev->bitmap_cap = NULL;
+ }
tpg_s_crop_compose(&dev->tpg, crop, compose);
return 0;
}
@@ -1276,7 +1292,14 @@ int vivid_vid_cap_s_fbuf(struct file *file, void *fh,
return -EINVAL;
if (a->fmt.bytesperline < (a->fmt.width * fmt->bit_depth[0]) / 8)
return -EINVAL;
- if (a->fmt.height * a->fmt.bytesperline < a->fmt.sizeimage)
+ if (a->fmt.bytesperline > a->fmt.sizeimage / a->fmt.height)
+ return -EINVAL;
+
+ /*
+ * Only support the framebuffer of one of the vivid instances.
+ * Anything else is rejected.
+ */
+ if (!vivid_validate_fb(a))
return -EINVAL;
dev->fb_vbase_cap = phys_to_virt((unsigned long)a->base);
diff --git a/drivers/media/v4l2-core/v4l2-dv-timings.c b/drivers/media/v4l2-core/v4l2-dv-timings.c
index af48705c704f..003c32fed3f7 100644
--- a/drivers/media/v4l2-core/v4l2-dv-timings.c
+++ b/drivers/media/v4l2-core/v4l2-dv-timings.c
@@ -161,6 +161,20 @@ bool v4l2_valid_dv_timings(const struct v4l2_dv_timings *t,
(bt->interlaced && !(caps & V4L2_DV_BT_CAP_INTERLACED)) ||
(!bt->interlaced && !(caps & V4L2_DV_BT_CAP_PROGRESSIVE)))
return false;
+
+ /* sanity checks for the blanking timings */
+ if (!bt->interlaced &&
+ (bt->il_vbackporch || bt->il_vsync || bt->il_vfrontporch))
+ return false;
+ if (bt->hfrontporch > 2 * bt->width ||
+ bt->hsync > 1024 || bt->hbackporch > 1024)
+ return false;
+ if (bt->vfrontporch > 4096 ||
+ bt->vsync > 128 || bt->vbackporch > 4096)
+ return false;
+ if (bt->interlaced && (bt->il_vfrontporch > 4096 ||
+ bt->il_vsync > 128 || bt->il_vbackporch > 4096))
+ return false;
return fnc == NULL || fnc(t, fnc_handle);
}
EXPORT_SYMBOL_GPL(v4l2_valid_dv_timings);
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 9afda47efbf2..6706ef3c5977 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -152,7 +152,7 @@ static int gru_assign_asid(struct gru_state *gru)
* Optionally, build an array of chars that contain the bit numbers allocated.
*/
static unsigned long reserve_resources(unsigned long *p, int n, int mmax,
- char *idx)
+ signed char *idx)
{
unsigned long bits = 0;
int i;
@@ -170,14 +170,14 @@ static unsigned long reserve_resources(unsigned long *p, int n, int mmax,
}
unsigned long gru_reserve_cb_resources(struct gru_state *gru, int cbr_au_count,
- char *cbmap)
+ signed char *cbmap)
{
return reserve_resources(&gru->gs_cbr_map, cbr_au_count, GRU_CBR_AU,
cbmap);
}
unsigned long gru_reserve_ds_resources(struct gru_state *gru, int dsr_au_count,
- char *dsmap)
+ signed char *dsmap)
{
return reserve_resources(&gru->gs_dsr_map, dsr_au_count, GRU_DSR_AU,
dsmap);
diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h
index 5efc869fe59a..8c52776db234 100644
--- a/drivers/misc/sgi-gru/grutables.h
+++ b/drivers/misc/sgi-gru/grutables.h
@@ -351,7 +351,7 @@ struct gru_thread_state {
pid_t ts_tgid_owner; /* task that is using the
context - for migration */
short ts_user_blade_id;/* user selected blade */
- char ts_user_chiplet_id;/* user selected chiplet */
+ signed char ts_user_chiplet_id;/* user selected chiplet */
unsigned short ts_sizeavail; /* Pagesizes in use */
int ts_tsid; /* thread that owns the
structure */
@@ -364,11 +364,11 @@ struct gru_thread_state {
required for contest */
unsigned char ts_cbr_au_count;/* Number of CBR resources
required for contest */
- char ts_cch_req_slice;/* CCH packet slice */
- char ts_blade; /* If >= 0, migrate context if
+ signed char ts_cch_req_slice;/* CCH packet slice */
+ signed char ts_blade; /* If >= 0, migrate context if
ref from different blade */
- char ts_force_cch_reload;
- char ts_cbr_idx[GRU_CBR_AU];/* CBR numbers of each
+ signed char ts_force_cch_reload;
+ signed char ts_cbr_idx[GRU_CBR_AU];/* CBR numbers of each
allocated CB */
int ts_data_valid; /* Indicates if ts_gdata has
valid data */
@@ -643,9 +643,9 @@ extern struct gru_thread_state *gru_alloc_gts(struct vm_area_struct *vma,
int cbr_au_count, int dsr_au_count,
unsigned char tlb_preload_count, int options, int tsid);
extern unsigned long gru_reserve_cb_resources(struct gru_state *gru,
- int cbr_au_count, char *cbmap);
+ int cbr_au_count, signed char *cbmap);
extern unsigned long gru_reserve_ds_resources(struct gru_state *gru,
- int dsr_au_count, char *dsmap);
+ int dsr_au_count, signed char *dsmap);
extern vm_fault_t gru_fault(struct vm_fault *vmf);
extern struct gru_mm_struct *gru_register_mmu_notifier(void);
extern void gru_drop_mmu_notifier(struct gru_mm_struct *gms);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 54cd009aee50..db6d8a099910 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -134,6 +134,7 @@ struct mmc_blk_data {
* track of the current selected device partition.
*/
unsigned int part_curr;
+#define MMC_BLK_PART_INVALID UINT_MAX /* Unknown partition active */
int area_type;
/* debugfs files (only in main mmc_blk_data) */
@@ -987,33 +988,39 @@ static unsigned int mmc_blk_data_timeout_ms(struct mmc_host *host,
return ms;
}
+/*
+ * Attempts to reset the card and get back to the requested partition.
+ * Therefore any error here must result in cancelling the block layer
+ * request, it must not be reattempted without going through the mmc_blk
+ * partition sanity checks.
+ */
static int mmc_blk_reset(struct mmc_blk_data *md, struct mmc_host *host,
int type)
{
int err;
+ struct mmc_blk_data *main_md = dev_get_drvdata(&host->card->dev);
if (md->reset_done & type)
return -EEXIST;
md->reset_done |= type;
err = mmc_hw_reset(host->card);
+ /*
+ * A successful reset will leave the card in the main partition, but
+ * upon failure it might not be, so set it to MMC_BLK_PART_INVALID
+ * in that case.
+ */
+ main_md->part_curr = err ? MMC_BLK_PART_INVALID : main_md->part_type;
+ if (err)
+ return err;
/* Ensure we switch back to the correct partition */
- if (err) {
- struct mmc_blk_data *main_md =
- dev_get_drvdata(&host->card->dev);
- int part_err;
-
- main_md->part_curr = main_md->part_type;
- part_err = mmc_blk_part_switch(host->card, md->part_type);
- if (part_err) {
- /*
- * We have failed to get back into the correct
- * partition, so we need to abort the whole request.
- */
- return -ENODEV;
- }
- }
- return err;
+ if (mmc_blk_part_switch(host->card, md->part_type))
+ /*
+ * We have failed to get back into the correct
+ * partition, so we need to abort the whole request.
+ */
+ return -ENODEV;
+ return 0;
}
static inline void mmc_blk_reset_success(struct mmc_blk_data *md, int type)
@@ -1871,8 +1878,9 @@ static void mmc_blk_mq_rw_recovery(struct mmc_queue *mq, struct request *req)
return;
/* Reset before last retry */
- if (mqrq->retries + 1 == MMC_MAX_RETRIES)
- mmc_blk_reset(md, card->host, type);
+ if (mqrq->retries + 1 == MMC_MAX_RETRIES &&
+ mmc_blk_reset(md, card->host, type))
+ return;
/* Command errors fail fast, so use all MMC_MAX_RETRIES */
if (brq->sbc.error || brq->cmd.error)
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index fefaa901b50f..b396e3900717 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -48,6 +48,7 @@ static enum mmc_issue_type mmc_cqe_issue_type(struct mmc_host *host,
case REQ_OP_DRV_OUT:
case REQ_OP_DISCARD:
case REQ_OP_SECURE_ERASE:
+ case REQ_OP_WRITE_ZEROES:
return MMC_ISSUE_SYNC;
case REQ_OP_FLUSH:
return mmc_cqe_can_dcmd(host) ? MMC_ISSUE_DCMD : MMC_ISSUE_SYNC;
@@ -493,6 +494,13 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
if (blk_queue_quiesced(q))
blk_mq_unquiesce_queue(q);
+ /*
+ * If the recovery completes the last (and only remaining) request in
+ * the queue, and the card has been removed, we could end up here with
+ * the recovery not quite finished yet, so cancel it.
+ */
+ cancel_work_sync(&mq->recovery_work);
+
blk_mq_free_tag_set(&mq->tag_set);
/*
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index c6268c38c69e..babf21a0adeb 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -291,7 +291,8 @@ static void sdio_release_func(struct device *dev)
{
struct sdio_func *func = dev_to_sdio_func(dev);
- sdio_free_func_cis(func);
+ if (!(func->card->quirks & MMC_QUIRK_NONSTD_SDIO))
+ sdio_free_func_cis(func);
kfree(func->info);
kfree(func->tmpbuf);
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index f324daadaf70..fb1062a6394c 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -1075,9 +1075,10 @@ config MMC_SDHCI_OMAP
config MMC_SDHCI_AM654
tristate "Support for the SDHCI Controller in TI's AM654 SOCs"
- depends on MMC_SDHCI_PLTFM && OF && REGMAP_MMIO
+ depends on MMC_SDHCI_PLTFM && OF
select MMC_SDHCI_IO_ACCESSORS
select MMC_CQHCI
+ select REGMAP_MMIO
help
This selects the Secure Digital Host Controller Interface (SDHCI)
support present in TI's AM654 SOCs. The controller supports
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index 55981b0f0b10..747df79d90ee 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -1660,6 +1660,10 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
host->mmc_host_ops.execute_tuning = usdhc_execute_tuning;
}
+ err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data);
+ if (err)
+ goto disable_ahb_clk;
+
if (imx_data->socdata->flags & ESDHC_FLAG_MAN_TUNING)
sdhci_esdhc_ops.platform_execute_tuning =
esdhc_executing_tuning;
@@ -1667,13 +1671,15 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
- if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
+ if (host->caps & MMC_CAP_8_BIT_DATA &&
+ imx_data->socdata->flags & ESDHC_FLAG_HS400)
host->mmc->caps2 |= MMC_CAP2_HS400;
if (imx_data->socdata->flags & ESDHC_FLAG_BROKEN_AUTO_CMD23)
host->quirks2 |= SDHCI_QUIRK2_ACMD23_BROKEN;
- if (imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) {
+ if (host->caps & MMC_CAP_8_BIT_DATA &&
+ imx_data->socdata->flags & ESDHC_FLAG_HS400_ES) {
host->mmc->caps2 |= MMC_CAP2_HS400_ES;
host->mmc_host_ops.hs400_enhanced_strobe =
esdhc_hs400_enhanced_strobe;
@@ -1695,10 +1701,6 @@ static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
goto disable_ahb_clk;
}
- err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data);
- if (err)
- goto disable_ahb_clk;
-
sdhci_esdhc_imx_hwinit(host);
err = sdhci_add_host(host);
diff --git a/drivers/mmc/host/sdhci-pci-core.c b/drivers/mmc/host/sdhci-pci-core.c
index 169b84761041..34ea1acbb3cc 100644
--- a/drivers/mmc/host/sdhci-pci-core.c
+++ b/drivers/mmc/host/sdhci-pci-core.c
@@ -914,6 +914,12 @@ static bool glk_broken_cqhci(struct sdhci_pci_slot *slot)
dmi_match(DMI_SYS_VENDOR, "IRBIS"));
}
+static bool jsl_broken_hs400es(struct sdhci_pci_slot *slot)
+{
+ return slot->chip->pdev->device == PCI_DEVICE_ID_INTEL_JSL_EMMC &&
+ dmi_match(DMI_BIOS_VENDOR, "ASUSTeK COMPUTER INC.");
+}
+
static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot)
{
int ret = byt_emmc_probe_slot(slot);
@@ -922,9 +928,11 @@ static int glk_emmc_probe_slot(struct sdhci_pci_slot *slot)
slot->host->mmc->caps2 |= MMC_CAP2_CQE;
if (slot->chip->pdev->device != PCI_DEVICE_ID_INTEL_GLK_EMMC) {
- slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES;
- slot->host->mmc_host_ops.hs400_enhanced_strobe =
- intel_hs400_enhanced_strobe;
+ if (!jsl_broken_hs400es(slot)) {
+ slot->host->mmc->caps2 |= MMC_CAP2_HS400_ES;
+ slot->host->mmc_host_ops.hs400_enhanced_strobe =
+ intel_hs400_enhanced_strobe;
+ }
slot->host->mmc->caps2 |= MMC_CAP2_CQE_DCMD;
}
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 18aa54460d36..0b4ca0aa4132 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -562,7 +562,7 @@ static void mtd_check_of_node(struct mtd_info *mtd)
if (!mtd_is_partition(mtd))
return;
parent = mtd->parent;
- parent_dn = dev_of_node(&parent->dev);
+ parent_dn = of_node_get(dev_of_node(&parent->dev));
if (!parent_dn)
return;
diff --git a/drivers/mtd/nand/raw/intel-nand-controller.c b/drivers/mtd/nand/raw/intel-nand-controller.c
index d4a0987e93ac..6f4cea81f97c 100644
--- a/drivers/mtd/nand/raw/intel-nand-controller.c
+++ b/drivers/mtd/nand/raw/intel-nand-controller.c
@@ -608,11 +608,12 @@ static int ebu_nand_probe(struct platform_device *pdev)
ret = of_property_read_u32(chip_np, "reg", &cs);
if (ret) {
dev_err(dev, "failed to get chip select: %d\n", ret);
- return ret;
+ goto err_of_node_put;
}
if (cs >= MAX_CS) {
dev_err(dev, "got invalid chip select: %d\n", cs);
- return -EINVAL;
+ ret = -EINVAL;
+ goto err_of_node_put;
}
ebu_host->cs_num = cs;
@@ -620,18 +621,22 @@ static int ebu_nand_probe(struct platform_device *pdev)
resname = devm_kasprintf(dev, GFP_KERNEL, "nand_cs%d", cs);
ebu_host->cs[cs].chipaddr = devm_platform_ioremap_resource_byname(pdev,
resname);
- if (IS_ERR(ebu_host->cs[cs].chipaddr))
- return PTR_ERR(ebu_host->cs[cs].chipaddr);
+ if (IS_ERR(ebu_host->cs[cs].chipaddr)) {
+ ret = PTR_ERR(ebu_host->cs[cs].chipaddr);
+ goto err_of_node_put;
+ }
ebu_host->clk = devm_clk_get(dev, NULL);
- if (IS_ERR(ebu_host->clk))
- return dev_err_probe(dev, PTR_ERR(ebu_host->clk),
- "failed to get clock\n");
+ if (IS_ERR(ebu_host->clk)) {
+ ret = dev_err_probe(dev, PTR_ERR(ebu_host->clk),
+ "failed to get clock\n");
+ goto err_of_node_put;
+ }
ret = clk_prepare_enable(ebu_host->clk);
if (ret) {
dev_err(dev, "failed to enable clock: %d\n", ret);
- return ret;
+ goto err_of_node_put;
}
ebu_host->dma_tx = dma_request_chan(dev, "tx");
@@ -695,6 +700,8 @@ err_cleanup_dma:
ebu_dma_cleanup(ebu_host);
err_disable_unprepare_clk:
clk_disable_unprepare(ebu_host->clk);
+err_of_node_put:
+ of_node_put(chip_np);
return ret;
}
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index d9f2f1d0b5ef..b9d1e96e3334 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2678,7 +2678,7 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
chip->controller = &nfc->controller;
nand_set_flash_node(chip, np);
- if (!of_property_read_bool(np, "marvell,nand-keep-config"))
+ if (of_property_read_bool(np, "marvell,nand-keep-config"))
chip->options |= NAND_KEEP_TIMINGS;
mtd = nand_to_mtd(chip);
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index e12f9f580a15..a9b9031ce616 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -1181,7 +1181,7 @@ static int tegra_nand_probe(struct platform_device *pdev)
pm_runtime_enable(&pdev->dev);
err = pm_runtime_resume_and_get(&pdev->dev);
if (err)
- return err;
+ goto err_dis_pm;
err = reset_control_reset(rst);
if (err) {
@@ -1215,6 +1215,8 @@ static int tegra_nand_probe(struct platform_device *pdev)
err_put_pm:
pm_runtime_put_sync_suspend(ctrl->dev);
pm_runtime_force_suspend(ctrl->dev);
+err_dis_pm:
+ pm_runtime_disable(&pdev->dev);
return err;
}
diff --git a/drivers/mtd/parsers/bcm47xxpart.c b/drivers/mtd/parsers/bcm47xxpart.c
index 50fcf4c2174b..13daf9bffd08 100644
--- a/drivers/mtd/parsers/bcm47xxpart.c
+++ b/drivers/mtd/parsers/bcm47xxpart.c
@@ -233,11 +233,11 @@ static int bcm47xxpart_parse(struct mtd_info *master,
}
/* Read middle of the block */
- err = mtd_read(master, offset + 0x8000, 0x4, &bytes_read,
+ err = mtd_read(master, offset + (blocksize / 2), 0x4, &bytes_read,
(uint8_t *)buf);
if (err && !mtd_is_bitflip(err)) {
pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
- offset + 0x8000, err);
+ offset + (blocksize / 2), err);
continue;
}
diff --git a/drivers/mtd/spi-nor/core.c b/drivers/mtd/spi-nor/core.c
index f2c64006f8d7..bee8fc4c9f07 100644
--- a/drivers/mtd/spi-nor/core.c
+++ b/drivers/mtd/spi-nor/core.c
@@ -2724,7 +2724,9 @@ static int spi_nor_init(struct spi_nor *nor)
*/
WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
"enabling reset hack; may not recover from unexpected reboots\n");
- return nor->params->set_4byte_addr_mode(nor, true);
+ err = nor->params->set_4byte_addr_mode(nor, true);
+ if (err && err != -ENOTSUPP)
+ return err;
}
return 0;
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index c469b2f3e57d..b0ed798ae70f 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -322,14 +322,14 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
&mscan_clksrc);
if (!priv->can.clock.freq) {
dev_err(&ofdev->dev, "couldn't get MSCAN clock properties\n");
- goto exit_free_mscan;
+ goto exit_put_clock;
}
err = register_mscandev(dev, mscan_clksrc);
if (err) {
dev_err(&ofdev->dev, "registering %s failed (err=%d)\n",
DRV_NAME, err);
- goto exit_free_mscan;
+ goto exit_put_clock;
}
dev_info(&ofdev->dev, "MSCAN at 0x%p, irq %d, clock %d Hz\n",
@@ -337,7 +337,9 @@ static int mpc5xxx_can_probe(struct platform_device *ofdev)
return 0;
-exit_free_mscan:
+exit_put_clock:
+ if (data->put_clock)
+ data->put_clock(ofdev);
free_candev(dev);
exit_dispose_irq:
irq_dispose_mapping(irq);
diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index 567620d215f8..198da643ee6d 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -1157,11 +1157,13 @@ static void rcar_canfd_handle_global_receive(struct rcar_canfd_global *gpriv, u3
{
struct rcar_canfd_channel *priv = gpriv->ch[ch];
u32 ridx = ch + RCANFD_RFFIFO_IDX;
- u32 sts;
+ u32 sts, cc;
/* Handle Rx interrupts */
sts = rcar_canfd_read(priv->base, RCANFD_RFSTS(gpriv, ridx));
- if (likely(sts & RCANFD_RFSTS_RFIF)) {
+ cc = rcar_canfd_read(priv->base, RCANFD_RFCC(gpriv, ridx));
+ if (likely(sts & RCANFD_RFSTS_RFIF &&
+ cc & RCANFD_RFCC_RFIE)) {
if (napi_schedule_prep(&priv->napi)) {
/* Disable Rx FIFO interrupts */
rcar_canfd_clear_bit(priv->base,
@@ -1244,11 +1246,9 @@ static void rcar_canfd_handle_channel_tx(struct rcar_canfd_global *gpriv, u32 ch
static irqreturn_t rcar_canfd_channel_tx_interrupt(int irq, void *dev_id)
{
- struct rcar_canfd_global *gpriv = dev_id;
- u32 ch;
+ struct rcar_canfd_channel *priv = dev_id;
- for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels)
- rcar_canfd_handle_channel_tx(gpriv, ch);
+ rcar_canfd_handle_channel_tx(priv->gpriv, priv->channel);
return IRQ_HANDLED;
}
@@ -1276,11 +1276,9 @@ static void rcar_canfd_handle_channel_err(struct rcar_canfd_global *gpriv, u32 c
static irqreturn_t rcar_canfd_channel_err_interrupt(int irq, void *dev_id)
{
- struct rcar_canfd_global *gpriv = dev_id;
- u32 ch;
+ struct rcar_canfd_channel *priv = dev_id;
- for_each_set_bit(ch, &gpriv->channels_mask, gpriv->max_channels)
- rcar_canfd_handle_channel_err(gpriv, ch);
+ rcar_canfd_handle_channel_err(priv->gpriv, priv->channel);
return IRQ_HANDLED;
}
@@ -1721,6 +1719,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
priv->ndev = ndev;
priv->base = gpriv->base;
priv->channel = ch;
+ priv->gpriv = gpriv;
priv->can.clock.freq = fcan_freq;
dev_info(&pdev->dev, "can_clk rate is %u\n", priv->can.clock.freq);
@@ -1749,7 +1748,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
}
err = devm_request_irq(&pdev->dev, err_irq,
rcar_canfd_channel_err_interrupt, 0,
- irq_name, gpriv);
+ irq_name, priv);
if (err) {
dev_err(&pdev->dev, "devm_request_irq CH Err(%d) failed, error %d\n",
err_irq, err);
@@ -1763,7 +1762,7 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
}
err = devm_request_irq(&pdev->dev, tx_irq,
rcar_canfd_channel_tx_interrupt, 0,
- irq_name, gpriv);
+ irq_name, priv);
if (err) {
dev_err(&pdev->dev, "devm_request_irq Tx (%d) failed, error %d\n",
tx_irq, err);
@@ -1789,7 +1788,6 @@ static int rcar_canfd_channel_probe(struct rcar_canfd_global *gpriv, u32 ch,
priv->can.do_set_mode = rcar_canfd_do_set_mode;
priv->can.do_get_berr_counter = rcar_canfd_get_berr_counter;
- priv->gpriv = gpriv;
SET_NETDEV_DEV(ndev, &pdev->dev);
netif_napi_add_weight(ndev, &priv->napi, rcar_canfd_rx_poll,
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index c320de474f40..24883a65ca66 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1415,11 +1415,14 @@ static int mcp251x_can_probe(struct spi_device *spi)
ret = mcp251x_gpio_setup(priv);
if (ret)
- goto error_probe;
+ goto out_unregister_candev;
netdev_info(net, "MCP%x successfully initialized.\n", priv->model);
return 0;
+out_unregister_candev:
+ unregister_candev(net);
+
error_probe:
destroy_workqueue(priv->wq);
priv->wq = NULL;
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
index 7b52fda73d82..66f672ea631b 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -1875,7 +1875,7 @@ static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv)
{
int err;
- init_completion(&priv->start_comp);
+ reinit_completion(&priv->start_comp);
err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ,
priv->channel);
@@ -1893,7 +1893,7 @@ static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv)
{
int err;
- init_completion(&priv->stop_comp);
+ reinit_completion(&priv->stop_comp);
/* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT
* see comment in kvaser_usb_hydra_update_state()
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 50f2ac8319ff..19958037720f 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -1320,7 +1320,7 @@ static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv)
{
int err;
- init_completion(&priv->start_comp);
+ reinit_completion(&priv->start_comp);
err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP,
priv->channel);
@@ -1338,7 +1338,7 @@ static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv)
{
int err;
- init_completion(&priv->stop_comp);
+ reinit_completion(&priv->stop_comp);
err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
priv->channel);
diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c
index b9107fe40023..5b139f2206b6 100644
--- a/drivers/net/dsa/dsa_loop.c
+++ b/drivers/net/dsa/dsa_loop.c
@@ -376,6 +376,17 @@ static struct mdio_driver dsa_loop_drv = {
#define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2)
+static void dsa_loop_phydevs_unregister(void)
+{
+ unsigned int i;
+
+ for (i = 0; i < NUM_FIXED_PHYS; i++)
+ if (!IS_ERR(phydevs[i])) {
+ fixed_phy_unregister(phydevs[i]);
+ phy_device_free(phydevs[i]);
+ }
+}
+
static int __init dsa_loop_init(void)
{
struct fixed_phy_status status = {
@@ -383,23 +394,23 @@ static int __init dsa_loop_init(void)
.speed = SPEED_100,
.duplex = DUPLEX_FULL,
};
- unsigned int i;
+ unsigned int i, ret;
for (i = 0; i < NUM_FIXED_PHYS; i++)
phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL);
- return mdio_driver_register(&dsa_loop_drv);
+ ret = mdio_driver_register(&dsa_loop_drv);
+ if (ret)
+ dsa_loop_phydevs_unregister();
+
+ return ret;
}
module_init(dsa_loop_init);
static void __exit dsa_loop_exit(void)
{
- unsigned int i;
-
mdio_driver_unregister(&dsa_loop_drv);
- for (i = 0; i < NUM_FIXED_PHYS; i++)
- if (!IS_ERR(phydevs[i]))
- fixed_phy_unregister(phydevs[i]);
+ dsa_loop_phydevs_unregister();
}
module_exit(dsa_loop_exit);
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 1744d623999d..606c97610808 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1512,16 +1512,15 @@ static struct notifier_block adin1110_switchdev_notifier = {
.notifier_call = adin1110_switchdev_event,
};
-static void adin1110_unregister_notifiers(void *data)
+static void adin1110_unregister_notifiers(void)
{
unregister_switchdev_blocking_notifier(&adin1110_switchdev_blocking_notifier);
unregister_switchdev_notifier(&adin1110_switchdev_notifier);
unregister_netdevice_notifier(&adin1110_netdevice_nb);
}
-static int adin1110_setup_notifiers(struct adin1110_priv *priv)
+static int adin1110_setup_notifiers(void)
{
- struct device *dev = &priv->spidev->dev;
int ret;
ret = register_netdevice_notifier(&adin1110_netdevice_nb);
@@ -1536,13 +1535,14 @@ static int adin1110_setup_notifiers(struct adin1110_priv *priv)
if (ret < 0)
goto err_sdev;
- return devm_add_action_or_reset(dev, adin1110_unregister_notifiers, NULL);
+ return 0;
err_sdev:
unregister_switchdev_notifier(&adin1110_switchdev_notifier);
err_netdev:
unregister_netdevice_notifier(&adin1110_netdevice_nb);
+
return ret;
}
@@ -1613,10 +1613,6 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
if (ret < 0)
return ret;
- ret = adin1110_setup_notifiers(priv);
- if (ret < 0)
- return ret;
-
for (i = 0; i < priv->cfg->ports_nr; i++) {
ret = devm_register_netdev(dev, priv->ports[i]->netdev);
if (ret < 0) {
@@ -1693,7 +1689,31 @@ static struct spi_driver adin1110_driver = {
.probe = adin1110_probe,
.id_table = adin1110_spi_id,
};
-module_spi_driver(adin1110_driver);
+
+static int __init adin1110_driver_init(void)
+{
+ int ret;
+
+ ret = adin1110_setup_notifiers();
+ if (ret < 0)
+ return ret;
+
+ ret = spi_register_driver(&adin1110_driver);
+ if (ret < 0) {
+ adin1110_unregister_notifiers();
+ return ret;
+ }
+
+ return 0;
+}
+
+static void __exit adin1110_exit(void)
+{
+ adin1110_unregister_notifiers();
+ spi_unregister_driver(&adin1110_driver);
+}
+module_init(adin1110_driver_init);
+module_exit(adin1110_exit);
MODULE_DESCRIPTION("ADIN1110 Network driver");
MODULE_AUTHOR("Alexandru Tachici <alexandru.tachici@analog.com>");
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
index 2af3da4b2d05..f409d7bd1f1e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-pci.c
@@ -285,6 +285,9 @@ static int xgbe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
/* Yellow Carp devices do not need cdr workaround */
pdata->vdata->an_cdr_workaround = 0;
+
+ /* Yellow Carp devices do not need rrc */
+ pdata->vdata->enable_rrc = 0;
} else {
pdata->xpcs_window_def_reg = PCS_V2_WINDOW_DEF;
pdata->xpcs_window_sel_reg = PCS_V2_WINDOW_SELECT;
@@ -483,6 +486,7 @@ static struct xgbe_version_data xgbe_v2a = {
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
.an_cdr_workaround = 1,
+ .enable_rrc = 1,
};
static struct xgbe_version_data xgbe_v2b = {
@@ -498,6 +502,7 @@ static struct xgbe_version_data xgbe_v2b = {
.tx_desc_prefetch = 5,
.rx_desc_prefetch = 5,
.an_cdr_workaround = 1,
+ .enable_rrc = 1,
};
static const struct pci_device_id xgbe_pci_table[] = {
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 2156600641b6..4064c3e3dd49 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -239,6 +239,7 @@ enum xgbe_sfp_speed {
#define XGBE_SFP_BASE_BR_1GBE_MAX 0x0d
#define XGBE_SFP_BASE_BR_10GBE_MIN 0x64
#define XGBE_SFP_BASE_BR_10GBE_MAX 0x68
+#define XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX 0x78
#define XGBE_SFP_BASE_CU_CABLE_LEN 18
@@ -284,6 +285,8 @@ struct xgbe_sfp_eeprom {
#define XGBE_BEL_FUSE_VENDOR "BEL-FUSE "
#define XGBE_BEL_FUSE_PARTNO "1GBT-SFP06 "
+#define XGBE_MOLEX_VENDOR "Molex Inc. "
+
struct xgbe_sfp_ascii {
union {
char vendor[XGBE_SFP_BASE_VENDOR_NAME_LEN + 1];
@@ -834,7 +837,11 @@ static bool xgbe_phy_sfp_bit_rate(struct xgbe_sfp_eeprom *sfp_eeprom,
break;
case XGBE_SFP_SPEED_10000:
min = XGBE_SFP_BASE_BR_10GBE_MIN;
- max = XGBE_SFP_BASE_BR_10GBE_MAX;
+ if (memcmp(&sfp_eeprom->base[XGBE_SFP_BASE_VENDOR_NAME],
+ XGBE_MOLEX_VENDOR, XGBE_SFP_BASE_VENDOR_NAME_LEN) == 0)
+ max = XGBE_MOLEX_SFP_BASE_BR_10GBE_MAX;
+ else
+ max = XGBE_SFP_BASE_BR_10GBE_MAX;
break;
default:
return false;
@@ -1151,7 +1158,10 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
}
/* Determine the type of SFP */
- if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR)
+ if (phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE &&
+ xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000))
+ phy_data->sfp_base = XGBE_SFP_BASE_10000_CR;
+ else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_SR)
phy_data->sfp_base = XGBE_SFP_BASE_10000_SR;
else if (sfp_base[XGBE_SFP_BASE_10GBE_CC] & XGBE_SFP_BASE_10GBE_CC_LR)
phy_data->sfp_base = XGBE_SFP_BASE_10000_LR;
@@ -1167,9 +1177,6 @@ static void xgbe_phy_sfp_parse_eeprom(struct xgbe_prv_data *pdata)
phy_data->sfp_base = XGBE_SFP_BASE_1000_CX;
else if (sfp_base[XGBE_SFP_BASE_1GBE_CC] & XGBE_SFP_BASE_1GBE_CC_T)
phy_data->sfp_base = XGBE_SFP_BASE_1000_T;
- else if ((phy_data->sfp_cable == XGBE_SFP_CABLE_PASSIVE) &&
- xgbe_phy_sfp_bit_rate(sfp_eeprom, XGBE_SFP_SPEED_10000))
- phy_data->sfp_base = XGBE_SFP_BASE_10000_CR;
switch (phy_data->sfp_base) {
case XGBE_SFP_BASE_1000_T:
@@ -1979,6 +1986,10 @@ static void xgbe_phy_rx_reset(struct xgbe_prv_data *pdata)
static void xgbe_phy_pll_ctrl(struct xgbe_prv_data *pdata, bool enable)
{
+ /* PLL_CTRL feature needs to be enabled for fixed PHY modes (Non-Autoneg) only */
+ if (pdata->phy.autoneg != AUTONEG_DISABLE)
+ return;
+
XMDIO_WRITE_BITS(pdata, MDIO_MMD_PMAPMD, MDIO_VEND2_PMA_MISC_CTRL0,
XGBE_PMA_PLL_CTRL_MASK,
enable ? XGBE_PMA_PLL_CTRL_ENABLE
@@ -1989,7 +2000,7 @@ static void xgbe_phy_pll_ctrl(struct xgbe_prv_data *pdata, bool enable)
}
static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata,
- unsigned int cmd, unsigned int sub_cmd)
+ enum xgbe_mb_cmd cmd, enum xgbe_mb_subcmd sub_cmd)
{
unsigned int s0 = 0;
unsigned int wait;
@@ -2029,14 +2040,16 @@ static void xgbe_phy_perform_ratechange(struct xgbe_prv_data *pdata,
xgbe_phy_rx_reset(pdata);
reenable_pll:
- /* Enable PLL re-initialization */
- xgbe_phy_pll_ctrl(pdata, true);
+ /* Enable PLL re-initialization, not needed for PHY Power Off and RRC cmds */
+ if (cmd != XGBE_MB_CMD_POWER_OFF &&
+ cmd != XGBE_MB_CMD_RRC)
+ xgbe_phy_pll_ctrl(pdata, true);
}
static void xgbe_phy_rrc(struct xgbe_prv_data *pdata)
{
/* Receiver Reset Cycle */
- xgbe_phy_perform_ratechange(pdata, 5, 0);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_RRC, XGBE_MB_SUBCMD_NONE);
netif_dbg(pdata, link, pdata->netdev, "receiver reset complete\n");
}
@@ -2046,7 +2059,7 @@ static void xgbe_phy_power_off(struct xgbe_prv_data *pdata)
struct xgbe_phy_data *phy_data = pdata->phy_data;
/* Power off */
- xgbe_phy_perform_ratechange(pdata, 0, 0);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_POWER_OFF, XGBE_MB_SUBCMD_NONE);
phy_data->cur_mode = XGBE_MODE_UNKNOWN;
@@ -2061,14 +2074,17 @@ static void xgbe_phy_sfi_mode(struct xgbe_prv_data *pdata)
/* 10G/SFI */
if (phy_data->sfp_cable != XGBE_SFP_CABLE_PASSIVE) {
- xgbe_phy_perform_ratechange(pdata, 3, 0);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI, XGBE_MB_SUBCMD_ACTIVE);
} else {
if (phy_data->sfp_cable_len <= 1)
- xgbe_phy_perform_ratechange(pdata, 3, 1);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI,
+ XGBE_MB_SUBCMD_PASSIVE_1M);
else if (phy_data->sfp_cable_len <= 3)
- xgbe_phy_perform_ratechange(pdata, 3, 2);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI,
+ XGBE_MB_SUBCMD_PASSIVE_3M);
else
- xgbe_phy_perform_ratechange(pdata, 3, 3);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_SFI,
+ XGBE_MB_SUBCMD_PASSIVE_OTHER);
}
phy_data->cur_mode = XGBE_MODE_SFI;
@@ -2083,7 +2099,7 @@ static void xgbe_phy_x_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 1G/X */
- xgbe_phy_perform_ratechange(pdata, 1, 3);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_1G, XGBE_MB_SUBCMD_1G_KX);
phy_data->cur_mode = XGBE_MODE_X;
@@ -2097,7 +2113,7 @@ static void xgbe_phy_sgmii_1000_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 1G/SGMII */
- xgbe_phy_perform_ratechange(pdata, 1, 2);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_1G, XGBE_MB_SUBCMD_1G_SGMII);
phy_data->cur_mode = XGBE_MODE_SGMII_1000;
@@ -2111,7 +2127,7 @@ static void xgbe_phy_sgmii_100_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 100M/SGMII */
- xgbe_phy_perform_ratechange(pdata, 1, 1);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_1G, XGBE_MB_SUBCMD_100MBITS);
phy_data->cur_mode = XGBE_MODE_SGMII_100;
@@ -2125,7 +2141,7 @@ static void xgbe_phy_kr_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 10G/KR */
- xgbe_phy_perform_ratechange(pdata, 4, 0);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_10G_KR, XGBE_MB_SUBCMD_NONE);
phy_data->cur_mode = XGBE_MODE_KR;
@@ -2139,7 +2155,7 @@ static void xgbe_phy_kx_2500_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 2.5G/KX */
- xgbe_phy_perform_ratechange(pdata, 2, 0);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_2_5G, XGBE_MB_SUBCMD_NONE);
phy_data->cur_mode = XGBE_MODE_KX_2500;
@@ -2153,7 +2169,7 @@ static void xgbe_phy_kx_1000_mode(struct xgbe_prv_data *pdata)
xgbe_phy_set_redrv_mode(pdata);
/* 1G/KX */
- xgbe_phy_perform_ratechange(pdata, 1, 3);
+ xgbe_phy_perform_ratechange(pdata, XGBE_MB_CMD_SET_1G, XGBE_MB_SUBCMD_1G_KX);
phy_data->cur_mode = XGBE_MODE_KX_1000;
@@ -2640,7 +2656,7 @@ static int xgbe_phy_link_status(struct xgbe_prv_data *pdata, int *an_restart)
}
/* No link, attempt a receiver reset cycle */
- if (phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
+ if (pdata->vdata->enable_rrc && phy_data->rrc_count++ > XGBE_RRC_FREQUENCY) {
phy_data->rrc_count = 0;
xgbe_phy_rrc(pdata);
}
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index b875c430222e..71f24cb47935 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -611,6 +611,31 @@ enum xgbe_mdio_mode {
XGBE_MDIO_MODE_CL45,
};
+enum xgbe_mb_cmd {
+ XGBE_MB_CMD_POWER_OFF = 0,
+ XGBE_MB_CMD_SET_1G,
+ XGBE_MB_CMD_SET_2_5G,
+ XGBE_MB_CMD_SET_10G_SFI,
+ XGBE_MB_CMD_SET_10G_KR,
+ XGBE_MB_CMD_RRC
+};
+
+enum xgbe_mb_subcmd {
+ XGBE_MB_SUBCMD_NONE = 0,
+
+ /* 10GbE SFP subcommands */
+ XGBE_MB_SUBCMD_ACTIVE = 0,
+ XGBE_MB_SUBCMD_PASSIVE_1M,
+ XGBE_MB_SUBCMD_PASSIVE_3M,
+ XGBE_MB_SUBCMD_PASSIVE_OTHER,
+
+ /* 1GbE Mode subcommands */
+ XGBE_MB_SUBCMD_10MBITS = 0,
+ XGBE_MB_SUBCMD_100MBITS,
+ XGBE_MB_SUBCMD_1G_SGMII,
+ XGBE_MB_SUBCMD_1G_KX
+};
+
struct xgbe_phy {
struct ethtool_link_ksettings lks;
@@ -1013,6 +1038,7 @@ struct xgbe_version_data {
unsigned int tx_desc_prefetch;
unsigned int rx_desc_prefetch;
unsigned int an_cdr_workaround;
+ unsigned int enable_rrc;
};
struct xgbe_prv_data {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
index 3d0e16791e1c..a0180811305d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_macsec.c
@@ -1394,26 +1394,57 @@ static void aq_check_txsa_expiration(struct aq_nic_s *nic)
egress_sa_threshold_expired);
}
+#define AQ_LOCKED_MDO_DEF(mdo) \
+static int aq_locked_mdo_##mdo(struct macsec_context *ctx) \
+{ \
+ struct aq_nic_s *nic = netdev_priv(ctx->netdev); \
+ int ret; \
+ mutex_lock(&nic->macsec_mutex); \
+ ret = aq_mdo_##mdo(ctx); \
+ mutex_unlock(&nic->macsec_mutex); \
+ return ret; \
+}
+
+AQ_LOCKED_MDO_DEF(dev_open)
+AQ_LOCKED_MDO_DEF(dev_stop)
+AQ_LOCKED_MDO_DEF(add_secy)
+AQ_LOCKED_MDO_DEF(upd_secy)
+AQ_LOCKED_MDO_DEF(del_secy)
+AQ_LOCKED_MDO_DEF(add_rxsc)
+AQ_LOCKED_MDO_DEF(upd_rxsc)
+AQ_LOCKED_MDO_DEF(del_rxsc)
+AQ_LOCKED_MDO_DEF(add_rxsa)
+AQ_LOCKED_MDO_DEF(upd_rxsa)
+AQ_LOCKED_MDO_DEF(del_rxsa)
+AQ_LOCKED_MDO_DEF(add_txsa)
+AQ_LOCKED_MDO_DEF(upd_txsa)
+AQ_LOCKED_MDO_DEF(del_txsa)
+AQ_LOCKED_MDO_DEF(get_dev_stats)
+AQ_LOCKED_MDO_DEF(get_tx_sc_stats)
+AQ_LOCKED_MDO_DEF(get_tx_sa_stats)
+AQ_LOCKED_MDO_DEF(get_rx_sc_stats)
+AQ_LOCKED_MDO_DEF(get_rx_sa_stats)
+
const struct macsec_ops aq_macsec_ops = {
- .mdo_dev_open = aq_mdo_dev_open,
- .mdo_dev_stop = aq_mdo_dev_stop,
- .mdo_add_secy = aq_mdo_add_secy,
- .mdo_upd_secy = aq_mdo_upd_secy,
- .mdo_del_secy = aq_mdo_del_secy,
- .mdo_add_rxsc = aq_mdo_add_rxsc,
- .mdo_upd_rxsc = aq_mdo_upd_rxsc,
- .mdo_del_rxsc = aq_mdo_del_rxsc,
- .mdo_add_rxsa = aq_mdo_add_rxsa,
- .mdo_upd_rxsa = aq_mdo_upd_rxsa,
- .mdo_del_rxsa = aq_mdo_del_rxsa,
- .mdo_add_txsa = aq_mdo_add_txsa,
- .mdo_upd_txsa = aq_mdo_upd_txsa,
- .mdo_del_txsa = aq_mdo_del_txsa,
- .mdo_get_dev_stats = aq_mdo_get_dev_stats,
- .mdo_get_tx_sc_stats = aq_mdo_get_tx_sc_stats,
- .mdo_get_tx_sa_stats = aq_mdo_get_tx_sa_stats,
- .mdo_get_rx_sc_stats = aq_mdo_get_rx_sc_stats,
- .mdo_get_rx_sa_stats = aq_mdo_get_rx_sa_stats,
+ .mdo_dev_open = aq_locked_mdo_dev_open,
+ .mdo_dev_stop = aq_locked_mdo_dev_stop,
+ .mdo_add_secy = aq_locked_mdo_add_secy,
+ .mdo_upd_secy = aq_locked_mdo_upd_secy,
+ .mdo_del_secy = aq_locked_mdo_del_secy,
+ .mdo_add_rxsc = aq_locked_mdo_add_rxsc,
+ .mdo_upd_rxsc = aq_locked_mdo_upd_rxsc,
+ .mdo_del_rxsc = aq_locked_mdo_del_rxsc,
+ .mdo_add_rxsa = aq_locked_mdo_add_rxsa,
+ .mdo_upd_rxsa = aq_locked_mdo_upd_rxsa,
+ .mdo_del_rxsa = aq_locked_mdo_del_rxsa,
+ .mdo_add_txsa = aq_locked_mdo_add_txsa,
+ .mdo_upd_txsa = aq_locked_mdo_upd_txsa,
+ .mdo_del_txsa = aq_locked_mdo_del_txsa,
+ .mdo_get_dev_stats = aq_locked_mdo_get_dev_stats,
+ .mdo_get_tx_sc_stats = aq_locked_mdo_get_tx_sc_stats,
+ .mdo_get_tx_sa_stats = aq_locked_mdo_get_tx_sa_stats,
+ .mdo_get_rx_sc_stats = aq_locked_mdo_get_rx_sc_stats,
+ .mdo_get_rx_sa_stats = aq_locked_mdo_get_rx_sa_stats,
};
int aq_macsec_init(struct aq_nic_s *nic)
@@ -1435,6 +1466,7 @@ int aq_macsec_init(struct aq_nic_s *nic)
nic->ndev->features |= NETIF_F_HW_MACSEC;
nic->ndev->macsec_ops = &aq_macsec_ops;
+ mutex_init(&nic->macsec_mutex);
return 0;
}
@@ -1458,7 +1490,7 @@ int aq_macsec_enable(struct aq_nic_s *nic)
if (!nic->macsec_cfg)
return 0;
- rtnl_lock();
+ mutex_lock(&nic->macsec_mutex);
if (nic->aq_fw_ops->send_macsec_req) {
struct macsec_cfg_request cfg = { 0 };
@@ -1507,7 +1539,7 @@ int aq_macsec_enable(struct aq_nic_s *nic)
ret = aq_apply_macsec_cfg(nic);
unlock:
- rtnl_unlock();
+ mutex_unlock(&nic->macsec_mutex);
return ret;
}
@@ -1519,9 +1551,9 @@ void aq_macsec_work(struct aq_nic_s *nic)
if (!netif_carrier_ok(nic->ndev))
return;
- rtnl_lock();
+ mutex_lock(&nic->macsec_mutex);
aq_check_txsa_expiration(nic);
- rtnl_unlock();
+ mutex_unlock(&nic->macsec_mutex);
}
int aq_macsec_rx_sa_cnt(struct aq_nic_s *nic)
@@ -1532,21 +1564,30 @@ int aq_macsec_rx_sa_cnt(struct aq_nic_s *nic)
if (!cfg)
return 0;
+ mutex_lock(&nic->macsec_mutex);
+
for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
if (!test_bit(i, &cfg->rxsc_idx_busy))
continue;
cnt += hweight_long(cfg->aq_rxsc[i].rx_sa_idx_busy);
}
+ mutex_unlock(&nic->macsec_mutex);
return cnt;
}
int aq_macsec_tx_sc_cnt(struct aq_nic_s *nic)
{
+ int cnt;
+
if (!nic->macsec_cfg)
return 0;
- return hweight_long(nic->macsec_cfg->txsc_idx_busy);
+ mutex_lock(&nic->macsec_mutex);
+ cnt = hweight_long(nic->macsec_cfg->txsc_idx_busy);
+ mutex_unlock(&nic->macsec_mutex);
+
+ return cnt;
}
int aq_macsec_tx_sa_cnt(struct aq_nic_s *nic)
@@ -1557,12 +1598,15 @@ int aq_macsec_tx_sa_cnt(struct aq_nic_s *nic)
if (!cfg)
return 0;
+ mutex_lock(&nic->macsec_mutex);
+
for (i = 0; i < AQ_MACSEC_MAX_SC; i++) {
if (!test_bit(i, &cfg->txsc_idx_busy))
continue;
cnt += hweight_long(cfg->aq_txsc[i].tx_sa_idx_busy);
}
+ mutex_unlock(&nic->macsec_mutex);
return cnt;
}
@@ -1634,6 +1678,8 @@ u64 *aq_macsec_get_stats(struct aq_nic_s *nic, u64 *data)
if (!cfg)
return data;
+ mutex_lock(&nic->macsec_mutex);
+
aq_macsec_update_stats(nic);
common_stats = &cfg->stats;
@@ -1716,5 +1762,7 @@ u64 *aq_macsec_get_stats(struct aq_nic_s *nic, u64 *data)
data += i;
+ mutex_unlock(&nic->macsec_mutex);
+
return data;
}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 935ba889bd9a..ad33f8586532 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -157,6 +157,8 @@ struct aq_nic_s {
struct mutex fwreq_mutex;
#if IS_ENABLED(CONFIG_MACSEC)
struct aq_macsec_cfg *macsec_cfg;
+ /* mutex to protect data in macsec_cfg */
+ struct mutex macsec_mutex;
#endif
/* PTP support */
struct aq_ptp_s *aq_ptp;
diff --git a/drivers/net/ethernet/broadcom/bcm4908_enet.c b/drivers/net/ethernet/broadcom/bcm4908_enet.c
index 93ccf549e2ed..a737b1913cf9 100644
--- a/drivers/net/ethernet/broadcom/bcm4908_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm4908_enet.c
@@ -561,8 +561,6 @@ static netdev_tx_t bcm4908_enet_start_xmit(struct sk_buff *skb, struct net_devic
if (++ring->write_idx == ring->length - 1)
ring->write_idx = 0;
- enet->netdev->stats.tx_bytes += skb->len;
- enet->netdev->stats.tx_packets++;
return NETDEV_TX_OK;
}
@@ -635,6 +633,7 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight)
struct bcm4908_enet_dma_ring_bd *buf_desc;
struct bcm4908_enet_dma_ring_slot *slot;
struct device *dev = enet->dev;
+ unsigned int bytes = 0;
int handled = 0;
while (handled < weight && tx_ring->read_idx != tx_ring->write_idx) {
@@ -645,12 +644,17 @@ static int bcm4908_enet_poll_tx(struct napi_struct *napi, int weight)
dma_unmap_single(dev, slot->dma_addr, slot->len, DMA_TO_DEVICE);
dev_kfree_skb(slot->skb);
- if (++tx_ring->read_idx == tx_ring->length)
- tx_ring->read_idx = 0;
handled++;
+ bytes += slot->len;
+
+ if (++tx_ring->read_idx == tx_ring->length)
+ tx_ring->read_idx = 0;
}
+ enet->netdev->stats.tx_packets += handled;
+ enet->netdev->stats.tx_bytes += bytes;
+
if (handled < weight) {
napi_complete_done(napi, handled);
bcm4908_enet_dma_ring_intrs_on(enet, tx_ring);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 867f14c30e09..425d6ccd5413 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1991,6 +1991,9 @@ static int bcm_sysport_open(struct net_device *dev)
goto out_clk_disable;
}
+ /* Indicate that the MAC is responsible for PHY PM */
+ phydev->mac_managed_pm = true;
+
/* Reset house keeping link status */
priv->old_duplex = -1;
priv->old_link = -1;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 51c9fd6f68a4..4f63f1ba3161 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -806,6 +806,7 @@ static int macb_mii_probe(struct net_device *dev)
bp->phylink_config.dev = &dev->dev;
bp->phylink_config.type = PHYLINK_NETDEV;
+ bp->phylink_config.mac_managed_pm = true;
if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) {
bp->phylink_config.poll_fixed_state = true;
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 31cfa121333d..fc68a32ce2f7 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -221,8 +221,8 @@ static int dpaa_netdev_init(struct net_device *net_dev,
net_dev->netdev_ops = dpaa_ops;
mac_addr = mac_dev->addr;
- net_dev->mem_start = (unsigned long)mac_dev->vaddr;
- net_dev->mem_end = (unsigned long)mac_dev->vaddr_end;
+ net_dev->mem_start = (unsigned long)priv->mac_dev->res->start;
+ net_dev->mem_end = (unsigned long)priv->mac_dev->res->end;
net_dev->min_mtu = ETH_MIN_MTU;
net_dev->max_mtu = dpaa_get_max_mtu();
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
index 258eb6c8f4c0..4fee74c024bd 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth_sysfs.c
@@ -18,7 +18,7 @@ static ssize_t dpaa_eth_show_addr(struct device *dev,
if (mac_dev)
return sprintf(buf, "%llx",
- (unsigned long long)mac_dev->vaddr);
+ (unsigned long long)mac_dev->res->start);
else
return sprintf(buf, "none");
}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 54bc92fc6bf0..f8c06c3f9464 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -2090,7 +2090,12 @@ static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
else
enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE);
+ /* Also prepare the consumer index in case page allocation never
+ * succeeds. In that case, hardware will never advance producer index
+ * to match consumer index, and will drop all frames.
+ */
enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0);
+ enetc_rxbdr_wr(hw, idx, ENETC_RBCIR, 1);
/* enable Rx ints by setting pkt thr to 1 */
enetc_rxbdr_wr(hw, idx, ENETC_RBICR0, ENETC_RBICR0_ICEN | 0x1);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 98d5cd313fdd..f623c12eaf95 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -713,7 +713,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb,
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
- return NETDEV_TX_BUSY;
+ return NETDEV_TX_OK;
}
bdp->cbd_datlen = cpu_to_fec16(size);
@@ -775,7 +775,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq,
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
- return NETDEV_TX_BUSY;
+ return NETDEV_TX_OK;
}
}
@@ -2432,6 +2432,31 @@ static u32 fec_enet_register_offset[] = {
IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
IEEE_R_FDXFC, IEEE_R_OCTETS_OK
};
+/* for i.MX6ul */
+static u32 fec_enet_register_offset_6ul[] = {
+ FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
+ FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
+ FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_RXIC0,
+ FEC_HASH_TABLE_HIGH, FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH,
+ FEC_GRP_HASH_TABLE_LOW, FEC_X_WMRK, FEC_R_DES_START_0,
+ FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM,
+ FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC,
+ RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT,
+ RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG,
+ RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255,
+ RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047,
+ RMON_T_P_GTE2048, RMON_T_OCTETS,
+ IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF,
+ IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE,
+ IEEE_T_FDXFC, IEEE_T_OCTETS_OK,
+ RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN,
+ RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB,
+ RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255,
+ RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047,
+ RMON_R_P_GTE2048, RMON_R_OCTETS,
+ IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
+ IEEE_R_FDXFC, IEEE_R_OCTETS_OK
+};
#else
static __u32 fec_enet_register_version = 1;
static u32 fec_enet_register_offset[] = {
@@ -2456,7 +2481,24 @@ static void fec_enet_get_regs(struct net_device *ndev,
u32 *buf = (u32 *)regbuf;
u32 i, off;
int ret;
+#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
+ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
+ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+ u32 *reg_list;
+ u32 reg_cnt;
+ if (!of_machine_is_compatible("fsl,imx6ul")) {
+ reg_list = fec_enet_register_offset;
+ reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
+ } else {
+ reg_list = fec_enet_register_offset_6ul;
+ reg_cnt = ARRAY_SIZE(fec_enet_register_offset_6ul);
+ }
+#else
+ /* coldfire */
+ static u32 *reg_list = fec_enet_register_offset;
+ static const u32 reg_cnt = ARRAY_SIZE(fec_enet_register_offset);
+#endif
ret = pm_runtime_resume_and_get(dev);
if (ret < 0)
return;
@@ -2465,8 +2507,8 @@ static void fec_enet_get_regs(struct net_device *ndev,
memset(buf, 0, regs->len);
- for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
- off = fec_enet_register_offset[i];
+ for (i = 0; i < reg_cnt; i++) {
+ off = reg_list[i];
if ((off == FEC_R_BOUND || off == FEC_R_FSTART) &&
!(fep->quirks & FEC_QUIRK_HAS_FRREG))
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 7b7526fd7da3..65df308bad97 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -279,7 +279,6 @@ static int mac_probe(struct platform_device *_of_dev)
struct device_node *mac_node, *dev_node;
struct mac_device *mac_dev;
struct platform_device *of_dev;
- struct resource *res;
struct mac_priv_s *priv;
struct fman_mac_params params;
u32 val;
@@ -338,24 +337,25 @@ static int mac_probe(struct platform_device *_of_dev)
of_node_put(dev_node);
/* Get the address of the memory mapped registers */
- res = platform_get_mem_or_io(_of_dev, 0);
- if (!res) {
+ mac_dev->res = platform_get_mem_or_io(_of_dev, 0);
+ if (!mac_dev->res) {
dev_err(dev, "could not get registers\n");
return -EINVAL;
}
- err = devm_request_resource(dev, fman_get_mem_region(priv->fman), res);
+ err = devm_request_resource(dev, fman_get_mem_region(priv->fman),
+ mac_dev->res);
if (err) {
dev_err_probe(dev, err, "could not request resource\n");
return err;
}
- mac_dev->vaddr = devm_ioremap(dev, res->start, resource_size(res));
+ mac_dev->vaddr = devm_ioremap(dev, mac_dev->res->start,
+ resource_size(mac_dev->res));
if (!mac_dev->vaddr) {
dev_err(dev, "devm_ioremap() failed\n");
return -EIO;
}
- mac_dev->vaddr_end = mac_dev->vaddr + resource_size(res);
if (!of_device_is_available(mac_node))
return -ENODEV;
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index b95d384271bd..13b69ca5f00c 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -20,8 +20,8 @@ struct mac_priv_s;
struct mac_device {
void __iomem *vaddr;
- void __iomem *vaddr_end;
struct device *dev;
+ struct resource *res;
u8 addr[ETH_ALEN];
struct fman_port *port[2];
u32 if_support;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c
index 19eb839177ec..061952c6c21a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_debugfs.c
@@ -85,6 +85,7 @@ static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx)
struct tag_sml_funcfg_tbl *funcfg_table_elem;
struct hinic_cmd_lt_rd *read_data;
u16 out_size = sizeof(*read_data);
+ int ret = ~0;
int err;
read_data = kzalloc(sizeof(*read_data), GFP_KERNEL);
@@ -111,20 +112,25 @@ static int hinic_dbg_get_func_table(struct hinic_dev *nic_dev, int idx)
switch (idx) {
case VALID:
- return funcfg_table_elem->dw0.bs.valid;
+ ret = funcfg_table_elem->dw0.bs.valid;
+ break;
case RX_MODE:
- return funcfg_table_elem->dw0.bs.nic_rx_mode;
+ ret = funcfg_table_elem->dw0.bs.nic_rx_mode;
+ break;
case MTU:
- return funcfg_table_elem->dw1.bs.mtu;
+ ret = funcfg_table_elem->dw1.bs.mtu;
+ break;
case RQ_DEPTH:
- return funcfg_table_elem->dw13.bs.cfg_rq_depth;
+ ret = funcfg_table_elem->dw13.bs.cfg_rq_depth;
+ break;
case QUEUE_NUM:
- return funcfg_table_elem->dw13.bs.cfg_q_num;
+ ret = funcfg_table_elem->dw13.bs.cfg_q_num;
+ break;
}
kfree(read_data);
- return ~0;
+ return ret;
}
static ssize_t hinic_dbg_cmd_read(struct file *filp, char __user *buffer, size_t count,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
index 78190e88cd75..d39eec9c62bf 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c
@@ -924,7 +924,7 @@ int hinic_init_cmdqs(struct hinic_cmdqs *cmdqs, struct hinic_hwif *hwif,
err_set_cmdq_depth:
hinic_ceq_unregister_cb(&func_to_io->ceqs, HINIC_CEQ_CMDQ);
-
+ free_cmdq(&cmdqs->cmdq[HINIC_CMDQ_SYNC]);
err_cmdq_ctxt:
hinic_wqs_cmdq_free(&cmdqs->cmdq_pages, cmdqs->saved_wqs,
HINIC_MAX_CMDQ_TYPES);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 94f470556295..27795288c586 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -877,7 +877,7 @@ int hinic_set_interrupt_cfg(struct hinic_hwdev *hwdev,
if (err)
return -EINVAL;
- interrupt_info->lli_credit_cnt = temp_info.lli_timer_cnt;
+ interrupt_info->lli_credit_cnt = temp_info.lli_credit_cnt;
interrupt_info->lli_timer_cnt = temp_info.lli_timer_cnt;
err = hinic_msg_to_mgmt(&pfhwdev->pf_to_mgmt, HINIC_MOD_COMM,
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
index a5f08b969e3f..f7e05b41385b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_sriov.c
@@ -1174,7 +1174,6 @@ int hinic_vf_func_init(struct hinic_hwdev *hwdev)
dev_err(&hwdev->hwif->pdev->dev,
"Failed to register VF, err: %d, status: 0x%x, out size: 0x%x\n",
err, register_info.status, out_size);
- hinic_unregister_vf_mbox_cb(hwdev, HINIC_MOD_L2NIC);
return -EIO;
}
} else {
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 294bdbbeacc3..b4aff59b3eb4 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -2900,6 +2900,7 @@ static struct device *ehea_register_port(struct ehea_port *port,
ret = of_device_register(&port->ofdev);
if (ret) {
pr_err("failed to register device. ret=%d\n", ret);
+ put_device(&port->ofdev.dev);
goto out;
}
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 65dbfbec487a..9282381a438f 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -3007,19 +3007,19 @@ static void __ibmvnic_reset(struct work_struct *work)
rwi = get_next_rwi(adapter);
/*
- * If there is another reset queued, free the previous rwi
- * and process the new reset even if previous reset failed
- * (the previous reset could have failed because of a fail
- * over for instance, so process the fail over).
- *
* If there are no resets queued and the previous reset failed,
* the adapter would be in an undefined state. So retry the
* previous reset as a hard reset.
+ *
+ * Else, free the previous rwi and, if there is another reset
+ * queued, process the new reset even if previous reset failed
+ * (the previous reset could have failed because of a fail
+ * over for instance, so process the fail over).
*/
- if (rwi)
- kfree(tmprwi);
- else if (rc)
+ if (!rwi && rc)
rwi = tmprwi;
+ else
+ kfree(tmprwi);
if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER ||
rwi->reset_reason == VNIC_RESET_MOBILITY || rc))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 87f36d1ce800..4a6a6e48c615 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -3185,10 +3185,17 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
if (cmd->flow_type == TCP_V4_FLOW ||
cmd->flow_type == UDP_V4_FLOW) {
- if (i_set & I40E_L3_SRC_MASK)
- cmd->data |= RXH_IP_SRC;
- if (i_set & I40E_L3_DST_MASK)
- cmd->data |= RXH_IP_DST;
+ if (hw->mac.type == I40E_MAC_X722) {
+ if (i_set & I40E_X722_L3_SRC_MASK)
+ cmd->data |= RXH_IP_SRC;
+ if (i_set & I40E_X722_L3_DST_MASK)
+ cmd->data |= RXH_IP_DST;
+ } else {
+ if (i_set & I40E_L3_SRC_MASK)
+ cmd->data |= RXH_IP_SRC;
+ if (i_set & I40E_L3_DST_MASK)
+ cmd->data |= RXH_IP_DST;
+ }
} else if (cmd->flow_type == TCP_V6_FLOW ||
cmd->flow_type == UDP_V6_FLOW) {
if (i_set & I40E_L3_V6_SRC_MASK)
@@ -3546,12 +3553,15 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd,
/**
* i40e_get_rss_hash_bits - Read RSS Hash bits from register
+ * @hw: hw structure
* @nfc: pointer to user request
* @i_setc: bits currently set
*
* Returns value of bits to be set per user request
**/
-static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
+static u64 i40e_get_rss_hash_bits(struct i40e_hw *hw,
+ struct ethtool_rxnfc *nfc,
+ u64 i_setc)
{
u64 i_set = i_setc;
u64 src_l3 = 0, dst_l3 = 0;
@@ -3570,8 +3580,13 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
dst_l3 = I40E_L3_V6_DST_MASK;
} else if (nfc->flow_type == TCP_V4_FLOW ||
nfc->flow_type == UDP_V4_FLOW) {
- src_l3 = I40E_L3_SRC_MASK;
- dst_l3 = I40E_L3_DST_MASK;
+ if (hw->mac.type == I40E_MAC_X722) {
+ src_l3 = I40E_X722_L3_SRC_MASK;
+ dst_l3 = I40E_X722_L3_DST_MASK;
+ } else {
+ src_l3 = I40E_L3_SRC_MASK;
+ dst_l3 = I40E_L3_DST_MASK;
+ }
} else {
/* Any other flow type are not supported here */
return i_set;
@@ -3589,6 +3604,7 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc)
return i_set;
}
+#define FLOW_PCTYPES_SIZE 64
/**
* i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash
* @pf: pointer to the physical function struct
@@ -3601,9 +3617,11 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
struct i40e_hw *hw = &pf->hw;
u64 hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
- u8 flow_pctype = 0;
+ DECLARE_BITMAP(flow_pctypes, FLOW_PCTYPES_SIZE);
u64 i_set, i_setc;
+ bitmap_zero(flow_pctypes, FLOW_PCTYPES_SIZE);
+
if (pf->flags & I40E_FLAG_MFP_ENABLED) {
dev_err(&pf->pdev->dev,
"Change of RSS hash input set is not supported when MFP mode is enabled\n");
@@ -3619,36 +3637,35 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
switch (nfc->flow_type) {
case TCP_V4_FLOW:
- flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
- hena |=
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
+ flow_pctypes);
break;
case TCP_V6_FLOW:
- flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
- if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
- hena |=
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK);
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
- hena |=
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK);
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
+ flow_pctypes);
break;
case UDP_V4_FLOW:
- flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
- if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
- hena |=
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP);
-
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
+ if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+ set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
+ flow_pctypes);
+ set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
+ flow_pctypes);
+ }
hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
break;
case UDP_V6_FLOW:
- flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
- if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE)
- hena |=
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) |
- BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP);
-
+ set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
+ if (pf->hw_features & I40E_HW_MULTIPLE_TCP_UDP_RSS_PCTYPE) {
+ set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
+ flow_pctypes);
+ set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
+ flow_pctypes);
+ }
hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
break;
case AH_ESP_V4_FLOW:
@@ -3681,17 +3698,20 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
return -EINVAL;
}
- if (flow_pctype) {
- i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0,
- flow_pctype)) |
- ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1,
- flow_pctype)) << 32);
- i_set = i40e_get_rss_hash_bits(nfc, i_setc);
- i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_pctype),
- (u32)i_set);
- i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_pctype),
- (u32)(i_set >> 32));
- hena |= BIT_ULL(flow_pctype);
+ if (bitmap_weight(flow_pctypes, FLOW_PCTYPES_SIZE)) {
+ u8 flow_id;
+
+ for_each_set_bit(flow_id, flow_pctypes, FLOW_PCTYPES_SIZE) {
+ i_setc = (u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id)) |
+ ((u64)i40e_read_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id)) << 32);
+ i_set = i40e_get_rss_hash_bits(&pf->hw, nfc, i_setc);
+
+ i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(0, flow_id),
+ (u32)i_set);
+ i40e_write_rx_ctl(hw, I40E_GLQF_HASH_INSET(1, flow_id),
+ (u32)(i_set >> 32));
+ hena |= BIT_ULL(flow_id);
+ }
}
i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 7b3f30beb757..388c3d36d96a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -1404,6 +1404,10 @@ struct i40e_lldp_variables {
#define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000
/* INPUT SET MASK for RSS, flow director, and flexible payload */
+#define I40E_X722_L3_SRC_SHIFT 49
+#define I40E_X722_L3_SRC_MASK (0x3ULL << I40E_X722_L3_SRC_SHIFT)
+#define I40E_X722_L3_DST_SHIFT 41
+#define I40E_X722_L3_DST_MASK (0x3ULL << I40E_X722_L3_DST_SHIFT)
#define I40E_L3_SRC_SHIFT 47
#define I40E_L3_SRC_MASK (0x3ULL << I40E_L3_SRC_SHIFT)
#define I40E_L3_V6_SRC_SHIFT 43
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 7e9f6a69eb10..72ddcefc45b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1536,10 +1536,12 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
if (test_bit(__I40E_VF_RESETS_DISABLED, pf->state))
return true;
- /* If the VFs have been disabled, this means something else is
- * resetting the VF, so we shouldn't continue.
- */
- if (test_and_set_bit(__I40E_VF_DISABLE, pf->state))
+ /* Bail out if VFs are disabled. */
+ if (test_bit(__I40E_VF_DISABLE, pf->state))
+ return true;
+
+ /* If VF is being reset already we don't need to continue. */
+ if (test_and_set_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
return true;
i40e_trigger_vf_reset(vf, flr);
@@ -1576,7 +1578,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
i40e_cleanup_reset_vf(vf);
i40e_flush(hw);
- clear_bit(__I40E_VF_DISABLE, pf->state);
+ clear_bit(I40E_VF_STATE_RESETTING, &vf->vf_states);
return true;
}
@@ -1609,8 +1611,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
return false;
/* Begin reset on all VFs at once */
- for (v = 0; v < pf->num_alloc_vfs; v++)
- i40e_trigger_vf_reset(&pf->vf[v], flr);
+ for (v = 0; v < pf->num_alloc_vfs; v++) {
+ vf = &pf->vf[v];
+ /* If VF is being reset no need to trigger reset again */
+ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+ i40e_trigger_vf_reset(&pf->vf[v], flr);
+ }
/* HW requires some time to make sure it can flush the FIFO for a VF
* when it resets it. Poll the VPGEN_VFRSTAT register for each VF in
@@ -1626,9 +1632,11 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
*/
while (v < pf->num_alloc_vfs) {
vf = &pf->vf[v];
- reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
- if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
- break;
+ if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) {
+ reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
+ if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
+ break;
+ }
/* If the current VF has finished resetting, move on
* to the next VF in sequence.
@@ -1656,6 +1664,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
if (pf->vf[v].lan_vsi_idx == 0)
continue;
+ /* If VF is reset in another thread just continue */
+ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+ continue;
+
i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
}
@@ -1667,6 +1679,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
if (pf->vf[v].lan_vsi_idx == 0)
continue;
+ /* If VF is reset in another thread just continue */
+ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+ continue;
+
i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
}
@@ -1676,8 +1692,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr)
mdelay(50);
/* Finish the reset on each VF */
- for (v = 0; v < pf->num_alloc_vfs; v++)
+ for (v = 0; v < pf->num_alloc_vfs; v++) {
+ /* If VF is reset in another thread just continue */
+ if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
+ continue;
+
i40e_cleanup_reset_vf(&pf->vf[v]);
+ }
i40e_flush(hw);
clear_bit(__I40E_VF_DISABLE, pf->state);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index a554d0a0b09b..358bbdb58795 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -39,6 +39,7 @@ enum i40e_vf_states {
I40E_VF_STATE_MC_PROMISC,
I40E_VF_STATE_UC_PROMISC,
I40E_VF_STATE_PRE_ENABLE,
+ I40E_VF_STATE_RESETTING
};
/* VF capabilities */
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 59aab4086dcc..f5961bdcc480 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -485,7 +485,6 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev)
len = skb->len < ETH_ZLEN ? ETH_ZLEN : skb->len;
if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) {
- dev_kfree_skb_any(skb);
netdev_err(dev, "tx ring full\n");
netif_tx_stop_queue(txq);
return NETDEV_TX_BUSY;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 0377392848d9..46ba4c2faad2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2004,7 +2004,7 @@ void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
ctx->dev = dev;
/* Starts at 1 to avoid doing wake_up if we are not cleaning up */
atomic_set(&ctx->num_inflight, 1);
- init_waitqueue_head(&ctx->wait);
+ init_completion(&ctx->inflight_done);
}
EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
@@ -2018,8 +2018,8 @@ EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
*/
void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx)
{
- atomic_dec(&ctx->num_inflight);
- wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0);
+ if (!atomic_dec_and_test(&ctx->num_inflight))
+ wait_for_completion(&ctx->inflight_done);
}
EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);
@@ -2032,7 +2032,7 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
status = cmd_status_err(ctx->dev, status, work->opcode, work->out);
work->user_callback(status, work);
if (atomic_dec_and_test(&ctx->num_inflight))
- wake_up(&ctx->wait);
+ complete(&ctx->inflight_done);
}
int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
@@ -2050,7 +2050,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
mlx5_cmd_exec_cb_handler, work, false);
if (ret && atomic_dec_and_test(&ctx->num_inflight))
- wake_up(&ctx->wait);
+ complete(&ctx->inflight_done);
return ret;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 5bce554e131a..cc7efde88ac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -6,6 +6,7 @@
#include "en.h"
#include "en_stats.h"
+#include "en/txrx.h"
#include <linux/ptp_classify.h>
#define MLX5E_PTP_CHANNEL_IX 0
@@ -68,6 +69,14 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
fk.ports.dst == htons(PTP_EV_PORT));
}
+static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq)
+{
+ if (!sq->ptpsq)
+ return true;
+
+ return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo);
+}
+
int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
u8 lag_port, struct mlx5e_ptp **cp);
void mlx5e_ptp_close(struct mlx5e_ptp *c);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
index 10c9a8a79d00..2e42d7c5451e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_priv.h
@@ -96,6 +96,7 @@ struct mlx5e_tc_flow {
struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
struct mlx5e_tc_flow *peer_flow;
struct mlx5e_mod_hdr_handle *mh; /* attached mod header instance */
+ struct mlx5e_mod_hdr_handle *slow_mh; /* attached mod header instance for slow path */
struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */
struct list_head hairpin; /* flows sharing the same hairpin */
struct list_head peer; /* flows with peer flow */
@@ -111,6 +112,7 @@ struct mlx5e_tc_flow {
struct completion del_hw_done;
struct mlx5_flow_attr *attr;
struct list_head attrs;
+ u32 chain_mapping;
};
struct mlx5_flow_handle *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 4456ad5cedf1..cb164b62f543 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -58,6 +58,12 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
static inline bool
+mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo)
+{
+ return (*fifo->pc - *fifo->cc) < fifo->mask;
+}
+
+static inline bool
mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
{
return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 2a8fd7020622..a715601865d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -101,7 +101,6 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
struct xfrm_replay_state_esn *replay_esn;
u32 seq_bottom = 0;
u8 overlap;
- u32 *esn;
if (!(sa_entry->x->props.flags & XFRM_STATE_ESN)) {
sa_entry->esn_state.trigger = 0;
@@ -116,11 +115,9 @@ static bool mlx5e_ipsec_update_esn_state(struct mlx5e_ipsec_sa_entry *sa_entry)
sa_entry->esn_state.esn = xfrm_replay_seqhi(sa_entry->x,
htonl(seq_bottom));
- esn = &sa_entry->esn_state.esn;
sa_entry->esn_state.trigger = 1;
if (unlikely(overlap && seq_bottom < MLX5E_IPSEC_ESN_SCOPE_MID)) {
- ++(*esn);
sa_entry->esn_state.overlap = 0;
return true;
} else if (unlikely(!overlap &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
index 41970067917b..2ef36cb9555a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c
@@ -432,7 +432,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec,
bool active)
{
struct mlx5_core_dev *mdev = macsec->mdev;
- struct mlx5_macsec_obj_attrs attrs;
+ struct mlx5_macsec_obj_attrs attrs = {};
int err = 0;
if (rx_sa->active != active)
@@ -444,7 +444,7 @@ static int mlx5e_macsec_update_rx_sa(struct mlx5e_macsec *macsec,
return 0;
}
- attrs.sci = rx_sa->sci;
+ attrs.sci = cpu_to_be64((__force u64)rx_sa->sci);
attrs.enc_key_id = rx_sa->enc_key_id;
err = mlx5e_macsec_create_object(mdev, &attrs, false, &rx_sa->macsec_obj_id);
if (err)
@@ -999,11 +999,11 @@ static int mlx5e_macsec_upd_rxsa(struct macsec_context *ctx)
}
rx_sa = rx_sc->rx_sa[assoc_num];
- if (rx_sa) {
+ if (!rx_sa) {
netdev_err(ctx->netdev,
- "MACsec offload rx_sc sci %lld rx_sa %d already exist\n",
+ "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n",
sci, assoc_num);
- err = -EEXIST;
+ err = -EINVAL;
goto out;
}
@@ -1055,11 +1055,11 @@ static int mlx5e_macsec_del_rxsa(struct macsec_context *ctx)
}
rx_sa = rx_sc->rx_sa[assoc_num];
- if (rx_sa) {
+ if (!rx_sa) {
netdev_err(ctx->netdev,
- "MACsec offload rx_sc sci %lld rx_sa %d already exist\n",
+ "MACsec offload rx_sc sci %lld rx_sa %d doesn't exist\n",
sci, assoc_num);
- err = -EEXIST;
+ err = -EINVAL;
goto out;
}
@@ -1846,25 +1846,16 @@ err_hash:
void mlx5e_macsec_cleanup(struct mlx5e_priv *priv)
{
struct mlx5e_macsec *macsec = priv->macsec;
- struct mlx5_core_dev *mdev = macsec->mdev;
+ struct mlx5_core_dev *mdev = priv->mdev;
if (!macsec)
return;
mlx5_notifier_unregister(mdev, &macsec->nb);
-
mlx5e_macsec_fs_cleanup(macsec->macsec_fs);
-
- /* Cleanup workqueue */
destroy_workqueue(macsec->wq);
-
mlx5e_macsec_aso_cleanup(&macsec->aso, mdev);
-
- priv->macsec = NULL;
-
rhashtable_destroy(&macsec->sci_hash);
-
mutex_destroy(&macsec->lock);
-
kfree(macsec);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
index 13dc628b988a..1ac0cf04e811 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec_fs.c
@@ -1180,7 +1180,7 @@ macsec_fs_rx_add_rule(struct mlx5e_macsec_fs *macsec_fs,
rx_rule->rule[0] = rule;
/* Rx crypto table without SCI rule */
- if (cpu_to_be64((__force u64)attrs->sci) & ntohs(MACSEC_PORT_ES)) {
+ if ((cpu_to_be64((__force u64)attrs->sci) & 0xFFFF) == ntohs(MACSEC_PORT_ES)) {
memset(spec, 0, sizeof(struct mlx5_flow_spec));
memset(&dest, 0, sizeof(struct mlx5_flow_destination));
memset(&flow_act, 0, sizeof(flow_act));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 70a7a61f9708..dd6fea9e9a5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1405,8 +1405,13 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
struct mlx5e_tc_flow *flow,
struct mlx5_flow_spec *spec)
{
+ struct mlx5e_tc_mod_hdr_acts mod_acts = {};
+ struct mlx5e_mod_hdr_handle *mh = NULL;
struct mlx5_flow_attr *slow_attr;
struct mlx5_flow_handle *rule;
+ bool fwd_and_modify_cap;
+ u32 chain_mapping = 0;
+ int err;
slow_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
if (!slow_attr)
@@ -1417,13 +1422,56 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
slow_attr->esw_attr->split_count = 0;
slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
+ fwd_and_modify_cap = MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table);
+ if (!fwd_and_modify_cap)
+ goto skip_restore;
+
+ err = mlx5_chains_get_chain_mapping(esw_chains(esw), flow->attr->chain, &chain_mapping);
+ if (err)
+ goto err_get_chain;
+
+ err = mlx5e_tc_match_to_reg_set(esw->dev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB,
+ CHAIN_TO_REG, chain_mapping);
+ if (err)
+ goto err_reg_set;
+
+ mh = mlx5e_mod_hdr_attach(esw->dev, get_mod_hdr_table(flow->priv, flow),
+ MLX5_FLOW_NAMESPACE_FDB, &mod_acts);
+ if (IS_ERR(mh)) {
+ err = PTR_ERR(mh);
+ goto err_attach;
+ }
+
+ slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ slow_attr->modify_hdr = mlx5e_mod_hdr_get(mh);
+
+skip_restore:
rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
- if (!IS_ERR(rule))
- flow_flag_set(flow, SLOW);
+ if (IS_ERR(rule)) {
+ err = PTR_ERR(rule);
+ goto err_offload;
+ }
+ flow->slow_mh = mh;
+ flow->chain_mapping = chain_mapping;
+ flow_flag_set(flow, SLOW);
+
+ mlx5e_mod_hdr_dealloc(&mod_acts);
kfree(slow_attr);
return rule;
+
+err_offload:
+ if (fwd_and_modify_cap)
+ mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), mh);
+err_attach:
+err_reg_set:
+ if (fwd_and_modify_cap)
+ mlx5_chains_put_chain_mapping(esw_chains(esw), chain_mapping);
+err_get_chain:
+ mlx5e_mod_hdr_dealloc(&mod_acts);
+ kfree(slow_attr);
+ return ERR_PTR(err);
}
void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
@@ -1441,7 +1489,17 @@ void mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
slow_attr->esw_attr->split_count = 0;
slow_attr->flags |= MLX5_ATTR_FLAG_SLOW_PATH;
+ if (flow->slow_mh) {
+ slow_attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+ slow_attr->modify_hdr = mlx5e_mod_hdr_get(flow->slow_mh);
+ }
mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
+ if (flow->slow_mh) {
+ mlx5e_mod_hdr_detach(esw->dev, get_mod_hdr_table(flow->priv, flow), flow->slow_mh);
+ mlx5_chains_put_chain_mapping(esw_chains(esw), flow->chain_mapping);
+ flow->chain_mapping = 0;
+ flow->slow_mh = NULL;
+ }
flow_flag_clear(flow, SLOW);
kfree(slow_attr);
}
@@ -3575,6 +3633,10 @@ mlx5e_clone_flow_attr_for_post_act(struct mlx5_flow_attr *attr,
attr2->action = 0;
attr2->flags = 0;
attr2->parse_attr = parse_attr;
+ attr2->esw_attr->out_count = 0;
+ attr2->esw_attr->split_count = 0;
+ attr2->dest_chain = 0;
+ attr2->dest_ft = NULL;
return attr2;
}
@@ -4008,6 +4070,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,
struct mlx5e_tc_flow_parse_attr *parse_attr;
struct mlx5_flow_attr *attr = flow->attr;
struct mlx5_esw_flow_attr *esw_attr;
+ struct net_device *filter_dev;
int err;
err = flow_action_supported(flow_action, extack);
@@ -4016,6 +4079,7 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,
esw_attr = attr->esw_attr;
parse_attr = attr->parse_attr;
+ filter_dev = parse_attr->filter_dev;
parse_state = &parse_attr->parse_state;
mlx5e_tc_act_init_parse_state(parse_state, flow, flow_action, extack);
parse_state->ct_priv = get_ct_priv(priv);
@@ -4025,13 +4089,21 @@ parse_tc_fdb_actions(struct mlx5e_priv *priv,
return err;
/* Forward to/from internal port can only have 1 dest */
- if ((netif_is_ovs_master(parse_attr->filter_dev) || esw_attr->dest_int_port) &&
+ if ((netif_is_ovs_master(filter_dev) || esw_attr->dest_int_port) &&
esw_attr->out_count > 1) {
NL_SET_ERR_MSG_MOD(extack,
"Rules with internal port can have only one destination");
return -EOPNOTSUPP;
}
+ /* Forward from tunnel/internal port to internal port is not supported */
+ if ((mlx5e_get_tc_tun(filter_dev) || netif_is_ovs_master(filter_dev)) &&
+ esw_attr->dest_int_port) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Forwarding from tunnel/internal port to internal port is not supported");
+ return -EOPNOTSUPP;
+ }
+
err = actions_prepare_mod_hdr_actions(priv, flow, attr, extack);
if (err)
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index bf2232a2a836..6adca01fbdc9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -392,6 +392,11 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
if (unlikely(sq->ptpsq)) {
mlx5e_skb_cb_hwtstamp_init(skb);
mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb);
+ if (!netif_tx_queue_stopped(sq->txq) &&
+ !mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo)) {
+ netif_tx_stop_queue(sq->txq);
+ sq->stats->stopped++;
+ }
skb_get(skb);
}
@@ -868,6 +873,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
if (netif_tx_queue_stopped(sq->txq) &&
mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) &&
+ mlx5e_ptpsq_fifo_has_room(sq) &&
!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
netif_tx_wake_queue(sq->txq);
stats->wake++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index e8896f368362..07c583996c29 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -358,6 +358,23 @@ static int mlx5_pci_link_toggle(struct mlx5_core_dev *dev)
err = -ETIMEDOUT;
}
+ do {
+ err = pci_read_config_word(dev->pdev, PCI_DEVICE_ID, &reg16);
+ if (err)
+ return err;
+ if (reg16 == dev_id)
+ break;
+ msleep(20);
+ } while (!time_after(jiffies, timeout));
+
+ if (reg16 == dev_id) {
+ mlx5_core_info(dev, "Firmware responds to PCI config cycles again\n");
+ } else {
+ mlx5_core_err(dev, "Firmware is not responsive (0x%04x) after %llu ms\n",
+ reg16, mlx5_tout_ms(dev, PCI_TOGGLE));
+ err = -ETIMEDOUT;
+ }
+
restore:
list_for_each_entry(sdev, &bridge_bus->devices, bus_list) {
pci_cfg_access_unlock(sdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
index baa8092f335e..c971ff04dd04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/aso.c
@@ -3,6 +3,7 @@
#include <linux/mlx5/device.h>
#include <linux/mlx5/transobj.h>
+#include "clock.h"
#include "aso.h"
#include "wq.h"
@@ -179,6 +180,7 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn,
{
void *in, *sqc, *wq;
int inlen, err;
+ u8 ts_format;
inlen = MLX5_ST_SZ_BYTES(create_sq_in) +
sizeof(u64) * sq->wq_ctrl.buf.npages;
@@ -195,6 +197,11 @@ static int create_aso_sq(struct mlx5_core_dev *mdev, int pdn,
MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+ ts_format = mlx5_is_real_time_sq(mdev) ?
+ MLX5_TIMESTAMP_FORMAT_REAL_TIME :
+ MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
+ MLX5_SET(sqc, sqc, ts_format, ts_format);
+
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
MLX5_SET(wq, wq, uar_page, mdev->mlx5e_res.hw_objs.bfreg.index);
MLX5_SET(wq, wq, log_wq_pg_sz, sq->wq_ctrl.buf.page_shift -
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 839a01da110f..8ff16318e32d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -122,7 +122,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
{
struct mlx5_mpfs *mpfs = dev->priv.mpfs;
- if (!MLX5_ESWITCH_MANAGER(dev))
+ if (!mpfs)
return;
WARN_ON(!hlist_empty(mpfs->hash));
@@ -137,7 +137,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
int err = 0;
u32 index;
- if (!MLX5_ESWITCH_MANAGER(dev))
+ if (!mpfs)
return 0;
mutex_lock(&mpfs->lock);
@@ -185,7 +185,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
int err = 0;
u32 index;
- if (!MLX5_ESWITCH_MANAGER(dev))
+ if (!mpfs)
return 0;
mutex_lock(&mpfs->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 0b459d841c3a..283c4cc28944 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1872,6 +1872,10 @@ static void mlx5_pci_resume(struct pci_dev *pdev)
err = mlx5_load_one(dev, false);
+ if (!err)
+ devlink_health_reporter_state_update(dev->priv.health.fw_fatal_reporter,
+ DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
mlx5_pci_trace(dev, "Done, err = %d, device %s\n", err,
!err ? "recovered" : "Failed");
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index ddfaf7891188..91ff19f67695 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -1200,7 +1200,8 @@ free_rule:
}
remove_from_nic_tbl:
- mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher);
+ if (!nic_matcher->rules)
+ mlx5dr_matcher_remove_from_tbl_nic(dmn, nic_matcher);
free_hw_ste:
mlx5dr_domain_nic_unlock(nic_dmn);
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 468520079c65..e6acd1e7b263 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -6851,7 +6851,7 @@ static int pcidev_init(struct pci_dev *pdev, const struct pci_device_id *id)
char banner[sizeof(version)];
struct ksz_switch *sw = NULL;
- result = pci_enable_device(pdev);
+ result = pcim_enable_device(pdev);
if (result)
return result;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
index e58a27fd8b50..fea42542be28 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_ethtool.c
@@ -656,7 +656,15 @@ void lan966x_stats_get(struct net_device *dev,
stats->rx_dropped = dev->stats.rx_dropped +
lan966x->stats[idx + SYS_COUNT_RX_LONG] +
lan966x->stats[idx + SYS_COUNT_DR_LOCAL] +
- lan966x->stats[idx + SYS_COUNT_DR_TAIL];
+ lan966x->stats[idx + SYS_COUNT_DR_TAIL] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_0] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_1] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_2] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_3] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_4] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_5] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_6] +
+ lan966x->stats[idx + SYS_COUNT_RX_RED_PRIO_7];
for (i = 0; i < LAN966X_NUM_TC; i++) {
stats->rx_dropped +=
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
index 7e4061c854f0..e6948939ccc2 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_fdma.c
@@ -309,6 +309,7 @@ static void lan966x_fdma_tx_disable(struct lan966x_tx *tx)
lan966x, FDMA_CH_DB_DISCARD);
tx->activated = false;
+ tx->last_in_use = -1;
}
static void lan966x_fdma_tx_reload(struct lan966x_tx *tx)
@@ -413,13 +414,15 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx)
/* Get the received frame and unmap it */
db = &rx->dcbs[rx->dcb_index].db[rx->db_index];
page = rx->page[rx->dcb_index][rx->db_index];
+
+ dma_sync_single_for_cpu(lan966x->dev, (dma_addr_t)db->dataptr,
+ FDMA_DCB_STATUS_BLOCKL(db->status),
+ DMA_FROM_DEVICE);
+
skb = build_skb(page_address(page), PAGE_SIZE << rx->page_order);
if (unlikely(!skb))
goto unmap_page;
- dma_unmap_single(lan966x->dev, (dma_addr_t)db->dataptr,
- FDMA_DCB_STATUS_BLOCKL(db->status),
- DMA_FROM_DEVICE);
skb_put(skb, FDMA_DCB_STATUS_BLOCKL(db->status));
lan966x_ifh_get_src_port(skb->data, &src_port);
@@ -428,6 +431,10 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx)
if (WARN_ON(src_port >= lan966x->num_phys_ports))
goto free_skb;
+ dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr,
+ PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+
skb->dev = lan966x->ports[src_port]->dev;
skb_pull(skb, IFH_LEN * sizeof(u32));
@@ -453,9 +460,9 @@ static struct sk_buff *lan966x_fdma_rx_get_frame(struct lan966x_rx *rx)
free_skb:
kfree_skb(skb);
unmap_page:
- dma_unmap_page(lan966x->dev, (dma_addr_t)db->dataptr,
- FDMA_DCB_STATUS_BLOCKL(db->status),
- DMA_FROM_DEVICE);
+ dma_unmap_single_attrs(lan966x->dev, (dma_addr_t)db->dataptr,
+ PAGE_SIZE << rx->page_order, DMA_FROM_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
__free_pages(page, rx->page_order);
return NULL;
@@ -667,12 +674,14 @@ static int lan966x_fdma_get_max_mtu(struct lan966x *lan966x)
int i;
for (i = 0; i < lan966x->num_phys_ports; ++i) {
+ struct lan966x_port *port;
int mtu;
- if (!lan966x->ports[i])
+ port = lan966x->ports[i];
+ if (!port)
continue;
- mtu = lan966x->ports[i]->dev->mtu;
+ mtu = lan_rd(lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port));
if (mtu > max_mtu)
max_mtu = mtu;
}
@@ -687,17 +696,14 @@ static int lan966x_qsys_sw_status(struct lan966x *lan966x)
static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
{
- void *rx_dcbs, *tx_dcbs, *tx_dcbs_buf;
- dma_addr_t rx_dma, tx_dma;
+ dma_addr_t rx_dma;
+ void *rx_dcbs;
u32 size;
int err;
/* Store these for later to free them */
rx_dma = lan966x->rx.dma;
- tx_dma = lan966x->tx.dma;
rx_dcbs = lan966x->rx.dcbs;
- tx_dcbs = lan966x->tx.dcbs;
- tx_dcbs_buf = lan966x->tx.dcbs_buf;
napi_synchronize(&lan966x->napi);
napi_disable(&lan966x->napi);
@@ -715,17 +721,6 @@ static int lan966x_fdma_reload(struct lan966x *lan966x, int new_mtu)
size = ALIGN(size, PAGE_SIZE);
dma_free_coherent(lan966x->dev, size, rx_dcbs, rx_dma);
- lan966x_fdma_tx_disable(&lan966x->tx);
- err = lan966x_fdma_tx_alloc(&lan966x->tx);
- if (err)
- goto restore_tx;
-
- size = sizeof(struct lan966x_tx_dcb) * FDMA_DCB_MAX;
- size = ALIGN(size, PAGE_SIZE);
- dma_free_coherent(lan966x->dev, size, tx_dcbs, tx_dma);
-
- kfree(tx_dcbs_buf);
-
lan966x_fdma_wakeup_netdev(lan966x);
napi_enable(&lan966x->napi);
@@ -735,11 +730,6 @@ restore:
lan966x->rx.dcbs = rx_dcbs;
lan966x_fdma_rx_start(&lan966x->rx);
-restore_tx:
- lan966x->tx.dma = tx_dma;
- lan966x->tx.dcbs = tx_dcbs;
- lan966x->tx.dcbs_buf = tx_dcbs_buf;
-
return err;
}
@@ -751,6 +741,8 @@ int lan966x_fdma_change_mtu(struct lan966x *lan966x)
max_mtu = lan966x_fdma_get_max_mtu(lan966x);
max_mtu += IFH_LEN * sizeof(u32);
+ max_mtu += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+ max_mtu += VLAN_HLEN * 2;
if (round_up(max_mtu, PAGE_SIZE) / PAGE_SIZE - 1 ==
lan966x->rx.page_order)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index be2fd030cccb..20ee5b28f70a 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -386,7 +386,7 @@ static int lan966x_port_change_mtu(struct net_device *dev, int new_mtu)
int old_mtu = dev->mtu;
int err;
- lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(new_mtu),
+ lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(LAN966X_HW_MTU(new_mtu)),
lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port));
dev->mtu = new_mtu;
@@ -395,7 +395,7 @@ static int lan966x_port_change_mtu(struct net_device *dev, int new_mtu)
err = lan966x_fdma_change_mtu(lan966x);
if (err) {
- lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(old_mtu),
+ lan_wr(DEV_MAC_MAXLEN_CFG_MAX_LEN_SET(LAN966X_HW_MTU(old_mtu)),
lan966x, DEV_MAC_MAXLEN_CFG(port->chip_port));
dev->mtu = old_mtu;
}
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
index 9656071b8289..4ec33999e4df 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.h
@@ -26,6 +26,8 @@
#define LAN966X_BUFFER_MEMORY (160 * 1024)
#define LAN966X_BUFFER_MIN_SZ 60
+#define LAN966X_HW_MTU(mtu) ((mtu) + ETH_HLEN + ETH_FCS_LEN)
+
#define PGID_AGGR 64
#define PGID_SRC 80
#define PGID_ENTRIES 89
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h
index 1d90b93dd417..fb5087fef22e 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_regs.h
@@ -585,6 +585,21 @@ enum lan966x_target {
#define DEV_MAC_MAXLEN_CFG_MAX_LEN_GET(x)\
FIELD_GET(DEV_MAC_MAXLEN_CFG_MAX_LEN, x)
+/* DEV:MAC_CFG_STATUS:MAC_TAGS_CFG */
+#define DEV_MAC_TAGS_CFG(t) __REG(TARGET_DEV, t, 8, 28, 0, 1, 44, 12, 0, 1, 4)
+
+#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA BIT(1)
+#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_SET(x)\
+ FIELD_PREP(DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA, x)
+#define DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_GET(x)\
+ FIELD_GET(DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA, x)
+
+#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA BIT(0)
+#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(x)\
+ FIELD_PREP(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA, x)
+#define DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_GET(x)\
+ FIELD_GET(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA, x)
+
/* DEV:MAC_CFG_STATUS:MAC_IFG_CFG */
#define DEV_MAC_IFG_CFG(t) __REG(TARGET_DEV, t, 8, 28, 0, 1, 44, 20, 0, 1, 4)
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
index 8d7260cd7da9..3c44660128da 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_vlan.c
@@ -169,6 +169,12 @@ void lan966x_vlan_port_apply(struct lan966x_port *port)
ANA_VLAN_CFG_VLAN_POP_CNT,
lan966x, ANA_VLAN_CFG(port->chip_port));
+ lan_rmw(DEV_MAC_TAGS_CFG_VLAN_AWR_ENA_SET(port->vlan_aware) |
+ DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA_SET(port->vlan_aware),
+ DEV_MAC_TAGS_CFG_VLAN_AWR_ENA |
+ DEV_MAC_TAGS_CFG_VLAN_DBL_AWR_ENA,
+ lan966x, DEV_MAC_TAGS_CFG(port->chip_port));
+
/* Drop frames with multicast source address */
val = ANA_DROP_CFG_DROP_MC_SMAC_ENA_SET(1);
if (port->vlan_aware && !pvid)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index e66e548919d4..71301dbd8fb5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -716,16 +716,26 @@ static u64 nfp_net_pf_get_app_cap(struct nfp_pf *pf)
return val;
}
-static int nfp_pf_cfg_hwinfo(struct nfp_pf *pf, bool sp_indiff)
+static void nfp_pf_cfg_hwinfo(struct nfp_pf *pf)
{
struct nfp_nsp *nsp;
char hwinfo[32];
+ bool sp_indiff;
int err;
nsp = nfp_nsp_open(pf->cpp);
if (IS_ERR(nsp))
- return PTR_ERR(nsp);
+ return;
+
+ if (!nfp_nsp_has_hwinfo_set(nsp))
+ goto end;
+ sp_indiff = (nfp_net_pf_get_app_id(pf) == NFP_APP_FLOWER_NIC) ||
+ (nfp_net_pf_get_app_cap(pf) & NFP_NET_APP_CAP_SP_INDIFF);
+
+ /* No need to clean `sp_indiff` in driver, management firmware
+ * will do it when application firmware is unloaded.
+ */
snprintf(hwinfo, sizeof(hwinfo), "sp_indiff=%d", sp_indiff);
err = nfp_nsp_hwinfo_set(nsp, hwinfo, sizeof(hwinfo));
/* Not a fatal error, no need to return error to stop driver from loading */
@@ -739,21 +749,8 @@ static int nfp_pf_cfg_hwinfo(struct nfp_pf *pf, bool sp_indiff)
pf->eth_tbl = __nfp_eth_read_ports(pf->cpp, nsp);
}
+end:
nfp_nsp_close(nsp);
- return 0;
-}
-
-static int nfp_pf_nsp_cfg(struct nfp_pf *pf)
-{
- bool sp_indiff = (nfp_net_pf_get_app_id(pf) == NFP_APP_FLOWER_NIC) ||
- (nfp_net_pf_get_app_cap(pf) & NFP_NET_APP_CAP_SP_INDIFF);
-
- return nfp_pf_cfg_hwinfo(pf, sp_indiff);
-}
-
-static void nfp_pf_nsp_clean(struct nfp_pf *pf)
-{
- nfp_pf_cfg_hwinfo(pf, false);
}
static int nfp_pci_probe(struct pci_dev *pdev,
@@ -856,13 +853,11 @@ static int nfp_pci_probe(struct pci_dev *pdev,
goto err_fw_unload;
}
- err = nfp_pf_nsp_cfg(pf);
- if (err)
- goto err_fw_unload;
+ nfp_pf_cfg_hwinfo(pf);
err = nfp_net_pci_probe(pf);
if (err)
- goto err_nsp_clean;
+ goto err_fw_unload;
err = nfp_hwmon_register(pf);
if (err) {
@@ -874,8 +869,6 @@ static int nfp_pci_probe(struct pci_dev *pdev,
err_net_remove:
nfp_net_pci_remove(pf);
-err_nsp_clean:
- nfp_pf_nsp_clean(pf);
err_fw_unload:
kfree(pf->rtbl);
nfp_mip_close(pf->mip);
@@ -915,7 +908,6 @@ static void __nfp_pci_shutdown(struct pci_dev *pdev, bool unload_fw)
nfp_net_pci_remove(pf);
- nfp_pf_nsp_clean(pf);
vfree(pf->dumpspec);
kfree(pf->rtbl);
nfp_mip_close(pf->mip);
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 054d5ce6029e..0556542d7a6b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1059,8 +1059,10 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
/* Allocate and initialise a struct net_device */
net_dev = alloc_etherdev_mq(sizeof(probe_data), EFX_MAX_CORE_TX_QUEUES);
- if (!net_dev)
- return -ENOMEM;
+ if (!net_dev) {
+ rc = -ENOMEM;
+ goto fail0;
+ }
probe_ptr = netdev_priv(net_dev);
*probe_ptr = probe_data;
efx->net_dev = net_dev;
@@ -1132,6 +1134,8 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
WARN_ON(rc > 0);
netif_dbg(efx, drv, efx->net_dev, "initialisation failed. rc=%d\n", rc);
free_netdev(net_dev);
+ fail0:
+ kfree(probe_data);
return rc;
}
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 2240f6d0b89b..9b46579b5a10 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1961,11 +1961,13 @@ static int netsec_register_mdio(struct netsec_priv *priv, u32 phy_addr)
ret = PTR_ERR(priv->phydev);
dev_err(priv->dev, "get_phy_device err(%d)\n", ret);
priv->phydev = NULL;
+ mdiobus_unregister(bus);
return -ENODEV;
}
ret = phy_device_register(priv->phydev);
if (ret) {
+ phy_device_free(priv->phydev);
mdiobus_unregister(bus);
dev_err(priv->dev,
"phy_device_register err(%d)\n", ret);
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 1fa09b49ba7f..d2c6a5dfdc0e 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -1229,6 +1229,8 @@ static int ave_init(struct net_device *ndev)
phy_support_asym_pause(phydev);
+ phydev->mac_managed_pm = true;
+
phy_attached_info(phydev);
return 0;
@@ -1756,6 +1758,10 @@ static int ave_resume(struct device *dev)
ave_global_reset(ndev);
+ ret = phy_init_hw(ndev->phydev);
+ if (ret)
+ return ret;
+
ave_ethtool_get_wol(ndev, &wol);
wol.wolopts = priv->wolopts;
__ave_ethtool_set_wol(ndev, &wol);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 017dbbda0c1c..79fa7870563b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -51,7 +51,6 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
struct stmmac_resources res;
struct device_node *np;
int ret, i, phy_mode;
- bool mdio = false;
np = dev_of_node(&pdev->dev);
@@ -69,12 +68,10 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
if (!plat)
return -ENOMEM;
+ plat->mdio_node = of_get_child_by_name(np, "mdio");
if (plat->mdio_node) {
- dev_err(&pdev->dev, "Found MDIO subnode\n");
- mdio = true;
- }
+ dev_info(&pdev->dev, "Found MDIO subnode\n");
- if (mdio) {
plat->mdio_bus_data = devm_kzalloc(&pdev->dev,
sizeof(*plat->mdio_bus_data),
GFP_KERNEL);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index f7269d79a385..6656d76b6766 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1243,6 +1243,12 @@ static const struct rk_gmac_ops rk3588_ops = {
.set_rgmii_speed = rk3588_set_gmac_speed,
.set_rmii_speed = rk3588_set_gmac_speed,
.set_clock_selection = rk3588_set_clock_selection,
+ .regs_valid = true,
+ .regs = {
+ 0xfe1b0000, /* gmac0 */
+ 0xfe1c0000, /* gmac1 */
+ 0x0, /* sentinel */
+ },
};
#define RV1108_GRF_GMAC_CON0 0X0900
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 05848ff15fb5..a3967f8de417 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -108,7 +108,7 @@
* @next_tx_buf_to_use: next Tx buffer to write to
* @next_rx_buf_to_use: next Rx buffer to read from
* @base_addr: base address of the Emaclite device
- * @reset_lock: lock used for synchronization
+ * @reset_lock: lock to serialize xmit and tx_timeout execution
* @deferred_skb: holds an skb (for transmission at a later time) when the
* Tx buffer is not free
* @phy_dev: pointer to the PHY device
diff --git a/drivers/net/ipa/data/ipa_data-v3.5.1.c b/drivers/net/ipa/data/ipa_data-v3.5.1.c
index 383ef1890065..42f2c88a92d4 100644
--- a/drivers/net/ipa/data/ipa_data-v3.5.1.c
+++ b/drivers/net/ipa/data/ipa_data-v3.5.1.c
@@ -179,10 +179,10 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
static const struct ipa_resource ipa_resource_src[] = {
[IPA_RESOURCE_TYPE_SRC_PKT_CONTEXTS] = {
.limits[IPA_RSRC_GROUP_SRC_LWA_DL] = {
- .min = 1, .max = 255,
+ .min = 1, .max = 63,
},
.limits[IPA_RSRC_GROUP_SRC_UL_DL] = {
- .min = 1, .max = 255,
+ .min = 1, .max = 63,
},
.limits[IPA_RSRC_GROUP_SRC_UC_RX_Q] = {
.min = 1, .max = 63,
diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c
index 3461ad3029ab..49537fccf6ad 100644
--- a/drivers/net/ipa/ipa_main.c
+++ b/drivers/net/ipa/ipa_main.c
@@ -434,6 +434,9 @@ static void ipa_idle_indication_cfg(struct ipa *ipa,
const struct ipa_reg *reg;
u32 val;
+ if (ipa->version < IPA_VERSION_3_5_1)
+ return;
+
reg = ipa_reg(ipa, IDLE_INDICATION_CFG);
val = ipa_reg_encode(reg, ENTER_IDLE_DEBOUNCE_THRESH,
enter_idle_debounce_thresh);
diff --git a/drivers/net/ipa/reg/ipa_reg-v3.1.c b/drivers/net/ipa/reg/ipa_reg-v3.1.c
index 116b27717e3d..0d002c3c38a2 100644
--- a/drivers/net/ipa/reg/ipa_reg-v3.1.c
+++ b/drivers/net/ipa/reg/ipa_reg-v3.1.c
@@ -127,112 +127,80 @@ static const u32 ipa_reg_counter_cfg_fmask[] = {
IPA_REG_FIELDS(COUNTER_CFG, counter_cfg, 0x000001f0);
static const u32 ipa_reg_src_rsrc_grp_01_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_01_RSRC_TYPE, src_rsrc_grp_01_rsrc_type,
0x00000400, 0x0020);
static const u32 ipa_reg_src_rsrc_grp_23_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_23_RSRC_TYPE, src_rsrc_grp_23_rsrc_type,
0x00000404, 0x0020);
static const u32 ipa_reg_src_rsrc_grp_45_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_45_RSRC_TYPE, src_rsrc_grp_45_rsrc_type,
0x00000408, 0x0020);
static const u32 ipa_reg_src_rsrc_grp_67_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(SRC_RSRC_GRP_67_RSRC_TYPE, src_rsrc_grp_67_rsrc_type,
0x0000040c, 0x0020);
static const u32 ipa_reg_dst_rsrc_grp_01_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_01_RSRC_TYPE, dst_rsrc_grp_01_rsrc_type,
0x00000500, 0x0020);
static const u32 ipa_reg_dst_rsrc_grp_23_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_23_RSRC_TYPE, dst_rsrc_grp_23_rsrc_type,
0x00000504, 0x0020);
static const u32 ipa_reg_dst_rsrc_grp_45_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_45_RSRC_TYPE, dst_rsrc_grp_45_rsrc_type,
0x00000508, 0x0020);
static const u32 ipa_reg_dst_rsrc_grp_67_rsrc_type_fmask[] = {
- [X_MIN_LIM] = GENMASK(5, 0),
- /* Bits 6-7 reserved */
- [X_MAX_LIM] = GENMASK(13, 8),
- /* Bits 14-15 reserved */
- [Y_MIN_LIM] = GENMASK(21, 16),
- /* Bits 22-23 reserved */
- [Y_MAX_LIM] = GENMASK(29, 24),
- /* Bits 30-31 reserved */
+ [X_MIN_LIM] = GENMASK(7, 0),
+ [X_MAX_LIM] = GENMASK(15, 8),
+ [Y_MIN_LIM] = GENMASK(23, 16),
+ [Y_MAX_LIM] = GENMASK(31, 24),
};
IPA_REG_STRIDE_FIELDS(DST_RSRC_GRP_67_RSRC_TYPE, dst_rsrc_grp_67_rsrc_type,
diff --git a/drivers/net/netdevsim/bus.c b/drivers/net/netdevsim/bus.c
index b5f4df1a07a3..0052968e881e 100644
--- a/drivers/net/netdevsim/bus.c
+++ b/drivers/net/netdevsim/bus.c
@@ -117,6 +117,10 @@ static const struct attribute_group *nsim_bus_dev_attr_groups[] = {
static void nsim_bus_dev_release(struct device *dev)
{
+ struct nsim_bus_dev *nsim_bus_dev;
+
+ nsim_bus_dev = container_of(dev, struct nsim_bus_dev, dev);
+ kfree(nsim_bus_dev);
}
static struct device_type nsim_bus_dev_type = {
@@ -291,6 +295,8 @@ nsim_bus_dev_new(unsigned int id, unsigned int port_count, unsigned int num_queu
err_nsim_bus_dev_id_free:
ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
+ put_device(&nsim_bus_dev->dev);
+ nsim_bus_dev = NULL;
err_nsim_bus_dev_free:
kfree(nsim_bus_dev);
return ERR_PTR(err);
@@ -300,9 +306,8 @@ static void nsim_bus_dev_del(struct nsim_bus_dev *nsim_bus_dev)
{
/* Disallow using nsim_bus_dev */
smp_store_release(&nsim_bus_dev->init, false);
- device_unregister(&nsim_bus_dev->dev);
ida_free(&nsim_bus_dev_ids, nsim_bus_dev->dev.id);
- kfree(nsim_bus_dev);
+ device_unregister(&nsim_bus_dev->dev);
}
static struct device_driver nsim_driver = {
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 794fc0cc73b8..a7880c7ce94c 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -309,8 +309,10 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
if (IS_ERR(nsim_dev->ddir))
return PTR_ERR(nsim_dev->ddir);
nsim_dev->ports_ddir = debugfs_create_dir("ports", nsim_dev->ddir);
- if (IS_ERR(nsim_dev->ports_ddir))
- return PTR_ERR(nsim_dev->ports_ddir);
+ if (IS_ERR(nsim_dev->ports_ddir)) {
+ err = PTR_ERR(nsim_dev->ports_ddir);
+ goto err_ddir;
+ }
debugfs_create_bool("fw_update_status", 0600, nsim_dev->ddir,
&nsim_dev->fw_update_status);
debugfs_create_u32("fw_update_overwrite_mask", 0600, nsim_dev->ddir,
@@ -346,7 +348,7 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
nsim_dev->nodes_ddir = debugfs_create_dir("rate_nodes", nsim_dev->ddir);
if (IS_ERR(nsim_dev->nodes_ddir)) {
err = PTR_ERR(nsim_dev->nodes_ddir);
- goto err_out;
+ goto err_ports_ddir;
}
debugfs_create_bool("fail_trap_drop_counter_get", 0600,
nsim_dev->ddir,
@@ -354,8 +356,9 @@ static int nsim_dev_debugfs_init(struct nsim_dev *nsim_dev)
nsim_udp_tunnels_debugfs_create(nsim_dev);
return 0;
-err_out:
+err_ports_ddir:
debugfs_remove_recursive(nsim_dev->ports_ddir);
+err_ddir:
debugfs_remove_recursive(nsim_dev->ddir);
return err;
}
@@ -442,7 +445,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
&params);
if (err) {
pr_err("Failed to register IPv4 top resource\n");
- goto out;
+ goto err_out;
}
err = devl_resource_register(devlink, "fib", (u64)-1,
@@ -450,7 +453,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
NSIM_RESOURCE_IPV4, &params);
if (err) {
pr_err("Failed to register IPv4 FIB resource\n");
- return err;
+ goto err_out;
}
err = devl_resource_register(devlink, "fib-rules", (u64)-1,
@@ -458,7 +461,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
NSIM_RESOURCE_IPV4, &params);
if (err) {
pr_err("Failed to register IPv4 FIB rules resource\n");
- return err;
+ goto err_out;
}
/* Resources for IPv6 */
@@ -468,7 +471,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
&params);
if (err) {
pr_err("Failed to register IPv6 top resource\n");
- goto out;
+ goto err_out;
}
err = devl_resource_register(devlink, "fib", (u64)-1,
@@ -476,7 +479,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
NSIM_RESOURCE_IPV6, &params);
if (err) {
pr_err("Failed to register IPv6 FIB resource\n");
- return err;
+ goto err_out;
}
err = devl_resource_register(devlink, "fib-rules", (u64)-1,
@@ -484,7 +487,7 @@ static int nsim_dev_resources_register(struct devlink *devlink)
NSIM_RESOURCE_IPV6, &params);
if (err) {
pr_err("Failed to register IPv6 FIB rules resource\n");
- return err;
+ goto err_out;
}
/* Resources for nexthops */
@@ -492,8 +495,14 @@ static int nsim_dev_resources_register(struct devlink *devlink)
NSIM_RESOURCE_NEXTHOPS,
DEVLINK_RESOURCE_ID_PARENT_TOP,
&params);
+ if (err) {
+ pr_err("Failed to register NEXTHOPS resource\n");
+ goto err_out;
+ }
+ return 0;
-out:
+err_out:
+ devl_resources_unregister(devlink);
return err;
}
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index f82090bdf7ab..1cd604cd1fa1 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -583,7 +583,7 @@ int __mdiobus_register(struct mii_bus *bus, struct module *owner)
}
for (i = 0; i < PHY_MAX_ADDR; i++) {
- if ((bus->phy_mask & (1 << i)) == 0) {
+ if ((bus->phy_mask & BIT(i)) == 0) {
struct phy_device *phydev;
phydev = mdiobus_scan(bus, i);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 27c6d235cbda..946628050f28 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1459,7 +1459,8 @@ static struct sk_buff *tun_napi_alloc_frags(struct tun_file *tfile,
int err;
int i;
- if (it->nr_segs > MAX_SKB_FRAGS + 1)
+ if (it->nr_segs > MAX_SKB_FRAGS + 1 ||
+ len > (ETH_MAX_MTU - NET_SKB_PAD - NET_IP_ALIGN))
return ERR_PTR(-EMSGSIZE);
local_bh_disable();
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index c6b3334f24c9..f12f903a9dd1 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -249,11 +249,19 @@ static int fdp_nci_close(struct nci_dev *ndev)
static int fdp_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
{
struct fdp_nci_info *info = nci_get_drvdata(ndev);
+ int ret;
if (atomic_dec_and_test(&info->data_pkt_counter))
info->data_pkt_counter_cb(ndev);
- return info->phy_ops->write(info->phy, skb);
+ ret = info->phy_ops->write(info->phy, skb);
+ if (ret < 0) {
+ kfree_skb(skb);
+ return ret;
+ }
+
+ consume_skb(skb);
+ return 0;
}
static int fdp_nci_request_firmware(struct nci_dev *ndev)
diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c
index acef0cfd76af..24436c9e54c9 100644
--- a/drivers/nfc/nfcmrvl/i2c.c
+++ b/drivers/nfc/nfcmrvl/i2c.c
@@ -132,10 +132,15 @@ static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv,
ret = -EREMOTEIO;
} else
ret = 0;
+ }
+
+ if (ret) {
kfree_skb(skb);
+ return ret;
}
- return ret;
+ consume_skb(skb);
+ return 0;
}
static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv,
diff --git a/drivers/nfc/nxp-nci/core.c b/drivers/nfc/nxp-nci/core.c
index 7c93d484dc1b..580cb6ecffee 100644
--- a/drivers/nfc/nxp-nci/core.c
+++ b/drivers/nfc/nxp-nci/core.c
@@ -80,10 +80,13 @@ static int nxp_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
return -EINVAL;
r = info->phy_ops->write(info->phy_id, skb);
- if (r < 0)
+ if (r < 0) {
kfree_skb(skb);
+ return r;
+ }
- return r;
+ consume_skb(skb);
+ return 0;
}
static int nxp_nci_rf_pll_unlocked_ntf(struct nci_dev *ndev,
diff --git a/drivers/nfc/s3fwrn5/core.c b/drivers/nfc/s3fwrn5/core.c
index 1c412007fabb..0270e05b68df 100644
--- a/drivers/nfc/s3fwrn5/core.c
+++ b/drivers/nfc/s3fwrn5/core.c
@@ -110,11 +110,15 @@ static int s3fwrn5_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
}
ret = s3fwrn5_write(info, skb);
- if (ret < 0)
+ if (ret < 0) {
kfree_skb(skb);
+ mutex_unlock(&info->mutex);
+ return ret;
+ }
+ consume_skb(skb);
mutex_unlock(&info->mutex);
- return ret;
+ return 0;
}
static int s3fwrn5_nci_post_setup(struct nci_dev *ndev)
diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c
index f577449e4935..85c06dbb2c44 100644
--- a/drivers/nfc/virtual_ncidev.c
+++ b/drivers/nfc/virtual_ncidev.c
@@ -54,16 +54,19 @@ static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb)
mutex_lock(&nci_mutex);
if (state != virtual_ncidev_enabled) {
mutex_unlock(&nci_mutex);
+ kfree_skb(skb);
return 0;
}
if (send_buff) {
mutex_unlock(&nci_mutex);
+ kfree_skb(skb);
return -1;
}
send_buff = skb_copy(skb, GFP_KERNEL);
mutex_unlock(&nci_mutex);
wake_up_interruptible(&wq);
+ consume_skb(skb);
return 0;
}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0ea7e441e080..93e2138a8b42 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -516,6 +516,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
/* set to a default value of 512 until the disk is validated */
blk_queue_logical_block_size(head->disk->queue, 512);
blk_set_stacking_limits(&head->disk->queue->limits);
+ blk_queue_dma_alignment(head->disk->queue, 3);
/* we need to propagate up the VMC settings */
if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1eed0fc26b3a..9b47dcb2a7d9 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -387,7 +387,7 @@ static inline void nvme_tcp_ddgst_update(struct ahash_request *hash,
{
struct scatterlist sg;
- sg_init_marker(&sg, 1);
+ sg_init_table(&sg, 1);
sg_set_page(&sg, page, len, off);
ahash_request_set_crypt(hash, &sg, NULL, len);
crypto_ahash_update(hash);
@@ -1141,6 +1141,7 @@ static int nvme_tcp_try_send_ddgst(struct nvme_tcp_request *req)
static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
{
struct nvme_tcp_request *req;
+ unsigned int noreclaim_flag;
int ret = 1;
if (!queue->request) {
@@ -1150,12 +1151,13 @@ static int nvme_tcp_try_send(struct nvme_tcp_queue *queue)
}
req = queue->request;
+ noreclaim_flag = memalloc_noreclaim_save();
if (req->state == NVME_TCP_SEND_CMD_PDU) {
ret = nvme_tcp_try_send_cmd_pdu(req);
if (ret <= 0)
goto done;
if (!nvme_tcp_has_inline_data(req))
- return ret;
+ goto out;
}
if (req->state == NVME_TCP_SEND_H2C_PDU) {
@@ -1181,6 +1183,8 @@ done:
nvme_tcp_fail_request(queue->request);
nvme_tcp_done_send_req(queue);
}
+out:
+ memalloc_noreclaim_restore(noreclaim_flag);
return ret;
}
@@ -1296,6 +1300,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
struct page *page;
struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl);
struct nvme_tcp_queue *queue = &ctrl->queues[qid];
+ unsigned int noreclaim_flag;
if (!test_and_clear_bit(NVME_TCP_Q_ALLOCATED, &queue->flags))
return;
@@ -1308,7 +1313,11 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid)
__page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias);
queue->pf_cache.va = NULL;
}
+
+ noreclaim_flag = memalloc_noreclaim_save();
sock_release(queue->sock);
+ memalloc_noreclaim_restore(noreclaim_flag);
+
kfree(queue->pdu);
mutex_destroy(&queue->send_mutex);
mutex_destroy(&queue->queue_lock);
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index bdef7a8d6ab8..bcc1dae00780 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -866,6 +866,7 @@ int iosapic_serial_irq(struct parisc_device *dev)
return vi->txn_irq;
}
+EXPORT_SYMBOL(iosapic_serial_irq);
#endif
diff --git a/drivers/parisc/pdc_stable.c b/drivers/parisc/pdc_stable.c
index d9e51036a4fa..d6af5726ddf3 100644
--- a/drivers/parisc/pdc_stable.c
+++ b/drivers/parisc/pdc_stable.c
@@ -14,7 +14,7 @@
* all) PA-RISC machines should have them. Anyway, for safety reasons, the
* following code can deal with just 96 bytes of Stable Storage, and all
* sizes between 96 and 192 bytes (provided they are multiple of struct
- * device_path size, eg: 128, 160 and 192) to provide full information.
+ * pdc_module_path size, eg: 128, 160 and 192) to provide full information.
* One last word: there's one path we can always count on: the primary path.
* Anything above 224 bytes is used for 'osdep2' OS-dependent storage area.
*
@@ -88,7 +88,7 @@ struct pdcspath_entry {
short ready; /* entry record is valid if != 0 */
unsigned long addr; /* entry address in stable storage */
char *name; /* entry name */
- struct device_path devpath; /* device path in parisc representation */
+ struct pdc_module_path devpath; /* device path in parisc representation */
struct device *dev; /* corresponding device */
struct kobject kobj;
};
@@ -138,7 +138,7 @@ struct pdcspath_attribute paths_attr_##_name = { \
static int
pdcspath_fetch(struct pdcspath_entry *entry)
{
- struct device_path *devpath;
+ struct pdc_module_path *devpath;
if (!entry)
return -EINVAL;
@@ -153,7 +153,7 @@ pdcspath_fetch(struct pdcspath_entry *entry)
return -EIO;
/* Find the matching device.
- NOTE: hardware_path overlays with device_path, so the nice cast can
+ NOTE: hardware_path overlays with pdc_module_path, so the nice cast can
be used */
entry->dev = hwpath_to_device((struct hardware_path *)devpath);
@@ -179,7 +179,7 @@ pdcspath_fetch(struct pdcspath_entry *entry)
static void
pdcspath_store(struct pdcspath_entry *entry)
{
- struct device_path *devpath;
+ struct pdc_module_path *devpath;
BUG_ON(!entry);
@@ -221,7 +221,7 @@ static ssize_t
pdcspath_hwpath_read(struct pdcspath_entry *entry, char *buf)
{
char *out = buf;
- struct device_path *devpath;
+ struct pdc_module_path *devpath;
short i;
if (!entry || !buf)
@@ -236,11 +236,11 @@ pdcspath_hwpath_read(struct pdcspath_entry *entry, char *buf)
return -ENODATA;
for (i = 0; i < 6; i++) {
- if (devpath->bc[i] >= 128)
+ if (devpath->path.bc[i] < 0)
continue;
- out += sprintf(out, "%u/", (unsigned char)devpath->bc[i]);
+ out += sprintf(out, "%d/", devpath->path.bc[i]);
}
- out += sprintf(out, "%u\n", (unsigned char)devpath->mod);
+ out += sprintf(out, "%u\n", (unsigned char)devpath->path.mod);
return out - buf;
}
@@ -296,12 +296,12 @@ pdcspath_hwpath_write(struct pdcspath_entry *entry, const char *buf, size_t coun
for (i=5; ((temp = strrchr(in, '/'))) && (temp-in > 0) && (likely(i)); i--) {
hwpath.bc[i] = simple_strtoul(temp+1, NULL, 10);
in[temp-in] = '\0';
- DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.bc[i]);
+ DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.path.bc[i]);
}
/* Store the final field */
hwpath.bc[i] = simple_strtoul(in, NULL, 10);
- DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.bc[i]);
+ DPRINTK("%s: bc[%d]: %d\n", __func__, i, hwpath.path.bc[i]);
/* Now we check that the user isn't trying to lure us */
if (!(dev = hwpath_to_device((struct hardware_path *)&hwpath))) {
@@ -342,7 +342,7 @@ static ssize_t
pdcspath_layer_read(struct pdcspath_entry *entry, char *buf)
{
char *out = buf;
- struct device_path *devpath;
+ struct pdc_module_path *devpath;
short i;
if (!entry || !buf)
@@ -547,7 +547,7 @@ static ssize_t pdcs_auto_read(struct kobject *kobj,
pathentry = &pdcspath_entry_primary;
read_lock(&pathentry->rw_lock);
- out += sprintf(out, "%s\n", (pathentry->devpath.flags & knob) ?
+ out += sprintf(out, "%s\n", (pathentry->devpath.path.flags & knob) ?
"On" : "Off");
read_unlock(&pathentry->rw_lock);
@@ -594,8 +594,8 @@ static ssize_t pdcs_timer_read(struct kobject *kobj,
/* print the timer value in seconds */
read_lock(&pathentry->rw_lock);
- out += sprintf(out, "%u\n", (pathentry->devpath.flags & PF_TIMER) ?
- (1 << (pathentry->devpath.flags & PF_TIMER)) : 0);
+ out += sprintf(out, "%u\n", (pathentry->devpath.path.flags & PF_TIMER) ?
+ (1 << (pathentry->devpath.path.flags & PF_TIMER)) : 0);
read_unlock(&pathentry->rw_lock);
return out - buf;
@@ -764,7 +764,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj,
/* Be nice to the existing flag record */
read_lock(&pathentry->rw_lock);
- flags = pathentry->devpath.flags;
+ flags = pathentry->devpath.path.flags;
read_unlock(&pathentry->rw_lock);
DPRINTK("%s: flags before: 0x%X\n", __func__, flags);
@@ -785,7 +785,7 @@ static ssize_t pdcs_auto_write(struct kobject *kobj,
write_lock(&pathentry->rw_lock);
/* Change the path entry flags first */
- pathentry->devpath.flags = flags;
+ pathentry->devpath.path.flags = flags;
/* Now, dive in. Write back to the hardware */
pdcspath_store(pathentry);
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index 7e732076dedf..9e46d83e5138 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -667,7 +667,7 @@ static u8 jz4755_lcd_24bit_funcs[] = { 1, 1, 1, 1, 0, 0, };
static const struct group_desc jz4755_groups[] = {
INGENIC_PIN_GROUP("uart0-data", jz4755_uart0_data, 0),
INGENIC_PIN_GROUP("uart0-hwflow", jz4755_uart0_hwflow, 0),
- INGENIC_PIN_GROUP("uart1-data", jz4755_uart1_data, 0),
+ INGENIC_PIN_GROUP("uart1-data", jz4755_uart1_data, 1),
INGENIC_PIN_GROUP("uart2-data", jz4755_uart2_data, 1),
INGENIC_PIN_GROUP("ssi-dt-b", jz4755_ssi_dt_b, 0),
INGENIC_PIN_GROUP("ssi-dt-f", jz4755_ssi_dt_f, 0),
@@ -721,7 +721,7 @@ static const char *jz4755_ssi_groups[] = {
"ssi-ce1-b", "ssi-ce1-f",
};
static const char *jz4755_mmc0_groups[] = { "mmc0-1bit", "mmc0-4bit", };
-static const char *jz4755_mmc1_groups[] = { "mmc0-1bit", "mmc0-4bit", };
+static const char *jz4755_mmc1_groups[] = { "mmc1-1bit", "mmc1-4bit", };
static const char *jz4755_i2c_groups[] = { "i2c-data", };
static const char *jz4755_cim_groups[] = { "cim-data", };
static const char *jz4755_lcd_groups[] = {
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index 62ce3957abe4..687aaa601555 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -1864,19 +1864,28 @@ static void ocelot_irq_unmask_level(struct irq_data *data)
if (val & bit)
ack = true;
+ /* Try to clear any rising edges */
+ if (!active && ack)
+ regmap_write_bits(info->map, REG(OCELOT_GPIO_INTR, info, gpio),
+ bit, bit);
+
/* Enable the interrupt now */
gpiochip_enable_irq(chip, gpio);
regmap_update_bits(info->map, REG(OCELOT_GPIO_INTR_ENA, info, gpio),
bit, bit);
/*
- * In case the interrupt line is still active and the interrupt
- * controller has not seen any changes in the interrupt line, then it
- * means that there happen another interrupt while the line was active.
+ * In case the interrupt line is still active then it means that
+ * there happen another interrupt while the line was active.
* So we missed that one, so we need to kick the interrupt again
* handler.
*/
- if (active && !ack) {
+ regmap_read(info->map, REG(OCELOT_GPIO_IN, info, gpio), &val);
+ if ((!(val & bit) && trigger_level == IRQ_TYPE_LEVEL_LOW) ||
+ (val & bit && trigger_level == IRQ_TYPE_LEVEL_HIGH))
+ active = true;
+
+ if (active) {
struct ocelot_irq_work *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
diff --git a/drivers/pinctrl/pinctrl-zynqmp.c b/drivers/pinctrl/pinctrl-zynqmp.c
index 7d2fbf8a02cd..c98f35ad8921 100644
--- a/drivers/pinctrl/pinctrl-zynqmp.c
+++ b/drivers/pinctrl/pinctrl-zynqmp.c
@@ -412,10 +412,6 @@ static int zynqmp_pinconf_cfg_set(struct pinctrl_dev *pctldev,
break;
case PIN_CONFIG_BIAS_HIGH_IMPEDANCE:
- param = PM_PINCTRL_CONFIG_TRI_STATE;
- arg = PM_PINCTRL_TRI_STATE_ENABLE;
- ret = zynqmp_pm_pinctrl_set_config(pin, param, arg);
- break;
case PIN_CONFIG_MODE_LOW_POWER:
/*
* These cases are mentioned in dts but configurable
@@ -424,11 +420,6 @@ static int zynqmp_pinconf_cfg_set(struct pinctrl_dev *pctldev,
*/
ret = 0;
break;
- case PIN_CONFIG_OUTPUT_ENABLE:
- param = PM_PINCTRL_CONFIG_TRI_STATE;
- arg = PM_PINCTRL_TRI_STATE_DISABLE;
- ret = zynqmp_pm_pinctrl_set_config(pin, param, arg);
- break;
default:
dev_warn(pctldev->dev,
"unsupported configuration parameter '%u'\n",
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index a2abfe987ab1..8bf8b21954fe 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -51,6 +51,7 @@
* detection.
* @skip_wake_irqs: Skip IRQs that are handled by wakeup interrupt controller
* @disabled_for_mux: These IRQs were disabled because we muxed away.
+ * @ever_gpio: This bit is set the first time we mux a pin to gpio_func.
* @soc: Reference to soc_data of platform specific data.
* @regs: Base addresses for the TLMM tiles.
* @phys_base: Physical base address
@@ -72,6 +73,7 @@ struct msm_pinctrl {
DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO);
DECLARE_BITMAP(skip_wake_irqs, MAX_NR_GPIO);
DECLARE_BITMAP(disabled_for_mux, MAX_NR_GPIO);
+ DECLARE_BITMAP(ever_gpio, MAX_NR_GPIO);
const struct msm_pinctrl_soc_data *soc;
void __iomem *regs[MAX_NR_TILES];
@@ -218,6 +220,25 @@ static int msm_pinmux_set_mux(struct pinctrl_dev *pctldev,
val = msm_readl_ctl(pctrl, g);
+ /*
+ * If this is the first time muxing to GPIO and the direction is
+ * output, make sure that we're not going to be glitching the pin
+ * by reading the current state of the pin and setting it as the
+ * output.
+ */
+ if (i == gpio_func && (val & BIT(g->oe_bit)) &&
+ !test_and_set_bit(group, pctrl->ever_gpio)) {
+ u32 io_val = msm_readl_io(pctrl, g);
+
+ if (io_val & BIT(g->in_bit)) {
+ if (!(io_val & BIT(g->out_bit)))
+ msm_writel_io(io_val | BIT(g->out_bit), pctrl, g);
+ } else {
+ if (io_val & BIT(g->out_bit))
+ msm_writel_io(io_val & ~BIT(g->out_bit), pctrl, g);
+ }
+ }
+
if (egpio_func && i == egpio_func) {
if (val & BIT(g->egpio_present))
val &= ~BIT(g->egpio_enable);
diff --git a/drivers/platform/loongarch/loongson-laptop.c b/drivers/platform/loongarch/loongson-laptop.c
index f0166ad5d2c2..99203584949d 100644
--- a/drivers/platform/loongarch/loongson-laptop.c
+++ b/drivers/platform/loongarch/loongson-laptop.c
@@ -199,6 +199,13 @@ static int loongson_hotkey_resume(struct device *dev)
struct key_entry ke;
struct backlight_device *bd;
+ bd = backlight_device_get_by_type(BACKLIGHT_PLATFORM);
+ if (bd) {
+ loongson_laptop_backlight_update(bd) ?
+ pr_warn("Loongson_backlight: resume brightness failed") :
+ pr_info("Loongson_backlight: resume brightness %d\n", bd->props.brightness);
+ }
+
/*
* Only if the firmware supports SW_LID event model, we can handle the
* event. This is for the consideration of development board without EC.
@@ -228,13 +235,6 @@ static int loongson_hotkey_resume(struct device *dev)
}
}
- bd = backlight_device_get_by_type(BACKLIGHT_PLATFORM);
- if (bd) {
- loongson_laptop_backlight_update(bd) ?
- pr_warn("Loongson_backlight: resume brightness failed") :
- pr_info("Loongson_backlight: resume brightness %d\n", bd->props.brightness);
- }
-
return 0;
}
@@ -448,6 +448,7 @@ static int __init event_init(struct generic_sub_driver *sub_driver)
if (ret < 0) {
pr_err("Failed to setup input device keymap\n");
input_free_device(generic_inputdev);
+ generic_inputdev = NULL;
return ret;
}
@@ -502,8 +503,11 @@ static int __init generic_subdriver_init(struct generic_sub_driver *sub_driver)
if (ret)
return -EINVAL;
- if (sub_driver->init)
- sub_driver->init(sub_driver);
+ if (sub_driver->init) {
+ ret = sub_driver->init(sub_driver);
+ if (ret)
+ goto err_out;
+ }
if (sub_driver->notify) {
ret = setup_acpi_notify(sub_driver);
@@ -519,7 +523,7 @@ static int __init generic_subdriver_init(struct generic_sub_driver *sub_driver)
err_out:
generic_subdriver_exit(sub_driver);
- return (ret < 0) ? ret : 0;
+ return ret;
}
static void generic_subdriver_exit(struct generic_sub_driver *sub_driver)
diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c
index ce859b300712..96e790e639a2 100644
--- a/drivers/platform/x86/amd/pmc.c
+++ b/drivers/platform/x86/amd/pmc.c
@@ -663,6 +663,13 @@ static int amd_pmc_verify_czn_rtc(struct amd_pmc_dev *pdev, u32 *arg)
struct rtc_time tm;
int rc;
+ /* we haven't yet read SMU version */
+ if (!pdev->major) {
+ rc = amd_pmc_get_smu_version(pdev);
+ if (rc)
+ return rc;
+ }
+
if (pdev->major < 64 || (pdev->major == 64 && pdev->minor < 53))
return 0;
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index 613c45c9fbe3..c685a705b73d 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -464,6 +464,15 @@ static const struct dmi_system_id asus_quirks[] = {
},
.driver_data = &quirk_asus_tablet_mode,
},
+ {
+ .callback = dmi_matched,
+ .ident = "ASUS ROG FLOW X16",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "GV601R"),
+ },
+ .driver_data = &quirk_asus_tablet_mode,
+ },
{},
};
diff --git a/drivers/platform/x86/intel/pmc/core.c b/drivers/platform/x86/intel/pmc/core.c
index a1fe1e0dcf4a..17ec5825d13d 100644
--- a/drivers/platform/x86/intel/pmc/core.c
+++ b/drivers/platform/x86/intel/pmc/core.c
@@ -1914,6 +1914,8 @@ static const struct x86_cpu_id intel_pmc_core_ids[] = {
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, &tgl_reg_map),
X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, &adl_reg_map),
X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, &tgl_reg_map),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, &adl_reg_map),
+ X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, &adl_reg_map),
{}
};
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 6a823b850a77..20e5c043a8e8 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -263,6 +263,8 @@ enum tpacpi_hkey_event_t {
#define TPACPI_DBG_BRGHT 0x0020
#define TPACPI_DBG_MIXER 0x0040
+#define FAN_NOT_PRESENT 65535
+
#define strlencmp(a, b) (strncmp((a), (b), strlen(b)))
@@ -8876,7 +8878,7 @@ static int __init fan_init(struct ibm_init_struct *iibm)
/* Try and probe the 2nd fan */
tp_features.second_fan = 1; /* needed for get_speed to work */
res = fan2_get_speed(&speed);
- if (res >= 0) {
+ if (res >= 0 && speed != FAN_NOT_PRESENT) {
/* It responded - so let's assume it's there */
tp_features.second_fan = 1;
tp_features.second_fan_ctl = 1;
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 610413b4e9ca..58cc2bae2f8a 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -1233,6 +1233,9 @@ static u32 rtc_handler(void *context)
static inline void rtc_wake_setup(struct device *dev)
{
+ if (acpi_disabled)
+ return;
+
acpi_install_fixed_event_handler(ACPI_EVENT_RTC, rtc_handler, dev);
/*
* After the RTC handler is installed, the Fixed_RTC event should
@@ -1286,7 +1289,6 @@ static void cmos_wake_setup(struct device *dev)
use_acpi_alarm_quirks();
- rtc_wake_setup(dev);
acpi_rtc_info.wake_on = rtc_wake_on;
acpi_rtc_info.wake_off = rtc_wake_off;
@@ -1344,6 +1346,9 @@ static void cmos_check_acpi_rtc_status(struct device *dev,
{
}
+static void rtc_wake_setup(struct device *dev)
+{
+}
#endif
#ifdef CONFIG_PNP
@@ -1354,6 +1359,8 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
{
int irq, ret;
+ cmos_wake_setup(&pnp->dev);
+
if (pnp_port_start(pnp, 0) == 0x70 && !pnp_irq_valid(pnp, 0)) {
irq = 0;
#ifdef CONFIG_X86
@@ -1372,7 +1379,7 @@ static int cmos_pnp_probe(struct pnp_dev *pnp, const struct pnp_device_id *id)
if (ret)
return ret;
- cmos_wake_setup(&pnp->dev);
+ rtc_wake_setup(&pnp->dev);
return 0;
}
@@ -1461,6 +1468,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev)
int irq, ret;
cmos_of_init(pdev);
+ cmos_wake_setup(&pdev->dev);
if (RTC_IOMAPPED)
resource = platform_get_resource(pdev, IORESOURCE_IO, 0);
@@ -1474,7 +1482,7 @@ static int __init cmos_platform_probe(struct platform_device *pdev)
if (ret)
return ret;
- cmos_wake_setup(&pdev->dev);
+ rtc_wake_setup(&pdev->dev);
return 0;
}
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 913b6ddd040b..c7db95398500 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -753,13 +753,9 @@ static int __unset_online(struct device *dev, void *data)
{
struct idset *set = data;
struct subchannel *sch = to_subchannel(dev);
- struct ccw_device *cdev;
- if (sch->st == SUBCHANNEL_TYPE_IO) {
- cdev = sch_get_cdev(sch);
- if (cdev && cdev->online)
- idset_sch_del(set, sch->schid);
- }
+ if (sch->st == SUBCHANNEL_TYPE_IO && sch->config.ena)
+ idset_sch_del(set, sch->schid);
return 0;
}
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 2eddd5f34ed3..976a65f32e7d 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -52,7 +52,7 @@ struct ap_matrix_dev {
struct mutex guests_lock; /* serializes access to each KVM guest */
struct mdev_parent parent;
struct mdev_type mdev_type;
- struct mdev_type *mdev_types[];
+ struct mdev_type *mdev_types[1];
};
extern struct ap_matrix_dev *matrix_dev;
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index ac0c7ccf2eae..852b025e2fec 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2582,7 +2582,7 @@ static int lpfcdiag_loop_self_unreg(struct lpfc_hba *phba, uint16_t rpi)
*
* This function obtains the transmit and receive ids required to send
* an unsolicited ct command with a payload. A special lpfc FsType and CmdRsp
- * flags are used to the unsolicted response handler is able to process
+ * flags are used to the unsolicited response handler is able to process
* the ct command sent on the same port.
**/
static int lpfcdiag_loop_get_xri(struct lpfc_hba *phba, uint16_t rpi,
@@ -2874,7 +2874,7 @@ out:
* @len: Number of data bytes
*
* This function allocates and posts a data buffer of sufficient size to receive
- * an unsolicted CT command.
+ * an unsolicited CT command.
**/
static int lpfcdiag_sli3_loop_post_rxbufs(struct lpfc_hba *phba, uint16_t rxxri,
size_t len)
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index 75fd2bfc212b..e941a99aa965 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -90,7 +90,7 @@ lpfc_ct_ignore_hbq_buffer(struct lpfc_hba *phba, struct lpfc_iocbq *piocbq,
get_job_ulpstatus(phba, piocbq));
}
lpfc_printf_log(phba, KERN_INFO, LOG_ELS,
- "0145 Ignoring unsolicted CT HBQ Size:%d "
+ "0145 Ignoring unsolicited CT HBQ Size:%d "
"status = x%x\n",
size, get_job_ulpstatus(phba, piocbq));
}
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 9be4ba61a076..d265a2d9d082 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5874,10 +5874,6 @@ fallback:
static
int megasas_get_device_list(struct megasas_instance *instance)
{
- memset(instance->pd_list, 0,
- (MEGASAS_MAX_PD * sizeof(struct megasas_pd_list)));
- memset(instance->ld_ids, 0xff, MEGASAS_MAX_LD_IDS);
-
if (instance->enable_fw_dev_list) {
if (megasas_host_device_list_query(instance, true))
return FAILED;
@@ -7220,7 +7216,7 @@ int megasas_alloc_ctrl_dma_buffers(struct megasas_instance *instance)
if (!fusion->ioc_init_request) {
dev_err(&pdev->dev,
- "Failed to allocate PD list buffer\n");
+ "Failed to allocate ioc init request\n");
return -ENOMEM;
}
@@ -7439,7 +7435,6 @@ static inline void megasas_init_ctrl_params(struct megasas_instance *instance)
(instance->pdev->device == PCI_DEVICE_ID_LSI_SAS0071SKINNY))
instance->flag_ieee = 1;
- megasas_dbg_lvl = 0;
instance->flag = 0;
instance->unload = 1;
instance->last_time = 0;
@@ -8762,33 +8757,26 @@ static
int megasas_update_device_list(struct megasas_instance *instance,
int event_type)
{
- int dcmd_ret = DCMD_SUCCESS;
+ int dcmd_ret;
if (instance->enable_fw_dev_list) {
- dcmd_ret = megasas_host_device_list_query(instance, false);
- if (dcmd_ret != DCMD_SUCCESS)
- goto out;
+ return megasas_host_device_list_query(instance, false);
} else {
if (event_type & SCAN_PD_CHANNEL) {
dcmd_ret = megasas_get_pd_list(instance);
-
if (dcmd_ret != DCMD_SUCCESS)
- goto out;
+ return dcmd_ret;
}
if (event_type & SCAN_VD_CHANNEL) {
if (!instance->requestorId ||
megasas_get_ld_vf_affiliation(instance, 0)) {
- dcmd_ret = megasas_ld_list_query(instance,
+ return megasas_ld_list_query(instance,
MR_LD_QUERY_TYPE_EXPOSED_TO_HOST);
- if (dcmd_ret != DCMD_SUCCESS)
- goto out;
}
}
}
-
-out:
- return dcmd_ret;
+ return DCMD_SUCCESS;
}
/**
@@ -8918,7 +8906,7 @@ megasas_aen_polling(struct work_struct *work)
sdev1 = scsi_device_lookup(instance->host,
MEGASAS_MAX_PD_CHANNELS +
(ld_target_id / MEGASAS_MAX_DEV_PER_CHANNEL),
- (ld_target_id - MEGASAS_MAX_DEV_PER_CHANNEL),
+ (ld_target_id % MEGASAS_MAX_DEV_PER_CHANNEL),
0);
if (sdev1)
megasas_remove_scsi_device(sdev1);
@@ -9016,6 +9004,7 @@ static int __init megasas_init(void)
*/
pr_info("megasas: %s\n", MEGASAS_VERSION);
+ megasas_dbg_lvl = 0;
support_poll_for_event = 2;
support_device_change = 1;
support_nvme_encapsulation = true;
diff --git a/drivers/scsi/mpi3mr/Kconfig b/drivers/scsi/mpi3mr/Kconfig
index 8997531940c2..f48740cd5b95 100644
--- a/drivers/scsi/mpi3mr/Kconfig
+++ b/drivers/scsi/mpi3mr/Kconfig
@@ -4,5 +4,6 @@ config SCSI_MPI3MR
tristate "Broadcom MPI3 Storage Controller Device Driver"
depends on PCI && SCSI
select BLK_DEV_BSGLIB
+ select SCSI_SAS_ATTRS
help
MPI3 based Storage & RAID Controllers Driver.
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 8b22df8c1792..4e981ccaac41 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2993,7 +2993,7 @@ _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev)
u64 coherent_dma_mask, dma_mask;
if (ioc->is_mcpu_endpoint || sizeof(dma_addr_t) == 4 ||
- dma_get_required_mask(&pdev->dev) <= 32) {
+ dma_get_required_mask(&pdev->dev) <= DMA_BIT_MASK(32)) {
ioc->dma_mask = 32;
coherent_dma_mask = dma_mask = DMA_BIT_MASK(32);
/* Set 63 bit DMA mask for all SAS3 and SAS35 controllers */
diff --git a/drivers/scsi/pm8001/pm8001_init.c b/drivers/scsi/pm8001/pm8001_init.c
index 2ff2fac1e403..7a7d63aa90e2 100644
--- a/drivers/scsi/pm8001/pm8001_init.c
+++ b/drivers/scsi/pm8001/pm8001_init.c
@@ -99,6 +99,7 @@ static void pm8001_map_queues(struct Scsi_Host *shost)
static struct scsi_host_template pm8001_sht = {
.module = THIS_MODULE,
.name = DRV_NAME,
+ .proc_name = DRV_NAME,
.queuecommand = sas_queuecommand,
.dma_need_drain = ata_scsi_dma_need_drain,
.target_alloc = sas_target_alloc,
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index fa1fcbfb946f..b67ad30d56e6 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -951,9 +951,9 @@ qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj,
if (!capable(CAP_SYS_ADMIN) || off != 0 || count > DCBX_TLV_DATA_SIZE)
return 0;
+ mutex_lock(&vha->hw->optrom_mutex);
if (ha->dcbx_tlv)
goto do_read;
- mutex_lock(&vha->hw->optrom_mutex);
if (qla2x00_chip_is_down(vha)) {
mutex_unlock(&vha->hw->optrom_mutex);
return 0;
@@ -3330,11 +3330,34 @@ struct fc_function_template qla2xxx_transport_vport_functions = {
.bsg_timeout = qla24xx_bsg_timeout,
};
+static uint
+qla2x00_get_host_supported_speeds(scsi_qla_host_t *vha, uint speeds)
+{
+ uint supported_speeds = FC_PORTSPEED_UNKNOWN;
+
+ if (speeds & FDMI_PORT_SPEED_64GB)
+ supported_speeds |= FC_PORTSPEED_64GBIT;
+ if (speeds & FDMI_PORT_SPEED_32GB)
+ supported_speeds |= FC_PORTSPEED_32GBIT;
+ if (speeds & FDMI_PORT_SPEED_16GB)
+ supported_speeds |= FC_PORTSPEED_16GBIT;
+ if (speeds & FDMI_PORT_SPEED_8GB)
+ supported_speeds |= FC_PORTSPEED_8GBIT;
+ if (speeds & FDMI_PORT_SPEED_4GB)
+ supported_speeds |= FC_PORTSPEED_4GBIT;
+ if (speeds & FDMI_PORT_SPEED_2GB)
+ supported_speeds |= FC_PORTSPEED_2GBIT;
+ if (speeds & FDMI_PORT_SPEED_1GB)
+ supported_speeds |= FC_PORTSPEED_1GBIT;
+
+ return supported_speeds;
+}
+
void
qla2x00_init_host_attr(scsi_qla_host_t *vha)
{
struct qla_hw_data *ha = vha->hw;
- u32 speeds = FC_PORTSPEED_UNKNOWN;
+ u32 speeds = 0, fdmi_speed = 0;
fc_host_dev_loss_tmo(vha->host) = ha->port_down_retry_count;
fc_host_node_name(vha->host) = wwn_to_u64(vha->node_name);
@@ -3344,7 +3367,8 @@ qla2x00_init_host_attr(scsi_qla_host_t *vha)
fc_host_max_npiv_vports(vha->host) = ha->max_npiv_vports;
fc_host_npiv_vports_inuse(vha->host) = ha->cur_vport_count;
- speeds = qla25xx_fdmi_port_speed_capability(ha);
+ fdmi_speed = qla25xx_fdmi_port_speed_capability(ha);
+ speeds = qla2x00_get_host_supported_speeds(vha, fdmi_speed);
fc_host_supported_speeds(vha->host) = speeds;
}
diff --git a/drivers/soc/imx/imx93-pd.c b/drivers/soc/imx/imx93-pd.c
index 1f3d7039c1de..4d235c8c4924 100644
--- a/drivers/soc/imx/imx93-pd.c
+++ b/drivers/soc/imx/imx93-pd.c
@@ -135,11 +135,24 @@ static int imx93_pd_probe(struct platform_device *pdev)
ret = pm_genpd_init(&domain->genpd, NULL, domain->init_off);
if (ret)
- return ret;
+ goto err_clk_unprepare;
platform_set_drvdata(pdev, domain);
- return of_genpd_add_provider_simple(np, &domain->genpd);
+ ret = of_genpd_add_provider_simple(np, &domain->genpd);
+ if (ret)
+ goto err_genpd_remove;
+
+ return 0;
+
+err_genpd_remove:
+ pm_genpd_remove(&domain->genpd);
+
+err_clk_unprepare:
+ if (!domain->init_off)
+ clk_bulk_disable_unprepare(domain->num_clks, domain->clks);
+
+ return ret;
}
static const struct of_device_id imx93_pd_ids[] = {
diff --git a/drivers/spi/spi-aspeed-smc.c b/drivers/spi/spi-aspeed-smc.c
index a334e89add86..b90571396a60 100644
--- a/drivers/spi/spi-aspeed-smc.c
+++ b/drivers/spi/spi-aspeed-smc.c
@@ -398,7 +398,7 @@ static void aspeed_spi_get_windows(struct aspeed_spi *aspi,
windows[cs].cs = cs;
windows[cs].size = data->segment_end(aspi, reg_val) -
data->segment_start(aspi, reg_val);
- windows[cs].offset = cs ? windows[cs - 1].offset + windows[cs - 1].size : 0;
+ windows[cs].offset = data->segment_start(aspi, reg_val) - aspi->ahb_base_phy;
dev_vdbg(aspi->dev, "CE%d offset=0x%.8x size=0x%x\n", cs,
windows[cs].offset, windows[cs].size);
}
@@ -1163,7 +1163,7 @@ static const struct aspeed_spi_data ast2500_spi_data = {
static const struct aspeed_spi_data ast2600_fmc_data = {
.max_cs = 3,
.hastype = false,
- .mode_bits = SPI_RX_QUAD | SPI_RX_QUAD,
+ .mode_bits = SPI_RX_QUAD | SPI_TX_QUAD,
.we0 = 16,
.ctl0 = CE0_CTRL_REG,
.timing = CE0_TIMING_COMPENSATION_REG,
@@ -1178,7 +1178,7 @@ static const struct aspeed_spi_data ast2600_fmc_data = {
static const struct aspeed_spi_data ast2600_spi_data = {
.max_cs = 2,
.hastype = false,
- .mode_bits = SPI_RX_QUAD | SPI_RX_QUAD,
+ .mode_bits = SPI_RX_QUAD | SPI_TX_QUAD,
.we0 = 16,
.ctl0 = CE0_CTRL_REG,
.timing = CE0_TIMING_COMPENSATION_REG,
diff --git a/drivers/spi/spi-gxp.c b/drivers/spi/spi-gxp.c
index 15b110183839..c900c2f39b57 100644
--- a/drivers/spi/spi-gxp.c
+++ b/drivers/spi/spi-gxp.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0=or-later
+// SPDX-License-Identifier: GPL-2.0-or-later
/* Copyright (C) 2022 Hewlett-Packard Development Company, L.P. */
#include <linux/iopoll.h>
diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c
index 55f4ee2db002..605acb1bf4b0 100644
--- a/drivers/spi/spi-intel.c
+++ b/drivers/spi/spi-intel.c
@@ -114,7 +114,7 @@
#define ERASE_OPCODE_SHIFT 8
#define ERASE_OPCODE_MASK (0xff << ERASE_OPCODE_SHIFT)
#define ERASE_64K_OPCODE_SHIFT 16
-#define ERASE_64K_OPCODE_MASK (0xff << ERASE_OPCODE_SHIFT)
+#define ERASE_64K_OPCODE_MASK (0xff << ERASE_64K_OPCODE_SHIFT)
/* Flash descriptor fields */
#define FLVALSIG_MAGIC 0x0ff0a55a
diff --git a/drivers/spi/spi-mpc52xx.c b/drivers/spi/spi-mpc52xx.c
index cb075c1acbee..7b64e64c65cf 100644
--- a/drivers/spi/spi-mpc52xx.c
+++ b/drivers/spi/spi-mpc52xx.c
@@ -151,7 +151,7 @@ mpc52xx_spi_fsmstate_idle(int irq, struct mpc52xx_spi *ms, u8 status, u8 data)
int spr, sppr;
u8 ctrl1;
- if (status && (irq != NO_IRQ))
+ if (status && irq)
dev_err(&ms->master->dev, "spurious irq, status=0x%.2x\n",
status);
diff --git a/drivers/spi/spi-qup.c b/drivers/spi/spi-qup.c
index 7d89510dc3f0..678dc51ef017 100644
--- a/drivers/spi/spi-qup.c
+++ b/drivers/spi/spi-qup.c
@@ -1057,6 +1057,8 @@ static int spi_qup_probe(struct platform_device *pdev)
else
master->num_chipselect = num_cs;
+ master->use_gpio_descriptors = true;
+ master->max_native_cs = SPI_NUM_CHIPSELECTS;
master->bus_num = pdev->id;
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LOOP;
master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index c89592b21ffc..904972606bd4 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -1157,6 +1157,11 @@ static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
msg->actual_length += xfer->len;
transfer_phase++;
}
+ if (!xfer->cs_change) {
+ tegra_qspi_transfer_end(spi);
+ spi_transfer_delay_exec(xfer);
+ }
+ ret = 0;
exit:
msg->status = ret;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index b7f16ee8aa0e..cb4f7cc02f8f 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -284,6 +284,25 @@ void target_pr_kref_release(struct kref *kref)
complete(&deve->pr_comp);
}
+/*
+ * Establish UA condition on SCSI device - all LUNs
+ */
+void target_dev_ua_allocate(struct se_device *dev, u8 asc, u8 ascq)
+{
+ struct se_dev_entry *se_deve;
+ struct se_lun *lun;
+
+ spin_lock(&dev->se_port_lock);
+ list_for_each_entry(lun, &dev->dev_sep_list, lun_dev_link) {
+
+ spin_lock(&lun->lun_deve_lock);
+ list_for_each_entry(se_deve, &lun->lun_deve_list, lun_link)
+ core_scsi3_ua_allocate(se_deve, asc, ascq);
+ spin_unlock(&lun->lun_deve_lock);
+ }
+ spin_unlock(&dev->se_port_lock);
+}
+
static void
target_luns_data_has_changed(struct se_node_acl *nacl, struct se_dev_entry *new,
bool skip_new)
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 8351c974cee3..d9266cf558dc 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -230,14 +230,12 @@ static void iblock_unplug_device(struct se_dev_plug *se_plug)
clear_bit(IBD_PLUGF_PLUGGED, &ib_dev_plug->flags);
}
-static unsigned long long iblock_emulate_read_cap_with_block_size(
- struct se_device *dev,
- struct block_device *bd,
- struct request_queue *q)
+static sector_t iblock_get_blocks(struct se_device *dev)
{
- u32 block_size = bdev_logical_block_size(bd);
+ struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
+ u32 block_size = bdev_logical_block_size(ib_dev->ibd_bd);
unsigned long long blocks_long =
- div_u64(bdev_nr_bytes(bd), block_size) - 1;
+ div_u64(bdev_nr_bytes(ib_dev->ibd_bd), block_size) - 1;
if (block_size == dev->dev_attrib.block_size)
return blocks_long;
@@ -829,15 +827,6 @@ fail:
return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
}
-static sector_t iblock_get_blocks(struct se_device *dev)
-{
- struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
- struct block_device *bd = ib_dev->ibd_bd;
- struct request_queue *q = bdev_get_queue(bd);
-
- return iblock_emulate_read_cap_with_block_size(dev, bd, q);
-}
-
static sector_t iblock_get_alignment_offset_lbas(struct se_device *dev)
{
struct iblock_dev *ib_dev = IBLOCK_DEV(dev);
diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index 30fcf69e1a1d..38a6d08f75b3 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -89,6 +89,7 @@ int target_configure_device(struct se_device *dev);
void target_free_device(struct se_device *);
int target_for_each_device(int (*fn)(struct se_device *dev, void *data),
void *data);
+void target_dev_ua_allocate(struct se_device *dev, u8 asc, u8 ascq);
/* target_core_configfs.c */
extern struct configfs_item_operations target_core_dev_item_ops;
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index a1d67554709f..1493b1d01194 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -2956,13 +2956,28 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
__core_scsi3_complete_pro_preempt(dev, pr_reg_n,
(preempt_type == PREEMPT_AND_ABORT) ? &preempt_and_abort_list : NULL,
type, scope, preempt_type);
-
- if (preempt_type == PREEMPT_AND_ABORT)
- core_scsi3_release_preempt_and_abort(
- &preempt_and_abort_list, pr_reg_n);
}
+
spin_unlock(&dev->dev_reservation_lock);
+ /*
+ * SPC-4 5.12.11.2.6 Preempting and aborting
+ * The actions described in this subclause shall be performed
+ * for all I_T nexuses that are registered with the non-zero
+ * SERVICE ACTION RESERVATION KEY value, without regard for
+ * whether the preempted I_T nexuses hold the persistent
+ * reservation. If the SERVICE ACTION RESERVATION KEY field is
+ * set to zero and an all registrants persistent reservation is
+ * present, the device server shall abort all commands for all
+ * registered I_T nexuses.
+ */
+ if (preempt_type == PREEMPT_AND_ABORT) {
+ core_tmr_lun_reset(dev, NULL, &preempt_and_abort_list,
+ cmd);
+ core_scsi3_release_preempt_and_abort(
+ &preempt_and_abort_list, pr_reg_n);
+ }
+
if (pr_tmpl->pr_aptpl_active)
core_scsi3_update_and_write_aptpl(cmd->se_dev, true);
@@ -3022,7 +3037,7 @@ core_scsi3_pro_preempt(struct se_cmd *cmd, int type, int scope, u64 res_key,
if (calling_it_nexus)
continue;
- if (pr_reg->pr_res_key != sa_res_key)
+ if (sa_res_key && pr_reg->pr_res_key != sa_res_key)
continue;
pr_reg_nacl = pr_reg->pr_reg_nacl;
@@ -3425,8 +3440,6 @@ after_iport_check:
* transport protocols where port names are not required;
* d) Register the reservation key specified in the SERVICE ACTION
* RESERVATION KEY field;
- * e) Retain the reservation key specified in the SERVICE ACTION
- * RESERVATION KEY field and associated information;
*
* Also, It is not an error for a REGISTER AND MOVE service action to
* register an I_T nexus that is already registered with the same
@@ -3448,6 +3461,12 @@ after_iport_check:
dest_pr_reg = __core_scsi3_locate_pr_reg(dev, dest_node_acl,
iport_ptr);
new_reg = 1;
+ } else {
+ /*
+ * e) Retain the reservation key specified in the SERVICE ACTION
+ * RESERVATION KEY field and associated information;
+ */
+ dest_pr_reg->pr_res_key = sa_res_key;
}
/*
* f) Release the persistent reservation for the persistent reservation
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7838dc20f713..5926316252eb 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3531,8 +3531,7 @@ static void target_tmr_work(struct work_struct *work)
tmr->response = (!ret) ? TMR_FUNCTION_COMPLETE :
TMR_FUNCTION_REJECTED;
if (tmr->response == TMR_FUNCTION_COMPLETE) {
- target_ua_allocate_lun(cmd->se_sess->se_node_acl,
- cmd->orig_fe_lun, 0x29,
+ target_dev_ua_allocate(dev, 0x29,
ASCQ_29H_BUS_DEVICE_RESET_FUNCTION_OCCURRED);
}
break;
diff --git a/drivers/tty/serial/8250/8250_gsc.c b/drivers/tty/serial/8250/8250_parisc.c
index 948d0a1c6ae8..948d0a1c6ae8 100644
--- a/drivers/tty/serial/8250/8250_gsc.c
+++ b/drivers/tty/serial/8250/8250_parisc.c
diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig
index d0b49e15fbf5..b0f62345bc84 100644
--- a/drivers/tty/serial/8250/Kconfig
+++ b/drivers/tty/serial/8250/Kconfig
@@ -116,9 +116,9 @@ config SERIAL_8250_CONSOLE
If unsure, say N.
-config SERIAL_8250_GSC
+config SERIAL_8250_PARISC
tristate
- depends on SERIAL_8250 && GSC
+ depends on SERIAL_8250 && PARISC
default SERIAL_8250
config SERIAL_8250_DMA
diff --git a/drivers/tty/serial/8250/Makefile b/drivers/tty/serial/8250/Makefile
index bee908f99ea0..1615bfdde2a0 100644
--- a/drivers/tty/serial/8250/Makefile
+++ b/drivers/tty/serial/8250/Makefile
@@ -12,7 +12,7 @@ obj-$(CONFIG_SERIAL_8250) += 8250.o 8250_base.o
8250_base-$(CONFIG_SERIAL_8250_DMA) += 8250_dma.o
8250_base-$(CONFIG_SERIAL_8250_DWLIB) += 8250_dwlib.o
8250_base-$(CONFIG_SERIAL_8250_FINTEK) += 8250_fintek.o
-obj-$(CONFIG_SERIAL_8250_GSC) += 8250_gsc.o
+obj-$(CONFIG_SERIAL_8250_PARISC) += 8250_parisc.o
obj-$(CONFIG_SERIAL_8250_PCI) += 8250_pci.o
obj-$(CONFIG_SERIAL_8250_EXAR) += 8250_exar.o
obj-$(CONFIG_SERIAL_8250_HP300) += 8250_hp300.o
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 7256e6c43ca6..b1f59a5fe632 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -772,7 +772,7 @@ static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 mask)
}
/**
- * ufshcd_utmrl_clear - Clear a bit in UTRMLCLR register
+ * ufshcd_utmrl_clear - Clear a bit in UTMRLCLR register
* @hba: per adapter instance
* @pos: position of the bit to be cleared
*/
@@ -3098,7 +3098,7 @@ static int ufshcd_query_flag_retry(struct ufs_hba *hba,
if (ret)
dev_err(hba->dev,
- "%s: query attribute, opcode %d, idn %d, failed with error %d after %d retries\n",
+ "%s: query flag, opcode %d, idn %d, failed with error %d after %d retries\n",
__func__, opcode, idn, ret, retries);
return ret;
}
diff --git a/drivers/ufs/core/ufshpb.c b/drivers/ufs/core/ufshpb.c
index 3d69a81c5b17..b7f412d0f301 100644
--- a/drivers/ufs/core/ufshpb.c
+++ b/drivers/ufs/core/ufshpb.c
@@ -383,7 +383,7 @@ int ufshpb_prep(struct ufs_hba *hba, struct ufshcd_lrb *lrbp)
rgn = hpb->rgn_tbl + rgn_idx;
srgn = rgn->srgn_tbl + srgn_idx;
- /* If command type is WRITE or DISCARD, set bitmap as drity */
+ /* If command type is WRITE or DISCARD, set bitmap as dirty */
if (ufshpb_is_write_or_discard(cmd)) {
ufshpb_iterate_rgn(hpb, rgn_idx, srgn_idx, srgn_offset,
transfer_len, true);
@@ -616,7 +616,7 @@ static void ufshpb_activate_subregion(struct ufshpb_lu *hpb,
static enum rq_end_io_ret ufshpb_umap_req_compl_fn(struct request *req,
blk_status_t error)
{
- struct ufshpb_req *umap_req = (struct ufshpb_req *)req->end_io_data;
+ struct ufshpb_req *umap_req = req->end_io_data;
ufshpb_put_req(umap_req->hpb, umap_req);
return RQ_END_IO_NONE;
@@ -625,7 +625,7 @@ static enum rq_end_io_ret ufshpb_umap_req_compl_fn(struct request *req,
static enum rq_end_io_ret ufshpb_map_req_compl_fn(struct request *req,
blk_status_t error)
{
- struct ufshpb_req *map_req = (struct ufshpb_req *) req->end_io_data;
+ struct ufshpb_req *map_req = req->end_io_data;
struct ufshpb_lu *hpb = map_req->hpb;
struct ufshpb_subregion *srgn;
unsigned long flags;
diff --git a/drivers/ufs/host/ufs-qcom-ice.c b/drivers/ufs/host/ufs-qcom-ice.c
index 745e48ec598f..62387ccd5b30 100644
--- a/drivers/ufs/host/ufs-qcom-ice.c
+++ b/drivers/ufs/host/ufs-qcom-ice.c
@@ -118,7 +118,6 @@ int ufs_qcom_ice_init(struct ufs_qcom_host *host)
host->ice_mmio = devm_ioremap_resource(dev, res);
if (IS_ERR(host->ice_mmio)) {
err = PTR_ERR(host->ice_mmio);
- dev_err(dev, "Failed to map ICE registers; err=%d\n", err);
return err;
}
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index ea51624461b5..c0e7c76dc5c8 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -23,6 +23,7 @@
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/of.h>
+#include <linux/of_graph.h>
#include <linux/acpi.h>
#include <linux/pinctrl/consumer.h>
#include <linux/reset.h>
@@ -85,7 +86,7 @@ static int dwc3_get_dr_mode(struct dwc3 *dwc)
* mode. If the controller supports DRD but the dr_mode is not
* specified or set to OTG, then set the mode to peripheral.
*/
- if (mode == USB_DR_MODE_OTG &&
+ if (mode == USB_DR_MODE_OTG && !dwc->edev &&
(!IS_ENABLED(CONFIG_USB_ROLE_SWITCH) ||
!device_property_read_bool(dwc->dev, "usb-role-switch")) &&
!DWC3_VER_IS_PRIOR(DWC3, 330A))
@@ -1690,6 +1691,46 @@ static void dwc3_check_params(struct dwc3 *dwc)
}
}
+static struct extcon_dev *dwc3_get_extcon(struct dwc3 *dwc)
+{
+ struct device *dev = dwc->dev;
+ struct device_node *np_phy;
+ struct extcon_dev *edev = NULL;
+ const char *name;
+
+ if (device_property_read_bool(dev, "extcon"))
+ return extcon_get_edev_by_phandle(dev, 0);
+
+ /*
+ * Device tree platforms should get extcon via phandle.
+ * On ACPI platforms, we get the name from a device property.
+ * This device property is for kernel internal use only and
+ * is expected to be set by the glue code.
+ */
+ if (device_property_read_string(dev, "linux,extcon-name", &name) == 0)
+ return extcon_get_extcon_dev(name);
+
+ /*
+ * Try to get an extcon device from the USB PHY controller's "port"
+ * node. Check if it has the "port" node first, to avoid printing the
+ * error message from underlying code, as it's a valid case: extcon
+ * device (and "port" node) may be missing in case of "usb-role-switch"
+ * or OTG mode.
+ */
+ np_phy = of_parse_phandle(dev->of_node, "phys", 0);
+ if (of_graph_is_present(np_phy)) {
+ struct device_node *np_conn;
+
+ np_conn = of_graph_get_remote_node(np_phy, -1, -1);
+ if (np_conn)
+ edev = extcon_find_edev_by_node(np_conn);
+ of_node_put(np_conn);
+ }
+ of_node_put(np_phy);
+
+ return edev;
+}
+
static int dwc3_probe(struct platform_device *pdev)
{
struct device *dev = &pdev->dev;
@@ -1840,6 +1881,12 @@ static int dwc3_probe(struct platform_device *pdev)
goto err2;
}
+ dwc->edev = dwc3_get_extcon(dwc);
+ if (IS_ERR(dwc->edev)) {
+ ret = dev_err_probe(dwc->dev, PTR_ERR(dwc->edev), "failed to get extcon\n");
+ goto err3;
+ }
+
ret = dwc3_get_dr_mode(dwc);
if (ret)
goto err3;
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index 8cad9e7d3368..039bf241769a 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -8,7 +8,6 @@
*/
#include <linux/extcon.h>
-#include <linux/of_graph.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include <linux/property.h>
@@ -439,51 +438,6 @@ static int dwc3_drd_notifier(struct notifier_block *nb,
return NOTIFY_DONE;
}
-static struct extcon_dev *dwc3_get_extcon(struct dwc3 *dwc)
-{
- struct device *dev = dwc->dev;
- struct device_node *np_phy;
- struct extcon_dev *edev = NULL;
- const char *name;
-
- if (device_property_read_bool(dev, "extcon"))
- return extcon_get_edev_by_phandle(dev, 0);
-
- /*
- * Device tree platforms should get extcon via phandle.
- * On ACPI platforms, we get the name from a device property.
- * This device property is for kernel internal use only and
- * is expected to be set by the glue code.
- */
- if (device_property_read_string(dev, "linux,extcon-name", &name) == 0) {
- edev = extcon_get_extcon_dev(name);
- if (!edev)
- return ERR_PTR(-EPROBE_DEFER);
-
- return edev;
- }
-
- /*
- * Try to get an extcon device from the USB PHY controller's "port"
- * node. Check if it has the "port" node first, to avoid printing the
- * error message from underlying code, as it's a valid case: extcon
- * device (and "port" node) may be missing in case of "usb-role-switch"
- * or OTG mode.
- */
- np_phy = of_parse_phandle(dev->of_node, "phys", 0);
- if (of_graph_is_present(np_phy)) {
- struct device_node *np_conn;
-
- np_conn = of_graph_get_remote_node(np_phy, -1, -1);
- if (np_conn)
- edev = extcon_find_edev_by_node(np_conn);
- of_node_put(np_conn);
- }
- of_node_put(np_phy);
-
- return edev;
-}
-
#if IS_ENABLED(CONFIG_USB_ROLE_SWITCH)
#define ROLE_SWITCH 1
static int dwc3_usb_role_switch_set(struct usb_role_switch *sw,
@@ -588,10 +542,6 @@ int dwc3_drd_init(struct dwc3 *dwc)
device_property_read_bool(dwc->dev, "usb-role-switch"))
return dwc3_setup_role_switch(dwc);
- dwc->edev = dwc3_get_extcon(dwc);
- if (IS_ERR(dwc->edev))
- return PTR_ERR(dwc->edev);
-
if (dwc->edev) {
dwc->edev_nb.notifier_call = dwc3_drd_notifier;
ret = extcon_register_notifier(dwc->edev, EXTCON_USB_HOST,
diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
index 6c14a79279f9..fea5290de83f 100644
--- a/drivers/usb/dwc3/dwc3-st.c
+++ b/drivers/usb/dwc3/dwc3-st.c
@@ -251,7 +251,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
/* Manage SoftReset */
reset_control_deassert(dwc3_data->rstc_rst);
- child = of_get_child_by_name(node, "usb");
+ child = of_get_compatible_child(node, "snps,dwc3");
if (!child) {
dev_err(&pdev->dev, "failed to find dwc3 core node\n");
ret = -ENODEV;
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 079cd333632e..5fe2d136dff5 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1292,8 +1292,8 @@ static void dwc3_prepare_one_trb(struct dwc3_ep *dep,
trb->ctrl = DWC3_TRBCTL_ISOCHRONOUS;
}
- /* always enable Interrupt on Missed ISOC */
- trb->ctrl |= DWC3_TRB_CTRL_ISP_IMI;
+ if (!no_interrupt && !chain)
+ trb->ctrl |= DWC3_TRB_CTRL_ISP_IMI;
break;
case USB_ENDPOINT_XFER_BULK:
@@ -1698,6 +1698,16 @@ static int __dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force, bool int
cmd |= DWC3_DEPCMD_PARAM(dep->resource_index);
memset(&params, 0, sizeof(params));
ret = dwc3_send_gadget_ep_cmd(dep, cmd, &params);
+ /*
+ * If the End Transfer command was timed out while the device is
+ * not in SETUP phase, it's possible that an incoming Setup packet
+ * may prevent the command's completion. Let's retry when the
+ * ep0state returns to EP0_SETUP_PHASE.
+ */
+ if (ret == -ETIMEDOUT && dep->dwc->ep0state != EP0_SETUP_PHASE) {
+ dep->flags |= DWC3_EP_DELAY_STOP;
+ return 0;
+ }
WARN_ON_ONCE(ret);
dep->resource_index = 0;
@@ -3238,6 +3248,10 @@ static int dwc3_gadget_ep_reclaim_completed_trb(struct dwc3_ep *dep,
if (event->status & DEPEVT_STATUS_SHORT && !chain)
return 1;
+ if ((trb->ctrl & DWC3_TRB_CTRL_ISP_IMI) &&
+ DWC3_TRB_SIZE_TRBSTS(trb->size) == DWC3_TRBSTS_MISSED_ISOC)
+ return 1;
+
if ((trb->ctrl & DWC3_TRB_CTRL_IOC) ||
(trb->ctrl & DWC3_TRB_CTRL_LST))
return 1;
@@ -3719,7 +3733,7 @@ void dwc3_stop_active_transfer(struct dwc3_ep *dep, bool force,
* timeout. Delay issuing the End Transfer command until the Setup TRB is
* prepared.
*/
- if (dwc->ep0state != EP0_SETUP_PHASE) {
+ if (dwc->ep0state != EP0_SETUP_PHASE && !dwc->delayed_status) {
dep->flags |= DWC3_EP_DELAY_STOP;
return;
}
diff --git a/drivers/usb/gadget/function/uvc_queue.c b/drivers/usb/gadget/function/uvc_queue.c
index ec500ee499ee..0aa3d7e1f3cc 100644
--- a/drivers/usb/gadget/function/uvc_queue.c
+++ b/drivers/usb/gadget/function/uvc_queue.c
@@ -304,6 +304,7 @@ int uvcg_queue_enable(struct uvc_video_queue *queue, int enable)
queue->sequence = 0;
queue->buf_used = 0;
+ queue->flags &= ~UVC_QUEUE_DROP_INCOMPLETE;
} else {
ret = vb2_streamoff(&queue->queue, queue->queue.type);
if (ret < 0)
@@ -329,10 +330,11 @@ int uvcg_queue_enable(struct uvc_video_queue *queue, int enable)
void uvcg_complete_buffer(struct uvc_video_queue *queue,
struct uvc_buffer *buf)
{
- if ((queue->flags & UVC_QUEUE_DROP_INCOMPLETE) &&
- buf->length != buf->bytesused) {
- buf->state = UVC_BUF_STATE_QUEUED;
+ if (queue->flags & UVC_QUEUE_DROP_INCOMPLETE) {
+ queue->flags &= ~UVC_QUEUE_DROP_INCOMPLETE;
+ buf->state = UVC_BUF_STATE_ERROR;
vb2_set_plane_payload(&buf->buf.vb2_buf, 0, 0);
+ vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_ERROR);
return;
}
diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
index bb037fcc90e6..dd1c6b2ca7c6 100644
--- a/drivers/usb/gadget/function/uvc_video.c
+++ b/drivers/usb/gadget/function/uvc_video.c
@@ -88,6 +88,7 @@ uvc_video_encode_bulk(struct usb_request *req, struct uvc_video *video,
struct uvc_buffer *buf)
{
void *mem = req->buf;
+ struct uvc_request *ureq = req->context;
int len = video->req_size;
int ret;
@@ -113,13 +114,14 @@ uvc_video_encode_bulk(struct usb_request *req, struct uvc_video *video,
video->queue.buf_used = 0;
buf->state = UVC_BUF_STATE_DONE;
list_del(&buf->queue);
- uvcg_complete_buffer(&video->queue, buf);
video->fid ^= UVC_STREAM_FID;
+ ureq->last_buf = buf;
video->payload_size = 0;
}
if (video->payload_size == video->max_payload_size ||
+ video->queue.flags & UVC_QUEUE_DROP_INCOMPLETE ||
buf->bytesused == video->queue.buf_used)
video->payload_size = 0;
}
@@ -155,10 +157,10 @@ uvc_video_encode_isoc_sg(struct usb_request *req, struct uvc_video *video,
sg = sg_next(sg);
for_each_sg(sg, iter, ureq->sgt.nents - 1, i) {
- if (!len || !buf->sg || !sg_dma_len(buf->sg))
+ if (!len || !buf->sg || !buf->sg->length)
break;
- sg_left = sg_dma_len(buf->sg) - buf->offset;
+ sg_left = buf->sg->length - buf->offset;
part = min_t(unsigned int, len, sg_left);
sg_set_page(iter, sg_page(buf->sg), part, buf->offset);
@@ -180,7 +182,8 @@ uvc_video_encode_isoc_sg(struct usb_request *req, struct uvc_video *video,
req->length -= len;
video->queue.buf_used += req->length - header_len;
- if (buf->bytesused == video->queue.buf_used || !buf->sg) {
+ if (buf->bytesused == video->queue.buf_used || !buf->sg ||
+ video->queue.flags & UVC_QUEUE_DROP_INCOMPLETE) {
video->queue.buf_used = 0;
buf->state = UVC_BUF_STATE_DONE;
buf->offset = 0;
@@ -195,6 +198,7 @@ uvc_video_encode_isoc(struct usb_request *req, struct uvc_video *video,
struct uvc_buffer *buf)
{
void *mem = req->buf;
+ struct uvc_request *ureq = req->context;
int len = video->req_size;
int ret;
@@ -209,12 +213,13 @@ uvc_video_encode_isoc(struct usb_request *req, struct uvc_video *video,
req->length = video->req_size - len;
- if (buf->bytesused == video->queue.buf_used) {
+ if (buf->bytesused == video->queue.buf_used ||
+ video->queue.flags & UVC_QUEUE_DROP_INCOMPLETE) {
video->queue.buf_used = 0;
buf->state = UVC_BUF_STATE_DONE;
list_del(&buf->queue);
- uvcg_complete_buffer(&video->queue, buf);
video->fid ^= UVC_STREAM_FID;
+ ureq->last_buf = buf;
}
}
@@ -255,6 +260,11 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)
case 0:
break;
+ case -EXDEV:
+ uvcg_dbg(&video->uvc->func, "VS request missed xfer.\n");
+ queue->flags |= UVC_QUEUE_DROP_INCOMPLETE;
+ break;
+
case -ESHUTDOWN: /* disconnect from host. */
uvcg_dbg(&video->uvc->func, "VS request cancelled.\n");
uvcg_queue_cancel(queue, 1);
@@ -431,7 +441,8 @@ static void uvcg_video_pump(struct work_struct *work)
/* Endpoint now owns the request */
req = NULL;
- video->req_int_count++;
+ if (buf->state != UVC_BUF_STATE_DONE)
+ video->req_int_count++;
}
if (!req)
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/dev.c b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
index b0dfca43fbdc..4f3bc27c1c62 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/dev.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/dev.c
@@ -591,6 +591,7 @@ int ast_vhub_init_dev(struct ast_vhub *vhub, unsigned int idx)
d->gadget.max_speed = USB_SPEED_HIGH;
d->gadget.speed = USB_SPEED_UNKNOWN;
d->gadget.dev.of_node = vhub->pdev->dev.of_node;
+ d->gadget.dev.of_node_reused = true;
rc = usb_add_gadget_udc(d->port_dev, &d->gadget);
if (rc != 0)
diff --git a/drivers/usb/gadget/udc/bdc/bdc_udc.c b/drivers/usb/gadget/udc/bdc/bdc_udc.c
index 5ac0ef88334e..53ffaf4e2e37 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_udc.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_udc.c
@@ -151,6 +151,7 @@ static void bdc_uspc_disconnected(struct bdc *bdc, bool reinit)
bdc->delayed_status = false;
bdc->reinit = reinit;
bdc->test_mode = false;
+ usb_gadget_set_state(&bdc->gadget, USB_STATE_NOTATTACHED);
}
/* TNotify wkaeup timer */
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 9e56aa28efcd..81ca2bc1f0be 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -889,15 +889,19 @@ void xhci_free_virt_device(struct xhci_hcd *xhci, int slot_id)
if (dev->eps[i].stream_info)
xhci_free_stream_info(xhci,
dev->eps[i].stream_info);
- /* Endpoints on the TT/root port lists should have been removed
- * when usb_disable_device() was called for the device.
- * We can't drop them anyway, because the udev might have gone
- * away by this point, and we can't tell what speed it was.
+ /*
+ * Endpoints are normally deleted from the bandwidth list when
+ * endpoints are dropped, before device is freed.
+ * If host is dying or being removed then endpoints aren't
+ * dropped cleanly, so delete the endpoint from list here.
+ * Only applicable for hosts with software bandwidth checking.
*/
- if (!list_empty(&dev->eps[i].bw_endpoint_list))
- xhci_warn(xhci, "Slot %u endpoint %u "
- "not removed from BW list!\n",
- slot_id, i);
+
+ if (!list_empty(&dev->eps[i].bw_endpoint_list)) {
+ list_del_init(&dev->eps[i].bw_endpoint_list);
+ xhci_dbg(xhci, "Slot %u endpoint %u not removed from BW list!\n",
+ slot_id, i);
+ }
}
/* If this is a hub, free the TT(s) from the TT list */
xhci_free_tt_info(xhci, dev, slot_id);
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 40228a3d77a0..7bccbe50bab1 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -58,25 +58,13 @@
#define PCI_DEVICE_ID_INTEL_CML_XHCI 0xa3af
#define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13
#define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138
-#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI 0x461e
-#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_XHCI 0x464e
-#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed
-#define PCI_DEVICE_ID_INTEL_RAPTOR_LAKE_XHCI 0xa71e
-#define PCI_DEVICE_ID_INTEL_METEOR_LAKE_XHCI 0x7ec0
+#define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed
#define PCI_DEVICE_ID_AMD_RENOIR_XHCI 0x1639
#define PCI_DEVICE_ID_AMD_PROMONTORYA_4 0x43b9
#define PCI_DEVICE_ID_AMD_PROMONTORYA_3 0x43ba
#define PCI_DEVICE_ID_AMD_PROMONTORYA_2 0x43bb
#define PCI_DEVICE_ID_AMD_PROMONTORYA_1 0x43bc
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_1 0x161a
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_2 0x161b
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 0x161d
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 0x161e
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 0x15d6
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 0x15d7
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 0x161c
-#define PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8 0x161f
#define PCI_DEVICE_ID_ASMEDIA_1042_XHCI 0x1042
#define PCI_DEVICE_ID_ASMEDIA_1042A_XHCI 0x1142
@@ -258,6 +246,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_MISSING_CAS;
if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+ pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI)
+ xhci->quirks |= XHCI_RESET_TO_DEFAULT;
+
+ if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
(pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_2C_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_4C_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_LP_XHCI ||
@@ -268,12 +260,7 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
pdev->device == PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI ||
pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_RAPTOR_LAKE_XHCI ||
- pdev->device == PCI_DEVICE_ID_INTEL_METEOR_LAKE_XHCI))
+ pdev->device == PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI))
xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
if (pdev->vendor == PCI_VENDOR_ID_ETRON &&
@@ -306,8 +293,14 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
}
if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
- pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI)
+ pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) {
+ /*
+ * try to tame the ASMedia 1042 controller which reports 0.96
+ * but appears to behave more like 1.0
+ */
+ xhci->quirks |= XHCI_SPURIOUS_SUCCESS;
xhci->quirks |= XHCI_BROKEN_STREAMS;
+ }
if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
pdev->device == PCI_DEVICE_ID_ASMEDIA_1042A_XHCI) {
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
@@ -336,15 +329,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
pdev->device == PCI_DEVICE_ID_AMD_PROMONTORYA_4))
xhci->quirks |= XHCI_NO_SOFT_RETRY;
- if (pdev->vendor == PCI_VENDOR_ID_AMD &&
- (pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_1 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_2 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_3 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_4 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_5 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_6 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_7 ||
- pdev->device == PCI_DEVICE_ID_AMD_YELLOW_CARP_XHCI_8))
+ /* xHC spec requires PCI devices to support D3hot and D3cold */
+ if (xhci->hci_version >= 0x120)
xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
if (xhci->quirks & XHCI_RESET_ON_RESUME)
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 5176765c4013..79d7931c048a 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -810,9 +810,15 @@ void xhci_shutdown(struct usb_hcd *hcd)
spin_lock_irq(&xhci->lock);
xhci_halt(xhci);
- /* Workaround for spurious wakeups at shutdown with HSW */
- if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
+
+ /*
+ * Workaround for spurious wakeps at shutdown with HSW, and for boot
+ * firmware delay in ADL-P PCH if port are left in U3 at shutdown
+ */
+ if (xhci->quirks & XHCI_SPURIOUS_WAKEUP ||
+ xhci->quirks & XHCI_RESET_TO_DEFAULT)
xhci_reset(xhci, XHCI_RESET_SHORT_USEC);
+
spin_unlock_irq(&xhci->lock);
xhci_cleanup_msix(xhci);
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index c0964fe8ac12..cc084d9505cd 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1897,6 +1897,7 @@ struct xhci_hcd {
#define XHCI_BROKEN_D3COLD BIT_ULL(41)
#define XHCI_EP_CTX_BROKEN_DCS BIT_ULL(42)
#define XHCI_SUSPEND_RESUME_CLKS BIT_ULL(43)
+#define XHCI_RESET_TO_DEFAULT BIT_ULL(44)
unsigned int num_active_eps;
unsigned int limit_active_eps;
diff --git a/drivers/usb/misc/sisusbvga/sisusb_struct.h b/drivers/usb/misc/sisusbvga/sisusb_struct.h
index 3df64d2a9d43..a86032a26d36 100644
--- a/drivers/usb/misc/sisusbvga/sisusb_struct.h
+++ b/drivers/usb/misc/sisusbvga/sisusb_struct.h
@@ -91,7 +91,7 @@ struct SiS_Ext {
unsigned char VB_ExtTVYFilterIndex;
unsigned char VB_ExtTVYFilterIndexROM661;
unsigned char REFindex;
- char ROMMODEIDX661;
+ signed char ROMMODEIDX661;
};
struct SiS_Ext2 {
diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 74fb5a4c6f21..a7987fc764cc 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -183,16 +183,6 @@ out:
}
EXPORT_SYMBOL_GPL(ucsi_send_command);
-int ucsi_resume(struct ucsi *ucsi)
-{
- u64 command;
-
- /* Restore UCSI notification enable mask after system resume */
- command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy;
-
- return ucsi_send_command(ucsi, command, NULL, 0);
-}
-EXPORT_SYMBOL_GPL(ucsi_resume);
/* -------------------------------------------------------------------------- */
struct ucsi_work {
@@ -744,6 +734,7 @@ static void ucsi_partner_change(struct ucsi_connector *con)
static int ucsi_check_connection(struct ucsi_connector *con)
{
+ u8 prev_flags = con->status.flags;
u64 command;
int ret;
@@ -754,10 +745,13 @@ static int ucsi_check_connection(struct ucsi_connector *con)
return ret;
}
+ if (con->status.flags == prev_flags)
+ return 0;
+
if (con->status.flags & UCSI_CONSTAT_CONNECTED) {
- if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) ==
- UCSI_CONSTAT_PWR_OPMODE_PD)
- ucsi_partner_task(con, ucsi_check_altmodes, 30, 0);
+ ucsi_register_partner(con);
+ ucsi_pwr_opmode_change(con);
+ ucsi_partner_change(con);
} else {
ucsi_partner_change(con);
ucsi_port_psy_changed(con);
@@ -1276,6 +1270,28 @@ err:
return ret;
}
+int ucsi_resume(struct ucsi *ucsi)
+{
+ struct ucsi_connector *con;
+ u64 command;
+ int ret;
+
+ /* Restore UCSI notification enable mask after system resume */
+ command = UCSI_SET_NOTIFICATION_ENABLE | ucsi->ntfy;
+ ret = ucsi_send_command(ucsi, command, NULL, 0);
+ if (ret < 0)
+ return ret;
+
+ for (con = ucsi->connector; con->port; con++) {
+ mutex_lock(&con->lock);
+ ucsi_check_connection(con);
+ mutex_unlock(&con->lock);
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ucsi_resume);
+
static void ucsi_init_work(struct work_struct *work)
{
struct ucsi *ucsi = container_of(work, struct ucsi, work.work);
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 8873c1644a29..ce0c8ef80c04 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -185,6 +185,15 @@ static int ucsi_acpi_remove(struct platform_device *pdev)
return 0;
}
+static int ucsi_acpi_resume(struct device *dev)
+{
+ struct ucsi_acpi *ua = dev_get_drvdata(dev);
+
+ return ucsi_resume(ua->ucsi);
+}
+
+static DEFINE_SIMPLE_DEV_PM_OPS(ucsi_acpi_pm_ops, NULL, ucsi_acpi_resume);
+
static const struct acpi_device_id ucsi_acpi_match[] = {
{ "PNP0CA0", 0 },
{ },
@@ -194,6 +203,7 @@ MODULE_DEVICE_TABLE(acpi, ucsi_acpi_match);
static struct platform_driver ucsi_acpi_platform_driver = {
.driver = {
.name = "ucsi_acpi",
+ .pm = pm_ptr(&ucsi_acpi_pm_ops),
.acpi_match_table = ACPI_PTR(ucsi_acpi_match),
},
.probe = ucsi_acpi_probe,
diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c
index 9e6bcc03a1a4..41e77de1ea82 100644
--- a/drivers/video/aperture.c
+++ b/drivers/video/aperture.c
@@ -340,12 +340,9 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na
size = pci_resource_len(pdev, bar);
ret = aperture_remove_conflicting_devices(base, size, primary, name);
if (ret)
- break;
+ return ret;
}
- if (ret)
- return ret;
-
/*
* WARNING: Apparently we must kick fbdev drivers before vgacon,
* otherwise the vga fbdev driver falls over.
diff --git a/drivers/video/fbdev/cyber2000fb.c b/drivers/video/fbdev/cyber2000fb.c
index 585af90a68a5..31ff1da82c05 100644
--- a/drivers/video/fbdev/cyber2000fb.c
+++ b/drivers/video/fbdev/cyber2000fb.c
@@ -1796,6 +1796,7 @@ failed_ioremap:
failed_regions:
cyberpro_free_fb_info(cfb);
failed_release:
+ pci_disable_device(dev);
return err;
}
@@ -1812,6 +1813,7 @@ static void cyberpro_pci_remove(struct pci_dev *dev)
int_cfb_info = NULL;
pci_release_regions(dev);
+ pci_disable_device(dev);
}
}
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
index ae76a2111c77..11922b009ed7 100644
--- a/drivers/video/fbdev/da8xx-fb.c
+++ b/drivers/video/fbdev/da8xx-fb.c
@@ -1076,7 +1076,8 @@ static int fb_remove(struct platform_device *dev)
if (par->lcd_supply) {
ret = regulator_disable(par->lcd_supply);
if (ret)
- return ret;
+ dev_warn(&dev->dev, "Failed to disable regulator (%pe)\n",
+ ERR_PTR(ret));
}
lcd_disable_raster(DA8XX_FRAME_WAIT);
diff --git a/drivers/video/fbdev/gbefb.c b/drivers/video/fbdev/gbefb.c
index 1582c718329c..000b4aa44241 100644
--- a/drivers/video/fbdev/gbefb.c
+++ b/drivers/video/fbdev/gbefb.c
@@ -1060,14 +1060,14 @@ static const struct fb_ops gbefb_ops = {
static ssize_t gbefb_show_memsize(struct device *dev, struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%u\n", gbe_mem_size);
+ return sysfs_emit(buf, "%u\n", gbe_mem_size);
}
static DEVICE_ATTR(size, S_IRUGO, gbefb_show_memsize, NULL);
static ssize_t gbefb_show_rev(struct device *device, struct device_attribute *attr, char *buf)
{
- return snprintf(buf, PAGE_SIZE, "%d\n", gbe_revision);
+ return sysfs_emit(buf, "%d\n", gbe_revision);
}
static DEVICE_ATTR(revision, S_IRUGO, gbefb_show_rev, NULL);
diff --git a/drivers/video/fbdev/sis/sis_accel.c b/drivers/video/fbdev/sis/sis_accel.c
index 1914ab5a5a91..5850e4325f07 100644
--- a/drivers/video/fbdev/sis/sis_accel.c
+++ b/drivers/video/fbdev/sis/sis_accel.c
@@ -202,7 +202,7 @@ SiS310SubsequentScreenToScreenCopy(struct sis_video_info *ivideo, int src_x, int
* and destination blitting areas overlap and
* adapt the bitmap addresses synchronously
* if the coordinates exceed the valid range.
- * The the areas do not overlap, we do our
+ * The areas do not overlap, we do our
* normal check.
*/
if((mymax - mymin) < height) {
diff --git a/drivers/video/fbdev/sis/vstruct.h b/drivers/video/fbdev/sis/vstruct.h
index ea94d214dcff..d7a14e63ba5a 100644
--- a/drivers/video/fbdev/sis/vstruct.h
+++ b/drivers/video/fbdev/sis/vstruct.h
@@ -148,7 +148,7 @@ struct SiS_Ext {
unsigned char VB_ExtTVYFilterIndex;
unsigned char VB_ExtTVYFilterIndexROM661;
unsigned char REFindex;
- char ROMMODEIDX661;
+ signed char ROMMODEIDX661;
};
struct SiS_Ext2 {
diff --git a/drivers/video/fbdev/sm501fb.c b/drivers/video/fbdev/sm501fb.c
index fce6cfbadfd6..f743bfbde2a6 100644
--- a/drivers/video/fbdev/sm501fb.c
+++ b/drivers/video/fbdev/sm501fb.c
@@ -1166,7 +1166,7 @@ static ssize_t sm501fb_crtsrc_show(struct device *dev,
ctrl = smc501_readl(info->regs + SM501_DC_CRT_CONTROL);
ctrl &= SM501_DC_CRT_CONTROL_SEL;
- return snprintf(buf, PAGE_SIZE, "%s\n", ctrl ? "crt" : "panel");
+ return sysfs_emit(buf, "%s\n", ctrl ? "crt" : "panel");
}
/* sm501fb_crtsrc_show
diff --git a/drivers/video/fbdev/smscufx.c b/drivers/video/fbdev/smscufx.c
index e65bdc499c23..9343b7a4ac89 100644
--- a/drivers/video/fbdev/smscufx.c
+++ b/drivers/video/fbdev/smscufx.c
@@ -97,7 +97,6 @@ struct ufx_data {
struct kref kref;
int fb_count;
bool virtualized; /* true when physical usb device not present */
- struct delayed_work free_framebuffer_work;
atomic_t usb_active; /* 0 = update virtual buffer, but no usb traffic */
atomic_t lost_pixels; /* 1 = a render op failed. Need screen refresh */
u8 *edid; /* null until we read edid from hw or get from sysfs */
@@ -1117,15 +1116,24 @@ static void ufx_free(struct kref *kref)
{
struct ufx_data *dev = container_of(kref, struct ufx_data, kref);
- /* this function will wait for all in-flight urbs to complete */
- if (dev->urbs.count > 0)
- ufx_free_urb_list(dev);
+ kfree(dev);
+}
- pr_debug("freeing ufx_data %p", dev);
+static void ufx_ops_destory(struct fb_info *info)
+{
+ struct ufx_data *dev = info->par;
+ int node = info->node;
- kfree(dev);
+ /* Assume info structure is freed after this point */
+ framebuffer_release(info);
+
+ pr_debug("fb_info for /dev/fb%d has been freed", node);
+
+ /* release reference taken by kref_init in probe() */
+ kref_put(&dev->kref, ufx_free);
}
+
static void ufx_release_urb_work(struct work_struct *work)
{
struct urb_node *unode = container_of(work, struct urb_node,
@@ -1134,14 +1142,9 @@ static void ufx_release_urb_work(struct work_struct *work)
up(&unode->dev->urbs.limit_sem);
}
-static void ufx_free_framebuffer_work(struct work_struct *work)
+static void ufx_free_framebuffer(struct ufx_data *dev)
{
- struct ufx_data *dev = container_of(work, struct ufx_data,
- free_framebuffer_work.work);
struct fb_info *info = dev->info;
- int node = info->node;
-
- unregister_framebuffer(info);
if (info->cmap.len != 0)
fb_dealloc_cmap(&info->cmap);
@@ -1153,11 +1156,6 @@ static void ufx_free_framebuffer_work(struct work_struct *work)
dev->info = NULL;
- /* Assume info structure is freed after this point */
- framebuffer_release(info);
-
- pr_debug("fb_info for /dev/fb%d has been freed", node);
-
/* ref taken in probe() as part of registering framebfufer */
kref_put(&dev->kref, ufx_free);
}
@@ -1169,11 +1167,13 @@ static int ufx_ops_release(struct fb_info *info, int user)
{
struct ufx_data *dev = info->par;
+ mutex_lock(&disconnect_mutex);
+
dev->fb_count--;
/* We can't free fb_info here - fbmem will touch it when we return */
if (dev->virtualized && (dev->fb_count == 0))
- schedule_delayed_work(&dev->free_framebuffer_work, HZ);
+ ufx_free_framebuffer(dev);
if ((dev->fb_count == 0) && (info->fbdefio)) {
fb_deferred_io_cleanup(info);
@@ -1186,6 +1186,8 @@ static int ufx_ops_release(struct fb_info *info, int user)
kref_put(&dev->kref, ufx_free);
+ mutex_unlock(&disconnect_mutex);
+
return 0;
}
@@ -1292,6 +1294,7 @@ static const struct fb_ops ufx_ops = {
.fb_blank = ufx_ops_blank,
.fb_check_var = ufx_ops_check_var,
.fb_set_par = ufx_ops_set_par,
+ .fb_destroy = ufx_ops_destory,
};
/* Assumes &info->lock held by caller
@@ -1673,9 +1676,6 @@ static int ufx_usb_probe(struct usb_interface *interface,
goto destroy_modedb;
}
- INIT_DELAYED_WORK(&dev->free_framebuffer_work,
- ufx_free_framebuffer_work);
-
retval = ufx_reg_read(dev, 0x3000, &id_rev);
check_warn_goto_error(retval, "error %d reading 0x3000 register from device", retval);
dev_dbg(dev->gdev, "ID_REV register value 0x%08x", id_rev);
@@ -1748,10 +1748,12 @@ e_nomem:
static void ufx_usb_disconnect(struct usb_interface *interface)
{
struct ufx_data *dev;
+ struct fb_info *info;
mutex_lock(&disconnect_mutex);
dev = usb_get_intfdata(interface);
+ info = dev->info;
pr_debug("USB disconnect starting\n");
@@ -1765,12 +1767,15 @@ static void ufx_usb_disconnect(struct usb_interface *interface)
/* if clients still have us open, will be freed on last close */
if (dev->fb_count == 0)
- schedule_delayed_work(&dev->free_framebuffer_work, 0);
+ ufx_free_framebuffer(dev);
- /* release reference taken by kref_init in probe() */
- kref_put(&dev->kref, ufx_free);
+ /* this function will wait for all in-flight urbs to complete */
+ if (dev->urbs.count > 0)
+ ufx_free_urb_list(dev);
- /* consider ufx_data freed */
+ pr_debug("freeing ufx_data %p", dev);
+
+ unregister_framebuffer(info);
mutex_unlock(&disconnect_mutex);
}
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 7753e586e65a..3feb6e40d56d 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1055,7 +1055,8 @@ stifb_fillrect(struct fb_info *info, const struct fb_fillrect *rect)
{
struct stifb_info *fb = container_of(info, struct stifb_info, info);
- if (rect->rop != ROP_COPY)
+ if (rect->rop != ROP_COPY ||
+ (fb->id == S9000_ID_HCRX && fb->info.var.bits_per_pixel == 32))
return cfb_fillrect(info, rect);
SETUP_HW(fb);
diff --git a/drivers/video/fbdev/xilinxfb.c b/drivers/video/fbdev/xilinxfb.c
index 438e2c78142f..1ac83900a21c 100644
--- a/drivers/video/fbdev/xilinxfb.c
+++ b/drivers/video/fbdev/xilinxfb.c
@@ -376,7 +376,7 @@ err_cmap:
return rc;
}
-static int xilinxfb_release(struct device *dev)
+static void xilinxfb_release(struct device *dev)
{
struct xilinxfb_drvdata *drvdata = dev_get_drvdata(dev);
@@ -402,8 +402,6 @@ static int xilinxfb_release(struct device *dev)
if (!(drvdata->flags & BUS_ACCESS_FLAG))
dcr_unmap(drvdata->dcr_host, drvdata->dcr_len);
#endif
-
- return 0;
}
/* ---------------------------------------------------------------------
@@ -480,7 +478,9 @@ static int xilinxfb_of_probe(struct platform_device *pdev)
static int xilinxfb_of_remove(struct platform_device *op)
{
- return xilinxfb_release(&op->dev);
+ xilinxfb_release(&op->dev);
+
+ return 0;
}
/* Match table for of_platform binding */
diff --git a/drivers/watchdog/exar_wdt.c b/drivers/watchdog/exar_wdt.c
index 35058d8b21bc..7c61ff343271 100644
--- a/drivers/watchdog/exar_wdt.c
+++ b/drivers/watchdog/exar_wdt.c
@@ -355,8 +355,10 @@ static int __init exar_wdt_register(struct wdt_priv *priv, const int idx)
&priv->wdt_res, 1,
priv, sizeof(*priv));
if (IS_ERR(n->pdev)) {
+ int err = PTR_ERR(n->pdev);
+
kfree(n);
- return PTR_ERR(n->pdev);
+ return err;
}
list_add_tail(&n->list, &pdev_list);
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index 78ba36689eec..2756ed54ca3d 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -88,7 +88,7 @@ static bool wdt_is_running(struct watchdog_device *wdd)
return (wdtcontrol & ENABLE_MASK) == ENABLE_MASK;
}
-/* This routine finds load value that will reset system in required timout */
+/* This routine finds load value that will reset system in required timeout */
static int wdt_setload(struct watchdog_device *wdd, unsigned int timeout)
{
struct sp805_wdt *wdt = watchdog_get_drvdata(wdd);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 63c7ebb0da89..6a11025e5850 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -911,7 +911,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
interp_elf_ex = kmalloc(sizeof(*interp_elf_ex), GFP_KERNEL);
if (!interp_elf_ex) {
retval = -ENOMEM;
- goto out_free_ph;
+ goto out_free_file;
}
/* Get the exec headers */
@@ -1354,6 +1354,7 @@ out:
out_free_dentry:
kfree(interp_elf_ex);
kfree(interp_elf_phdata);
+out_free_file:
allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 4ec18ceb2f21..18374a6d05bd 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -289,8 +289,10 @@ static void prelim_release(struct preftree *preftree)
struct prelim_ref *ref, *next_ref;
rbtree_postorder_for_each_entry_safe(ref, next_ref,
- &preftree->root.rb_root, rbnode)
+ &preftree->root.rb_root, rbnode) {
+ free_inode_elem_list(ref->inode_list);
free_pref(ref);
+ }
preftree->root = RB_ROOT_CACHED;
preftree->count = 0;
@@ -648,6 +650,18 @@ unode_aux_to_inode_list(struct ulist_node *node)
return (struct extent_inode_elem *)(uintptr_t)node->aux;
}
+static void free_leaf_list(struct ulist *ulist)
+{
+ struct ulist_node *node;
+ struct ulist_iterator uiter;
+
+ ULIST_ITER_INIT(&uiter);
+ while ((node = ulist_next(ulist, &uiter)))
+ free_inode_elem_list(unode_aux_to_inode_list(node));
+
+ ulist_free(ulist);
+}
+
/*
* We maintain three separate rbtrees: one for direct refs, one for
* indirect refs which have a key, and one for indirect refs which do not
@@ -762,7 +776,11 @@ static int resolve_indirect_refs(struct btrfs_fs_info *fs_info,
cond_resched();
}
out:
- ulist_free(parents);
+ /*
+ * We may have inode lists attached to refs in the parents ulist, so we
+ * must free them before freeing the ulist and its refs.
+ */
+ free_leaf_list(parents);
return ret;
}
@@ -1368,6 +1386,12 @@ again:
if (ret < 0)
goto out;
ref->inode_list = eie;
+ /*
+ * We transferred the list ownership to the ref,
+ * so set to NULL to avoid a double free in case
+ * an error happens after this.
+ */
+ eie = NULL;
}
ret = ulist_add_merge_ptr(refs, ref->parent,
ref->inode_list,
@@ -1393,6 +1417,14 @@ again:
eie->next = ref->inode_list;
}
eie = NULL;
+ /*
+ * We have transferred the inode list ownership from
+ * this ref to the ref we added to the 'refs' ulist.
+ * So set this ref's inode list to NULL to avoid
+ * use-after-free when our caller uses it or double
+ * frees in case an error happens before we return.
+ */
+ ref->inode_list = NULL;
}
cond_resched();
}
@@ -1409,24 +1441,6 @@ out:
return ret;
}
-static void free_leaf_list(struct ulist *blocks)
-{
- struct ulist_node *node = NULL;
- struct extent_inode_elem *eie;
- struct ulist_iterator uiter;
-
- ULIST_ITER_INIT(&uiter);
- while ((node = ulist_next(blocks, &uiter))) {
- if (!node->aux)
- continue;
- eie = unode_aux_to_inode_list(node);
- free_inode_elem_list(eie);
- node->aux = 0;
- }
-
- ulist_free(blocks);
-}
-
/*
* Finds all leafs with a reference to the specified combination of bytenr and
* offset. key_list_head will point to a list of corresponding keys (caller must
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 727595eee973..f677b49df8ae 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3462,7 +3462,10 @@ ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
const struct btrfs_ioctl_encoded_io_args *encoded);
-ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before);
+ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter,
+ size_t done_before);
+struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
+ size_t done_before);
extern const struct dentry_operations btrfs_dentry_operations;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a2da9313c694..4b28263c3d32 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -166,11 +166,9 @@ static bool btrfs_supported_super_csum(u16 csum_type)
* Return 0 if the superblock checksum type matches the checksum value of that
* algorithm. Pass the raw disk superblock data.
*/
-static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
- char *raw_disk_sb)
+int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
+ const struct btrfs_super_block *disk_sb)
{
- struct btrfs_super_block *disk_sb =
- (struct btrfs_super_block *)raw_disk_sb;
char result[BTRFS_CSUM_SIZE];
SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
@@ -181,7 +179,7 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
* BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is
* filled with zeros and is included in the checksum.
*/
- crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE,
+ crypto_shash_digest(shash, (const u8 *)disk_sb + BTRFS_CSUM_SIZE,
BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result);
if (memcmp(disk_sb->csum, result, fs_info->csum_size))
@@ -3479,7 +3477,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
* We want to check superblock checksum, the type is stored inside.
* Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
*/
- if (btrfs_check_super_csum(fs_info, (u8 *)disk_super)) {
+ if (btrfs_check_super_csum(fs_info, disk_super)) {
btrfs_err(fs_info, "superblock checksum mismatch");
err = -EINVAL;
btrfs_release_disk_super(disk_super);
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index c67c15d4d20b..9fa923e005a3 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -42,6 +42,8 @@ struct extent_buffer *btrfs_find_create_tree_block(
void btrfs_clean_tree_block(struct extent_buffer *buf);
void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info);
int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info);
+int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
+ const struct btrfs_super_block *disk_sb);
int __cold open_ctree(struct super_block *sb,
struct btrfs_fs_devices *fs_devices,
char *options);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 1d4c2397d0d6..fab7eb76e53b 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -58,7 +58,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
}
struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
- u64 root_objectid, u32 generation,
+ u64 root_objectid, u64 generation,
int check_generation)
{
struct btrfs_fs_info *fs_info = btrfs_sb(sb);
diff --git a/fs/btrfs/export.h b/fs/btrfs/export.h
index f32f4113c976..5afb7ca42828 100644
--- a/fs/btrfs/export.h
+++ b/fs/btrfs/export.h
@@ -19,7 +19,7 @@ struct btrfs_fid {
} __attribute__ ((packed));
struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid,
- u64 root_objectid, u32 generation,
+ u64 root_objectid, u64 generation,
int check_generation);
struct dentry *btrfs_get_parent(struct dentry *child);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index cd2d36580f1a..2801c991814f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3295,21 +3295,22 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
}
/*
- * If this is a leaf and there are tree mod log users, we may
- * have recorded mod log operations that point to this leaf.
- * So we must make sure no one reuses this leaf's extent before
- * mod log operations are applied to a node, otherwise after
- * rewinding a node using the mod log operations we get an
- * inconsistent btree, as the leaf's extent may now be used as
- * a node or leaf for another different btree.
+ * If there are tree mod log users we may have recorded mod log
+ * operations for this node. If we re-allocate this node we
+ * could replay operations on this node that happened when it
+ * existed in a completely different root. For example if it
+ * was part of root A, then was reallocated to root B, and we
+ * are doing a btrfs_old_search_slot(root b), we could replay
+ * operations that happened when the block was part of root A,
+ * giving us an inconsistent view of the btree.
+ *
* We are safe from races here because at this point no other
* node or root points to this extent buffer, so if after this
- * check a new tree mod log user joins, it will not be able to
- * find a node pointing to this leaf and record operations that
- * point to this leaf.
+ * check a new tree mod log user joins we will not have an
+ * existing log of operations on this node that we have to
+ * contend with.
*/
- if (btrfs_header_level(buf) == 0 &&
- test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
+ if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
must_pin = true;
if (must_pin || btrfs_is_zoned(fs_info)) {
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 176b432035ae..d01631d47806 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1598,14 +1598,19 @@ static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
write_bytes);
else
btrfs_check_nocow_unlock(BTRFS_I(inode));
+
+ if (nowait && ret == -ENOSPC)
+ ret = -EAGAIN;
break;
}
release_bytes = reserve_bytes;
again:
ret = balance_dirty_pages_ratelimited_flags(inode->i_mapping, bdp_flags);
- if (ret)
+ if (ret) {
+ btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
break;
+ }
/*
* This is going to setup the pages array with the number of
@@ -1765,6 +1770,7 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
loff_t endbyte;
ssize_t err;
unsigned int ilock_flags = 0;
+ struct iomap_dio *dio;
if (iocb->ki_flags & IOCB_NOWAIT)
ilock_flags |= BTRFS_ILOCK_TRY;
@@ -1825,11 +1831,22 @@ relock:
* So here we disable page faults in the iov_iter and then retry if we
* got -EFAULT, faulting in the pages before the retry.
*/
-again:
from->nofault = true;
- err = btrfs_dio_rw(iocb, from, written);
+ dio = btrfs_dio_write(iocb, from, written);
from->nofault = false;
+ /*
+ * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
+ * iocb, and that needs to lock the inode. So unlock it before calling
+ * iomap_dio_complete() to avoid a deadlock.
+ */
+ btrfs_inode_unlock(inode, ilock_flags);
+
+ if (IS_ERR_OR_NULL(dio))
+ err = PTR_ERR_OR_ZERO(dio);
+ else
+ err = iomap_dio_complete(dio);
+
/* No increment (+=) because iomap returns a cumulative value. */
if (err > 0)
written = err;
@@ -1855,12 +1872,10 @@ again:
} else {
fault_in_iov_iter_readable(from, left);
prev_left = left;
- goto again;
+ goto relock;
}
}
- btrfs_inode_unlock(inode, ilock_flags);
-
/*
* If 'err' is -ENOTBLK or we have not written all data, then it means
* we must fallback to buffered IO.
@@ -4035,7 +4050,7 @@ again:
*/
pagefault_disable();
to->nofault = true;
- ret = btrfs_dio_rw(iocb, to, read);
+ ret = btrfs_dio_read(iocb, to, read);
to->nofault = false;
pagefault_enable();
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b0807c59e321..0e516aefbf51 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7980,7 +7980,7 @@ static void btrfs_submit_direct(const struct iomap_iter *iter,
*/
status = BLK_STS_RESOURCE;
dip->csums = kcalloc(nr_sectors, fs_info->csum_size, GFP_NOFS);
- if (!dip)
+ if (!dip->csums)
goto out_err;
status = btrfs_lookup_bio_sums(inode, dio_bio, dip->csums);
@@ -8078,13 +8078,21 @@ static const struct iomap_dio_ops btrfs_dio_ops = {
.bio_set = &btrfs_dio_bioset,
};
-ssize_t btrfs_dio_rw(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
+ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
{
struct btrfs_dio_data data;
return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
- IOMAP_DIO_PARTIAL | IOMAP_DIO_NOSYNC,
- &data, done_before);
+ IOMAP_DIO_PARTIAL, &data, done_before);
+}
+
+struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
+ size_t done_before)
+{
+ struct btrfs_dio_data data;
+
+ return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
+ IOMAP_DIO_PARTIAL, &data, done_before);
}
static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f6395e8288d6..82c8e991300e 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1632,10 +1632,8 @@ static int full_stripe_write(struct btrfs_raid_bio *rbio)
int ret;
ret = alloc_rbio_parity_pages(rbio);
- if (ret) {
- __free_raid_bio(rbio);
+ if (ret)
return ret;
- }
ret = lock_stripe_add(rbio);
if (ret == 0)
@@ -1823,8 +1821,10 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc)
*/
if (rbio_is_full(rbio)) {
ret = full_stripe_write(rbio);
- if (ret)
+ if (ret) {
+ __free_raid_bio(rbio);
goto fail;
+ }
return;
}
@@ -1838,8 +1838,10 @@ void raid56_parity_write(struct bio *bio, struct btrfs_io_context *bioc)
list_add_tail(&rbio->plug_list, &plug->rbio_list);
} else {
ret = __raid56_parity_write(rbio);
- if (ret)
+ if (ret) {
+ __free_raid_bio(rbio);
goto fail;
+ }
}
return;
@@ -2742,8 +2744,10 @@ raid56_alloc_missing_rbio(struct bio *bio, struct btrfs_io_context *bioc)
rbio->faila = find_logical_bio_stripe(rbio, bio);
if (rbio->faila == -1) {
- BUG();
- kfree(rbio);
+ btrfs_warn_rl(fs_info,
+ "can not determine the failed stripe number for full stripe %llu",
+ bioc->raid_map[0]);
+ __free_raid_bio(rbio);
return NULL;
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index ec6e1752af2c..145c84b44fd0 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6668,17 +6668,19 @@ static int changed_inode(struct send_ctx *sctx,
/*
* First, process the inode as if it was deleted.
*/
- sctx->cur_inode_gen = right_gen;
- sctx->cur_inode_new = false;
- sctx->cur_inode_deleted = true;
- sctx->cur_inode_size = btrfs_inode_size(
- sctx->right_path->nodes[0], right_ii);
- sctx->cur_inode_mode = btrfs_inode_mode(
- sctx->right_path->nodes[0], right_ii);
- ret = process_all_refs(sctx,
- BTRFS_COMPARE_TREE_DELETED);
- if (ret < 0)
- goto out;
+ if (old_nlinks > 0) {
+ sctx->cur_inode_gen = right_gen;
+ sctx->cur_inode_new = false;
+ sctx->cur_inode_deleted = true;
+ sctx->cur_inode_size = btrfs_inode_size(
+ sctx->right_path->nodes[0], right_ii);
+ sctx->cur_inode_mode = btrfs_inode_mode(
+ sctx->right_path->nodes[0], right_ii);
+ ret = process_all_refs(sctx,
+ BTRFS_COMPARE_TREE_DELETED);
+ if (ret < 0)
+ goto out;
+ }
/*
* Now process the inode as if it was new.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9be4fd2db0f4..5942b9384088 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2555,6 +2555,7 @@ static int check_dev_super(struct btrfs_device *dev)
{
struct btrfs_fs_info *fs_info = dev->fs_info;
struct btrfs_super_block *sb;
+ u16 csum_type;
int ret = 0;
/* This should be called with fs still frozen. */
@@ -2569,6 +2570,21 @@ static int check_dev_super(struct btrfs_device *dev)
if (IS_ERR(sb))
return PTR_ERR(sb);
+ /* Verify the checksum. */
+ csum_type = btrfs_super_csum_type(sb);
+ if (csum_type != btrfs_super_csum_type(fs_info->super_copy)) {
+ btrfs_err(fs_info, "csum type changed, has %u expect %u",
+ csum_type, btrfs_super_csum_type(fs_info->super_copy));
+ ret = -EUCLEAN;
+ goto out;
+ }
+
+ if (btrfs_check_super_csum(fs_info, sb)) {
+ btrfs_err(fs_info, "csum for on-disk super block no longer matches");
+ ret = -EUCLEAN;
+ goto out;
+ }
+
/* Btrfs_validate_super() includes fsid check against super->fsid. */
ret = btrfs_validate_super(fs_info, sb, 0);
if (ret < 0)
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index eee1e4459541..63676ea19f29 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -225,20 +225,20 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
*/
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false);
if (ret) {
- ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
BTRFS_FS_TREE_OBJECTID);
- if (ret)
+ if (ret) {
+ ulist_free(old_roots);
return ret;
+ }
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);
if (ret) {
ulist_free(old_roots);
- ulist_free(new_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -250,29 +250,31 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
return ret;
}
+ /* btrfs_qgroup_account_extent() always frees the ulists passed to it. */
+ old_roots = NULL;
+ new_roots = NULL;
+
if (btrfs_verify_qgroup_counts(fs_info, BTRFS_FS_TREE_OBJECTID,
nodesize, nodesize)) {
test_err("qgroup counts didn't match expected values");
return -EINVAL;
}
- old_roots = NULL;
- new_roots = NULL;
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false);
if (ret) {
- ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = remove_extent_item(root, nodesize, nodesize);
- if (ret)
+ if (ret) {
+ ulist_free(old_roots);
return -EINVAL;
+ }
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);
if (ret) {
ulist_free(old_roots);
- ulist_free(new_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -322,20 +324,20 @@ static int test_multiple_refs(struct btrfs_root *root,
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false);
if (ret) {
- ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = insert_normal_tree_ref(root, nodesize, nodesize, 0,
BTRFS_FS_TREE_OBJECTID);
- if (ret)
+ if (ret) {
+ ulist_free(old_roots);
return ret;
+ }
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);
if (ret) {
ulist_free(old_roots);
- ulist_free(new_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -355,20 +357,20 @@ static int test_multiple_refs(struct btrfs_root *root,
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false);
if (ret) {
- ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = add_tree_ref(root, nodesize, nodesize, 0,
BTRFS_FIRST_FREE_OBJECTID);
- if (ret)
+ if (ret) {
+ ulist_free(old_roots);
return ret;
+ }
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);
if (ret) {
ulist_free(old_roots);
- ulist_free(new_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
@@ -394,20 +396,20 @@ static int test_multiple_refs(struct btrfs_root *root,
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &old_roots, false);
if (ret) {
- ulist_free(old_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
ret = remove_extent_ref(root, nodesize, nodesize, 0,
BTRFS_FIRST_FREE_OBJECTID);
- if (ret)
+ if (ret) {
+ ulist_free(old_roots);
return ret;
+ }
ret = btrfs_find_all_roots(&trans, fs_info, nodesize, 0, &new_roots, false);
if (ret) {
ulist_free(old_roots);
- ulist_free(new_roots);
test_err("couldn't find old roots: %d", ret);
return ret;
}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 94ba46d57920..a8d4bc6a1937 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7142,6 +7142,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
u64 devid;
u64 type;
u8 uuid[BTRFS_UUID_SIZE];
+ int index;
int num_stripes;
int ret;
int i;
@@ -7149,6 +7150,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
logical = key->offset;
length = btrfs_chunk_length(leaf, chunk);
type = btrfs_chunk_type(leaf, chunk);
+ index = btrfs_bg_flags_to_raid_index(type);
num_stripes = btrfs_chunk_num_stripes(leaf, chunk);
#if BITS_PER_LONG == 32
@@ -7202,7 +7204,15 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
map->io_align = btrfs_chunk_io_align(leaf, chunk);
map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
map->type = type;
- map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+ /*
+ * We can't use the sub_stripes value, as for profiles other than
+ * RAID10, they may have 0 as sub_stripes for filesystems created by
+ * older mkfs (<v5.4).
+ * In that case, it can cause divide-by-zero errors later.
+ * Since currently sub_stripes is fixed for each profile, let's
+ * use the trusted value instead.
+ */
+ map->sub_stripes = btrfs_raid_array[index].sub_stripes;
map->verified_stripes = 0;
em->orig_block_len = btrfs_calc_stripe_length(em);
for (i = 0; i < num_stripes; i++) {
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 599b9d5af349..f8b668dc8bf8 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -395,6 +395,7 @@ typedef void (*btrfs_bio_end_io_t)(struct btrfs_bio *bbio);
*/
struct btrfs_bio {
unsigned int mirror_num;
+ struct bvec_iter iter;
/* for direct I/O */
u64 file_offset;
@@ -403,7 +404,6 @@ struct btrfs_bio {
struct btrfs_device *device;
u8 *csum;
u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
- struct bvec_iter iter;
/* End I/O information supplied to btrfs_bio_alloc */
btrfs_bio_end_io_t end_io;
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d0b9fec111aa..fe220686bba4 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -1143,8 +1143,32 @@ const struct inode_operations cifs_file_inode_ops = {
.fiemap = cifs_fiemap,
};
+const char *cifs_get_link(struct dentry *dentry, struct inode *inode,
+ struct delayed_call *done)
+{
+ char *target_path;
+
+ target_path = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!target_path)
+ return ERR_PTR(-ENOMEM);
+
+ spin_lock(&inode->i_lock);
+ if (likely(CIFS_I(inode)->symlink_target)) {
+ strscpy(target_path, CIFS_I(inode)->symlink_target, PATH_MAX);
+ } else {
+ kfree(target_path);
+ target_path = ERR_PTR(-EOPNOTSUPP);
+ }
+ spin_unlock(&inode->i_lock);
+
+ if (!IS_ERR(target_path))
+ set_delayed_call(done, kfree_link, target_path);
+
+ return target_path;
+}
+
const struct inode_operations cifs_symlink_inode_ops = {
- .get_link = simple_get_link,
+ .get_link = cifs_get_link,
.permission = cifs_permission,
.listxattr = cifs_listxattr,
};
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index ffb291579bb9..1cc47dd3b4d6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1584,6 +1584,7 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
server->session_key.response = NULL;
server->session_key.len = 0;
kfree(server->hostname);
+ server->hostname = NULL;
task = xchg(&server->tsk, NULL);
if (task)
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5b3b308e115c..cd9698209930 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -2434,12 +2434,16 @@ cifs_writev_complete(struct work_struct *work)
struct cifs_writedata *
cifs_writedata_alloc(unsigned int nr_pages, work_func_t complete)
{
+ struct cifs_writedata *writedata = NULL;
struct page **pages =
kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
- if (pages)
- return cifs_writedata_direct_alloc(pages, complete);
+ if (pages) {
+ writedata = cifs_writedata_direct_alloc(pages, complete);
+ if (!writedata)
+ kvfree(pages);
+ }
- return NULL;
+ return writedata;
}
struct cifs_writedata *
@@ -3299,6 +3303,9 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
cifs_uncached_writev_complete);
if (!wdata) {
rc = -ENOMEM;
+ for (i = 0; i < nr_pages; i++)
+ put_page(pagevec[i]);
+ kvfree(pagevec);
add_credits_and_wake_if(server, credits, 0);
break;
}
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 9bde08d44617..4e2ca3c6e5c0 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -215,11 +215,6 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
kfree(cifs_i->symlink_target);
cifs_i->symlink_target = fattr->cf_symlink_target;
fattr->cf_symlink_target = NULL;
-
- if (unlikely(!cifs_i->symlink_target))
- inode->i_link = ERR_PTR(-EOPNOTSUPP);
- else
- inode->i_link = cifs_i->symlink_target;
}
spin_unlock(&inode->i_lock);
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index da51ffd02928..3e68d8208cf5 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -400,6 +400,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
{
struct smb_hdr *buf = (struct smb_hdr *)buffer;
struct smb_com_lock_req *pSMB = (struct smb_com_lock_req *)buf;
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
struct cifsInodeInfo *pCifsInode;
@@ -464,9 +465,12 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
if (!(pSMB->LockType & LOCKING_ANDX_OPLOCK_RELEASE))
return false;
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(srv) ? srv->primary_server : srv;
+
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(ses, &srv->smb_ses_list, smb_ses_list) {
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid != buf->Tid)
continue;
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index a38720477966..572293c18e16 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -135,6 +135,7 @@ static __u32 get_neg_ctxt_len(struct smb2_hdr *hdr, __u32 len,
int
smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
{
+ struct TCP_Server_Info *pserver;
struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
struct smb2_pdu *pdu = (struct smb2_pdu *)shdr;
int hdr_size = sizeof(struct smb2_hdr);
@@ -143,6 +144,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
__u32 calc_len; /* calculated length */
__u64 mid;
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
/*
* Add function to do table lookup of StructureSize by command
* ie Validate the wct via smb2_struct_sizes table above
@@ -155,7 +159,7 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *server)
/* decrypt frame now that it is completely read in */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(iter, &server->smb_ses_list, smb_ses_list) {
+ list_for_each_entry(iter, &pserver->smb_ses_list, smb_ses_list) {
if (iter->Suid == le64_to_cpu(thdr->SessionId)) {
ses = iter;
break;
@@ -608,51 +612,52 @@ smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon,
}
static bool
-smb2_is_valid_lease_break(char *buffer)
+smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server)
{
struct smb2_lease_break *rsp = (struct smb2_lease_break *)buffer;
- struct TCP_Server_Info *server;
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
struct cifs_pending_open *open;
cifs_dbg(FYI, "Checking for lease break\n");
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
- list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
- spin_lock(&tcon->open_file_lock);
- cifs_stats_inc(
- &tcon->stats.cifs_stats.num_oplock_brks);
- if (smb2_tcon_has_lease(tcon, rsp)) {
- spin_unlock(&tcon->open_file_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
- open = smb2_tcon_find_pending_open_lease(tcon,
- rsp);
- if (open) {
- __u8 lease_key[SMB2_LEASE_KEY_SIZE];
- struct tcon_link *tlink;
-
- tlink = cifs_get_tlink(open->tlink);
- memcpy(lease_key, open->lease_key,
- SMB2_LEASE_KEY_SIZE);
- spin_unlock(&tcon->open_file_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- smb2_queue_pending_open_break(tlink,
- lease_key,
- rsp->NewLeaseState);
- return true;
- }
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+ spin_lock(&tcon->open_file_lock);
+ cifs_stats_inc(
+ &tcon->stats.cifs_stats.num_oplock_brks);
+ if (smb2_tcon_has_lease(tcon, rsp)) {
spin_unlock(&tcon->open_file_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
+ }
+ open = smb2_tcon_find_pending_open_lease(tcon,
+ rsp);
+ if (open) {
+ __u8 lease_key[SMB2_LEASE_KEY_SIZE];
+ struct tcon_link *tlink;
+
+ tlink = cifs_get_tlink(open->tlink);
+ memcpy(lease_key, open->lease_key,
+ SMB2_LEASE_KEY_SIZE);
+ spin_unlock(&tcon->open_file_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ smb2_queue_pending_open_break(tlink,
+ lease_key,
+ rsp->NewLeaseState);
+ return true;
+ }
+ spin_unlock(&tcon->open_file_lock);
- if (cached_dir_lease_break(tcon, rsp->LeaseKey)) {
- spin_unlock(&cifs_tcp_ses_lock);
- return true;
- }
+ if (cached_dir_lease_break(tcon, rsp->LeaseKey)) {
+ spin_unlock(&cifs_tcp_ses_lock);
+ return true;
}
}
}
@@ -671,6 +676,7 @@ bool
smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
{
struct smb2_oplock_break *rsp = (struct smb2_oplock_break *)buffer;
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
struct cifsInodeInfo *cinode;
@@ -684,16 +690,19 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
if (rsp->StructureSize !=
smb2_rsp_struct_sizes[SMB2_OPLOCK_BREAK_HE]) {
if (le16_to_cpu(rsp->StructureSize) == 44)
- return smb2_is_valid_lease_break(buffer);
+ return smb2_is_valid_lease_break(buffer, server);
else
return false;
}
cifs_dbg(FYI, "oplock level 0x%x\n", rsp->OplockLevel);
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
/* look up tcon based on tid & uid */
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
spin_lock(&tcon->open_file_lock);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4f53fa012936..880cd494afea 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2302,14 +2302,18 @@ static void
smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server)
{
struct smb2_hdr *shdr = (struct smb2_hdr *)buf;
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
struct cifs_tcon *tcon;
if (shdr->Status != STATUS_NETWORK_NAME_DELETED)
return;
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
if (tcon->tid == le32_to_cpu(shdr->Id.SyncId.TreeId)) {
spin_lock(&tcon->tc_lock);
@@ -4264,21 +4268,23 @@ init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign)
static int
smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
{
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
u8 *ses_enc_key;
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(server, &cifs_tcp_ses_list, tcp_ses_list) {
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
- if (ses->Suid == ses_id) {
- spin_lock(&ses->ses_lock);
- ses_enc_key = enc ? ses->smb3encryptionkey :
- ses->smb3decryptionkey;
- memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
- spin_unlock(&ses->ses_lock);
- spin_unlock(&cifs_tcp_ses_lock);
- return 0;
- }
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (ses->Suid == ses_id) {
+ spin_lock(&ses->ses_lock);
+ ses_enc_key = enc ? ses->smb3encryptionkey :
+ ses->smb3decryptionkey;
+ memcpy(key, ses_enc_key, SMB3_ENC_DEC_KEY_SIZE);
+ spin_unlock(&ses->ses_lock);
+ spin_unlock(&cifs_tcp_ses_lock);
+ return 0;
}
}
spin_unlock(&cifs_tcp_ses_lock);
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 8e3f26e6f6b9..381babc1212c 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -77,18 +77,19 @@ static
int smb2_get_sign_key(__u64 ses_id, struct TCP_Server_Info *server, u8 *key)
{
struct cifs_chan *chan;
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses = NULL;
- struct TCP_Server_Info *it = NULL;
int i;
int rc = 0;
spin_lock(&cifs_tcp_ses_lock);
- list_for_each_entry(it, &cifs_tcp_ses_list, tcp_ses_list) {
- list_for_each_entry(ses, &it->smb_ses_list, smb_ses_list) {
- if (ses->Suid == ses_id)
- goto found;
- }
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
+ if (ses->Suid == ses_id)
+ goto found;
}
cifs_server_dbg(VFS, "%s: Could not find session 0x%llx\n",
__func__, ses_id);
@@ -136,9 +137,13 @@ out:
static struct cifs_ses *
smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
{
+ struct TCP_Server_Info *pserver;
struct cifs_ses *ses;
- list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+ /* If server is a channel, select the primary channel */
+ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server;
+
+ list_for_each_entry(ses, &pserver->smb_ses_list, smb_ses_list) {
if (ses->Suid != ses_id)
continue;
++ses->ses_count;
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 1cca09aa43f8..2a24b1f0ae68 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -205,14 +205,19 @@ static int allocate_filesystem_keyring(struct super_block *sb)
}
/*
- * This is called at unmount time to release all encryption keys that have been
- * added to the filesystem, along with the keyring that contains them.
+ * Release all encryption keys that have been added to the filesystem, along
+ * with the keyring that contains them.
*
- * Note that besides clearing and freeing memory, this might need to evict keys
- * from the keyslots of an inline crypto engine. Therefore, this must be called
- * while the filesystem's underlying block device(s) are still available.
+ * This is called at unmount time. The filesystem's underlying block device(s)
+ * are still available at this time; this is important because after user file
+ * accesses have been allowed, this function may need to evict keys from the
+ * keyslots of an inline crypto engine, which requires the block device(s).
+ *
+ * This is also called when the super_block is being freed. This is needed to
+ * avoid a memory leak if mounting fails after the "test_dummy_encryption"
+ * option was processed, as in that case the unmount-time call isn't made.
*/
-void fscrypt_sb_delete(struct super_block *sb)
+void fscrypt_destroy_keyring(struct super_block *sb)
{
struct fscrypt_keyring *keyring = sb->s_master_keys;
size_t i;
diff --git a/fs/exec.c b/fs/exec.c
index 349a5da91efe..a0b1f0337a62 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1012,7 +1012,6 @@ static int exec_mmap(struct mm_struct *mm)
active_mm = tsk->active_mm;
tsk->active_mm = mm;
tsk->mm = mm;
- lru_gen_add_mm(mm);
/*
* This prevents preemption while active_mm is being loaded and
* it and mm are being updated, which could cause problems for
@@ -1025,6 +1024,7 @@ static int exec_mmap(struct mm_struct *mm)
activate_mm(active_mm, mm);
if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
+ lru_gen_add_mm(mm);
task_unlock(tsk);
lru_gen_use_mm(mm);
if (old_mm) {
@@ -1197,11 +1197,11 @@ static int unshare_sighand(struct task_struct *me)
return -ENOMEM;
refcount_set(&newsighand->count, 1);
- memcpy(newsighand->action, oldsighand->action,
- sizeof(newsighand->action));
write_lock_irq(&tasklist_lock);
spin_lock(&oldsighand->siglock);
+ memcpy(newsighand->action, oldsighand->action,
+ sizeof(newsighand->action));
rcu_assign_pointer(me->sighand, newsighand);
spin_unlock(&oldsighand->siglock);
write_unlock_irq(&tasklist_lock);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index ef05bfa87798..0f6d0a80467d 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -1521,6 +1521,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
struct ext4_iloc iloc;
int inode_len, ino, ret, tag = tl->fc_tag;
struct ext4_extent_header *eh;
+ size_t off_gen = offsetof(struct ext4_inode, i_generation);
memcpy(&fc_inode, val, sizeof(fc_inode));
@@ -1548,8 +1549,8 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl,
raw_inode = ext4_raw_inode(&iloc);
memcpy(raw_inode, raw_fc_inode, offsetof(struct ext4_inode, i_block));
- memcpy(&raw_inode->i_generation, &raw_fc_inode->i_generation,
- inode_len - offsetof(struct ext4_inode, i_generation));
+ memcpy((u8 *)raw_inode + off_gen, (u8 *)raw_fc_inode + off_gen,
+ inode_len - off_gen);
if (le32_to_cpu(raw_inode->i_flags) & EXT4_EXTENTS_FL) {
eh = (struct ext4_extent_header *)(&raw_inode->i_block[0]);
if (eh->eh_magic != EXT4_EXT_MAGIC) {
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index ded535535b27..95dfea28bf4e 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -145,9 +145,8 @@ static int ext4_update_backup_sb(struct super_block *sb,
if (ext4_has_metadata_csum(sb) &&
es->s_checksum != ext4_superblock_csum(sb, es)) {
ext4_msg(sb, KERN_ERR, "Invalid checksum for backup "
- "superblock %llu\n", sb_block);
+ "superblock %llu", sb_block);
unlock_buffer(bh);
- err = -EFSBADCRC;
goto out_bh;
}
func(es, arg);
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 0a220ec9862d..a19a9661646e 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -424,7 +424,8 @@ int ext4_ext_migrate(struct inode *inode)
* already is extent-based, error out.
*/
if (!ext4_has_feature_extents(inode->i_sb) ||
- (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
+ ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+ ext4_has_inline_data(inode))
return -EINVAL;
if (S_ISLNK(inode->i_mode) && inode->i_blocks == 0)
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index d5daaf41e1fc..c08c0aba1883 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2259,8 +2259,16 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
memset(de, 0, len); /* wipe old data */
de = (struct ext4_dir_entry_2 *) data2;
top = data2 + len;
- while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
+ while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top) {
+ if (ext4_check_dir_entry(dir, NULL, de, bh2, data2, len,
+ (data2 + (blocksize - csum_size) -
+ (char *) de))) {
+ brelse(bh2);
+ brelse(bh);
+ return -EFSCORRUPTED;
+ }
de = de2;
+ }
de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) -
(char *) de, blocksize);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 6dfe9ccae0c5..46b87ffeb304 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1158,6 +1158,7 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data,
while (group < sbi->s_groups_count) {
struct buffer_head *bh;
ext4_fsblk_t backup_block;
+ struct ext4_super_block *es;
/* Out of journal space, and can't get more - abort - so sad */
err = ext4_resize_ensure_credits_batch(handle, 1);
@@ -1186,6 +1187,10 @@ static void update_backups(struct super_block *sb, sector_t blk_off, char *data,
memcpy(bh->b_data, data, size);
if (rest)
memset(bh->b_data + size, 0, rest);
+ es = (struct ext4_super_block *) bh->b_data;
+ es->s_block_group_nr = cpu_to_le16(group);
+ if (ext4_has_metadata_csum(sb))
+ es->s_checksum = ext4_superblock_csum(sb, es);
set_buffer_uptodate(bh);
unlock_buffer(bh);
err = ext4_handle_dirty_metadata(handle, NULL, bh);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 989365b878a6..7cdd2138c897 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1741,10 +1741,6 @@ static const struct fs_parameter_spec ext4_param_specs[] = {
#define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
-static const char deprecated_msg[] =
- "Mount option \"%s\" will be removed by %s\n"
- "Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
-
#define MOPT_SET 0x0001
#define MOPT_CLEAR 0x0002
#define MOPT_NOSUPPORT 0x0004
@@ -4885,7 +4881,7 @@ out:
flush_work(&sbi->s_error_work);
jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
- return err;
+ return -EINVAL;
}
static int ext4_journal_data_mode_check(struct super_block *sb)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1a3afd469e3a..71bfb663aac5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -3001,6 +3001,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
goto out;
}
+ err = file_modified(file);
+ if (err)
+ goto out;
+
if (!(mode & FALLOC_FL_KEEP_SIZE))
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index b4e565711045..e8deaacf1832 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -77,8 +77,10 @@ static void fuse_add_dirent_to_cache(struct file *file,
goto unlock;
addr = kmap_local_page(page);
- if (!offset)
+ if (!offset) {
clear_page(addr);
+ SetPageUptodate(page);
+ }
memcpy(addr + offset, dirent, reclen);
kunmap_local(addr);
fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen;
@@ -516,6 +518,12 @@ retry_locked:
page = find_get_page_flags(file->f_mapping, index,
FGP_ACCESSED | FGP_LOCK);
+ /* Page gone missing, then re-added to cache, but not initialized? */
+ if (page && !PageUptodate(page)) {
+ unlock_page(page);
+ put_page(page);
+ page = NULL;
+ }
spin_lock(&fi->rdc.lock);
if (!page) {
/*
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index da8da5cdbbc1..f50e025ae406 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -280,7 +280,7 @@ EXPORT_SYMBOL_GPL(nfs_put_client);
static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data)
{
struct nfs_client *clp;
- const struct sockaddr *sap = data->addr;
+ const struct sockaddr *sap = (struct sockaddr *)data->addr;
struct nfs_net *nn = net_generic(data->net, nfs_net_id);
int error;
@@ -666,7 +666,7 @@ static int nfs_init_server(struct nfs_server *server,
struct rpc_timeout timeparms;
struct nfs_client_initdata cl_init = {
.hostname = ctx->nfs_server.hostname,
- .addr = (const struct sockaddr *)&ctx->nfs_server.address,
+ .addr = &ctx->nfs_server._address,
.addrlen = ctx->nfs_server.addrlen,
.nfs_mod = ctx->nfs_mod,
.proto = ctx->nfs_server.protocol,
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5c97cad741a7..ead8a0e06abf 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -228,8 +228,7 @@ again:
*
*/
void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
- fmode_t type,
- const nfs4_stateid *stateid,
+ fmode_t type, const nfs4_stateid *stateid,
unsigned long pagemod_limit)
{
struct nfs_delegation *delegation;
@@ -239,25 +238,24 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
delegation = rcu_dereference(NFS_I(inode)->delegation);
if (delegation != NULL) {
spin_lock(&delegation->lock);
- if (nfs4_is_valid_delegation(delegation, 0)) {
- nfs4_stateid_copy(&delegation->stateid, stateid);
- delegation->type = type;
- delegation->pagemod_limit = pagemod_limit;
- oldcred = delegation->cred;
- delegation->cred = get_cred(cred);
- clear_bit(NFS_DELEGATION_NEED_RECLAIM,
- &delegation->flags);
- spin_unlock(&delegation->lock);
- rcu_read_unlock();
- put_cred(oldcred);
- trace_nfs4_reclaim_delegation(inode, type);
- return;
- }
- /* We appear to have raced with a delegation return. */
+ nfs4_stateid_copy(&delegation->stateid, stateid);
+ delegation->type = type;
+ delegation->pagemod_limit = pagemod_limit;
+ oldcred = delegation->cred;
+ delegation->cred = get_cred(cred);
+ clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
+ if (test_and_clear_bit(NFS_DELEGATION_REVOKED,
+ &delegation->flags))
+ atomic_long_inc(&nfs_active_delegations);
spin_unlock(&delegation->lock);
+ rcu_read_unlock();
+ put_cred(oldcred);
+ trace_nfs4_reclaim_delegation(inode, type);
+ } else {
+ rcu_read_unlock();
+ nfs_inode_set_delegation(inode, cred, type, stateid,
+ pagemod_limit);
}
- rcu_read_unlock();
- nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit);
}
static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync)
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 58036f657126..f594dac436a7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -2489,9 +2489,8 @@ int nfs_unlink(struct inode *dir, struct dentry *dentry)
spin_unlock(&dentry->d_lock);
goto out;
}
- if (dentry->d_fsdata)
- /* old devname */
- kfree(dentry->d_fsdata);
+ /* old devname */
+ kfree(dentry->d_fsdata);
dentry->d_fsdata = NFS_FSDATA_BLOCKED;
spin_unlock(&dentry->d_lock);
diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c
index e87d500ad95a..6603b5cee029 100644
--- a/fs/nfs/dns_resolve.c
+++ b/fs/nfs/dns_resolve.c
@@ -16,8 +16,9 @@
#include "dns_resolve.h"
ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen,
- struct sockaddr *sa, size_t salen)
+ struct sockaddr_storage *ss, size_t salen)
{
+ struct sockaddr *sa = (struct sockaddr *)ss;
ssize_t ret;
char *ip_addr = NULL;
int ip_len;
@@ -341,7 +342,7 @@ out:
}
ssize_t nfs_dns_resolve_name(struct net *net, char *name,
- size_t namelen, struct sockaddr *sa, size_t salen)
+ size_t namelen, struct sockaddr_storage *ss, size_t salen)
{
struct nfs_dns_ent key = {
.hostname = name,
@@ -354,7 +355,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name,
ret = do_cache_lookup_wait(nn->nfs_dns_resolve, &key, &item);
if (ret == 0) {
if (salen >= item->addrlen) {
- memcpy(sa, &item->addr, item->addrlen);
+ memcpy(ss, &item->addr, item->addrlen);
ret = item->addrlen;
} else
ret = -EOVERFLOW;
diff --git a/fs/nfs/dns_resolve.h b/fs/nfs/dns_resolve.h
index 576ff4b54c82..fe3b172c4de1 100644
--- a/fs/nfs/dns_resolve.h
+++ b/fs/nfs/dns_resolve.h
@@ -32,6 +32,6 @@ extern void nfs_dns_resolver_cache_destroy(struct net *net);
#endif
extern ssize_t nfs_dns_resolve_name(struct net *net, char *name,
- size_t namelen, struct sockaddr *sa, size_t salen);
+ size_t namelen, struct sockaddr_storage *sa, size_t salen);
#endif
diff --git a/fs/nfs/fs_context.c b/fs/nfs/fs_context.c
index 4da701fd1424..09833ec102fc 100644
--- a/fs/nfs/fs_context.c
+++ b/fs/nfs/fs_context.c
@@ -273,9 +273,9 @@ static const struct constant_table nfs_secflavor_tokens[] = {
* Address family must be initialized, and address must not be
* the ANY address for that family.
*/
-static int nfs_verify_server_address(struct sockaddr *addr)
+static int nfs_verify_server_address(struct sockaddr_storage *addr)
{
- switch (addr->sa_family) {
+ switch (addr->ss_family) {
case AF_INET: {
struct sockaddr_in *sa = (struct sockaddr_in *)addr;
return sa->sin_addr.s_addr != htonl(INADDR_ANY);
@@ -969,7 +969,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
{
struct nfs_fs_context *ctx = nfs_fc2context(fc);
struct nfs_fh *mntfh = ctx->mntfh;
- struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
+ struct sockaddr_storage *sap = &ctx->nfs_server._address;
int extra_flags = NFS_MOUNT_LEGACY_INTERFACE;
int ret;
@@ -1044,7 +1044,7 @@ static int nfs23_parse_monolithic(struct fs_context *fc,
memcpy(sap, &data->addr, sizeof(data->addr));
ctx->nfs_server.addrlen = sizeof(data->addr);
ctx->nfs_server.port = ntohs(data->addr.sin_port);
- if (sap->sa_family != AF_INET ||
+ if (sap->ss_family != AF_INET ||
!nfs_verify_server_address(sap))
goto out_no_address;
@@ -1200,7 +1200,7 @@ static int nfs4_parse_monolithic(struct fs_context *fc,
struct nfs4_mount_data *data)
{
struct nfs_fs_context *ctx = nfs_fc2context(fc);
- struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
+ struct sockaddr_storage *sap = &ctx->nfs_server._address;
int ret;
char *c;
@@ -1314,7 +1314,7 @@ static int nfs_fs_context_validate(struct fs_context *fc)
{
struct nfs_fs_context *ctx = nfs_fc2context(fc);
struct nfs_subversion *nfs_mod;
- struct sockaddr *sap = (struct sockaddr *)&ctx->nfs_server.address;
+ struct sockaddr_storage *sap = &ctx->nfs_server._address;
int max_namelen = PAGE_SIZE;
int max_pathlen = NFS_MAXPATHLEN;
int port = 0;
@@ -1540,7 +1540,7 @@ static int nfs_init_fs_context(struct fs_context *fc)
ctx->version = nfss->nfs_client->rpc_ops->version;
ctx->minorversion = nfss->nfs_client->cl_minorversion;
- memcpy(&ctx->nfs_server.address, &nfss->nfs_client->cl_addr,
+ memcpy(&ctx->nfs_server._address, &nfss->nfs_client->cl_addr,
ctx->nfs_server.addrlen);
if (fc->net_ns != net) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index d914d609b85b..647fc3f547cb 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -69,7 +69,7 @@ static inline fmode_t flags_to_mode(int flags)
struct nfs_client_initdata {
unsigned long init_flags;
const char *hostname; /* Hostname of the server */
- const struct sockaddr *addr; /* Address of the server */
+ const struct sockaddr_storage *addr; /* Address of the server */
const char *nodename; /* Hostname of the client */
const char *ip_addr; /* IP address of the client */
size_t addrlen;
@@ -180,7 +180,7 @@ static inline struct nfs_fs_context *nfs_fc2context(const struct fs_context *fc)
/* mount_clnt.c */
struct nfs_mount_request {
- struct sockaddr *sap;
+ struct sockaddr_storage *sap;
size_t salen;
char *hostname;
char *dirpath;
@@ -223,7 +223,7 @@ extern void nfs4_server_set_init_caps(struct nfs_server *);
extern struct nfs_server *nfs4_create_server(struct fs_context *);
extern struct nfs_server *nfs4_create_referral_server(struct fs_context *);
extern int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen,
+ struct sockaddr_storage *sap, size_t salen,
struct net *net);
extern void nfs_free_server(struct nfs_server *server);
extern struct nfs_server *nfs_clone_server(struct nfs_server *,
@@ -235,7 +235,7 @@ extern int nfs_client_init_status(const struct nfs_client *clp);
extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
- const struct sockaddr *ds_addr,
+ const struct sockaddr_storage *ds_addr,
int ds_addrlen, int ds_proto,
unsigned int ds_timeo,
unsigned int ds_retrans,
@@ -243,7 +243,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
struct inode *);
extern struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
- const struct sockaddr *ds_addr, int ds_addrlen,
+ const struct sockaddr_storage *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo,
unsigned int ds_retrans);
#ifdef CONFIG_PROC_FS
@@ -894,13 +894,13 @@ static inline bool nfs_error_is_fatal_on_server(int err)
* Select between a default port value and a user-specified port value.
* If a zero value is set, then autobind will be used.
*/
-static inline void nfs_set_port(struct sockaddr *sap, int *port,
+static inline void nfs_set_port(struct sockaddr_storage *sap, int *port,
const unsigned short default_port)
{
if (*port == NFS_UNSPEC_PORT)
*port = default_port;
- rpc_set_port(sap, *port);
+ rpc_set_port((struct sockaddr *)sap, *port);
}
struct nfs_direct_req {
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index c5e3b6b3366a..68e76b626371 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -158,7 +158,7 @@ int nfs_mount(struct nfs_mount_request *info, int timeo, int retrans)
struct rpc_create_args args = {
.net = info->net,
.protocol = info->protocol,
- .address = info->sap,
+ .address = (struct sockaddr *)info->sap,
.addrsize = info->salen,
.timeout = &mnt_timeout,
.servername = info->hostname,
@@ -245,7 +245,7 @@ void nfs_umount(const struct nfs_mount_request *info)
struct rpc_create_args args = {
.net = info->net,
.protocol = IPPROTO_UDP,
- .address = info->sap,
+ .address = (struct sockaddr *)info->sap,
.addrsize = info->salen,
.timeout = &nfs_umnt_timeout,
.servername = info->hostname,
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 3295af4110f1..2f336ace7555 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -175,7 +175,7 @@ struct vfsmount *nfs_d_automount(struct path *path)
}
/* for submounts we want the same server; referrals will reassign */
- memcpy(&ctx->nfs_server.address, &client->cl_addr, client->cl_addrlen);
+ memcpy(&ctx->nfs_server._address, &client->cl_addr, client->cl_addrlen);
ctx->nfs_server.addrlen = client->cl_addrlen;
ctx->nfs_server.port = server->port;
diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c
index b49359afac88..669cda757a5c 100644
--- a/fs/nfs/nfs3client.c
+++ b/fs/nfs/nfs3client.c
@@ -78,7 +78,7 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
* the MDS.
*/
struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
- const struct sockaddr *ds_addr, int ds_addrlen,
+ const struct sockaddr_storage *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
{
struct rpc_timeout ds_timeout;
@@ -98,7 +98,7 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_server *mds_srv,
char buf[INET6_ADDRSTRLEN + 1];
/* fake a hostname because lockd wants it */
- if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+ if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0)
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 13424f0d793b..ecb428512fe1 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -1093,6 +1093,9 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f,
&args.seq_args, &res.seq_res, 0);
trace_nfs4_clone(src_inode, dst_inode, &args, status);
if (status == 0) {
+ /* a zero-length count means clone to EOF in src */
+ if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE)
+ count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset;
nfs42_copy_dest_done(dst_inode, dst_offset, count);
status = nfs_post_op_update_inode(dst_inode, res.dst_fattr);
}
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 400a71e75238..cfef738d765e 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -281,7 +281,7 @@ struct rpc_clnt *nfs4_negotiate_security(struct rpc_clnt *, struct inode *,
int nfs4_submount(struct fs_context *, struct nfs_server *);
int nfs4_replace_transport(struct nfs_server *server,
const struct nfs4_fs_locations *locations);
-size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa,
+size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss,
size_t salen, struct net *net, int port);
/* nfs4proc.c */
extern int nfs4_handle_exception(struct nfs_server *, int, struct nfs4_exception *);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 7a5162afa5c0..d3051b051a56 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -346,6 +346,7 @@ int nfs40_init_client(struct nfs_client *clp)
ret = nfs4_setup_slot_table(tbl, NFS4_MAX_SLOT_TABLE,
"NFSv4.0 transport Slot table");
if (ret) {
+ nfs4_shutdown_slot_table(tbl);
kfree(tbl);
return ret;
}
@@ -889,7 +890,7 @@ nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr,
*/
static int nfs4_set_client(struct nfs_server *server,
const char *hostname,
- const struct sockaddr *addr,
+ const struct sockaddr_storage *addr,
const size_t addrlen,
const char *ip_addr,
int proto, const struct rpc_timeout *timeparms,
@@ -924,7 +925,7 @@ static int nfs4_set_client(struct nfs_server *server,
__set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
__set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
- server->port = rpc_get_port(addr);
+ server->port = rpc_get_port((struct sockaddr *)addr);
/* Allocate or find a client reference we can use */
clp = nfs_get_client(&cl_init);
@@ -960,7 +961,7 @@ static int nfs4_set_client(struct nfs_server *server,
* the MDS.
*/
struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
- const struct sockaddr *ds_addr, int ds_addrlen,
+ const struct sockaddr_storage *ds_addr, int ds_addrlen,
int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
u32 minor_version)
{
@@ -980,7 +981,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
};
char buf[INET6_ADDRSTRLEN + 1];
- if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+ if (rpc_ntop((struct sockaddr *)ds_addr, buf, sizeof(buf)) <= 0)
return ERR_PTR(-EINVAL);
cl_init.hostname = buf;
@@ -1148,7 +1149,7 @@ static int nfs4_init_server(struct nfs_server *server, struct fs_context *fc)
/* Get a client record */
error = nfs4_set_client(server,
ctx->nfs_server.hostname,
- &ctx->nfs_server.address,
+ &ctx->nfs_server._address,
ctx->nfs_server.addrlen,
ctx->client_address,
ctx->nfs_server.protocol,
@@ -1238,7 +1239,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
rpc_set_port(&ctx->nfs_server.address, NFS_RDMA_PORT);
error = nfs4_set_client(server,
ctx->nfs_server.hostname,
- &ctx->nfs_server.address,
+ &ctx->nfs_server._address,
ctx->nfs_server.addrlen,
parent_client->cl_ipaddr,
XPRT_TRANSPORT_RDMA,
@@ -1254,7 +1255,7 @@ struct nfs_server *nfs4_create_referral_server(struct fs_context *fc)
rpc_set_port(&ctx->nfs_server.address, NFS_PORT);
error = nfs4_set_client(server,
ctx->nfs_server.hostname,
- &ctx->nfs_server.address,
+ &ctx->nfs_server._address,
ctx->nfs_server.addrlen,
parent_client->cl_ipaddr,
XPRT_TRANSPORT_TCP,
@@ -1303,14 +1304,14 @@ error:
* Returns zero on success, or a negative errno value.
*/
int nfs4_update_server(struct nfs_server *server, const char *hostname,
- struct sockaddr *sap, size_t salen, struct net *net)
+ struct sockaddr_storage *sap, size_t salen, struct net *net)
{
struct nfs_client *clp = server->nfs_client;
struct rpc_clnt *clnt = server->client;
struct xprt_create xargs = {
.ident = clp->cl_proto,
.net = net,
- .dstaddr = sap,
+ .dstaddr = (struct sockaddr *)sap,
.addrlen = salen,
.servername = hostname,
};
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index f2dbf904c598..9a98595bb160 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -164,16 +164,17 @@ static int nfs4_validate_fspath(struct dentry *dentry,
return 0;
}
-size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr *sa,
+size_t nfs_parse_server_name(char *string, size_t len, struct sockaddr_storage *ss,
size_t salen, struct net *net, int port)
{
+ struct sockaddr *sa = (struct sockaddr *)ss;
ssize_t ret;
ret = rpc_pton(net, string, len, sa, salen);
if (ret == 0) {
ret = rpc_uaddr2sockaddr(net, string, len, sa, salen);
if (ret == 0) {
- ret = nfs_dns_resolve_name(net, string, len, sa, salen);
+ ret = nfs_dns_resolve_name(net, string, len, ss, salen);
if (ret < 0)
ret = 0;
}
@@ -331,7 +332,7 @@ static int try_location(struct fs_context *fc,
ctx->nfs_server.addrlen =
nfs_parse_server_name(buf->data, buf->len,
- &ctx->nfs_server.address,
+ &ctx->nfs_server._address,
sizeof(ctx->nfs_server._address),
fc->net_ns, 0);
if (ctx->nfs_server.addrlen == 0)
@@ -483,14 +484,13 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
char *page, char *page2,
const struct nfs4_fs_location *location)
{
- const size_t addr_bufsize = sizeof(struct sockaddr_storage);
struct net *net = rpc_net_ns(server->client);
- struct sockaddr *sap;
+ struct sockaddr_storage *sap;
unsigned int s;
size_t salen;
int error;
- sap = kmalloc(addr_bufsize, GFP_KERNEL);
+ sap = kmalloc(sizeof(*sap), GFP_KERNEL);
if (sap == NULL)
return -ENOMEM;
@@ -506,10 +506,10 @@ static int nfs4_try_replacing_one_location(struct nfs_server *server,
continue;
salen = nfs_parse_server_name(buf->data, buf->len,
- sap, addr_bufsize, net, 0);
+ sap, sizeof(*sap), net, 0);
if (salen == 0)
continue;
- rpc_set_port(sap, NFS_PORT);
+ rpc_set_port((struct sockaddr *)sap, NFS_PORT);
error = -ENOMEM;
hostname = kmemdup_nul(buf->data, buf->len, GFP_KERNEL);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e2efcd26336c..86ed5c0142c3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3951,7 +3951,7 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location,
for (i = 0; i < location->nservers; i++) {
struct nfs4_string *srv_loc = &location->servers[i];
- struct sockaddr addr;
+ struct sockaddr_storage addr;
size_t addrlen;
struct xprt_create xprt_args = {
.ident = 0,
@@ -3974,7 +3974,7 @@ static void test_fs_location_for_trunking(struct nfs4_fs_location *location,
clp->cl_net, server->port);
if (!addrlen)
return;
- xprt_args.dstaddr = &addr;
+ xprt_args.dstaddr = (struct sockaddr *)&addr;
xprt_args.addrlen = addrlen;
servername = kmalloc(srv_loc->len + 1, GFP_KERNEL);
if (!servername)
@@ -7138,6 +7138,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
{
struct nfs4_lockdata *data = calldata;
struct nfs4_lock_state *lsp = data->lsp;
+ struct nfs_server *server = NFS_SERVER(d_inode(data->ctx->dentry));
if (!nfs4_sequence_done(task, &data->res.seq_res))
return;
@@ -7145,8 +7146,7 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
data->rpc_status = task->tk_status;
switch (task->tk_status) {
case 0:
- renew_lease(NFS_SERVER(d_inode(data->ctx->dentry)),
- data->timestamp);
+ renew_lease(server, data->timestamp);
if (data->arg.new_lock && !data->cancelled) {
data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0)
@@ -7167,6 +7167,8 @@ static void nfs4_lock_done(struct rpc_task *task, void *calldata)
if (!nfs4_stateid_match(&data->arg.open_stateid,
&lsp->ls_state->open_stateid))
goto out_restart;
+ else if (nfs4_async_handle_error(task, server, lsp->ls_state, NULL) == -EAGAIN)
+ goto out_restart;
} else if (!nfs4_stateid_match(&data->arg.lock_stateid,
&lsp->ls_stateid))
goto out_restart;
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index c3503fb26fa2..a2d2d5d1b088 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1786,6 +1786,7 @@ static void nfs4_state_mark_reclaim_helper(struct nfs_client *clp,
static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
{
+ set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
/* Mark all delegations for reclaim */
nfs_delegation_mark_reclaim(clp);
nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
@@ -2670,6 +2671,7 @@ static void nfs4_state_manager(struct nfs_client *clp)
if (status < 0)
goto out_error;
nfs4_state_end_reclaim_reboot(clp);
+ continue;
}
/* Detect expired delegations... */
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 987c88ddeaf0..5d035dd2d7bf 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -821,7 +821,7 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
static struct nfs_client *(*get_v3_ds_connect)(
struct nfs_server *mds_srv,
- const struct sockaddr *ds_addr,
+ const struct sockaddr_storage *ds_addr,
int ds_addrlen,
int ds_proto,
unsigned int ds_timeo,
@@ -882,7 +882,7 @@ static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
continue;
}
clp = get_v3_ds_connect(mds_srv,
- (struct sockaddr *)&da->da_addr,
+ &da->da_addr,
da->da_addrlen, da->da_transport,
timeo, retrans);
if (IS_ERR(clp))
@@ -951,7 +951,7 @@ static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
put_cred(xprtdata.cred);
} else {
clp = nfs4_set_ds_client(mds_srv,
- (struct sockaddr *)&da->da_addr,
+ &da->da_addr,
da->da_addrlen,
da->da_transport, timeo,
retrans, minor_version);
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ee66ffdb985e..05ae23657527 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -822,8 +822,7 @@ static int nfs_request_mount(struct fs_context *fc,
{
struct nfs_fs_context *ctx = nfs_fc2context(fc);
struct nfs_mount_request request = {
- .sap = (struct sockaddr *)
- &ctx->mount_server.address,
+ .sap = &ctx->mount_server._address,
.dirpath = ctx->nfs_server.export_path,
.protocol = ctx->mount_server.protocol,
.fh = root_fh,
@@ -854,7 +853,7 @@ static int nfs_request_mount(struct fs_context *fc,
* Construct the mount server's address.
*/
if (ctx->mount_server.address.sa_family == AF_UNSPEC) {
- memcpy(request.sap, &ctx->nfs_server.address,
+ memcpy(request.sap, &ctx->nfs_server._address,
ctx->nfs_server.addrlen);
ctx->mount_server.addrlen = ctx->nfs_server.addrlen;
}
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 29a62db155fb..adc4e87a71d2 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -893,9 +893,8 @@ __nfsd_file_cache_purge(struct net *net)
nf = rhashtable_walk_next(&iter);
while (!IS_ERR_OR_NULL(nf)) {
- if (net && nf->nf_net != net)
- continue;
- nfsd_file_unhash_and_dispose(nf, &dispose);
+ if (!net || nf->nf_net == net)
+ nfsd_file_unhash_and_dispose(nf, &dispose);
nf = rhashtable_walk_next(&iter);
}
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index e56510964b22..8ba8c4c50770 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -506,8 +506,9 @@ static int squashfs_readahead_fragment(struct page **page,
squashfs_i(inode)->fragment_size);
struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
unsigned int n, mask = (1 << (msblk->block_log - PAGE_SHIFT)) - 1;
+ int error = buffer->error;
- if (buffer->error)
+ if (error)
goto out;
expected += squashfs_i(inode)->fragment_offset;
@@ -529,7 +530,7 @@ static int squashfs_readahead_fragment(struct page **page,
out:
squashfs_cache_put(buffer);
- return buffer->error;
+ return error;
}
static void squashfs_readahead(struct readahead_control *ractl)
@@ -557,6 +558,13 @@ static void squashfs_readahead(struct readahead_control *ractl)
int res, bsize;
u64 block = 0;
unsigned int expected;
+ struct page *last_page;
+
+ expected = start >> msblk->block_log == file_end ?
+ (i_size_read(inode) & (msblk->block_size - 1)) :
+ msblk->block_size;
+
+ max_pages = (expected + PAGE_SIZE - 1) >> PAGE_SHIFT;
nr_pages = __readahead_batch(ractl, pages, max_pages);
if (!nr_pages)
@@ -566,13 +574,10 @@ static void squashfs_readahead(struct readahead_control *ractl)
goto skip_pages;
index = pages[0]->index >> shift;
+
if ((pages[nr_pages - 1]->index >> shift) != index)
goto skip_pages;
- expected = index == file_end ?
- (i_size_read(inode) & (msblk->block_size - 1)) :
- msblk->block_size;
-
if (index == file_end && squashfs_i(inode)->fragment_block !=
SQUASHFS_INVALID_BLK) {
res = squashfs_readahead_fragment(pages, nr_pages,
@@ -593,15 +598,15 @@ static void squashfs_readahead(struct readahead_control *ractl)
res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
- squashfs_page_actor_free(actor);
+ last_page = squashfs_page_actor_free(actor);
if (res == expected) {
int bytes;
/* Last page (if present) may have trailing bytes not filled */
bytes = res % PAGE_SIZE;
- if (pages[nr_pages - 1]->index == file_end && bytes)
- memzero_page(pages[nr_pages - 1], bytes,
+ if (index == file_end && bytes && last_page)
+ memzero_page(last_page, bytes,
PAGE_SIZE - bytes);
for (i = 0; i < nr_pages; i++) {
diff --git a/fs/squashfs/page_actor.c b/fs/squashfs/page_actor.c
index 54b93bf4a25c..81af6c4ca115 100644
--- a/fs/squashfs/page_actor.c
+++ b/fs/squashfs/page_actor.c
@@ -71,11 +71,13 @@ static void *handle_next_page(struct squashfs_page_actor *actor)
(actor->next_index != actor->page[actor->next_page]->index)) {
actor->next_index++;
actor->returned_pages++;
+ actor->last_page = NULL;
return actor->alloc_buffer ? actor->tmp_buffer : ERR_PTR(-ENOMEM);
}
actor->next_index++;
actor->returned_pages++;
+ actor->last_page = actor->page[actor->next_page];
return actor->pageaddr = kmap_local_page(actor->page[actor->next_page++]);
}
@@ -125,6 +127,7 @@ struct squashfs_page_actor *squashfs_page_actor_init_special(struct squashfs_sb_
actor->returned_pages = 0;
actor->next_index = page[0]->index & ~((1 << (msblk->block_log - PAGE_SHIFT)) - 1);
actor->pageaddr = NULL;
+ actor->last_page = NULL;
actor->alloc_buffer = msblk->decompressor->alloc_buffer;
actor->squashfs_first_page = direct_first_page;
actor->squashfs_next_page = direct_next_page;
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 95ffbb543d91..97d4983559b1 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -16,6 +16,7 @@ struct squashfs_page_actor {
void *(*squashfs_first_page)(struct squashfs_page_actor *);
void *(*squashfs_next_page)(struct squashfs_page_actor *);
void (*squashfs_finish_page)(struct squashfs_page_actor *);
+ struct page *last_page;
int pages;
int length;
int next_page;
@@ -29,10 +30,13 @@ extern struct squashfs_page_actor *squashfs_page_actor_init(void **buffer,
extern struct squashfs_page_actor *squashfs_page_actor_init_special(
struct squashfs_sb_info *msblk,
struct page **page, int pages, int length);
-static inline void squashfs_page_actor_free(struct squashfs_page_actor *actor)
+static inline struct page *squashfs_page_actor_free(struct squashfs_page_actor *actor)
{
+ struct page *last_page = actor->last_page;
+
kfree(actor->tmp_buffer);
kfree(actor);
+ return last_page;
}
static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
{
diff --git a/fs/super.c b/fs/super.c
index 6a82660e1adb..8d39e4f11cfa 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -291,6 +291,7 @@ static void __put_super(struct super_block *s)
WARN_ON(s->s_inode_lru.node);
WARN_ON(!list_empty(&s->s_mounts));
security_sb_free(s);
+ fscrypt_destroy_keyring(s);
put_user_ns(s->s_user_ns);
kfree(s->s_subtype);
call_rcu(&s->rcu, destroy_super_rcu);
@@ -479,7 +480,7 @@ void generic_shutdown_super(struct super_block *sb)
evict_inodes(sb);
/* only nonzero refcount inodes can have marks */
fsnotify_sb_delete(sb);
- fscrypt_sb_delete(sb);
+ fscrypt_destroy_keyring(sb);
security_sb_delete(sb);
if (sb->s_dio_done_wq) {
diff --git a/fs/xfs/libxfs/xfs_ag.h b/fs/xfs/libxfs/xfs_ag.h
index 517a138faa66..191b22b9a35b 100644
--- a/fs/xfs/libxfs/xfs_ag.h
+++ b/fs/xfs/libxfs/xfs_ag.h
@@ -133,6 +133,21 @@ xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno)
return true;
}
+static inline bool
+xfs_verify_agbext(
+ struct xfs_perag *pag,
+ xfs_agblock_t agbno,
+ xfs_agblock_t len)
+{
+ if (agbno + len <= agbno)
+ return false;
+
+ if (!xfs_verify_agbno(pag, agbno))
+ return false;
+
+ return xfs_verify_agbno(pag, agbno + len - 1);
+}
+
/*
* Verify that an AG inode number pointer neither points outside the AG
* nor points at static metadata.
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 6261599bb389..de79f5d07f65 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -263,11 +263,7 @@ xfs_alloc_get_rec(
goto out_bad_rec;
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(pag, *bno))
- goto out_bad_rec;
- if (*bno > *bno + *len)
- goto out_bad_rec;
- if (!xfs_verify_agbno(pag, *bno + *len - 1))
+ if (!xfs_verify_agbext(pag, *bno, *len))
goto out_bad_rec;
return 0;
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index d9b66306a9a7..cb9e950a911d 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -146,6 +146,8 @@ xfs_dir3_leaf_check_int(
xfs_dir2_leaf_tail_t *ltp;
int stale;
int i;
+ bool isleaf1 = (hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
+ hdr->magic == XFS_DIR3_LEAF1_MAGIC);
ltp = xfs_dir2_leaf_tail_p(geo, leaf);
@@ -158,8 +160,7 @@ xfs_dir3_leaf_check_int(
return __this_address;
/* Leaves and bests don't overlap in leaf format. */
- if ((hdr->magic == XFS_DIR2_LEAF1_MAGIC ||
- hdr->magic == XFS_DIR3_LEAF1_MAGIC) &&
+ if (isleaf1 &&
(char *)&hdr->ents[hdr->count] > (char *)xfs_dir2_leaf_bests_p(ltp))
return __this_address;
@@ -175,6 +176,10 @@ xfs_dir3_leaf_check_int(
}
if (hdr->ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
stale++;
+ if (isleaf1 && xfs_dir2_dataptr_to_db(geo,
+ be32_to_cpu(hdr->ents[i].address)) >=
+ be32_to_cpu(ltp->bestcount))
+ return __this_address;
}
if (hdr->stale != stale)
return __this_address;
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index b55bdfa9c8a8..371dc07233e0 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1564,20 +1564,6 @@ struct xfs_rmap_rec {
#define RMAPBT_UNUSED_OFFSET_BITLEN 7
#define RMAPBT_OFFSET_BITLEN 54
-#define XFS_RMAP_ATTR_FORK (1 << 0)
-#define XFS_RMAP_BMBT_BLOCK (1 << 1)
-#define XFS_RMAP_UNWRITTEN (1 << 2)
-#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \
- XFS_RMAP_BMBT_BLOCK)
-#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN)
-struct xfs_rmap_irec {
- xfs_agblock_t rm_startblock; /* extent start block */
- xfs_extlen_t rm_blockcount; /* extent length */
- uint64_t rm_owner; /* extent owner */
- uint64_t rm_offset; /* offset within the owner */
- unsigned int rm_flags; /* state flags */
-};
-
/*
* Key structure
*
@@ -1626,7 +1612,7 @@ unsigned int xfs_refc_block(struct xfs_mount *mp);
* on the startblock. This speeds up mount time deletion of stale
* staging extents because they're all at the right side of the tree.
*/
-#define XFS_REFC_COW_START ((xfs_agblock_t)(1U << 31))
+#define XFS_REFC_COWFLAG (1U << 31)
#define REFCNTBT_COWFLAG_BITLEN 1
#define REFCNTBT_AGBLOCK_BITLEN 31
@@ -1640,12 +1626,6 @@ struct xfs_refcount_key {
__be32 rc_startblock; /* starting block number */
};
-struct xfs_refcount_irec {
- xfs_agblock_t rc_startblock; /* starting block number */
- xfs_extlen_t rc_blockcount; /* count of free blocks */
- xfs_nlink_t rc_refcount; /* number of inodes linked here */
-};
-
#define MAXREFCOUNT ((xfs_nlink_t)~0U)
#define MAXREFCEXTLEN ((xfs_extlen_t)~0U)
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index b351b9dc6561..f13e0809dc63 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -613,25 +613,49 @@ typedef struct xfs_efi_log_format {
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_t efi_extents[]; /* array of extents to free */
} xfs_efi_log_format_t;
+static inline size_t
+xfs_efi_log_format_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format) +
+ nr * sizeof(struct xfs_extent);
+}
+
typedef struct xfs_efi_log_format_32 {
uint16_t efi_type; /* efi log item type */
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_32_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_32_t efi_extents[]; /* array of extents to free */
} __attribute__((packed)) xfs_efi_log_format_32_t;
+static inline size_t
+xfs_efi_log_format32_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format_32) +
+ nr * sizeof(struct xfs_extent_32);
+}
+
typedef struct xfs_efi_log_format_64 {
uint16_t efi_type; /* efi log item type */
uint16_t efi_size; /* size of this item */
uint32_t efi_nextents; /* # extents to free */
uint64_t efi_id; /* efi identifier */
- xfs_extent_64_t efi_extents[1]; /* array of extents to free */
+ xfs_extent_64_t efi_extents[]; /* array of extents to free */
} xfs_efi_log_format_64_t;
+static inline size_t
+xfs_efi_log_format64_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efi_log_format_64) +
+ nr * sizeof(struct xfs_extent_64);
+}
+
/*
* This is the structure used to lay out an efd log item in the
* log. The efd_extents array is a variable size array whose
@@ -642,25 +666,49 @@ typedef struct xfs_efd_log_format {
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_t efd_extents[]; /* array of extents freed */
} xfs_efd_log_format_t;
+static inline size_t
+xfs_efd_log_format_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format) +
+ nr * sizeof(struct xfs_extent);
+}
+
typedef struct xfs_efd_log_format_32 {
uint16_t efd_type; /* efd log item type */
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_32_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_32_t efd_extents[]; /* array of extents freed */
} __attribute__((packed)) xfs_efd_log_format_32_t;
+static inline size_t
+xfs_efd_log_format32_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format_32) +
+ nr * sizeof(struct xfs_extent_32);
+}
+
typedef struct xfs_efd_log_format_64 {
uint16_t efd_type; /* efd log item type */
uint16_t efd_size; /* size of this item */
uint32_t efd_nextents; /* # of extents freed */
uint64_t efd_efi_id; /* id of corresponding efi */
- xfs_extent_64_t efd_extents[1]; /* array of extents freed */
+ xfs_extent_64_t efd_extents[]; /* array of extents freed */
} xfs_efd_log_format_64_t;
+static inline size_t
+xfs_efd_log_format64_sizeof(
+ unsigned int nr)
+{
+ return sizeof(struct xfs_efd_log_format_64) +
+ nr * sizeof(struct xfs_extent_64);
+}
+
/*
* RUI/RUD (reverse mapping) log format definitions
*/
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 64b910caafaa..3f34bafe18dd 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -46,13 +46,16 @@ STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
int
xfs_refcount_lookup_le(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
}
@@ -63,13 +66,16 @@ xfs_refcount_lookup_le(
int
xfs_refcount_lookup_ge(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_GE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
}
@@ -80,13 +86,16 @@ xfs_refcount_lookup_ge(
int
xfs_refcount_lookup_eq(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno, bno,
+ trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
cur->bc_rec.rc.rc_blockcount = 0;
+ cur->bc_rec.rc.rc_domain = domain;
return xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
}
@@ -96,7 +105,17 @@ xfs_refcount_btrec_to_irec(
const union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec)
{
- irec->rc_startblock = be32_to_cpu(rec->refc.rc_startblock);
+ uint32_t start;
+
+ start = be32_to_cpu(rec->refc.rc_startblock);
+ if (start & XFS_REFC_COWFLAG) {
+ start &= ~XFS_REFC_COWFLAG;
+ irec->rc_domain = XFS_REFC_DOMAIN_COW;
+ } else {
+ irec->rc_domain = XFS_REFC_DOMAIN_SHARED;
+ }
+
+ irec->rc_startblock = start;
irec->rc_blockcount = be32_to_cpu(rec->refc.rc_blockcount);
irec->rc_refcount = be32_to_cpu(rec->refc.rc_refcount);
}
@@ -114,7 +133,6 @@ xfs_refcount_get_rec(
struct xfs_perag *pag = cur->bc_ag.pag;
union xfs_btree_rec *rec;
int error;
- xfs_agblock_t realstart;
error = xfs_btree_get_rec(cur, &rec, stat);
if (error || !*stat)
@@ -124,22 +142,11 @@ xfs_refcount_get_rec(
if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
goto out_bad_rec;
- /* handle special COW-staging state */
- realstart = irec->rc_startblock;
- if (realstart & XFS_REFC_COW_START) {
- if (irec->rc_refcount != 1)
- goto out_bad_rec;
- realstart &= ~XFS_REFC_COW_START;
- } else if (irec->rc_refcount < 2) {
+ if (!xfs_refcount_check_domain(irec))
goto out_bad_rec;
- }
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(pag, realstart))
- goto out_bad_rec;
- if (realstart > realstart + irec->rc_blockcount)
- goto out_bad_rec;
- if (!xfs_verify_agbno(pag, realstart + irec->rc_blockcount - 1))
+ if (!xfs_verify_agbext(pag, irec->rc_startblock, irec->rc_blockcount))
goto out_bad_rec;
if (irec->rc_refcount == 0 || irec->rc_refcount > MAXREFCOUNT)
@@ -169,12 +176,17 @@ xfs_refcount_update(
struct xfs_refcount_irec *irec)
{
union xfs_btree_rec rec;
+ uint32_t start;
int error;
trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
- rec.refc.rc_startblock = cpu_to_be32(irec->rc_startblock);
+
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ rec.refc.rc_startblock = cpu_to_be32(start);
rec.refc.rc_blockcount = cpu_to_be32(irec->rc_blockcount);
rec.refc.rc_refcount = cpu_to_be32(irec->rc_refcount);
+
error = xfs_btree_update(cur, &rec);
if (error)
trace_xfs_refcount_update_error(cur->bc_mp,
@@ -196,9 +208,12 @@ xfs_refcount_insert(
int error;
trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+
cur->bc_rec.rc.rc_startblock = irec->rc_startblock;
cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
cur->bc_rec.rc.rc_refcount = irec->rc_refcount;
+ cur->bc_rec.rc.rc_domain = irec->rc_domain;
+
error = xfs_btree_insert(cur, i);
if (error)
goto out_error;
@@ -244,7 +259,8 @@ xfs_refcount_delete(
}
if (error)
goto out_error;
- error = xfs_refcount_lookup_ge(cur, irec.rc_startblock, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, irec.rc_domain, irec.rc_startblock,
+ &found_rec);
out_error:
if (error)
trace_xfs_refcount_delete_error(cur->bc_mp,
@@ -343,6 +359,7 @@ xfs_refc_next(
STATIC int
xfs_refcount_split_extent(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
bool *shape_changed)
{
@@ -351,7 +368,7 @@ xfs_refcount_split_extent(
int error;
*shape_changed = false;
- error = xfs_refcount_lookup_le(cur, agbno, &found_rec);
+ error = xfs_refcount_lookup_le(cur, domain, agbno, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -364,6 +381,8 @@ xfs_refcount_split_extent(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (rcext.rc_domain != domain)
+ return 0;
if (rcext.rc_startblock == agbno || xfs_refc_next(&rcext) <= agbno)
return 0;
@@ -415,6 +434,9 @@ xfs_refcount_merge_center_extents(
trace_xfs_refcount_merge_center_extents(cur->bc_mp,
cur->bc_ag.pag->pag_agno, left, center, right);
+ ASSERT(left->rc_domain == center->rc_domain);
+ ASSERT(right->rc_domain == center->rc_domain);
+
/*
* Make sure the center and right extents are not in the btree.
* If the center extent was synthesized, the first delete call
@@ -423,8 +445,8 @@ xfs_refcount_merge_center_extents(
* call removes the center and the second one removes the right
* extent.
*/
- error = xfs_refcount_lookup_ge(cur, center->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_ge(cur, center->rc_domain,
+ center->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -451,8 +473,8 @@ xfs_refcount_merge_center_extents(
}
/* Enlarge the left extent. */
- error = xfs_refcount_lookup_le(cur, left->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, left->rc_domain,
+ left->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -491,10 +513,12 @@ xfs_refcount_merge_left_extent(
trace_xfs_refcount_merge_left_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, left, cleft);
+ ASSERT(left->rc_domain == cleft->rc_domain);
+
/* If the extent at agbno (cleft) wasn't synthesized, remove it. */
if (cleft->rc_refcount > 1) {
- error = xfs_refcount_lookup_le(cur, cleft->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, cleft->rc_domain,
+ cleft->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -512,8 +536,8 @@ xfs_refcount_merge_left_extent(
}
/* Enlarge the left extent. */
- error = xfs_refcount_lookup_le(cur, left->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, left->rc_domain,
+ left->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -552,13 +576,15 @@ xfs_refcount_merge_right_extent(
trace_xfs_refcount_merge_right_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, cright, right);
+ ASSERT(right->rc_domain == cright->rc_domain);
+
/*
* If the extent ending at agbno+aglen (cright) wasn't synthesized,
* remove it.
*/
if (cright->rc_refcount > 1) {
- error = xfs_refcount_lookup_le(cur, cright->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, cright->rc_domain,
+ cright->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -576,8 +602,8 @@ xfs_refcount_merge_right_extent(
}
/* Enlarge the right extent. */
- error = xfs_refcount_lookup_le(cur, right->rc_startblock,
- &found_rec);
+ error = xfs_refcount_lookup_le(cur, right->rc_domain,
+ right->rc_startblock, &found_rec);
if (error)
goto out_error;
if (XFS_IS_CORRUPT(cur->bc_mp, found_rec != 1)) {
@@ -600,8 +626,6 @@ out_error:
return error;
}
-#define XFS_FIND_RCEXT_SHARED 1
-#define XFS_FIND_RCEXT_COW 2
/*
* Find the left extent and the one after it (cleft). This function assumes
* that we've already split any extent crossing agbno.
@@ -611,16 +635,16 @@ xfs_refcount_find_left_extents(
struct xfs_btree_cur *cur,
struct xfs_refcount_irec *left,
struct xfs_refcount_irec *cleft,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
- xfs_extlen_t aglen,
- int flags)
+ xfs_extlen_t aglen)
{
struct xfs_refcount_irec tmp;
int error;
int found_rec;
left->rc_startblock = cleft->rc_startblock = NULLAGBLOCK;
- error = xfs_refcount_lookup_le(cur, agbno - 1, &found_rec);
+ error = xfs_refcount_lookup_le(cur, domain, agbno - 1, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -634,11 +658,9 @@ xfs_refcount_find_left_extents(
goto out_error;
}
- if (xfs_refc_next(&tmp) != agbno)
- return 0;
- if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+ if (tmp.rc_domain != domain)
return 0;
- if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+ if (xfs_refc_next(&tmp) != agbno)
return 0;
/* We have a left extent; retrieve (or invent) the next right one */
*left = tmp;
@@ -655,6 +677,9 @@ xfs_refcount_find_left_extents(
goto out_error;
}
+ if (tmp.rc_domain != domain)
+ goto not_found;
+
/* if tmp starts at the end of our range, just use that */
if (tmp.rc_startblock == agbno)
*cleft = tmp;
@@ -671,8 +696,10 @@ xfs_refcount_find_left_extents(
cleft->rc_blockcount = min(aglen,
tmp.rc_startblock - agbno);
cleft->rc_refcount = 1;
+ cleft->rc_domain = domain;
}
} else {
+not_found:
/*
* No extents, so pretend that there's one covering the whole
* range.
@@ -680,6 +707,7 @@ xfs_refcount_find_left_extents(
cleft->rc_startblock = agbno;
cleft->rc_blockcount = aglen;
cleft->rc_refcount = 1;
+ cleft->rc_domain = domain;
}
trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
left, cleft, agbno);
@@ -700,16 +728,16 @@ xfs_refcount_find_right_extents(
struct xfs_btree_cur *cur,
struct xfs_refcount_irec *right,
struct xfs_refcount_irec *cright,
+ enum xfs_refc_domain domain,
xfs_agblock_t agbno,
- xfs_extlen_t aglen,
- int flags)
+ xfs_extlen_t aglen)
{
struct xfs_refcount_irec tmp;
int error;
int found_rec;
right->rc_startblock = cright->rc_startblock = NULLAGBLOCK;
- error = xfs_refcount_lookup_ge(cur, agbno + aglen, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, domain, agbno + aglen, &found_rec);
if (error)
goto out_error;
if (!found_rec)
@@ -723,11 +751,9 @@ xfs_refcount_find_right_extents(
goto out_error;
}
- if (tmp.rc_startblock != agbno + aglen)
- return 0;
- if ((flags & XFS_FIND_RCEXT_SHARED) && tmp.rc_refcount < 2)
+ if (tmp.rc_domain != domain)
return 0;
- if ((flags & XFS_FIND_RCEXT_COW) && tmp.rc_refcount > 1)
+ if (tmp.rc_startblock != agbno + aglen)
return 0;
/* We have a right extent; retrieve (or invent) the next left one */
*right = tmp;
@@ -744,6 +770,9 @@ xfs_refcount_find_right_extents(
goto out_error;
}
+ if (tmp.rc_domain != domain)
+ goto not_found;
+
/* if tmp ends at the end of our range, just use that */
if (xfs_refc_next(&tmp) == agbno + aglen)
*cright = tmp;
@@ -760,8 +789,10 @@ xfs_refcount_find_right_extents(
cright->rc_blockcount = right->rc_startblock -
cright->rc_startblock;
cright->rc_refcount = 1;
+ cright->rc_domain = domain;
}
} else {
+not_found:
/*
* No extents, so pretend that there's one covering the whole
* range.
@@ -769,6 +800,7 @@ xfs_refcount_find_right_extents(
cright->rc_startblock = agbno;
cright->rc_blockcount = aglen;
cright->rc_refcount = 1;
+ cright->rc_domain = domain;
}
trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
cright, right, agbno + aglen);
@@ -794,10 +826,10 @@ xfs_refc_valid(
STATIC int
xfs_refcount_merge_extents(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t *agbno,
xfs_extlen_t *aglen,
enum xfs_refc_adjust_op adjust,
- int flags,
bool *shape_changed)
{
struct xfs_refcount_irec left = {0}, cleft = {0};
@@ -812,12 +844,12 @@ xfs_refcount_merge_extents(
* just below (agbno + aglen) [cright], and just above (agbno + aglen)
* [right].
*/
- error = xfs_refcount_find_left_extents(cur, &left, &cleft, *agbno,
- *aglen, flags);
+ error = xfs_refcount_find_left_extents(cur, &left, &cleft, domain,
+ *agbno, *aglen);
if (error)
return error;
- error = xfs_refcount_find_right_extents(cur, &right, &cright, *agbno,
- *aglen, flags);
+ error = xfs_refcount_find_right_extents(cur, &right, &cright, domain,
+ *agbno, *aglen);
if (error)
return error;
@@ -870,7 +902,7 @@ xfs_refcount_merge_extents(
aglen);
}
- return error;
+ return 0;
}
/*
@@ -933,7 +965,8 @@ xfs_refcount_adjust_extents(
if (*aglen == 0)
return 0;
- error = xfs_refcount_lookup_ge(cur, *agbno, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_SHARED, *agbno,
+ &found_rec);
if (error)
goto out_error;
@@ -941,10 +974,11 @@ xfs_refcount_adjust_extents(
error = xfs_refcount_get_rec(cur, &ext, &found_rec);
if (error)
goto out_error;
- if (!found_rec) {
+ if (!found_rec || ext.rc_domain != XFS_REFC_DOMAIN_SHARED) {
ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
ext.rc_blockcount = 0;
ext.rc_refcount = 0;
+ ext.rc_domain = XFS_REFC_DOMAIN_SHARED;
}
/*
@@ -957,6 +991,8 @@ xfs_refcount_adjust_extents(
tmp.rc_blockcount = min(*aglen,
ext.rc_startblock - *agbno);
tmp.rc_refcount = 1 + adj;
+ tmp.rc_domain = XFS_REFC_DOMAIN_SHARED;
+
trace_xfs_refcount_modify_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, &tmp);
@@ -986,15 +1022,30 @@ xfs_refcount_adjust_extents(
(*agbno) += tmp.rc_blockcount;
(*aglen) -= tmp.rc_blockcount;
- error = xfs_refcount_lookup_ge(cur, *agbno,
+ /* Stop if there's nothing left to modify */
+ if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
+ break;
+
+ /* Move the cursor to the start of ext. */
+ error = xfs_refcount_lookup_ge(cur,
+ XFS_REFC_DOMAIN_SHARED, *agbno,
&found_rec);
if (error)
goto out_error;
}
- /* Stop if there's nothing left to modify */
- if (*aglen == 0 || !xfs_refcount_still_have_space(cur))
- break;
+ /*
+ * A previous step trimmed agbno/aglen such that the end of the
+ * range would not be in the middle of the record. If this is
+ * no longer the case, something is seriously wrong with the
+ * btree. Make sure we never feed the synthesized record into
+ * the processing loop below.
+ */
+ if (XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount == 0) ||
+ XFS_IS_CORRUPT(cur->bc_mp, ext.rc_blockcount > *aglen)) {
+ error = -EFSCORRUPTED;
+ goto out_error;
+ }
/*
* Adjust the reference count and either update the tree
@@ -1070,13 +1121,15 @@ xfs_refcount_adjust(
/*
* Ensure that no rcextents cross the boundary of the adjustment range.
*/
- error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+ agbno, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
shape_changes++;
- error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_SHARED,
+ agbno + aglen, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
@@ -1085,8 +1138,8 @@ xfs_refcount_adjust(
/*
* Try to merge with the left or right extents of the range.
*/
- error = xfs_refcount_merge_extents(cur, new_agbno, new_aglen, adj,
- XFS_FIND_RCEXT_SHARED, &shape_changed);
+ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_SHARED,
+ new_agbno, new_aglen, adj, &shape_changed);
if (error)
goto out_error;
if (shape_changed)
@@ -1125,6 +1178,32 @@ xfs_refcount_finish_one_cleanup(
}
/*
+ * Set up a continuation a deferred refcount operation by updating the intent.
+ * Checks to make sure we're not going to run off the end of the AG.
+ */
+static inline int
+xfs_refcount_continue_op(
+ struct xfs_btree_cur *cur,
+ xfs_fsblock_t startblock,
+ xfs_agblock_t new_agbno,
+ xfs_extlen_t new_len,
+ xfs_fsblock_t *new_fsbno)
+{
+ struct xfs_mount *mp = cur->bc_mp;
+ struct xfs_perag *pag = cur->bc_ag.pag;
+
+ if (XFS_IS_CORRUPT(mp, !xfs_verify_agbext(pag, new_agbno, new_len)))
+ return -EFSCORRUPTED;
+
+ *new_fsbno = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+
+ ASSERT(xfs_verify_fsbext(mp, *new_fsbno, new_len));
+ ASSERT(pag->pag_agno == XFS_FSB_TO_AGNO(mp, *new_fsbno));
+
+ return 0;
+}
+
+/*
* Process one of the deferred refcount operations. We pass back the
* btree cursor to maintain our lock on the btree between calls.
* This saves time and eliminates a buffer deadlock between the
@@ -1191,12 +1270,20 @@ xfs_refcount_finish_one(
case XFS_REFCOUNT_INCREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
new_len, XFS_REFCOUNT_ADJUST_INCREASE);
- *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+ if (error)
+ goto out_drop;
+ if (*new_len > 0)
+ error = xfs_refcount_continue_op(rcur, startblock,
+ new_agbno, *new_len, new_fsb);
break;
case XFS_REFCOUNT_DECREASE:
error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
new_len, XFS_REFCOUNT_ADJUST_DECREASE);
- *new_fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, new_agbno);
+ if (error)
+ goto out_drop;
+ if (*new_len > 0)
+ error = xfs_refcount_continue_op(rcur, startblock,
+ new_agbno, *new_len, new_fsb);
break;
case XFS_REFCOUNT_ALLOC_COW:
*new_fsb = startblock + blockcount;
@@ -1307,7 +1394,8 @@ xfs_refcount_find_shared(
*flen = 0;
/* Try to find a refcount extent that crosses the start */
- error = xfs_refcount_lookup_le(cur, agbno, &have);
+ error = xfs_refcount_lookup_le(cur, XFS_REFC_DOMAIN_SHARED, agbno,
+ &have);
if (error)
goto out_error;
if (!have) {
@@ -1325,6 +1413,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+ goto done;
/* If the extent ends before the start, look at the next one */
if (tmp.rc_startblock + tmp.rc_blockcount <= agbno) {
@@ -1340,6 +1430,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED)
+ goto done;
}
/* If the extent starts after the range we want, bail out */
@@ -1371,7 +1463,8 @@ xfs_refcount_find_shared(
error = -EFSCORRUPTED;
goto out_error;
}
- if (tmp.rc_startblock >= agbno + aglen ||
+ if (tmp.rc_domain != XFS_REFC_DOMAIN_SHARED ||
+ tmp.rc_startblock >= agbno + aglen ||
tmp.rc_startblock != *fbno + *flen)
break;
*flen = min(*flen + tmp.rc_blockcount, agbno + aglen - *fbno);
@@ -1455,17 +1548,23 @@ xfs_refcount_adjust_cow_extents(
return 0;
/* Find any overlapping refcount records */
- error = xfs_refcount_lookup_ge(cur, agbno, &found_rec);
+ error = xfs_refcount_lookup_ge(cur, XFS_REFC_DOMAIN_COW, agbno,
+ &found_rec);
if (error)
goto out_error;
error = xfs_refcount_get_rec(cur, &ext, &found_rec);
if (error)
goto out_error;
+ if (XFS_IS_CORRUPT(cur->bc_mp, found_rec &&
+ ext.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ error = -EFSCORRUPTED;
+ goto out_error;
+ }
if (!found_rec) {
- ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks +
- XFS_REFC_COW_START;
+ ext.rc_startblock = cur->bc_mp->m_sb.sb_agblocks;
ext.rc_blockcount = 0;
ext.rc_refcount = 0;
+ ext.rc_domain = XFS_REFC_DOMAIN_COW;
}
switch (adj) {
@@ -1480,6 +1579,8 @@ xfs_refcount_adjust_cow_extents(
tmp.rc_startblock = agbno;
tmp.rc_blockcount = aglen;
tmp.rc_refcount = 1;
+ tmp.rc_domain = XFS_REFC_DOMAIN_COW;
+
trace_xfs_refcount_modify_extent(cur->bc_mp,
cur->bc_ag.pag->pag_agno, &tmp);
@@ -1542,24 +1643,24 @@ xfs_refcount_adjust_cow(
bool shape_changed;
int error;
- agbno += XFS_REFC_COW_START;
-
/*
* Ensure that no rcextents cross the boundary of the adjustment range.
*/
- error = xfs_refcount_split_extent(cur, agbno, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+ agbno, &shape_changed);
if (error)
goto out_error;
- error = xfs_refcount_split_extent(cur, agbno + aglen, &shape_changed);
+ error = xfs_refcount_split_extent(cur, XFS_REFC_DOMAIN_COW,
+ agbno + aglen, &shape_changed);
if (error)
goto out_error;
/*
* Try to merge with the left or right extents of the range.
*/
- error = xfs_refcount_merge_extents(cur, &agbno, &aglen, adj,
- XFS_FIND_RCEXT_COW, &shape_changed);
+ error = xfs_refcount_merge_extents(cur, XFS_REFC_DOMAIN_COW, &agbno,
+ &aglen, adj, &shape_changed);
if (error)
goto out_error;
@@ -1666,10 +1767,18 @@ xfs_refcount_recover_extent(
be32_to_cpu(rec->refc.rc_refcount) != 1))
return -EFSCORRUPTED;
- rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0);
+ rr = kmalloc(sizeof(struct xfs_refcount_recovery),
+ GFP_KERNEL | __GFP_NOFAIL);
+ INIT_LIST_HEAD(&rr->rr_list);
xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
- list_add_tail(&rr->rr_list, debris);
+ if (XFS_IS_CORRUPT(cur->bc_mp,
+ rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
+ kfree(rr);
+ return -EFSCORRUPTED;
+ }
+
+ list_add_tail(&rr->rr_list, debris);
return 0;
}
@@ -1687,10 +1796,11 @@ xfs_refcount_recover_cow_leftovers(
union xfs_btree_irec low;
union xfs_btree_irec high;
xfs_fsblock_t fsb;
- xfs_agblock_t agbno;
int error;
- if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
+ /* reflink filesystems mustn't have AGs larger than 2^31-1 blocks */
+ BUILD_BUG_ON(XFS_MAX_CRC_AG_BLOCKS >= XFS_REFC_COWFLAG);
+ if (mp->m_sb.sb_agblocks > XFS_MAX_CRC_AG_BLOCKS)
return -EOPNOTSUPP;
INIT_LIST_HEAD(&debris);
@@ -1717,7 +1827,7 @@ xfs_refcount_recover_cow_leftovers(
/* Find all the leftover CoW staging extents. */
memset(&low, 0, sizeof(low));
memset(&high, 0, sizeof(high));
- low.rc.rc_startblock = XFS_REFC_COW_START;
+ low.rc.rc_domain = high.rc.rc_domain = XFS_REFC_DOMAIN_COW;
high.rc.rc_startblock = -1U;
error = xfs_btree_query_range(cur, &low, &high,
xfs_refcount_recover_extent, &debris);
@@ -1738,8 +1848,8 @@ xfs_refcount_recover_cow_leftovers(
&rr->rr_rrec);
/* Free the orphan record */
- agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
- fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno, agbno);
+ fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
+ rr->rr_rrec.rc_startblock);
xfs_refcount_free_cow_extent(tp, fsb,
rr->rr_rrec.rc_blockcount);
@@ -1751,7 +1861,7 @@ xfs_refcount_recover_cow_leftovers(
goto out_free;
list_del(&rr->rr_list);
- kmem_free(rr);
+ kfree(rr);
}
return error;
@@ -1761,7 +1871,7 @@ out_free:
/* Free the leftover list */
list_for_each_entry_safe(rr, n, &debris, rr_list) {
list_del(&rr->rr_list);
- kmem_free(rr);
+ kfree(rr);
}
return error;
}
@@ -1770,6 +1880,7 @@ out_free:
int
xfs_refcount_has_record(
struct xfs_btree_cur *cur,
+ enum xfs_refc_domain domain,
xfs_agblock_t bno,
xfs_extlen_t len,
bool *exists)
@@ -1781,6 +1892,7 @@ xfs_refcount_has_record(
low.rc.rc_startblock = bno;
memset(&high, 0xFF, sizeof(high));
high.rc.rc_startblock = bno + len - 1;
+ low.rc.rc_domain = high.rc.rc_domain = domain;
return xfs_btree_has_record(cur, &low, &high, exists);
}
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index e8b322de7f3d..452f30556f5a 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -14,14 +14,33 @@ struct xfs_bmbt_irec;
struct xfs_refcount_irec;
extern int xfs_refcount_lookup_le(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_lookup_ge(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_lookup_eq(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, int *stat);
+ enum xfs_refc_domain domain, xfs_agblock_t bno, int *stat);
extern int xfs_refcount_get_rec(struct xfs_btree_cur *cur,
struct xfs_refcount_irec *irec, int *stat);
+static inline uint32_t
+xfs_refcount_encode_startblock(
+ xfs_agblock_t startblock,
+ enum xfs_refc_domain domain)
+{
+ uint32_t start;
+
+ /*
+ * low level btree operations need to handle the generic btree range
+ * query functions (which set rc_domain == -1U), so we check that the
+ * domain is /not/ shared.
+ */
+ start = startblock & ~XFS_REFC_COWFLAG;
+ if (domain != XFS_REFC_DOMAIN_SHARED)
+ start |= XFS_REFC_COWFLAG;
+
+ return start;
+}
+
enum xfs_refcount_intent_type {
XFS_REFCOUNT_INCREASE = 1,
XFS_REFCOUNT_DECREASE,
@@ -36,6 +55,18 @@ struct xfs_refcount_intent {
xfs_fsblock_t ri_startblock;
};
+/* Check that the refcount is appropriate for the record domain. */
+static inline bool
+xfs_refcount_check_domain(
+ const struct xfs_refcount_irec *irec)
+{
+ if (irec->rc_domain == XFS_REFC_DOMAIN_COW && irec->rc_refcount != 1)
+ return false;
+ if (irec->rc_domain == XFS_REFC_DOMAIN_SHARED && irec->rc_refcount < 2)
+ return false;
+ return true;
+}
+
void xfs_refcount_increase_extent(struct xfs_trans *tp,
struct xfs_bmbt_irec *irec);
void xfs_refcount_decrease_extent(struct xfs_trans *tp,
@@ -79,7 +110,8 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
#define XFS_REFCOUNT_ITEM_OVERHEAD 32
extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
- xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
+ enum xfs_refc_domain domain, xfs_agblock_t bno,
+ xfs_extlen_t len, bool *exists);
union xfs_btree_rec;
extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
struct xfs_refcount_irec *irec);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 316c1ec0c3c2..e1f789866683 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -13,6 +13,7 @@
#include "xfs_btree.h"
#include "xfs_btree_staging.h"
#include "xfs_refcount_btree.h"
+#include "xfs_refcount.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
@@ -160,7 +161,12 @@ xfs_refcountbt_init_rec_from_cur(
struct xfs_btree_cur *cur,
union xfs_btree_rec *rec)
{
- rec->refc.rc_startblock = cpu_to_be32(cur->bc_rec.rc.rc_startblock);
+ const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+ uint32_t start;
+
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ rec->refc.rc_startblock = cpu_to_be32(start);
rec->refc.rc_blockcount = cpu_to_be32(cur->bc_rec.rc.rc_blockcount);
rec->refc.rc_refcount = cpu_to_be32(cur->bc_rec.rc.rc_refcount);
}
@@ -182,10 +188,13 @@ xfs_refcountbt_key_diff(
struct xfs_btree_cur *cur,
const union xfs_btree_key *key)
{
- struct xfs_refcount_irec *rec = &cur->bc_rec.rc;
const struct xfs_refcount_key *kp = &key->refc;
+ const struct xfs_refcount_irec *irec = &cur->bc_rec.rc;
+ uint32_t start;
- return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+ start = xfs_refcount_encode_startblock(irec->rc_startblock,
+ irec->rc_domain);
+ return (int64_t)be32_to_cpu(kp->rc_startblock) - start;
}
STATIC int64_t
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 094dfc897ebc..b56aca1e7c66 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -235,13 +235,8 @@ xfs_rmap_get_rec(
goto out_bad_rec;
} else {
/* check for valid extent range, including overflow */
- if (!xfs_verify_agbno(pag, irec->rm_startblock))
- goto out_bad_rec;
- if (irec->rm_startblock >
- irec->rm_startblock + irec->rm_blockcount)
- goto out_bad_rec;
- if (!xfs_verify_agbno(pag,
- irec->rm_startblock + irec->rm_blockcount - 1))
+ if (!xfs_verify_agbext(pag, irec->rm_startblock,
+ irec->rm_blockcount))
goto out_bad_rec;
}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 2c4ad6e4bb14..5b2f27cbdb80 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -422,7 +422,7 @@ xfs_calc_itruncate_reservation_minlogsize(
/*
* In renaming a files we can modify:
- * the four inodes involved: 4 * inode size
+ * the five inodes involved: 5 * inode size
* the two directory btrees: 2 * (max depth + v2) * dir block size
* the two directory bmap btrees: 2 * max depth * block size
* And the bmap_finish transaction can free dir and bmap blocks (two sets
@@ -437,7 +437,7 @@ xfs_calc_rename_reservation(
struct xfs_mount *mp)
{
return XFS_DQUOT_LOGRES(mp) +
- max((xfs_calc_inode_res(mp, 4) +
+ max((xfs_calc_inode_res(mp, 5) +
xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
XFS_FSB_TO_B(mp, 1))),
(xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index a6b7d98cf68f..5ebdda7e1078 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -166,6 +166,36 @@ typedef struct xfs_bmbt_irec
xfs_exntst_t br_state; /* extent state */
} xfs_bmbt_irec_t;
+enum xfs_refc_domain {
+ XFS_REFC_DOMAIN_SHARED = 0,
+ XFS_REFC_DOMAIN_COW,
+};
+
+#define XFS_REFC_DOMAIN_STRINGS \
+ { XFS_REFC_DOMAIN_SHARED, "shared" }, \
+ { XFS_REFC_DOMAIN_COW, "cow" }
+
+struct xfs_refcount_irec {
+ xfs_agblock_t rc_startblock; /* starting block number */
+ xfs_extlen_t rc_blockcount; /* count of free blocks */
+ xfs_nlink_t rc_refcount; /* number of inodes linked here */
+ enum xfs_refc_domain rc_domain; /* shared or cow staging extent? */
+};
+
+#define XFS_RMAP_ATTR_FORK (1 << 0)
+#define XFS_RMAP_BMBT_BLOCK (1 << 1)
+#define XFS_RMAP_UNWRITTEN (1 << 2)
+#define XFS_RMAP_KEY_FLAGS (XFS_RMAP_ATTR_FORK | \
+ XFS_RMAP_BMBT_BLOCK)
+#define XFS_RMAP_REC_FLAGS (XFS_RMAP_UNWRITTEN)
+struct xfs_rmap_irec {
+ xfs_agblock_t rm_startblock; /* extent start block */
+ xfs_extlen_t rm_blockcount; /* extent length */
+ uint64_t rm_owner; /* extent owner */
+ uint64_t rm_offset; /* offset within the owner */
+ unsigned int rm_flags; /* state flags */
+};
+
/* per-AG block reservation types */
enum xfs_ag_resv_type {
XFS_AG_RESV_NONE = 0,
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index ab427b4d7fe0..3b38f4e2a537 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -100,9 +100,7 @@ xchk_allocbt_rec(
bno = be32_to_cpu(rec->alloc.ar_startblock);
len = be32_to_cpu(rec->alloc.ar_blockcount);
- if (bno + len <= bno ||
- !xfs_verify_agbno(pag, bno) ||
- !xfs_verify_agbno(pag, bno + len - 1))
+ if (!xfs_verify_agbext(pag, bno, len))
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
xchk_allocbt_xref(bs->sc, bno, len);
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index e1026e07bf94..e312be7cd375 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -108,9 +108,8 @@ xchk_iallocbt_chunk(
xfs_agblock_t bno;
bno = XFS_AGINO_TO_AGBNO(mp, agino);
- if (bno + len <= bno ||
- !xfs_verify_agbno(pag, bno) ||
- !xfs_verify_agbno(pag, bno + len - 1))
+
+ if (!xfs_verify_agbext(pag, bno, len))
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index c68b767dc08f..a26ee0f24ef2 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -269,15 +269,13 @@ done:
STATIC void
xchk_refcountbt_xref_rmap(
struct xfs_scrub *sc,
- xfs_agblock_t bno,
- xfs_extlen_t len,
- xfs_nlink_t refcount)
+ const struct xfs_refcount_irec *irec)
{
struct xchk_refcnt_check refchk = {
- .sc = sc,
- .bno = bno,
- .len = len,
- .refcount = refcount,
+ .sc = sc,
+ .bno = irec->rc_startblock,
+ .len = irec->rc_blockcount,
+ .refcount = irec->rc_refcount,
.seen = 0,
};
struct xfs_rmap_irec low;
@@ -291,9 +289,9 @@ xchk_refcountbt_xref_rmap(
/* Cross-reference with the rmapbt to confirm the refcount. */
memset(&low, 0, sizeof(low));
- low.rm_startblock = bno;
+ low.rm_startblock = irec->rc_startblock;
memset(&high, 0xFF, sizeof(high));
- high.rm_startblock = bno + len - 1;
+ high.rm_startblock = irec->rc_startblock + irec->rc_blockcount - 1;
INIT_LIST_HEAD(&refchk.fragments);
error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
@@ -302,7 +300,7 @@ xchk_refcountbt_xref_rmap(
goto out_free;
xchk_refcountbt_process_rmap_fragments(&refchk);
- if (refcount != refchk.seen)
+ if (irec->rc_refcount != refchk.seen)
xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
out_free:
@@ -315,17 +313,16 @@ out_free:
/* Cross-reference with the other btrees. */
STATIC void
xchk_refcountbt_xref(
- struct xfs_scrub *sc,
- xfs_agblock_t agbno,
- xfs_extlen_t len,
- xfs_nlink_t refcount)
+ struct xfs_scrub *sc,
+ const struct xfs_refcount_irec *irec)
{
if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
return;
- xchk_xref_is_used_space(sc, agbno, len);
- xchk_xref_is_not_inode_chunk(sc, agbno, len);
- xchk_refcountbt_xref_rmap(sc, agbno, len, refcount);
+ xchk_xref_is_used_space(sc, irec->rc_startblock, irec->rc_blockcount);
+ xchk_xref_is_not_inode_chunk(sc, irec->rc_startblock,
+ irec->rc_blockcount);
+ xchk_refcountbt_xref_rmap(sc, irec);
}
/* Scrub a refcountbt record. */
@@ -334,35 +331,27 @@ xchk_refcountbt_rec(
struct xchk_btree *bs,
const union xfs_btree_rec *rec)
{
+ struct xfs_refcount_irec irec;
xfs_agblock_t *cow_blocks = bs->private;
struct xfs_perag *pag = bs->cur->bc_ag.pag;
- xfs_agblock_t bno;
- xfs_extlen_t len;
- xfs_nlink_t refcount;
- bool has_cowflag;
- bno = be32_to_cpu(rec->refc.rc_startblock);
- len = be32_to_cpu(rec->refc.rc_blockcount);
- refcount = be32_to_cpu(rec->refc.rc_refcount);
+ xfs_refcount_btrec_to_irec(rec, &irec);
- /* Only CoW records can have refcount == 1. */
- has_cowflag = (bno & XFS_REFC_COW_START);
- if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
+ /* Check the domain and refcount are not incompatible. */
+ if (!xfs_refcount_check_domain(&irec))
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
- if (has_cowflag)
- (*cow_blocks) += len;
+
+ if (irec.rc_domain == XFS_REFC_DOMAIN_COW)
+ (*cow_blocks) += irec.rc_blockcount;
/* Check the extent. */
- bno &= ~XFS_REFC_COW_START;
- if (bno + len <= bno ||
- !xfs_verify_agbno(pag, bno) ||
- !xfs_verify_agbno(pag, bno + len - 1))
+ if (!xfs_verify_agbext(pag, irec.rc_startblock, irec.rc_blockcount))
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
- if (refcount == 0)
+ if (irec.rc_refcount == 0)
xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
- xchk_refcountbt_xref(bs->sc, bno, len, refcount);
+ xchk_refcountbt_xref(bs->sc, &irec);
return 0;
}
@@ -426,7 +415,6 @@ xchk_xref_is_cow_staging(
xfs_extlen_t len)
{
struct xfs_refcount_irec rc;
- bool has_cowflag;
int has_refcount;
int error;
@@ -434,8 +422,8 @@ xchk_xref_is_cow_staging(
return;
/* Find the CoW staging extent. */
- error = xfs_refcount_lookup_le(sc->sa.refc_cur,
- agbno + XFS_REFC_COW_START, &has_refcount);
+ error = xfs_refcount_lookup_le(sc->sa.refc_cur, XFS_REFC_DOMAIN_COW,
+ agbno, &has_refcount);
if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
return;
if (!has_refcount) {
@@ -451,9 +439,8 @@ xchk_xref_is_cow_staging(
return;
}
- /* CoW flag must be set, refcount must be 1. */
- has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
- if (!has_cowflag || rc.rc_refcount != 1)
+ /* CoW lookup returned a shared extent record? */
+ if (rc.rc_domain != XFS_REFC_DOMAIN_COW)
xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
/* Must be at least as long as what was passed in */
@@ -477,7 +464,8 @@ xchk_xref_is_not_shared(
if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
return;
- error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
+ error = xfs_refcount_has_record(sc->sa.refc_cur, XFS_REFC_DOMAIN_SHARED,
+ agbno, len, &shared);
if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
return;
if (shared)
diff --git a/fs/xfs/xfs_attr_item.c b/fs/xfs/xfs_attr_item.c
index cf5ce607dc05..2788a6f2edcd 100644
--- a/fs/xfs/xfs_attr_item.c
+++ b/fs/xfs/xfs_attr_item.c
@@ -245,28 +245,6 @@ xfs_attri_init(
return attrip;
}
-/*
- * Copy an attr format buffer from the given buf, and into the destination attr
- * format structure.
- */
-STATIC int
-xfs_attri_copy_format(
- struct xfs_log_iovec *buf,
- struct xfs_attri_log_format *dst_attr_fmt)
-{
- struct xfs_attri_log_format *src_attr_fmt = buf->i_addr;
- size_t len;
-
- len = sizeof(struct xfs_attri_log_format);
- if (buf->i_len != len) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
- return -EFSCORRUPTED;
- }
-
- memcpy((char *)dst_attr_fmt, (char *)src_attr_fmt, len);
- return 0;
-}
-
static inline struct xfs_attrd_log_item *ATTRD_ITEM(struct xfs_log_item *lip)
{
return container_of(lip, struct xfs_attrd_log_item, attrd_item);
@@ -731,24 +709,50 @@ xlog_recover_attri_commit_pass2(
struct xfs_attri_log_nameval *nv;
const void *attr_value = NULL;
const void *attr_name;
- int error;
+ size_t len;
attri_formatp = item->ri_buf[0].i_addr;
attr_name = item->ri_buf[1].i_addr;
/* Validate xfs_attri_log_format before the large memory allocation */
+ len = sizeof(struct xfs_attri_log_format);
+ if (item->ri_buf[0].i_len != len) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
if (!xfs_attri_validate(mp, attri_formatp)) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
+ /* Validate the attr name */
+ if (item->ri_buf[1].i_len !=
+ xlog_calc_iovec_len(attri_formatp->alfi_name_len)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
if (!xfs_attr_namecheck(attr_name, attri_formatp->alfi_name_len)) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[1].i_addr, item->ri_buf[1].i_len);
return -EFSCORRUPTED;
}
- if (attri_formatp->alfi_value_len)
+ /* Validate the attr value, if present */
+ if (attri_formatp->alfi_value_len != 0) {
+ if (item->ri_buf[2].i_len != xlog_calc_iovec_len(attri_formatp->alfi_value_len)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr,
+ item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
attr_value = item->ri_buf[2].i_addr;
+ }
/*
* Memory alloc failure will cause replay to abort. We attach the
@@ -760,9 +764,7 @@ xlog_recover_attri_commit_pass2(
attri_formatp->alfi_value_len);
attrip = xfs_attri_init(mp, nv);
- error = xfs_attri_copy_format(&item->ri_buf[0], &attrip->attri_format);
- if (error)
- goto out;
+ memcpy(&attrip->attri_format, attri_formatp, len);
/*
* The ATTRI has two references. One for the ATTRD and one for ATTRI to
@@ -774,10 +776,6 @@ xlog_recover_attri_commit_pass2(
xfs_attri_release(attrip);
xfs_attri_log_nameval_put(nv);
return 0;
-out:
- xfs_attri_item_free(attrip);
- xfs_attri_log_nameval_put(nv);
- return error;
}
/*
@@ -842,7 +840,8 @@ xlog_recover_attrd_commit_pass2(
attrd_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len != sizeof(struct xfs_attrd_log_format)) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 51f66e982484..41323da523d1 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -608,28 +608,18 @@ static const struct xfs_item_ops xfs_bui_item_ops = {
.iop_relog = xfs_bui_item_relog,
};
-/*
- * Copy an BUI format buffer from the given buf, and into the destination
- * BUI format structure. The BUI/BUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
xfs_bui_copy_format(
- struct xfs_log_iovec *buf,
- struct xfs_bui_log_format *dst_bui_fmt)
+ struct xfs_bui_log_format *dst,
+ const struct xfs_bui_log_format *src)
{
- struct xfs_bui_log_format *src_bui_fmt;
- uint len;
+ unsigned int i;
- src_bui_fmt = buf->i_addr;
- len = xfs_bui_log_format_sizeof(src_bui_fmt->bui_nextents);
+ memcpy(dst, src, offsetof(struct xfs_bui_log_format, bui_extents));
- if (buf->i_len == len) {
- memcpy(dst_bui_fmt, src_bui_fmt, len);
- return 0;
- }
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
- return -EFSCORRUPTED;
+ for (i = 0; i < src->bui_nextents; i++)
+ memcpy(&dst->bui_extents[i], &src->bui_extents[i],
+ sizeof(struct xfs_map_extent));
}
/*
@@ -646,23 +636,34 @@ xlog_recover_bui_commit_pass2(
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
- int error;
struct xfs_mount *mp = log->l_mp;
struct xfs_bui_log_item *buip;
struct xfs_bui_log_format *bui_formatp;
+ size_t len;
bui_formatp = item->ri_buf[0].i_addr;
+ if (item->ri_buf[0].i_len < xfs_bui_log_format_sizeof(0)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
if (bui_formatp->bui_nextents != XFS_BUI_MAX_FAST_EXTENTS) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
- buip = xfs_bui_init(mp);
- error = xfs_bui_copy_format(&item->ri_buf[0], &buip->bui_format);
- if (error) {
- xfs_bui_item_free(buip);
- return error;
+
+ len = xfs_bui_log_format_sizeof(bui_formatp->bui_nextents);
+ if (item->ri_buf[0].i_len != len) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
}
+
+ buip = xfs_bui_init(mp);
+ xfs_bui_copy_format(&buip->bui_format, bui_formatp);
atomic_set(&buip->bui_next_extent, bui_formatp->bui_nextents);
/*
* Insert the intent into the AIL directly and drop one reference so
@@ -696,7 +697,8 @@ xlog_recover_bud_commit_pass2(
bud_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len != sizeof(struct xfs_bud_log_format)) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 7db588ed0be5..c6b2aabd6f18 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -234,13 +234,18 @@ int
xfs_errortag_init(
struct xfs_mount *mp)
{
+ int ret;
+
mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX,
KM_MAYFAIL);
if (!mp->m_errortag)
return -ENOMEM;
- return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
- &mp->m_kobj, "errortag");
+ ret = xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
+ &mp->m_kobj, "errortag");
+ if (ret)
+ kmem_free(mp->m_errortag);
+ return ret;
}
void
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 27ccfcd82f04..d5130d1fcfae 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -66,27 +66,16 @@ xfs_efi_release(
xfs_efi_item_free(efip);
}
-/*
- * This returns the number of iovecs needed to log the given efi item.
- * We only need 1 iovec for an efi item. It just logs the efi_log_format
- * structure.
- */
-static inline int
-xfs_efi_item_sizeof(
- struct xfs_efi_log_item *efip)
-{
- return sizeof(struct xfs_efi_log_format) +
- (efip->efi_format.efi_nextents - 1) * sizeof(xfs_extent_t);
-}
-
STATIC void
xfs_efi_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
+ struct xfs_efi_log_item *efip = EFI_ITEM(lip);
+
*nvecs += 1;
- *nbytes += xfs_efi_item_sizeof(EFI_ITEM(lip));
+ *nbytes += xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents);
}
/*
@@ -112,7 +101,7 @@ xfs_efi_item_format(
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFI_FORMAT,
&efip->efi_format,
- xfs_efi_item_sizeof(efip));
+ xfs_efi_log_format_sizeof(efip->efi_format.efi_nextents));
}
@@ -155,13 +144,11 @@ xfs_efi_init(
{
struct xfs_efi_log_item *efip;
- uint size;
ASSERT(nextents > 0);
if (nextents > XFS_EFI_MAX_FAST_EXTENTS) {
- size = (uint)(sizeof(struct xfs_efi_log_item) +
- ((nextents - 1) * sizeof(xfs_extent_t)));
- efip = kmem_zalloc(size, 0);
+ efip = kzalloc(xfs_efi_log_item_sizeof(nextents),
+ GFP_KERNEL | __GFP_NOFAIL);
} else {
efip = kmem_cache_zalloc(xfs_efi_cache,
GFP_KERNEL | __GFP_NOFAIL);
@@ -188,15 +175,17 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
{
xfs_efi_log_format_t *src_efi_fmt = buf->i_addr;
uint i;
- uint len = sizeof(xfs_efi_log_format_t) +
- (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_t);
- uint len32 = sizeof(xfs_efi_log_format_32_t) +
- (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_32_t);
- uint len64 = sizeof(xfs_efi_log_format_64_t) +
- (src_efi_fmt->efi_nextents - 1) * sizeof(xfs_extent_64_t);
+ uint len = xfs_efi_log_format_sizeof(src_efi_fmt->efi_nextents);
+ uint len32 = xfs_efi_log_format32_sizeof(src_efi_fmt->efi_nextents);
+ uint len64 = xfs_efi_log_format64_sizeof(src_efi_fmt->efi_nextents);
if (buf->i_len == len) {
- memcpy((char *)dst_efi_fmt, (char*)src_efi_fmt, len);
+ memcpy(dst_efi_fmt, src_efi_fmt,
+ offsetof(struct xfs_efi_log_format, efi_extents));
+ for (i = 0; i < src_efi_fmt->efi_nextents; i++)
+ memcpy(&dst_efi_fmt->efi_extents[i],
+ &src_efi_fmt->efi_extents[i],
+ sizeof(struct xfs_extent));
return 0;
} else if (buf->i_len == len32) {
xfs_efi_log_format_32_t *src_efi_fmt_32 = buf->i_addr;
@@ -227,7 +216,8 @@ xfs_efi_copy_format(xfs_log_iovec_t *buf, xfs_efi_log_format_t *dst_efi_fmt)
}
return 0;
}
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, NULL, buf->i_addr,
+ buf->i_len);
return -EFSCORRUPTED;
}
@@ -246,27 +236,16 @@ xfs_efd_item_free(struct xfs_efd_log_item *efdp)
kmem_cache_free(xfs_efd_cache, efdp);
}
-/*
- * This returns the number of iovecs needed to log the given efd item.
- * We only need 1 iovec for an efd item. It just logs the efd_log_format
- * structure.
- */
-static inline int
-xfs_efd_item_sizeof(
- struct xfs_efd_log_item *efdp)
-{
- return sizeof(xfs_efd_log_format_t) +
- (efdp->efd_format.efd_nextents - 1) * sizeof(xfs_extent_t);
-}
-
STATIC void
xfs_efd_item_size(
struct xfs_log_item *lip,
int *nvecs,
int *nbytes)
{
+ struct xfs_efd_log_item *efdp = EFD_ITEM(lip);
+
*nvecs += 1;
- *nbytes += xfs_efd_item_sizeof(EFD_ITEM(lip));
+ *nbytes += xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents);
}
/*
@@ -291,7 +270,7 @@ xfs_efd_item_format(
xlog_copy_iovec(lv, &vecp, XLOG_REG_TYPE_EFD_FORMAT,
&efdp->efd_format,
- xfs_efd_item_sizeof(efdp));
+ xfs_efd_log_format_sizeof(efdp->efd_format.efd_nextents));
}
/*
@@ -340,9 +319,8 @@ xfs_trans_get_efd(
ASSERT(nextents > 0);
if (nextents > XFS_EFD_MAX_FAST_EXTENTS) {
- efdp = kmem_zalloc(sizeof(struct xfs_efd_log_item) +
- (nextents - 1) * sizeof(struct xfs_extent),
- 0);
+ efdp = kzalloc(xfs_efd_log_item_sizeof(nextents),
+ GFP_KERNEL | __GFP_NOFAIL);
} else {
efdp = kmem_cache_zalloc(xfs_efd_cache,
GFP_KERNEL | __GFP_NOFAIL);
@@ -733,6 +711,12 @@ xlog_recover_efi_commit_pass2(
efi_formatp = item->ri_buf[0].i_addr;
+ if (item->ri_buf[0].i_len < xfs_efi_log_format_sizeof(0)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
efip = xfs_efi_init(mp, efi_formatp->efi_nextents);
error = xfs_efi_copy_format(&item->ri_buf[0], &efip->efi_format);
if (error) {
@@ -769,12 +753,24 @@ xlog_recover_efd_commit_pass2(
xfs_lsn_t lsn)
{
struct xfs_efd_log_format *efd_formatp;
+ int buflen = item->ri_buf[0].i_len;
efd_formatp = item->ri_buf[0].i_addr;
- ASSERT((item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_32_t) +
- ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_32_t)))) ||
- (item->ri_buf[0].i_len == (sizeof(xfs_efd_log_format_64_t) +
- ((efd_formatp->efd_nextents - 1) * sizeof(xfs_extent_64_t)))));
+
+ if (buflen < sizeof(struct xfs_efd_log_format)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ efd_formatp, buflen);
+ return -EFSCORRUPTED;
+ }
+
+ if (item->ri_buf[0].i_len != xfs_efd_log_format32_sizeof(
+ efd_formatp->efd_nextents) &&
+ item->ri_buf[0].i_len != xfs_efd_log_format64_sizeof(
+ efd_formatp->efd_nextents)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ efd_formatp, buflen);
+ return -EFSCORRUPTED;
+ }
xlog_recover_release_intent(log, XFS_LI_EFI, efd_formatp->efd_efi_id);
return 0;
diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h
index 186d0f2137f1..da6a5afa607c 100644
--- a/fs/xfs/xfs_extfree_item.h
+++ b/fs/xfs/xfs_extfree_item.h
@@ -52,6 +52,14 @@ struct xfs_efi_log_item {
xfs_efi_log_format_t efi_format;
};
+static inline size_t
+xfs_efi_log_item_sizeof(
+ unsigned int nr)
+{
+ return offsetof(struct xfs_efi_log_item, efi_format) +
+ xfs_efi_log_format_sizeof(nr);
+}
+
/*
* This is the "extent free done" log item. It is used to log
* the fact that some extents earlier mentioned in an efi item
@@ -64,6 +72,14 @@ struct xfs_efd_log_item {
xfs_efd_log_format_t efd_format;
};
+static inline size_t
+xfs_efd_log_item_sizeof(
+ unsigned int nr)
+{
+ return offsetof(struct xfs_efd_log_item, efd_format) +
+ xfs_efd_log_format_sizeof(nr);
+}
+
/*
* Max number of extents in fast allocation path.
*/
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index c6c80265c0b2..e462d39c840e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1261,7 +1261,7 @@ xfs_file_llseek(
}
#ifdef CONFIG_FS_DAX
-static int
+static inline vm_fault_t
xfs_dax_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size,
@@ -1274,14 +1274,15 @@ xfs_dax_fault(
&xfs_read_iomap_ops);
}
#else
-static int
+static inline vm_fault_t
xfs_dax_fault(
struct vm_fault *vmf,
enum page_entry_size pe_size,
bool write_fault,
pfn_t *pfn)
{
- return 0;
+ ASSERT(0);
+ return VM_FAULT_SIGBUS;
}
#endif
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c000b74dd203..aa303be11576 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2818,7 +2818,7 @@ retry:
* Lock all the participating inodes. Depending upon whether
* the target_name exists in the target directory, and
* whether the target directory is the same as the source
- * directory, we can lock from 2 to 4 inodes.
+ * directory, we can lock from 2 to 5 inodes.
*/
xfs_lock_inodes(inodes, num_inodes, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 17e923b9c5fa..322eb2ee6c55 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2552,6 +2552,8 @@ xlog_recover_process_intents(
for (lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
lip != NULL;
lip = xfs_trans_ail_cursor_next(ailp, &cur)) {
+ const struct xfs_item_ops *ops;
+
if (!xlog_item_is_intent(lip))
break;
@@ -2567,13 +2569,17 @@ xlog_recover_process_intents(
* deferred ops, you /must/ attach them to the capture list in
* the recover routine or else those subsequent intents will be
* replayed in the wrong order!
+ *
+ * The recovery function can free the log item, so we must not
+ * access lip after it returns.
*/
spin_unlock(&ailp->ail_lock);
- error = lip->li_ops->iop_recover(lip, &capture_list);
+ ops = lip->li_ops;
+ error = ops->iop_recover(lip, &capture_list);
spin_lock(&ailp->ail_lock);
if (error) {
trace_xlog_intent_recovery_failed(log->l_mp, error,
- lip->li_ops->iop_recover);
+ ops->iop_recover);
break;
}
}
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 758702b9495f..9737b5a9f405 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -118,10 +118,10 @@ xfs_check_ondisk_structs(void)
/* log structures */
XFS_CHECK_STRUCT_SIZE(struct xfs_buf_log_format, 88);
XFS_CHECK_STRUCT_SIZE(struct xfs_dq_logformat, 24);
- XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 28);
- XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 32);
- XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 28);
- XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 32);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_32, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_efd_log_format_64, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_32, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_efi_log_format_64, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_extent_32, 12);
XFS_CHECK_STRUCT_SIZE(struct xfs_extent_64, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_log_dinode, 176);
@@ -134,6 +134,21 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16);
XFS_CHECK_STRUCT_SIZE(struct xfs_attri_log_format, 40);
XFS_CHECK_STRUCT_SIZE(struct xfs_attrd_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_bui_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_bud_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_cui_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_cud_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_rui_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_rud_log_format, 16);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_map_extent, 32);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_phys_extent, 16);
+
+ XFS_CHECK_OFFSET(struct xfs_bui_log_format, bui_extents, 16);
+ XFS_CHECK_OFFSET(struct xfs_cui_log_format, cui_extents, 16);
+ XFS_CHECK_OFFSET(struct xfs_rui_log_format, rui_extents, 16);
+ XFS_CHECK_OFFSET(struct xfs_efi_log_format, efi_extents, 16);
+ XFS_CHECK_OFFSET(struct xfs_efi_log_format_32, efi_extents, 16);
+ XFS_CHECK_OFFSET(struct xfs_efi_log_format_64, efi_extents, 16);
/*
* The v5 superblock format extended several v4 header structures with
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 7e97bf19793d..858e3e9eb4a8 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -523,7 +523,9 @@ xfs_cui_item_recover(
type = refc_type;
break;
default:
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &cuip->cui_format,
+ sizeof(cuip->cui_format));
error = -EFSCORRUPTED;
goto abort_error;
}
@@ -536,7 +538,8 @@ xfs_cui_item_recover(
&new_fsb, &new_len, &rcur);
if (error == -EFSCORRUPTED)
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
- refc, sizeof(*refc));
+ &cuip->cui_format,
+ sizeof(cuip->cui_format));
if (error)
goto abort_error;
@@ -622,28 +625,18 @@ static const struct xfs_item_ops xfs_cui_item_ops = {
.iop_relog = xfs_cui_item_relog,
};
-/*
- * Copy an CUI format buffer from the given buf, and into the destination
- * CUI format structure. The CUI/CUD items were designed not to need any
- * special alignment handling.
- */
-static int
+static inline void
xfs_cui_copy_format(
- struct xfs_log_iovec *buf,
- struct xfs_cui_log_format *dst_cui_fmt)
+ struct xfs_cui_log_format *dst,
+ const struct xfs_cui_log_format *src)
{
- struct xfs_cui_log_format *src_cui_fmt;
- uint len;
+ unsigned int i;
- src_cui_fmt = buf->i_addr;
- len = xfs_cui_log_format_sizeof(src_cui_fmt->cui_nextents);
+ memcpy(dst, src, offsetof(struct xfs_cui_log_format, cui_extents));
- if (buf->i_len == len) {
- memcpy(dst_cui_fmt, src_cui_fmt, len);
- return 0;
- }
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
- return -EFSCORRUPTED;
+ for (i = 0; i < src->cui_nextents; i++)
+ memcpy(&dst->cui_extents[i], &src->cui_extents[i],
+ sizeof(struct xfs_phys_extent));
}
/*
@@ -660,19 +653,28 @@ xlog_recover_cui_commit_pass2(
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
- int error;
struct xfs_mount *mp = log->l_mp;
struct xfs_cui_log_item *cuip;
struct xfs_cui_log_format *cui_formatp;
+ size_t len;
cui_formatp = item->ri_buf[0].i_addr;
- cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
- error = xfs_cui_copy_format(&item->ri_buf[0], &cuip->cui_format);
- if (error) {
- xfs_cui_item_free(cuip);
- return error;
+ if (item->ri_buf[0].i_len < xfs_cui_log_format_sizeof(0)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
}
+
+ len = xfs_cui_log_format_sizeof(cui_formatp->cui_nextents);
+ if (item->ri_buf[0].i_len != len) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
+ cuip = xfs_cui_init(mp, cui_formatp->cui_nextents);
+ xfs_cui_copy_format(&cuip->cui_format, cui_formatp);
atomic_set(&cuip->cui_next_extent, cui_formatp->cui_nextents);
/*
* Insert the intent into the AIL directly and drop one reference so
@@ -706,7 +708,8 @@ xlog_recover_cud_commit_pass2(
cud_formatp = item->ri_buf[0].i_addr;
if (item->ri_buf[0].i_len != sizeof(struct xfs_cud_log_format)) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, log->l_mp);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
return -EFSCORRUPTED;
}
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index fef92e02f3bb..534504ede1a3 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -155,31 +155,6 @@ xfs_rui_init(
return ruip;
}
-/*
- * Copy an RUI format buffer from the given buf, and into the destination
- * RUI format structure. The RUI/RUD items were designed not to need any
- * special alignment handling.
- */
-STATIC int
-xfs_rui_copy_format(
- struct xfs_log_iovec *buf,
- struct xfs_rui_log_format *dst_rui_fmt)
-{
- struct xfs_rui_log_format *src_rui_fmt;
- uint len;
-
- src_rui_fmt = buf->i_addr;
- len = xfs_rui_log_format_sizeof(src_rui_fmt->rui_nextents);
-
- if (buf->i_len != len) {
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
- return -EFSCORRUPTED;
- }
-
- memcpy(dst_rui_fmt, src_rui_fmt, len);
- return 0;
-}
-
static inline struct xfs_rud_log_item *RUD_ITEM(struct xfs_log_item *lip)
{
return container_of(lip, struct xfs_rud_log_item, rud_item);
@@ -582,7 +557,9 @@ xfs_rui_item_recover(
type = XFS_RMAP_FREE;
break;
default:
- XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ &ruip->rui_format,
+ sizeof(ruip->rui_format));
error = -EFSCORRUPTED;
goto abort_error;
}
@@ -652,6 +629,20 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
.iop_relog = xfs_rui_item_relog,
};
+static inline void
+xfs_rui_copy_format(
+ struct xfs_rui_log_format *dst,
+ const struct xfs_rui_log_format *src)
+{
+ unsigned int i;
+
+ memcpy(dst, src, offsetof(struct xfs_rui_log_format, rui_extents));
+
+ for (i = 0; i < src->rui_nextents; i++)
+ memcpy(&dst->rui_extents[i], &src->rui_extents[i],
+ sizeof(struct xfs_map_extent));
+}
+
/*
* This routine is called to create an in-core extent rmap update
* item from the rui format structure which was logged on disk.
@@ -666,19 +657,28 @@ xlog_recover_rui_commit_pass2(
struct xlog_recover_item *item,
xfs_lsn_t lsn)
{
- int error;
struct xfs_mount *mp = log->l_mp;
struct xfs_rui_log_item *ruip;
struct xfs_rui_log_format *rui_formatp;
+ size_t len;
rui_formatp = item->ri_buf[0].i_addr;
- ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
- error = xfs_rui_copy_format(&item->ri_buf[0], &ruip->rui_format);
- if (error) {
- xfs_rui_item_free(ruip);
- return error;
+ if (item->ri_buf[0].i_len < xfs_rui_log_format_sizeof(0)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
+
+ len = xfs_rui_log_format_sizeof(rui_formatp->rui_nextents);
+ if (item->ri_buf[0].i_len != len) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ item->ri_buf[0].i_addr, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
}
+
+ ruip = xfs_rui_init(mp, rui_formatp->rui_nextents);
+ xfs_rui_copy_format(&ruip->rui_format, rui_formatp);
atomic_set(&ruip->rui_next_extent, rui_formatp->rui_nextents);
/*
* Insert the intent into the AIL directly and drop one reference so
@@ -711,7 +711,11 @@ xlog_recover_rud_commit_pass2(
struct xfs_rud_log_format *rud_formatp;
rud_formatp = item->ri_buf[0].i_addr;
- ASSERT(item->ri_buf[0].i_len == sizeof(struct xfs_rud_log_format));
+ if (item->ri_buf[0].i_len != sizeof(struct xfs_rud_log_format)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, log->l_mp,
+ rud_formatp, item->ri_buf[0].i_len);
+ return -EFSCORRUPTED;
+ }
xlog_recover_release_intent(log, XFS_LI_RUI, rud_formatp->rud_rui_id);
return 0;
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f029c6702dda..ee4b429a2f2c 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2028,18 +2028,14 @@ xfs_init_caches(void)
goto out_destroy_trans_cache;
xfs_efd_cache = kmem_cache_create("xfs_efd_item",
- (sizeof(struct xfs_efd_log_item) +
- (XFS_EFD_MAX_FAST_EXTENTS - 1) *
- sizeof(struct xfs_extent)),
- 0, 0, NULL);
+ xfs_efd_log_item_sizeof(XFS_EFD_MAX_FAST_EXTENTS),
+ 0, 0, NULL);
if (!xfs_efd_cache)
goto out_destroy_buf_item_cache;
xfs_efi_cache = kmem_cache_create("xfs_efi_item",
- (sizeof(struct xfs_efi_log_item) +
- (XFS_EFI_MAX_FAST_EXTENTS - 1) *
- sizeof(struct xfs_extent)),
- 0, 0, NULL);
+ xfs_efi_log_item_sizeof(XFS_EFI_MAX_FAST_EXTENTS),
+ 0, 0, NULL);
if (!xfs_efi_cache)
goto out_destroy_efd_cache;
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index 43585850f154..513095e353a5 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -33,10 +33,15 @@ xfs_sysfs_init(
const char *name)
{
struct kobject *parent;
+ int err;
parent = parent_kobj ? &parent_kobj->kobject : NULL;
init_completion(&kobj->complete);
- return kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name);
+ err = kobject_init_and_add(&kobj->kobject, ktype, parent, "%s", name);
+ if (err)
+ kobject_put(&kobj->kobject);
+
+ return err;
}
static inline void
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index cb7c81ba7fa3..372d871bccc5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -799,6 +799,9 @@ TRACE_DEFINE_ENUM(PE_SIZE_PTE);
TRACE_DEFINE_ENUM(PE_SIZE_PMD);
TRACE_DEFINE_ENUM(PE_SIZE_PUD);
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED);
+TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW);
+
TRACE_EVENT(xfs_filemap_fault,
TP_PROTO(struct xfs_inode *ip, enum page_entry_size pe_size,
bool write_fault),
@@ -2925,6 +2928,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, domain)
__field(xfs_agblock_t, startblock)
__field(xfs_extlen_t, blockcount)
__field(xfs_nlink_t, refcount)
@@ -2932,13 +2936,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
+ __entry->domain = irec->rc_domain;
__entry->startblock = irec->rc_startblock;
__entry->blockcount = irec->rc_blockcount;
__entry->refcount = irec->rc_refcount;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
__entry->startblock,
__entry->blockcount,
__entry->refcount)
@@ -2958,6 +2964,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, domain)
__field(xfs_agblock_t, startblock)
__field(xfs_extlen_t, blockcount)
__field(xfs_nlink_t, refcount)
@@ -2966,14 +2973,16 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
+ __entry->domain = irec->rc_domain;
__entry->startblock = irec->rc_startblock;
__entry->blockcount = irec->rc_blockcount;
__entry->refcount = irec->rc_refcount;
__entry->agbno = agbno;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
__entry->startblock,
__entry->blockcount,
__entry->refcount,
@@ -2994,9 +3003,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, i1_domain)
__field(xfs_agblock_t, i1_startblock)
__field(xfs_extlen_t, i1_blockcount)
__field(xfs_nlink_t, i1_refcount)
+ __field(enum xfs_refc_domain, i2_domain)
__field(xfs_agblock_t, i2_startblock)
__field(xfs_extlen_t, i2_blockcount)
__field(xfs_nlink_t, i2_refcount)
@@ -3004,20 +3015,24 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
+ __entry->i1_domain = i1->rc_domain;
__entry->i1_startblock = i1->rc_startblock;
__entry->i1_blockcount = i1->rc_blockcount;
__entry->i1_refcount = i1->rc_refcount;
+ __entry->i2_domain = i2->rc_domain;
__entry->i2_startblock = i2->rc_startblock;
__entry->i2_blockcount = i2->rc_blockcount;
__entry->i2_refcount = i2->rc_refcount;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
- "agbno 0x%x fsbcount 0x%x refcount %u",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+ "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i1_startblock,
__entry->i1_blockcount,
__entry->i1_refcount,
+ __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i2_startblock,
__entry->i2_blockcount,
__entry->i2_refcount)
@@ -3038,9 +3053,11 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, i1_domain)
__field(xfs_agblock_t, i1_startblock)
__field(xfs_extlen_t, i1_blockcount)
__field(xfs_nlink_t, i1_refcount)
+ __field(enum xfs_refc_domain, i2_domain)
__field(xfs_agblock_t, i2_startblock)
__field(xfs_extlen_t, i2_blockcount)
__field(xfs_nlink_t, i2_refcount)
@@ -3049,21 +3066,25 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
+ __entry->i1_domain = i1->rc_domain;
__entry->i1_startblock = i1->rc_startblock;
__entry->i1_blockcount = i1->rc_blockcount;
__entry->i1_refcount = i1->rc_refcount;
+ __entry->i2_domain = i2->rc_domain;
__entry->i2_startblock = i2->rc_startblock;
__entry->i2_blockcount = i2->rc_blockcount;
__entry->i2_refcount = i2->rc_refcount;
__entry->agbno = agbno;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
- "agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+ "dom %s agbno 0x%x fsbcount 0x%x refcount %u @ agbno 0x%x",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i1_startblock,
__entry->i1_blockcount,
__entry->i1_refcount,
+ __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i2_startblock,
__entry->i2_blockcount,
__entry->i2_refcount,
@@ -3086,12 +3107,15 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
TP_STRUCT__entry(
__field(dev_t, dev)
__field(xfs_agnumber_t, agno)
+ __field(enum xfs_refc_domain, i1_domain)
__field(xfs_agblock_t, i1_startblock)
__field(xfs_extlen_t, i1_blockcount)
__field(xfs_nlink_t, i1_refcount)
+ __field(enum xfs_refc_domain, i2_domain)
__field(xfs_agblock_t, i2_startblock)
__field(xfs_extlen_t, i2_blockcount)
__field(xfs_nlink_t, i2_refcount)
+ __field(enum xfs_refc_domain, i3_domain)
__field(xfs_agblock_t, i3_startblock)
__field(xfs_extlen_t, i3_blockcount)
__field(xfs_nlink_t, i3_refcount)
@@ -3099,27 +3123,33 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
__entry->agno = agno;
+ __entry->i1_domain = i1->rc_domain;
__entry->i1_startblock = i1->rc_startblock;
__entry->i1_blockcount = i1->rc_blockcount;
__entry->i1_refcount = i1->rc_refcount;
+ __entry->i2_domain = i2->rc_domain;
__entry->i2_startblock = i2->rc_startblock;
__entry->i2_blockcount = i2->rc_blockcount;
__entry->i2_refcount = i2->rc_refcount;
+ __entry->i3_domain = i3->rc_domain;
__entry->i3_startblock = i3->rc_startblock;
__entry->i3_blockcount = i3->rc_blockcount;
__entry->i3_refcount = i3->rc_refcount;
),
- TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u -- "
- "agbno 0x%x fsbcount 0x%x refcount %u -- "
- "agbno 0x%x fsbcount 0x%x refcount %u",
+ TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+ "dom %s agbno 0x%x fsbcount 0x%x refcount %u -- "
+ "dom %s agbno 0x%x fsbcount 0x%x refcount %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
__entry->agno,
+ __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i1_startblock,
__entry->i1_blockcount,
__entry->i1_refcount,
+ __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i2_startblock,
__entry->i2_blockcount,
__entry->i2_refcount,
+ __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS),
__entry->i3_startblock,
__entry->i3_blockcount,
__entry->i3_refcount)
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 16fbf2a1144c..f51df7d94ef7 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -730,11 +730,10 @@ void
xfs_ail_push_all_sync(
struct xfs_ail *ailp)
{
- struct xfs_log_item *lip;
DEFINE_WAIT(wait);
spin_lock(&ailp->ail_lock);
- while ((lip = xfs_ail_max(ailp)) != NULL) {
+ while (xfs_ail_max(ailp) != NULL) {
prepare_to_wait(&ailp->ail_empty, &wait, TASK_UNINTERRUPTIBLE);
wake_up_process(ailp->ail_task);
spin_unlock(&ailp->ail_lock);
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
index aeb257ad3d1a..8392caea398f 100644
--- a/include/asm-generic/compat.h
+++ b/include/asm-generic/compat.h
@@ -15,7 +15,7 @@
#endif
#ifndef compat_arg_u64
-#ifdef CONFIG_CPU_BIG_ENDIAN
+#ifndef CONFIG_CPU_BIG_ENDIAN
#define compat_arg_u64(name) u32 name##_lo, u32 name##_hi
#define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi
#else
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index fdce7a4cfc6f..020ca9bdbb79 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -399,6 +399,11 @@ struct hv_vpset {
u64 bank_contents[];
} __packed;
+/* The maximum number of sparse vCPU banks which can be encoded by 'struct hv_vpset' */
+#define HV_MAX_SPARSE_VCPU_BANKS (64)
+/* The number of vCPUs in one sparse bank */
+#define HV_VCPUS_PER_SPARSE_BANK (64)
+
/* HvCallSendSyntheticClusterIpi hypercall */
struct hv_send_ipi {
u32 vector;
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index bfb9eb9d7215..d55d2833a37b 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -211,9 +211,10 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
{
int cpu, vcpu, vcpu_bank, vcpu_offset, nr_bank = 1;
int this_cpu = smp_processor_id();
+ int max_vcpu_bank = hv_max_vp_index / HV_VCPUS_PER_SPARSE_BANK;
- /* valid_bank_mask can represent up to 64 banks */
- if (hv_max_vp_index / 64 >= 64)
+ /* vpset.valid_bank_mask can represent up to HV_MAX_SPARSE_VCPU_BANKS banks */
+ if (max_vcpu_bank >= HV_MAX_SPARSE_VCPU_BANKS)
return 0;
/*
@@ -221,7 +222,7 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
* structs are not cleared between calls, we risk flushing unneeded
* vCPUs otherwise.
*/
- for (vcpu_bank = 0; vcpu_bank <= hv_max_vp_index / 64; vcpu_bank++)
+ for (vcpu_bank = 0; vcpu_bank <= max_vcpu_bank; vcpu_bank++)
vpset->bank_contents[vcpu_bank] = 0;
/*
@@ -233,8 +234,8 @@ static inline int __cpumask_to_vpset(struct hv_vpset *vpset,
vcpu = hv_cpu_number_to_vp_number(cpu);
if (vcpu == VP_INVAL)
return -1;
- vcpu_bank = vcpu / 64;
- vcpu_offset = vcpu % 64;
+ vcpu_bank = vcpu / HV_VCPUS_PER_SPARSE_BANK;
+ vcpu_offset = vcpu % HV_VCPUS_PER_SPARSE_BANK;
__set_bit(vcpu_offset, (unsigned long *)
&vpset->bank_contents[vcpu_bank]);
if (vcpu_bank >= nr_bank)
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ba18e9bdb799..d6119c5d1069 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -853,7 +853,8 @@ static inline bool blk_mq_add_to_batch(struct request *req,
struct io_comp_batch *iob, int ioerror,
void (*complete)(struct io_comp_batch *))
{
- if (!iob || (req->rq_flags & RQF_ELV) || ioerror)
+ if (!iob || (req->rq_flags & RQF_ELV) || ioerror ||
+ (req->end_io && !blk_rq_is_passthrough(req)))
return false;
if (!iob->complete)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9e7d46d16032..0566705c1d4e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -27,6 +27,7 @@
#include <linux/bpfptr.h>
#include <linux/btf.h>
#include <linux/rcupdate_trace.h>
+#include <linux/init.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
@@ -970,6 +971,8 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
struct bpf_attach_target_info *tgt_info);
void bpf_trampoline_put(struct bpf_trampoline *tr);
int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
+int __init bpf_arch_init_dispatcher_early(void *ip);
+
#define BPF_DISPATCHER_INIT(_name) { \
.mutex = __MUTEX_INITIALIZER(_name.mutex), \
.func = &_name##_func, \
@@ -983,6 +986,13 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
}, \
}
+#define BPF_DISPATCHER_INIT_CALL(_name) \
+ static int __init _name##_init(void) \
+ { \
+ return bpf_arch_init_dispatcher_early(_name##_func); \
+ } \
+ early_initcall(_name##_init)
+
#ifdef CONFIG_X86_64
#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5)))
#else
@@ -1000,7 +1010,9 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
} \
EXPORT_SYMBOL(bpf_dispatcher_##name##_func); \
struct bpf_dispatcher bpf_dispatcher_##name = \
- BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
+ BPF_DISPATCHER_INIT(bpf_dispatcher_##name); \
+ BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name);
+
#define DECLARE_BPF_DISPATCHER(name) \
unsigned int bpf_dispatcher_##name##_func( \
const void *ctx, \
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index e3a0be2c90ad..3aa3640f8c18 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -77,4 +77,13 @@
#define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset) \
+ BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset), \
+ "Offset of " #field " in " #type " has changed.")
+
+
#endif /* _LINUX_BUILD_BUG_H */
diff --git a/include/linux/counter.h b/include/linux/counter.h
index c41fa602ed28..b63746637de2 100644
--- a/include/linux/counter.h
+++ b/include/linux/counter.h
@@ -542,11 +542,10 @@ struct counter_array {
#define DEFINE_COUNTER_ARRAY_CAPTURE(_name, _length) \
DEFINE_COUNTER_ARRAY_U64(_name, _length)
-#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _enums, _length) \
- DEFINE_COUNTER_AVAILABLE(_name##_available, _enums); \
+#define DEFINE_COUNTER_ARRAY_POLARITY(_name, _available, _length) \
struct counter_array _name = { \
.type = COUNTER_COMP_SIGNAL_POLARITY, \
- .avail = &(_name##_available), \
+ .avail = &(_available), \
.length = (_length), \
}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 80f3c1c7827d..929d559ad41d 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1222,7 +1222,7 @@ efi_status_t efi_random_get_seed(void);
arch_efi_call_virt_teardown(); \
})
-#define EFI_RANDOM_SEED_SIZE 64U
+#define EFI_RANDOM_SEED_SIZE 32U // BLAKE2S_HASH_SIZE
struct linux_efi_random_seed {
u32 size;
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 0aff76bcbb00..bcb8658f5b64 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -555,7 +555,7 @@ static inline struct apertures_struct *alloc_apertures(unsigned int max_num) {
#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) || \
defined(__hppa__) || defined(__sh__) || defined(__powerpc__) || \
- defined(__arm__) || defined(__aarch64__)
+ defined(__arm__) || defined(__aarch64__) || defined(__mips__)
#define fb_readb __raw_readb
#define fb_readw __raw_readw
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 4029fe368a4f..1067a8450826 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -43,11 +43,24 @@ extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
#else
-#define __underlying_memchr __builtin_memchr
-#define __underlying_memcmp __builtin_memcmp
+
+#if defined(__SANITIZE_MEMORY__)
+/*
+ * For KMSAN builds all memcpy/memset/memmove calls should be replaced by the
+ * corresponding __msan_XXX functions.
+ */
+#include <linux/kmsan_string.h>
+#define __underlying_memcpy __msan_memcpy
+#define __underlying_memmove __msan_memmove
+#define __underlying_memset __msan_memset
+#else
#define __underlying_memcpy __builtin_memcpy
#define __underlying_memmove __builtin_memmove
#define __underlying_memset __builtin_memset
+#endif
+
+#define __underlying_memchr __builtin_memchr
+#define __underlying_memcmp __builtin_memcmp
#define __underlying_strcat __builtin_strcat
#define __underlying_strcpy __builtin_strcpy
#define __underlying_strlen __builtin_strlen
@@ -441,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
#define __fortify_memcpy_chk(p, q, size, p_size, q_size, \
p_size_field, q_size_field, op) ({ \
- size_t __fortify_size = (size_t)(size); \
- WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size, \
- p_size_field, q_size_field, #op), \
+ const size_t __fortify_size = (size_t)(size); \
+ const size_t __p_size = (p_size); \
+ const size_t __q_size = (q_size); \
+ const size_t __p_size_field = (p_size_field); \
+ const size_t __q_size_field = (q_size_field); \
+ WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size, \
+ __q_size, __p_size_field, \
+ __q_size_field, #op), \
#op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \
__fortify_size, \
"field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \
- p_size_field); \
+ __p_size_field); \
__underlying_##op(p, q, __fortify_size); \
})
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index cad78b569c7e..4f5f8a651213 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -307,7 +307,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
}
/* keyring.c */
-void fscrypt_sb_delete(struct super_block *sb);
+void fscrypt_destroy_keyring(struct super_block *sb);
int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
int fscrypt_add_test_dummy_key(struct super_block *sb,
const struct fscrypt_dummy_policy *dummy_policy);
@@ -521,7 +521,7 @@ fscrypt_free_dummy_policy(struct fscrypt_dummy_policy *dummy_policy)
}
/* keyring.c */
-static inline void fscrypt_sb_delete(struct super_block *sb)
+static inline void fscrypt_destroy_keyring(struct super_block *sb)
{
}
diff --git a/include/linux/kmsan_string.h b/include/linux/kmsan_string.h
new file mode 100644
index 000000000000..7287da6f52ef
--- /dev/null
+++ b/include/linux/kmsan_string.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * KMSAN string functions API used in other headers.
+ *
+ * Copyright (C) 2022 Google LLC
+ * Author: Alexander Potapenko <glider@google.com>
+ *
+ */
+#ifndef _LINUX_KMSAN_STRING_H
+#define _LINUX_KMSAN_STRING_H
+
+/*
+ * KMSAN overrides the default memcpy/memset/memmove implementations in the
+ * kernel, which requires having __msan_XXX function prototypes in several other
+ * headers. Keep them in one place instead of open-coding.
+ */
+void *__msan_memcpy(void *dst, const void *src, size_t size);
+void *__msan_memset(void *s, int c, size_t n);
+void *__msan_memmove(void *dest, const void *src, size_t len);
+
+#endif /* _LINUX_KMSAN_STRING_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 00c3448ba7f8..b8d12356f015 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -96,6 +96,7 @@
#define KVM_PFN_ERR_FAULT (KVM_PFN_ERR_MASK)
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
+#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3)
/*
* error pfns indicate that the gfn is in slot but faild to
@@ -107,6 +108,15 @@ static inline bool is_error_pfn(kvm_pfn_t pfn)
}
/*
+ * KVM_PFN_ERR_SIGPENDING indicates that fetching the PFN was interrupted
+ * by a pending signal. Note, the signal may or may not be fatal.
+ */
+static inline bool is_sigpending_pfn(kvm_pfn_t pfn)
+{
+ return pfn == KVM_PFN_ERR_SIGPENDING;
+}
+
+/*
* error_noslot pfns indicate that the gfn can not be
* translated to pfn - it is not in slot or failed to
* translate it to pfn.
@@ -655,6 +665,8 @@ struct kvm_irq_routing_table {
};
#endif
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
+
#ifndef KVM_INTERNAL_MEM_SLOTS
#define KVM_INTERNAL_MEM_SLOTS 0
#endif
@@ -710,6 +722,11 @@ struct kvm {
/* The current active memslot set for each address space */
struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
struct xarray vcpu_array;
+ /*
+ * Protected by slots_lock, but can be read outside if an
+ * incorrect answer is acceptable.
+ */
+ atomic_t nr_memslots_dirty_logging;
/* Used to wait for completion of MMU notifiers. */
spinlock_t mn_invalidate_lock;
@@ -1140,8 +1157,8 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool *async, bool write_fault,
- bool *writable, hva_t *hva);
+ bool atomic, bool interruptible, bool *async,
+ bool write_fault, bool *writable, hva_t *hva);
void kvm_release_pfn_clean(kvm_pfn_t pfn);
void kvm_release_pfn_dirty(kvm_pfn_t pfn);
@@ -1240,8 +1257,18 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
/**
- * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a
- * given guest physical address.
+ * kvm_gpc_init - initialize gfn_to_pfn_cache.
+ *
+ * @gpc: struct gfn_to_pfn_cache object.
+ *
+ * This sets up a gfn_to_pfn_cache by initializing locks. Note, the cache must
+ * be zero-allocated (or zeroed by the caller before init).
+ */
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc);
+
+/**
+ * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
+ * physical address.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
@@ -1265,9 +1292,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
* kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
* accessing the target page.
*/
-int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
- struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
- gpa_t gpa, unsigned long len);
+int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+ gpa_t gpa, unsigned long len);
/**
* kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
@@ -1324,7 +1351,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
/**
- * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache.
+ * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache.
*
* @kvm: pointer to kvm instance.
* @gpc: struct gfn_to_pfn_cache object.
@@ -1332,7 +1359,7 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
* This removes a cache from the @kvm's list to be processed on MMU notifier
* invocation.
*/
-void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
+void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
void kvm_sigset_activate(struct kvm_vcpu *vcpu);
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a12929bc31b2..af2ceb4160bc 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -970,7 +970,7 @@ void mlx5_cmd_allowed_opcode(struct mlx5_core_dev *dev, u16 opcode);
struct mlx5_async_ctx {
struct mlx5_core_dev *dev;
atomic_t num_inflight;
- struct wait_queue_head wait;
+ struct completion inflight_done;
};
struct mlx5_async_work;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8bbcccbc5565..3c84f4e48cd7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2958,6 +2958,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */
#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */
#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */
+#define FOLL_INTERRUPTIBLE 0x100000 /* allow interrupts from generic signals */
/*
* FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 19dfdd74835e..1d3be1a2204c 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -51,8 +51,8 @@ static inline bool __must_check __must_check_overflow(bool overflow)
return unlikely(overflow);
}
-/** check_add_overflow() - Calculate addition with overflow checking
- *
+/**
+ * check_add_overflow() - Calculate addition with overflow checking
* @a: first addend
* @b: second addend
* @d: pointer to store sum
@@ -66,8 +66,8 @@ static inline bool __must_check __must_check_overflow(bool overflow)
#define check_add_overflow(a, b, d) \
__must_check_overflow(__builtin_add_overflow(a, b, d))
-/** check_sub_overflow() - Calculate subtraction with overflow checking
- *
+/**
+ * check_sub_overflow() - Calculate subtraction with overflow checking
* @a: minuend; value to subtract from
* @b: subtrahend; value to subtract from @a
* @d: pointer to store difference
@@ -81,8 +81,8 @@ static inline bool __must_check __must_check_overflow(bool overflow)
#define check_sub_overflow(a, b, d) \
__must_check_overflow(__builtin_sub_overflow(a, b, d))
-/** check_mul_overflow() - Calculate multiplication with overflow checking
- *
+/**
+ * check_mul_overflow() - Calculate multiplication with overflow checking
* @a: first factor
* @b: second factor
* @d: pointer to store product
@@ -96,23 +96,24 @@ static inline bool __must_check __must_check_overflow(bool overflow)
#define check_mul_overflow(a, b, d) \
__must_check_overflow(__builtin_mul_overflow(a, b, d))
-/** check_shl_overflow() - Calculate a left-shifted value and check overflow
- *
+/**
+ * check_shl_overflow() - Calculate a left-shifted value and check overflow
* @a: Value to be shifted
* @s: How many bits left to shift
* @d: Pointer to where to store the result
*
* Computes *@d = (@a << @s)
*
- * Returns true if '*d' cannot hold the result or when 'a << s' doesn't
+ * Returns true if '*@d' cannot hold the result or when '@a << @s' doesn't
* make sense. Example conditions:
- * - 'a << s' causes bits to be lost when stored in *d.
- * - 's' is garbage (e.g. negative) or so large that the result of
- * 'a << s' is guaranteed to be 0.
- * - 'a' is negative.
- * - 'a << s' sets the sign bit, if any, in '*d'.
*
- * '*d' will hold the results of the attempted shift, but is not
+ * - '@a << @s' causes bits to be lost when stored in *@d.
+ * - '@s' is garbage (e.g. negative) or so large that the result of
+ * '@a << @s' is guaranteed to be 0.
+ * - '@a' is negative.
+ * - '@a << @s' sets the sign bit, if any, in '*@d'.
+ *
+ * '*@d' will hold the results of the attempted shift, but is not
* considered "safe for use" if true is returned.
*/
#define check_shl_overflow(a, s, d) __must_check_overflow(({ \
@@ -129,7 +130,6 @@ static inline bool __must_check __must_check_overflow(bool overflow)
/**
* size_mul() - Calculate size_t multiplication with saturation at SIZE_MAX
- *
* @factor1: first factor
* @factor2: second factor
*
@@ -149,7 +149,6 @@ static inline size_t __must_check size_mul(size_t factor1, size_t factor2)
/**
* size_add() - Calculate size_t addition with saturation at SIZE_MAX
- *
* @addend1: first addend
* @addend2: second addend
*
@@ -169,7 +168,6 @@ static inline size_t __must_check size_add(size_t addend1, size_t addend2)
/**
* size_sub() - Calculate size_t subtraction with saturation at SIZE_MAX
- *
* @minuend: value to subtract from
* @subtrahend: value to subtract from @minuend
*
@@ -192,7 +190,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
/**
* array_size() - Calculate size of 2-dimensional array.
- *
* @a: dimension one
* @b: dimension two
*
@@ -205,7 +202,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
/**
* array3_size() - Calculate size of 3-dimensional array.
- *
* @a: dimension one
* @b: dimension two
* @c: dimension three
@@ -220,7 +216,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
/**
* flex_array_size() - Calculate size of a flexible array member
* within an enclosing structure.
- *
* @p: Pointer to the structure.
* @member: Name of the flexible array member.
* @count: Number of elements in the array.
@@ -237,7 +232,6 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
/**
* struct_size() - Calculate size of structure with trailing flexible array.
- *
* @p: Pointer to the structure.
* @member: Name of the array member.
* @count: Number of elements in the array.
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 2ba044d0d5e5..8e984d75f5b6 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -225,7 +225,7 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
/**
* struct spi_controller_mem_ops - SPI memory operations
* @adjust_op_size: shrink the data xfer of an operation to match controller's
- * limitations (can be alignment of max RX/TX size
+ * limitations (can be alignment or max RX/TX size
* limitations)
* @supports_op: check if an operation is supported by the controller
* @exec_op: execute a SPI memory operation
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f07e6998bb68..9df0b9a762cc 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -146,9 +146,9 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
static inline bool vma_can_userfault(struct vm_area_struct *vma,
unsigned long vm_flags)
{
- if (vm_flags & VM_UFFD_MINOR)
- return is_vm_hugetlb_page(vma) || vma_is_shmem(vma);
-
+ if ((vm_flags & VM_UFFD_MINOR) &&
+ (!is_vm_hugetlb_page(vma) && !vma_is_shmem(vma)))
+ return false;
#ifndef CONFIG_PTE_MARKER_UFFD_WP
/*
* If user requested uffd-wp but not enabled pte markers for
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 3d08e67b3cfc..9f97f73615b6 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -41,13 +41,21 @@ struct genl_info;
* @mcgrps: multicast groups used by this family
* @n_mcgrps: number of multicast groups
* @resv_start_op: first operation for which reserved fields of the header
- * can be validated, new families should leave this field at zero
+ * can be validated and policies are required (see below);
+ * new families should leave this field at zero
* @mcgrp_offset: starting number of multicast group IDs in this family
* (private)
* @ops: the operations supported by this family
* @n_ops: number of operations supported by this family
* @small_ops: the small-struct operations supported by this family
* @n_small_ops: number of small-struct operations supported by this family
+ *
+ * Attribute policies (the combination of @policy and @maxattr fields)
+ * can be attached at the family level or at the operation level.
+ * If both are present the per-operation policy takes precedence.
+ * For operations before @resv_start_op lack of policy means that the core
+ * will perform no attribute parsing or validation. For newer operations
+ * if policy is not provided core will reject all TLV attributes.
*/
struct genl_family {
int id; /* private */
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 4418b1981e31..6bfa972f2fbf 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -181,6 +181,8 @@ enum {
NLA_S64,
NLA_BITFIELD32,
NLA_REJECT,
+ NLA_BE16,
+ NLA_BE32,
__NLA_TYPE_MAX,
};
@@ -231,6 +233,7 @@ enum nla_policy_validation {
* NLA_U32, NLA_U64,
* NLA_S8, NLA_S16,
* NLA_S32, NLA_S64,
+ * NLA_BE16, NLA_BE32,
* NLA_MSECS Leaving the length field zero will verify the
* given type fits, using it verifies minimum length
* just like "All other"
@@ -261,6 +264,8 @@ enum nla_policy_validation {
* NLA_U16,
* NLA_U32,
* NLA_U64,
+ * NLA_BE16,
+ * NLA_BE32,
* NLA_S8,
* NLA_S16,
* NLA_S32,
@@ -317,19 +322,10 @@ struct nla_policy {
u8 validation_type;
u16 len;
union {
- const u32 bitfield32_valid;
- const u32 mask;
- const char *reject_message;
- const struct nla_policy *nested_policy;
- struct netlink_range_validation *range;
- struct netlink_range_validation_signed *range_signed;
- struct {
- s16 min, max;
- u8 network_byte_order:1;
- };
- int (*validate)(const struct nlattr *attr,
- struct netlink_ext_ack *extack);
- /* This entry is special, and used for the attribute at index 0
+ /**
+ * @strict_start_type: first attribute to validate strictly
+ *
+ * This entry is special, and used for the attribute at index 0
* only, and specifies special data about the policy, namely it
* specifies the "boundary type" where strict length validation
* starts for any attribute types >= this value, also, strict
@@ -348,6 +344,19 @@ struct nla_policy {
* was added to enforce strict validation from thereon.
*/
u16 strict_start_type;
+
+ /* private: use NLA_POLICY_*() to set */
+ const u32 bitfield32_valid;
+ const u32 mask;
+ const char *reject_message;
+ const struct nla_policy *nested_policy;
+ struct netlink_range_validation *range;
+ struct netlink_range_validation_signed *range_signed;
+ struct {
+ s16 min, max;
+ };
+ int (*validate)(const struct nlattr *attr,
+ struct netlink_ext_ack *extack);
};
};
@@ -369,6 +378,8 @@ struct nla_policy {
(tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || tp == NLA_U64)
#define __NLA_IS_SINT_TYPE(tp) \
(tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64)
+#define __NLA_IS_BEINT_TYPE(tp) \
+ (tp == NLA_BE16 || tp == NLA_BE32)
#define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition))
#define NLA_ENSURE_UINT_TYPE(tp) \
@@ -382,6 +393,7 @@ struct nla_policy {
#define NLA_ENSURE_INT_OR_BINARY_TYPE(tp) \
(__NLA_ENSURE(__NLA_IS_UINT_TYPE(tp) || \
__NLA_IS_SINT_TYPE(tp) || \
+ __NLA_IS_BEINT_TYPE(tp) || \
tp == NLA_MSECS || \
tp == NLA_BINARY) + tp)
#define NLA_ENSURE_NO_VALIDATION_PTR(tp) \
@@ -389,6 +401,8 @@ struct nla_policy {
tp != NLA_REJECT && \
tp != NLA_NESTED && \
tp != NLA_NESTED_ARRAY) + tp)
+#define NLA_ENSURE_BEINT_TYPE(tp) \
+ (__NLA_ENSURE(__NLA_IS_BEINT_TYPE(tp)) + tp)
#define NLA_POLICY_RANGE(tp, _min, _max) { \
.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
@@ -419,14 +433,6 @@ struct nla_policy {
.type = NLA_ENSURE_INT_OR_BINARY_TYPE(tp), \
.validation_type = NLA_VALIDATE_MAX, \
.max = _max, \
- .network_byte_order = 0, \
-}
-
-#define NLA_POLICY_MAX_BE(tp, _max) { \
- .type = NLA_ENSURE_UINT_TYPE(tp), \
- .validation_type = NLA_VALIDATE_MAX, \
- .max = _max, \
- .network_byte_order = 1, \
}
#define NLA_POLICY_MASK(tp, _mask) { \
diff --git a/include/net/sock.h b/include/net/sock.h
index 9e464f6409a7..5db02546941c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1889,6 +1889,13 @@ void sock_kfree_s(struct sock *sk, void *mem, int size);
void sock_kzfree_s(struct sock *sk, void *mem, int size);
void sk_send_sigurg(struct sock *sk);
+static inline void sock_replace_proto(struct sock *sk, struct proto *proto)
+{
+ if (sk->sk_socket)
+ clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+ WRITE_ONCE(sk->sk_prot, proto);
+}
+
struct sockcm_cookie {
u64 transmit_time;
u32 mark;
@@ -2585,7 +2592,7 @@ static inline gfp_t gfp_any(void)
static inline gfp_t gfp_memcg_charge(void)
{
- return in_softirq() ? GFP_NOWAIT : GFP_KERNEL;
+ return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}
static inline long sock_rcvtimeo(const struct sock *sk, bool noblock)
diff --git a/include/sound/control.h b/include/sound/control.h
index eae443ba79ba..cc3dcc6cfb0f 100644
--- a/include/sound/control.h
+++ b/include/sound/control.h
@@ -138,6 +138,7 @@ int snd_ctl_remove(struct snd_card * card, struct snd_kcontrol * kcontrol);
int snd_ctl_replace(struct snd_card *card, struct snd_kcontrol *kcontrol, bool add_on_replace);
int snd_ctl_remove_id(struct snd_card * card, struct snd_ctl_elem_id *id);
int snd_ctl_rename_id(struct snd_card * card, struct snd_ctl_elem_id *src_id, struct snd_ctl_elem_id *dst_id);
+void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl, const char *name);
int snd_ctl_activate_id(struct snd_card *card, struct snd_ctl_elem_id *id, int active);
struct snd_kcontrol *snd_ctl_find_numid(struct snd_card * card, unsigned int numid);
struct snd_kcontrol *snd_ctl_find_id(struct snd_card * card, struct snd_ctl_elem_id *id);
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index a0b827f0c2f6..25e049f44178 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -177,6 +177,7 @@ void asoc_simple_convert_fixup(struct asoc_simple_data *data,
struct snd_pcm_hw_params *params);
void asoc_simple_parse_convert(struct device_node *np, char *prefix,
struct asoc_simple_data *data);
+bool asoc_simple_is_convert_required(const struct asoc_simple_data *data);
int asoc_simple_parse_routing(struct snd_soc_card *card,
char *prefix);
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 7ee65c0b4f70..0d93ec132ebb 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -763,6 +763,8 @@ struct drm_amdgpu_cs_chunk_data {
#define AMDGPU_INFO_FW_MES_KIQ 0x19
/* Subquery id: Query MES firmware version */
#define AMDGPU_INFO_FW_MES 0x1a
+ /* Subquery id: Query IMU firmware version */
+ #define AMDGPU_INFO_FW_IMU 0x1b
/* number of bytes moved for TTM migration */
#define AMDGPU_INFO_NUM_BYTES_MOVED 0x0f
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d3f86a280858..88448397642c 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -485,6 +485,9 @@ struct kvm_run {
#define KVM_MSR_EXIT_REASON_INVAL (1 << 0)
#define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1)
#define KVM_MSR_EXIT_REASON_FILTER (1 << 2)
+#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \
+ KVM_MSR_EXIT_REASON_UNKNOWN | \
+ KVM_MSR_EXIT_REASON_FILTER)
__u32 reason; /* kernel -> user */
__u32 index; /* kernel -> user */
__u64 data; /* kernel <-> user */
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 85be78e0e7f6..ccb7f5dad59b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1337,7 +1337,7 @@ union perf_mem_data_src {
#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */
#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */
/* 5-0x8 available */
-#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */
+#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */
#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */
#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 86cae23cc446..29da1f4b4578 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -1601,7 +1601,8 @@ struct v4l2_bt_timings {
((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt))
#define V4L2_DV_BT_BLANKING_HEIGHT(bt) \
((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \
- (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch)
+ ((bt)->interlaced ? \
+ ((bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) : 0))
#define V4L2_DV_BT_FRAME_HEIGHT(bt) \
((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt))
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 6cc16e39b27f..ac8c488e3077 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1173,7 +1173,7 @@ static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
}
}
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked)
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked)
{
struct llist_node *node;
struct llist_node fake;
@@ -1192,7 +1192,7 @@ again:
struct io_kiocb *req = container_of(node, struct io_kiocb,
io_task_work.node);
prefetch(container_of(next, struct io_kiocb, io_task_work.node));
- req->io_task_work.func(req, &locked);
+ req->io_task_work.func(req, locked);
ret++;
node = next;
}
@@ -1208,7 +1208,7 @@ again:
goto again;
}
- if (locked)
+ if (*locked)
io_submit_flush_completions(ctx);
trace_io_uring_local_work_run(ctx, ret, loops);
return ret;
@@ -1225,7 +1225,7 @@ int io_run_local_work(struct io_ring_ctx *ctx)
__set_current_state(TASK_RUNNING);
locked = mutex_trylock(&ctx->uring_lock);
- ret = __io_run_local_work(ctx, locked);
+ ret = __io_run_local_work(ctx, &locked);
if (locked)
mutex_unlock(&ctx->uring_lock);
@@ -1446,8 +1446,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min)
io_task_work_pending(ctx)) {
u32 tail = ctx->cached_cq_tail;
- if (!llist_empty(&ctx->work_llist))
- __io_run_local_work(ctx, true);
+ (void) io_run_local_work_locked(ctx);
if (task_work_pending(current) ||
wq_list_empty(&ctx->iopoll_list)) {
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index ef77d2aa3172..e99a79f2df9b 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -27,7 +27,7 @@ enum {
struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow);
bool io_req_cqe_overflow(struct io_kiocb *req);
int io_run_task_work_sig(struct io_ring_ctx *ctx);
-int __io_run_local_work(struct io_ring_ctx *ctx, bool locked);
+int __io_run_local_work(struct io_ring_ctx *ctx, bool *locked);
int io_run_local_work(struct io_ring_ctx *ctx);
void io_req_complete_failed(struct io_kiocb *req, s32 res);
void __io_req_complete(struct io_kiocb *req, unsigned issue_flags);
@@ -277,9 +277,18 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx)
static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
{
+ bool locked;
+ int ret;
+
if (llist_empty(&ctx->work_llist))
return 0;
- return __io_run_local_work(ctx, true);
+
+ locked = true;
+ ret = __io_run_local_work(ctx, &locked);
+ /* shouldn't happen! */
+ if (WARN_ON_ONCE(!locked))
+ mutex_lock(&ctx->uring_lock);
+ return ret;
}
static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
diff --git a/ipc/msg.c b/ipc/msg.c
index e4e0990e08f7..fd08b3cb36d7 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -1329,11 +1329,11 @@ fail_msg_bytes:
#ifdef CONFIG_IPC_NS
void msg_exit_ns(struct ipc_namespace *ns)
{
- percpu_counter_destroy(&ns->percpu_msg_bytes);
- percpu_counter_destroy(&ns->percpu_msg_hdrs);
free_ipcs(ns, &msg_ids(ns), freeque);
idr_destroy(&ns->ids[IPC_MSG_IDS].ipcs_idr);
rhashtable_destroy(&ns->ids[IPC_MSG_IDS].key_ht);
+ percpu_counter_destroy(&ns->percpu_msg_bytes);
+ percpu_counter_destroy(&ns->percpu_msg_hdrs);
}
#endif
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index eba603cec2c5..35c07afac924 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -4436,6 +4436,11 @@ static int btf_func_proto_check(struct btf_verifier_env *env,
return -EINVAL;
}
+ if (btf_type_is_resolve_source_only(ret_type)) {
+ btf_verifier_log_type(env, t, "Invalid return type");
+ return -EINVAL;
+ }
+
if (btf_type_needs_resolve(ret_type) &&
!env_type_is_resolved(env, ret_type_id)) {
err = btf_resolve(env, ret_type, ret_type_id);
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index fa64b80b8bca..04f0a045dcaa 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -4,6 +4,7 @@
#include <linux/hash.h>
#include <linux/bpf.h>
#include <linux/filter.h>
+#include <linux/init.h>
/* The BPF dispatcher is a multiway branch code generator. The
* dispatcher is a mechanism to avoid the performance penalty of an
@@ -90,6 +91,11 @@ int __weak arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int n
return -ENOTSUPP;
}
+int __weak __init bpf_arch_init_dispatcher_early(void *ip)
+{
+ return -ENOTSUPP;
+}
+
static int bpf_dispatcher_prepare(struct bpf_dispatcher *d, void *image, void *buf)
{
s64 ips[BPF_DISPATCHER_MAX] = {}, *ipsp = &ips[0];
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 5f83be1d2018..4901fa1048cd 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -418,14 +418,17 @@ static void drain_mem_cache(struct bpf_mem_cache *c)
/* No progs are using this bpf_mem_cache, but htab_map_free() called
* bpf_mem_cache_free() for all remaining elements and they can be in
* free_by_rcu or in waiting_for_gp lists, so drain those lists now.
+ *
+ * Except for waiting_for_gp list, there are no concurrent operations
+ * on these lists, so it is safe to use __llist_del_all().
*/
llist_for_each_safe(llnode, t, __llist_del_all(&c->free_by_rcu))
free_one(c, llnode);
llist_for_each_safe(llnode, t, llist_del_all(&c->waiting_for_gp))
free_one(c, llnode);
- llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist))
+ llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist))
free_one(c, llnode);
- llist_for_each_safe(llnode, t, llist_del_all(&c->free_llist_extra))
+ llist_for_each_safe(llnode, t, __llist_del_all(&c->free_llist_extra))
free_one(c, llnode);
}
@@ -493,6 +496,16 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
rcu_in_progress = 0;
for_each_possible_cpu(cpu) {
c = per_cpu_ptr(ma->cache, cpu);
+ /*
+ * refill_work may be unfinished for PREEMPT_RT kernel
+ * in which irq work is invoked in a per-CPU RT thread.
+ * It is also possible for kernel with
+ * arch_irq_work_has_interrupt() being false and irq
+ * work is invoked in timer interrupt. So waiting for
+ * the completion of irq work to ease the handling of
+ * concurrency.
+ */
+ irq_work_sync(&c->refill_work);
drain_mem_cache(c);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
@@ -507,6 +520,7 @@ void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma)
cc = per_cpu_ptr(ma->caches, cpu);
for (i = 0; i < NUM_CACHES; i++) {
c = &cc->cache[i];
+ irq_work_sync(&c->refill_work);
drain_mem_cache(c);
rcu_in_progress += atomic_read(&c->call_rcu_in_progress);
}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 014ee0953dbd..7f0a9f6cb889 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6946,6 +6946,7 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
__mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
callee->in_callback_fn = true;
+ callee->callback_ret_range = tnum_range(0, 1);
return 0;
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 01933db7629c..4ec3717003d5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9846,6 +9846,7 @@ void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size,
perf_sample_data_init(&data, 0, 0);
data.raw = &raw;
+ data.sample_flags |= PERF_SAMPLE_RAW;
perf_trace_buf_update(record, event_type);
diff --git a/kernel/events/hw_breakpoint_test.c b/kernel/events/hw_breakpoint_test.c
index 5ced822df788..c57610f52bb4 100644
--- a/kernel/events/hw_breakpoint_test.c
+++ b/kernel/events/hw_breakpoint_test.c
@@ -295,11 +295,11 @@ static int test_init(struct kunit *test)
{
/* Most test cases want 2 distinct CPUs. */
if (num_online_cpus() < 2)
- return -EINVAL;
+ kunit_skip(test, "not enough cpus");
/* Want the system to not use breakpoints elsewhere. */
if (hw_breakpoint_is_used())
- return -EBUSY;
+ kunit_skip(test, "hw breakpoint already in use");
return 0;
}
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3220b0a2fb4a..cd9f5a66a690 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2429,8 +2429,11 @@ int enable_kprobe(struct kprobe *kp)
if (!kprobes_all_disarmed && kprobe_disabled(p)) {
p->flags &= ~KPROBE_FLAG_DISABLED;
ret = arm_kprobe(p);
- if (ret)
+ if (ret) {
p->flags |= KPROBE_FLAG_DISABLED;
+ if (p != kp)
+ kp->flags |= KPROBE_FLAG_DISABLED;
+ }
}
out:
mutex_unlock(&kprobe_mutex);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index f58a0aa92310..793c55a2becb 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -645,7 +645,7 @@ static void power_down(void)
int error;
if (hibernation_mode == HIBERNATION_SUSPEND) {
- error = suspend_devices_and_enter(PM_SUSPEND_MEM);
+ error = suspend_devices_and_enter(mem_sleep_current);
if (error) {
hibernation_mode = hibernation_ops ?
HIBERNATION_PLATFORM :
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6bb8e72bc815..93416afebd59 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1403,30 +1403,32 @@ static void rcu_poll_gp_seq_end(unsigned long *snap)
// where caller does not hold the root rcu_node structure's lock.
static void rcu_poll_gp_seq_start_unlocked(unsigned long *snap)
{
+ unsigned long flags;
struct rcu_node *rnp = rcu_get_root();
if (rcu_init_invoked()) {
lockdep_assert_irqs_enabled();
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
rcu_poll_gp_seq_start(snap);
if (rcu_init_invoked())
- raw_spin_unlock_irq_rcu_node(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
// Make the polled API aware of the end of a grace period, but where
// caller does not hold the root rcu_node structure's lock.
static void rcu_poll_gp_seq_end_unlocked(unsigned long *snap)
{
+ unsigned long flags;
struct rcu_node *rnp = rcu_get_root();
if (rcu_init_invoked()) {
lockdep_assert_irqs_enabled();
- raw_spin_lock_irq_rcu_node(rnp);
+ raw_spin_lock_irqsave_rcu_node(rnp, flags);
}
rcu_poll_gp_seq_end(snap);
if (rcu_init_invoked())
- raw_spin_unlock_irq_rcu_node(rnp);
+ raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
}
/*
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index aac63ca9c3d1..e8143e368074 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -141,6 +141,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
return -E2BIG;
fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
+ if (!fp->rethook)
+ return -ENOMEM;
for (i = 0; i < size; i++) {
struct fprobe_rethook_node *node;
@@ -301,7 +303,8 @@ int unregister_fprobe(struct fprobe *fp)
{
int ret;
- if (!fp || fp->ops.func != fprobe_handler)
+ if (!fp || (fp->ops.saved_func != fprobe_handler &&
+ fp->ops.saved_func != fprobe_kprobe_handler))
return -EINVAL;
/*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index fbf2543111c0..7dc023641bf1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3028,18 +3028,8 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
command |= FTRACE_UPDATE_TRACE_FUNC;
}
- if (!command || !ftrace_enabled) {
- /*
- * If these are dynamic or per_cpu ops, they still
- * need their data freed. Since, function tracing is
- * not currently active, we can just free them
- * without synchronizing all CPUs.
- */
- if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
- goto free_ops;
-
- return 0;
- }
+ if (!command || !ftrace_enabled)
+ goto out;
/*
* If the ops uses a trampoline, then it needs to be
@@ -3076,6 +3066,7 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
removed_ops = NULL;
ops->flags &= ~FTRACE_OPS_FL_REMOVING;
+out:
/*
* Dynamic ops may be freed, we must make sure that all
* callers are done before leaving this function.
@@ -3103,7 +3094,6 @@ int ftrace_shutdown(struct ftrace_ops *ops, int command)
if (IS_ENABLED(CONFIG_PREEMPTION))
synchronize_rcu_tasks();
- free_ops:
ftrace_trampoline_free(ops);
}
diff --git a/kernel/trace/kprobe_event_gen_test.c b/kernel/trace/kprobe_event_gen_test.c
index 80e04a1e1977..d81f7c51025c 100644
--- a/kernel/trace/kprobe_event_gen_test.c
+++ b/kernel/trace/kprobe_event_gen_test.c
@@ -100,20 +100,20 @@ static int __init test_gen_kprobe_cmd(void)
KPROBE_GEN_TEST_FUNC,
KPROBE_GEN_TEST_ARG0, KPROBE_GEN_TEST_ARG1);
if (ret)
- goto free;
+ goto out;
/* Use kprobe_event_add_fields to add the rest of the fields */
ret = kprobe_event_add_fields(&cmd, KPROBE_GEN_TEST_ARG2, KPROBE_GEN_TEST_ARG3);
if (ret)
- goto free;
+ goto out;
/*
* This actually creates the event.
*/
ret = kprobe_event_gen_cmd_end(&cmd);
if (ret)
- goto free;
+ goto out;
/*
* Now get the gen_kprobe_test event file. We need to prevent
@@ -136,13 +136,11 @@ static int __init test_gen_kprobe_cmd(void)
goto delete;
}
out:
+ kfree(buf);
return ret;
delete:
/* We got an error after creating the event, delete it */
ret = kprobe_event_delete("gen_kprobe_test");
- free:
- kfree(buf);
-
goto out;
}
@@ -170,14 +168,14 @@ static int __init test_gen_kretprobe_cmd(void)
KPROBE_GEN_TEST_FUNC,
"$retval");
if (ret)
- goto free;
+ goto out;
/*
* This actually creates the event.
*/
ret = kretprobe_event_gen_cmd_end(&cmd);
if (ret)
- goto free;
+ goto out;
/*
* Now get the gen_kretprobe_test event file. We need to
@@ -201,13 +199,11 @@ static int __init test_gen_kretprobe_cmd(void)
goto delete;
}
out:
+ kfree(buf);
return ret;
delete:
/* We got an error after creating the event, delete it */
ret = kprobe_event_delete("gen_kretprobe_test");
- free:
- kfree(buf);
-
goto out;
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 199759c73519..9712083832f4 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -937,6 +937,9 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
struct ring_buffer_per_cpu *cpu_buffer;
struct rb_irq_work *rbwork;
+ if (!buffer)
+ return;
+
if (cpu == RING_BUFFER_ALL_CPUS) {
/* Wake up individual ones too. One level recursion */
@@ -945,7 +948,15 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu)
rbwork = &buffer->irq_work;
} else {
+ if (WARN_ON_ONCE(!buffer->buffers))
+ return;
+ if (WARN_ON_ONCE(cpu >= nr_cpu_ids))
+ return;
+
cpu_buffer = buffer->buffers[cpu];
+ /* The CPU buffer may not have been initialized yet */
+ if (!cpu_buffer)
+ return;
rbwork = &cpu_buffer->irq_work;
}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 3fc7abffc7aa..29280072dc0e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -400,8 +400,9 @@ config FRAME_WARN
default 1536 if (!64BIT && XTENSA)
default 1024 if !64BIT
default 2048 if 64BIT
+ default 0 if KMSAN
help
- Tell gcc to warn at build time for stack frames larger than this.
+ Tell the compiler to warn at build time for stack frames larger than this.
Setting this too low will cause a lot of warnings.
Setting it to 0 disables the warning.
diff --git a/lib/kunit/string-stream.c b/lib/kunit/string-stream.c
index f5ae79c37400..a608746020a9 100644
--- a/lib/kunit/string-stream.c
+++ b/lib/kunit/string-stream.c
@@ -56,8 +56,8 @@ int string_stream_vadd(struct string_stream *stream,
frag_container = alloc_string_stream_fragment(stream->test,
len,
stream->gfp);
- if (!frag_container)
- return -ENOMEM;
+ if (IS_ERR(frag_container))
+ return PTR_ERR(frag_container);
len = vsnprintf(frag_container->fragment, len, fmt, args);
spin_lock(&stream->lock);
diff --git a/lib/kunit/test.c b/lib/kunit/test.c
index 90640a43cf62..2a6992fe7c3e 100644
--- a/lib/kunit/test.c
+++ b/lib/kunit/test.c
@@ -265,7 +265,7 @@ static void kunit_fail(struct kunit *test, const struct kunit_loc *loc,
kunit_set_failure(test);
stream = alloc_string_stream(test, GFP_KERNEL);
- if (!stream) {
+ if (IS_ERR(stream)) {
WARN(true,
"Could not allocate stream to print failed assertion in %s:%d\n",
loc->file,
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index e1743803c851..fbde494444b8 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -2903,8 +2903,8 @@ static inline void *mtree_range_walk(struct ma_state *mas)
unsigned long max, min;
unsigned long prev_max, prev_min;
- last = next = mas->node;
- prev_min = min = mas->min;
+ next = mas->node;
+ min = mas->min;
max = mas->max;
do {
offset = 0;
diff --git a/lib/nlattr.c b/lib/nlattr.c
index 40f22b177d69..b67a53e29b8f 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -124,10 +124,12 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
range->max = U8_MAX;
break;
case NLA_U16:
+ case NLA_BE16:
case NLA_BINARY:
range->max = U16_MAX;
break;
case NLA_U32:
+ case NLA_BE32:
range->max = U32_MAX;
break;
case NLA_U64:
@@ -159,31 +161,6 @@ void nla_get_range_unsigned(const struct nla_policy *pt,
}
}
-static u64 nla_get_attr_bo(const struct nla_policy *pt,
- const struct nlattr *nla)
-{
- switch (pt->type) {
- case NLA_U16:
- if (pt->network_byte_order)
- return ntohs(nla_get_be16(nla));
-
- return nla_get_u16(nla);
- case NLA_U32:
- if (pt->network_byte_order)
- return ntohl(nla_get_be32(nla));
-
- return nla_get_u32(nla);
- case NLA_U64:
- if (pt->network_byte_order)
- return be64_to_cpu(nla_get_be64(nla));
-
- return nla_get_u64(nla);
- }
-
- WARN_ON_ONCE(1);
- return 0;
-}
-
static int nla_validate_range_unsigned(const struct nla_policy *pt,
const struct nlattr *nla,
struct netlink_ext_ack *extack,
@@ -197,9 +174,13 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
value = nla_get_u8(nla);
break;
case NLA_U16:
+ value = nla_get_u16(nla);
+ break;
case NLA_U32:
+ value = nla_get_u32(nla);
+ break;
case NLA_U64:
- value = nla_get_attr_bo(pt, nla);
+ value = nla_get_u64(nla);
break;
case NLA_MSECS:
value = nla_get_u64(nla);
@@ -207,6 +188,12 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt,
case NLA_BINARY:
value = nla_len(nla);
break;
+ case NLA_BE16:
+ value = ntohs(nla_get_be16(nla));
+ break;
+ case NLA_BE32:
+ value = ntohl(nla_get_be32(nla));
+ break;
default:
return -EINVAL;
}
@@ -334,6 +321,8 @@ static int nla_validate_int_range(const struct nla_policy *pt,
case NLA_U64:
case NLA_MSECS:
case NLA_BINARY:
+ case NLA_BE16:
+ case NLA_BE32:
return nla_validate_range_unsigned(pt, nla, extack, validate);
case NLA_S8:
case NLA_S16:
diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
index 5369634701fa..b8556a2e7bb1 100644
--- a/lib/overflow_kunit.c
+++ b/lib/overflow_kunit.c
@@ -16,6 +16,34 @@
#include <linux/types.h>
#include <linux/vmalloc.h>
+#define SKIP(cond, reason) do { \
+ if (cond) { \
+ kunit_skip(test, reason); \
+ return; \
+ } \
+} while (0)
+
+/*
+ * Clang 11 and earlier generate unwanted libcalls for signed output
+ * on unsigned input.
+ */
+#if defined(CONFIG_CC_IS_CLANG) && __clang_major__ <= 11
+# define SKIP_SIGN_MISMATCH(t) SKIP(t, "Clang 11 unwanted libcalls")
+#else
+# define SKIP_SIGN_MISMATCH(t) do { } while (0)
+#endif
+
+/*
+ * Clang 13 and earlier generate unwanted libcalls for 64-bit tests on
+ * 32-bit hosts.
+ */
+#if defined(CONFIG_CC_IS_CLANG) && __clang_major__ <= 13 && \
+ BITS_PER_LONG != 64
+# define SKIP_64_ON_32(t) SKIP(t, "Clang 13 unwanted libcalls")
+#else
+# define SKIP_64_ON_32(t) do { } while (0)
+#endif
+
#define DEFINE_TEST_ARRAY_TYPED(t1, t2, t) \
static const struct test_ ## t1 ## _ ## t2 ## __ ## t { \
t1 a; \
@@ -94,7 +122,6 @@ DEFINE_TEST_ARRAY(u32) = {
{-4U, 5U, 1U, -9U, -20U, true, false, true},
};
-#if BITS_PER_LONG == 64
DEFINE_TEST_ARRAY(u64) = {
{0, 0, 0, 0, 0, false, false, false},
{1, 1, 2, 0, 1, false, false, false},
@@ -118,7 +145,6 @@ DEFINE_TEST_ARRAY(u64) = {
false, true, false},
{-15ULL, 10ULL, -5ULL, -25ULL, -150ULL, false, false, true},
};
-#endif
DEFINE_TEST_ARRAY(s8) = {
{0, 0, 0, 0, 0, false, false, false},
@@ -194,7 +220,6 @@ DEFINE_TEST_ARRAY(s32) = {
{S32_MAX, S32_MAX, -2, 0, 1, true, false, true},
};
-#if BITS_PER_LONG == 64
DEFINE_TEST_ARRAY(s64) = {
{0, 0, 0, 0, 0, false, false, false},
@@ -223,7 +248,6 @@ DEFINE_TEST_ARRAY(s64) = {
{-128, -1, -129, -127, 128, false, false, false},
{0, -S64_MAX, -S64_MAX, S64_MAX, 0, false, false, false},
};
-#endif
#define check_one_op(t, fmt, op, sym, a, b, r, of) do { \
int _a_orig = a, _a_bump = a + 1; \
@@ -246,7 +270,7 @@ DEFINE_TEST_ARRAY(s64) = {
#define DEFINE_TEST_FUNC_TYPED(n, t, fmt) \
static void do_test_ ## n(struct kunit *test, const struct test_ ## n *p) \
-{ \
+{ \
check_one_op(t, fmt, add, "+", p->a, p->b, p->sum, p->s_of); \
check_one_op(t, fmt, add, "+", p->b, p->a, p->sum, p->s_of); \
check_one_op(t, fmt, sub, "-", p->a, p->b, p->diff, p->d_of); \
@@ -257,6 +281,12 @@ static void do_test_ ## n(struct kunit *test, const struct test_ ## n *p) \
static void n ## _overflow_test(struct kunit *test) { \
unsigned i; \
\
+ SKIP_64_ON_32(__same_type(t, u64)); \
+ SKIP_64_ON_32(__same_type(t, s64)); \
+ SKIP_SIGN_MISMATCH(__same_type(n ## _tests[0].a, u32) && \
+ __same_type(n ## _tests[0].b, u32) && \
+ __same_type(n ## _tests[0].sum, int)); \
+ \
for (i = 0; i < ARRAY_SIZE(n ## _tests); ++i) \
do_test_ ## n(test, &n ## _tests[i]); \
kunit_info(test, "%zu %s arithmetic tests finished\n", \
@@ -272,10 +302,8 @@ DEFINE_TEST_FUNC(u16, "%d");
DEFINE_TEST_FUNC(s16, "%d");
DEFINE_TEST_FUNC(u32, "%u");
DEFINE_TEST_FUNC(s32, "%d");
-#if BITS_PER_LONG == 64
DEFINE_TEST_FUNC(u64, "%llu");
DEFINE_TEST_FUNC(s64, "%lld");
-#endif
DEFINE_TEST_ARRAY_TYPED(u32, u32, u8) = {
{0, 0, 0, 0, 0, false, false, false},
@@ -715,13 +743,10 @@ static struct kunit_case overflow_test_cases[] = {
KUNIT_CASE(s16_s16__s16_overflow_test),
KUNIT_CASE(u32_u32__u32_overflow_test),
KUNIT_CASE(s32_s32__s32_overflow_test),
-/* Clang 13 and earlier generate unwanted libcalls on 32-bit. */
-#if BITS_PER_LONG == 64
KUNIT_CASE(u64_u64__u64_overflow_test),
KUNIT_CASE(s64_s64__s64_overflow_test),
-#endif
- KUNIT_CASE(u32_u32__u8_overflow_test),
KUNIT_CASE(u32_u32__int_overflow_test),
+ KUNIT_CASE(u32_u32__u8_overflow_test),
KUNIT_CASE(u8_u8__int_overflow_test),
KUNIT_CASE(int_int__u8_overflow_test),
KUNIT_CASE(shift_sane_test),
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index b358a74ed7ed..f2ba5787055a 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -369,18 +369,10 @@ static int __init test_rhltable(unsigned int entries)
pr_info("test %d random rhlist add/delete operations\n", entries);
for (j = 0; j < entries; j++) {
u32 i = prandom_u32_max(entries);
- u32 prand = get_random_u32();
+ u32 prand = prandom_u32_max(4);
cond_resched();
- if (prand == 0)
- prand = get_random_u32();
-
- if (prand & 1) {
- prand >>= 1;
- continue;
- }
-
err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
if (test_bit(i, obj_in_table)) {
clear_bit(i, obj_in_table);
@@ -393,35 +385,29 @@ static int __init test_rhltable(unsigned int entries)
}
if (prand & 1) {
- prand >>= 1;
- continue;
- }
-
- err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
- if (err == 0) {
- if (WARN(test_and_set_bit(i, obj_in_table), "succeeded to insert same object %d", i))
- continue;
- } else {
- if (WARN(!test_bit(i, obj_in_table), "failed to insert object %d", i))
- continue;
- }
-
- if (prand & 1) {
- prand >>= 1;
- continue;
+ err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+ if (err == 0) {
+ if (WARN(test_and_set_bit(i, obj_in_table), "succeeded to insert same object %d", i))
+ continue;
+ } else {
+ if (WARN(!test_bit(i, obj_in_table), "failed to insert object %d", i))
+ continue;
+ }
}
- i = prandom_u32_max(entries);
- if (test_bit(i, obj_in_table)) {
- err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
- WARN(err, "cannot remove element at slot %d", i);
- if (err == 0)
- clear_bit(i, obj_in_table);
- } else {
- err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
- WARN(err, "failed to insert object %d", i);
- if (err == 0)
- set_bit(i, obj_in_table);
+ if (prand & 2) {
+ i = prandom_u32_max(entries);
+ if (test_bit(i, obj_in_table)) {
+ err = rhltable_remove(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+ WARN(err, "cannot remove element at slot %d", i);
+ if (err == 0)
+ clear_bit(i, obj_in_table);
+ } else {
+ err = rhltable_insert(&rhlt, &rhl_test_objects[i].list_node, test_rht_params);
+ WARN(err, "failed to insert object %d", i);
+ if (err == 0)
+ set_bit(i, obj_in_table);
+ }
}
}
diff --git a/mm/gup.c b/mm/gup.c
index fe195d47de74..90e372352e82 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -989,8 +989,17 @@ static int faultin_page(struct vm_area_struct *vma,
fault_flags |= FAULT_FLAG_WRITE;
if (*flags & FOLL_REMOTE)
fault_flags |= FAULT_FLAG_REMOTE;
- if (locked)
+ if (locked) {
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
+ /*
+ * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set
+ * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE.
+ * That's because some callers may not be prepared to
+ * handle early exits caused by non-fatal signals.
+ */
+ if (*flags & FOLL_INTERRUPTIBLE)
+ fault_flags |= FAULT_FLAG_INTERRUPTIBLE;
+ }
if (*flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT;
if (*flags & FOLL_TRIED) {
@@ -1392,6 +1401,22 @@ retry:
EXPORT_SYMBOL_GPL(fixup_user_fault);
/*
+ * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is
+ * specified, it'll also respond to generic signals. The caller of GUP
+ * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption.
+ */
+static bool gup_signal_pending(unsigned int flags)
+{
+ if (fatal_signal_pending(current))
+ return true;
+
+ if (!(flags & FOLL_INTERRUPTIBLE))
+ return false;
+
+ return signal_pending(current);
+}
+
+/*
* Please note that this function, unlike __get_user_pages will not
* return 0 for nr_pages > 0 without FOLL_NOWAIT
*/
@@ -1472,11 +1497,11 @@ retry:
* Repeat on the address that fired VM_FAULT_RETRY
* with both FAULT_FLAG_ALLOW_RETRY and
* FAULT_FLAG_TRIED. Note that GUP can be interrupted
- * by fatal signals, so we need to check it before we
+ * by fatal signals of even common signals, depending on
+ * the caller's request. So we need to check it before we
* start trying again otherwise it can loop forever.
*/
-
- if (fatal_signal_pending(current)) {
+ if (gup_signal_pending(flags)) {
if (!pages_done)
pages_done = -EINTR;
break;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 03fc7e5edf07..561a42567477 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2462,7 +2462,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
* Fix up and warn once if private is unexpectedly set.
*/
if (!folio_test_swapcache(page_folio(head))) {
- VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, head);
+ VM_WARN_ON_ONCE_PAGE(page_tail->private != 0, page_tail);
page_tail->private = 0;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 546df97c31e4..b5ed54f760bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6285,9 +6285,12 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
fault_flags |= FAULT_FLAG_WRITE;
else if (unshare)
fault_flags |= FAULT_FLAG_UNSHARE;
- if (locked)
+ if (locked) {
fault_flags |= FAULT_FLAG_ALLOW_RETRY |
FAULT_FLAG_KILLABLE;
+ if (flags & FOLL_INTERRUPTIBLE)
+ fault_flags |= FAULT_FLAG_INTERRUPTIBLE;
+ }
if (flags & FOLL_NOWAIT)
fault_flags |= FAULT_FLAG_ALLOW_RETRY |
FAULT_FLAG_RETRY_NOWAIT;
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 37af2dc8dac9..646e2979641f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1461,6 +1461,27 @@ static void scan_gray_list(void)
}
/*
+ * Conditionally call resched() in a object iteration loop while making sure
+ * that the given object won't go away without RCU read lock by performing a
+ * get_object() if !pinned.
+ *
+ * Return: false if can't do a cond_resched() due to get_object() failure
+ * true otherwise
+ */
+static bool kmemleak_cond_resched(struct kmemleak_object *object, bool pinned)
+{
+ if (!pinned && !get_object(object))
+ return false;
+
+ rcu_read_unlock();
+ cond_resched();
+ rcu_read_lock();
+ if (!pinned)
+ put_object(object);
+ return true;
+}
+
+/*
* Scan data sections and all the referenced memory blocks allocated via the
* kernel's standard allocators. This function must be called with the
* scan_mutex held.
@@ -1471,7 +1492,7 @@ static void kmemleak_scan(void)
struct zone *zone;
int __maybe_unused i;
int new_leaks = 0;
- int loop1_cnt = 0;
+ int loop_cnt = 0;
jiffies_last_scan = jiffies;
@@ -1480,7 +1501,6 @@ static void kmemleak_scan(void)
list_for_each_entry_rcu(object, &object_list, object_list) {
bool obj_pinned = false;
- loop1_cnt++;
raw_spin_lock_irq(&object->lock);
#ifdef DEBUG
/*
@@ -1514,24 +1534,11 @@ static void kmemleak_scan(void)
raw_spin_unlock_irq(&object->lock);
/*
- * Do a cond_resched() to avoid soft lockup every 64k objects.
- * Make sure a reference has been taken so that the object
- * won't go away without RCU read lock.
+ * Do a cond_resched() every 64k objects to avoid soft lockup.
*/
- if (!(loop1_cnt & 0xffff)) {
- if (!obj_pinned && !get_object(object)) {
- /* Try the next object instead */
- loop1_cnt--;
- continue;
- }
-
- rcu_read_unlock();
- cond_resched();
- rcu_read_lock();
-
- if (!obj_pinned)
- put_object(object);
- }
+ if (!(++loop_cnt & 0xffff) &&
+ !kmemleak_cond_resched(object, obj_pinned))
+ loop_cnt--; /* Try again on next object */
}
rcu_read_unlock();
@@ -1598,8 +1605,16 @@ static void kmemleak_scan(void)
* scan and color them gray until the next scan.
*/
rcu_read_lock();
+ loop_cnt = 0;
list_for_each_entry_rcu(object, &object_list, object_list) {
/*
+ * Do a cond_resched() every 64k objects to avoid soft lockup.
+ */
+ if (!(++loop_cnt & 0xffff) &&
+ !kmemleak_cond_resched(object, false))
+ loop_cnt--; /* Try again on next object */
+
+ /*
* This is racy but we can save the overhead of lock/unlock
* calls. The missed objects, if any, should be caught in
* the next scan.
@@ -1632,8 +1647,16 @@ static void kmemleak_scan(void)
* Scanning result reporting.
*/
rcu_read_lock();
+ loop_cnt = 0;
list_for_each_entry_rcu(object, &object_list, object_list) {
/*
+ * Do a cond_resched() every 64k objects to avoid soft lockup.
+ */
+ if (!(++loop_cnt & 0xffff) &&
+ !kmemleak_cond_resched(object, false))
+ loop_cnt--; /* Try again on next object */
+
+ /*
* This is racy but we can save the overhead of lock/unlock
* calls. The missed objects, if any, should be caught in
* the next scan.
diff --git a/mm/kmsan/instrumentation.c b/mm/kmsan/instrumentation.c
index 280d15413268..271f135f97a1 100644
--- a/mm/kmsan/instrumentation.c
+++ b/mm/kmsan/instrumentation.c
@@ -14,6 +14,7 @@
#include "kmsan.h"
#include <linux/gfp.h>
+#include <linux/kmsan_string.h>
#include <linux/mm.h>
#include <linux/uaccess.h>
diff --git a/mm/kmsan/shadow.c b/mm/kmsan/shadow.c
index 21e3e196ec3c..a787c04e9583 100644
--- a/mm/kmsan/shadow.c
+++ b/mm/kmsan/shadow.c
@@ -167,6 +167,7 @@ void kmsan_copy_page_meta(struct page *dst, struct page *src)
__memcpy(origin_ptr_for(dst), origin_ptr_for(src), PAGE_SIZE);
kmsan_leave_runtime();
}
+EXPORT_SYMBOL(kmsan_copy_page_meta);
void kmsan_alloc_page(struct page *page, unsigned int order, gfp_t flags)
{
diff --git a/mm/madvise.c b/mm/madvise.c
index 2baa93ca2310..c7105ec6d08c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -813,7 +813,14 @@ static bool madvise_dontneed_free_valid_vma(struct vm_area_struct *vma,
if (start & ~huge_page_mask(hstate_vma(vma)))
return false;
- *end = ALIGN(*end, huge_page_size(hstate_vma(vma)));
+ /*
+ * Madvise callers expect the length to be rounded up to PAGE_SIZE
+ * boundaries, and may be unaware that this VMA uses huge pages.
+ * Avoid unexpected data loss by rounding down the number of
+ * huge pages freed.
+ */
+ *end = ALIGN_DOWN(*end, huge_page_size(hstate_vma(vma)));
+
return true;
}
@@ -828,6 +835,9 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
if (!madvise_dontneed_free_valid_vma(vma, start, &end, behavior))
return -EINVAL;
+ if (start == end)
+ return 0;
+
if (!userfaultfd_remove(vma, start, end)) {
*prev = NULL; /* mmap_lock has been dropped, prev is stale */
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index f116b7b6333e..fa8c9d07f9ce 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -131,8 +131,8 @@ static void memory_tier_device_release(struct device *dev)
kfree(tier);
}
-static ssize_t nodes_show(struct device *dev,
- struct device_attribute *attr, char *buf)
+static ssize_t nodelist_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
int ret;
nodemask_t nmask;
@@ -143,10 +143,10 @@ static ssize_t nodes_show(struct device *dev,
mutex_unlock(&memory_tier_lock);
return ret;
}
-static DEVICE_ATTR_RO(nodes);
+static DEVICE_ATTR_RO(nodelist);
static struct attribute *memtier_dev_attrs[] = {
- &dev_attr_nodes.attr,
+ &dev_attr_nodelist.attr,
NULL
};
diff --git a/mm/migrate.c b/mm/migrate.c
index 1379e1912772..dff333593a8a 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1582,6 +1582,13 @@ out:
*/
list_splice(&ret_pages, from);
+ /*
+ * Return 0 in case all subpages of fail-to-migrate THPs are
+ * migrated successfully.
+ */
+ if (list_empty(from))
+ rc = 0;
+
count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
count_vm_events(PGMIGRATE_FAIL, nr_failed_pages);
count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
diff --git a/mm/mmap.c b/mm/mmap.c
index e270057ed04e..2def55555e05 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2852,6 +2852,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
if (next->vm_flags != vma->vm_flags)
goto out;
+ if (start + size <= next->vm_end)
+ break;
+
prev = next;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b5a6c815ae28..218b28ee49ed 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -807,6 +807,7 @@ static void prep_compound_tail(struct page *head, int tail_idx)
p->mapping = TAIL_MAPPING;
set_compound_head(p, head);
+ set_page_private(p, 0);
}
void prep_compound_page(struct page *page, unsigned int order)
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 04141a9bea70..47fbc1696466 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -330,7 +330,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
zone->zone_start_pfn);
if (skip_isolation) {
- int mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
+ int mt __maybe_unused = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
VM_BUG_ON(!is_migrate_isolate(mt));
} else {
diff --git a/mm/shmem.c b/mm/shmem.c
index 8280a5cb48df..c1d8b8a1aa3b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2424,9 +2424,26 @@ int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
if (!zeropage) { /* COPY */
page_kaddr = kmap_local_folio(folio, 0);
+ /*
+ * The read mmap_lock is held here. Despite the
+ * mmap_lock being read recursive a deadlock is still
+ * possible if a writer has taken a lock. For example:
+ *
+ * process A thread 1 takes read lock on own mmap_lock
+ * process A thread 2 calls mmap, blocks taking write lock
+ * process B thread 1 takes page fault, read lock on own mmap lock
+ * process B thread 2 calls mmap, blocks taking write lock
+ * process A thread 1 blocks taking read lock on process B
+ * process B thread 1 blocks taking read lock on process A
+ *
+ * Disable page faults to prevent potential deadlock
+ * and retry the copy outside the mmap_lock.
+ */
+ pagefault_disable();
ret = copy_from_user(page_kaddr,
(const void __user *)src_addr,
PAGE_SIZE);
+ pagefault_enable();
kunmap_local(page_kaddr);
/* fallback to copy_from_user outside mmap_lock */
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index e24e8a47ce8a..3d0fef3980b3 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -157,11 +157,28 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm,
if (!page)
goto out;
- page_kaddr = kmap_atomic(page);
+ page_kaddr = kmap_local_page(page);
+ /*
+ * The read mmap_lock is held here. Despite the
+ * mmap_lock being read recursive a deadlock is still
+ * possible if a writer has taken a lock. For example:
+ *
+ * process A thread 1 takes read lock on own mmap_lock
+ * process A thread 2 calls mmap, blocks taking write lock
+ * process B thread 1 takes page fault, read lock on own mmap lock
+ * process B thread 2 calls mmap, blocks taking write lock
+ * process A thread 1 blocks taking read lock on process B
+ * process B thread 1 blocks taking read lock on process A
+ *
+ * Disable page faults to prevent potential deadlock
+ * and retry the copy outside the mmap_lock.
+ */
+ pagefault_disable();
ret = copy_from_user(page_kaddr,
(const void __user *) src_addr,
PAGE_SIZE);
- kunmap_atomic(page_kaddr);
+ pagefault_enable();
+ kunmap_local(page_kaddr);
/* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
@@ -646,11 +663,11 @@ retry:
mmap_read_unlock(dst_mm);
BUG_ON(!page);
- page_kaddr = kmap(page);
+ page_kaddr = kmap_local_page(page);
err = copy_from_user(page_kaddr,
(const void __user *) src_addr,
PAGE_SIZE);
- kunmap(page);
+ kunmap_local(page_kaddr);
if (unlikely(err)) {
err = -EFAULT;
goto out;
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7a59c4487050..a6c12863a253 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1067,10 +1067,21 @@ int hci_conn_del(struct hci_conn *conn)
hdev->acl_cnt += conn->sent;
} else {
struct hci_conn *acl = conn->link;
+
if (acl) {
acl->link = NULL;
hci_conn_drop(acl);
}
+
+ /* Unacked ISO frames */
+ if (conn->type == ISO_LINK) {
+ if (hdev->iso_pkts)
+ hdev->iso_cnt += conn->sent;
+ else if (hdev->le_pkts)
+ hdev->le_cnt += conn->sent;
+ else
+ hdev->acl_cnt += conn->sent;
+ }
}
if (conn->amp_mgr)
@@ -1761,6 +1772,7 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
if (!cis)
return ERR_PTR(-ENOMEM);
cis->cleanup = cis_cleanup;
+ cis->dst_type = dst_type;
}
if (cis->state == BT_CONNECTED)
@@ -2140,12 +2152,6 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
struct hci_conn *le;
struct hci_conn *cis;
- /* Convert from ISO socket address type to HCI address type */
- if (dst_type == BDADDR_LE_PUBLIC)
- dst_type = ADDR_LE_DEV_PUBLIC;
- else
- dst_type = ADDR_LE_DEV_RANDOM;
-
if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
le = hci_connect_le(hdev, dst, dst_type, false,
BT_SECURITY_LOW,
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 613039ba5dbf..f825857db6d0 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -235,6 +235,14 @@ static int iso_chan_add(struct iso_conn *conn, struct sock *sk,
return err;
}
+static inline u8 le_addr_type(u8 bdaddr_type)
+{
+ if (bdaddr_type == BDADDR_LE_PUBLIC)
+ return ADDR_LE_DEV_PUBLIC;
+ else
+ return ADDR_LE_DEV_RANDOM;
+}
+
static int iso_connect_bis(struct sock *sk)
{
struct iso_conn *conn;
@@ -328,14 +336,16 @@ static int iso_connect_cis(struct sock *sk)
/* Just bind if DEFER_SETUP has been set */
if (test_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
hcon = hci_bind_cis(hdev, &iso_pi(sk)->dst,
- iso_pi(sk)->dst_type, &iso_pi(sk)->qos);
+ le_addr_type(iso_pi(sk)->dst_type),
+ &iso_pi(sk)->qos);
if (IS_ERR(hcon)) {
err = PTR_ERR(hcon);
goto done;
}
} else {
hcon = hci_connect_cis(hdev, &iso_pi(sk)->dst,
- iso_pi(sk)->dst_type, &iso_pi(sk)->qos);
+ le_addr_type(iso_pi(sk)->dst_type),
+ &iso_pi(sk)->qos);
if (IS_ERR(hcon)) {
err = PTR_ERR(hcon);
goto done;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 1f34b82ca0ec..9c24947aa41e 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1990,7 +1990,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm,
if (link_type == LE_LINK && c->src_type == BDADDR_BREDR)
continue;
- if (c->psm == psm) {
+ if (c->chan_type != L2CAP_CHAN_FIXED && c->psm == psm) {
int src_match, dst_match;
int src_any, dst_any;
@@ -3764,7 +3764,8 @@ done:
l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC,
sizeof(rfc), (unsigned long) &rfc, endptr - ptr);
- if (test_bit(FLAG_EFS_ENABLE, &chan->flags)) {
+ if (remote_efs &&
+ test_bit(FLAG_EFS_ENABLE, &chan->flags)) {
chan->remote_id = efs.id;
chan->remote_stype = efs.stype;
chan->remote_msdu = le16_to_cpu(efs.msdu);
@@ -5813,6 +5814,19 @@ static int l2cap_le_connect_req(struct l2cap_conn *conn,
BT_DBG("psm 0x%2.2x scid 0x%4.4x mtu %u mps %u", __le16_to_cpu(psm),
scid, mtu, mps);
+ /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A
+ * page 1059:
+ *
+ * Valid range: 0x0001-0x00ff
+ *
+ * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges
+ */
+ if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) {
+ result = L2CAP_CR_LE_BAD_PSM;
+ chan = NULL;
+ goto response;
+ }
+
/* Check if we have socket listening on psm */
pchan = l2cap_global_chan_by_psm(BT_LISTEN, psm, &conn->hcon->src,
&conn->hcon->dst, LE_LINK);
@@ -6001,6 +6015,18 @@ static inline int l2cap_ecred_conn_req(struct l2cap_conn *conn,
psm = req->psm;
+ /* BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part A
+ * page 1059:
+ *
+ * Valid range: 0x0001-0x00ff
+ *
+ * Table 4.15: L2CAP_LE_CREDIT_BASED_CONNECTION_REQ SPSM ranges
+ */
+ if (!psm || __le16_to_cpu(psm) > L2CAP_PSM_LE_DYN_END) {
+ result = L2CAP_CR_LE_BAD_PSM;
+ goto response;
+ }
+
BT_DBG("psm 0x%2.2x mtu %u mps %u", __le16_to_cpu(psm), mtu, mps);
memset(&pdu, 0, sizeof(pdu));
@@ -6885,6 +6911,7 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan,
struct l2cap_ctrl *control,
struct sk_buff *skb, u8 event)
{
+ struct l2cap_ctrl local_control;
int err = 0;
bool skb_in_use = false;
@@ -6909,15 +6936,32 @@ static int l2cap_rx_state_recv(struct l2cap_chan *chan,
chan->buffer_seq = chan->expected_tx_seq;
skb_in_use = true;
+ /* l2cap_reassemble_sdu may free skb, hence invalidate
+ * control, so make a copy in advance to use it after
+ * l2cap_reassemble_sdu returns and to avoid the race
+ * condition, for example:
+ *
+ * The current thread calls:
+ * l2cap_reassemble_sdu
+ * chan->ops->recv == l2cap_sock_recv_cb
+ * __sock_queue_rcv_skb
+ * Another thread calls:
+ * bt_sock_recvmsg
+ * skb_recv_datagram
+ * skb_free_datagram
+ * Then the current thread tries to access control, but
+ * it was freed by skb_free_datagram.
+ */
+ local_control = *control;
err = l2cap_reassemble_sdu(chan, skb, control);
if (err)
break;
- if (control->final) {
+ if (local_control.final) {
if (!test_and_clear_bit(CONN_REJ_ACT,
&chan->conn_state)) {
- control->final = 0;
- l2cap_retransmit_all(chan, control);
+ local_control.final = 0;
+ l2cap_retransmit_all(chan, &local_control);
l2cap_ertm_send(chan);
}
}
@@ -7297,11 +7341,27 @@ static int l2cap_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
struct sk_buff *skb)
{
+ /* l2cap_reassemble_sdu may free skb, hence invalidate control, so store
+ * the txseq field in advance to use it after l2cap_reassemble_sdu
+ * returns and to avoid the race condition, for example:
+ *
+ * The current thread calls:
+ * l2cap_reassemble_sdu
+ * chan->ops->recv == l2cap_sock_recv_cb
+ * __sock_queue_rcv_skb
+ * Another thread calls:
+ * bt_sock_recvmsg
+ * skb_recv_datagram
+ * skb_free_datagram
+ * Then the current thread tries to access control, but it was freed by
+ * skb_free_datagram.
+ */
+ u16 txseq = control->txseq;
+
BT_DBG("chan %p, control %p, skb %p, state %d", chan, control, skb,
chan->rx_state);
- if (l2cap_classify_txseq(chan, control->txseq) ==
- L2CAP_TXSEQ_EXPECTED) {
+ if (l2cap_classify_txseq(chan, txseq) == L2CAP_TXSEQ_EXPECTED) {
l2cap_pass_to_tx(chan, control);
BT_DBG("buffer_seq %u->%u", chan->buffer_seq,
@@ -7324,8 +7384,8 @@ static int l2cap_stream_rx(struct l2cap_chan *chan, struct l2cap_ctrl *control,
}
}
- chan->last_acked_seq = control->txseq;
- chan->expected_tx_seq = __next_seq(chan, control->txseq);
+ chan->last_acked_seq = txseq;
+ chan->expected_tx_seq = __next_seq(chan, txseq);
return 0;
}
@@ -7581,6 +7641,7 @@ static void l2cap_data_channel(struct l2cap_conn *conn, u16 cid,
return;
}
+ l2cap_chan_hold(chan);
l2cap_chan_lock(chan);
} else {
BT_DBG("unknown cid 0x%4.4x", cid);
@@ -8426,9 +8487,8 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
* expected length.
*/
if (skb->len < L2CAP_LEN_SIZE) {
- if (l2cap_recv_frag(conn, skb, conn->mtu) < 0)
- goto drop;
- return;
+ l2cap_recv_frag(conn, skb, conn->mtu);
+ break;
}
len = get_unaligned_le16(skb->data) + L2CAP_HDR_SIZE;
@@ -8472,7 +8532,7 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
/* Header still could not be read just continue */
if (conn->rx_skb->len < L2CAP_LEN_SIZE)
- return;
+ break;
}
if (skb->len > conn->rx_len) {
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 5aeb3646e74c..d087fd4c784a 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1332,7 +1332,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
if (data[IFLA_BR_FDB_FLUSH]) {
struct net_bridge_fdb_flush_desc desc = {
- .flags_mask = BR_FDB_STATIC
+ .flags_mask = BIT(BR_FDB_STATIC)
};
br_fdb_flush(br, &desc);
diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c
index 612e367fff20..ea733542244c 100644
--- a/net/bridge/br_sysfs_br.c
+++ b/net/bridge/br_sysfs_br.c
@@ -345,7 +345,7 @@ static int set_flush(struct net_bridge *br, unsigned long val,
struct netlink_ext_ack *extack)
{
struct net_bridge_fdb_flush_desc desc = {
- .flags_mask = BR_FDB_STATIC
+ .flags_mask = BIT(BR_FDB_STATIC)
};
br_fdb_flush(br, &desc);
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index d7d86c944d76..55f29c9f9e08 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -342,10 +342,12 @@ static void j1939_session_skb_drop_old(struct j1939_session *session)
__skb_unlink(do_skb, &session->skb_queue);
/* drop ref taken in j1939_session_skb_queue() */
skb_unref(do_skb);
+ spin_unlock_irqrestore(&session->skb_queue.lock, flags);
kfree_skb(do_skb);
+ } else {
+ spin_unlock_irqrestore(&session->skb_queue.lock, flags);
}
- spin_unlock_irqrestore(&session->skb_queue.lock, flags);
}
void j1939_session_skb_queue(struct j1939_session *session,
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 3c4786b99907..a77a85e357e0 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -409,7 +409,7 @@ static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev,
write_lock_bh(&tbl->lock);
neigh_flush_dev(tbl, dev, skip_perm);
pneigh_ifdown_and_unlock(tbl, dev);
- pneigh_queue_purge(&tbl->proxy_queue, dev_net(dev));
+ pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL);
if (skb_queue_empty_lockless(&tbl->proxy_queue))
del_timer_sync(&tbl->proxy_timer);
return 0;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 0ec2f5906a27..f64654df71a2 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -117,6 +117,7 @@ static int net_assign_generic(struct net *net, unsigned int id, void *data)
static int ops_init(const struct pernet_operations *ops, struct net *net)
{
+ struct net_generic *ng;
int err = -ENOMEM;
void *data = NULL;
@@ -135,7 +136,13 @@ static int ops_init(const struct pernet_operations *ops, struct net *net)
if (!err)
return 0;
+ if (ops->id && ops->size) {
cleanup:
+ ng = rcu_dereference_protected(net->gen,
+ lockdep_is_held(&pernet_ops_rwsem));
+ ng->ptr[*ops->id] = NULL;
+ }
+
kfree(data);
out:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1d9719e72f9d..d1a3fa6f3f12 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3971,7 +3971,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page,
} else if (i < MAX_SKB_FRAGS) {
skb_zcopy_downgrade_managed(skb);
get_page(page);
- skb_fill_page_desc(skb, i, page, offset, size);
+ skb_fill_page_desc_noacc(skb, i, page, offset, size);
} else {
return -EMSGSIZE;
}
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index af0e2c0394ac..e504a18fc125 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1409,9 +1409,9 @@ static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp,
static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master,
const char *user_protocol)
{
+ const struct dsa_device_ops *tag_ops = NULL;
struct dsa_switch *ds = dp->ds;
struct dsa_switch_tree *dst = ds->dst;
- const struct dsa_device_ops *tag_ops;
enum dsa_tag_protocol default_proto;
/* Find out which protocol the switch would prefer. */
@@ -1434,10 +1434,17 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master,
}
tag_ops = dsa_find_tagger_by_name(user_protocol);
- } else {
- tag_ops = dsa_tag_driver_get(default_proto);
+ if (IS_ERR(tag_ops)) {
+ dev_warn(ds->dev,
+ "Failed to find a tagging driver for protocol %s, using default\n",
+ user_protocol);
+ tag_ops = NULL;
+ }
}
+ if (!tag_ops)
+ tag_ops = dsa_tag_driver_get(default_proto);
+
if (IS_ERR(tag_ops)) {
if (PTR_ERR(tag_ops) == -ENOPROTOOPT)
return -EPROBE_DEFER;
diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c
index 1c94bb8ea03f..49c0a2a77f02 100644
--- a/net/ethtool/eeprom.c
+++ b/net/ethtool/eeprom.c
@@ -124,7 +124,7 @@ static int eeprom_prepare_data(const struct ethnl_req_info *req_base,
if (ret)
goto err_free;
- ret = get_module_eeprom_by_page(dev, &page_data, info->extack);
+ ret = get_module_eeprom_by_page(dev, &page_data, info ? info->extack : NULL);
if (ret < 0)
goto err_ops;
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 5a471e115b66..e8683e485dc9 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
if (ret < 0)
return ret;
- ret = pse_get_pse_attributes(dev, info->extack, data);
+ ret = pse_get_pse_attributes(dev, info ? info->extack : NULL, data);
ethnl_ops_complete(dev);
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 6e55fae4c686..1fa2fe041ec0 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -502,8 +502,10 @@ static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len)
if (err < 0)
goto out;
- if (addr->family != AF_IEEE802154)
+ if (addr->family != AF_IEEE802154) {
+ err = -EINVAL;
goto out;
+ }
ieee802154_addr_from_sa(&haddr, &addr->addr);
dev = ieee802154_get_dev(sock_net(sk), &haddr);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3dd02396517d..4728087c42a5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -754,6 +754,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags,
(TCPF_ESTABLISHED | TCPF_SYN_RECV |
TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+ if (test_bit(SOCK_SUPPORT_ZC, &sock->flags))
+ set_bit(SOCK_SUPPORT_ZC, &newsock->flags);
sock_graft(sk2, newsock);
newsock->state = SS_CONNECTED;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 943edf4ad4db..f361d3d56be2 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
dev_match = dev_match || (res.type == RTN_LOCAL &&
dev == net->loopback_dev);
if (dev_match) {
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
@@ -401,7 +401,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
ret = 0;
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
}
return ret;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index e9a7f70a54df..f721c308248b 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
nh->fib_nh_dev = in_dev->dev;
netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
- nh->fib_nh_scope = RT_SCOPE_LINK;
+ nh->fib_nh_scope = RT_SCOPE_HOST;
if (!netif_carrier_ok(nh->fib_nh_dev))
nh->fib_nh_flags |= RTNH_F_LINKDOWN;
err = 0;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 853a75a8fbaf..d8ef05347fd9 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2534,7 +2534,7 @@ static int nh_create_ipv4(struct net *net, struct nexthop *nh,
if (!err) {
nh->nh_flags = fib_nh->fib_nh_flags;
fib_info_update_nhc_saddr(net, &fib_nh->nh_common,
- fib_nh->fib_nh_scope);
+ !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1);
} else {
fib_nh_release(net, fib_nh);
}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index a1626afe87a1..c501c329b1db 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -607,7 +607,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
} else {
sk->sk_write_space = psock->saved_write_space;
/* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
}
return 0;
}
@@ -620,7 +620,7 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
}
/* Pairs with lockless read in sk_clone_lock() */
- WRITE_ONCE(sk->sk_prot, &tcp_bpf_prots[family][config]);
+ sock_replace_proto(sk, &tcp_bpf_prots[family][config]);
return 0;
}
EXPORT_SYMBOL_GPL(tcp_bpf_update_proto);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index bc2ea12221f9..0640453fce54 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2192,7 +2192,8 @@ void tcp_enter_loss(struct sock *sk)
*/
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
- if (flag & FLAG_SACK_RENEGING) {
+ if (flag & FLAG_SACK_RENEGING &&
+ flag & FLAG_SND_UNA_ADVANCED) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
msecs_to_jiffies(10));
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7a250ef9d1b7..87d440f47a70 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1874,11 +1874,13 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
__skb_push(skb, hdrlen);
no_coalesce:
+ limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+
/* Only socket owner can try to collapse/prune rx queues
* to reduce memory overhead, so add a little headroom here.
* Few sockets backlog are possibly concurrently non empty.
*/
- limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf) + 64*1024;
+ limit += 64 * 1024;
if (unlikely(sk_add_backlog(sk, skb, limit))) {
bh_unlock_sock(sk);
diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c
index 7c27aa629af1..9ae50b1bd844 100644
--- a/net/ipv4/tcp_ulp.c
+++ b/net/ipv4/tcp_ulp.c
@@ -136,6 +136,9 @@ static int __tcp_set_ulp(struct sock *sk, const struct tcp_ulp_ops *ulp_ops)
if (icsk->icsk_ulp_ops)
goto out_err;
+ if (sk->sk_socket)
+ clear_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
+
err = ulp_ops->init(sk);
if (err)
goto out_err;
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index ff15918b7bdc..e5dc91d0e079 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -141,14 +141,14 @@ int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
if (restore) {
sk->sk_write_space = psock->saved_write_space;
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
return 0;
}
if (sk->sk_family == AF_INET6)
udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
- WRITE_ONCE(sk->sk_prot, &udp_bpf_prots[family]);
+ sock_replace_proto(sk, &udp_bpf_prots[family]);
return 0;
}
EXPORT_SYMBOL_GPL(udp_bpf_update_proto);
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 48b4ff0294f6..c035a96fba3a 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1175,14 +1175,16 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
dev->needed_headroom = dst_len;
if (set_mtu) {
- dev->mtu = rt->dst.dev->mtu - t_hlen;
+ int mtu = rt->dst.dev->mtu - t_hlen;
+
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu -= 8;
+ mtu -= 8;
if (dev->type == ARPHRD_ETHER)
- dev->mtu -= ETH_HLEN;
+ mtu -= ETH_HLEN;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
}
}
ip6_rt_put(rt);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index cc5d5e75b658..2fb4c6ad7243 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1450,8 +1450,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
struct net_device *tdev = NULL;
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
- unsigned int mtu;
int t_hlen;
+ int mtu;
__dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
@@ -1498,12 +1498,13 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
dev->hard_header_len = tdev->hard_header_len + t_hlen;
mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
- dev->mtu = mtu - t_hlen;
+ mtu = mtu - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
- dev->mtu -= 8;
+ mtu -= 8;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
}
}
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 69252eb462b2..2f355f0ec32a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6555,10 +6555,16 @@ static void __net_exit ip6_route_net_exit(struct net *net)
static int __net_init ip6_route_net_init_late(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_create_net("ipv6_route", 0, net->proc_net, &ipv6_route_seq_ops,
- sizeof(struct ipv6_route_iter));
- proc_create_net_single("rt6_stats", 0444, net->proc_net,
- rt6_stats_seq_show, NULL);
+ if (!proc_create_net("ipv6_route", 0, net->proc_net,
+ &ipv6_route_seq_ops,
+ sizeof(struct ipv6_route_iter)))
+ return -ENOMEM;
+
+ if (!proc_create_net_single("rt6_stats", 0444, net->proc_net,
+ rt6_stats_seq_show, NULL)) {
+ remove_proc_entry("ipv6_route", net->proc_net);
+ return -ENOMEM;
+ }
#endif
return 0;
}
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d27683e3fc97..5703d3cbea9b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1124,10 +1124,12 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
if (tdev && !netif_is_l3_master(tdev)) {
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+ int mtu;
- dev->mtu = tdev->mtu - t_hlen;
- if (dev->mtu < IPV6_MIN_MTU)
- dev->mtu = IPV6_MIN_MTU;
+ mtu = tdev->mtu - t_hlen;
+ if (mtu < IPV6_MIN_MTU)
+ mtu = IPV6_MIN_MTU;
+ WRITE_ONCE(dev->mtu, mtu);
}
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 129ec5a9b0eb..bc65e5b7195b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -66,6 +66,7 @@ int udpv6_init_sock(struct sock *sk)
{
skb_queue_head_init(&udp_sk(sk)->reader_queue);
sk->sk_destruct = udpv6_destruct_sock;
+ set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
return 0;
}
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 27725464ec08..a5004228111d 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -162,7 +162,8 @@ static void kcm_rcv_ready(struct kcm_sock *kcm)
/* Buffer limit is okay now, add to ready list */
list_add_tail(&kcm->wait_rx_list,
&kcm->mux->kcm_rx_waiters);
- kcm->rx_wait = true;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_wait, true);
}
static void kcm_rfree(struct sk_buff *skb)
@@ -178,7 +179,7 @@ static void kcm_rfree(struct sk_buff *skb)
/* For reading rx_wait and rx_psock without holding lock */
smp_mb__after_atomic();
- if (!kcm->rx_wait && !kcm->rx_psock &&
+ if (!READ_ONCE(kcm->rx_wait) && !READ_ONCE(kcm->rx_psock) &&
sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) {
spin_lock_bh(&mux->rx_lock);
kcm_rcv_ready(kcm);
@@ -237,7 +238,8 @@ try_again:
if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
/* Should mean socket buffer full */
list_del(&kcm->wait_rx_list);
- kcm->rx_wait = false;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_wait, false);
/* Commit rx_wait to read in kcm_free */
smp_wmb();
@@ -280,10 +282,12 @@ static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock,
kcm = list_first_entry(&mux->kcm_rx_waiters,
struct kcm_sock, wait_rx_list);
list_del(&kcm->wait_rx_list);
- kcm->rx_wait = false;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_wait, false);
psock->rx_kcm = kcm;
- kcm->rx_psock = psock;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_psock, psock);
spin_unlock_bh(&mux->rx_lock);
@@ -310,7 +314,8 @@ static void unreserve_rx_kcm(struct kcm_psock *psock,
spin_lock_bh(&mux->rx_lock);
psock->rx_kcm = NULL;
- kcm->rx_psock = NULL;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_psock, NULL);
/* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with
* kcm_rfree
@@ -834,7 +839,7 @@ static ssize_t kcm_sendpage(struct socket *sock, struct page *page,
}
get_page(page);
- skb_fill_page_desc(skb, i, page, offset, size);
+ skb_fill_page_desc_noacc(skb, i, page, offset, size);
skb_shinfo(skb)->flags |= SKBFL_SHARED_FRAG;
coalesced:
@@ -1240,7 +1245,8 @@ static void kcm_recv_disable(struct kcm_sock *kcm)
if (!kcm->rx_psock) {
if (kcm->rx_wait) {
list_del(&kcm->wait_rx_list);
- kcm->rx_wait = false;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_wait, false);
}
requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
@@ -1793,7 +1799,8 @@ static void kcm_done(struct kcm_sock *kcm)
if (kcm->rx_wait) {
list_del(&kcm->wait_rx_list);
- kcm->rx_wait = false;
+ /* paired with lockless reads in kcm_rfree() */
+ WRITE_ONCE(kcm->rx_wait, false);
}
/* Move any pending receive messages to other kcm sockets */
requeue_rx_msgs(mux, &sk->sk_receive_queue);
diff --git a/net/mac802154/rx.c b/net/mac802154/rx.c
index c439125ef2b9..726b47a4611b 100644
--- a/net/mac802154/rx.c
+++ b/net/mac802154/rx.c
@@ -132,7 +132,7 @@ static int
ieee802154_parse_frame_start(struct sk_buff *skb, struct ieee802154_hdr *hdr)
{
int hlen;
- struct ieee802154_mac_cb *cb = mac_cb_init(skb);
+ struct ieee802154_mac_cb *cb = mac_cb(skb);
skb_reset_mac_header(skb);
@@ -294,8 +294,9 @@ void
ieee802154_rx_irqsafe(struct ieee802154_hw *hw, struct sk_buff *skb, u8 lqi)
{
struct ieee802154_local *local = hw_to_local(hw);
+ struct ieee802154_mac_cb *cb = mac_cb_init(skb);
- mac_cb(skb)->lqi = lqi;
+ cb->lqi = lqi;
skb->pkt_type = IEEE802154_RX_MSG;
skb_queue_tail(&local->skb_queue, skb);
tasklet_schedule(&local->tasklet);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index f599ad44ed24..b6dc6e260334 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1673,6 +1673,37 @@ static void mptcp_set_nospace(struct sock *sk)
set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
}
+static int mptcp_sendmsg_fastopen(struct sock *sk, struct sock *ssk, struct msghdr *msg,
+ size_t len, int *copied_syn)
+{
+ unsigned int saved_flags = msg->msg_flags;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ int ret;
+
+ lock_sock(ssk);
+ msg->msg_flags |= MSG_DONTWAIT;
+ msk->connect_flags = O_NONBLOCK;
+ msk->is_sendmsg = 1;
+ ret = tcp_sendmsg_fastopen(ssk, msg, copied_syn, len, NULL);
+ msk->is_sendmsg = 0;
+ msg->msg_flags = saved_flags;
+ release_sock(ssk);
+
+ /* do the blocking bits of inet_stream_connect outside the ssk socket lock */
+ if (ret == -EINPROGRESS && !(msg->msg_flags & MSG_DONTWAIT)) {
+ ret = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+ msg->msg_namelen, msg->msg_flags, 1);
+
+ /* Keep the same behaviour of plain TCP: zero the copied bytes in
+ * case of any error, except timeout or signal
+ */
+ if (ret && ret != -EINPROGRESS && ret != -ERESTARTSYS && ret != -EINTR)
+ *copied_syn = 0;
+ }
+
+ return ret;
+}
+
static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1693,23 +1724,14 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ssock = __mptcp_nmpc_socket(msk);
if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) {
- struct sock *ssk = ssock->sk;
int copied_syn = 0;
- lock_sock(ssk);
-
- ret = tcp_sendmsg_fastopen(ssk, msg, &copied_syn, len, NULL);
+ ret = mptcp_sendmsg_fastopen(sk, ssock->sk, msg, len, &copied_syn);
copied += copied_syn;
- if (ret == -EINPROGRESS && copied_syn > 0) {
- /* reflect the new state on the MPTCP socket */
- inet_sk_state_store(sk, inet_sk_state_load(ssk));
- release_sock(ssk);
+ if (ret == -EINPROGRESS && copied_syn > 0)
goto out;
- } else if (ret) {
- release_sock(ssk);
+ else if (ret)
goto do_error;
- }
- release_sock(ssk);
}
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
@@ -2952,7 +2974,7 @@ static void mptcp_close(struct sock *sk, long timeout)
sock_put(sk);
}
-static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
+void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
{
#if IS_ENABLED(CONFIG_MPTCP_IPV6)
const struct ipv6_pinfo *ssk6 = inet6_sk(ssk);
@@ -3507,10 +3529,73 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return put_user(answ, (int __user *)arg);
}
+static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
+ struct mptcp_subflow_context *subflow)
+{
+ subflow->request_mptcp = 0;
+ __mptcp_do_fallback(msk);
+}
+
+static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct socket *ssock;
+ int err = -EINVAL;
+
+ ssock = __mptcp_nmpc_socket(msk);
+ if (!ssock)
+ return -EINVAL;
+
+ mptcp_token_destroy(msk);
+ inet_sk_state_store(sk, TCP_SYN_SENT);
+ subflow = mptcp_subflow_ctx(ssock->sk);
+#ifdef CONFIG_TCP_MD5SIG
+ /* no MPTCP if MD5SIG is enabled on this socket or we may run out of
+ * TCP option space.
+ */
+ if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
+ mptcp_subflow_early_fallback(msk, subflow);
+#endif
+ if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) {
+ MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT);
+ mptcp_subflow_early_fallback(msk, subflow);
+ }
+ if (likely(!__mptcp_check_fallback(msk)))
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVE);
+
+ /* if reaching here via the fastopen/sendmsg path, the caller already
+ * acquired the subflow socket lock, too.
+ */
+ if (msk->is_sendmsg)
+ err = __inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags, 1);
+ else
+ err = inet_stream_connect(ssock, uaddr, addr_len, msk->connect_flags);
+ inet_sk(sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
+
+ /* on successful connect, the msk state will be moved to established by
+ * subflow_finish_connect()
+ */
+ if (unlikely(err && err != -EINPROGRESS)) {
+ inet_sk_state_store(sk, inet_sk_state_load(ssock->sk));
+ return err;
+ }
+
+ mptcp_copy_inaddrs(sk, ssock->sk);
+
+ /* unblocking connect, mptcp-level inet_stream_connect will error out
+ * without changing the socket state, update it here.
+ */
+ if (err == -EINPROGRESS)
+ sk->sk_socket->state = ssock->state;
+ return err;
+}
+
static struct proto mptcp_prot = {
.name = "MPTCP",
.owner = THIS_MODULE,
.init = mptcp_init_sock,
+ .connect = mptcp_connect,
.disconnect = mptcp_disconnect,
.close = mptcp_close,
.accept = mptcp_accept,
@@ -3562,78 +3647,16 @@ unlock:
return err;
}
-static void mptcp_subflow_early_fallback(struct mptcp_sock *msk,
- struct mptcp_subflow_context *subflow)
-{
- subflow->request_mptcp = 0;
- __mptcp_do_fallback(msk);
-}
-
static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags)
{
- struct mptcp_sock *msk = mptcp_sk(sock->sk);
- struct mptcp_subflow_context *subflow;
- struct socket *ssock;
- int err = -EINVAL;
+ int ret;
lock_sock(sock->sk);
- if (uaddr) {
- if (addr_len < sizeof(uaddr->sa_family))
- goto unlock;
-
- if (uaddr->sa_family == AF_UNSPEC) {
- err = mptcp_disconnect(sock->sk, flags);
- sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
- goto unlock;
- }
- }
-
- if (sock->state != SS_UNCONNECTED && msk->subflow) {
- /* pending connection or invalid state, let existing subflow
- * cope with that
- */
- ssock = msk->subflow;
- goto do_connect;
- }
-
- ssock = __mptcp_nmpc_socket(msk);
- if (!ssock)
- goto unlock;
-
- mptcp_token_destroy(msk);
- inet_sk_state_store(sock->sk, TCP_SYN_SENT);
- subflow = mptcp_subflow_ctx(ssock->sk);
-#ifdef CONFIG_TCP_MD5SIG
- /* no MPTCP if MD5SIG is enabled on this socket or we may run out of
- * TCP option space.
- */
- if (rcu_access_pointer(tcp_sk(ssock->sk)->md5sig_info))
- mptcp_subflow_early_fallback(msk, subflow);
-#endif
- if (subflow->request_mptcp && mptcp_token_new_connect(ssock->sk)) {
- MPTCP_INC_STATS(sock_net(ssock->sk), MPTCP_MIB_TOKENFALLBACKINIT);
- mptcp_subflow_early_fallback(msk, subflow);
- }
- if (likely(!__mptcp_check_fallback(msk)))
- MPTCP_INC_STATS(sock_net(sock->sk), MPTCP_MIB_MPCAPABLEACTIVE);
-
-do_connect:
- err = ssock->ops->connect(ssock, uaddr, addr_len, flags);
- inet_sk(sock->sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
- sock->state = ssock->state;
-
- /* on successful connect, the msk state will be moved to established by
- * subflow_finish_connect()
- */
- if (!err || err == -EINPROGRESS)
- mptcp_copy_inaddrs(sock->sk, ssock->sk);
- else
- inet_sk_state_store(sock->sk, inet_sk_state_load(ssock->sk));
-
-unlock:
+ mptcp_sk(sock->sk)->connect_flags = flags;
+ ret = __inet_stream_connect(sock, uaddr, addr_len, flags, 0);
release_sock(sock->sk);
- return err;
+ return ret;
}
static int mptcp_listen(struct socket *sock, int backlog)
@@ -3699,7 +3722,6 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
if (mptcp_is_fully_established(newsk))
mptcp_pm_fully_established(msk, msk->first, GFP_KERNEL);
- mptcp_copy_inaddrs(newsk, msk->first);
mptcp_rcv_space_init(msk, msk->first);
mptcp_propagate_sndbuf(newsk, msk->first);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c0b5b4628f65..6a09ab99a12d 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -285,7 +285,9 @@ struct mptcp_sock {
u8 mpc_endpoint_id;
u8 recvmsg_inq:1,
cork:1,
- nodelay:1;
+ nodelay:1,
+ is_sendmsg:1;
+ int connect_flags;
struct work_struct work;
struct sk_buff *ooo_last_skb;
struct rb_root out_of_order_queue;
@@ -599,6 +601,7 @@ int mptcp_is_checksum_enabled(const struct net *net);
int mptcp_allow_join_id0(const struct net *net);
unsigned int mptcp_stale_loss_cnt(const struct net *net);
int mptcp_get_pm_type(const struct net *net);
+void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk);
void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
struct mptcp_options_received *mp_opt);
bool __mptcp_retransmit_pending_data(struct sock *sk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 07dd23d0fe04..02a54d59697b 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -723,6 +723,8 @@ create_child:
goto dispose_child;
}
+ if (new_msk)
+ mptcp_copy_inaddrs(new_msk, child);
subflow_drop_ctx(child);
goto out;
}
@@ -750,6 +752,11 @@ create_child:
ctx->conn = new_msk;
new_msk = NULL;
+ /* set msk addresses early to ensure mptcp_pm_get_local_id()
+ * uses the correct data
+ */
+ mptcp_copy_inaddrs(ctx->conn, child);
+
/* with OoO packets we can reach here without ingress
* mpc option
*/
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 6e391308431d..3adc291d9ce1 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -42,31 +42,8 @@
#define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE)
/* Max muber of elements in the array block when tuned */
#define AHASH_MAX_TUNED 64
-
#define AHASH_MAX(h) ((h)->bucketsize)
-/* Max number of elements can be tuned */
-#ifdef IP_SET_HASH_WITH_MULTI
-static u8
-tune_bucketsize(u8 curr, u32 multi)
-{
- u32 n;
-
- if (multi < curr)
- return curr;
-
- n = curr + AHASH_INIT_SIZE;
- /* Currently, at listing one hash bucket must fit into a message.
- * Therefore we have a hard limit here.
- */
- return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
-}
-#define TUNE_BUCKETSIZE(h, multi) \
- ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
-#else
-#define TUNE_BUCKETSIZE(h, multi)
-#endif
-
/* A hash bucket */
struct hbucket {
struct rcu_head rcu; /* for call_rcu */
@@ -936,7 +913,12 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
goto set_full;
/* Create a new slot */
if (n->pos >= n->size) {
- TUNE_BUCKETSIZE(h, multi);
+#ifdef IP_SET_HASH_WITH_MULTI
+ if (h->bucketsize >= AHASH_MAX_TUNED)
+ goto set_full;
+ else if (h->bucketsize < multi)
+ h->bucketsize += AHASH_INIT_SIZE;
+#endif
if (n->size >= AHASH_MAX(h)) {
/* Trigger rehashing */
mtype_data_next(&h->next, d);
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index f9b16f2b2219..fdacbc3c15be 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -599,13 +599,19 @@ static const struct seq_operations ip_vs_app_seq_ops = {
int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs)
{
INIT_LIST_HEAD(&ipvs->app_list);
- proc_create_net("ip_vs_app", 0, ipvs->net->proc_net, &ip_vs_app_seq_ops,
- sizeof(struct seq_net_private));
+#ifdef CONFIG_PROC_FS
+ if (!proc_create_net("ip_vs_app", 0, ipvs->net->proc_net,
+ &ip_vs_app_seq_ops,
+ sizeof(struct seq_net_private)))
+ return -ENOMEM;
+#endif
return 0;
}
void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs)
{
unregister_ip_vs_app(ipvs, NULL /* all */);
+#ifdef CONFIG_PROC_FS
remove_proc_entry("ip_vs_app", ipvs->net->proc_net);
+#endif
}
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 8c04bb57dd6f..13534e02346c 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1265,8 +1265,8 @@ static inline int todrop_entry(struct ip_vs_conn *cp)
* The drop rate array needs tuning for real environments.
* Called from timer bh only => no locking
*/
- static const char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8};
- static char todrop_counter[9] = {0};
+ static const signed char todrop_rate[9] = {0, 1, 2, 3, 4, 5, 6, 7, 8};
+ static signed char todrop_counter[9] = {0};
int i;
/* if the conn entry hasn't lasted for 60 seconds, don't drop it.
@@ -1447,20 +1447,36 @@ int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs)
{
atomic_set(&ipvs->conn_count, 0);
- proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net,
- &ip_vs_conn_seq_ops, sizeof(struct ip_vs_iter_state));
- proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net,
- &ip_vs_conn_sync_seq_ops,
- sizeof(struct ip_vs_iter_state));
+#ifdef CONFIG_PROC_FS
+ if (!proc_create_net("ip_vs_conn", 0, ipvs->net->proc_net,
+ &ip_vs_conn_seq_ops,
+ sizeof(struct ip_vs_iter_state)))
+ goto err_conn;
+
+ if (!proc_create_net("ip_vs_conn_sync", 0, ipvs->net->proc_net,
+ &ip_vs_conn_sync_seq_ops,
+ sizeof(struct ip_vs_iter_state)))
+ goto err_conn_sync;
+#endif
+
return 0;
+
+#ifdef CONFIG_PROC_FS
+err_conn_sync:
+ remove_proc_entry("ip_vs_conn", ipvs->net->proc_net);
+err_conn:
+ return -ENOMEM;
+#endif
}
void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs)
{
/* flush all the connection entries first */
ip_vs_conn_flush(ipvs);
+#ifdef CONFIG_PROC_FS
remove_proc_entry("ip_vs_conn", ipvs->net->proc_net);
remove_proc_entry("ip_vs_conn_sync", ipvs->net->proc_net);
+#endif
}
int __init ip_vs_conn_init(void)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 18319a6e6806..e29e4ccb5c5a 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1152,7 +1152,16 @@ static int __init nf_nat_init(void)
WARN_ON(nf_nat_hook != NULL);
RCU_INIT_POINTER(nf_nat_hook, &nat_hook);
- return register_nf_nat_bpf();
+ ret = register_nf_nat_bpf();
+ if (ret < 0) {
+ RCU_INIT_POINTER(nf_nat_hook, NULL);
+ nf_ct_helper_expectfn_unregister(&follow_master_nat);
+ synchronize_net();
+ unregister_pernet_subsys(&nat_net_ops);
+ kvfree(nf_nat_bysource);
+ }
+
+ return ret;
}
static void __exit nf_nat_cleanup(void)
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 58d9cbc9ccdc..76bd4d03dbda 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8465,9 +8465,6 @@ static void nft_commit_release(struct nft_trans *trans)
nf_tables_chain_destroy(&trans->ctx);
break;
case NFT_MSG_DELRULE:
- if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)
- nft_flow_rule_destroy(nft_trans_flow_rule(trans));
-
nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans));
break;
case NFT_MSG_DELSET:
@@ -8973,6 +8970,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
nft_rule_expr_deactivate(&trans->ctx,
nft_trans_rule(trans),
NFT_TRANS_COMMIT);
+
+ if (trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD)
+ nft_flow_rule_destroy(nft_trans_flow_rule(trans));
break;
case NFT_MSG_NEWSET:
nft_clear(net, nft_trans_set(trans));
@@ -10030,6 +10030,8 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
nft_net = nft_pernet(net);
deleted = 0;
mutex_lock(&nft_net->commit_mutex);
+ if (!list_empty(&nf_tables_destroy_list))
+ rcu_barrier();
again:
list_for_each_entry(table, &nft_net->tables, list) {
if (nft_table_has_owner(table) &&
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 088244f9d838..4edd899aeb9b 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -173,10 +173,10 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = {
[NFTA_PAYLOAD_SREG] = { .type = NLA_U32 },
[NFTA_PAYLOAD_DREG] = { .type = NLA_U32 },
[NFTA_PAYLOAD_BASE] = { .type = NLA_U32 },
- [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255),
- [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX_BE(NLA_U32, 255),
+ [NFTA_PAYLOAD_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255),
+ [NFTA_PAYLOAD_LEN] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 },
- [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX_BE(NLA_U32, 255),
+ [NFTA_PAYLOAD_CSUM_OFFSET] = NLA_POLICY_MAX(NLA_BE32, 255),
[NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 },
};
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 39b7c00e4cef..3e16527beb91 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -78,10 +78,29 @@ static unsigned long mc_group_start = 0x3 | BIT(GENL_ID_CTRL) |
static unsigned long *mc_groups = &mc_group_start;
static unsigned long mc_groups_longs = 1;
+/* We need the last attribute with non-zero ID therefore a 2-entry array */
+static struct nla_policy genl_policy_reject_all[] = {
+ { .type = NLA_REJECT },
+ { .type = NLA_REJECT },
+};
+
static int genl_ctrl_event(int event, const struct genl_family *family,
const struct genl_multicast_group *grp,
int grp_id);
+static void
+genl_op_fill_in_reject_policy(const struct genl_family *family,
+ struct genl_ops *op)
+{
+ BUILD_BUG_ON(ARRAY_SIZE(genl_policy_reject_all) - 1 != 1);
+
+ if (op->policy || op->cmd < family->resv_start_op)
+ return;
+
+ op->policy = genl_policy_reject_all;
+ op->maxattr = 1;
+}
+
static const struct genl_family *genl_family_find_byid(unsigned int id)
{
return idr_find(&genl_fam_idr, id);
@@ -113,6 +132,8 @@ static void genl_op_from_full(const struct genl_family *family,
op->maxattr = family->maxattr;
if (!op->policy)
op->policy = family->policy;
+
+ genl_op_fill_in_reject_policy(family, op);
}
static int genl_get_cmd_full(u32 cmd, const struct genl_family *family,
@@ -142,6 +163,8 @@ static void genl_op_from_small(const struct genl_family *family,
op->maxattr = family->maxattr;
op->policy = family->policy;
+
+ genl_op_fill_in_reject_policy(family, op);
}
static int genl_get_cmd_small(u32 cmd, const struct genl_family *family,
@@ -357,6 +380,8 @@ static int genl_validate_ops(const struct genl_family *family)
genl_get_cmd_by_index(i, family, &op);
if (op.dumpit == NULL && op.doit == NULL)
return -EINVAL;
+ if (WARN_ON(op.cmd >= family->resv_start_op && op.validate))
+ return -EINVAL;
for (j = i + 1; j < genl_get_cmd_cnt(family); j++) {
struct genl_ops op2;
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index c8a9075ddd0a..8b84869eb2ac 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1616,7 +1616,8 @@ static void ovs_dp_reset_user_features(struct sk_buff *skb,
if (IS_ERR(dp))
return;
- WARN(dp->user_features, "Dropping previously announced user features\n");
+ pr_warn("%s: Dropping previously announced user features\n",
+ ovs_dp_name(dp));
dp->user_features = 0;
}
@@ -2543,6 +2544,7 @@ struct genl_family dp_vport_genl_family __ro_after_init = {
.parallel_ops = true,
.small_ops = dp_vport_genl_ops,
.n_small_ops = ARRAY_SIZE(dp_vport_genl_ops),
+ .resv_start_op = OVS_VPORT_CMD_SET + 1,
.mcgrps = &ovs_dp_vport_multicast_group,
.n_mcgrps = 1,
.module = THIS_MODULE,
diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c
index 8b96a56d3a49..0f77ae8ef944 100644
--- a/net/rose/rose_link.c
+++ b/net/rose/rose_link.c
@@ -236,6 +236,9 @@ void rose_transmit_clear_request(struct rose_neigh *neigh, unsigned int lci, uns
unsigned char *dptr;
int len;
+ if (!neigh->dev)
+ return;
+
len = AX25_BPQ_HEADER_LEN + AX25_MAX_HEADER_LEN + ROSE_MIN_LEN + 3;
if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL)
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index a5a401f93c1a..98129324e157 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -72,6 +72,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
{
struct red_sched_data *q = qdisc_priv(sch);
struct Qdisc *child = q->qdisc;
+ unsigned int len;
int ret;
q->vars.qavg = red_calc_qavg(&q->parms,
@@ -126,9 +127,10 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch,
break;
}
+ len = qdisc_pkt_len(skb);
ret = qdisc_enqueue(skb, child, to_free);
if (likely(ret == NET_XMIT_SUCCESS)) {
- qdisc_qstats_backlog_inc(sch, skb);
+ sch->qstats.backlog += len;
sch->q.qlen++;
} else if (net_xmit_drop_count(ret)) {
q->stats.pdrop++;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 3ccbf3c201cd..e12d4fa5aece 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3380,14 +3380,14 @@ static int __init smc_init(void)
rc = register_pernet_subsys(&smc_net_stat_ops);
if (rc)
- return rc;
+ goto out_pernet_subsys;
smc_ism_init();
smc_clc_init();
rc = smc_nl_init();
if (rc)
- goto out_pernet_subsys;
+ goto out_pernet_subsys_stat;
rc = smc_pnet_init();
if (rc)
@@ -3480,6 +3480,8 @@ out_pnet:
smc_pnet_exit();
out_nl:
smc_nl_exit();
+out_pernet_subsys_stat:
+ unregister_pernet_subsys(&smc_net_stat_ops);
out_pernet_subsys:
unregister_pernet_subsys(&smc_net_ops);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index a31a27816cc0..7bb247c51e2f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1989,7 +1989,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
goto unwrap_failed;
mic.len = len;
mic.data = kmalloc(len, GFP_KERNEL);
- if (!mic.data)
+ if (ZERO_OR_NULL_PTR(mic.data))
goto unwrap_failed;
if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len))
goto unwrap_failed;
diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c
index c65c90ad626a..c1f559892ae8 100644
--- a/net/sunrpc/sysfs.c
+++ b/net/sunrpc/sysfs.c
@@ -518,13 +518,16 @@ void rpc_sysfs_client_setup(struct rpc_clnt *clnt,
struct net *net)
{
struct rpc_sysfs_client *rpc_client;
+ struct rpc_sysfs_xprt_switch *xswitch =
+ (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs;
+
+ if (!xswitch)
+ return;
rpc_client = rpc_sysfs_client_alloc(rpc_sunrpc_client_kobj,
net, clnt->cl_clid);
if (rpc_client) {
char name[] = "switch";
- struct rpc_sysfs_xprt_switch *xswitch =
- (struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs;
int ret;
clnt->cl_sysfs = rpc_client;
@@ -558,6 +561,8 @@ void rpc_sysfs_xprt_switch_setup(struct rpc_xprt_switch *xprt_switch,
rpc_xprt_switch->xprt_switch = xprt_switch;
rpc_xprt_switch->xprt = xprt;
kobject_uevent(&rpc_xprt_switch->kobject, KOBJ_ADD);
+ } else {
+ xprt_switch->xps_sysfs = NULL;
}
}
@@ -569,6 +574,9 @@ void rpc_sysfs_xprt_setup(struct rpc_xprt_switch *xprt_switch,
struct rpc_sysfs_xprt_switch *switch_obj =
(struct rpc_sysfs_xprt_switch *)xprt_switch->xps_sysfs;
+ if (!switch_obj)
+ return;
+
rpc_xprt = rpc_sysfs_xprt_alloc(&switch_obj->kobject, xprt, gfp_flags);
if (rpc_xprt) {
xprt->xprt_sysfs = rpc_xprt;
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 14fd05fd6107..d92ec92f0b71 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -450,12 +450,19 @@ static void tipc_conn_data_ready(struct sock *sk)
static void tipc_topsrv_accept(struct work_struct *work)
{
struct tipc_topsrv *srv = container_of(work, struct tipc_topsrv, awork);
- struct socket *lsock = srv->listener;
- struct socket *newsock;
+ struct socket *newsock, *lsock;
struct tipc_conn *con;
struct sock *newsk;
int ret;
+ spin_lock_bh(&srv->idr_lock);
+ if (!srv->listener) {
+ spin_unlock_bh(&srv->idr_lock);
+ return;
+ }
+ lsock = srv->listener;
+ spin_unlock_bh(&srv->idr_lock);
+
while (1) {
ret = kernel_accept(lsock, &newsock, O_NONBLOCK);
if (ret < 0)
@@ -489,7 +496,7 @@ static void tipc_topsrv_listener_data_ready(struct sock *sk)
read_lock_bh(&sk->sk_callback_lock);
srv = sk->sk_user_data;
- if (srv->listener)
+ if (srv)
queue_work(srv->rcv_wq, &srv->awork);
read_unlock_bh(&sk->sk_callback_lock);
}
@@ -699,8 +706,9 @@ static void tipc_topsrv_stop(struct net *net)
__module_get(lsock->sk->sk_prot_creator->owner);
srv->listener = NULL;
spin_unlock_bh(&srv->idr_lock);
- sock_release(lsock);
+
tipc_topsrv_work_stop(srv);
+ sock_release(lsock);
idr_destroy(&srv->conn_idr);
kfree(srv);
}
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 7cf14c6b1725..e9bf15513961 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -145,12 +145,12 @@ int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool re
if (restore) {
sk->sk_write_space = psock->saved_write_space;
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
return 0;
}
unix_dgram_bpf_check_needs_rebuild(psock->sk_proto);
- WRITE_ONCE(sk->sk_prot, &unix_dgram_bpf_prot);
+ sock_replace_proto(sk, &unix_dgram_bpf_prot);
return 0;
}
@@ -158,12 +158,12 @@ int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool r
{
if (restore) {
sk->sk_write_space = psock->saved_write_space;
- WRITE_ONCE(sk->sk_prot, psock->sk_proto);
+ sock_replace_proto(sk, psock->sk_proto);
return 0;
}
unix_stream_bpf_check_needs_rebuild(psock->sk_proto);
- WRITE_ONCE(sk->sk_prot, &unix_stream_bpf_prot);
+ sock_replace_proto(sk, &unix_stream_bpf_prot);
return 0;
}
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ee418701cdee..884eca7f6743 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1905,8 +1905,11 @@ static int vsock_connectible_wait_data(struct sock *sk,
err = 0;
transport = vsk->transport;
- while ((data = vsock_connectible_has_data(vsk)) == 0) {
+ while (1) {
prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE);
+ data = vsock_connectible_has_data(vsk);
+ if (data != 0)
+ break;
if (sk->sk_err != 0 ||
(sk->sk_shutdown & RCV_SHUTDOWN) ||
@@ -2092,8 +2095,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
const struct vsock_transport *transport;
int err;
- DEFINE_WAIT(wait);
-
sk = sock->sk;
vsk = vsock_sk(sk);
err = 0;
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index 8489a3402eb8..e41dee64d429 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -122,7 +122,7 @@ quiet_cmd_modpost = MODPOST $@
sed 's/ko$$/o/' $(or $(modorder-if-needed), /dev/null) | $(MODPOST) $(modpost-args) -T - $(vmlinux.o-if-present)
targets += $(output-symdump)
-$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(moudle.symvers-if-present) $(MODPOST) FORCE
+$(output-symdump): $(modorder-if-needed) $(vmlinux.o-if-present) $(module.symvers-if-present) $(MODPOST) FORCE
$(call if_changed,modpost)
__modpost: $(output-symdump)
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 62b6313f51c8..109325f31bef 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -722,8 +722,8 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
if (!expr_eq(prop->menu->dep, prop->visible.expr))
get_dep_str(r, prop->visible.expr, " Visible if: ");
- menu = prop->menu->parent;
- for (i = 0; menu && i < 8; menu = menu->parent) {
+ menu = prop->menu;
+ for (i = 0; menu != &rootmenu && i < 8; menu = menu->parent) {
bool accessible = menu_is_visible(menu);
submenu[i++] = menu;
@@ -733,16 +733,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
if (head && location) {
jump = xmalloc(sizeof(struct jump_key));
- if (menu_is_visible(prop->menu)) {
- /*
- * There is not enough room to put the hint at the
- * beginning of the "Prompt" line. Put the hint on the
- * last "Location" line even when it would belong on
- * the former.
- */
- jump->target = prop->menu;
- } else
- jump->target = location;
+ jump->target = location;
if (list_empty(head))
jump->index = 0;
@@ -758,13 +749,7 @@ static void get_prompt_str(struct gstr *r, struct property *prop,
menu = submenu[i];
if (jump && menu == location)
jump->offset = strlen(r->s);
-
- if (menu == &rootmenu)
- /* The real rootmenu prompt is ugly */
- str_printf(r, "%*cMain menu", j, ' ');
- else
- str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu));
-
+ str_printf(r, "%*c-> %s", j, ' ', menu_get_prompt(menu));
if (menu->sym) {
str_printf(r, " (%s [=%s])", menu->sym->name ?
menu->sym->name : "<choice>",
diff --git a/security/commoncap.c b/security/commoncap.c
index 5fc8986c3c77..bc751fa5adad 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -401,8 +401,10 @@ int cap_inode_getsecurity(struct user_namespace *mnt_userns,
&tmpbuf, size, GFP_NOFS);
dput(dentry);
- if (ret < 0 || !tmpbuf)
- return ret;
+ if (ret < 0 || !tmpbuf) {
+ size = ret;
+ goto out_free;
+ }
fs_ns = inode->i_sb->s_user_ns;
cap = (struct vfs_cap_data *) tmpbuf;
diff --git a/sound/aoa/soundbus/i2sbus/core.c b/sound/aoa/soundbus/i2sbus/core.c
index faf6b03131ee..51ed2f34b276 100644
--- a/sound/aoa/soundbus/i2sbus/core.c
+++ b/sound/aoa/soundbus/i2sbus/core.c
@@ -147,6 +147,7 @@ static int i2sbus_get_and_fixup_rsrc(struct device_node *np, int index,
return rc;
}
+/* Returns 1 if added, 0 for otherwise; don't return a negative value! */
/* FIXME: look at device node refcounting */
static int i2sbus_add_dev(struct macio_dev *macio,
struct i2sbus_control *control,
@@ -213,7 +214,7 @@ static int i2sbus_add_dev(struct macio_dev *macio,
* either as the second one in that case is just a modem. */
if (!ok) {
kfree(dev);
- return -ENODEV;
+ return 0;
}
mutex_init(&dev->lock);
@@ -302,6 +303,10 @@ static int i2sbus_add_dev(struct macio_dev *macio,
if (soundbus_add_one(&dev->sound)) {
printk(KERN_DEBUG "i2sbus: device registration error!\n");
+ if (dev->sound.ofdev.dev.kobj.state_initialized) {
+ soundbus_dev_put(&dev->sound);
+ return 0;
+ }
goto err;
}
diff --git a/sound/core/control.c b/sound/core/control.c
index a7271927d875..50e7ba66f187 100644
--- a/sound/core/control.c
+++ b/sound/core/control.c
@@ -753,6 +753,29 @@ int snd_ctl_rename_id(struct snd_card *card, struct snd_ctl_elem_id *src_id,
}
EXPORT_SYMBOL(snd_ctl_rename_id);
+/**
+ * snd_ctl_rename - rename the control on the card
+ * @card: the card instance
+ * @kctl: the control to rename
+ * @name: the new name
+ *
+ * Renames the specified control on the card to the new name.
+ *
+ * Make sure to take the control write lock - down_write(&card->controls_rwsem).
+ */
+void snd_ctl_rename(struct snd_card *card, struct snd_kcontrol *kctl,
+ const char *name)
+{
+ remove_hash_entries(card, kctl);
+
+ if (strscpy(kctl->id.name, name, sizeof(kctl->id.name)) < 0)
+ pr_warn("ALSA: Renamed control new name '%s' truncated to '%s'\n",
+ name, kctl->id.name);
+
+ add_hash_entries(card, kctl);
+}
+EXPORT_SYMBOL(snd_ctl_rename);
+
#ifndef CONFIG_SND_CTL_FAST_LOOKUP
static struct snd_kcontrol *
snd_ctl_find_numid_slow(struct snd_card *card, unsigned int numid)
diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c
index cb60a07d39a8..ff685321f1a1 100644
--- a/sound/pci/ac97/ac97_codec.c
+++ b/sound/pci/ac97/ac97_codec.c
@@ -2009,6 +2009,7 @@ static int snd_ac97_dev_register(struct snd_device *device)
err = device_register(&ac97->dev);
if (err < 0) {
ac97_err(ac97, "Can't register ac97 bus\n");
+ put_device(&ac97->dev);
ac97->dev.bus = NULL;
return err;
}
@@ -2655,11 +2656,18 @@ EXPORT_SYMBOL(snd_ac97_resume);
*/
static void set_ctl_name(char *dst, const char *src, const char *suffix)
{
- if (suffix)
- sprintf(dst, "%s %s", src, suffix);
- else
- strcpy(dst, src);
-}
+ const size_t msize = SNDRV_CTL_ELEM_ID_NAME_MAXLEN;
+
+ if (suffix) {
+ if (snprintf(dst, msize, "%s %s", src, suffix) >= msize)
+ pr_warn("ALSA: AC97 control name '%s %s' truncated to '%s'\n",
+ src, suffix, dst);
+ } else {
+ if (strscpy(dst, src, msize) < 0)
+ pr_warn("ALSA: AC97 control name '%s' truncated to '%s'\n",
+ src, dst);
+ }
+}
/* remove the control with the given name and optional suffix */
static int snd_ac97_remove_ctl(struct snd_ac97 *ac97, const char *name,
@@ -2686,8 +2694,11 @@ static int snd_ac97_rename_ctl(struct snd_ac97 *ac97, const char *src,
const char *dst, const char *suffix)
{
struct snd_kcontrol *kctl = ctl_find(ac97, src, suffix);
+ char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+
if (kctl) {
- set_ctl_name(kctl->id.name, dst, suffix);
+ set_ctl_name(name, dst, suffix);
+ snd_ctl_rename(ac97->bus->card, kctl, name);
return 0;
}
return -ENOENT;
@@ -2706,11 +2717,17 @@ static int snd_ac97_swap_ctl(struct snd_ac97 *ac97, const char *s1,
const char *s2, const char *suffix)
{
struct snd_kcontrol *kctl1, *kctl2;
+ char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+
kctl1 = ctl_find(ac97, s1, suffix);
kctl2 = ctl_find(ac97, s2, suffix);
if (kctl1 && kctl2) {
- set_ctl_name(kctl1->id.name, s2, suffix);
- set_ctl_name(kctl2->id.name, s1, suffix);
+ set_ctl_name(name, s2, suffix);
+ snd_ctl_rename(ac97->bus->card, kctl1, name);
+
+ set_ctl_name(name, s1, suffix);
+ snd_ctl_rename(ac97->bus->card, kctl2, name);
+
return 0;
}
return -ENOENT;
diff --git a/sound/pci/au88x0/au88x0.h b/sound/pci/au88x0/au88x0.h
index 0aa7af049b1b..6cbb2bc4a048 100644
--- a/sound/pci/au88x0/au88x0.h
+++ b/sound/pci/au88x0/au88x0.h
@@ -141,7 +141,7 @@ struct snd_vortex {
#ifndef CHIP_AU8810
stream_t dma_wt[NR_WT];
wt_voice_t wt_voice[NR_WT]; /* WT register cache. */
- char mixwt[(NR_WT / NR_WTPB) * 6]; /* WT mixin objects */
+ s8 mixwt[(NR_WT / NR_WTPB) * 6]; /* WT mixin objects */
#endif
/* Global resources */
@@ -235,8 +235,8 @@ static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v);
static void vortex_connect_default(vortex_t * vortex, int en);
static int vortex_adb_allocroute(vortex_t * vortex, int dma, int nr_ch,
int dir, int type, int subdev);
-static char vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out,
- int restype);
+static int vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out,
+ int restype);
#ifndef CHIP_AU8810
static int vortex_wt_allocroute(vortex_t * vortex, int dma, int nr_ch);
static void vortex_wt_connect(vortex_t * vortex, int en);
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index 2ed5100b8cae..f217c02dfdfa 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -1998,7 +1998,7 @@ static const int resnum[VORTEX_RESOURCE_LAST] =
out: Mean checkout if != 0. Else mean Checkin resource.
restype: Indicates type of resource to be checked in or out.
*/
-static char
+static int
vortex_adb_checkinout(vortex_t * vortex, int resmap[], int out, int restype)
{
int i, qty = resnum[restype], resinuse = 0;
diff --git a/sound/pci/ca0106/ca0106_mixer.c b/sound/pci/ca0106/ca0106_mixer.c
index 05f56015ddd8..f6381c098d4f 100644
--- a/sound/pci/ca0106/ca0106_mixer.c
+++ b/sound/pci/ca0106/ca0106_mixer.c
@@ -720,7 +720,7 @@ static int rename_ctl(struct snd_card *card, const char *src, const char *dst)
{
struct snd_kcontrol *kctl = ctl_find(card, src);
if (kctl) {
- strcpy(kctl->id.name, dst);
+ snd_ctl_rename(card, kctl, dst);
return 0;
}
return -ENOENT;
diff --git a/sound/pci/emu10k1/emumixer.c b/sound/pci/emu10k1/emumixer.c
index e9c0fe3b8446..3c115f8ab96c 100644
--- a/sound/pci/emu10k1/emumixer.c
+++ b/sound/pci/emu10k1/emumixer.c
@@ -1767,7 +1767,7 @@ static int rename_ctl(struct snd_card *card, const char *src, const char *dst)
{
struct snd_kcontrol *kctl = ctl_find(card, src);
if (kctl) {
- strcpy(kctl->id.name, dst);
+ snd_ctl_rename(card, kctl, dst);
return 0;
}
return -ENOENT;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e6c4bb5fa041..701a72ec5629 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2142,7 +2142,7 @@ static void rename_ctl(struct hda_codec *codec, const char *oldname,
kctl = snd_hda_find_mixer_ctl(codec, oldname);
if (kctl)
- strcpy(kctl->id.name, newname);
+ snd_ctl_rename(codec->card, kctl, newname);
}
static void alc1220_fixup_gb_dual_codecs(struct hda_codec *codec,
@@ -6654,13 +6654,8 @@ static int comp_bind(struct device *dev)
{
struct hda_codec *cdc = dev_to_hda_codec(dev);
struct alc_spec *spec = cdc->spec;
- int ret;
- ret = component_bind_all(dev, spec->comps);
- if (ret)
- return ret;
-
- return 0;
+ return component_bind_all(dev, spec->comps);
}
static void comp_unbind(struct device *dev)
@@ -9328,6 +9323,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED),
+ SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8971, "HP EliteBook 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8972, "HP EliteBook 840 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -9346,6 +9342,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x89aa, "HP EliteBook 630 G9", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89ac, "HP EliteBook 640 G9", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89ae, "HP EliteBook 650 G9", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x89c0, "HP ZBook Power 15.6 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89c3, "Zbook Studio G9", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
@@ -9400,6 +9397,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x1d42, "ASUS Zephyrus G14 2022", ALC289_FIXUP_ASUS_GA401),
SND_PCI_QUIRK(0x1043, 0x1d4e, "ASUS TM420", ALC256_FIXUP_ASUS_HPE),
+ SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402", ALC245_FIXUP_CS35L41_SPI_2),
SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
diff --git a/sound/pci/rme9652/hdsp.c b/sound/pci/rme9652/hdsp.c
index dcc43a81ae0e..65add92c88aa 100644
--- a/sound/pci/rme9652/hdsp.c
+++ b/sound/pci/rme9652/hdsp.c
@@ -433,7 +433,7 @@ struct hdsp_midi {
struct snd_rawmidi *rmidi;
struct snd_rawmidi_substream *input;
struct snd_rawmidi_substream *output;
- char istimer; /* timer in use */
+ signed char istimer; /* timer in use */
struct timer_list timer;
spinlock_t lock;
int pending;
@@ -480,7 +480,7 @@ struct hdsp {
pid_t playback_pid;
int running;
int system_sample_rate;
- const char *channel_map;
+ const signed char *channel_map;
int dev;
int irq;
unsigned long port;
@@ -502,7 +502,7 @@ struct hdsp {
where the data for that channel can be read/written from/to.
*/
-static const char channel_map_df_ss[HDSP_MAX_CHANNELS] = {
+static const signed char channel_map_df_ss[HDSP_MAX_CHANNELS] = {
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
};
@@ -517,7 +517,7 @@ static const char channel_map_mf_ss[HDSP_MAX_CHANNELS] = { /* Multiface */
-1, -1, -1, -1, -1, -1, -1, -1
};
-static const char channel_map_ds[HDSP_MAX_CHANNELS] = {
+static const signed char channel_map_ds[HDSP_MAX_CHANNELS] = {
/* ADAT channels are remapped */
1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23,
/* channels 12 and 13 are S/PDIF */
@@ -526,7 +526,7 @@ static const char channel_map_ds[HDSP_MAX_CHANNELS] = {
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
-static const char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = {
+static const signed char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = {
/* ADAT channels */
0, 1, 2, 3, 4, 5, 6, 7,
/* SPDIF */
@@ -540,7 +540,7 @@ static const char channel_map_H9632_ss[HDSP_MAX_CHANNELS] = {
-1, -1
};
-static const char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = {
+static const signed char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = {
/* ADAT */
1, 3, 5, 7,
/* SPDIF */
@@ -554,7 +554,7 @@ static const char channel_map_H9632_ds[HDSP_MAX_CHANNELS] = {
-1, -1, -1, -1, -1, -1
};
-static const char channel_map_H9632_qs[HDSP_MAX_CHANNELS] = {
+static const signed char channel_map_H9632_qs[HDSP_MAX_CHANNELS] = {
/* ADAT is disabled in this mode */
/* SPDIF */
8, 9,
@@ -3939,7 +3939,7 @@ static snd_pcm_uframes_t snd_hdsp_hw_pointer(struct snd_pcm_substream *substream
return hdsp_hw_pointer(hdsp);
}
-static char *hdsp_channel_buffer_location(struct hdsp *hdsp,
+static signed char *hdsp_channel_buffer_location(struct hdsp *hdsp,
int stream,
int channel)
@@ -3964,7 +3964,7 @@ static int snd_hdsp_playback_copy(struct snd_pcm_substream *substream,
void __user *src, unsigned long count)
{
struct hdsp *hdsp = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
if (snd_BUG_ON(pos + count > HDSP_CHANNEL_BUFFER_BYTES))
return -EINVAL;
@@ -3982,7 +3982,7 @@ static int snd_hdsp_playback_copy_kernel(struct snd_pcm_substream *substream,
void *src, unsigned long count)
{
struct hdsp *hdsp = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = hdsp_channel_buffer_location(hdsp, substream->pstr->stream, channel);
if (snd_BUG_ON(!channel_buf))
@@ -3996,7 +3996,7 @@ static int snd_hdsp_capture_copy(struct snd_pcm_substream *substream,
void __user *dst, unsigned long count)
{
struct hdsp *hdsp = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
if (snd_BUG_ON(pos + count > HDSP_CHANNEL_BUFFER_BYTES))
return -EINVAL;
@@ -4014,7 +4014,7 @@ static int snd_hdsp_capture_copy_kernel(struct snd_pcm_substream *substream,
void *dst, unsigned long count)
{
struct hdsp *hdsp = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = hdsp_channel_buffer_location(hdsp, substream->pstr->stream, channel);
if (snd_BUG_ON(!channel_buf))
@@ -4028,7 +4028,7 @@ static int snd_hdsp_hw_silence(struct snd_pcm_substream *substream,
unsigned long count)
{
struct hdsp *hdsp = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = hdsp_channel_buffer_location (hdsp, substream->pstr->stream, channel);
if (snd_BUG_ON(!channel_buf))
diff --git a/sound/pci/rme9652/rme9652.c b/sound/pci/rme9652/rme9652.c
index 1d614fe89a6a..e7c320afefe8 100644
--- a/sound/pci/rme9652/rme9652.c
+++ b/sound/pci/rme9652/rme9652.c
@@ -230,7 +230,7 @@ struct snd_rme9652 {
int last_spdif_sample_rate; /* so that we can catch externally ... */
int last_adat_sample_rate; /* ... induced rate changes */
- const char *channel_map;
+ const signed char *channel_map;
struct snd_card *card;
struct snd_pcm *pcm;
@@ -247,12 +247,12 @@ struct snd_rme9652 {
where the data for that channel can be read/written from/to.
*/
-static const char channel_map_9652_ss[26] = {
+static const signed char channel_map_9652_ss[26] = {
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
};
-static const char channel_map_9636_ss[26] = {
+static const signed char channel_map_9636_ss[26] = {
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
/* channels 16 and 17 are S/PDIF */
24, 25,
@@ -260,7 +260,7 @@ static const char channel_map_9636_ss[26] = {
-1, -1, -1, -1, -1, -1, -1, -1
};
-static const char channel_map_9652_ds[26] = {
+static const signed char channel_map_9652_ds[26] = {
/* ADAT channels are remapped */
1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23,
/* channels 12 and 13 are S/PDIF */
@@ -269,7 +269,7 @@ static const char channel_map_9652_ds[26] = {
-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
};
-static const char channel_map_9636_ds[26] = {
+static const signed char channel_map_9636_ds[26] = {
/* ADAT channels are remapped */
1, 3, 5, 7, 9, 11, 13, 15,
/* channels 8 and 9 are S/PDIF */
@@ -1819,7 +1819,7 @@ static snd_pcm_uframes_t snd_rme9652_hw_pointer(struct snd_pcm_substream *substr
return rme9652_hw_pointer(rme9652);
}
-static char *rme9652_channel_buffer_location(struct snd_rme9652 *rme9652,
+static signed char *rme9652_channel_buffer_location(struct snd_rme9652 *rme9652,
int stream,
int channel)
@@ -1847,7 +1847,7 @@ static int snd_rme9652_playback_copy(struct snd_pcm_substream *substream,
void __user *src, unsigned long count)
{
struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
if (snd_BUG_ON(pos + count > RME9652_CHANNEL_BUFFER_BYTES))
return -EINVAL;
@@ -1867,7 +1867,7 @@ static int snd_rme9652_playback_copy_kernel(struct snd_pcm_substream *substream,
void *src, unsigned long count)
{
struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = rme9652_channel_buffer_location(rme9652,
substream->pstr->stream,
@@ -1883,7 +1883,7 @@ static int snd_rme9652_capture_copy(struct snd_pcm_substream *substream,
void __user *dst, unsigned long count)
{
struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
if (snd_BUG_ON(pos + count > RME9652_CHANNEL_BUFFER_BYTES))
return -EINVAL;
@@ -1903,7 +1903,7 @@ static int snd_rme9652_capture_copy_kernel(struct snd_pcm_substream *substream,
void *dst, unsigned long count)
{
struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = rme9652_channel_buffer_location(rme9652,
substream->pstr->stream,
@@ -1919,7 +1919,7 @@ static int snd_rme9652_hw_silence(struct snd_pcm_substream *substream,
unsigned long count)
{
struct snd_rme9652 *rme9652 = snd_pcm_substream_chip(substream);
- char *channel_buf;
+ signed char *channel_buf;
channel_buf = rme9652_channel_buffer_location (rme9652,
substream->pstr->stream,
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 2cb50d5cf1a9..6c0f1de10429 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -49,6 +49,27 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
.driver_data = &acp6x_card,
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "21D0"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "21D0"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "21D1"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
DMI_MATCH(DMI_PRODUCT_NAME, "21D2"),
}
},
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index e3b90c425faf..7022e6286e6c 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1629,6 +1629,7 @@ config SND_SOC_TFA989X
config SND_SOC_TLV320ADC3XXX
tristate "Texas Instruments TLV320ADC3001/3101 audio ADC"
depends on I2C
+ depends on GPIOLIB
help
Enable support for Texas Instruments TLV320ADC3001 and TLV320ADC3101
ADCs.
diff --git a/sound/soc/codecs/cx2072x.h b/sound/soc/codecs/cx2072x.h
index ebdd567fa225..09e3a92b184f 100644
--- a/sound/soc/codecs/cx2072x.h
+++ b/sound/soc/codecs/cx2072x.h
@@ -177,7 +177,7 @@
#define CX2072X_PLBK_DRC_PARM_LEN 9
#define CX2072X_CLASSD_AMP_LEN 6
-/* DAI interfae type */
+/* DAI interface type */
#define CX2072X_DAI_HIFI 1
#define CX2072X_DAI_DSP 2
#define CX2072X_DAI_DSP_PWM 3 /* 4 ch, including mic and AEC */
diff --git a/sound/soc/codecs/jz4725b.c b/sound/soc/codecs/jz4725b.c
index 5201a8f6d7b6..71ea576f7e67 100644
--- a/sound/soc/codecs/jz4725b.c
+++ b/sound/soc/codecs/jz4725b.c
@@ -136,14 +136,17 @@ enum {
#define REG_CGR3_GO1L_OFFSET 0
#define REG_CGR3_GO1L_MASK (0x1f << REG_CGR3_GO1L_OFFSET)
+#define REG_CGR10_GIL_OFFSET 0
+#define REG_CGR10_GIR_OFFSET 4
+
struct jz_icdc {
struct regmap *regmap;
void __iomem *base;
struct clk *clk;
};
-static const SNDRV_CTL_TLVD_DECLARE_DB_LINEAR(jz4725b_dac_tlv, -2250, 0);
-static const SNDRV_CTL_TLVD_DECLARE_DB_LINEAR(jz4725b_line_tlv, -1500, 600);
+static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(jz4725b_adc_tlv, 0, 150, 0);
+static const SNDRV_CTL_TLVD_DECLARE_DB_SCALE(jz4725b_dac_tlv, -2250, 150, 0);
static const struct snd_kcontrol_new jz4725b_codec_controls[] = {
SOC_DOUBLE_TLV("Master Playback Volume",
@@ -151,11 +154,11 @@ static const struct snd_kcontrol_new jz4725b_codec_controls[] = {
REG_CGR1_GODL_OFFSET,
REG_CGR1_GODR_OFFSET,
0xf, 1, jz4725b_dac_tlv),
- SOC_DOUBLE_R_TLV("Master Capture Volume",
- JZ4725B_CODEC_REG_CGR3,
- JZ4725B_CODEC_REG_CGR2,
- REG_CGR2_GO1R_OFFSET,
- 0x1f, 1, jz4725b_line_tlv),
+ SOC_DOUBLE_TLV("Master Capture Volume",
+ JZ4725B_CODEC_REG_CGR10,
+ REG_CGR10_GIL_OFFSET,
+ REG_CGR10_GIR_OFFSET,
+ 0xf, 0, jz4725b_adc_tlv),
SOC_SINGLE("Master Playback Switch", JZ4725B_CODEC_REG_CR1,
REG_CR1_DAC_MUTE_OFFSET, 1, 1),
@@ -180,7 +183,7 @@ static SOC_VALUE_ENUM_SINGLE_DECL(jz4725b_codec_adc_src_enum,
jz4725b_codec_adc_src_texts,
jz4725b_codec_adc_src_values);
static const struct snd_kcontrol_new jz4725b_codec_adc_src_ctrl =
- SOC_DAPM_ENUM("Route", jz4725b_codec_adc_src_enum);
+ SOC_DAPM_ENUM("ADC Source Capture Route", jz4725b_codec_adc_src_enum);
static const struct snd_kcontrol_new jz4725b_codec_mixer_controls[] = {
SOC_DAPM_SINGLE("Line In Bypass", JZ4725B_CODEC_REG_CR1,
@@ -225,7 +228,7 @@ static const struct snd_soc_dapm_widget jz4725b_codec_dapm_widgets[] = {
SND_SOC_DAPM_ADC("ADC", "Capture",
JZ4725B_CODEC_REG_PMR1, REG_PMR1_SB_ADC_OFFSET, 1),
- SND_SOC_DAPM_MUX("ADC Source", SND_SOC_NOPM, 0, 0,
+ SND_SOC_DAPM_MUX("ADC Source Capture Route", SND_SOC_NOPM, 0, 0,
&jz4725b_codec_adc_src_ctrl),
/* Mixer */
@@ -236,7 +239,8 @@ static const struct snd_soc_dapm_widget jz4725b_codec_dapm_widgets[] = {
SND_SOC_DAPM_MIXER("DAC to Mixer", JZ4725B_CODEC_REG_CR1,
REG_CR1_DACSEL_OFFSET, 0, NULL, 0),
- SND_SOC_DAPM_MIXER("Line In", SND_SOC_NOPM, 0, 0, NULL, 0),
+ SND_SOC_DAPM_MIXER("Line In", JZ4725B_CODEC_REG_PMR1,
+ REG_PMR1_SB_LIN_OFFSET, 1, NULL, 0),
SND_SOC_DAPM_MIXER("HP Out", JZ4725B_CODEC_REG_CR1,
REG_CR1_HP_DIS_OFFSET, 1, NULL, 0),
@@ -283,11 +287,11 @@ static const struct snd_soc_dapm_route jz4725b_codec_dapm_routes[] = {
{"Mixer", NULL, "DAC to Mixer"},
{"Mixer to ADC", NULL, "Mixer"},
- {"ADC Source", "Mixer", "Mixer to ADC"},
- {"ADC Source", "Line In", "Line In"},
- {"ADC Source", "Mic 1", "Mic 1"},
- {"ADC Source", "Mic 2", "Mic 2"},
- {"ADC", NULL, "ADC Source"},
+ {"ADC Source Capture Route", "Mixer", "Mixer to ADC"},
+ {"ADC Source Capture Route", "Line In", "Line In"},
+ {"ADC Source Capture Route", "Mic 1", "Mic 1"},
+ {"ADC Source Capture Route", "Mic 2", "Mic 2"},
+ {"ADC", NULL, "ADC Source Capture Route"},
{"Out Stage", NULL, "Mixer"},
{"HP Out", NULL, "Out Stage"},
diff --git a/sound/soc/codecs/mt6660.c b/sound/soc/codecs/mt6660.c
index 554c33e8b62f..cc2df5f7ea19 100644
--- a/sound/soc/codecs/mt6660.c
+++ b/sound/soc/codecs/mt6660.c
@@ -503,14 +503,14 @@ static int mt6660_i2c_probe(struct i2c_client *client)
dev_err(chip->dev, "read chip revision fail\n");
goto probe_fail;
}
+ pm_runtime_set_active(chip->dev);
+ pm_runtime_enable(chip->dev);
ret = devm_snd_soc_register_component(chip->dev,
&mt6660_component_driver,
&mt6660_codec_dai, 1);
- if (!ret) {
- pm_runtime_set_active(chip->dev);
- pm_runtime_enable(chip->dev);
- }
+ if (ret)
+ pm_runtime_disable(chip->dev);
return ret;
diff --git a/sound/soc/codecs/rt1019.c b/sound/soc/codecs/rt1019.c
index b66bfecbb879..49f527c61a7a 100644
--- a/sound/soc/codecs/rt1019.c
+++ b/sound/soc/codecs/rt1019.c
@@ -391,18 +391,18 @@ static int rt1019_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
unsigned int rx_mask, int slots, int slot_width)
{
struct snd_soc_component *component = dai->component;
- unsigned int val = 0, rx_slotnum;
+ unsigned int cn = 0, cl = 0, rx_slotnum;
int ret = 0, first_bit;
switch (slots) {
case 4:
- val |= RT1019_I2S_TX_4CH;
+ cn = RT1019_I2S_TX_4CH;
break;
case 6:
- val |= RT1019_I2S_TX_6CH;
+ cn = RT1019_I2S_TX_6CH;
break;
case 8:
- val |= RT1019_I2S_TX_8CH;
+ cn = RT1019_I2S_TX_8CH;
break;
case 2:
break;
@@ -412,16 +412,16 @@ static int rt1019_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
switch (slot_width) {
case 20:
- val |= RT1019_I2S_DL_20;
+ cl = RT1019_TDM_CL_20;
break;
case 24:
- val |= RT1019_I2S_DL_24;
+ cl = RT1019_TDM_CL_24;
break;
case 32:
- val |= RT1019_I2S_DL_32;
+ cl = RT1019_TDM_CL_32;
break;
case 8:
- val |= RT1019_I2S_DL_8;
+ cl = RT1019_TDM_CL_8;
break;
case 16:
break;
@@ -470,8 +470,10 @@ static int rt1019_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
goto _set_tdm_err_;
}
+ snd_soc_component_update_bits(component, RT1019_TDM_1,
+ RT1019_TDM_CL_MASK, cl);
snd_soc_component_update_bits(component, RT1019_TDM_2,
- RT1019_I2S_CH_TX_MASK | RT1019_I2S_DF_MASK, val);
+ RT1019_I2S_CH_TX_MASK, cn);
_set_tdm_err_:
return ret;
diff --git a/sound/soc/codecs/rt1019.h b/sound/soc/codecs/rt1019.h
index 64df831eeb72..48ba15efb48d 100644
--- a/sound/soc/codecs/rt1019.h
+++ b/sound/soc/codecs/rt1019.h
@@ -95,6 +95,12 @@
#define RT1019_TDM_BCLK_MASK (0x1 << 6)
#define RT1019_TDM_BCLK_NORM (0x0 << 6)
#define RT1019_TDM_BCLK_INV (0x1 << 6)
+#define RT1019_TDM_CL_MASK (0x7)
+#define RT1019_TDM_CL_8 (0x4)
+#define RT1019_TDM_CL_32 (0x3)
+#define RT1019_TDM_CL_24 (0x2)
+#define RT1019_TDM_CL_20 (0x1)
+#define RT1019_TDM_CL_16 (0x0)
/* 0x0401 TDM Control-2 */
#define RT1019_I2S_CH_TX_MASK (0x3 << 6)
diff --git a/sound/soc/codecs/rt1308-sdw.c b/sound/soc/codecs/rt1308-sdw.c
index 5c29416aa781..f99aed353f10 100644
--- a/sound/soc/codecs/rt1308-sdw.c
+++ b/sound/soc/codecs/rt1308-sdw.c
@@ -50,6 +50,7 @@ static bool rt1308_volatile_register(struct device *dev, unsigned int reg)
case 0x3008:
case 0x300a:
case 0xc000:
+ case 0xc710:
case 0xc860 ... 0xc863:
case 0xc870 ... 0xc873:
return true;
@@ -200,6 +201,7 @@ static int rt1308_io_init(struct device *dev, struct sdw_slave *slave)
{
struct rt1308_sdw_priv *rt1308 = dev_get_drvdata(dev);
int ret = 0;
+ unsigned int tmp;
if (rt1308->hw_init)
return 0;
@@ -231,6 +233,10 @@ static int rt1308_io_init(struct device *dev, struct sdw_slave *slave)
/* sw reset */
regmap_write(rt1308->regmap, RT1308_SDW_RESET, 0);
+ regmap_read(rt1308->regmap, 0xc710, &tmp);
+ rt1308->hw_ver = tmp;
+ dev_dbg(dev, "%s, hw_ver=0x%x\n", __func__, rt1308->hw_ver);
+
/* initial settings */
regmap_write(rt1308->regmap, 0xc103, 0xc0);
regmap_write(rt1308->regmap, 0xc030, 0x17);
@@ -246,8 +252,14 @@ static int rt1308_io_init(struct device *dev, struct sdw_slave *slave)
regmap_write(rt1308->regmap, 0xc062, 0x05);
regmap_write(rt1308->regmap, 0xc171, 0x07);
regmap_write(rt1308->regmap, 0xc173, 0x0d);
- regmap_write(rt1308->regmap, 0xc311, 0x7f);
- regmap_write(rt1308->regmap, 0xc900, 0x90);
+ if (rt1308->hw_ver == RT1308_VER_C) {
+ regmap_write(rt1308->regmap, 0xc311, 0x7f);
+ regmap_write(rt1308->regmap, 0xc300, 0x09);
+ } else {
+ regmap_write(rt1308->regmap, 0xc311, 0x4f);
+ regmap_write(rt1308->regmap, 0xc300, 0x0b);
+ }
+ regmap_write(rt1308->regmap, 0xc900, 0x5a);
regmap_write(rt1308->regmap, 0xc1a0, 0x84);
regmap_write(rt1308->regmap, 0xc1a1, 0x01);
regmap_write(rt1308->regmap, 0xc360, 0x78);
@@ -257,7 +269,6 @@ static int rt1308_io_init(struct device *dev, struct sdw_slave *slave)
regmap_write(rt1308->regmap, 0xc070, 0x00);
regmap_write(rt1308->regmap, 0xc100, 0xd7);
regmap_write(rt1308->regmap, 0xc101, 0xd7);
- regmap_write(rt1308->regmap, 0xc300, 0x09);
if (rt1308->first_hw_init) {
regcache_cache_bypass(rt1308->regmap, false);
diff --git a/sound/soc/codecs/rt1308-sdw.h b/sound/soc/codecs/rt1308-sdw.h
index 6668e19d85d4..62ce27799307 100644
--- a/sound/soc/codecs/rt1308-sdw.h
+++ b/sound/soc/codecs/rt1308-sdw.h
@@ -139,10 +139,12 @@ static const struct reg_default rt1308_reg_defaults[] = {
{ 0x3005, 0x23 },
{ 0x3008, 0x02 },
{ 0x300a, 0x00 },
+ { 0xc000 | (RT1308_DATA_PATH << 4), 0x00 },
{ 0xc003 | (RT1308_DAC_SET << 4), 0x00 },
{ 0xc000 | (RT1308_POWER << 4), 0x00 },
{ 0xc001 | (RT1308_POWER << 4), 0x00 },
{ 0xc002 | (RT1308_POWER << 4), 0x00 },
+ { 0xc000 | (RT1308_POWER_STATUS << 4), 0x00 },
};
#define RT1308_SDW_OFFSET 0xc000
@@ -163,6 +165,7 @@ struct rt1308_sdw_priv {
bool first_hw_init;
int rx_mask;
int slots;
+ int hw_ver;
};
struct sdw_stream_data {
diff --git a/sound/soc/codecs/rt1308.h b/sound/soc/codecs/rt1308.h
index ff7c423e879e..d3a0f91630ca 100644
--- a/sound/soc/codecs/rt1308.h
+++ b/sound/soc/codecs/rt1308.h
@@ -286,4 +286,9 @@ enum {
RT1308_AIFS
};
+enum rt1308_hw_ver {
+ RT1308_VER_C = 2,
+ RT1308_VER_D
+};
+
#endif /* end of _RT1308_H_ */
diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c
index 466a37f3500c..80c673aa14db 100644
--- a/sound/soc/codecs/rt5682s.c
+++ b/sound/soc/codecs/rt5682s.c
@@ -1981,7 +1981,7 @@ static int rt5682s_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
unsigned int rx_mask, int slots, int slot_width)
{
struct snd_soc_component *component = dai->component;
- unsigned int cl, val = 0;
+ unsigned int cl, val = 0, tx_slotnum;
if (tx_mask || rx_mask)
snd_soc_component_update_bits(component,
@@ -1990,6 +1990,16 @@ static int rt5682s_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
snd_soc_component_update_bits(component,
RT5682S_TDM_ADDA_CTRL_2, RT5682S_TDM_EN, 0);
+ /* Tx slot configuration */
+ tx_slotnum = hweight_long(tx_mask);
+ if (tx_slotnum) {
+ if (tx_slotnum > slots) {
+ dev_err(component->dev, "Invalid or oversized Tx slots.\n");
+ return -EINVAL;
+ }
+ val |= (tx_slotnum - 1) << RT5682S_TDM_ADC_DL_SFT;
+ }
+
switch (slots) {
case 4:
val |= RT5682S_TDM_TX_CH_4;
@@ -2010,7 +2020,8 @@ static int rt5682s_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
}
snd_soc_component_update_bits(component, RT5682S_TDM_CTRL,
- RT5682S_TDM_TX_CH_MASK | RT5682S_TDM_RX_CH_MASK, val);
+ RT5682S_TDM_TX_CH_MASK | RT5682S_TDM_RX_CH_MASK |
+ RT5682S_TDM_ADC_DL_MASK, val);
switch (slot_width) {
case 8:
diff --git a/sound/soc/codecs/rt5682s.h b/sound/soc/codecs/rt5682s.h
index 824dc6543c18..45464a041765 100644
--- a/sound/soc/codecs/rt5682s.h
+++ b/sound/soc/codecs/rt5682s.h
@@ -899,6 +899,7 @@
#define RT5682S_TDM_RX_CH_8 (0x3 << 8)
#define RT5682S_TDM_ADC_LCA_MASK (0x7 << 4)
#define RT5682S_TDM_ADC_LCA_SFT 4
+#define RT5682S_TDM_ADC_DL_MASK (0x3 << 0)
#define RT5682S_TDM_ADC_DL_SFT 0
/* TDM control 2 (0x007a) */
diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c
index baab320ef988..a969547708d4 100644
--- a/sound/soc/codecs/tlv320adc3xxx.c
+++ b/sound/soc/codecs/tlv320adc3xxx.c
@@ -1449,7 +1449,7 @@ static struct i2c_driver adc3xxx_i2c_driver = {
.of_match_table = tlv320adc3xxx_of_match,
},
.probe_new = adc3xxx_i2c_probe,
- .remove = adc3xxx_i2c_remove,
+ .remove = __exit_p(adc3xxx_i2c_remove),
.id_table = adc3xxx_i2c_id,
};
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index c09c9ac51b3e..adaf886b0a9d 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -2099,6 +2099,9 @@ static int wm5102_probe(struct platform_device *pdev)
regmap_update_bits(arizona->regmap, wm5102_digital_vu[i],
WM5102_DIG_VU, WM5102_DIG_VU);
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_idle(&pdev->dev);
+
ret = arizona_request_irq(arizona, ARIZONA_IRQ_DSP_IRQ1,
"ADSP2 Compressed IRQ", wm5102_adsp2_irq,
wm5102);
@@ -2131,9 +2134,6 @@ static int wm5102_probe(struct platform_device *pdev)
goto err_spk_irqs;
}
- pm_runtime_enable(&pdev->dev);
- pm_runtime_idle(&pdev->dev);
-
return ret;
err_spk_irqs:
@@ -2142,6 +2142,7 @@ err_dsp_irq:
arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5102);
err_jack_codec_dev:
+ pm_runtime_disable(&pdev->dev);
arizona_jack_codec_dev_remove(&wm5102->core);
return ret;
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index fc634c995834..e0b971620d0f 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -2457,6 +2457,9 @@ static int wm5110_probe(struct platform_device *pdev)
regmap_update_bits(arizona->regmap, wm5110_digital_vu[i],
WM5110_DIG_VU, WM5110_DIG_VU);
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_idle(&pdev->dev);
+
ret = arizona_request_irq(arizona, ARIZONA_IRQ_DSP_IRQ1,
"ADSP2 Compressed IRQ", wm5110_adsp2_irq,
wm5110);
@@ -2489,9 +2492,6 @@ static int wm5110_probe(struct platform_device *pdev)
goto err_spk_irqs;
}
- pm_runtime_enable(&pdev->dev);
- pm_runtime_idle(&pdev->dev);
-
return ret;
err_spk_irqs:
@@ -2500,6 +2500,7 @@ err_dsp_irq:
arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5110);
err_jack_codec_dev:
+ pm_runtime_disable(&pdev->dev);
arizona_jack_codec_dev_remove(&wm5110->core);
return ret;
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 81049664387e..b4b4355c6728 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -1840,6 +1840,49 @@ SOC_SINGLE_TLV("SPKOUTR Mixer DACR Volume", WM8962_SPEAKER_MIXER_5,
4, 1, 0, inmix_tlv),
};
+static int tp_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+{
+ int ret, reg, val, mask;
+ struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+
+ ret = pm_runtime_resume_and_get(component->dev);
+ if (ret < 0) {
+ dev_err(component->dev, "Failed to resume device: %d\n", ret);
+ return ret;
+ }
+
+ reg = WM8962_ADDITIONAL_CONTROL_4;
+
+ if (!strcmp(w->name, "TEMP_HP")) {
+ mask = WM8962_TEMP_ENA_HP_MASK;
+ val = WM8962_TEMP_ENA_HP;
+ } else if (!strcmp(w->name, "TEMP_SPK")) {
+ mask = WM8962_TEMP_ENA_SPK_MASK;
+ val = WM8962_TEMP_ENA_SPK;
+ } else {
+ pm_runtime_put(component->dev);
+ return -EINVAL;
+ }
+
+ switch (event) {
+ case SND_SOC_DAPM_POST_PMD:
+ val = 0;
+ fallthrough;
+ case SND_SOC_DAPM_POST_PMU:
+ ret = snd_soc_component_update_bits(component, reg, mask, val);
+ break;
+ default:
+ WARN(1, "Invalid event %d\n", event);
+ pm_runtime_put(component->dev);
+ return -EINVAL;
+ }
+
+ pm_runtime_put(component->dev);
+
+ return 0;
+}
+
static int cp_event(struct snd_soc_dapm_widget *w,
struct snd_kcontrol *kcontrol, int event)
{
@@ -2140,8 +2183,10 @@ SND_SOC_DAPM_SUPPLY("TOCLK", WM8962_ADDITIONAL_CONTROL_1, 0, 0, NULL, 0),
SND_SOC_DAPM_SUPPLY_S("DSP2", 1, WM8962_DSP2_POWER_MANAGEMENT,
WM8962_DSP2_ENA_SHIFT, 0, dsp2_event,
SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD),
-SND_SOC_DAPM_SUPPLY("TEMP_HP", WM8962_ADDITIONAL_CONTROL_4, 2, 0, NULL, 0),
-SND_SOC_DAPM_SUPPLY("TEMP_SPK", WM8962_ADDITIONAL_CONTROL_4, 1, 0, NULL, 0),
+SND_SOC_DAPM_SUPPLY("TEMP_HP", SND_SOC_NOPM, 0, 0, tp_event,
+ SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_POST_PMD),
+SND_SOC_DAPM_SUPPLY("TEMP_SPK", SND_SOC_NOPM, 0, 0, tp_event,
+ SND_SOC_DAPM_POST_PMU|SND_SOC_DAPM_POST_PMD),
SND_SOC_DAPM_MIXER("INPGAL", WM8962_LEFT_INPUT_PGA_CONTROL, 4, 0,
inpgal, ARRAY_SIZE(inpgal)),
@@ -3763,6 +3808,11 @@ static int wm8962_i2c_probe(struct i2c_client *i2c)
if (ret < 0)
goto err_pm_runtime;
+ regmap_update_bits(wm8962->regmap, WM8962_ADDITIONAL_CONTROL_4,
+ WM8962_TEMP_ENA_HP_MASK, 0);
+ regmap_update_bits(wm8962->regmap, WM8962_ADDITIONAL_CONTROL_4,
+ WM8962_TEMP_ENA_SPK_MASK, 0);
+
regcache_cache_only(wm8962->regmap, true);
/* The drivers should power up as needed */
diff --git a/sound/soc/codecs/wm8997.c b/sound/soc/codecs/wm8997.c
index 77136a521605..c0207e9a7d53 100644
--- a/sound/soc/codecs/wm8997.c
+++ b/sound/soc/codecs/wm8997.c
@@ -1161,6 +1161,9 @@ static int wm8997_probe(struct platform_device *pdev)
regmap_update_bits(arizona->regmap, wm8997_digital_vu[i],
WM8997_DIG_VU, WM8997_DIG_VU);
+ pm_runtime_enable(&pdev->dev);
+ pm_runtime_idle(&pdev->dev);
+
arizona_init_common(arizona);
ret = arizona_init_vol_limit(arizona);
@@ -1179,14 +1182,12 @@ static int wm8997_probe(struct platform_device *pdev)
goto err_spk_irqs;
}
- pm_runtime_enable(&pdev->dev);
- pm_runtime_idle(&pdev->dev);
-
return ret;
err_spk_irqs:
arizona_free_spk_irqs(arizona);
err_jack_codec_dev:
+ pm_runtime_disable(&pdev->dev);
arizona_jack_codec_dev_remove(&wm8997->core);
return ret;
diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index b327372f2e4a..fe7cf972d44c 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -417,7 +417,7 @@ static inline bool parse_as_dpcm_link(struct asoc_simple_priv *priv,
* or has convert-xxx property
*/
if ((of_get_child_count(codec_port) > 1) ||
- (adata->convert_rate || adata->convert_channels))
+ asoc_simple_is_convert_required(adata))
return true;
return false;
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index bef16833c487..be69bbc47f81 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -85,6 +85,21 @@ void asoc_simple_parse_convert(struct device_node *np,
}
EXPORT_SYMBOL_GPL(asoc_simple_parse_convert);
+/**
+ * asoc_simple_is_convert_required() - Query if HW param conversion was requested
+ * @data: Link data.
+ *
+ * Returns true if any HW param conversion was requested for this DAI link with
+ * any "convert-xxx" properties.
+ */
+bool asoc_simple_is_convert_required(const struct asoc_simple_data *data)
+{
+ return data->convert_rate ||
+ data->convert_channels ||
+ data->convert_sample_format;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_is_convert_required);
+
int asoc_simple_parse_daifmt(struct device *dev,
struct device_node *node,
struct device_node *codec,
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 78419e18717d..feb55b66239b 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -393,8 +393,7 @@ static int __simple_for_each_link(struct asoc_simple_priv *priv,
* or has convert-xxx property
*/
if (dpcm_selectable &&
- (num > 2 ||
- adata.convert_rate || adata.convert_channels)) {
+ (num > 2 || asoc_simple_is_convert_required(&adata))) {
/*
* np
* |1(CPU)|0(Codec) li->cpu
diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c
index 2d0986824b3d..2358be208c1f 100644
--- a/sound/soc/intel/boards/sof_rt5682.c
+++ b/sound/soc/intel/boards/sof_rt5682.c
@@ -223,6 +223,18 @@ static const struct dmi_system_id sof_rt5682_quirk_table[] = {
SOF_RT5682_SSP_AMP(2) |
SOF_RT5682_NUM_HDMIDEV(4)),
},
+ {
+ .callback = sof_rt5682_quirk_cb,
+ .matches = {
+ DMI_MATCH(DMI_PRODUCT_FAMILY, "Google_Rex"),
+ },
+ .driver_data = (void *)(SOF_RT5682_MCLK_EN |
+ SOF_RT5682_SSP_CODEC(2) |
+ SOF_SPEAKER_AMP_PRESENT |
+ SOF_RT5682_SSP_AMP(0) |
+ SOF_RT5682_NUM_HDMIDEV(4)
+ ),
+ },
{}
};
diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 2ff30b40a1e4..ee9857dc3135 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -202,6 +202,17 @@ static const struct dmi_system_id sof_sdw_quirk_table[] = {
SOF_SDW_PCH_DMIC |
RT711_JD1),
},
+ {
+ /* NUC15 LAPBC710 skews */
+ .callback = sof_sdw_quirk_cb,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Intel Corporation"),
+ DMI_MATCH(DMI_BOARD_NAME, "LAPBC710"),
+ },
+ .driver_data = (void *)(SOF_SDW_TGL_HDMI |
+ SOF_SDW_PCH_DMIC |
+ RT711_JD1),
+ },
/* TigerLake-SDCA devices */
{
.callback = sof_sdw_quirk_cb,
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index bbba2df33aaf..3312b57e3c0c 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -689,11 +689,6 @@ static void load_codec_module(struct hda_codec *codec)
#endif /* CONFIG_SND_SOC_INTEL_SKYLAKE_HDAUDIO_CODEC */
-static void skl_codec_device_exit(struct device *dev)
-{
- snd_hdac_device_exit(dev_to_hdac_dev(dev));
-}
-
static struct hda_codec *skl_codec_device_init(struct hdac_bus *bus, int addr)
{
struct hda_codec *codec;
@@ -706,12 +701,11 @@ static struct hda_codec *skl_codec_device_init(struct hdac_bus *bus, int addr)
}
codec->core.type = HDA_DEV_ASOC;
- codec->core.dev.release = skl_codec_device_exit;
ret = snd_hdac_device_register(&codec->core);
if (ret) {
dev_err(bus->dev, "failed to register hdac device\n");
- snd_hdac_device_exit(&codec->core);
+ put_device(&codec->core.dev);
return ERR_PTR(ret);
}
diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index d0e59e07b1fc..8c7398bc1ca8 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -187,6 +187,7 @@ config SND_SOC_SC8280XP
config SND_SOC_SC7180
tristate "SoC Machine driver for SC7180 boards"
depends on I2C && GPIOLIB
+ depends on SOUNDWIRE || SOUNDWIRE=n
select SND_SOC_QCOM_COMMON
select SND_SOC_LPASS_SC7180
select SND_SOC_MAX98357A
diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
index 8a56f38dc7e8..54353842dc07 100644
--- a/sound/soc/qcom/lpass-cpu.c
+++ b/sound/soc/qcom/lpass-cpu.c
@@ -782,10 +782,20 @@ static bool lpass_hdmi_regmap_volatile(struct device *dev, unsigned int reg)
return true;
if (reg == LPASS_HDMI_TX_LEGACY_ADDR(v))
return true;
+ if (reg == LPASS_HDMI_TX_VBIT_CTL_ADDR(v))
+ return true;
+ if (reg == LPASS_HDMI_TX_PARITY_ADDR(v))
+ return true;
for (i = 0; i < v->hdmi_rdma_channels; ++i) {
if (reg == LPAIF_HDMI_RDMACURR_REG(v, i))
return true;
+ if (reg == LPASS_HDMI_TX_DMA_ADDR(v, i))
+ return true;
+ if (reg == LPASS_HDMI_TX_CH_LSB_ADDR(v, i))
+ return true;
+ if (reg == LPASS_HDMI_TX_CH_MSB_ADDR(v, i))
+ return true;
}
return false;
}
diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c
index 659b9ade4158..e12f8244242b 100644
--- a/sound/soc/soc-component.c
+++ b/sound/soc/soc-component.c
@@ -1213,9 +1213,11 @@ int snd_soc_pcm_component_pm_runtime_get(struct snd_soc_pcm_runtime *rtd,
int i;
for_each_rtd_components(rtd, i, component) {
- int ret = pm_runtime_resume_and_get(component->dev);
- if (ret < 0 && ret != -EACCES)
+ int ret = pm_runtime_get_sync(component->dev);
+ if (ret < 0 && ret != -EACCES) {
+ pm_runtime_put_noidle(component->dev);
return soc_component_ret(component, ret);
+ }
/* mark stream if succeeded */
soc_component_mark_push(component, stream, pm);
}
diff --git a/sound/soc/sof/intel/hda-codec.c b/sound/soc/sof/intel/hda-codec.c
index 1e9afc48394c..f2ec2a6c2e0f 100644
--- a/sound/soc/sof/intel/hda-codec.c
+++ b/sound/soc/sof/intel/hda-codec.c
@@ -109,11 +109,6 @@ EXPORT_SYMBOL_NS(hda_codec_jack_check, SND_SOC_SOF_HDA_AUDIO_CODEC);
#define is_generic_config(x) 0
#endif
-static void hda_codec_device_exit(struct device *dev)
-{
- snd_hdac_device_exit(dev_to_hdac_dev(dev));
-}
-
static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, int type)
{
struct hda_codec *codec;
@@ -126,12 +121,11 @@ static struct hda_codec *hda_codec_device_init(struct hdac_bus *bus, int addr, i
}
codec->core.type = type;
- codec->core.dev.release = hda_codec_device_exit;
ret = snd_hdac_device_register(&codec->core);
if (ret) {
dev_err(bus->dev, "failed to register hdac device\n");
- snd_hdac_device_exit(&codec->core);
+ put_device(&codec->core.dev);
return ERR_PTR(ret);
}
diff --git a/sound/soc/sof/intel/pci-mtl.c b/sound/soc/sof/intel/pci-mtl.c
index 899b00d53d64..9f39da984e9f 100644
--- a/sound/soc/sof/intel/pci-mtl.c
+++ b/sound/soc/sof/intel/pci-mtl.c
@@ -38,7 +38,7 @@ static const struct sof_dev_desc mtl_desc = {
[SOF_INTEL_IPC4] = "intel/sof-ace-tplg",
},
.default_fw_filename = {
- [SOF_INTEL_IPC4] = "dsp_basefw.bin",
+ [SOF_INTEL_IPC4] = "sof-mtl.ri",
},
.nocodec_tplg_filename = "sof-mtl-nocodec.tplg",
.ops = &sof_mtl_ops,
diff --git a/sound/soc/sof/intel/pci-tgl.c b/sound/soc/sof/intel/pci-tgl.c
index 2d63cc236a68..4cfe4f242fc5 100644
--- a/sound/soc/sof/intel/pci-tgl.c
+++ b/sound/soc/sof/intel/pci-tgl.c
@@ -159,6 +159,34 @@ static const struct sof_dev_desc adl_desc = {
.ops_init = sof_tgl_ops_init,
};
+static const struct sof_dev_desc adl_n_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,
+ .irqindex_host_ipc = -1,
+ .chip_info = &tgl_chip_info,
+ .ipc_supported_mask = BIT(SOF_IPC) | BIT(SOF_INTEL_IPC4),
+ .ipc_default = SOF_IPC,
+ .default_fw_path = {
+ [SOF_IPC] = "intel/sof",
+ [SOF_INTEL_IPC4] = "intel/avs/adl-n",
+ },
+ .default_tplg_path = {
+ [SOF_IPC] = "intel/sof-tplg",
+ [SOF_INTEL_IPC4] = "intel/avs-tplg",
+ },
+ .default_fw_filename = {
+ [SOF_IPC] = "sof-adl-n.ri",
+ [SOF_INTEL_IPC4] = "dsp_basefw.bin",
+ },
+ .nocodec_tplg_filename = "sof-adl-nocodec.tplg",
+ .ops = &sof_tgl_ops,
+ .ops_init = sof_tgl_ops_init,
+};
+
static const struct sof_dev_desc rpls_desc = {
.machines = snd_soc_acpi_intel_rpl_machines,
.alt_machines = snd_soc_acpi_intel_rpl_sdw_machines,
@@ -246,7 +274,7 @@ static const struct pci_device_id sof_pci_ids[] = {
{ PCI_DEVICE(0x8086, 0x51cf), /* RPL-PX */
.driver_data = (unsigned long)&rpl_desc},
{ PCI_DEVICE(0x8086, 0x54c8), /* ADL-N */
- .driver_data = (unsigned long)&adl_desc},
+ .driver_data = (unsigned long)&adl_n_desc},
{ 0, }
};
MODULE_DEVICE_TABLE(pci, sof_pci_ids);
diff --git a/sound/soc/sof/ipc4-mtrace.c b/sound/soc/sof/ipc4-mtrace.c
index 9c7080041d08..70dea8ae706e 100644
--- a/sound/soc/sof/ipc4-mtrace.c
+++ b/sound/soc/sof/ipc4-mtrace.c
@@ -108,6 +108,7 @@ struct sof_mtrace_core_data {
int id;
u32 slot_offset;
void *log_buffer;
+ struct mutex buffer_lock; /* for log_buffer alloc/free */
u32 host_read_ptr;
u32 dsp_write_ptr;
/* pos update IPC arrived before the slot offset is known, queried */
@@ -128,14 +129,22 @@ static int sof_ipc4_mtrace_dfs_open(struct inode *inode, struct file *file)
struct sof_mtrace_core_data *core_data = inode->i_private;
int ret;
+ mutex_lock(&core_data->buffer_lock);
+
+ if (core_data->log_buffer) {
+ ret = -EBUSY;
+ goto out;
+ }
+
ret = debugfs_file_get(file->f_path.dentry);
if (unlikely(ret))
- return ret;
+ goto out;
core_data->log_buffer = kmalloc(SOF_MTRACE_SLOT_SIZE, GFP_KERNEL);
if (!core_data->log_buffer) {
debugfs_file_put(file->f_path.dentry);
- return -ENOMEM;
+ ret = -ENOMEM;
+ goto out;
}
ret = simple_open(inode, file);
@@ -144,6 +153,9 @@ static int sof_ipc4_mtrace_dfs_open(struct inode *inode, struct file *file)
debugfs_file_put(file->f_path.dentry);
}
+out:
+ mutex_unlock(&core_data->buffer_lock);
+
return ret;
}
@@ -280,7 +292,10 @@ static int sof_ipc4_mtrace_dfs_release(struct inode *inode, struct file *file)
debugfs_file_put(file->f_path.dentry);
+ mutex_lock(&core_data->buffer_lock);
kfree(core_data->log_buffer);
+ core_data->log_buffer = NULL;
+ mutex_unlock(&core_data->buffer_lock);
return 0;
}
@@ -563,6 +578,7 @@ static int ipc4_mtrace_init(struct snd_sof_dev *sdev)
struct sof_mtrace_core_data *core_data = &priv->cores[i];
init_waitqueue_head(&core_data->trace_sleep);
+ mutex_init(&core_data->buffer_lock);
core_data->sdev = sdev;
core_data->id = i;
}
diff --git a/sound/synth/emux/emux.c b/sound/synth/emux/emux.c
index 5ed8e36d2e04..a870759d179e 100644
--- a/sound/synth/emux/emux.c
+++ b/sound/synth/emux/emux.c
@@ -126,15 +126,10 @@ EXPORT_SYMBOL(snd_emux_register);
*/
int snd_emux_free(struct snd_emux *emu)
{
- unsigned long flags;
-
if (! emu)
return -EINVAL;
- spin_lock_irqsave(&emu->voice_lock, flags);
- if (emu->timer_active)
- del_timer(&emu->tlist);
- spin_unlock_irqrestore(&emu->voice_lock, flags);
+ del_timer_sync(&emu->tlist);
snd_emux_proc_free(emu);
snd_emux_delete_virmidi(emu);
diff --git a/sound/usb/implicit.c b/sound/usb/implicit.c
index e1bf1b5da423..f3e8484b3d9c 100644
--- a/sound/usb/implicit.c
+++ b/sound/usb/implicit.c
@@ -47,6 +47,8 @@ struct snd_usb_implicit_fb_match {
static const struct snd_usb_implicit_fb_match playback_implicit_fb_quirks[] = {
/* Fixed EP */
/* FIXME: check the availability of generic matching */
+ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2030, 0x81, 3), /* M-Audio Fast Track C400 */
+ IMPLICIT_FB_FIXED_DEV(0x0763, 0x2031, 0x81, 3), /* M-Audio Fast Track C600 */
IMPLICIT_FB_FIXED_DEV(0x0763, 0x2080, 0x81, 2), /* M-Audio FastTrack Ultra */
IMPLICIT_FB_FIXED_DEV(0x0763, 0x2081, 0x81, 2), /* M-Audio FastTrack Ultra */
IMPLICIT_FB_FIXED_DEV(0x2466, 0x8010, 0x81, 2), /* Fractal Audio Axe-Fx III */
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index a5641956ef10..9105ec623120 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -1631,7 +1631,7 @@ static void check_no_speaker_on_headset(struct snd_kcontrol *kctl,
if (!found)
return;
- strscpy(kctl->id.name, "Headphone", sizeof(kctl->id.name));
+ snd_ctl_rename(card, kctl, "Headphone");
}
static const struct usb_feature_control_info *get_feature_control_info(int control)
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 8aa0d276a636..abc418650fec 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -60,6 +60,7 @@
#define ARM_CPU_IMP_FUJITSU 0x46
#define ARM_CPU_IMP_HISI 0x48
#define ARM_CPU_IMP_APPLE 0x61
+#define ARM_CPU_IMP_AMPERE 0xC0
#define ARM_CPU_PART_AEM_V8 0xD0F
#define ARM_CPU_PART_FOUNDATION 0xD00
@@ -123,6 +124,8 @@
#define APPLE_CPU_PART_M1_ICESTORM_MAX 0x028
#define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029
+#define AMPERE_CPU_PART_AMPERE1 0xAC3
+
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72)
@@ -172,6 +175,7 @@
#define MIDR_APPLE_M1_FIRESTORM_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_PRO)
#define MIDR_APPLE_M1_ICESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_ICESTORM_MAX)
#define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX)
+#define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
/* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
#define MIDR_FUJITSU_ERRATUM_010001 MIDR_FUJITSU_A64FX
diff --git a/tools/arch/x86/include/asm/atomic.h b/tools/arch/x86/include/asm/atomic.h
index 1f5e26aae9fc..01cc27ec4520 100644
--- a/tools/arch/x86/include/asm/atomic.h
+++ b/tools/arch/x86/include/asm/atomic.h
@@ -8,6 +8,7 @@
#define LOCK_PREFIX "\n\tlock; "
+#include <asm/asm.h>
#include <asm/cmpxchg.h>
/*
@@ -70,4 +71,10 @@ static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
return cmpxchg(&v->counter, old, new);
}
+static inline int atomic_test_and_set_bit(long nr, unsigned long *addr)
+{
+ GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, "Ir", nr, "%0", "c");
+
+}
+
#endif /* _TOOLS_LINUX_ASM_X86_ATOMIC_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index ef4775c6db01..b71f4f2ecdd5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -96,7 +96,7 @@
#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* "" syscall in IA32 userspace */
#define X86_FEATURE_SYSENTER32 ( 3*32+15) /* "" sysenter in IA32 userspace */
#define X86_FEATURE_REP_GOOD ( 3*32+16) /* REP microcode works well */
-/* FREE! ( 3*32+17) */
+#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* AMD Last Branch Record Extension Version 2 */
#define X86_FEATURE_LFENCE_RDTSC ( 3*32+18) /* "" LFENCE synchronizes RDTSC */
#define X86_FEATURE_ACC_POWER ( 3*32+19) /* AMD Accumulated Power Mechanism */
#define X86_FEATURE_NOPL ( 3*32+20) /* The NOPL (0F 1F) instructions */
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index d0d7b9bc6cad..5418e2f99834 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -27,7 +27,7 @@
* Output:
* rax original destination
*/
-SYM_FUNC_START(__memcpy)
+SYM_TYPED_FUNC_START(__memcpy)
ALTERNATIVE_2 "jmp memcpy_orig", "", X86_FEATURE_REP_GOOD, \
"jmp memcpy_erms", X86_FEATURE_ERMS
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 57619f240b56..38f8851bd7cb 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -103,6 +103,7 @@ FEATURE_TESTS_EXTRA := \
libbpf-bpf_prog_load \
libbpf-bpf_object__next_program \
libbpf-bpf_object__next_map \
+ libbpf-bpf_program__set_insns \
libbpf-bpf_create_map \
libpfm4 \
libdebuginfod \
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 04b07ff88234..690fe97be190 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -63,6 +63,7 @@ FILES= \
test-libbpf-bpf_map_create.bin \
test-libbpf-bpf_object__next_program.bin \
test-libbpf-bpf_object__next_map.bin \
+ test-libbpf-bpf_program__set_insns.bin \
test-libbpf-btf__raw_data.bin \
test-get_cpuid.bin \
test-sdt.bin \
@@ -316,6 +317,9 @@ $(OUTPUT)test-libbpf-bpf_object__next_program.bin:
$(OUTPUT)test-libbpf-bpf_object__next_map.bin:
$(BUILD) -lbpf
+$(OUTPUT)test-libbpf-bpf_program__set_insns.bin:
+ $(BUILD) -lbpf
+
$(OUTPUT)test-libbpf-btf__raw_data.bin:
$(BUILD) -lbpf
diff --git a/tools/build/feature/test-libbpf-bpf_program__set_insns.c b/tools/build/feature/test-libbpf-bpf_program__set_insns.c
new file mode 100644
index 000000000000..f3b7f18c8f49
--- /dev/null
+++ b/tools/build/feature/test-libbpf-bpf_program__set_insns.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/libbpf.h>
+
+int main(void)
+{
+ bpf_program__set_insns(NULL /* prog */, NULL /* new_insns */, 0 /* new_insn_cnt */);
+ return 0;
+}
diff --git a/tools/iio/iio_utils.c b/tools/iio/iio_utils.c
index aadee6d34c74..8d35893b2fa8 100644
--- a/tools/iio/iio_utils.c
+++ b/tools/iio/iio_utils.c
@@ -547,6 +547,10 @@ static int calc_digits(int num)
{
int count = 0;
+ /* It takes a digit to represent zero */
+ if (!num)
+ return 1;
+
while (num != 0) {
num /= 10;
count++;
diff --git a/tools/include/asm-generic/atomic-gcc.h b/tools/include/asm-generic/atomic-gcc.h
index 4c1966f7c77a..6daa68bf5b9e 100644
--- a/tools/include/asm-generic/atomic-gcc.h
+++ b/tools/include/asm-generic/atomic-gcc.h
@@ -4,6 +4,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
+#include <linux/bitops.h>
/*
* Atomic operations that C can't guarantee us. Useful for
@@ -69,4 +70,15 @@ static inline int atomic_cmpxchg(atomic_t *v, int oldval, int newval)
return cmpxchg(&(v)->counter, oldval, newval);
}
+static inline int atomic_test_and_set_bit(long nr, unsigned long *addr)
+{
+ unsigned long mask = BIT_MASK(nr);
+ long old;
+
+ addr += BIT_WORD(nr);
+
+ old = __sync_fetch_and_or(addr, mask);
+ return !!(old & mask);
+}
+
#endif /* __TOOLS_ASM_GENERIC_ATOMIC_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index bef35bee9c44..ad97c0d522b8 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -19,9 +19,9 @@ static __attribute__((unused))
int memcmp(const void *s1, const void *s2, size_t n)
{
size_t ofs = 0;
- char c1 = 0;
+ int c1 = 0;
- while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
+ while (ofs < n && !(c1 = ((unsigned char *)s1)[ofs] - ((unsigned char *)s2)[ofs])) {
ofs++;
}
return c1;
@@ -125,14 +125,18 @@ char *strcpy(char *dst, const char *src)
}
/* this function is only used with arguments that are not constants or when
- * it's not known because optimizations are disabled.
+ * it's not known because optimizations are disabled. Note that gcc 12
+ * recognizes an strlen() pattern and replaces it with a jump to strlen(),
+ * thus itself, hence the asm() statement below that's meant to disable this
+ * confusing practice.
*/
static __attribute__((unused))
-size_t nolibc_strlen(const char *str)
+size_t strlen(const char *str)
{
size_t len;
- for (len = 0; str[len]; len++);
+ for (len = 0; str[len]; len++)
+ asm("");
return len;
}
@@ -140,13 +144,12 @@ size_t nolibc_strlen(const char *str)
* the two branches, then will rely on an external definition of strlen().
*/
#if defined(__OPTIMIZE__)
+#define nolibc_strlen(x) strlen(x)
#define strlen(str) ({ \
__builtin_constant_p((str)) ? \
__builtin_strlen((str)) : \
nolibc_strlen((str)); \
})
-#else
-#define strlen(str) nolibc_strlen((str))
#endif
static __attribute__((unused))
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index 14168225cecd..f243ce665f74 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -68,6 +68,8 @@ enum {
#define IPPROTO_PIM IPPROTO_PIM
IPPROTO_COMP = 108, /* Compression Header Protocol */
#define IPPROTO_COMP IPPROTO_COMP
+ IPPROTO_L2TP = 115, /* Layer 2 Tunnelling Protocol */
+#define IPPROTO_L2TP IPPROTO_L2TP
IPPROTO_SCTP = 132, /* Stream Control Transport Protocol */
#define IPPROTO_SCTP IPPROTO_SCTP
IPPROTO_UDPLITE = 136, /* UDP-Lite (RFC 3828) */
@@ -188,21 +190,13 @@ struct ip_mreq_source {
};
struct ip_msfilter {
+ __be32 imsf_multiaddr;
+ __be32 imsf_interface;
+ __u32 imsf_fmode;
+ __u32 imsf_numsrc;
union {
- struct {
- __be32 imsf_multiaddr_aux;
- __be32 imsf_interface_aux;
- __u32 imsf_fmode_aux;
- __u32 imsf_numsrc_aux;
- __be32 imsf_slist[1];
- };
- struct {
- __be32 imsf_multiaddr;
- __be32 imsf_interface;
- __u32 imsf_fmode;
- __u32 imsf_numsrc;
- __be32 imsf_slist_flex[];
- };
+ __be32 imsf_slist[1];
+ __DECLARE_FLEX_ARRAY(__be32, imsf_slist_flex);
};
};
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index ea6defacc1a7..ccb7f5dad59b 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -164,8 +164,6 @@ enum perf_event_sample_format {
PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24,
PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */
-
- __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */
};
#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT)
@@ -263,6 +261,17 @@ enum {
PERF_BR_MAX,
};
+/*
+ * Common branch speculation outcome classification
+ */
+enum {
+ PERF_BR_SPEC_NA = 0, /* Not available */
+ PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */
+ PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */
+ PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */
+ PERF_BR_SPEC_MAX,
+};
+
enum {
PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */
PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */
@@ -282,11 +291,11 @@ enum {
PERF_BR_PRIV_HV = 3,
};
-#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1
-#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2
-#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3
-#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4
-#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5
+#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1
+#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2
+#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3
+#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4
+#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5
#define PERF_SAMPLE_BRANCH_PLM_ALL \
(PERF_SAMPLE_BRANCH_USER|\
@@ -1397,6 +1406,7 @@ union perf_mem_data_src {
* abort: aborting a hardware transaction
* cycles: cycles from last branch (or 0 if not supported)
* type: branch type
+ * spec: branch speculation info (or 0 if not supported)
*/
struct perf_branch_entry {
__u64 from;
@@ -1407,9 +1417,10 @@ struct perf_branch_entry {
abort:1, /* transaction abort */
cycles:16, /* cycle count to last branch */
type:4, /* branch type */
+ spec:2, /* branch speculation info */
new_type:4, /* additional branch type */
priv:3, /* privilege level */
- reserved:33;
+ reserved:31;
};
union perf_sample_weight {
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index 1500a0f58041..7cab2c65d3d7 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -124,7 +124,8 @@ struct statx {
__u32 stx_dev_minor;
/* 0x90 */
__u64 stx_mnt_id;
- __u64 __spare2;
+ __u32 stx_dio_mem_align; /* Memory buffer alignment for direct I/O */
+ __u32 stx_dio_offset_align; /* File offset alignment for direct I/O */
/* 0xa0 */
__u64 __spare3[12]; /* Spare space for future expansion */
/* 0x100 */
@@ -152,6 +153,7 @@ struct statx {
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
+#define STATX_DIOALIGN 0x00002000U /* Want/got direct I/O alignment info */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h
index 3974a2a911cc..de6810e94abe 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/include/uapi/sound/asound.h
@@ -3,22 +3,6 @@
* Advanced Linux Sound Architecture - ALSA - Driver
* Copyright (c) 1994-2003 by Jaroslav Kysela <perex@perex.cz>,
* Abramo Bagnara <abramo@alsa-project.org>
- *
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- *
*/
#ifndef _UAPI__SOUND_ASOUND_H
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 9c366b3a676d..6f28180ffeea 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -41,11 +41,14 @@ VMX_EXIT_REASONS = {
'EXCEPTION_NMI': 0,
'EXTERNAL_INTERRUPT': 1,
'TRIPLE_FAULT': 2,
- 'PENDING_INTERRUPT': 7,
+ 'INIT_SIGNAL': 3,
+ 'SIPI_SIGNAL': 4,
+ 'INTERRUPT_WINDOW': 7,
'NMI_WINDOW': 8,
'TASK_SWITCH': 9,
'CPUID': 10,
'HLT': 12,
+ 'INVD': 13,
'INVLPG': 14,
'RDPMC': 15,
'RDTSC': 16,
@@ -65,26 +68,48 @@ VMX_EXIT_REASONS = {
'MSR_READ': 31,
'MSR_WRITE': 32,
'INVALID_STATE': 33,
+ 'MSR_LOAD_FAIL': 34,
'MWAIT_INSTRUCTION': 36,
+ 'MONITOR_TRAP_FLAG': 37,
'MONITOR_INSTRUCTION': 39,
'PAUSE_INSTRUCTION': 40,
'MCE_DURING_VMENTRY': 41,
'TPR_BELOW_THRESHOLD': 43,
'APIC_ACCESS': 44,
+ 'EOI_INDUCED': 45,
+ 'GDTR_IDTR': 46,
+ 'LDTR_TR': 47,
'EPT_VIOLATION': 48,
'EPT_MISCONFIG': 49,
+ 'INVEPT': 50,
+ 'RDTSCP': 51,
+ 'PREEMPTION_TIMER': 52,
+ 'INVVPID': 53,
'WBINVD': 54,
'XSETBV': 55,
'APIC_WRITE': 56,
+ 'RDRAND': 57,
'INVPCID': 58,
+ 'VMFUNC': 59,
+ 'ENCLS': 60,
+ 'RDSEED': 61,
+ 'PML_FULL': 62,
+ 'XSAVES': 63,
+ 'XRSTORS': 64,
+ 'UMWAIT': 67,
+ 'TPAUSE': 68,
+ 'BUS_LOCK': 74,
+ 'NOTIFY': 75,
}
SVM_EXIT_REASONS = {
'READ_CR0': 0x000,
+ 'READ_CR2': 0x002,
'READ_CR3': 0x003,
'READ_CR4': 0x004,
'READ_CR8': 0x008,
'WRITE_CR0': 0x010,
+ 'WRITE_CR2': 0x012,
'WRITE_CR3': 0x013,
'WRITE_CR4': 0x014,
'WRITE_CR8': 0x018,
@@ -105,6 +130,7 @@ SVM_EXIT_REASONS = {
'WRITE_DR6': 0x036,
'WRITE_DR7': 0x037,
'EXCP_BASE': 0x040,
+ 'LAST_EXCP': 0x05f,
'INTR': 0x060,
'NMI': 0x061,
'SMI': 0x062,
@@ -151,21 +177,45 @@ SVM_EXIT_REASONS = {
'MWAIT': 0x08b,
'MWAIT_COND': 0x08c,
'XSETBV': 0x08d,
+ 'RDPRU': 0x08e,
+ 'EFER_WRITE_TRAP': 0x08f,
+ 'CR0_WRITE_TRAP': 0x090,
+ 'CR1_WRITE_TRAP': 0x091,
+ 'CR2_WRITE_TRAP': 0x092,
+ 'CR3_WRITE_TRAP': 0x093,
+ 'CR4_WRITE_TRAP': 0x094,
+ 'CR5_WRITE_TRAP': 0x095,
+ 'CR6_WRITE_TRAP': 0x096,
+ 'CR7_WRITE_TRAP': 0x097,
+ 'CR8_WRITE_TRAP': 0x098,
+ 'CR9_WRITE_TRAP': 0x099,
+ 'CR10_WRITE_TRAP': 0x09a,
+ 'CR11_WRITE_TRAP': 0x09b,
+ 'CR12_WRITE_TRAP': 0x09c,
+ 'CR13_WRITE_TRAP': 0x09d,
+ 'CR14_WRITE_TRAP': 0x09e,
+ 'CR15_WRITE_TRAP': 0x09f,
+ 'INVPCID': 0x0a2,
'NPF': 0x400,
+ 'AVIC_INCOMPLETE_IPI': 0x401,
+ 'AVIC_UNACCELERATED_ACCESS': 0x402,
+ 'VMGEXIT': 0x403,
}
-# EC definition of HSR (from arch/arm64/include/asm/kvm_arm.h)
+# EC definition of HSR (from arch/arm64/include/asm/esr.h)
AARCH64_EXIT_REASONS = {
'UNKNOWN': 0x00,
- 'WFI': 0x01,
+ 'WFx': 0x01,
'CP15_32': 0x03,
'CP15_64': 0x04,
'CP14_MR': 0x05,
'CP14_LS': 0x06,
'FP_ASIMD': 0x07,
'CP10_ID': 0x08,
+ 'PAC': 0x09,
'CP14_64': 0x0C,
- 'ILL_ISS': 0x0E,
+ 'BTI': 0x0D,
+ 'ILL': 0x0E,
'SVC32': 0x11,
'HVC32': 0x12,
'SMC32': 0x13,
@@ -173,21 +223,26 @@ AARCH64_EXIT_REASONS = {
'HVC64': 0x16,
'SMC64': 0x17,
'SYS64': 0x18,
- 'IABT': 0x20,
- 'IABT_HYP': 0x21,
+ 'SVE': 0x19,
+ 'ERET': 0x1A,
+ 'FPAC': 0x1C,
+ 'SME': 0x1D,
+ 'IMP_DEF': 0x1F,
+ 'IABT_LOW': 0x20,
+ 'IABT_CUR': 0x21,
'PC_ALIGN': 0x22,
- 'DABT': 0x24,
- 'DABT_HYP': 0x25,
+ 'DABT_LOW': 0x24,
+ 'DABT_CUR': 0x25,
'SP_ALIGN': 0x26,
'FP_EXC32': 0x28,
'FP_EXC64': 0x2C,
'SERROR': 0x2F,
- 'BREAKPT': 0x30,
- 'BREAKPT_HYP': 0x31,
- 'SOFTSTP': 0x32,
- 'SOFTSTP_HYP': 0x33,
- 'WATCHPT': 0x34,
- 'WATCHPT_HYP': 0x35,
+ 'BREAKPT_LOW': 0x30,
+ 'BREAKPT_CUR': 0x31,
+ 'SOFTSTP_LOW': 0x32,
+ 'SOFTSTP_CUR': 0x33,
+ 'WATCHPT_LOW': 0x34,
+ 'WATCHPT_CUR': 0x35,
'BKPT32': 0x38,
'VECTOR32': 0x3A,
'BRK64': 0x3C,
@@ -220,6 +275,19 @@ USERSPACE_EXIT_REASONS = {
'S390_TSCH': 22,
'EPR': 23,
'SYSTEM_EVENT': 24,
+ 'S390_STSI': 25,
+ 'IOAPIC_EOI': 26,
+ 'HYPERV': 27,
+ 'ARM_NISV': 28,
+ 'X86_RDMSR': 29,
+ 'X86_WRMSR': 30,
+ 'DIRTY_RING_FULL': 31,
+ 'AP_RESET_HOLD': 32,
+ 'X86_BUS_LOCK': 33,
+ 'XEN': 34,
+ 'RISCV_SBI': 35,
+ 'RISCV_CSR': 36,
+ 'NOTIFY': 37,
}
IOCTL_NUMBERS = {
@@ -1756,7 +1824,7 @@ def assign_globals():
debugfs = ''
for line in open('/proc/mounts'):
- if line.split(' ')[0] == 'debugfs':
+ if line.split(' ')[2] == 'debugfs':
debugfs = line.split(' ')[1]
break
if debugfs == '':
diff --git a/tools/perf/Documentation/perf-arm-coresight.txt b/tools/perf/Documentation/arm-coresight.txt
index c117fc50a2a9..c117fc50a2a9 100644
--- a/tools/perf/Documentation/perf-arm-coresight.txt
+++ b/tools/perf/Documentation/arm-coresight.txt
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 6fd4b1384b97..898226ea8cad 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -588,6 +588,10 @@ ifndef NO_LIBELF
ifeq ($(feature-libbpf-bpf_object__next_map), 1)
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
endif
+ $(call feature_check,libbpf-bpf_program__set_insns)
+ ifeq ($(feature-libbpf-bpf_program__set_insns), 1)
+ CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+ endif
$(call feature_check,libbpf-btf__raw_data)
ifeq ($(feature-libbpf-btf__raw_data), 1)
CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
@@ -604,6 +608,7 @@ ifndef NO_LIBELF
CFLAGS += -DHAVE_LIBBPF_BPF_PROG_LOAD
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_PROGRAM
CFLAGS += -DHAVE_LIBBPF_BPF_OBJECT__NEXT_MAP
+ CFLAGS += -DHAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
CFLAGS += -DHAVE_LIBBPF_BTF__RAW_DATA
CFLAGS += -DHAVE_LIBBPF_BPF_MAP_CREATE
endif
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 2bca64f96164..e9e0df4f9a61 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -228,8 +228,10 @@
176 64 rt_sigtimedwait sys_rt_sigtimedwait
177 nospu rt_sigqueueinfo sys_rt_sigqueueinfo compat_sys_rt_sigqueueinfo
178 nospu rt_sigsuspend sys_rt_sigsuspend compat_sys_rt_sigsuspend
-179 common pread64 sys_pread64 compat_sys_ppc_pread64
-180 common pwrite64 sys_pwrite64 compat_sys_ppc_pwrite64
+179 32 pread64 sys_ppc_pread64 compat_sys_ppc_pread64
+179 64 pread64 sys_pread64
+180 32 pwrite64 sys_ppc_pwrite64 compat_sys_ppc_pwrite64
+180 64 pwrite64 sys_pwrite64
181 common chown sys_chown
182 common getcwd sys_getcwd
183 common capget sys_capget
@@ -242,10 +244,11 @@
188 common putpmsg sys_ni_syscall
189 nospu vfork sys_vfork
190 common ugetrlimit sys_getrlimit compat_sys_getrlimit
-191 common readahead sys_readahead compat_sys_ppc_readahead
+191 32 readahead sys_ppc_readahead compat_sys_ppc_readahead
+191 64 readahead sys_readahead
192 32 mmap2 sys_mmap2 compat_sys_mmap2
-193 32 truncate64 sys_truncate64 compat_sys_ppc_truncate64
-194 32 ftruncate64 sys_ftruncate64 compat_sys_ppc_ftruncate64
+193 32 truncate64 sys_ppc_truncate64 compat_sys_ppc_truncate64
+194 32 ftruncate64 sys_ppc_ftruncate64 compat_sys_ppc_ftruncate64
195 32 stat64 sys_stat64
196 32 lstat64 sys_lstat64
197 32 fstat64 sys_fstat64
@@ -288,7 +291,8 @@
230 common io_submit sys_io_submit compat_sys_io_submit
231 common io_cancel sys_io_cancel
232 nospu set_tid_address sys_set_tid_address
-233 common fadvise64 sys_fadvise64 compat_sys_ppc32_fadvise64
+233 32 fadvise64 sys_ppc32_fadvise64 compat_sys_ppc32_fadvise64
+233 64 fadvise64 sys_fadvise64
234 nospu exit_group sys_exit_group
235 nospu lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie
236 common epoll_create sys_epoll_create
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 52d254b1530c..e128b855ddde 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -649,7 +649,7 @@ static int record__pushfn(struct mmap *map, void *to, void *bf, size_t size)
static volatile int signr = -1;
static volatile int child_finished;
#ifdef HAVE_EVENTFD_SUPPORT
-static int done_fd = -1;
+static volatile int done_fd = -1;
#endif
static void sig_handler(int sig)
@@ -661,19 +661,24 @@ static void sig_handler(int sig)
done = 1;
#ifdef HAVE_EVENTFD_SUPPORT
-{
- u64 tmp = 1;
- /*
- * It is possible for this signal handler to run after done is checked
- * in the main loop, but before the perf counter fds are polled. If this
- * happens, the poll() will continue to wait even though done is set,
- * and will only break out if either another signal is received, or the
- * counters are ready for read. To ensure the poll() doesn't sleep when
- * done is set, use an eventfd (done_fd) to wake up the poll().
- */
- if (write(done_fd, &tmp, sizeof(tmp)) < 0)
- pr_err("failed to signal wakeup fd, error: %m\n");
-}
+ if (done_fd >= 0) {
+ u64 tmp = 1;
+ int orig_errno = errno;
+
+ /*
+ * It is possible for this signal handler to run after done is
+ * checked in the main loop, but before the perf counter fds are
+ * polled. If this happens, the poll() will continue to wait
+ * even though done is set, and will only break out if either
+ * another signal is received, or the counters are ready for
+ * read. To ensure the poll() doesn't sleep when done is set,
+ * use an eventfd (done_fd) to wake up the poll().
+ */
+ if (write(done_fd, &tmp, sizeof(tmp)) < 0)
+ pr_err("failed to signal wakeup fd, error: %m\n");
+
+ errno = orig_errno;
+ }
#endif // HAVE_EVENTFD_SUPPORT
}
@@ -2834,8 +2839,12 @@ out_free_threads:
out_delete_session:
#ifdef HAVE_EVENTFD_SUPPORT
- if (done_fd >= 0)
- close(done_fd);
+ if (done_fd >= 0) {
+ fd = done_fd;
+ done_fd = -1;
+
+ close(fd);
+ }
#endif
zstd_fini(&session->zstd_data);
perf_session__delete(session);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 6ee44b18c6b5..eacca9a874e2 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -143,7 +143,7 @@ for i in $SYNC_CHECK_FILES; do
done
# diff with extra ignore lines
-check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))"'
+check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memcpy_\(erms\|orig\))" -I"^#include <linux/cfi_types.h>"'
check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"'
check arch/x86/include/asm/amd-ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"'
check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
index 6970203cb247..6443a061e22a 100644
--- a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json
@@ -112,21 +112,21 @@
"MetricName": "indirect_branch"
},
{
- "MetricExpr": "(armv8_pmuv3_0@event\\=0x1014@ + armv8_pmuv3_0@event\\=0x1018@) / BR_MIS_PRED",
+ "MetricExpr": "(armv8_pmuv3_0@event\\=0x1013@ + armv8_pmuv3_0@event\\=0x1016@) / BR_MIS_PRED",
"PublicDescription": "Push branch L3 topdown metric",
"BriefDescription": "Push branch L3 topdown metric",
"MetricGroup": "TopDownL3",
"MetricName": "push_branch"
},
{
- "MetricExpr": "armv8_pmuv3_0@event\\=0x100c@ / BR_MIS_PRED",
+ "MetricExpr": "armv8_pmuv3_0@event\\=0x100d@ / BR_MIS_PRED",
"PublicDescription": "Pop branch L3 topdown metric",
"BriefDescription": "Pop branch L3 topdown metric",
"MetricGroup": "TopDownL3",
"MetricName": "pop_branch"
},
{
- "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1014@ - armv8_pmuv3_0@event\\=0x1018@ - armv8_pmuv3_0@event\\=0x100c@) / BR_MIS_PRED",
+ "MetricExpr": "(BR_MIS_PRED - armv8_pmuv3_0@event\\=0x1010@ - armv8_pmuv3_0@event\\=0x1013@ - armv8_pmuv3_0@event\\=0x1016@ - armv8_pmuv3_0@event\\=0x100d@) / BR_MIS_PRED",
"PublicDescription": "Other branch L3 topdown metric",
"BriefDescription": "Other branch L3 topdown metric",
"MetricGroup": "TopDownL3",
diff --git a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json
index 8ba3e81c9808..fe050d44374b 100644
--- a/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json
+++ b/tools/perf/pmu-events/arch/powerpc/power10/nest_metrics.json
@@ -1,13 +1,13 @@
[
{
"MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P01",
- "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@) * 100",
+ "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP01\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "VEC_GROUP_PUMP_RETRY_RATIO_P23",
- "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@) * 100",
+ "MetricExpr": "(hv_24x7@PM_PB_RTY_VG_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_VG_PUMP23\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
@@ -61,13 +61,13 @@
},
{
"MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P01",
- "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@) * 100",
+ "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP01\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP01\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "REMOTE_NODE_PUMPS_RETRIES_RATIO_P23",
- "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@) * 100",
+ "MetricExpr": "(hv_24x7@PM_PB_RTY_RNS_PUMP23\\,chip\\=?@ / (1 + hv_24x7@PM_PB_RNS_PUMP23\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
@@ -151,193 +151,193 @@
},
{
"MetricName": "XLINK0_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK1_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK2_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK3_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK4_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK5_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK6_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK7_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK0_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK1_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK2_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK3_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK4_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK5_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK6_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "XLINK7_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_XLINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_XLINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_XLINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK0_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK1_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK2_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK3_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK4_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK5_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK6_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK7_OUT_TOTAL_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_TOTAL_UTIL\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_TOTAL_UTIL\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK0_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK0_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK0_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK0_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK1_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK1_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK1_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK1_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK2_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK2_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK2_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK2_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK3_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK3_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK3_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK3_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK4_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK4_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK4_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK4_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK5_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK5_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK5_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK5_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK6_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK6_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK6_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK6_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
{
"MetricName": "ALINK7_OUT_DATA_UTILIZATION",
- "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
+ "MetricExpr": "((hv_24x7@PM_ALINK7_OUT_ODD_DATA\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_DATA\\,chip\\=?@) / (1 + hv_24x7@PM_ALINK7_OUT_ODD_AVLBL_CYCLES\\,chip\\=?@ + hv_24x7@PM_ALINK7_OUT_EVEN_AVLBL_CYCLES\\,chip\\=?@)) * 100",
"ScaleUnit": "1.063%",
"AggregationMode": "PerChip"
},
diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json
index cf8563d059b9..cf8563d059b9 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z16/pai.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z16/pai_crypto.json
diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh
index 4c0aabbe33bd..f5ed7b1af419 100755
--- a/tools/perf/tests/shell/test_intel_pt.sh
+++ b/tools/perf/tests/shell/test_intel_pt.sh
@@ -526,6 +526,12 @@ test_kernel_trace()
test_virtual_lbr()
{
echo "--- Test virtual LBR ---"
+ # Check if python script is supported
+ libpython=$(perf version --build-options | grep python | grep -cv OFF)
+ if [ "${libpython}" != "1" ] ; then
+ echo "SKIP: python scripting is not supported"
+ return 2
+ fi
# Python script to determine the maximum size of branch stacks
cat << "_end_of_file_" > "${maxbrstack}"
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 110f0c609d84..5f5320f7c6e2 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -66,6 +66,7 @@ size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_a
P_FLAG(BLOCKS);
P_FLAG(BTIME);
P_FLAG(MNT_ID);
+ P_FLAG(DIOALIGN);
#undef P_FLAG
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 60d8beb662aa..46ada5ec3f9a 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -2325,11 +2325,19 @@ struct sym_args {
bool near;
};
+static bool kern_sym_name_match(const char *kname, const char *name)
+{
+ size_t n = strlen(name);
+
+ return !strcmp(kname, name) ||
+ (!strncmp(kname, name, n) && kname[n] == '\t');
+}
+
static bool kern_sym_match(struct sym_args *args, const char *name, char type)
{
/* A function with the same name, and global or the n'th found or any */
return kallsyms__is_function(type) &&
- !strcmp(name, args->name) &&
+ kern_sym_name_match(name, args->name) &&
((args->global && isupper(type)) ||
(args->selected && ++(args->cnt) == args->idx) ||
(!args->global && !args->selected));
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index eee64ddb766d..cc7c1f90cf62 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -36,6 +36,11 @@ struct btf *btf__load_from_kernel_by_id(__u32 id)
#endif
#ifndef HAVE_LIBBPF_BPF_PROG_LOAD
+LIBBPF_API int bpf_load_program(enum bpf_prog_type type,
+ const struct bpf_insn *insns, size_t insns_cnt,
+ const char *license, __u32 kern_version,
+ char *log_buf, size_t log_buf_sz);
+
int bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name __maybe_unused,
const char *license,
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index d657594894cf..f4adeccdbbcb 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -36,6 +36,24 @@
#include <internal/xyarray.h>
+#ifndef HAVE_LIBBPF_BPF_PROGRAM__SET_INSNS
+int bpf_program__set_insns(struct bpf_program *prog __maybe_unused,
+ struct bpf_insn *new_insns __maybe_unused, size_t new_insn_cnt __maybe_unused)
+{
+ pr_err("%s: not support, update libbpf\n", __func__);
+ return -ENOTSUP;
+}
+
+int libbpf_register_prog_handler(const char *sec __maybe_unused,
+ enum bpf_prog_type prog_type __maybe_unused,
+ enum bpf_attach_type exp_attach_type __maybe_unused,
+ const struct libbpf_prog_handler_opts *opts __maybe_unused)
+{
+ pr_err("%s: not support, update libbpf\n", __func__);
+ return -ENOTSUP;
+}
+#endif
+
/* temporarily disable libbpf deprecation warnings */
#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index aa0c5179836d..75e2248416f5 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -115,4 +115,17 @@
SYM_ALIAS(alias, name, SYM_T_FUNC, SYM_L_WEAK)
#endif
+// In the kernel sources (include/linux/cfi_types.h), this has a different
+// definition when CONFIG_CFI_CLANG is used, for tools/ just use the !clang
+// definition:
+#ifndef SYM_TYPED_START
+#define SYM_TYPED_START(name, linkage, align...) \
+ SYM_START(name, linkage, align)
+#endif
+
+#ifndef SYM_TYPED_FUNC_START
+#define SYM_TYPED_FUNC_START(name) \
+ SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
+#endif
+
#endif /* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/power/pm-graph/README b/tools/power/pm-graph/README
index e6020c0d59ec..3213dbe63b74 100644
--- a/tools/power/pm-graph/README
+++ b/tools/power/pm-graph/README
@@ -6,22 +6,22 @@
|_| |___/ |_|
pm-graph: suspend/resume/boot timing analysis tools
- Version: 5.9
+ Version: 5.10
Author: Todd Brandt <todd.e.brandt@intel.com>
- Home Page: https://01.org/pm-graph
+ Home Page: https://www.intel.com/content/www/us/en/developer/topic-technology/open/pm-graph/overview.html
Report bugs/issues at bugzilla.kernel.org Tools/pm-graph
- https://bugzilla.kernel.org/buglist.cgi?component=pm-graph&product=Tools
Full documentation available online & in man pages
- Getting Started:
- https://01.org/pm-graph/documentation/getting-started
+ https://www.intel.com/content/www/us/en/developer/articles/technical/usage.html
- - Config File Format:
- https://01.org/pm-graph/documentation/3-config-file-format
+ - Feature Summary:
+ https://www.intel.com/content/www/us/en/developer/topic-technology/open/pm-graph/features.html
- upstream version in git:
- https://github.com/intel/pm-graph/
+ git clone https://github.com/intel/pm-graph/
Table of Contents
- Overview
diff --git a/tools/power/pm-graph/sleepgraph.8 b/tools/power/pm-graph/sleepgraph.8
index 5126271de98a..643271b6fc6f 100644
--- a/tools/power/pm-graph/sleepgraph.8
+++ b/tools/power/pm-graph/sleepgraph.8
@@ -78,6 +78,9 @@ This helps maintain the consistency of test data for better comparison.
If a wifi connection is available, check that it reconnects after resume. Include
the reconnect time in the total resume time calculation and treat wifi timeouts
as resume failures.
+.TP
+\fB-wifitrace\fR
+Trace through the wifi reconnect time and include it in the timeline.
.SS "advanced"
.TP
diff --git a/tools/power/pm-graph/sleepgraph.py b/tools/power/pm-graph/sleepgraph.py
index 33981adcdd68..cfe343306e08 100755
--- a/tools/power/pm-graph/sleepgraph.py
+++ b/tools/power/pm-graph/sleepgraph.py
@@ -86,7 +86,7 @@ def ascii(text):
# store system values and test parameters
class SystemValues:
title = 'SleepGraph'
- version = '5.9'
+ version = '5.10'
ansi = False
rs = 0
display = ''
@@ -100,6 +100,7 @@ class SystemValues:
ftracelog = False
acpidebug = True
tstat = True
+ wifitrace = False
mindevlen = 0.0001
mincglen = 0.0
cgphase = ''
@@ -124,6 +125,7 @@ class SystemValues:
epath = '/sys/kernel/debug/tracing/events/power/'
pmdpath = '/sys/power/pm_debug_messages'
s0ixpath = '/sys/module/intel_pmc_core/parameters/warn_on_s0ix_failures'
+ s0ixres = '/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us'
acpipath='/sys/module/acpi/parameters/debug_level'
traceevents = [
'suspend_resume',
@@ -180,6 +182,7 @@ class SystemValues:
tmstart = 'SUSPEND START %Y%m%d-%H:%M:%S.%f'
tmend = 'RESUME COMPLETE %Y%m%d-%H:%M:%S.%f'
tracefuncs = {
+ 'async_synchronize_full': {},
'sys_sync': {},
'ksys_sync': {},
'__pm_notifier_call_chain': {},
@@ -304,6 +307,7 @@ class SystemValues:
[2, 'suspendstats', 'sh', '-c', 'grep -v invalid /sys/power/suspend_stats/*'],
[2, 'cpuidle', 'sh', '-c', 'grep -v invalid /sys/devices/system/cpu/cpu*/cpuidle/state*/s2idle/*'],
[2, 'battery', 'sh', '-c', 'grep -v invalid /sys/class/power_supply/*/*'],
+ [2, 'thermal', 'sh', '-c', 'grep . /sys/class/thermal/thermal_zone*/temp'],
]
cgblacklist = []
kprobes = dict()
@@ -777,7 +781,7 @@ class SystemValues:
return
if not quiet:
sysvals.printSystemInfo(False)
- pprint('INITIALIZING FTRACE...')
+ pprint('INITIALIZING FTRACE')
# turn trace off
self.fsetVal('0', 'tracing_on')
self.cleanupFtrace()
@@ -841,7 +845,7 @@ class SystemValues:
for name in self.dev_tracefuncs:
self.defaultKprobe(name, self.dev_tracefuncs[name])
if not quiet:
- pprint('INITIALIZING KPROBES...')
+ pprint('INITIALIZING KPROBES')
self.addKprobes(self.verbose)
if(self.usetraceevents):
# turn trace events on
@@ -1133,6 +1137,15 @@ class SystemValues:
self.cfgdef[file] = fp.read().strip()
fp.write(value)
fp.close()
+ def s0ixSupport(self):
+ if not os.path.exists(self.s0ixres) or not os.path.exists(self.mempowerfile):
+ return False
+ fp = open(sysvals.mempowerfile, 'r')
+ data = fp.read().strip()
+ fp.close()
+ if '[s2idle]' in data:
+ return True
+ return False
def haveTurbostat(self):
if not self.tstat:
return False
@@ -1146,7 +1159,7 @@ class SystemValues:
self.vprint(out)
return True
return False
- def turbostat(self):
+ def turbostat(self, s0ixready):
cmd = self.getExec('turbostat')
rawout = keyline = valline = ''
fullcmd = '%s -q -S echo freeze > %s' % (cmd, self.powerfile)
@@ -1173,6 +1186,8 @@ class SystemValues:
for key in keyline:
idx = keyline.index(key)
val = valline[idx]
+ if key == 'SYS%LPI' and not s0ixready and re.match('^[0\.]*$', val):
+ continue
out.append('%s=%s' % (key, val))
return '|'.join(out)
def netfixon(self, net='both'):
@@ -1183,14 +1198,6 @@ class SystemValues:
out = ascii(fp.read()).strip()
fp.close()
return out
- def wifiRepair(self):
- out = self.netfixon('wifi')
- if not out or 'error' in out.lower():
- return ''
- m = re.match('WIFI \S* ONLINE (?P<action>\S*)', out)
- if not m:
- return 'dead'
- return m.group('action')
def wifiDetails(self, dev):
try:
info = open('/sys/class/net/%s/device/uevent' % dev, 'r').read().strip()
@@ -1220,11 +1227,6 @@ class SystemValues:
return '%s reconnected %.2f' % \
(self.wifiDetails(dev), max(0, time.time() - start))
time.sleep(0.01)
- if self.netfix:
- res = self.wifiRepair()
- if res:
- timeout = max(0, time.time() - start)
- return '%s %s %d' % (self.wifiDetails(dev), res, timeout)
return '%s timeout %d' % (self.wifiDetails(dev), timeout)
def errorSummary(self, errinfo, msg):
found = False
@@ -1346,6 +1348,20 @@ class SystemValues:
for i in self.rslist:
self.setVal(self.rstgt, i)
pprint('runtime suspend settings restored on %d devices' % len(self.rslist))
+ def start(self, pm):
+ if self.useftrace:
+ self.dlog('start ftrace tracing')
+ self.fsetVal('1', 'tracing_on')
+ if self.useprocmon:
+ self.dlog('start the process monitor')
+ pm.start()
+ def stop(self, pm):
+ if self.useftrace:
+ if self.useprocmon:
+ self.dlog('stop the process monitor')
+ pm.stop()
+ self.dlog('stop ftrace tracing')
+ self.fsetVal('0', 'tracing_on')
sysvals = SystemValues()
switchvalues = ['enable', 'disable', 'on', 'off', 'true', 'false', '1', '0']
@@ -1643,19 +1659,20 @@ class Data:
ubiquitous = False
if kprobename in dtf and 'ub' in dtf[kprobename]:
ubiquitous = True
- title = cdata+' '+rdata
- mstr = '\(.*\) *(?P<args>.*) *\((?P<caller>.*)\+.* arg1=(?P<ret>.*)'
- m = re.match(mstr, title)
- if m:
- c = m.group('caller')
- a = m.group('args').strip()
- r = m.group('ret')
+ mc = re.match('\(.*\) *(?P<args>.*)', cdata)
+ mr = re.match('\((?P<caller>\S*).* arg1=(?P<ret>.*)', rdata)
+ if mc and mr:
+ c = mr.group('caller').split('+')[0]
+ a = mc.group('args').strip()
+ r = mr.group('ret')
if len(r) > 6:
r = ''
else:
r = 'ret=%s ' % r
if ubiquitous and c in dtf and 'ub' in dtf[c]:
return False
+ else:
+ return False
color = sysvals.kprobeColor(kprobename)
e = DevFunction(displayname, a, c, r, start, end, ubiquitous, proc, pid, color)
tgtdev['src'].append(e)
@@ -1772,6 +1789,14 @@ class Data:
e.time = self.trimTimeVal(e.time, t0, dT, left)
e.end = self.trimTimeVal(e.end, t0, dT, left)
e.length = e.end - e.time
+ if('cpuexec' in d):
+ cpuexec = dict()
+ for e in d['cpuexec']:
+ c0, cN = e
+ c0 = self.trimTimeVal(c0, t0, dT, left)
+ cN = self.trimTimeVal(cN, t0, dT, left)
+ cpuexec[(c0, cN)] = d['cpuexec'][e]
+ d['cpuexec'] = cpuexec
for dir in ['suspend', 'resume']:
list = []
for e in self.errorinfo[dir]:
@@ -2086,75 +2111,43 @@ class Data:
return d
def addProcessUsageEvent(self, name, times):
# get the start and end times for this process
- maxC = 0
- tlast = 0
- start = -1
- end = -1
+ cpuexec = dict()
+ tlast = start = end = -1
for t in sorted(times):
- if tlast == 0:
+ if tlast < 0:
tlast = t
continue
- if name in self.pstl[t]:
- if start == -1 or tlast < start:
+ if name in self.pstl[t] and self.pstl[t][name] > 0:
+ if start < 0:
start = tlast
- if end == -1 or t > end:
- end = t
+ end, key = t, (tlast, t)
+ maxj = (t - tlast) * 1024.0
+ cpuexec[key] = min(1.0, float(self.pstl[t][name]) / maxj)
tlast = t
- if start == -1 or end == -1:
- return 0
+ if start < 0 or end < 0:
+ return
# add a new action for this process and get the object
out = self.newActionGlobal(name, start, end, -3)
- if not out:
- return 0
- phase, devname = out
- dev = self.dmesg[phase]['list'][devname]
- # get the cpu exec data
- tlast = 0
- clast = 0
- cpuexec = dict()
- for t in sorted(times):
- if tlast == 0 or t <= start or t > end:
- tlast = t
- continue
- list = self.pstl[t]
- c = 0
- if name in list:
- c = list[name]
- if c > maxC:
- maxC = c
- if c != clast:
- key = (tlast, t)
- cpuexec[key] = c
- tlast = t
- clast = c
- dev['cpuexec'] = cpuexec
- return maxC
+ if out:
+ phase, devname = out
+ dev = self.dmesg[phase]['list'][devname]
+ dev['cpuexec'] = cpuexec
def createProcessUsageEvents(self):
- # get an array of process names
- proclist = []
- for t in sorted(self.pstl):
- pslist = self.pstl[t]
- for ps in sorted(pslist):
- if ps not in proclist:
- proclist.append(ps)
- # get a list of data points for suspend and resume
- tsus = []
- tres = []
+ # get an array of process names and times
+ proclist = {'sus': dict(), 'res': dict()}
+ tdata = {'sus': [], 'res': []}
for t in sorted(self.pstl):
- if t < self.tSuspended:
- tsus.append(t)
- else:
- tres.append(t)
+ dir = 'sus' if t < self.tSuspended else 'res'
+ for ps in sorted(self.pstl[t]):
+ if ps not in proclist[dir]:
+ proclist[dir][ps] = 0
+ tdata[dir].append(t)
# process the events for suspend and resume
- if len(proclist) > 0:
+ if len(proclist['sus']) > 0 or len(proclist['res']) > 0:
sysvals.vprint('Process Execution:')
- for ps in proclist:
- c = self.addProcessUsageEvent(ps, tsus)
- if c > 0:
- sysvals.vprint('%25s (sus): %d' % (ps, c))
- c = self.addProcessUsageEvent(ps, tres)
- if c > 0:
- sysvals.vprint('%25s (res): %d' % (ps, c))
+ for dir in ['sus', 'res']:
+ for ps in sorted(proclist[dir]):
+ self.addProcessUsageEvent(ps, tdata[dir])
def handleEndMarker(self, time, msg=''):
dm = self.dmesg
self.setEnd(time, msg)
@@ -3218,7 +3211,7 @@ class ProcessMonitor:
# markers, and/or kprobes required for primary parsing.
def doesTraceLogHaveTraceEvents():
kpcheck = ['_cal: (', '_ret: (']
- techeck = ['suspend_resume', 'device_pm_callback']
+ techeck = ['suspend_resume', 'device_pm_callback', 'tracing_mark_write']
tmcheck = ['SUSPEND START', 'RESUME COMPLETE']
sysvals.usekprobes = False
fp = sysvals.openlog(sysvals.ftracefile, 'r')
@@ -3241,7 +3234,7 @@ def doesTraceLogHaveTraceEvents():
check.remove(i)
tmcheck = check
fp.close()
- sysvals.usetraceevents = True if len(techeck) < 2 else False
+ sysvals.usetraceevents = True if len(techeck) < 3 else False
sysvals.usetracemarkers = True if len(tmcheck) == 0 else False
# Function: appendIncompleteTraceLog
@@ -3456,6 +3449,8 @@ def parseTraceLog(live=False):
continue
# process cpu exec line
if t.type == 'tracing_mark_write':
+ if t.name == 'CMD COMPLETE' and data.tKernRes == 0:
+ data.tKernRes = t.time
m = re.match(tp.procexecfmt, t.name)
if(m):
parts, msg = 1, m.group('ps')
@@ -3674,6 +3669,9 @@ def parseTraceLog(live=False):
e = next((x for x in reversed(tp.ktemp[key]) if x['end'] < 0), 0)
if not e:
continue
+ if (t.time - e['begin']) * 1000 < sysvals.mindevlen:
+ tp.ktemp[key].pop()
+ continue
e['end'] = t.time
e['rdata'] = kprobedata
# end of kernel resume
@@ -4213,6 +4211,8 @@ def callgraphHTML(sv, hf, num, cg, title, color, devid):
fmt = '<n>(%.3f ms @ '+sv.timeformat+')</n>'
flen = fmt % (line.length*1000, line.time)
if line.isLeaf():
+ if line.length * 1000 < sv.mincglen:
+ continue
hf.write(html_func_leaf.format(line.name, flen))
elif line.freturn:
hf.write(html_func_end)
@@ -4827,14 +4827,11 @@ def createHTML(testruns, testfail):
if('cpuexec' in dev):
for t in sorted(dev['cpuexec']):
start, end = t
- j = float(dev['cpuexec'][t]) / 5
- if j > 1.0:
- j = 1.0
height = '%.3f' % (rowheight/3)
top = '%.3f' % (rowtop + devtl.scaleH + 2*rowheight/3)
left = '%f' % (((start-m0)*100)/mTotal)
width = '%f' % ((end-start)*100/mTotal)
- color = 'rgba(255, 0, 0, %f)' % j
+ color = 'rgba(255, 0, 0, %f)' % dev['cpuexec'][t]
devtl.html += \
html_cpuexec.format(left, top, height, width, color)
if('src' not in dev):
@@ -5453,17 +5450,9 @@ def executeSuspend(quiet=False):
call('sync', shell=True)
sv.dlog('read dmesg')
sv.initdmesg()
- # start ftrace
- if sv.useftrace:
- if not quiet:
- pprint('START TRACING')
- sv.dlog('start ftrace tracing')
- sv.fsetVal('1', 'tracing_on')
- if sv.useprocmon:
- sv.dlog('start the process monitor')
- pm.start()
- sv.dlog('run the cmdinfo list before')
+ sv.dlog('cmdinfo before')
sv.cmdinfo(True)
+ sv.start(pm)
# execute however many s/r runs requested
for count in range(1,sv.execcount+1):
# x2delay in between test runs
@@ -5500,6 +5489,7 @@ def executeSuspend(quiet=False):
if res != 0:
tdata['error'] = 'cmd returned %d' % res
else:
+ s0ixready = sv.s0ixSupport()
mode = sv.suspendmode
if sv.memmode and os.path.exists(sv.mempowerfile):
mode = 'mem'
@@ -5509,9 +5499,10 @@ def executeSuspend(quiet=False):
sv.testVal(sv.diskpowerfile, 'radio', sv.diskmode)
if sv.acpidebug:
sv.testVal(sv.acpipath, 'acpi', '0xe')
- if mode == 'freeze' and sv.haveTurbostat():
+ if ((mode == 'freeze') or (sv.memmode == 's2idle')) \
+ and sv.haveTurbostat():
# execution will pause here
- turbo = sv.turbostat()
+ turbo = sv.turbostat(s0ixready)
if turbo:
tdata['turbo'] = turbo
else:
@@ -5522,7 +5513,8 @@ def executeSuspend(quiet=False):
pf.close()
except Exception as e:
tdata['error'] = str(e)
- sv.dlog('system returned from resume')
+ sv.fsetVal('CMD COMPLETE', 'trace_marker')
+ sv.dlog('system returned')
# reset everything
sv.testVal('restoreall')
if(sv.rtcwake):
@@ -5535,33 +5527,29 @@ def executeSuspend(quiet=False):
sv.fsetVal('WAIT END', 'trace_marker')
# return from suspend
pprint('RESUME COMPLETE')
- sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker')
+ if(count < sv.execcount):
+ sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker')
+ elif(not sv.wifitrace):
+ sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker')
+ sv.stop(pm)
if sv.wifi and wifi:
tdata['wifi'] = sv.pollWifi(wifi)
sv.dlog('wifi check, %s' % tdata['wifi'])
- if sv.netfix:
- netfixout = sv.netfixon('wired')
- elif sv.netfix:
- netfixout = sv.netfixon()
- if sv.netfix and netfixout:
- tdata['netfix'] = netfixout
+ if(count == sv.execcount and sv.wifitrace):
+ sv.fsetVal(datetime.now().strftime(sv.tmend), 'trace_marker')
+ sv.stop(pm)
+ if sv.netfix:
+ tdata['netfix'] = sv.netfixon()
sv.dlog('netfix, %s' % tdata['netfix'])
if(sv.suspendmode == 'mem' or sv.suspendmode == 'command'):
sv.dlog('read the ACPI FPDT')
tdata['fw'] = getFPDT(False)
testdata.append(tdata)
- sv.dlog('run the cmdinfo list after')
+ sv.dlog('cmdinfo after')
cmdafter = sv.cmdinfo(False)
- # stop ftrace
- if sv.useftrace:
- if sv.useprocmon:
- sv.dlog('stop the process monitor')
- pm.stop()
- sv.fsetVal('0', 'tracing_on')
# grab a copy of the dmesg output
if not quiet:
pprint('CAPTURING DMESG')
- sysvals.dlog('EXECUTION TRACE END')
sv.getdmesg(testdata)
# grab a copy of the ftrace output
if sv.useftrace:
@@ -6350,6 +6338,8 @@ def data_from_html(file, outpath, issues, fulldetail=False):
if not m:
continue
name, time, phase = m.group('n'), m.group('t'), m.group('p')
+ if name == 'async_synchronize_full':
+ continue
if ' async' in name or ' sync' in name:
name = ' '.join(name.split(' ')[:-1])
if phase.startswith('suspend'):
@@ -6701,6 +6691,7 @@ def printHelp():
' -skiphtml Run the test and capture the trace logs, but skip the timeline (default: disabled)\n'\
' -result fn Export a results table to a text file for parsing.\n'\
' -wifi If a wifi connection is available, check that it reconnects after resume.\n'\
+ ' -wifitrace Trace kernel execution through wifi reconnect.\n'\
' -netfix Use netfix to reset the network in the event it fails to resume.\n'\
' [testprep]\n'\
' -sync Sync the filesystems before starting the test\n'\
@@ -6828,6 +6819,8 @@ if __name__ == '__main__':
sysvals.sync = True
elif(arg == '-wifi'):
sysvals.wifi = True
+ elif(arg == '-wifitrace'):
+ sysvals.wifitrace = True
elif(arg == '-netfix'):
sysvals.netfix = True
elif(arg == '-gzip'):
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index a072b2d3e726..7edce12fd2ce 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -12,30 +12,62 @@
#include "mock.h"
#define NR_CXL_HOST_BRIDGES 2
+#define NR_CXL_SINGLE_HOST 1
#define NR_CXL_ROOT_PORTS 2
#define NR_CXL_SWITCH_PORTS 2
#define NR_CXL_PORT_DECODERS 8
static struct platform_device *cxl_acpi;
static struct platform_device *cxl_host_bridge[NR_CXL_HOST_BRIDGES];
-static struct platform_device
- *cxl_root_port[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS];
-static struct platform_device
- *cxl_switch_uport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS];
-static struct platform_device
- *cxl_switch_dport[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS *
- NR_CXL_SWITCH_PORTS];
-struct platform_device
- *cxl_mem[NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS];
+#define NR_MULTI_ROOT (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS)
+static struct platform_device *cxl_root_port[NR_MULTI_ROOT];
+static struct platform_device *cxl_switch_uport[NR_MULTI_ROOT];
+#define NR_MEM_MULTI \
+ (NR_CXL_HOST_BRIDGES * NR_CXL_ROOT_PORTS * NR_CXL_SWITCH_PORTS)
+static struct platform_device *cxl_switch_dport[NR_MEM_MULTI];
+
+static struct platform_device *cxl_hb_single[NR_CXL_SINGLE_HOST];
+static struct platform_device *cxl_root_single[NR_CXL_SINGLE_HOST];
+static struct platform_device *cxl_swu_single[NR_CXL_SINGLE_HOST];
+#define NR_MEM_SINGLE (NR_CXL_SINGLE_HOST * NR_CXL_SWITCH_PORTS)
+static struct platform_device *cxl_swd_single[NR_MEM_SINGLE];
+
+struct platform_device *cxl_mem[NR_MEM_MULTI];
+struct platform_device *cxl_mem_single[NR_MEM_SINGLE];
+
+
+static inline bool is_multi_bridge(struct device *dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++)
+ if (&cxl_host_bridge[i]->dev == dev)
+ return true;
+ return false;
+}
+
+static inline bool is_single_bridge(struct device *dev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++)
+ if (&cxl_hb_single[i]->dev == dev)
+ return true;
+ return false;
+}
static struct acpi_device acpi0017_mock;
-static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES] = {
+static struct acpi_device host_bridge[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST] = {
[0] = {
.handle = &host_bridge[0],
},
[1] = {
.handle = &host_bridge[1],
},
+ [2] = {
+ .handle = &host_bridge[2],
+ },
+
};
static bool is_mock_dev(struct device *dev)
@@ -45,6 +77,9 @@ static bool is_mock_dev(struct device *dev)
for (i = 0; i < ARRAY_SIZE(cxl_mem); i++)
if (dev == &cxl_mem[i]->dev)
return true;
+ for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++)
+ if (dev == &cxl_mem_single[i]->dev)
+ return true;
if (dev == &cxl_acpi->dev)
return true;
return false;
@@ -66,7 +101,7 @@ static bool is_mock_adev(struct acpi_device *adev)
static struct {
struct acpi_table_cedt cedt;
- struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES];
+ struct acpi_cedt_chbs chbs[NR_CXL_HOST_BRIDGES + NR_CXL_SINGLE_HOST];
struct {
struct acpi_cedt_cfmws cfmws;
u32 target[1];
@@ -83,6 +118,10 @@ static struct {
struct acpi_cedt_cfmws cfmws;
u32 target[2];
} cfmws3;
+ struct {
+ struct acpi_cedt_cfmws cfmws;
+ u32 target[1];
+ } cfmws4;
} __packed mock_cedt = {
.cedt = {
.header = {
@@ -107,6 +146,14 @@ static struct {
.uid = 1,
.cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20,
},
+ .chbs[2] = {
+ .header = {
+ .type = ACPI_CEDT_TYPE_CHBS,
+ .length = sizeof(mock_cedt.chbs[0]),
+ },
+ .uid = 2,
+ .cxl_version = ACPI_CEDT_CHBS_VERSION_CXL20,
+ },
.cfmws0 = {
.cfmws = {
.header = {
@@ -167,13 +214,29 @@ static struct {
},
.target = { 0, 1, },
},
+ .cfmws4 = {
+ .cfmws = {
+ .header = {
+ .type = ACPI_CEDT_TYPE_CFMWS,
+ .length = sizeof(mock_cedt.cfmws4),
+ },
+ .interleave_ways = 0,
+ .granularity = 4,
+ .restrictions = ACPI_CEDT_CFMWS_RESTRICT_TYPE3 |
+ ACPI_CEDT_CFMWS_RESTRICT_PMEM,
+ .qtg_id = 4,
+ .window_size = SZ_256M * 4UL,
+ },
+ .target = { 2 },
+ },
};
-struct acpi_cedt_cfmws *mock_cfmws[4] = {
+struct acpi_cedt_cfmws *mock_cfmws[] = {
[0] = &mock_cedt.cfmws0.cfmws,
[1] = &mock_cedt.cfmws1.cfmws,
[2] = &mock_cedt.cfmws2.cfmws,
[3] = &mock_cedt.cfmws3.cfmws,
+ [4] = &mock_cedt.cfmws4.cfmws,
};
struct cxl_mock_res {
@@ -304,6 +367,9 @@ static bool is_mock_bridge(struct device *dev)
for (i = 0; i < ARRAY_SIZE(cxl_host_bridge); i++)
if (dev == &cxl_host_bridge[i]->dev)
return true;
+ for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++)
+ if (dev == &cxl_hb_single[i]->dev)
+ return true;
return false;
}
@@ -326,6 +392,18 @@ static bool is_mock_port(struct device *dev)
if (dev == &cxl_switch_dport[i]->dev)
return true;
+ for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++)
+ if (dev == &cxl_root_single[i]->dev)
+ return true;
+
+ for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++)
+ if (dev == &cxl_swu_single[i]->dev)
+ return true;
+
+ for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++)
+ if (dev == &cxl_swd_single[i]->dev)
+ return true;
+
if (is_cxl_memdev(dev))
return is_mock_dev(dev->parent);
@@ -561,11 +639,31 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port)
int i, array_size;
if (port->depth == 1) {
- array_size = ARRAY_SIZE(cxl_root_port);
- array = cxl_root_port;
+ if (is_multi_bridge(port->uport)) {
+ array_size = ARRAY_SIZE(cxl_root_port);
+ array = cxl_root_port;
+ } else if (is_single_bridge(port->uport)) {
+ array_size = ARRAY_SIZE(cxl_root_single);
+ array = cxl_root_single;
+ } else {
+ dev_dbg(&port->dev, "%s: unknown bridge type\n",
+ dev_name(port->uport));
+ return -ENXIO;
+ }
} else if (port->depth == 2) {
- array_size = ARRAY_SIZE(cxl_switch_dport);
- array = cxl_switch_dport;
+ struct cxl_port *parent = to_cxl_port(port->dev.parent);
+
+ if (is_multi_bridge(parent->uport)) {
+ array_size = ARRAY_SIZE(cxl_switch_dport);
+ array = cxl_switch_dport;
+ } else if (is_single_bridge(parent->uport)) {
+ array_size = ARRAY_SIZE(cxl_swd_single);
+ array = cxl_swd_single;
+ } else {
+ dev_dbg(&port->dev, "%s: unknown bridge type\n",
+ dev_name(port->uport));
+ return -ENXIO;
+ }
} else {
dev_WARN_ONCE(&port->dev, 1, "unexpected depth %d\n",
port->depth);
@@ -576,8 +674,12 @@ static int mock_cxl_port_enumerate_dports(struct cxl_port *port)
struct platform_device *pdev = array[i];
struct cxl_dport *dport;
- if (pdev->dev.parent != port->uport)
+ if (pdev->dev.parent != port->uport) {
+ dev_dbg(&port->dev, "%s: mismatch parent %s\n",
+ dev_name(port->uport),
+ dev_name(pdev->dev.parent));
continue;
+ }
dport = devm_cxl_add_dport(port, &pdev->dev, pdev->id,
CXL_RESOURCE_NONE);
@@ -627,6 +729,157 @@ static void mock_companion(struct acpi_device *adev, struct device *dev)
#define SZ_512G (SZ_64G * 8)
#endif
+static __init int cxl_single_init(void)
+{
+ int i, rc;
+
+ for (i = 0; i < ARRAY_SIZE(cxl_hb_single); i++) {
+ struct acpi_device *adev =
+ &host_bridge[NR_CXL_HOST_BRIDGES + i];
+ struct platform_device *pdev;
+
+ pdev = platform_device_alloc("cxl_host_bridge",
+ NR_CXL_HOST_BRIDGES + i);
+ if (!pdev)
+ goto err_bridge;
+
+ mock_companion(adev, &pdev->dev);
+ rc = platform_device_add(pdev);
+ if (rc) {
+ platform_device_put(pdev);
+ goto err_bridge;
+ }
+
+ cxl_hb_single[i] = pdev;
+ rc = sysfs_create_link(&pdev->dev.kobj, &pdev->dev.kobj,
+ "physical_node");
+ if (rc)
+ goto err_bridge;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cxl_root_single); i++) {
+ struct platform_device *bridge =
+ cxl_hb_single[i % ARRAY_SIZE(cxl_hb_single)];
+ struct platform_device *pdev;
+
+ pdev = platform_device_alloc("cxl_root_port",
+ NR_MULTI_ROOT + i);
+ if (!pdev)
+ goto err_port;
+ pdev->dev.parent = &bridge->dev;
+
+ rc = platform_device_add(pdev);
+ if (rc) {
+ platform_device_put(pdev);
+ goto err_port;
+ }
+ cxl_root_single[i] = pdev;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cxl_swu_single); i++) {
+ struct platform_device *root_port = cxl_root_single[i];
+ struct platform_device *pdev;
+
+ pdev = platform_device_alloc("cxl_switch_uport",
+ NR_MULTI_ROOT + i);
+ if (!pdev)
+ goto err_uport;
+ pdev->dev.parent = &root_port->dev;
+
+ rc = platform_device_add(pdev);
+ if (rc) {
+ platform_device_put(pdev);
+ goto err_uport;
+ }
+ cxl_swu_single[i] = pdev;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cxl_swd_single); i++) {
+ struct platform_device *uport =
+ cxl_swu_single[i % ARRAY_SIZE(cxl_swu_single)];
+ struct platform_device *pdev;
+
+ pdev = platform_device_alloc("cxl_switch_dport",
+ i + NR_MEM_MULTI);
+ if (!pdev)
+ goto err_dport;
+ pdev->dev.parent = &uport->dev;
+
+ rc = platform_device_add(pdev);
+ if (rc) {
+ platform_device_put(pdev);
+ goto err_dport;
+ }
+ cxl_swd_single[i] = pdev;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cxl_mem_single); i++) {
+ struct platform_device *dport = cxl_swd_single[i];
+ struct platform_device *pdev;
+
+ pdev = platform_device_alloc("cxl_mem", NR_MEM_MULTI + i);
+ if (!pdev)
+ goto err_mem;
+ pdev->dev.parent = &dport->dev;
+ set_dev_node(&pdev->dev, i % 2);
+
+ rc = platform_device_add(pdev);
+ if (rc) {
+ platform_device_put(pdev);
+ goto err_mem;
+ }
+ cxl_mem_single[i] = pdev;
+ }
+
+ return 0;
+
+err_mem:
+ for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_mem_single[i]);
+err_dport:
+ for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_swd_single[i]);
+err_uport:
+ for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_swu_single[i]);
+err_port:
+ for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_root_single[i]);
+err_bridge:
+ for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) {
+ struct platform_device *pdev = cxl_hb_single[i];
+
+ if (!pdev)
+ continue;
+ sysfs_remove_link(&pdev->dev.kobj, "physical_node");
+ platform_device_unregister(cxl_hb_single[i]);
+ }
+
+ return rc;
+}
+
+static void cxl_single_exit(void)
+{
+ int i;
+
+ for (i = ARRAY_SIZE(cxl_mem_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_mem_single[i]);
+ for (i = ARRAY_SIZE(cxl_swd_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_swd_single[i]);
+ for (i = ARRAY_SIZE(cxl_swu_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_swu_single[i]);
+ for (i = ARRAY_SIZE(cxl_root_single) - 1; i >= 0; i--)
+ platform_device_unregister(cxl_root_single[i]);
+ for (i = ARRAY_SIZE(cxl_hb_single) - 1; i >= 0; i--) {
+ struct platform_device *pdev = cxl_hb_single[i];
+
+ if (!pdev)
+ continue;
+ sysfs_remove_link(&pdev->dev.kobj, "physical_node");
+ platform_device_unregister(cxl_hb_single[i]);
+ }
+}
+
static __init int cxl_test_init(void)
{
int rc, i;
@@ -695,7 +948,7 @@ static __init int cxl_test_init(void)
pdev = platform_device_alloc("cxl_switch_uport", i);
if (!pdev)
- goto err_port;
+ goto err_uport;
pdev->dev.parent = &root_port->dev;
rc = platform_device_add(pdev);
@@ -713,7 +966,7 @@ static __init int cxl_test_init(void)
pdev = platform_device_alloc("cxl_switch_dport", i);
if (!pdev)
- goto err_port;
+ goto err_dport;
pdev->dev.parent = &uport->dev;
rc = platform_device_add(pdev);
@@ -724,7 +977,6 @@ static __init int cxl_test_init(void)
cxl_switch_dport[i] = pdev;
}
- BUILD_BUG_ON(ARRAY_SIZE(cxl_mem) != ARRAY_SIZE(cxl_switch_dport));
for (i = 0; i < ARRAY_SIZE(cxl_mem); i++) {
struct platform_device *dport = cxl_switch_dport[i];
struct platform_device *pdev;
@@ -743,9 +995,13 @@ static __init int cxl_test_init(void)
cxl_mem[i] = pdev;
}
+ rc = cxl_single_init();
+ if (rc)
+ goto err_mem;
+
cxl_acpi = platform_device_alloc("cxl_acpi", 0);
if (!cxl_acpi)
- goto err_mem;
+ goto err_single;
mock_companion(&acpi0017_mock, &cxl_acpi->dev);
acpi0017_mock.dev.bus = &platform_bus_type;
@@ -758,6 +1014,8 @@ static __init int cxl_test_init(void)
err_add:
platform_device_put(cxl_acpi);
+err_single:
+ cxl_single_exit();
err_mem:
for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--)
platform_device_unregister(cxl_mem[i]);
@@ -793,6 +1051,7 @@ static __exit void cxl_test_exit(void)
int i;
platform_device_unregister(cxl_acpi);
+ cxl_single_exit();
for (i = ARRAY_SIZE(cxl_mem) - 1; i >= 0; i--)
platform_device_unregister(cxl_mem[i]);
for (i = ARRAY_SIZE(cxl_switch_dport) - 1; i >= 0; i--)
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 0464b2c6c1e4..f07aef7c592c 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -49,6 +49,7 @@ TARGETS += net
TARGETS += net/af_unix
TARGETS += net/forwarding
TARGETS += net/mptcp
+TARGETS += net/openvswitch
TARGETS += netfilter
TARGETS += nsfs
TARGETS += pidfd
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 127b8caa3dc1..24dd6214394e 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3936,6 +3936,19 @@ static struct btf_raw_test raw_tests[] = {
.err_str = "Invalid type_id",
},
{
+ .descr = "decl_tag test #16, func proto, return type",
+ .raw_types = {
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), 2), (-1), /* [3] */
+ BTF_FUNC_PROTO_ENC(3, 0), /* [4] */
+ BTF_END_RAW,
+ },
+ BTF_STR_SEC("\0local\0tag1"),
+ .btf_load_err = true,
+ .err_str = "Invalid return type",
+},
+{
.descr = "type_tag test #1",
.raw_types = {
BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
diff --git a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
index 099c23d9aa21..b39093dd5715 100644
--- a/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
+++ b/tools/testing/selftests/bpf/progs/user_ringbuf_success.c
@@ -47,14 +47,14 @@ record_sample(struct bpf_dynptr *dynptr, void *context)
if (status) {
bpf_printk("bpf_dynptr_read() failed: %d\n", status);
err = 1;
- return 0;
+ return 1;
}
} else {
sample = bpf_dynptr_data(dynptr, 0, sizeof(*sample));
if (!sample) {
bpf_printk("Unexpectedly failed to get sample\n");
err = 2;
- return 0;
+ return 1;
}
stack_sample = *sample;
}
diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile
index e9dab5f9d773..6b8d2e2f23c2 100644
--- a/tools/testing/selftests/drivers/net/bonding/Makefile
+++ b/tools/testing/selftests/drivers/net/bonding/Makefile
@@ -7,6 +7,8 @@ TEST_PROGS := \
bond-lladdr-target.sh \
dev_addr_lists.sh
-TEST_FILES := lag_lib.sh
+TEST_FILES := \
+ lag_lib.sh \
+ net_forwarding_lib.sh
include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
index e6fa24eded5b..5cfe7d8ebc25 100755
--- a/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
+++ b/tools/testing/selftests/drivers/net/bonding/dev_addr_lists.sh
@@ -14,7 +14,7 @@ ALL_TESTS="
REQUIRE_MZ=no
NUM_NETIFS=0
lib_dir=$(dirname "$0")
-source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/net_forwarding_lib.sh
source "$lib_dir"/lag_lib.sh
diff --git a/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh
new file mode 120000
index 000000000000..39c96828c5ef
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/bonding/net_forwarding_lib.sh
@@ -0,0 +1 @@
+../../../net/forwarding/lib.sh \ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
index dca8be6092b9..a1f269ee84da 100755
--- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
+++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
@@ -18,8 +18,8 @@ NUM_NETIFS=1
REQUIRE_JQ="no"
REQUIRE_MZ="no"
NETIF_CREATE="no"
-lib_dir=$(dirname $0)/../../../net/forwarding
-source $lib_dir/lib.sh
+lib_dir=$(dirname "$0")
+source "$lib_dir"/lib.sh
cleanup() {
echo "Cleaning up"
diff --git a/tools/testing/selftests/drivers/net/team/Makefile b/tools/testing/selftests/drivers/net/team/Makefile
index 642d8df1c137..6a86e61e8bfe 100644
--- a/tools/testing/selftests/drivers/net/team/Makefile
+++ b/tools/testing/selftests/drivers/net/team/Makefile
@@ -3,4 +3,8 @@
TEST_PROGS := dev_addr_lists.sh
+TEST_FILES := \
+ lag_lib.sh \
+ net_forwarding_lib.sh
+
include ../../../lib.mk
diff --git a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
index debda7262956..33913112d5ca 100755
--- a/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
+++ b/tools/testing/selftests/drivers/net/team/dev_addr_lists.sh
@@ -11,14 +11,14 @@ ALL_TESTS="
REQUIRE_MZ=no
NUM_NETIFS=0
lib_dir=$(dirname "$0")
-source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/net_forwarding_lib.sh
-source "$lib_dir"/../bonding/lag_lib.sh
+source "$lib_dir"/lag_lib.sh
destroy()
{
- local ifnames=(dummy0 dummy1 team0 mv0)
+ local ifnames=(dummy1 dummy2 team0 mv0)
local ifname
for ifname in "${ifnames[@]}"; do
diff --git a/tools/testing/selftests/drivers/net/team/lag_lib.sh b/tools/testing/selftests/drivers/net/team/lag_lib.sh
new file mode 120000
index 000000000000..e1347a10afde
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/lag_lib.sh
@@ -0,0 +1 @@
+../bonding/lag_lib.sh \ No newline at end of file
diff --git a/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh
new file mode 120000
index 000000000000..39c96828c5ef
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/team/net_forwarding_lib.sh
@@ -0,0 +1 @@
+../../../net/forwarding/lib.sh \ No newline at end of file
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
index db522577ff78..d3a79da215c8 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/test_duplicates.tc
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: Generic dynamic event - check if duplicate events are caught
-# requires: dynamic_events "e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]":README
+# requires: dynamic_events "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README
echo 0 > events/enable
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc
index 914fe2e5d030..6461c375694f 100644
--- a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-eprobe.tc
@@ -1,7 +1,7 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# description: event trigger - test inter-event histogram trigger eprobe on synthetic event
-# requires: dynamic_events synthetic_events events/syscalls/sys_enter_openat/hist "e[:[<group>/]<event>] <attached-group>.<attached-event> [<args>]":README
+# requires: dynamic_events synthetic_events events/syscalls/sys_enter_openat/hist "e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>]":README
echo 0 > events/enable
diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile
index 732149011692..5a0e0df8de9b 100644
--- a/tools/testing/selftests/futex/functional/Makefile
+++ b/tools/testing/selftests/futex/functional/Makefile
@@ -3,11 +3,11 @@ INCLUDES := -I../include -I../../ -I../../../../../usr/include/
CFLAGS := $(CFLAGS) -g -O2 -Wall -D_GNU_SOURCE -pthread $(INCLUDES) $(KHDR_INCLUDES)
LDLIBS := -lpthread -lrt
-HEADERS := \
+LOCAL_HDRS := \
../include/futextest.h \
../include/atomic.h \
../include/logging.h
-TEST_GEN_FILES := \
+TEST_GEN_PROGS := \
futex_wait_timeout \
futex_wait_wouldblock \
futex_requeue_pi \
@@ -24,5 +24,3 @@ TEST_PROGS := run.sh
top_srcdir = ../../../../..
DEFAULT_INSTALL_HDR_PATH := 1
include ../../lib.mk
-
-$(TEST_GEN_FILES): $(HEADERS)
diff --git a/tools/testing/selftests/intel_pstate/Makefile b/tools/testing/selftests/intel_pstate/Makefile
index 39f0fa2a8fd6..05d66ef50c97 100644
--- a/tools/testing/selftests/intel_pstate/Makefile
+++ b/tools/testing/selftests/intel_pstate/Makefile
@@ -2,10 +2,10 @@
CFLAGS := $(CFLAGS) -Wall -D_GNU_SOURCE
LDLIBS += -lm
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+ARCH ?= $(shell uname -m 2>/dev/null || echo not)
+ARCH_PROCESSED := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-ifeq (x86,$(ARCH))
+ifeq (x86,$(ARCH_PROCESSED))
TEST_GEN_FILES := msr aperf
endif
diff --git a/tools/testing/selftests/kexec/Makefile b/tools/testing/selftests/kexec/Makefile
index 806a150648c3..67fe7a46cb62 100644
--- a/tools/testing/selftests/kexec/Makefile
+++ b/tools/testing/selftests/kexec/Makefile
@@ -1,10 +1,10 @@
# SPDX-License-Identifier: GPL-2.0-only
# Makefile for kexec tests
-uname_M := $(shell uname -m 2>/dev/null || echo not)
-ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
+ARCH ?= $(shell uname -m 2>/dev/null || echo not)
+ARCH_PROCESSED := $(shell echo $(ARCH) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
-ifeq ($(ARCH),$(filter $(ARCH),x86 ppc64le))
+ifeq ($(ARCH_PROCESSED),$(filter $(ARCH_PROCESSED),x86 ppc64le))
TEST_PROGS := test_kexec_load.sh test_kexec_file_load.sh
TEST_FILES := kexec_common_lib.sh
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 2f0d705db9db..082855d94c72 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -16,16 +16,18 @@
/x86_64/cpuid_test
/x86_64/cr4_cpuid_sync_test
/x86_64/debug_regs
-/x86_64/evmcs_test
-/x86_64/emulator_error_test
+/x86_64/exit_on_emulation_failure_test
/x86_64/fix_hypercall_test
/x86_64/get_msr_index_features
/x86_64/kvm_clock_test
/x86_64/kvm_pv_test
/x86_64/hyperv_clock
/x86_64/hyperv_cpuid
+/x86_64/hyperv_evmcs
/x86_64/hyperv_features
+/x86_64/hyperv_ipi
/x86_64/hyperv_svm_test
+/x86_64/hyperv_tlb_flush
/x86_64/max_vcpuid_cap_test
/x86_64/mmio_warning_test
/x86_64/monitor_mwait_test
@@ -36,11 +38,13 @@
/x86_64/set_boot_cpu_id
/x86_64/set_sregs_test
/x86_64/sev_migrate_tests
+/x86_64/smaller_maxphyaddr_emulation_test
/x86_64/smm_test
/x86_64/state_test
/x86_64/svm_vmcall_test
/x86_64/svm_int_ctl_test
/x86_64/svm_nested_soft_inject_test
+/x86_64/svm_nested_shutdown_test
/x86_64/sync_regs_test
/x86_64/tsc_msrs_test
/x86_64/tsc_scaling_sync
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 0172eb6cb6ee..2275ba861e0e 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -43,16 +43,18 @@ LIBKVM += lib/elf.c
LIBKVM += lib/guest_modes.c
LIBKVM += lib/io.c
LIBKVM += lib/kvm_util.c
-LIBKVM += lib/perf_test_util.c
+LIBKVM += lib/memstress.c
LIBKVM += lib/rbtree.c
LIBKVM += lib/sparsebit.c
LIBKVM += lib/test_util.c
+LIBKVM += lib/ucall_common.c
LIBKVM_STRING += lib/string_override.c
LIBKVM_x86_64 += lib/x86_64/apic.c
LIBKVM_x86_64 += lib/x86_64/handlers.S
-LIBKVM_x86_64 += lib/x86_64/perf_test_util.c
+LIBKVM_x86_64 += lib/x86_64/hyperv.c
+LIBKVM_x86_64 += lib/x86_64/memstress.c
LIBKVM_x86_64 += lib/x86_64/processor.c
LIBKVM_x86_64 += lib/x86_64/svm.c
LIBKVM_x86_64 += lib/x86_64/ucall.c
@@ -80,13 +82,15 @@ TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh
TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test
TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test
TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
-TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
-TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
+TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test
TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test
+TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush
TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test
TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
@@ -96,11 +100,13 @@ TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test
TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id
TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
+TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test
TEST_GEN_PROGS_x86_64 += x86_64/smm_test
TEST_GEN_PROGS_x86_64 += x86_64/state_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
+TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test
TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
index 6f9c1f19c7f6..b1d2158c0b6d 100644
--- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
+++ b/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c
@@ -158,12 +158,9 @@ int main(void)
TEST_REQUIRE(vcpu_aarch64_only(vcpu));
- ucall_init(vm, NULL);
-
test_user_raz_wi(vcpu);
test_user_raz_invariant(vcpu);
test_guest_raz(vcpu);
- ucall_uninit(vm);
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index 574eb73f0e90..f2a96779716a 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -375,7 +375,6 @@ static struct kvm_vm *test_vm_create(void)
for (i = 0; i < nr_vcpus; i++)
vcpu_init_descriptor_tables(vcpus[i]);
- ucall_init(vm, NULL);
test_init_timer_irq(vm);
gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
__TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3");
@@ -414,36 +413,21 @@ static bool parse_args(int argc, char *argv[])
while ((opt = getopt(argc, argv, "hn:i:p:m:")) != -1) {
switch (opt) {
case 'n':
- test_args.nr_vcpus = atoi(optarg);
- if (test_args.nr_vcpus <= 0) {
- pr_info("Positive value needed for -n\n");
- goto err;
- } else if (test_args.nr_vcpus > KVM_MAX_VCPUS) {
+ test_args.nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+ if (test_args.nr_vcpus > KVM_MAX_VCPUS) {
pr_info("Max allowed vCPUs: %u\n",
KVM_MAX_VCPUS);
goto err;
}
break;
case 'i':
- test_args.nr_iter = atoi(optarg);
- if (test_args.nr_iter <= 0) {
- pr_info("Positive value needed for -i\n");
- goto err;
- }
+ test_args.nr_iter = atoi_positive("Number of iterations", optarg);
break;
case 'p':
- test_args.timer_period_ms = atoi(optarg);
- if (test_args.timer_period_ms <= 0) {
- pr_info("Positive value needed for -p\n");
- goto err;
- }
+ test_args.timer_period_ms = atoi_positive("Periodicity", optarg);
break;
case 'm':
- test_args.migration_freq_ms = atoi(optarg);
- if (test_args.migration_freq_ms < 0) {
- pr_info("0 or positive value needed for -m\n");
- goto err;
- }
+ test_args.migration_freq_ms = atoi_non_negative("Frequency", optarg);
break;
case 'h':
default:
@@ -462,9 +446,6 @@ int main(int argc, char *argv[])
{
struct kvm_vm *vm;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
if (!parse_args(argc, argv))
exit(KSFT_SKIP);
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index 947bd201435c..d86c4e4d1c82 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -241,7 +241,6 @@ static void guest_svc_handler(struct ex_regs *regs)
enum single_step_op {
SINGLE_STEP_ENABLE = 0,
- SINGLE_STEP_DISABLE = 1,
};
static void guest_code_ss(int test_cnt)
@@ -258,7 +257,7 @@ static void guest_code_ss(int test_cnt)
GUEST_SYNC(SINGLE_STEP_ENABLE);
/*
- * The userspace will veriry that the pc is as expected during
+ * The userspace will verify that the pc is as expected during
* single step execution between iter_ss_begin and iter_ss_end.
*/
asm volatile("iter_ss_begin:nop\n");
@@ -268,11 +267,9 @@ static void guest_code_ss(int test_cnt)
bvr = read_sysreg(dbgbvr0_el1);
wvr = read_sysreg(dbgwvr0_el1);
+ /* Userspace disables Single Step when the end is nigh. */
asm volatile("iter_ss_end:\n");
- /* Disable Single Step execution */
- GUEST_SYNC(SINGLE_STEP_DISABLE);
-
GUEST_ASSERT(bvr == w_bvr);
GUEST_ASSERT(wvr == w_wvr);
}
@@ -295,7 +292,6 @@ static void test_guest_debug_exceptions(void)
int stage;
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
- ucall_init(vm, NULL);
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vcpu);
@@ -346,7 +342,6 @@ void test_single_step_from_userspace(int test_cnt)
struct kvm_guest_debug debug = {};
vm = vm_create_with_one_vcpu(&vcpu, guest_code_ss);
- ucall_init(vm, NULL);
run = vcpu->run;
vcpu_args_set(vcpu, 1, test_cnt);
@@ -364,15 +359,12 @@ void test_single_step_from_userspace(int test_cnt)
TEST_ASSERT(cmd == UCALL_SYNC,
"Unexpected ucall cmd 0x%lx", cmd);
- if (uc.args[1] == SINGLE_STEP_ENABLE) {
- debug.control = KVM_GUESTDBG_ENABLE |
- KVM_GUESTDBG_SINGLESTEP;
- ss_enable = true;
- } else {
- debug.control = SINGLE_STEP_DISABLE;
- ss_enable = false;
- }
+ TEST_ASSERT(uc.args[1] == SINGLE_STEP_ENABLE,
+ "Unexpected ucall action 0x%lx", uc.args[1]);
+ debug.control = KVM_GUESTDBG_ENABLE |
+ KVM_GUESTDBG_SINGLESTEP;
+ ss_enable = true;
vcpu_guest_debug_set(vcpu, &debug);
continue;
}
@@ -385,6 +377,14 @@ void test_single_step_from_userspace(int test_cnt)
"Unexpected pc 0x%lx (expected 0x%lx)",
pc, test_pc);
+ if ((pc + 4) == (uint64_t)&iter_ss_end) {
+ test_pc = 0;
+ debug.control = KVM_GUESTDBG_ENABLE;
+ ss_enable = false;
+ vcpu_guest_debug_set(vcpu, &debug);
+ continue;
+ }
+
/*
* If the current pc is between iter_ss_bgin and
* iter_ss_end, the pc for the next KVM_EXIT_DEBUG should
@@ -423,7 +423,7 @@ int main(int argc, char *argv[])
while ((opt = getopt(argc, argv, "i:")) != -1) {
switch (opt) {
case 'i':
- ss_iteration = atoi(optarg);
+ ss_iteration = atoi_positive("Number of iterations", optarg);
break;
case 'h':
default:
diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/aarch64/hypercalls.c
index a39da3fe4952..bef1499fb465 100644
--- a/tools/testing/selftests/kvm/aarch64/hypercalls.c
+++ b/tools/testing/selftests/kvm/aarch64/hypercalls.c
@@ -236,7 +236,6 @@ static struct kvm_vm *test_vm_create(struct kvm_vcpu **vcpu)
vm = vm_create_with_one_vcpu(vcpu, guest_code);
- ucall_init(vm, NULL);
steal_time_init(*vcpu);
return vm;
@@ -306,8 +305,6 @@ static void test_run(void)
int main(void)
{
- setbuf(stdout, NULL);
-
test_run();
return 0;
}
diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/aarch64/psci_test.c
index e0b9e81a3e09..cfa36f387948 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_test.c
@@ -79,7 +79,6 @@ static struct kvm_vm *setup_vm(void *guest_code, struct kvm_vcpu **source,
struct kvm_vm *vm;
vm = vm_create(2);
- ucall_init(vm, NULL);
vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init);
init.features[0] |= (1 << KVM_ARM_VCPU_PSCI_0_2);
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c
index 9c131d977a1b..eef816b80993 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_init.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c
@@ -68,8 +68,6 @@ static void guest_code(void)
/* we don't want to assert on run execution, hence that helper */
static int run_vcpu(struct kvm_vcpu *vcpu)
{
- ucall_init(vcpu->vm, NULL);
-
return __vcpu_run(vcpu) ? -errno : 0;
}
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
index 17417220a083..90d854e0fcff 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_irq.c
@@ -756,7 +756,6 @@ static void test_vgic(uint32_t nr_irqs, bool level_sensitive, bool eoi_split)
print_args(&args);
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
- ucall_init(vm, NULL);
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vcpu);
@@ -818,22 +817,19 @@ int main(int argc, char **argv)
int opt;
bool eoi_split = false;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
while ((opt = getopt(argc, argv, "hn:e:l:")) != -1) {
switch (opt) {
case 'n':
- nr_irqs = atoi(optarg);
+ nr_irqs = atoi_non_negative("Number of IRQs", optarg);
if (nr_irqs > 1024 || nr_irqs % 32)
help(argv[0]);
break;
case 'e':
- eoi_split = (bool)atoi(optarg);
+ eoi_split = (bool)atoi_paranoid(optarg);
default_args = false;
break;
case 'l':
- level_sensitive = (bool)atoi(optarg);
+ level_sensitive = (bool)atoi_paranoid(optarg);
default_args = false;
break;
case 'h':
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
index 76c583a07ea2..02d3587cab0a 100644
--- a/tools/testing/selftests/kvm/access_tracking_perf_test.c
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -44,7 +44,7 @@
#include "kvm_util.h"
#include "test_util.h"
-#include "perf_test_util.h"
+#include "memstress.h"
#include "guest_modes.h"
/* Global variable used to synchronize all of the vCPU threads. */
@@ -126,7 +126,7 @@ static void mark_page_idle(int page_idle_fd, uint64_t pfn)
}
static void mark_vcpu_memory_idle(struct kvm_vm *vm,
- struct perf_test_vcpu_args *vcpu_args)
+ struct memstress_vcpu_args *vcpu_args)
{
int vcpu_idx = vcpu_args->vcpu_idx;
uint64_t base_gva = vcpu_args->gva;
@@ -148,7 +148,7 @@ static void mark_vcpu_memory_idle(struct kvm_vm *vm,
TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap.");
for (page = 0; page < pages; page++) {
- uint64_t gva = base_gva + page * perf_test_args.guest_page_size;
+ uint64_t gva = base_gva + page * memstress_args.guest_page_size;
uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva);
if (!pfn) {
@@ -220,10 +220,10 @@ static bool spin_wait_for_next_iteration(int *current_iteration)
return true;
}
-static void vcpu_thread_main(struct perf_test_vcpu_args *vcpu_args)
+static void vcpu_thread_main(struct memstress_vcpu_args *vcpu_args)
{
struct kvm_vcpu *vcpu = vcpu_args->vcpu;
- struct kvm_vm *vm = perf_test_args.vm;
+ struct kvm_vm *vm = memstress_args.vm;
int vcpu_idx = vcpu_args->vcpu_idx;
int current_iteration = 0;
@@ -279,7 +279,7 @@ static void run_iteration(struct kvm_vm *vm, int nr_vcpus, const char *descripti
static void access_memory(struct kvm_vm *vm, int nr_vcpus,
enum access_type access, const char *description)
{
- perf_test_set_wr_fract(vm, (access == ACCESS_READ) ? INT_MAX : 1);
+ memstress_set_write_percent(vm, (access == ACCESS_READ) ? 0 : 100);
iteration_work = ITERATION_ACCESS_MEMORY;
run_iteration(vm, nr_vcpus, description);
}
@@ -303,10 +303,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct kvm_vm *vm;
int nr_vcpus = params->nr_vcpus;
- vm = perf_test_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1,
+ vm = memstress_create_vm(mode, nr_vcpus, params->vcpu_memory_bytes, 1,
params->backing_src, !overlap_memory_access);
- perf_test_start_vcpu_threads(nr_vcpus, vcpu_thread_main);
+ memstress_start_vcpu_threads(nr_vcpus, vcpu_thread_main);
pr_info("\n");
access_memory(vm, nr_vcpus, ACCESS_WRITE, "Populating memory");
@@ -324,8 +324,8 @@ static void run_test(enum vm_guest_mode mode, void *arg)
/* Set done to signal the vCPU threads to exit */
done = true;
- perf_test_join_vcpu_threads(nr_vcpus);
- perf_test_destroy_vm(vm);
+ memstress_join_vcpu_threads(nr_vcpus);
+ memstress_destroy_vm(vm);
}
static void help(char *name)
@@ -368,7 +368,7 @@ int main(int argc, char *argv[])
params.vcpu_memory_bytes = parse_size(optarg);
break;
case 'v':
- params.nr_vcpus = atoi(optarg);
+ params.nr_vcpus = atoi_positive("Number of vCPUs", optarg);
break;
case 'o':
overlap_memory_access = true;
diff --git a/tools/testing/selftests/kvm/demand_paging_test.c b/tools/testing/selftests/kvm/demand_paging_test.c
index 779ae54f89c4..3a977ddf07b2 100644
--- a/tools/testing/selftests/kvm/demand_paging_test.c
+++ b/tools/testing/selftests/kvm/demand_paging_test.c
@@ -20,7 +20,7 @@
#include "kvm_util.h"
#include "test_util.h"
-#include "perf_test_util.h"
+#include "memstress.h"
#include "guest_modes.h"
#ifdef __NR_userfaultfd
@@ -42,7 +42,7 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
static size_t demand_paging_size;
static char *guest_data_prototype;
-static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
+static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
{
struct kvm_vcpu *vcpu = vcpu_args->vcpu;
int vcpu_idx = vcpu_args->vcpu_idx;
@@ -285,7 +285,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct kvm_vm *vm;
int r, i;
- vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
+ vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
p->src_type, p->partition_vcpu_memory_access);
demand_paging_size = get_backing_src_pagesz(p->src_type);
@@ -307,11 +307,11 @@ static void run_test(enum vm_guest_mode mode, void *arg)
TEST_ASSERT(pipefds, "Unable to allocate memory for pipefd");
for (i = 0; i < nr_vcpus; i++) {
- struct perf_test_vcpu_args *vcpu_args;
+ struct memstress_vcpu_args *vcpu_args;
void *vcpu_hva;
void *vcpu_alias;
- vcpu_args = &perf_test_args.vcpu_args[i];
+ vcpu_args = &memstress_args.vcpu_args[i];
/* Cache the host addresses of the region */
vcpu_hva = addr_gpa2hva(vm, vcpu_args->gpa);
@@ -329,17 +329,17 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pipefds[i * 2], p->uffd_mode,
p->uffd_delay, &uffd_args[i],
vcpu_hva, vcpu_alias,
- vcpu_args->pages * perf_test_args.guest_page_size);
+ vcpu_args->pages * memstress_args.guest_page_size);
}
}
pr_info("Finished creating vCPUs and starting uffd threads\n");
clock_gettime(CLOCK_MONOTONIC, &start);
- perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
+ memstress_start_vcpu_threads(nr_vcpus, vcpu_worker);
pr_info("Started all vCPUs\n");
- perf_test_join_vcpu_threads(nr_vcpus);
+ memstress_join_vcpu_threads(nr_vcpus);
ts_diff = timespec_elapsed(start);
pr_info("All vCPU threads joined\n");
@@ -358,10 +358,10 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pr_info("Total guest execution time: %ld.%.9lds\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
pr_info("Overall demand paging rate: %f pgs/sec\n",
- perf_test_args.vcpu_args[0].pages * nr_vcpus /
+ memstress_args.vcpu_args[0].pages * nr_vcpus /
((double)ts_diff.tv_sec + (double)ts_diff.tv_nsec / 100000000.0));
- perf_test_destroy_vm(vm);
+ memstress_destroy_vm(vm);
free(guest_data_prototype);
if (p->uffd_mode) {
@@ -427,8 +427,8 @@ int main(int argc, char *argv[])
p.src_type = parse_backing_src_type(optarg);
break;
case 'v':
- nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+ TEST_ASSERT(nr_vcpus <= max_vcpus,
"Invalid number of vcpus, must be between 1 and %d", max_vcpus);
break;
case 'o':
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index f99e39a672d3..c33e89012ae6 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -16,7 +16,7 @@
#include "kvm_util.h"
#include "test_util.h"
-#include "perf_test_util.h"
+#include "memstress.h"
#include "guest_modes.h"
#ifdef __aarch64__
@@ -67,7 +67,7 @@ static bool host_quit;
static int iteration;
static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
-static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
+static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
{
struct kvm_vcpu *vcpu = vcpu_args->vcpu;
int vcpu_idx = vcpu_args->vcpu_idx;
@@ -128,10 +128,12 @@ static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
struct test_params {
unsigned long iterations;
uint64_t phys_offset;
- int wr_fract;
bool partition_vcpu_memory_access;
enum vm_mem_backing_src_type backing_src;
int slots;
+ uint32_t write_percent;
+ uint32_t random_seed;
+ bool random_access;
};
static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
@@ -139,7 +141,7 @@ static void toggle_dirty_logging(struct kvm_vm *vm, int slots, bool enable)
int i;
for (i = 0; i < slots; i++) {
- int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+ int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
int flags = enable ? KVM_MEM_LOG_DIRTY_PAGES : 0;
vm_mem_region_set_flags(vm, slot, flags);
@@ -161,7 +163,7 @@ static void get_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[], int slots
int i;
for (i = 0; i < slots; i++) {
- int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+ int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
kvm_vm_get_dirty_log(vm, slot, bitmaps[i]);
}
@@ -173,7 +175,7 @@ static void clear_dirty_log(struct kvm_vm *vm, unsigned long *bitmaps[],
int i;
for (i = 0; i < slots; i++) {
- int slot = PERF_TEST_MEM_SLOT_INDEX + i;
+ int slot = MEMSTRESS_MEM_SLOT_INDEX + i;
kvm_vm_clear_dirty_log(vm, slot, bitmaps[i], 0, pages_per_slot);
}
@@ -221,11 +223,13 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct timespec clear_dirty_log_total = (struct timespec){0};
int i;
- vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
+ vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size,
p->slots, p->backing_src,
p->partition_vcpu_memory_access);
- perf_test_set_wr_fract(vm, p->wr_fract);
+ pr_info("Random seed: %u\n", p->random_seed);
+ memstress_set_random_seed(vm, p->random_seed);
+ memstress_set_write_percent(vm, p->write_percent);
guest_num_pages = (nr_vcpus * guest_percpu_mem_size) >> vm->page_shift;
guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
@@ -248,7 +252,16 @@ static void run_test(enum vm_guest_mode mode, void *arg)
for (i = 0; i < nr_vcpus; i++)
vcpu_last_completed_iteration[i] = -1;
- perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
+ /*
+ * Use 100% writes during the population phase to ensure all
+ * memory is actually populated and not just mapped to the zero
+ * page. The prevents expensive copy-on-write faults from
+ * occurring during the dirty memory iterations below, which
+ * would pollute the performance results.
+ */
+ memstress_set_write_percent(vm, 100);
+ memstress_set_random_access(vm, false);
+ memstress_start_vcpu_threads(nr_vcpus, vcpu_worker);
/* Allow the vCPUs to populate memory */
pr_debug("Starting iteration %d - Populating\n", iteration);
@@ -269,6 +282,9 @@ static void run_test(enum vm_guest_mode mode, void *arg)
pr_info("Enabling dirty logging time: %ld.%.9lds\n\n",
ts_diff.tv_sec, ts_diff.tv_nsec);
+ memstress_set_write_percent(vm, p->write_percent);
+ memstress_set_random_access(vm, p->random_access);
+
while (iteration < p->iterations) {
/*
* Incrementing the iteration number will start the vCPUs
@@ -329,7 +345,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
* wait for them to exit.
*/
host_quit = true;
- perf_test_join_vcpu_threads(nr_vcpus);
+ memstress_join_vcpu_threads(nr_vcpus);
avg = timespec_div(get_dirty_log_total, p->iterations);
pr_info("Get dirty log over %lu iterations took %ld.%.9lds. (Avg %ld.%.9lds/iteration)\n",
@@ -345,16 +361,17 @@ static void run_test(enum vm_guest_mode mode, void *arg)
free_bitmaps(bitmaps, p->slots);
arch_cleanup_vm(vm);
- perf_test_destroy_vm(vm);
+ memstress_destroy_vm(vm);
}
static void help(char *name)
{
puts("");
- printf("usage: %s [-h] [-i iterations] [-p offset] [-g] "
- "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-s mem type]"
- "[-x memslots]\n", name);
+ printf("usage: %s [-h] [-a] [-i iterations] [-p offset] [-g] "
+ "[-m mode] [-n] [-b vcpu bytes] [-v vcpus] [-o] [-r random seed ] [-s mem type]"
+ "[-x memslots] [-w percentage] [-c physical cpus to run test on]\n", name);
puts("");
+ printf(" -a: access memory randomly rather than in order.\n");
printf(" -i: specify iteration counts (default: %"PRIu64")\n",
TEST_HOST_LOOP_N);
printf(" -g: Do not enable KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2. This\n"
@@ -373,16 +390,29 @@ static void help(char *name)
printf(" -b: specify the size of the memory region which should be\n"
" dirtied by each vCPU. e.g. 10M or 3G.\n"
" (default: 1G)\n");
- printf(" -f: specify the fraction of pages which should be written to\n"
- " as opposed to simply read, in the form\n"
- " 1/<fraction of pages to write>.\n"
- " (default: 1 i.e. all pages are written to.)\n");
printf(" -v: specify the number of vCPUs to run.\n");
printf(" -o: Overlap guest memory accesses instead of partitioning\n"
" them into a separate region of memory for each vCPU.\n");
+ printf(" -r: specify the starting random seed.\n");
backing_src_help("-s");
printf(" -x: Split the memory region into this number of memslots.\n"
" (default: 1)\n");
+ printf(" -w: specify the percentage of pages which should be written to\n"
+ " as an integer from 0-100 inclusive. This is probabalistic,\n"
+ " so -w X means each page has an X%% chance of writing\n"
+ " and a (100-X)%% chance of reading.\n"
+ " (default: 100 i.e. all pages are written to.)\n");
+ printf(" -c: Pin tasks to physical CPUs. Takes a list of comma separated\n"
+ " values (target pCPU), one for each vCPU, plus an optional\n"
+ " entry for the main application task (specified via entry\n"
+ " <nr_vcpus + 1>). If used, entries must be provided for all\n"
+ " vCPUs, i.e. pinning vCPUs is all or nothing.\n\n"
+ " E.g. to create 3 vCPUs, pin vCPU0=>pCPU22, vCPU1=>pCPU23,\n"
+ " vCPU2=>pCPU24, and pin the application task to pCPU50:\n\n"
+ " ./dirty_log_perf_test -v 3 -c 22,23,24,50\n\n"
+ " To leave the application task unpinned, drop the final entry:\n\n"
+ " ./dirty_log_perf_test -v 3 -c 22,23,24\n\n"
+ " (default: no pinning)\n");
puts("");
exit(0);
}
@@ -390,12 +420,14 @@ static void help(char *name)
int main(int argc, char *argv[])
{
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+ const char *pcpu_list = NULL;
struct test_params p = {
.iterations = TEST_HOST_LOOP_N,
- .wr_fract = 1,
.partition_vcpu_memory_access = true,
.backing_src = DEFAULT_VM_MEM_SRC,
.slots = 1,
+ .random_seed = 1,
+ .write_percent = 100,
};
int opt;
@@ -406,55 +438,73 @@ int main(int argc, char *argv[])
guest_modes_append_default();
- while ((opt = getopt(argc, argv, "eghi:p:m:nb:f:v:os:x:")) != -1) {
+ while ((opt = getopt(argc, argv, "ab:c:eghi:m:nop:r:s:v:x:w:")) != -1) {
switch (opt) {
+ case 'a':
+ p.random_access = true;
+ break;
+ case 'b':
+ guest_percpu_mem_size = parse_size(optarg);
+ break;
+ case 'c':
+ pcpu_list = optarg;
+ break;
case 'e':
/* 'e' is for evil. */
run_vcpus_while_disabling_dirty_logging = true;
+ break;
case 'g':
dirty_log_manual_caps = 0;
break;
- case 'i':
- p.iterations = atoi(optarg);
+ case 'h':
+ help(argv[0]);
break;
- case 'p':
- p.phys_offset = strtoull(optarg, NULL, 0);
+ case 'i':
+ p.iterations = atoi_positive("Number of iterations", optarg);
break;
case 'm':
guest_modes_cmdline(optarg);
break;
case 'n':
- perf_test_args.nested = true;
- break;
- case 'b':
- guest_percpu_mem_size = parse_size(optarg);
- break;
- case 'f':
- p.wr_fract = atoi(optarg);
- TEST_ASSERT(p.wr_fract >= 1,
- "Write fraction cannot be less than one");
- break;
- case 'v':
- nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
- "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
+ memstress_args.nested = true;
break;
case 'o':
p.partition_vcpu_memory_access = false;
break;
+ case 'p':
+ p.phys_offset = strtoull(optarg, NULL, 0);
+ break;
+ case 'r':
+ p.random_seed = atoi_positive("Random seed", optarg);
+ break;
case 's':
p.backing_src = parse_backing_src_type(optarg);
break;
+ case 'v':
+ nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+ TEST_ASSERT(nr_vcpus <= max_vcpus,
+ "Invalid number of vcpus, must be between 1 and %d", max_vcpus);
+ break;
+ case 'w':
+ p.write_percent = atoi_non_negative("Write percentage", optarg);
+ TEST_ASSERT(p.write_percent <= 100,
+ "Write percentage must be between 0 and 100");
+ break;
case 'x':
- p.slots = atoi(optarg);
+ p.slots = atoi_positive("Number of slots", optarg);
break;
- case 'h':
default:
help(argv[0]);
break;
}
}
+ if (pcpu_list) {
+ kvm_parse_vcpu_pinning(pcpu_list, memstress_args.vcpu_to_pcpu,
+ nr_vcpus);
+ memstress_args.pin_vcpus = true;
+ }
+
TEST_ASSERT(p.iterations >= 2, "The test should have at least two iterations");
pr_info("Test iterations: %"PRIu64"\n", p.iterations);
diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index b5234d6efbe1..a38c4369fb8e 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -756,8 +756,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
/* Cache the HVA pointer of the region */
host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
- ucall_init(vm, NULL);
-
/* Export the shared variables to the guest */
sync_global_to_guest(vm, host_page_size);
sync_global_to_guest(vm, guest_page_size);
@@ -813,7 +811,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
free(bmap);
free(host_bmap_track);
- ucall_uninit(vm);
kvm_vm_free(vm);
}
diff --git a/tools/testing/selftests/kvm/include/kvm_util_base.h b/tools/testing/selftests/kvm/include/kvm_util_base.h
index e42a09cd24a0..c7685c7038ff 100644
--- a/tools/testing/selftests/kvm/include/kvm_util_base.h
+++ b/tools/testing/selftests/kvm/include/kvm_util_base.h
@@ -16,6 +16,7 @@
#include <linux/kvm.h>
#include "linux/rbtree.h"
+#include <asm/atomic.h>
#include <sys/ioctl.h>
@@ -81,6 +82,7 @@ struct kvm_vm {
struct sparsebit *vpages_mapped;
bool has_irqchip;
bool pgd_created;
+ vm_paddr_t ucall_mmio_addr;
vm_paddr_t pgd;
vm_vaddr_t gdt;
vm_vaddr_t tss;
@@ -383,6 +385,7 @@ void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
void vm_mem_region_move(struct kvm_vm *vm, uint32_t slot, uint64_t new_gpa);
void vm_mem_region_delete(struct kvm_vm *vm, uint32_t slot);
struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id);
+vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min);
vm_vaddr_t vm_vaddr_alloc_pages(struct kvm_vm *vm, int nr_pages);
vm_vaddr_t vm_vaddr_alloc_page(struct kvm_vm *vm);
@@ -688,6 +691,10 @@ static inline struct kvm_vm *vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm);
+void kvm_pin_this_task_to_pcpu(uint32_t pcpu);
+void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
+ int nr_vcpus);
+
unsigned long vm_compute_max_gfn(struct kvm_vm *vm);
unsigned int vm_calc_num_guest_pages(enum vm_guest_mode mode, size_t size);
unsigned int vm_num_host_pages(enum vm_guest_mode mode, unsigned int num_guest_pages);
@@ -718,6 +725,19 @@ kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
memcpy(&(g), _p, sizeof(g)); \
})
+/*
+ * Write a global value, but only in the VM's (guest's) domain. Primarily used
+ * for "globals" that hold per-VM values (VMs always duplicate code and global
+ * data into their own region of physical memory), but can be used anytime it's
+ * undesirable to change the host's copy of the global.
+ */
+#define write_guest_global(vm, g, val) ({ \
+ typeof(g) *_p = addr_gva2hva(vm, (vm_vaddr_t)&(g)); \
+ typeof(g) _val = val; \
+ \
+ memcpy(_p, &(_val), sizeof(g)); \
+})
+
void assert_on_unhandled_exception(struct kvm_vcpu *vcpu);
void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu,
@@ -838,4 +858,13 @@ static inline int __vm_disable_nx_huge_pages(struct kvm_vm *vm)
return __vm_enable_cap(vm, KVM_CAP_VM_DISABLE_NX_HUGE_PAGES, 0);
}
+/*
+ * Arch hook that is invoked via a constructor, i.e. before exeucting main(),
+ * to allow for arch-specific setup that is common to all tests, e.g. computing
+ * the default guest "mode".
+ */
+void kvm_selftest_arch_init(void);
+
+void kvm_arch_vm_post_create(struct kvm_vm *vm);
+
#endif /* SELFTEST_KVM_UTIL_BASE_H */
diff --git a/tools/testing/selftests/kvm/include/memstress.h b/tools/testing/selftests/kvm/include/memstress.h
new file mode 100644
index 000000000000..bbd2a302df10
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/memstress.h
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/memstress.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_MEMSTRESS_H
+#define SELFTEST_KVM_MEMSTRESS_H
+
+#include <pthread.h>
+
+#include "kvm_util.h"
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM 0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
+
+#define MEMSTRESS_MEM_SLOT_INDEX 1
+
+struct memstress_vcpu_args {
+ uint64_t gpa;
+ uint64_t gva;
+ uint64_t pages;
+
+ /* Only used by the host userspace part of the vCPU thread */
+ struct kvm_vcpu *vcpu;
+ int vcpu_idx;
+};
+
+struct memstress_args {
+ struct kvm_vm *vm;
+ /* The starting address and size of the guest test region. */
+ uint64_t gpa;
+ uint64_t size;
+ uint64_t guest_page_size;
+ uint32_t random_seed;
+ uint32_t write_percent;
+
+ /* Run vCPUs in L2 instead of L1, if the architecture supports it. */
+ bool nested;
+ /* Randomize which pages are accessed by the guest. */
+ bool random_access;
+ /* True if all vCPUs are pinned to pCPUs */
+ bool pin_vcpus;
+ /* The vCPU=>pCPU pinning map. Only valid if pin_vcpus is true. */
+ uint32_t vcpu_to_pcpu[KVM_MAX_VCPUS];
+
+ struct memstress_vcpu_args vcpu_args[KVM_MAX_VCPUS];
+};
+
+extern struct memstress_args memstress_args;
+
+struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
+ uint64_t vcpu_memory_bytes, int slots,
+ enum vm_mem_backing_src_type backing_src,
+ bool partition_vcpu_memory_access);
+void memstress_destroy_vm(struct kvm_vm *vm);
+
+void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent);
+void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed);
+void memstress_set_random_access(struct kvm_vm *vm, bool random_access);
+
+void memstress_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct memstress_vcpu_args *));
+void memstress_join_vcpu_threads(int vcpus);
+void memstress_guest_code(uint32_t vcpu_id);
+
+uint64_t memstress_nested_pages(int nr_vcpus);
+void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]);
+
+#endif /* SELFTEST_KVM_MEMSTRESS_H */
diff --git a/tools/testing/selftests/kvm/include/perf_test_util.h b/tools/testing/selftests/kvm/include/perf_test_util.h
deleted file mode 100644
index eaa88df0555a..000000000000
--- a/tools/testing/selftests/kvm/include/perf_test_util.h
+++ /dev/null
@@ -1,63 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * tools/testing/selftests/kvm/include/perf_test_util.h
- *
- * Copyright (C) 2020, Google LLC.
- */
-
-#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
-#define SELFTEST_KVM_PERF_TEST_UTIL_H
-
-#include <pthread.h>
-
-#include "kvm_util.h"
-
-/* Default guest test virtual memory offset */
-#define DEFAULT_GUEST_TEST_MEM 0xc0000000
-
-#define DEFAULT_PER_VCPU_MEM_SIZE (1 << 30) /* 1G */
-
-#define PERF_TEST_MEM_SLOT_INDEX 1
-
-struct perf_test_vcpu_args {
- uint64_t gpa;
- uint64_t gva;
- uint64_t pages;
-
- /* Only used by the host userspace part of the vCPU thread */
- struct kvm_vcpu *vcpu;
- int vcpu_idx;
-};
-
-struct perf_test_args {
- struct kvm_vm *vm;
- /* The starting address and size of the guest test region. */
- uint64_t gpa;
- uint64_t size;
- uint64_t guest_page_size;
- int wr_fract;
-
- /* Run vCPUs in L2 instead of L1, if the architecture supports it. */
- bool nested;
-
- struct perf_test_vcpu_args vcpu_args[KVM_MAX_VCPUS];
-};
-
-extern struct perf_test_args perf_test_args;
-
-struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
- uint64_t vcpu_memory_bytes, int slots,
- enum vm_mem_backing_src_type backing_src,
- bool partition_vcpu_memory_access);
-void perf_test_destroy_vm(struct kvm_vm *vm);
-
-void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract);
-
-void perf_test_start_vcpu_threads(int vcpus, void (*vcpu_fn)(struct perf_test_vcpu_args *));
-void perf_test_join_vcpu_threads(int vcpus);
-void perf_test_guest_code(uint32_t vcpu_id);
-
-uint64_t perf_test_nested_pages(int nr_vcpus);
-void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[]);
-
-#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index befc754ce9b3..80d6416f3012 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -77,6 +77,13 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
struct timespec timespec_elapsed(struct timespec start);
struct timespec timespec_div(struct timespec ts, int divisor);
+struct guest_random_state {
+ uint32_t seed;
+};
+
+struct guest_random_state new_guest_random_state(uint32_t seed);
+uint32_t guest_random_u32(struct guest_random_state *state);
+
enum vm_mem_backing_src_type {
VM_MEM_SRC_ANONYMOUS,
VM_MEM_SRC_ANONYMOUS_THP,
@@ -152,4 +159,22 @@ static inline void *align_ptr_up(void *x, size_t size)
return (void *)align_up((unsigned long)x, size);
}
+int atoi_paranoid(const char *num_str);
+
+static inline uint32_t atoi_positive(const char *name, const char *num_str)
+{
+ int num = atoi_paranoid(num_str);
+
+ TEST_ASSERT(num > 0, "%s must be greater than 0, got '%s'", name, num_str);
+ return num;
+}
+
+static inline uint32_t atoi_non_negative(const char *name, const char *num_str)
+{
+ int num = atoi_paranoid(num_str);
+
+ TEST_ASSERT(num >= 0, "%s must be non-negative, got '%s'", name, num_str);
+ return num;
+}
+
#endif /* SELFTEST_KVM_TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index ee79d180e07e..bdd373189a77 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -22,12 +22,18 @@ enum {
struct ucall {
uint64_t cmd;
uint64_t args[UCALL_MAX_ARGS];
+
+ /* Host virtual address of this struct. */
+ struct ucall *hva;
};
-void ucall_init(struct kvm_vm *vm, void *arg);
-void ucall_uninit(struct kvm_vm *vm);
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
+void ucall_arch_do_ucall(vm_vaddr_t uc);
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu);
+
void ucall(uint64_t cmd, int nargs, ...);
uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc);
+void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa);
#define GUEST_SYNC_ARGS(stage, arg1, arg2, arg3, arg4) \
ucall(UCALL_SYNC, 6, "hello", stage, arg1, arg2, arg3, arg4)
diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
index 58db74f68af2..901caf0e0939 100644
--- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h
+++ b/tools/testing/selftests/kvm/include/x86_64/evmcs.h
@@ -10,6 +10,7 @@
#define SELFTEST_KVM_EVMCS_H
#include <stdint.h>
+#include "hyperv.h"
#include "vmx.h"
#define u16 uint16_t
@@ -20,15 +21,6 @@
extern bool enable_evmcs;
-struct hv_vp_assist_page {
- __u32 apic_assist;
- __u32 reserved;
- __u64 vtl_control[2];
- __u64 nested_enlightenments_control[2];
- __u32 enlighten_vmentry;
- __u64 current_nested_vmcs;
-};
-
struct hv_enlightened_vmcs {
u32 revision_id;
u32 abort;
@@ -41,6 +33,8 @@ struct hv_enlightened_vmcs {
u16 host_gs_selector;
u16 host_tr_selector;
+ u16 padding16_1;
+
u64 host_ia32_pat;
u64 host_ia32_efer;
@@ -159,7 +153,7 @@ struct hv_enlightened_vmcs {
u64 ept_pointer;
u16 virtual_processor_id;
- u16 padding16[3];
+ u16 padding16_2[3];
u64 padding64_2[5];
u64 guest_physical_address;
@@ -195,13 +189,13 @@ struct hv_enlightened_vmcs {
u64 guest_rip;
u32 hv_clean_fields;
- u32 hv_padding_32;
+ u32 padding32_1;
u32 hv_synthetic_controls;
struct {
u32 nested_flush_hypercall:1;
u32 msr_bitmap:1;
u32 reserved:30;
- } hv_enlightenments_control;
+ } __packed hv_enlightenments_control;
u32 hv_vp_id;
u32 padding32_2;
u64 hv_vm_id;
@@ -222,7 +216,7 @@ struct hv_enlightened_vmcs {
u64 host_ssp;
u64 host_ia32_int_ssp_table_addr;
u64 padding64_6;
-};
+} __packed;
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE 0
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP BIT(0)
@@ -243,29 +237,15 @@ struct hv_enlightened_vmcs {
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL BIT(15)
#define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF
-#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
-#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
-#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
-#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
- (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031
extern struct hv_enlightened_vmcs *current_evmcs;
-extern struct hv_vp_assist_page *current_vp_assist;
int vcpu_enable_evmcs(struct kvm_vcpu *vcpu);
-static inline int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
+static inline void evmcs_enable(void)
{
- u64 val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
- HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
-
- wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val);
-
- current_vp_assist = vp_assist;
-
enable_evmcs = true;
-
- return 0;
}
static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
@@ -278,6 +258,16 @@ static inline int evmcs_vmptrld(uint64_t vmcs_pa, void *vmcs)
return 0;
}
+static inline bool load_evmcs(struct hyperv_test_pages *hv)
+{
+ if (evmcs_vmptrld(hv->enlightened_vmcs_gpa, hv->enlightened_vmcs))
+ return false;
+
+ current_evmcs->revision_id = EVMCS_VERSION;
+
+ return true;
+}
+
static inline int evmcs_vmptrst(uint64_t *value)
{
*value = current_vp_assist->current_nested_vmcs &
diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
index b66910702c0a..9218bb5f44bf 100644
--- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h
+++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
@@ -9,6 +9,8 @@
#ifndef SELFTEST_KVM_HYPERV_H
#define SELFTEST_KVM_HYPERV_H
+#include "processor.h"
+
#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS 0x40000000
#define HYPERV_CPUID_INTERFACE 0x40000001
#define HYPERV_CPUID_VERSION 0x40000002
@@ -184,5 +186,106 @@
/* hypercall options */
#define HV_HYPERCALL_FAST_BIT BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET 17
+#define HV_HYPERCALL_REP_COMP_OFFSET 32
+
+/*
+ * Issue a Hyper-V hypercall. Returns exception vector raised or 0, 'hv_status'
+ * is set to the hypercall status (if no exception occurred).
+ */
+static inline uint8_t __hyperv_hypercall(u64 control, vm_vaddr_t input_address,
+ vm_vaddr_t output_address,
+ uint64_t *hv_status)
+{
+ uint64_t error_code;
+ uint8_t vector;
+
+ /* Note both the hypercall and the "asm safe" clobber r9-r11. */
+ asm volatile("mov %[output_address], %%r8\n\t"
+ KVM_ASM_SAFE("vmcall")
+ : "=a" (*hv_status),
+ "+c" (control), "+d" (input_address),
+ KVM_ASM_SAFE_OUTPUTS(vector, error_code)
+ : [output_address] "r"(output_address),
+ "a" (-EFAULT)
+ : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS);
+ return vector;
+}
+
+/* Issue a Hyper-V hypercall and assert that it succeeded. */
+static inline void hyperv_hypercall(u64 control, vm_vaddr_t input_address,
+ vm_vaddr_t output_address)
+{
+ uint64_t hv_status;
+ uint8_t vector;
+
+ vector = __hyperv_hypercall(control, input_address, output_address, &hv_status);
+
+ GUEST_ASSERT(!vector);
+ GUEST_ASSERT((hv_status & 0xffff) == 0);
+}
+
+/* Write 'Fast' hypercall input 'data' to the first 'n_sse_regs' SSE regs */
+static inline void hyperv_write_xmm_input(void *data, int n_sse_regs)
+{
+ int i;
+
+ for (i = 0; i < n_sse_regs; i++)
+ write_sse_reg(i, (sse128_t *)(data + sizeof(sse128_t) * i));
+}
+
+/* Proper HV_X64_MSR_GUEST_OS_ID value */
+#define HYPERV_LINUX_OS_ID ((u64)0x8100 << 48)
+
+#define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073
+#define HV_X64_MSR_VP_ASSIST_PAGE_ENABLE 0x00000001
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT 12
+#define HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK \
+ (~((1ull << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+struct hv_nested_enlightenments_control {
+ struct {
+ __u32 directhypercall:1;
+ __u32 reserved:31;
+ } features;
+ struct {
+ __u32 reserved;
+ } hypercallControls;
+} __packed;
+
+/* Define virtual processor assist page structure. */
+struct hv_vp_assist_page {
+ __u32 apic_assist;
+ __u32 reserved1;
+ __u64 vtl_control[3];
+ struct hv_nested_enlightenments_control nested_control;
+ __u8 enlighten_vmentry;
+ __u8 reserved2[7];
+ __u64 current_nested_vmcs;
+} __packed;
+
+extern struct hv_vp_assist_page *current_vp_assist;
+
+int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist);
+
+struct hyperv_test_pages {
+ /* VP assist page */
+ void *vp_assist_hva;
+ uint64_t vp_assist_gpa;
+ void *vp_assist;
+
+ /* Partition assist page */
+ void *partition_assist_hva;
+ uint64_t partition_assist_gpa;
+ void *partition_assist;
+
+ /* Enlightened VMCS */
+ void *enlightened_vmcs_hva;
+ uint64_t enlightened_vmcs_gpa;
+ void *enlightened_vmcs;
+};
+
+struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm,
+ vm_vaddr_t *p_hv_pages_gva);
#endif /* !SELFTEST_KVM_HYPERV_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index e8ca0d8a6a7e..5d310abe6c3f 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -63,16 +63,21 @@ struct kvm_x86_cpu_feature {
u8 reg;
u8 bit;
};
-#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \
-({ \
- struct kvm_x86_cpu_feature feature = { \
- .function = fn, \
- .index = idx, \
- .reg = KVM_CPUID_##gpr, \
- .bit = __bit, \
- }; \
- \
- feature; \
+#define KVM_X86_CPU_FEATURE(fn, idx, gpr, __bit) \
+({ \
+ struct kvm_x86_cpu_feature feature = { \
+ .function = fn, \
+ .index = idx, \
+ .reg = KVM_CPUID_##gpr, \
+ .bit = __bit, \
+ }; \
+ \
+ static_assert((fn & 0xc0000000) == 0 || \
+ (fn & 0xc0000000) == 0x40000000 || \
+ (fn & 0xc0000000) == 0x80000000 || \
+ (fn & 0xc0000000) == 0xc0000000); \
+ static_assert(idx < BIT(sizeof(feature.index) * BITS_PER_BYTE)); \
+ feature; \
})
/*
@@ -89,6 +94,7 @@ struct kvm_x86_cpu_feature {
#define X86_FEATURE_XSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 26)
#define X86_FEATURE_OSXSAVE KVM_X86_CPU_FEATURE(0x1, 0, ECX, 27)
#define X86_FEATURE_RDRAND KVM_X86_CPU_FEATURE(0x1, 0, ECX, 30)
+#define X86_FEATURE_PAE KVM_X86_CPU_FEATURE(0x1, 0, EDX, 6)
#define X86_FEATURE_MCE KVM_X86_CPU_FEATURE(0x1, 0, EDX, 7)
#define X86_FEATURE_APIC KVM_X86_CPU_FEATURE(0x1, 0, EDX, 9)
#define X86_FEATURE_CLFLUSH KVM_X86_CPU_FEATURE(0x1, 0, EDX, 19)
@@ -162,6 +168,102 @@ struct kvm_x86_cpu_feature {
#define X86_FEATURE_KVM_HC_MAP_GPA_RANGE KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 16)
#define X86_FEATURE_KVM_MIGRATION_CONTROL KVM_X86_CPU_FEATURE(0x40000001, 0, EAX, 17)
+/*
+ * Same idea as X86_FEATURE_XXX, but X86_PROPERTY_XXX retrieves a multi-bit
+ * value/property as opposed to a single-bit feature. Again, pack the info
+ * into a 64-bit value to pass by value with no overhead.
+ */
+struct kvm_x86_cpu_property {
+ u32 function;
+ u8 index;
+ u8 reg;
+ u8 lo_bit;
+ u8 hi_bit;
+};
+#define KVM_X86_CPU_PROPERTY(fn, idx, gpr, low_bit, high_bit) \
+({ \
+ struct kvm_x86_cpu_property property = { \
+ .function = fn, \
+ .index = idx, \
+ .reg = KVM_CPUID_##gpr, \
+ .lo_bit = low_bit, \
+ .hi_bit = high_bit, \
+ }; \
+ \
+ static_assert(low_bit < high_bit); \
+ static_assert((fn & 0xc0000000) == 0 || \
+ (fn & 0xc0000000) == 0x40000000 || \
+ (fn & 0xc0000000) == 0x80000000 || \
+ (fn & 0xc0000000) == 0xc0000000); \
+ static_assert(idx < BIT(sizeof(property.index) * BITS_PER_BYTE)); \
+ property; \
+})
+
+#define X86_PROPERTY_MAX_BASIC_LEAF KVM_X86_CPU_PROPERTY(0, 0, EAX, 0, 31)
+#define X86_PROPERTY_PMU_VERSION KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 0, 7)
+#define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
+#define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
+
+#define X86_PROPERTY_XSTATE_MAX_SIZE_XCR0 KVM_X86_CPU_PROPERTY(0xd, 0, EBX, 0, 31)
+#define X86_PROPERTY_XSTATE_MAX_SIZE KVM_X86_CPU_PROPERTY(0xd, 0, ECX, 0, 31)
+#define X86_PROPERTY_XSTATE_TILE_SIZE KVM_X86_CPU_PROPERTY(0xd, 18, EAX, 0, 31)
+#define X86_PROPERTY_XSTATE_TILE_OFFSET KVM_X86_CPU_PROPERTY(0xd, 18, EBX, 0, 31)
+#define X86_PROPERTY_AMX_TOTAL_TILE_BYTES KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 0, 15)
+#define X86_PROPERTY_AMX_BYTES_PER_TILE KVM_X86_CPU_PROPERTY(0x1d, 1, EAX, 16, 31)
+#define X86_PROPERTY_AMX_BYTES_PER_ROW KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 0, 15)
+#define X86_PROPERTY_AMX_NR_TILE_REGS KVM_X86_CPU_PROPERTY(0x1d, 1, EBX, 16, 31)
+#define X86_PROPERTY_AMX_MAX_ROWS KVM_X86_CPU_PROPERTY(0x1d, 1, ECX, 0, 15)
+
+#define X86_PROPERTY_MAX_KVM_LEAF KVM_X86_CPU_PROPERTY(0x40000000, 0, EAX, 0, 31)
+
+#define X86_PROPERTY_MAX_EXT_LEAF KVM_X86_CPU_PROPERTY(0x80000000, 0, EAX, 0, 31)
+#define X86_PROPERTY_MAX_PHY_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 0, 7)
+#define X86_PROPERTY_MAX_VIRT_ADDR KVM_X86_CPU_PROPERTY(0x80000008, 0, EAX, 8, 15)
+#define X86_PROPERTY_PHYS_ADDR_REDUCTION KVM_X86_CPU_PROPERTY(0x8000001F, 0, EBX, 6, 11)
+
+#define X86_PROPERTY_MAX_CENTAUR_LEAF KVM_X86_CPU_PROPERTY(0xC0000000, 0, EAX, 0, 31)
+
+/*
+ * Intel's architectural PMU events are bizarre. They have a "feature" bit
+ * that indicates the feature is _not_ supported, and a property that states
+ * the length of the bit mask of unsupported features. A feature is supported
+ * if the size of the bit mask is larger than the "unavailable" bit, and said
+ * bit is not set.
+ *
+ * Wrap the "unavailable" feature to simplify checking whether or not a given
+ * architectural event is supported.
+ */
+struct kvm_x86_pmu_feature {
+ struct kvm_x86_cpu_feature anti_feature;
+};
+#define KVM_X86_PMU_FEATURE(name, __bit) \
+({ \
+ struct kvm_x86_pmu_feature feature = { \
+ .anti_feature = KVM_X86_CPU_FEATURE(0xa, 0, EBX, __bit), \
+ }; \
+ \
+ feature; \
+})
+
+#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(BRANCH_INSNS_RETIRED, 5)
+
+static inline unsigned int x86_family(unsigned int eax)
+{
+ unsigned int x86;
+
+ x86 = (eax >> 8) & 0xf;
+
+ if (x86 == 0xf)
+ x86 += (eax >> 20) & 0xff;
+
+ return x86;
+}
+
+static inline unsigned int x86_model(unsigned int eax)
+{
+ return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
+}
+
/* Page table bitfield declarations */
#define PTE_PRESENT_MASK BIT_ULL(0)
#define PTE_WRITABLE_MASK BIT_ULL(1)
@@ -172,12 +274,18 @@ struct kvm_x86_cpu_feature {
#define PTE_GLOBAL_MASK BIT_ULL(8)
#define PTE_NX_MASK BIT_ULL(63)
+#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12)
+
#define PAGE_SHIFT 12
#define PAGE_SIZE (1ULL << PAGE_SHIFT)
-#define PAGE_MASK (~(PAGE_SIZE-1))
+#define PAGE_MASK (~(PAGE_SIZE-1) & PHYSICAL_PAGE_MASK)
-#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12)
-#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+#define HUGEPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9))
+#define HUGEPAGE_SIZE(x) (1UL << HUGEPAGE_SHIFT(x))
+#define HUGEPAGE_MASK(x) (~(HUGEPAGE_SIZE(x) - 1) & PHYSICAL_PAGE_MASK)
+
+#define PTE_GET_PA(pte) ((pte) & PHYSICAL_PAGE_MASK)
+#define PTE_GET_PFN(pte) (PTE_GET_PA(pte) >> PAGE_SHIFT)
/* General Registers in 64-Bit Mode */
struct gpr64_regs {
@@ -425,82 +533,143 @@ static inline void cpuid(uint32_t function,
return __cpuid(function, 0, eax, ebx, ecx, edx);
}
-static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature)
+static inline uint32_t this_cpu_fms(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+ return eax;
+}
+
+static inline uint32_t this_cpu_family(void)
+{
+ return x86_family(this_cpu_fms());
+}
+
+static inline uint32_t this_cpu_model(void)
+{
+ return x86_model(this_cpu_fms());
+}
+
+static inline uint32_t __this_cpu_has(uint32_t function, uint32_t index,
+ uint8_t reg, uint8_t lo, uint8_t hi)
{
uint32_t gprs[4];
- __cpuid(feature.function, feature.index,
+ __cpuid(function, index,
&gprs[KVM_CPUID_EAX], &gprs[KVM_CPUID_EBX],
&gprs[KVM_CPUID_ECX], &gprs[KVM_CPUID_EDX]);
- return gprs[feature.reg] & BIT(feature.bit);
+ return (gprs[reg] & GENMASK(hi, lo)) >> lo;
+}
+
+static inline bool this_cpu_has(struct kvm_x86_cpu_feature feature)
+{
+ return __this_cpu_has(feature.function, feature.index,
+ feature.reg, feature.bit, feature.bit);
}
-#define SET_XMM(__var, __xmm) \
- asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
+static inline uint32_t this_cpu_property(struct kvm_x86_cpu_property property)
+{
+ return __this_cpu_has(property.function, property.index,
+ property.reg, property.lo_bit, property.hi_bit);
+}
-static inline void set_xmm(int n, unsigned long val)
+static __always_inline bool this_cpu_has_p(struct kvm_x86_cpu_property property)
{
- switch (n) {
+ uint32_t max_leaf;
+
+ switch (property.function & 0xc0000000) {
case 0:
- SET_XMM(val, xmm0);
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF);
+ break;
+ case 0x40000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF);
+ break;
+ case 0x80000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_EXT_LEAF);
+ break;
+ case 0xc0000000:
+ max_leaf = this_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF);
+ }
+ return max_leaf >= property.function;
+}
+
+static inline bool this_pmu_has(struct kvm_x86_pmu_feature feature)
+{
+ uint32_t nr_bits = this_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+
+ return nr_bits > feature.anti_feature.bit &&
+ !this_cpu_has(feature.anti_feature);
+}
+
+typedef u32 __attribute__((vector_size(16))) sse128_t;
+#define __sse128_u union { sse128_t vec; u64 as_u64[2]; u32 as_u32[4]; }
+#define sse128_lo(x) ({ __sse128_u t; t.vec = x; t.as_u64[0]; })
+#define sse128_hi(x) ({ __sse128_u t; t.vec = x; t.as_u64[1]; })
+
+static inline void read_sse_reg(int reg, sse128_t *data)
+{
+ switch (reg) {
+ case 0:
+ asm("movdqa %%xmm0, %0" : "=m"(*data));
break;
case 1:
- SET_XMM(val, xmm1);
+ asm("movdqa %%xmm1, %0" : "=m"(*data));
break;
case 2:
- SET_XMM(val, xmm2);
+ asm("movdqa %%xmm2, %0" : "=m"(*data));
break;
case 3:
- SET_XMM(val, xmm3);
+ asm("movdqa %%xmm3, %0" : "=m"(*data));
break;
case 4:
- SET_XMM(val, xmm4);
+ asm("movdqa %%xmm4, %0" : "=m"(*data));
break;
case 5:
- SET_XMM(val, xmm5);
+ asm("movdqa %%xmm5, %0" : "=m"(*data));
break;
case 6:
- SET_XMM(val, xmm6);
+ asm("movdqa %%xmm6, %0" : "=m"(*data));
break;
case 7:
- SET_XMM(val, xmm7);
+ asm("movdqa %%xmm7, %0" : "=m"(*data));
break;
+ default:
+ BUG();
}
}
-#define GET_XMM(__xmm) \
-({ \
- unsigned long __val; \
- asm volatile("movq %%"#__xmm", %0" : "=r"(__val)); \
- __val; \
-})
-
-static inline unsigned long get_xmm(int n)
+static inline void write_sse_reg(int reg, const sse128_t *data)
{
- assert(n >= 0 && n <= 7);
-
- switch (n) {
+ switch (reg) {
case 0:
- return GET_XMM(xmm0);
+ asm("movdqa %0, %%xmm0" : : "m"(*data));
+ break;
case 1:
- return GET_XMM(xmm1);
+ asm("movdqa %0, %%xmm1" : : "m"(*data));
+ break;
case 2:
- return GET_XMM(xmm2);
+ asm("movdqa %0, %%xmm2" : : "m"(*data));
+ break;
case 3:
- return GET_XMM(xmm3);
+ asm("movdqa %0, %%xmm3" : : "m"(*data));
+ break;
case 4:
- return GET_XMM(xmm4);
+ asm("movdqa %0, %%xmm4" : : "m"(*data));
+ break;
case 5:
- return GET_XMM(xmm5);
+ asm("movdqa %0, %%xmm5" : : "m"(*data));
+ break;
case 6:
- return GET_XMM(xmm6);
+ asm("movdqa %0, %%xmm6" : : "m"(*data));
+ break;
case 7:
- return GET_XMM(xmm7);
+ asm("movdqa %0, %%xmm7" : : "m"(*data));
+ break;
+ default:
+ BUG();
}
-
- /* never reached */
- return 0;
}
static inline void cpu_relax(void)
@@ -508,11 +677,6 @@ static inline void cpu_relax(void)
asm volatile("rep; nop" ::: "memory");
}
-#define vmmcall() \
- __asm__ __volatile__( \
- "vmmcall\n" \
- )
-
#define ud2() \
__asm__ __volatile__( \
"ud2\n" \
@@ -526,23 +690,6 @@ static inline void cpu_relax(void)
bool is_intel_cpu(void);
bool is_amd_cpu(void);
-static inline unsigned int x86_family(unsigned int eax)
-{
- unsigned int x86;
-
- x86 = (eax >> 8) & 0xf;
-
- if (x86 == 0xf)
- x86 += (eax >> 20) & 0xff;
-
- return x86;
-}
-
-static inline unsigned int x86_model(unsigned int eax)
-{
- return ((eax >> 12) & 0xf0) | ((eax >> 4) & 0x0f);
-}
-
struct kvm_x86_state *vcpu_save_state(struct kvm_vcpu *vcpu);
void vcpu_load_state(struct kvm_vcpu *vcpu, struct kvm_x86_state *state);
void kvm_x86_state_cleanup(struct kvm_x86_state *state);
@@ -604,10 +751,27 @@ static inline void vcpu_xcrs_set(struct kvm_vcpu *vcpu, struct kvm_xcrs *xcrs)
vcpu_ioctl(vcpu, KVM_SET_XCRS, xcrs);
}
+const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,
+ uint32_t function, uint32_t index);
const struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
const struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(void);
const struct kvm_cpuid2 *vcpu_get_supported_hv_cpuid(struct kvm_vcpu *vcpu);
+static inline uint32_t kvm_cpu_fms(void)
+{
+ return get_cpuid_entry(kvm_get_supported_cpuid(), 0x1, 0)->eax;
+}
+
+static inline uint32_t kvm_cpu_family(void)
+{
+ return x86_family(kvm_cpu_fms());
+}
+
+static inline uint32_t kvm_cpu_model(void)
+{
+ return x86_model(kvm_cpu_fms());
+}
+
bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid,
struct kvm_x86_cpu_feature feature);
@@ -616,6 +780,42 @@ static inline bool kvm_cpu_has(struct kvm_x86_cpu_feature feature)
return kvm_cpuid_has(kvm_get_supported_cpuid(), feature);
}
+uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid,
+ struct kvm_x86_cpu_property property);
+
+static inline uint32_t kvm_cpu_property(struct kvm_x86_cpu_property property)
+{
+ return kvm_cpuid_property(kvm_get_supported_cpuid(), property);
+}
+
+static __always_inline bool kvm_cpu_has_p(struct kvm_x86_cpu_property property)
+{
+ uint32_t max_leaf;
+
+ switch (property.function & 0xc0000000) {
+ case 0:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_BASIC_LEAF);
+ break;
+ case 0x40000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_KVM_LEAF);
+ break;
+ case 0x80000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_EXT_LEAF);
+ break;
+ case 0xc0000000:
+ max_leaf = kvm_cpu_property(X86_PROPERTY_MAX_CENTAUR_LEAF);
+ }
+ return max_leaf >= property.function;
+}
+
+static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature)
+{
+ uint32_t nr_bits = kvm_cpu_property(X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH);
+
+ return nr_bits > feature.anti_feature.bit &&
+ !kvm_cpu_has(feature.anti_feature);
+}
+
static inline size_t kvm_cpuid2_size(int nr_entries)
{
return sizeof(struct kvm_cpuid2) +
@@ -639,8 +839,6 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries)
return cpuid;
}
-const struct kvm_cpuid_entry2 *get_cpuid_entry(const struct kvm_cpuid2 *cpuid,
- uint32_t function, uint32_t index);
void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid);
void vcpu_set_hv_cpuid(struct kvm_vcpu *vcpu);
@@ -701,17 +899,6 @@ static inline void vcpu_clear_cpuid_feature(struct kvm_vcpu *vcpu,
vcpu_set_or_clear_cpuid_feature(vcpu, feature, false);
}
-static inline const struct kvm_cpuid_entry2 *__kvm_get_supported_cpuid_entry(uint32_t function,
- uint32_t index)
-{
- return get_cpuid_entry(kvm_get_supported_cpuid(), function, index);
-}
-
-static inline const struct kvm_cpuid_entry2 *kvm_get_supported_cpuid_entry(uint32_t function)
-{
- return __kvm_get_supported_cpuid_entry(function, 0);
-}
-
uint64_t vcpu_get_msr(struct kvm_vcpu *vcpu, uint64_t msr_index);
int _vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index, uint64_t msr_value);
@@ -723,15 +910,6 @@ static inline void vcpu_set_msr(struct kvm_vcpu *vcpu, uint64_t msr_index,
TEST_ASSERT(r == 1, KVM_IOCTL_ERROR(KVM_SET_MSRS, r));
}
-static inline uint32_t kvm_get_cpuid_max_basic(void)
-{
- return kvm_get_supported_cpuid_entry(0)->eax;
-}
-
-static inline uint32_t kvm_get_cpuid_max_extended(void)
-{
- return kvm_get_supported_cpuid_entry(0x80000000)->eax;
-}
void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
bool vm_is_unrestricted_guest(struct kvm_vm *vm);
@@ -748,6 +926,19 @@ struct ex_regs {
uint64_t rflags;
};
+struct idt_entry {
+ uint16_t offset0;
+ uint16_t selector;
+ uint16_t ist : 3;
+ uint16_t : 5;
+ uint16_t type : 4;
+ uint16_t : 1;
+ uint16_t dpl : 2;
+ uint16_t p : 1;
+ uint16_t offset1;
+ uint32_t offset2; uint32_t reserved;
+};
+
void vm_init_descriptor_tables(struct kvm_vm *vm);
void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu);
void vm_install_exception_handler(struct kvm_vm *vm, int vector,
@@ -764,7 +955,7 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
* for recursive faults when accessing memory in the handler. The downside to
* using registers is that it restricts what registers can be used by the actual
* instruction. But, selftests are 64-bit only, making register* pressure a
- * minor concern. Use r9-r11 as they are volatile, i.e. don't need* to be saved
+ * minor concern. Use r9-r11 as they are volatile, i.e. don't need to be saved
* by the callee, and except for r11 are not implicit parameters to any
* instructions. Ideally, fixup would use r8-r10 and thus avoid implicit
* parameters entirely, but Hyper-V's hypercall ABI uses r8 and testing Hyper-V
@@ -780,39 +971,52 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
*
* REGISTER OUTPUTS:
* r9 = exception vector (non-zero)
+ * r10 = error code
*/
#define KVM_ASM_SAFE(insn) \
"mov $" __stringify(KVM_EXCEPTION_MAGIC) ", %%r9\n\t" \
"lea 1f(%%rip), %%r10\n\t" \
"lea 2f(%%rip), %%r11\n\t" \
"1: " insn "\n\t" \
- "movb $0, %[vector]\n\t" \
- "jmp 3f\n\t" \
+ "xor %%r9, %%r9\n\t" \
"2:\n\t" \
"mov %%r9b, %[vector]\n\t" \
- "3:\n\t"
+ "mov %%r10, %[error_code]\n\t"
-#define KVM_ASM_SAFE_OUTPUTS(v) [vector] "=qm"(v)
+#define KVM_ASM_SAFE_OUTPUTS(v, ec) [vector] "=qm"(v), [error_code] "=rm"(ec)
#define KVM_ASM_SAFE_CLOBBERS "r9", "r10", "r11"
-#define kvm_asm_safe(insn, inputs...) \
-({ \
- uint8_t vector; \
- \
- asm volatile(KVM_ASM_SAFE(insn) \
- : KVM_ASM_SAFE_OUTPUTS(vector) \
- : inputs \
- : KVM_ASM_SAFE_CLOBBERS); \
- vector; \
+#define kvm_asm_safe(insn, inputs...) \
+({ \
+ uint64_t ign_error_code; \
+ uint8_t vector; \
+ \
+ asm volatile(KVM_ASM_SAFE(insn) \
+ : KVM_ASM_SAFE_OUTPUTS(vector, ign_error_code) \
+ : inputs \
+ : KVM_ASM_SAFE_CLOBBERS); \
+ vector; \
+})
+
+#define kvm_asm_safe_ec(insn, error_code, inputs...) \
+({ \
+ uint8_t vector; \
+ \
+ asm volatile(KVM_ASM_SAFE(insn) \
+ : KVM_ASM_SAFE_OUTPUTS(vector, error_code) \
+ : inputs \
+ : KVM_ASM_SAFE_CLOBBERS); \
+ vector; \
})
static inline uint8_t rdmsr_safe(uint32_t msr, uint64_t *val)
{
+ uint64_t error_code;
uint8_t vector;
uint32_t a, d;
asm volatile(KVM_ASM_SAFE("rdmsr")
- : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector)
+ : "=a"(a), "=d"(d), KVM_ASM_SAFE_OUTPUTS(vector, error_code)
: "c"(msr)
: KVM_ASM_SAFE_CLOBBERS);
@@ -827,10 +1031,9 @@ static inline uint8_t wrmsr_safe(uint32_t msr, uint64_t val)
bool kvm_is_tdp_enabled(void);
-uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
- uint64_t vaddr);
-void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
- uint64_t vaddr, uint64_t pte);
+uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
+ int *level);
+uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr);
uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
uint64_t a3);
@@ -882,4 +1085,27 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
#define XSTATE_XTILE_DATA_MASK (1ULL << XSTATE_XTILE_DATA_BIT)
#define XFEATURE_XTILE_MASK (XSTATE_XTILE_CFG_MASK | \
XSTATE_XTILE_DATA_MASK)
+
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+#define PFERR_PK_BIT 5
+#define PFERR_SGX_BIT 15
+#define PFERR_GUEST_FINAL_BIT 32
+#define PFERR_GUEST_PAGE_BIT 33
+#define PFERR_IMPLICIT_ACCESS_BIT 48
+
+#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT)
+#define PFERR_USER_MASK BIT(PFERR_USER_BIT)
+#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT)
+#define PFERR_PK_MASK BIT(PFERR_PK_BIT)
+#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT)
+#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT)
+#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT)
+#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT)
+
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86_64/svm.h
index c8343ff84f7f..4803e1056055 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm.h
@@ -58,6 +58,27 @@ enum {
INTERCEPT_RDPRU,
};
+struct hv_vmcb_enlightenments {
+ struct __packed hv_enlightenments_control {
+ u32 nested_flush_hypercall:1;
+ u32 msr_bitmap:1;
+ u32 enlightened_npt_tlb: 1;
+ u32 reserved:29;
+ } __packed hv_enlightenments_control;
+ u32 hv_vp_id;
+ u64 hv_vm_id;
+ u64 partition_assist_page;
+ u64 reserved;
+} __packed;
+
+/*
+ * Hyper-V uses the software reserved clean bit in VMCB
+ */
+#define HV_VMCB_NESTED_ENLIGHTENMENTS (1U << 31)
+
+/* Synthetic VM-Exit */
+#define HV_SVM_EXITCODE_ENL 0xf0000000
+#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1)
struct __attribute__ ((__packed__)) vmcb_control_area {
u32 intercept_cr;
@@ -106,7 +127,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
* Offset 0x3e0, 32 bytes reserved
* for use by hypervisor/software.
*/
- u8 reserved_sw[32];
+ union {
+ struct hv_vmcb_enlightenments hv_enlightenments;
+ u8 reserved_sw[32];
+ };
};
diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
index 7aee6244ab6a..044f0f872ba9 100644
--- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h
+++ b/tools/testing/selftests/kvm/include/x86_64/svm_util.h
@@ -32,6 +32,20 @@ struct svm_test_data {
uint64_t msr_gpa;
};
+static inline void vmmcall(void)
+{
+ /*
+ * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle
+ * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended
+ * use of this function is to exit to L1 from L2. Clobber all other
+ * GPRs as L1 doesn't correctly preserve them during vmexits.
+ */
+ __asm__ __volatile__("push %%rbp; vmmcall; pop %%rbp"
+ : : "a"(0xdeadbeef), "c"(0xbeefdead)
+ : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
+}
+
#define stgi() \
__asm__ __volatile__( \
"stgi\n" \
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 71b290b6469d..5f0c0a29c556 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -437,11 +437,16 @@ static inline int vmresume(void)
static inline void vmcall(void)
{
- /* Currently, L1 destroys our GPRs during vmexits. */
- __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp" : : :
- "rax", "rbx", "rcx", "rdx",
- "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
- "r13", "r14", "r15");
+ /*
+ * Stuff RAX and RCX with "safe" values to make sure L0 doesn't handle
+ * it as a valid hypercall (e.g. Hyper-V L2 TLB flush) as the intended
+ * use of this function is to exit to L1 from L2. Clobber all other
+ * GPRs as L1 doesn't correctly preserve them during vmexits.
+ */
+ __asm__ __volatile__("push %%rbp; vmcall; pop %%rbp"
+ : : "a"(0xdeadbeef), "c"(0xbeefdead)
+ : "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
}
static inline int vmread(uint64_t encoding, uint64_t *value)
@@ -517,14 +522,6 @@ struct vmx_pages {
uint64_t vmwrite_gpa;
void *vmwrite;
- void *vp_assist_hva;
- uint64_t vp_assist_gpa;
- void *vp_assist;
-
- void *enlightened_vmcs_hva;
- uint64_t enlightened_vmcs_gpa;
- void *enlightened_vmcs;
-
void *eptp_hva;
uint64_t eptp_gpa;
void *eptp;
@@ -572,7 +569,7 @@ void nested_map_memslot(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t memslot);
void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
uint64_t addr, uint64_t size);
-bool kvm_vm_has_ept(struct kvm_vm *vm);
+bool kvm_cpu_has_ept(void);
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot);
void prepare_virtualize_apic_accesses(struct vmx_pages *vmx, struct kvm_vm *vm);
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index f42c6ac6d71d..b3b00be1ef82 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -289,7 +289,6 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
host_test_mem = addr_gpa2hva(vm, (vm_paddr_t)guest_test_phys_mem);
/* Export shared structure test_args to guest */
- ucall_init(vm, NULL);
sync_global_to_guest(vm, test_args);
ret = sem_init(&test_stage_updated, 0, 0);
@@ -417,7 +416,6 @@ static void run_test(enum vm_guest_mode mode, void *arg)
TEST_ASSERT(ret == 0, "Error in sem_destroy");
free(vcpu_threads);
- ucall_uninit(vm);
kvm_vm_free(vm);
}
@@ -461,8 +459,8 @@ int main(int argc, char *argv[])
p.test_mem_size = parse_size(optarg);
break;
case 'v':
- nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+ TEST_ASSERT(nr_vcpus <= max_vcpus,
"Invalid number of vcpus, must be between 1 and %d", max_vcpus);
break;
case 's':
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 6f5551368944..0de4aabc0c76 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -495,15 +495,6 @@ void aarch64_get_supported_page_sizes(uint32_t ipa,
close(kvm_fd);
}
-/*
- * arm64 doesn't have a true default mode, so start by computing the
- * available IPA space and page sizes early.
- */
-void __attribute__((constructor)) init_guest_modes(void)
-{
- guest_modes_append_default();
-}
-
void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
uint64_t arg6, struct arm_smccc_res *res)
@@ -528,3 +519,12 @@ void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
[arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6)
: "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7");
}
+
+void kvm_selftest_arch_init(void)
+{
+ /*
+ * arm64 doesn't have a true default mode, so start by computing the
+ * available IPA space and page sizes early.
+ */
+ guest_modes_append_default();
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
index ed237b744690..562c16dfbb00 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -6,108 +6,36 @@
*/
#include "kvm_util.h"
+/*
+ * ucall_exit_mmio_addr holds per-VM values (global data is duplicated by each
+ * VM), it must not be accessed from host code.
+ */
static vm_vaddr_t *ucall_exit_mmio_addr;
-static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
-{
- if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
- return false;
-
- virt_pg_map(vm, gpa, gpa);
-
- ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
- sync_global_to_guest(vm, ucall_exit_mmio_addr);
-
- return true;
-}
-
-void ucall_init(struct kvm_vm *vm, void *arg)
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
{
- vm_paddr_t gpa, start, end, step, offset;
- unsigned int bits;
- bool ret;
+ virt_pg_map(vm, mmio_gpa, mmio_gpa);
- if (arg) {
- gpa = (vm_paddr_t)arg;
- ret = ucall_mmio_init(vm, gpa);
- TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa);
- return;
- }
+ vm->ucall_mmio_addr = mmio_gpa;
- /*
- * Find an address within the allowed physical and virtual address
- * spaces, that does _not_ have a KVM memory region associated with
- * it. Identity mapping an address like this allows the guest to
- * access it, but as KVM doesn't know what to do with it, it
- * will assume it's something userspace handles and exit with
- * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
- * Here we start with a guess that the addresses around 5/8th
- * of the allowed space are unmapped and then work both down and
- * up from there in 1/16th allowed space sized steps.
- *
- * Note, we need to use VA-bits - 1 when calculating the allowed
- * virtual address space for an identity mapping because the upper
- * half of the virtual address space is the two's complement of the
- * lower and won't match physical addresses.
- */
- bits = vm->va_bits - 1;
- bits = min(vm->pa_bits, bits);
- end = 1ul << bits;
- start = end * 5 / 8;
- step = end / 16;
- for (offset = 0; offset < end - start; offset += step) {
- if (ucall_mmio_init(vm, start - offset))
- return;
- if (ucall_mmio_init(vm, start + offset))
- return;
- }
- TEST_FAIL("Can't find a ucall mmio address");
+ write_guest_global(vm, ucall_exit_mmio_addr, (vm_vaddr_t *)mmio_gpa);
}
-void ucall_uninit(struct kvm_vm *vm)
+void ucall_arch_do_ucall(vm_vaddr_t uc)
{
- ucall_exit_mmio_addr = 0;
- sync_global_to_guest(vm, ucall_exit_mmio_addr);
+ WRITE_ONCE(*ucall_exit_mmio_addr, uc);
}
-void ucall(uint64_t cmd, int nargs, ...)
-{
- struct ucall uc = {};
- va_list va;
- int i;
-
- WRITE_ONCE(uc.cmd, cmd);
- nargs = min(nargs, UCALL_MAX_ARGS);
-
- va_start(va, nargs);
- for (i = 0; i < nargs; ++i)
- WRITE_ONCE(uc.args[i], va_arg(va, uint64_t));
- va_end(va);
-
- WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc);
-}
-
-uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
- struct ucall ucall = {};
-
- if (uc)
- memset(uc, 0, sizeof(*uc));
if (run->exit_reason == KVM_EXIT_MMIO &&
- run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
- vm_vaddr_t gva;
-
- TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
+ run->mmio.phys_addr == vcpu->vm->ucall_mmio_addr) {
+ TEST_ASSERT(run->mmio.is_write && run->mmio.len == sizeof(uint64_t),
"Unexpected ucall exit mmio address access");
- memcpy(&gva, run->mmio.data, sizeof(gva));
- memcpy(&ucall, addr_gva2hva(vcpu->vm, gva), sizeof(ucall));
-
- vcpu_run_complete_io(vcpu);
- if (uc)
- memcpy(uc, &ucall, sizeof(ucall));
+ return (void *)(*((uint64_t *)run->mmio.data));
}
- return ucall.cmd;
+ return NULL;
}
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
index 9f54c098d9d0..d71a9a5974de 100644
--- a/tools/testing/selftests/kvm/lib/elf.c
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -138,7 +138,7 @@ void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename)
offset = hdr.e_phoff + (n1 * hdr.e_phentsize);
offset_rv = lseek(fd, offset, SEEK_SET);
TEST_ASSERT(offset_rv == offset,
- "Failed to seek to begining of program header %u,\n"
+ "Failed to seek to beginning of program header %u,\n"
" filename: %s\n"
" rv: %jd errno: %i",
n1, filename, (intmax_t) offset_rv, errno);
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index f1cb1627161f..1d26a2160178 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -11,6 +11,7 @@
#include "processor.h"
#include <assert.h>
+#include <sched.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
@@ -334,15 +335,24 @@ struct kvm_vm *__vm_create(enum vm_guest_mode mode, uint32_t nr_runnable_vcpus,
{
uint64_t nr_pages = vm_nr_pages_required(mode, nr_runnable_vcpus,
nr_extra_pages);
+ struct userspace_mem_region *slot0;
struct kvm_vm *vm;
vm = ____vm_create(mode, nr_pages);
kvm_vm_elf_load(vm, program_invocation_name);
-#ifdef __x86_64__
- vm_create_irqchip(vm);
-#endif
+ /*
+ * TODO: Add proper defines to protect the library's memslots, and then
+ * carve out memslot1 for the ucall MMIO address. KVM treats writes to
+ * read-only memslots as MMIO, and creating a read-only memslot for the
+ * MMIO region would prevent silently clobbering the MMIO region.
+ */
+ slot0 = memslot2region(vm, 0);
+ ucall_init(vm, slot0->region.guest_phys_addr + slot0->region.memory_size);
+
+ kvm_arch_vm_post_create(vm);
+
return vm;
}
@@ -443,6 +453,59 @@ struct kvm_vcpu *vm_recreate_with_one_vcpu(struct kvm_vm *vm)
return vm_vcpu_recreate(vm, 0);
}
+void kvm_pin_this_task_to_pcpu(uint32_t pcpu)
+{
+ cpu_set_t mask;
+ int r;
+
+ CPU_ZERO(&mask);
+ CPU_SET(pcpu, &mask);
+ r = sched_setaffinity(0, sizeof(mask), &mask);
+ TEST_ASSERT(!r, "sched_setaffinity() failed for pCPU '%u'.\n", pcpu);
+}
+
+static uint32_t parse_pcpu(const char *cpu_str, const cpu_set_t *allowed_mask)
+{
+ uint32_t pcpu = atoi_non_negative("CPU number", cpu_str);
+
+ TEST_ASSERT(CPU_ISSET(pcpu, allowed_mask),
+ "Not allowed to run on pCPU '%d', check cgroups?\n", pcpu);
+ return pcpu;
+}
+
+void kvm_parse_vcpu_pinning(const char *pcpus_string, uint32_t vcpu_to_pcpu[],
+ int nr_vcpus)
+{
+ cpu_set_t allowed_mask;
+ char *cpu, *cpu_list;
+ char delim[2] = ",";
+ int i, r;
+
+ cpu_list = strdup(pcpus_string);
+ TEST_ASSERT(cpu_list, "strdup() allocation failed.\n");
+
+ r = sched_getaffinity(0, sizeof(allowed_mask), &allowed_mask);
+ TEST_ASSERT(!r, "sched_getaffinity() failed");
+
+ cpu = strtok(cpu_list, delim);
+
+ /* 1. Get all pcpus for vcpus. */
+ for (i = 0; i < nr_vcpus; i++) {
+ TEST_ASSERT(cpu, "pCPU not provided for vCPU '%d'\n", i);
+ vcpu_to_pcpu[i] = parse_pcpu(cpu, &allowed_mask);
+ cpu = strtok(NULL, delim);
+ }
+
+ /* 2. Check if the main worker needs to be pinned. */
+ if (cpu) {
+ kvm_pin_this_task_to_pcpu(parse_pcpu(cpu, &allowed_mask));
+ cpu = strtok(NULL, delim);
+ }
+
+ TEST_ASSERT(!cpu, "pCPU list contains trailing garbage characters '%s'", cpu);
+ free(cpu_list);
+}
+
/*
* Userspace Memory Region Find
*
@@ -1151,8 +1214,8 @@ struct kvm_vcpu *__vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id)
* TEST_ASSERT failure occurs for invalid input or no area of at least
* sz unallocated bytes >= vaddr_min is available.
*/
-static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
- vm_vaddr_t vaddr_min)
+vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
+ vm_vaddr_t vaddr_min)
{
uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;
@@ -1256,8 +1319,7 @@ vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min)
virt_pg_map(vm, vaddr, paddr);
- sparsebit_set(vm->vpages_mapped,
- vaddr >> vm->page_shift);
+ sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
}
return vaddr_start;
@@ -1330,6 +1392,8 @@ void virt_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
virt_pg_map(vm, vaddr, paddr);
vaddr += page_size;
paddr += page_size;
+
+ sparsebit_set(vm->vpages_mapped, vaddr >> vm->page_shift);
}
}
@@ -2021,3 +2085,19 @@ void __vm_get_stat(struct kvm_vm *vm, const char *stat_name, uint64_t *data,
break;
}
}
+
+__weak void kvm_arch_vm_post_create(struct kvm_vm *vm)
+{
+}
+
+__weak void kvm_selftest_arch_init(void)
+{
+}
+
+void __attribute((constructor)) kvm_selftest_init(void)
+{
+ /* Tell stdout not to buffer its content. */
+ setbuf(stdout, NULL);
+
+ kvm_selftest_arch_init();
+}
diff --git a/tools/testing/selftests/kvm/lib/perf_test_util.c b/tools/testing/selftests/kvm/lib/memstress.c
index 9618b37c66f7..2de8a5d527b3 100644
--- a/tools/testing/selftests/kvm/lib/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/memstress.c
@@ -2,13 +2,15 @@
/*
* Copyright (C) 2020, Google LLC.
*/
+#define _GNU_SOURCE
+
#include <inttypes.h>
#include "kvm_util.h"
-#include "perf_test_util.h"
+#include "memstress.h"
#include "processor.h"
-struct perf_test_args perf_test_args;
+struct memstress_args memstress_args;
/*
* Guest virtual memory offset of the testing memory slot.
@@ -31,7 +33,7 @@ struct vcpu_thread {
static struct vcpu_thread vcpu_threads[KVM_MAX_VCPUS];
/* The function run by each vCPU thread, as provided by the test. */
-static void (*vcpu_thread_fn)(struct perf_test_vcpu_args *);
+static void (*vcpu_thread_fn)(struct memstress_vcpu_args *);
/* Set to true once all vCPU threads are up and running. */
static bool all_vcpu_threads_running;
@@ -42,14 +44,19 @@ static struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
* Continuously write to the first 8 bytes of each page in the
* specified region.
*/
-void perf_test_guest_code(uint32_t vcpu_idx)
+void memstress_guest_code(uint32_t vcpu_idx)
{
- struct perf_test_args *pta = &perf_test_args;
- struct perf_test_vcpu_args *vcpu_args = &pta->vcpu_args[vcpu_idx];
+ struct memstress_args *args = &memstress_args;
+ struct memstress_vcpu_args *vcpu_args = &args->vcpu_args[vcpu_idx];
+ struct guest_random_state rand_state;
uint64_t gva;
uint64_t pages;
+ uint64_t addr;
+ uint64_t page;
int i;
+ rand_state = new_guest_random_state(args->random_seed + vcpu_idx);
+
gva = vcpu_args->gva;
pages = vcpu_args->pages;
@@ -58,9 +65,14 @@ void perf_test_guest_code(uint32_t vcpu_idx)
while (true) {
for (i = 0; i < pages; i++) {
- uint64_t addr = gva + (i * pta->guest_page_size);
+ if (args->random_access)
+ page = guest_random_u32(&rand_state) % pages;
+ else
+ page = i;
- if (i % pta->wr_fract == 0)
+ addr = gva + (page * args->guest_page_size);
+
+ if (guest_random_u32(&rand_state) % 100 < args->write_percent)
*(uint64_t *)addr = 0x0123456789ABCDEF;
else
READ_ONCE(*(uint64_t *)addr);
@@ -70,17 +82,17 @@ void perf_test_guest_code(uint32_t vcpu_idx)
}
}
-void perf_test_setup_vcpus(struct kvm_vm *vm, int nr_vcpus,
+void memstress_setup_vcpus(struct kvm_vm *vm, int nr_vcpus,
struct kvm_vcpu *vcpus[],
uint64_t vcpu_memory_bytes,
bool partition_vcpu_memory_access)
{
- struct perf_test_args *pta = &perf_test_args;
- struct perf_test_vcpu_args *vcpu_args;
+ struct memstress_args *args = &memstress_args;
+ struct memstress_vcpu_args *vcpu_args;
int i;
for (i = 0; i < nr_vcpus; i++) {
- vcpu_args = &pta->vcpu_args[i];
+ vcpu_args = &args->vcpu_args[i];
vcpu_args->vcpu = vcpus[i];
vcpu_args->vcpu_idx = i;
@@ -89,29 +101,29 @@ void perf_test_setup_vcpus(struct kvm_vm *vm, int nr_vcpus,
vcpu_args->gva = guest_test_virt_mem +
(i * vcpu_memory_bytes);
vcpu_args->pages = vcpu_memory_bytes /
- pta->guest_page_size;
- vcpu_args->gpa = pta->gpa + (i * vcpu_memory_bytes);
+ args->guest_page_size;
+ vcpu_args->gpa = args->gpa + (i * vcpu_memory_bytes);
} else {
vcpu_args->gva = guest_test_virt_mem;
vcpu_args->pages = (nr_vcpus * vcpu_memory_bytes) /
- pta->guest_page_size;
- vcpu_args->gpa = pta->gpa;
+ args->guest_page_size;
+ vcpu_args->gpa = args->gpa;
}
vcpu_args_set(vcpus[i], 1, i);
pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
i, vcpu_args->gpa, vcpu_args->gpa +
- (vcpu_args->pages * pta->guest_page_size));
+ (vcpu_args->pages * args->guest_page_size));
}
}
-struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
+struct kvm_vm *memstress_create_vm(enum vm_guest_mode mode, int nr_vcpus,
uint64_t vcpu_memory_bytes, int slots,
enum vm_mem_backing_src_type backing_src,
bool partition_vcpu_memory_access)
{
- struct perf_test_args *pta = &perf_test_args;
+ struct memstress_args *args = &memstress_args;
struct kvm_vm *vm;
uint64_t guest_num_pages, slot0_pages = 0;
uint64_t backing_src_pagesz = get_backing_src_pagesz(backing_src);
@@ -121,20 +133,20 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
/* By default vCPUs will write to memory. */
- pta->wr_fract = 1;
+ args->write_percent = 100;
/*
* Snapshot the non-huge page size. This is used by the guest code to
* access/dirty pages at the logging granularity.
*/
- pta->guest_page_size = vm_guest_mode_params[mode].page_size;
+ args->guest_page_size = vm_guest_mode_params[mode].page_size;
guest_num_pages = vm_adjust_num_guest_pages(mode,
- (nr_vcpus * vcpu_memory_bytes) / pta->guest_page_size);
+ (nr_vcpus * vcpu_memory_bytes) / args->guest_page_size);
TEST_ASSERT(vcpu_memory_bytes % getpagesize() == 0,
"Guest memory size is not host page size aligned.");
- TEST_ASSERT(vcpu_memory_bytes % pta->guest_page_size == 0,
+ TEST_ASSERT(vcpu_memory_bytes % args->guest_page_size == 0,
"Guest memory size is not guest page size aligned.");
TEST_ASSERT(guest_num_pages % slots == 0,
"Guest memory cannot be evenly divided into %d slots.",
@@ -144,8 +156,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
* If using nested, allocate extra pages for the nested page tables and
* in-memory data structures.
*/
- if (pta->nested)
- slot0_pages += perf_test_nested_pages(nr_vcpus);
+ if (args->nested)
+ slot0_pages += memstress_nested_pages(nr_vcpus);
/*
* Pass guest_num_pages to populate the page tables for test memory.
@@ -153,9 +165,9 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
* effect as KVM allows aliasing HVAs in meslots.
*/
vm = __vm_create_with_vcpus(mode, nr_vcpus, slot0_pages + guest_num_pages,
- perf_test_guest_code, vcpus);
+ memstress_guest_code, vcpus);
- pta->vm = vm;
+ args->vm = vm;
/* Put the test region at the top guest physical memory. */
region_end_gfn = vm->max_gfn + 1;
@@ -165,8 +177,8 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
* When running vCPUs in L2, restrict the test region to 48 bits to
* avoid needing 5-level page tables to identity map L2.
*/
- if (pta->nested)
- region_end_gfn = min(region_end_gfn, (1UL << 48) / pta->guest_page_size);
+ if (args->nested)
+ region_end_gfn = min(region_end_gfn, (1UL << 48) / args->guest_page_size);
#endif
/*
* If there should be more memory in the guest test region than there
@@ -178,63 +190,72 @@ struct kvm_vm *perf_test_create_vm(enum vm_guest_mode mode, int nr_vcpus,
" nr_vcpus: %d wss: %" PRIx64 "]\n",
guest_num_pages, region_end_gfn - 1, nr_vcpus, vcpu_memory_bytes);
- pta->gpa = (region_end_gfn - guest_num_pages - 1) * pta->guest_page_size;
- pta->gpa = align_down(pta->gpa, backing_src_pagesz);
+ args->gpa = (region_end_gfn - guest_num_pages - 1) * args->guest_page_size;
+ args->gpa = align_down(args->gpa, backing_src_pagesz);
#ifdef __s390x__
/* Align to 1M (segment size) */
- pta->gpa = align_down(pta->gpa, 1 << 20);
+ args->gpa = align_down(args->gpa, 1 << 20);
#endif
- pta->size = guest_num_pages * pta->guest_page_size;
+ args->size = guest_num_pages * args->guest_page_size;
pr_info("guest physical test memory: [0x%lx, 0x%lx)\n",
- pta->gpa, pta->gpa + pta->size);
+ args->gpa, args->gpa + args->size);
/* Add extra memory slots for testing */
for (i = 0; i < slots; i++) {
uint64_t region_pages = guest_num_pages / slots;
- vm_paddr_t region_start = pta->gpa + region_pages * pta->guest_page_size * i;
+ vm_paddr_t region_start = args->gpa + region_pages * args->guest_page_size * i;
vm_userspace_mem_region_add(vm, backing_src, region_start,
- PERF_TEST_MEM_SLOT_INDEX + i,
+ MEMSTRESS_MEM_SLOT_INDEX + i,
region_pages, 0);
}
/* Do mapping for the demand paging memory slot */
- virt_map(vm, guest_test_virt_mem, pta->gpa, guest_num_pages);
+ virt_map(vm, guest_test_virt_mem, args->gpa, guest_num_pages);
- perf_test_setup_vcpus(vm, nr_vcpus, vcpus, vcpu_memory_bytes,
+ memstress_setup_vcpus(vm, nr_vcpus, vcpus, vcpu_memory_bytes,
partition_vcpu_memory_access);
- if (pta->nested) {
+ if (args->nested) {
pr_info("Configuring vCPUs to run in L2 (nested).\n");
- perf_test_setup_nested(vm, nr_vcpus, vcpus);
+ memstress_setup_nested(vm, nr_vcpus, vcpus);
}
- ucall_init(vm, NULL);
-
/* Export the shared variables to the guest. */
- sync_global_to_guest(vm, perf_test_args);
+ sync_global_to_guest(vm, memstress_args);
return vm;
}
-void perf_test_destroy_vm(struct kvm_vm *vm)
+void memstress_destroy_vm(struct kvm_vm *vm)
{
- ucall_uninit(vm);
kvm_vm_free(vm);
}
-void perf_test_set_wr_fract(struct kvm_vm *vm, int wr_fract)
+void memstress_set_write_percent(struct kvm_vm *vm, uint32_t write_percent)
+{
+ memstress_args.write_percent = write_percent;
+ sync_global_to_guest(vm, memstress_args.write_percent);
+}
+
+void memstress_set_random_seed(struct kvm_vm *vm, uint32_t random_seed)
+{
+ memstress_args.random_seed = random_seed;
+ sync_global_to_guest(vm, memstress_args.random_seed);
+}
+
+void memstress_set_random_access(struct kvm_vm *vm, bool random_access)
{
- perf_test_args.wr_fract = wr_fract;
- sync_global_to_guest(vm, perf_test_args);
+ memstress_args.random_access = random_access;
+ sync_global_to_guest(vm, memstress_args.random_access);
}
-uint64_t __weak perf_test_nested_pages(int nr_vcpus)
+uint64_t __weak memstress_nested_pages(int nr_vcpus)
{
return 0;
}
-void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu **vcpus)
+void __weak memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu **vcpus)
{
pr_info("%s() not support on this architecture, skipping.\n", __func__);
exit(KSFT_SKIP);
@@ -243,6 +264,10 @@ void __weak perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_v
static void *vcpu_thread_main(void *data)
{
struct vcpu_thread *vcpu = data;
+ int vcpu_idx = vcpu->vcpu_idx;
+
+ if (memstress_args.pin_vcpus)
+ kvm_pin_this_task_to_pcpu(memstress_args.vcpu_to_pcpu[vcpu_idx]);
WRITE_ONCE(vcpu->running, true);
@@ -255,13 +280,13 @@ static void *vcpu_thread_main(void *data)
while (!READ_ONCE(all_vcpu_threads_running))
;
- vcpu_thread_fn(&perf_test_args.vcpu_args[vcpu->vcpu_idx]);
+ vcpu_thread_fn(&memstress_args.vcpu_args[vcpu_idx]);
return NULL;
}
-void perf_test_start_vcpu_threads(int nr_vcpus,
- void (*vcpu_fn)(struct perf_test_vcpu_args *))
+void memstress_start_vcpu_threads(int nr_vcpus,
+ void (*vcpu_fn)(struct memstress_vcpu_args *))
{
int i;
@@ -285,7 +310,7 @@ void perf_test_start_vcpu_threads(int nr_vcpus,
WRITE_ONCE(all_vcpu_threads_running, true);
}
-void perf_test_join_vcpu_threads(int nr_vcpus)
+void memstress_join_vcpu_threads(int nr_vcpus)
{
int i;
diff --git a/tools/testing/selftests/kvm/lib/riscv/ucall.c b/tools/testing/selftests/kvm/lib/riscv/ucall.c
index 087b9740bc8f..9a3476a2dfca 100644
--- a/tools/testing/selftests/kvm/lib/riscv/ucall.c
+++ b/tools/testing/selftests/kvm/lib/riscv/ucall.c
@@ -10,11 +10,7 @@
#include "kvm_util.h"
#include "processor.h"
-void ucall_init(struct kvm_vm *vm, void *arg)
-{
-}
-
-void ucall_uninit(struct kvm_vm *vm)
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
{
}
@@ -44,47 +40,22 @@ struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
return ret;
}
-void ucall(uint64_t cmd, int nargs, ...)
+void ucall_arch_do_ucall(vm_vaddr_t uc)
{
- struct ucall uc = {
- .cmd = cmd,
- };
- va_list va;
- int i;
-
- nargs = min(nargs, UCALL_MAX_ARGS);
-
- va_start(va, nargs);
- for (i = 0; i < nargs; ++i)
- uc.args[i] = va_arg(va, uint64_t);
- va_end(va);
-
sbi_ecall(KVM_RISCV_SELFTESTS_SBI_EXT,
KVM_RISCV_SELFTESTS_SBI_UCALL,
- (vm_vaddr_t)&uc, 0, 0, 0, 0, 0);
+ uc, 0, 0, 0, 0, 0);
}
-uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
- struct ucall ucall = {};
-
- if (uc)
- memset(uc, 0, sizeof(*uc));
if (run->exit_reason == KVM_EXIT_RISCV_SBI &&
run->riscv_sbi.extension_id == KVM_RISCV_SELFTESTS_SBI_EXT) {
switch (run->riscv_sbi.function_id) {
case KVM_RISCV_SELFTESTS_SBI_UCALL:
- memcpy(&ucall,
- addr_gva2hva(vcpu->vm, run->riscv_sbi.args[0]),
- sizeof(ucall));
-
- vcpu_run_complete_io(vcpu);
- if (uc)
- memcpy(uc, &ucall, sizeof(ucall));
-
- break;
+ return (void *)run->riscv_sbi.args[0];
case KVM_RISCV_SELFTESTS_SBI_UNEXP:
vcpu_dump(stderr, vcpu, 2);
TEST_ASSERT(0, "Unexpected trap taken by guest");
@@ -93,6 +64,5 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
break;
}
}
-
- return ucall.cmd;
+ return NULL;
}
diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390x/ucall.c
index 73dc4e21190f..a7f02dc372cf 100644
--- a/tools/testing/selftests/kvm/lib/s390x/ucall.c
+++ b/tools/testing/selftests/kvm/lib/s390x/ucall.c
@@ -6,40 +6,19 @@
*/
#include "kvm_util.h"
-void ucall_init(struct kvm_vm *vm, void *arg)
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
{
}
-void ucall_uninit(struct kvm_vm *vm)
+void ucall_arch_do_ucall(vm_vaddr_t uc)
{
-}
-
-void ucall(uint64_t cmd, int nargs, ...)
-{
- struct ucall uc = {
- .cmd = cmd,
- };
- va_list va;
- int i;
-
- nargs = min(nargs, UCALL_MAX_ARGS);
-
- va_start(va, nargs);
- for (i = 0; i < nargs; ++i)
- uc.args[i] = va_arg(va, uint64_t);
- va_end(va);
-
/* Exit via DIAGNOSE 0x501 (normally used for breakpoints) */
- asm volatile ("diag 0,%0,0x501" : : "a"(&uc) : "memory");
+ asm volatile ("diag 0,%0,0x501" : : "a"(uc) : "memory");
}
-uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
- struct ucall ucall = {};
-
- if (uc)
- memset(uc, 0, sizeof(*uc));
if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
run->s390_sieic.icptcode == 4 &&
@@ -47,13 +26,7 @@ uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
(run->s390_sieic.ipb >> 16) == 0x501) {
int reg = run->s390_sieic.ipa & 0xf;
- memcpy(&ucall, addr_gva2hva(vcpu->vm, run->s.regs.gprs[reg]),
- sizeof(ucall));
-
- vcpu_run_complete_io(vcpu);
- if (uc)
- memcpy(uc, &ucall, sizeof(ucall));
+ return (void *)run->s.regs.gprs[reg];
}
-
- return ucall.cmd;
+ return NULL;
}
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 6d23878bbfe1..5c22fa4c2825 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -18,6 +18,23 @@
#include "test_util.h"
/*
+ * Random number generator that is usable from guest code. This is the
+ * Park-Miller LCG using standard constants.
+ */
+
+struct guest_random_state new_guest_random_state(uint32_t seed)
+{
+ struct guest_random_state s = {.seed = seed};
+ return s;
+}
+
+uint32_t guest_random_u32(struct guest_random_state *state)
+{
+ state->seed = (uint64_t)state->seed * 48271 % ((uint32_t)(1 << 31) - 1);
+ return state->seed;
+}
+
+/*
* Parses "[0-9]+[kmgt]?".
*/
size_t parse_size(const char *size)
@@ -334,3 +351,22 @@ long get_run_delay(void)
return val[1];
}
+
+int atoi_paranoid(const char *num_str)
+{
+ char *end_ptr;
+ long num;
+
+ errno = 0;
+ num = strtol(num_str, &end_ptr, 0);
+ TEST_ASSERT(!errno, "strtol(\"%s\") failed", num_str);
+ TEST_ASSERT(num_str != end_ptr,
+ "strtol(\"%s\") didn't find a valid integer.", num_str);
+ TEST_ASSERT(*end_ptr == '\0',
+ "strtol(\"%s\") failed to parse trailing characters \"%s\".",
+ num_str, end_ptr);
+ TEST_ASSERT(num >= INT_MIN && num <= INT_MAX,
+ "%ld not in range of [%d, %d]", num, INT_MIN, INT_MAX);
+
+ return num;
+}
diff --git a/tools/testing/selftests/kvm/lib/ucall_common.c b/tools/testing/selftests/kvm/lib/ucall_common.c
new file mode 100644
index 000000000000..fcae96461e46
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/ucall_common.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include "kvm_util.h"
+#include "linux/types.h"
+#include "linux/bitmap.h"
+#include "linux/atomic.h"
+
+struct ucall_header {
+ DECLARE_BITMAP(in_use, KVM_MAX_VCPUS);
+ struct ucall ucalls[KVM_MAX_VCPUS];
+};
+
+/*
+ * ucall_pool holds per-VM values (global data is duplicated by each VM), it
+ * must not be accessed from host code.
+ */
+static struct ucall_header *ucall_pool;
+
+void ucall_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
+{
+ struct ucall_header *hdr;
+ struct ucall *uc;
+ vm_vaddr_t vaddr;
+ int i;
+
+ vaddr = vm_vaddr_alloc(vm, sizeof(*hdr), KVM_UTIL_MIN_VADDR);
+ hdr = (struct ucall_header *)addr_gva2hva(vm, vaddr);
+ memset(hdr, 0, sizeof(*hdr));
+
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ uc = &hdr->ucalls[i];
+ uc->hva = uc;
+ }
+
+ write_guest_global(vm, ucall_pool, (struct ucall_header *)vaddr);
+
+ ucall_arch_init(vm, mmio_gpa);
+}
+
+static struct ucall *ucall_alloc(void)
+{
+ struct ucall *uc;
+ int i;
+
+ GUEST_ASSERT(ucall_pool);
+
+ for (i = 0; i < KVM_MAX_VCPUS; ++i) {
+ if (!atomic_test_and_set_bit(i, ucall_pool->in_use)) {
+ uc = &ucall_pool->ucalls[i];
+ memset(uc->args, 0, sizeof(uc->args));
+ return uc;
+ }
+ }
+
+ GUEST_ASSERT(0);
+ return NULL;
+}
+
+static void ucall_free(struct ucall *uc)
+{
+ /* Beware, here be pointer arithmetic. */
+ clear_bit(uc - ucall_pool->ucalls, ucall_pool->in_use);
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+ struct ucall *uc;
+ va_list va;
+ int i;
+
+ uc = ucall_alloc();
+
+ WRITE_ONCE(uc->cmd, cmd);
+
+ nargs = min(nargs, UCALL_MAX_ARGS);
+
+ va_start(va, nargs);
+ for (i = 0; i < nargs; ++i)
+ WRITE_ONCE(uc->args[i], va_arg(va, uint64_t));
+ va_end(va);
+
+ ucall_arch_do_ucall((vm_vaddr_t)uc->hva);
+
+ ucall_free(uc);
+}
+
+uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+{
+ struct ucall ucall;
+ void *addr;
+
+ if (!uc)
+ uc = &ucall;
+
+ addr = ucall_arch_get_ucall(vcpu);
+ if (addr) {
+ memcpy(uc, addr, sizeof(*uc));
+ vcpu_run_complete_io(vcpu);
+ } else {
+ memset(uc, 0, sizeof(*uc));
+ }
+
+ return uc->cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
new file mode 100644
index 000000000000..efb7e7a1354d
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86_64/hyperv.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Hyper-V specific functions.
+ *
+ * Copyright (C) 2021, Red Hat Inc.
+ */
+#include <stdint.h>
+#include "processor.h"
+#include "hyperv.h"
+
+struct hyperv_test_pages *vcpu_alloc_hyperv_test_pages(struct kvm_vm *vm,
+ vm_vaddr_t *p_hv_pages_gva)
+{
+ vm_vaddr_t hv_pages_gva = vm_vaddr_alloc_page(vm);
+ struct hyperv_test_pages *hv = addr_gva2hva(vm, hv_pages_gva);
+
+ /* Setup of a region of guest memory for the VP Assist page. */
+ hv->vp_assist = (void *)vm_vaddr_alloc_page(vm);
+ hv->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->vp_assist);
+ hv->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->vp_assist);
+
+ /* Setup of a region of guest memory for the partition assist page. */
+ hv->partition_assist = (void *)vm_vaddr_alloc_page(vm);
+ hv->partition_assist_hva = addr_gva2hva(vm, (uintptr_t)hv->partition_assist);
+ hv->partition_assist_gpa = addr_gva2gpa(vm, (uintptr_t)hv->partition_assist);
+
+ /* Setup of a region of guest memory for the enlightened VMCS. */
+ hv->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm);
+ hv->enlightened_vmcs_hva = addr_gva2hva(vm, (uintptr_t)hv->enlightened_vmcs);
+ hv->enlightened_vmcs_gpa = addr_gva2gpa(vm, (uintptr_t)hv->enlightened_vmcs);
+
+ *p_hv_pages_gva = hv_pages_gva;
+ return hv;
+}
+
+int enable_vp_assist(uint64_t vp_assist_pa, void *vp_assist)
+{
+ uint64_t val = (vp_assist_pa & HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_MASK) |
+ HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
+
+ wrmsr(HV_X64_MSR_VP_ASSIST_PAGE, val);
+
+ current_vp_assist = vp_assist;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c b/tools/testing/selftests/kvm/lib/x86_64/memstress.c
index 0f344a7c89c4..d61e623afc8c 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/perf_test_util.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/memstress.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * x86_64-specific extensions to perf_test_util.c.
+ * x86_64-specific extensions to memstress.c.
*
* Copyright (C) 2022, Google, Inc.
*/
@@ -11,25 +11,25 @@
#include "test_util.h"
#include "kvm_util.h"
-#include "perf_test_util.h"
+#include "memstress.h"
#include "processor.h"
#include "vmx.h"
-void perf_test_l2_guest_code(uint64_t vcpu_id)
+void memstress_l2_guest_code(uint64_t vcpu_id)
{
- perf_test_guest_code(vcpu_id);
+ memstress_guest_code(vcpu_id);
vmcall();
}
-extern char perf_test_l2_guest_entry[];
+extern char memstress_l2_guest_entry[];
__asm__(
-"perf_test_l2_guest_entry:"
+"memstress_l2_guest_entry:"
" mov (%rsp), %rdi;"
-" call perf_test_l2_guest_code;"
+" call memstress_l2_guest_code;"
" ud2;"
);
-static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
+static void memstress_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
{
#define L2_GUEST_STACK_SIZE 64
unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
@@ -42,14 +42,14 @@ static void perf_test_l1_guest_code(struct vmx_pages *vmx, uint64_t vcpu_id)
rsp = &l2_guest_stack[L2_GUEST_STACK_SIZE - 1];
*rsp = vcpu_id;
- prepare_vmcs(vmx, perf_test_l2_guest_entry, rsp);
+ prepare_vmcs(vmx, memstress_l2_guest_entry, rsp);
GUEST_ASSERT(!vmlaunch());
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
GUEST_DONE();
}
-uint64_t perf_test_nested_pages(int nr_vcpus)
+uint64_t memstress_nested_pages(int nr_vcpus)
{
/*
* 513 page tables is enough to identity-map 256 TiB of L2 with 1G
@@ -59,7 +59,7 @@ uint64_t perf_test_nested_pages(int nr_vcpus)
return 513 + 10 * nr_vcpus;
}
-void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
+void memstress_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
{
uint64_t start, end;
@@ -72,12 +72,12 @@ void perf_test_setup_ept(struct vmx_pages *vmx, struct kvm_vm *vm)
*/
nested_identity_map_1g(vmx, vm, 0, 0x100000000ULL);
- start = align_down(perf_test_args.gpa, PG_SIZE_1G);
- end = align_up(perf_test_args.gpa + perf_test_args.size, PG_SIZE_1G);
+ start = align_down(memstress_args.gpa, PG_SIZE_1G);
+ end = align_up(memstress_args.gpa + memstress_args.size, PG_SIZE_1G);
nested_identity_map_1g(vmx, vm, start, end - start);
}
-void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[])
+void memstress_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vcpus[])
{
struct vmx_pages *vmx, *vmx0 = NULL;
struct kvm_regs regs;
@@ -85,12 +85,13 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc
int vcpu_id;
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+ TEST_REQUIRE(kvm_cpu_has_ept());
for (vcpu_id = 0; vcpu_id < nr_vcpus; vcpu_id++) {
vmx = vcpu_alloc_vmx(vm, &vmx_gva);
if (vcpu_id == 0) {
- perf_test_setup_ept(vmx, vm);
+ memstress_setup_ept(vmx, vm);
vmx0 = vmx;
} else {
/* Share the same EPT table across all vCPUs. */
@@ -100,11 +101,11 @@ void perf_test_setup_nested(struct kvm_vm *vm, int nr_vcpus, struct kvm_vcpu *vc
}
/*
- * Override the vCPU to run perf_test_l1_guest_code() which will
- * bounce it into L2 before calling perf_test_guest_code().
+ * Override the vCPU to run memstress_l1_guest_code() which will
+ * bounce it into L2 before calling memstress_guest_code().
*/
vcpu_regs_get(vcpus[vcpu_id], &regs);
- regs.rip = (unsigned long) perf_test_l1_guest_code;
+ regs.rip = (unsigned long) memstress_l1_guest_code;
vcpu_regs_set(vcpus[vcpu_id], &regs);
vcpu_args_set(vcpus[vcpu_id], 2, vmx_gva, vcpu_id);
}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 39c4409ef56a..d532c20c74fd 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -131,23 +131,28 @@ void virt_arch_pgd_alloc(struct kvm_vm *vm)
}
}
-static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
- int level)
+static void *virt_get_pte(struct kvm_vm *vm, uint64_t *parent_pte,
+ uint64_t vaddr, int level)
{
- uint64_t *page_table = addr_gpa2hva(vm, pt_pfn << vm->page_shift);
+ uint64_t pt_gpa = PTE_GET_PA(*parent_pte);
+ uint64_t *page_table = addr_gpa2hva(vm, pt_gpa);
int index = (vaddr >> PG_LEVEL_SHIFT(level)) & 0x1ffu;
+ TEST_ASSERT((*parent_pte & PTE_PRESENT_MASK) || parent_pte == &vm->pgd,
+ "Parent PTE (level %d) not PRESENT for gva: 0x%08lx",
+ level + 1, vaddr);
+
return &page_table[index];
}
static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
- uint64_t pt_pfn,
+ uint64_t *parent_pte,
uint64_t vaddr,
uint64_t paddr,
int current_level,
int target_level)
{
- uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, current_level);
+ uint64_t *pte = virt_get_pte(vm, parent_pte, vaddr, current_level);
if (!(*pte & PTE_PRESENT_MASK)) {
*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
@@ -197,21 +202,20 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr, int level)
* Allocate upper level page tables, if not already present. Return
* early if a hugepage was created.
*/
- pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
- vaddr, paddr, PG_LEVEL_512G, level);
+ pml4e = virt_create_upper_pte(vm, &vm->pgd, vaddr, paddr, PG_LEVEL_512G, level);
if (*pml4e & PTE_LARGE_MASK)
return;
- pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, PG_LEVEL_1G, level);
+ pdpe = virt_create_upper_pte(vm, pml4e, vaddr, paddr, PG_LEVEL_1G, level);
if (*pdpe & PTE_LARGE_MASK)
return;
- pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, PG_LEVEL_2M, level);
+ pde = virt_create_upper_pte(vm, pdpe, vaddr, paddr, PG_LEVEL_2M, level);
if (*pde & PTE_LARGE_MASK)
return;
/* Fill in page table entry. */
- pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, PG_LEVEL_4K);
+ pte = virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
"PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
*pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
@@ -241,30 +245,25 @@ void virt_map_level(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
}
}
-static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm,
- struct kvm_vcpu *vcpu,
- uint64_t vaddr)
+static bool vm_is_target_pte(uint64_t *pte, int *level, int current_level)
{
- uint16_t index[4];
- uint64_t *pml4e, *pdpe, *pde;
- uint64_t *pte;
- struct kvm_sregs sregs;
- uint64_t rsvd_mask = 0;
+ if (*pte & PTE_LARGE_MASK) {
+ TEST_ASSERT(*level == PG_LEVEL_NONE ||
+ *level == current_level,
+ "Unexpected hugepage at level %d\n", current_level);
+ *level = current_level;
+ }
- /* Set the high bits in the reserved mask. */
- if (vm->pa_bits < 52)
- rsvd_mask = GENMASK_ULL(51, vm->pa_bits);
+ return *level == current_level;
+}
- /*
- * SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries
- * with 4-Level Paging and 5-Level Paging".
- * If IA32_EFER.NXE = 0 and the P flag of a paging-structure entry is 1,
- * the XD flag (bit 63) is reserved.
- */
- vcpu_sregs_get(vcpu, &sregs);
- if ((sregs.efer & EFER_NX) == 0) {
- rsvd_mask |= PTE_NX_MASK;
- }
+uint64_t *__vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr,
+ int *level)
+{
+ uint64_t *pml4e, *pdpe, *pde;
+
+ TEST_ASSERT(*level >= PG_LEVEL_NONE && *level < PG_LEVEL_NUM,
+ "Invalid PG_LEVEL_* '%d'", *level);
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -279,54 +278,26 @@ static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm,
TEST_ASSERT(vaddr == (((int64_t)vaddr << 16) >> 16),
"Canonical check failed. The virtual address is invalid.");
- index[0] = (vaddr >> 12) & 0x1ffu;
- index[1] = (vaddr >> 21) & 0x1ffu;
- index[2] = (vaddr >> 30) & 0x1ffu;
- index[3] = (vaddr >> 39) & 0x1ffu;
+ pml4e = virt_get_pte(vm, &vm->pgd, vaddr, PG_LEVEL_512G);
+ if (vm_is_target_pte(pml4e, level, PG_LEVEL_512G))
+ return pml4e;
- pml4e = addr_gpa2hva(vm, vm->pgd);
- TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK,
- "Expected pml4e to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0,
- "Unexpected reserved bits set.");
+ pdpe = virt_get_pte(vm, pml4e, vaddr, PG_LEVEL_1G);
+ if (vm_is_target_pte(pdpe, level, PG_LEVEL_1G))
+ return pdpe;
- pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
- TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK,
- "Expected pdpe to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK),
- "Expected pdpe to map a pde not a 1-GByte page.");
- TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0,
- "Unexpected reserved bits set.");
+ pde = virt_get_pte(vm, pdpe, vaddr, PG_LEVEL_2M);
+ if (vm_is_target_pte(pde, level, PG_LEVEL_2M))
+ return pde;
- pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
- TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK,
- "Expected pde to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK),
- "Expected pde to map a pte not a 2-MByte page.");
- TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0,
- "Unexpected reserved bits set.");
-
- pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
- TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK,
- "Expected pte to be present for gva: 0x%08lx", vaddr);
-
- return &pte[index[0]];
+ return virt_get_pte(vm, pde, vaddr, PG_LEVEL_4K);
}
-uint64_t vm_get_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
- uint64_t vaddr)
+uint64_t *vm_get_page_table_entry(struct kvm_vm *vm, uint64_t vaddr)
{
- uint64_t *pte = _vm_get_page_table_entry(vm, vcpu, vaddr);
+ int level = PG_LEVEL_4K;
- return *(uint64_t *)pte;
-}
-
-void vm_set_page_table_entry(struct kvm_vm *vm, struct kvm_vcpu *vcpu,
- uint64_t vaddr, uint64_t pte)
-{
- uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpu, vaddr);
-
- *(uint64_t *)new_pte = pte;
+ return __vm_get_page_table_entry(vm, vaddr, &level);
}
void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
@@ -512,41 +483,17 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
- uint16_t index[4];
- uint64_t *pml4e, *pdpe, *pde;
- uint64_t *pte;
-
- TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
- "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
-
- index[0] = (gva >> 12) & 0x1ffu;
- index[1] = (gva >> 21) & 0x1ffu;
- index[2] = (gva >> 30) & 0x1ffu;
- index[3] = (gva >> 39) & 0x1ffu;
+ int level = PG_LEVEL_NONE;
+ uint64_t *pte = __vm_get_page_table_entry(vm, gva, &level);
- if (!vm->pgd_created)
- goto unmapped_gva;
- pml4e = addr_gpa2hva(vm, vm->pgd);
- if (!(pml4e[index[3]] & PTE_PRESENT_MASK))
- goto unmapped_gva;
+ TEST_ASSERT(*pte & PTE_PRESENT_MASK,
+ "Leaf PTE not PRESENT for gva: 0x%08lx", gva);
- pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
- if (!(pdpe[index[2]] & PTE_PRESENT_MASK))
- goto unmapped_gva;
-
- pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
- if (!(pde[index[1]] & PTE_PRESENT_MASK))
- goto unmapped_gva;
-
- pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
- if (!(pte[index[0]] & PTE_PRESENT_MASK))
- goto unmapped_gva;
-
- return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK);
-
-unmapped_gva:
- TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
- exit(EXIT_FAILURE);
+ /*
+ * No need for a hugepage mask on the PTE, x86-64 requires the "unused"
+ * address bits to be zero.
+ */
+ return PTE_GET_PA(*pte) | (gva & ~HUGEPAGE_MASK(level));
}
static void kvm_setup_gdt(struct kvm_vm *vm, struct kvm_dtable *dt)
@@ -639,6 +586,11 @@ void __vm_xsave_require_permission(int bit, const char *name)
bitmask);
}
+void kvm_arch_vm_post_create(struct kvm_vm *vm)
+{
+ vm_create_irqchip(vm);
+}
+
struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
void *guest_code)
{
@@ -700,8 +652,9 @@ const struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
return cpuid;
}
-bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid,
- struct kvm_x86_cpu_feature feature)
+static uint32_t __kvm_cpu_has(const struct kvm_cpuid2 *cpuid,
+ uint32_t function, uint32_t index,
+ uint8_t reg, uint8_t lo, uint8_t hi)
{
const struct kvm_cpuid_entry2 *entry;
int i;
@@ -714,12 +667,25 @@ bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid,
* order, but kvm_x86_cpu_feature matches that mess, so yay
* pointer shenanigans!
*/
- if (entry->function == feature.function &&
- entry->index == feature.index)
- return (&entry->eax)[feature.reg] & BIT(feature.bit);
+ if (entry->function == function && entry->index == index)
+ return ((&entry->eax)[reg] & GENMASK(hi, lo)) >> lo;
}
- return false;
+ return 0;
+}
+
+bool kvm_cpuid_has(const struct kvm_cpuid2 *cpuid,
+ struct kvm_x86_cpu_feature feature)
+{
+ return __kvm_cpu_has(cpuid, feature.function, feature.index,
+ feature.reg, feature.bit, feature.bit);
+}
+
+uint32_t kvm_cpuid_property(const struct kvm_cpuid2 *cpuid,
+ struct kvm_x86_cpu_property property)
+{
+ return __kvm_cpu_has(cpuid, property.function, property.index,
+ property.reg, property.lo_bit, property.hi_bit);
}
uint64_t kvm_get_feature_msr(uint64_t msr_index)
@@ -1059,34 +1025,15 @@ bool is_amd_cpu(void)
void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
{
- const struct kvm_cpuid_entry2 *entry;
- bool pae;
-
- /* SDM 4.1.4 */
- if (kvm_get_cpuid_max_extended() < 0x80000008) {
- pae = kvm_get_supported_cpuid_entry(1)->edx & (1 << 6);
- *pa_bits = pae ? 36 : 32;
+ if (!kvm_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR)) {
+ *pa_bits == kvm_cpu_has(X86_FEATURE_PAE) ? 36 : 32;
*va_bits = 32;
} else {
- entry = kvm_get_supported_cpuid_entry(0x80000008);
- *pa_bits = entry->eax & 0xff;
- *va_bits = (entry->eax >> 8) & 0xff;
+ *pa_bits = kvm_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);
+ *va_bits = kvm_cpu_property(X86_PROPERTY_MAX_VIRT_ADDR);
}
}
-struct idt_entry {
- uint16_t offset0;
- uint16_t selector;
- uint16_t ist : 3;
- uint16_t : 5;
- uint16_t type : 4;
- uint16_t : 1;
- uint16_t dpl : 2;
- uint16_t p : 1;
- uint16_t offset1;
- uint32_t offset2; uint32_t reserved;
-};
-
static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
int dpl, unsigned short selector)
{
@@ -1116,6 +1063,7 @@ static bool kvm_fixup_exception(struct ex_regs *regs)
regs->rip = regs->r11;
regs->r9 = regs->vector;
+ regs->r10 = regs->error_code;
return true;
}
@@ -1278,7 +1226,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
{
const unsigned long num_ht_pages = 12 << (30 - vm->page_shift); /* 12 GiB */
unsigned long ht_gfn, max_gfn, max_pfn;
- uint32_t eax, ebx, ecx, edx, max_ext_leaf;
+ uint8_t maxphyaddr;
max_gfn = (1ULL << (vm->pa_bits - vm->page_shift)) - 1;
@@ -1292,8 +1240,7 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
/* Before family 17h, the HyperTransport area is just below 1T. */
ht_gfn = (1 << 28) - num_ht_pages;
- cpuid(1, &eax, &ebx, &ecx, &edx);
- if (x86_family(eax) < 0x17)
+ if (this_cpu_family() < 0x17)
goto done;
/*
@@ -1301,17 +1248,14 @@ unsigned long vm_compute_max_gfn(struct kvm_vm *vm)
* reduced due to SME by bits 11:6 of CPUID[0x8000001f].EBX. Use
* the old conservative value if MAXPHYADDR is not enumerated.
*/
- cpuid(0x80000000, &eax, &ebx, &ecx, &edx);
- max_ext_leaf = eax;
- if (max_ext_leaf < 0x80000008)
+ if (!this_cpu_has_p(X86_PROPERTY_MAX_PHY_ADDR))
goto done;
- cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
- max_pfn = (1ULL << ((eax & 0xff) - vm->page_shift)) - 1;
- if (max_ext_leaf >= 0x8000001f) {
- cpuid(0x8000001f, &eax, &ebx, &ecx, &edx);
- max_pfn >>= (ebx >> 6) & 0x3f;
- }
+ maxphyaddr = this_cpu_property(X86_PROPERTY_MAX_PHY_ADDR);
+ max_pfn = (1ULL << (maxphyaddr - vm->page_shift)) - 1;
+
+ if (this_cpu_has_p(X86_PROPERTY_PHYS_ADDR_REDUCTION))
+ max_pfn >>= this_cpu_property(X86_PROPERTY_PHYS_ADDR_REDUCTION);
ht_gfn = max_pfn - num_ht_pages;
done:
diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
index e5f0f9e0d3ee..4d41dc63cc9e 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/ucall.c
@@ -8,52 +8,25 @@
#define UCALL_PIO_PORT ((uint16_t)0x1000)
-void ucall_init(struct kvm_vm *vm, void *arg)
+void ucall_arch_init(struct kvm_vm *vm, vm_paddr_t mmio_gpa)
{
}
-void ucall_uninit(struct kvm_vm *vm)
+void ucall_arch_do_ucall(vm_vaddr_t uc)
{
-}
-
-void ucall(uint64_t cmd, int nargs, ...)
-{
- struct ucall uc = {
- .cmd = cmd,
- };
- va_list va;
- int i;
-
- nargs = min(nargs, UCALL_MAX_ARGS);
-
- va_start(va, nargs);
- for (i = 0; i < nargs; ++i)
- uc.args[i] = va_arg(va, uint64_t);
- va_end(va);
-
asm volatile("in %[port], %%al"
- : : [port] "d" (UCALL_PIO_PORT), "D" (&uc) : "rax", "memory");
+ : : [port] "d" (UCALL_PIO_PORT), "D" (uc) : "rax", "memory");
}
-uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+void *ucall_arch_get_ucall(struct kvm_vcpu *vcpu)
{
struct kvm_run *run = vcpu->run;
- struct ucall ucall = {};
-
- if (uc)
- memset(uc, 0, sizeof(*uc));
if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
struct kvm_regs regs;
vcpu_regs_get(vcpu, &regs);
- memcpy(&ucall, addr_gva2hva(vcpu->vm, (vm_vaddr_t)regs.rdi),
- sizeof(ucall));
-
- vcpu_run_complete_io(vcpu);
- if (uc)
- memcpy(uc, &ucall, sizeof(ucall));
+ return (void *)regs.rdi;
}
-
- return ucall.cmd;
+ return NULL;
}
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index d21049c38fc5..59d97531c9b1 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -109,18 +109,6 @@ vcpu_alloc_vmx(struct kvm_vm *vm, vm_vaddr_t *p_vmx_gva)
vmx->vmwrite_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vmwrite);
memset(vmx->vmwrite_hva, 0, getpagesize());
- /* Setup of a region of guest memory for the VP Assist page. */
- vmx->vp_assist = (void *)vm_vaddr_alloc_page(vm);
- vmx->vp_assist_hva = addr_gva2hva(vm, (uintptr_t)vmx->vp_assist);
- vmx->vp_assist_gpa = addr_gva2gpa(vm, (uintptr_t)vmx->vp_assist);
-
- /* Setup of a region of guest memory for the enlightened VMCS. */
- vmx->enlightened_vmcs = (void *)vm_vaddr_alloc_page(vm);
- vmx->enlightened_vmcs_hva =
- addr_gva2hva(vm, (uintptr_t)vmx->enlightened_vmcs);
- vmx->enlightened_vmcs_gpa =
- addr_gva2gpa(vm, (uintptr_t)vmx->enlightened_vmcs);
-
*p_vmx_gva = vmx_gva;
return vmx;
}
@@ -171,26 +159,18 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx)
bool load_vmcs(struct vmx_pages *vmx)
{
- if (!enable_evmcs) {
- /* Load a VMCS. */
- *(uint32_t *)(vmx->vmcs) = vmcs_revision();
- if (vmclear(vmx->vmcs_gpa))
- return false;
-
- if (vmptrld(vmx->vmcs_gpa))
- return false;
-
- /* Setup shadow VMCS, do not load it yet. */
- *(uint32_t *)(vmx->shadow_vmcs) =
- vmcs_revision() | 0x80000000ul;
- if (vmclear(vmx->shadow_vmcs_gpa))
- return false;
- } else {
- if (evmcs_vmptrld(vmx->enlightened_vmcs_gpa,
- vmx->enlightened_vmcs))
- return false;
- current_evmcs->revision_id = EVMCS_VERSION;
- }
+ /* Load a VMCS. */
+ *(uint32_t *)(vmx->vmcs) = vmcs_revision();
+ if (vmclear(vmx->vmcs_gpa))
+ return false;
+
+ if (vmptrld(vmx->vmcs_gpa))
+ return false;
+
+ /* Setup shadow VMCS, do not load it yet. */
+ *(uint32_t *)(vmx->shadow_vmcs) = vmcs_revision() | 0x80000000ul;
+ if (vmclear(vmx->shadow_vmcs_gpa))
+ return false;
return true;
}
@@ -544,26 +524,22 @@ void nested_identity_map_1g(struct vmx_pages *vmx, struct kvm_vm *vm,
__nested_map(vmx, vm, addr, addr, size, PG_LEVEL_1G);
}
-bool kvm_vm_has_ept(struct kvm_vm *vm)
+bool kvm_cpu_has_ept(void)
{
- struct kvm_vcpu *vcpu;
uint64_t ctrl;
- vcpu = list_first_entry(&vm->vcpus, struct kvm_vcpu, list);
- TEST_ASSERT(vcpu, "Cannot determine EPT support without vCPUs.\n");
-
- ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32;
+ ctrl = kvm_get_feature_msr(MSR_IA32_VMX_TRUE_PROCBASED_CTLS) >> 32;
if (!(ctrl & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
return false;
- ctrl = vcpu_get_msr(vcpu, MSR_IA32_VMX_PROCBASED_CTLS2) >> 32;
+ ctrl = kvm_get_feature_msr(MSR_IA32_VMX_PROCBASED_CTLS2) >> 32;
return ctrl & SECONDARY_EXEC_ENABLE_EPT;
}
void prepare_eptp(struct vmx_pages *vmx, struct kvm_vm *vm,
uint32_t eptp_memslot)
{
- TEST_REQUIRE(kvm_vm_has_ept(vm));
+ TEST_ASSERT(kvm_cpu_has_ept(), "KVM doesn't support nested EPT");
vmx->eptp = (void *)vm_vaddr_alloc_page(vm);
vmx->eptp_hva = addr_gva2hva(vm, (uintptr_t)vmx->eptp);
diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/max_guest_memory_test.c
index 9a6e4f3ad6b5..feaf2be20ff2 100644
--- a/tools/testing/selftests/kvm/max_guest_memory_test.c
+++ b/tools/testing/selftests/kvm/max_guest_memory_test.c
@@ -11,6 +11,7 @@
#include <linux/bitmap.h>
#include <linux/bitops.h>
#include <linux/atomic.h>
+#include <linux/sizes.h>
#include "kvm_util.h"
#include "test_util.h"
@@ -162,8 +163,7 @@ int main(int argc, char *argv[])
* just below the 4gb boundary. This test could create memory at
* 1gb-3gb,but it's simpler to skip straight to 4gb.
*/
- const uint64_t size_1gb = (1 << 30);
- const uint64_t start_gpa = (4ull * size_1gb);
+ const uint64_t start_gpa = SZ_4G;
const int first_slot = 1;
struct timespec time_start, time_run1, time_reset, time_run2;
@@ -180,29 +180,26 @@ int main(int argc, char *argv[])
* are quite common for x86, requires changing only max_mem (KVM allows
* 32k memslots, 32k * 2gb == ~64tb of guest memory).
*/
- slot_size = 2 * size_1gb;
+ slot_size = SZ_2G;
max_slots = kvm_check_cap(KVM_CAP_NR_MEMSLOTS);
TEST_ASSERT(max_slots > first_slot, "KVM is broken");
/* All KVM MMUs should be able to survive a 128gb guest. */
- max_mem = 128 * size_1gb;
+ max_mem = 128ull * SZ_1G;
calc_default_nr_vcpus();
while ((opt = getopt(argc, argv, "c:h:m:s:H")) != -1) {
switch (opt) {
case 'c':
- nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0, "number of vcpus must be >0");
+ nr_vcpus = atoi_positive("Number of vCPUs", optarg);
break;
case 'm':
- max_mem = atoi(optarg) * size_1gb;
- TEST_ASSERT(max_mem > 0, "memory size must be >0");
+ max_mem = 1ull * atoi_positive("Memory size", optarg) * SZ_1G;
break;
case 's':
- slot_size = atoi(optarg) * size_1gb;
- TEST_ASSERT(slot_size > 0, "slot size must be >0");
+ slot_size = 1ull * atoi_positive("Slot size", optarg) * SZ_1G;
break;
case 'H':
hugepages = true;
@@ -245,7 +242,7 @@ int main(int argc, char *argv[])
#ifdef __x86_64__
/* Identity map memory in the guest using 1gb pages. */
- for (i = 0; i < slot_size; i += size_1gb)
+ for (i = 0; i < slot_size; i += SZ_1G)
__virt_pg_map(vm, gpa + i, gpa + i, PG_LEVEL_1G);
#else
for (i = 0; i < slot_size; i += vm->page_size)
@@ -260,7 +257,7 @@ int main(int argc, char *argv[])
vcpus = NULL;
pr_info("Running with %lugb of guest memory and %u vCPUs\n",
- (gpa - start_gpa) / size_1gb, nr_vcpus);
+ (gpa - start_gpa) / SZ_1G, nr_vcpus);
rendezvous_with_vcpus(&time_start, "spawning");
rendezvous_with_vcpus(&time_run1, "run 1");
diff --git a/tools/testing/selftests/kvm/memslot_modification_stress_test.c b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
index bb1d17a1171b..d07e921bfcc5 100644
--- a/tools/testing/selftests/kvm/memslot_modification_stress_test.c
+++ b/tools/testing/selftests/kvm/memslot_modification_stress_test.c
@@ -21,7 +21,7 @@
#include <linux/bitops.h>
#include <linux/userfaultfd.h>
-#include "perf_test_util.h"
+#include "memstress.h"
#include "processor.h"
#include "test_util.h"
#include "guest_modes.h"
@@ -36,7 +36,7 @@ static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
static bool run_vcpus = true;
-static void vcpu_worker(struct perf_test_vcpu_args *vcpu_args)
+static void vcpu_worker(struct memstress_vcpu_args *vcpu_args)
{
struct kvm_vcpu *vcpu = vcpu_args->vcpu;
struct kvm_run *run;
@@ -72,10 +72,10 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
int i;
/*
- * Add the dummy memslot just below the perf_test_util memslot, which is
+ * Add the dummy memslot just below the memstress memslot, which is
* at the top of the guest physical address space.
*/
- gpa = perf_test_args.gpa - pages * vm->page_size;
+ gpa = memstress_args.gpa - pages * vm->page_size;
for (i = 0; i < nr_modifications; i++) {
usleep(delay);
@@ -87,8 +87,8 @@ static void add_remove_memslot(struct kvm_vm *vm, useconds_t delay,
}
struct test_params {
- useconds_t memslot_modification_delay;
- uint64_t nr_memslot_modifications;
+ useconds_t delay;
+ uint64_t nr_iterations;
bool partition_vcpu_memory_access;
};
@@ -97,25 +97,24 @@ static void run_test(enum vm_guest_mode mode, void *arg)
struct test_params *p = arg;
struct kvm_vm *vm;
- vm = perf_test_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
+ vm = memstress_create_vm(mode, nr_vcpus, guest_percpu_mem_size, 1,
VM_MEM_SRC_ANONYMOUS,
p->partition_vcpu_memory_access);
pr_info("Finished creating vCPUs\n");
- perf_test_start_vcpu_threads(nr_vcpus, vcpu_worker);
+ memstress_start_vcpu_threads(nr_vcpus, vcpu_worker);
pr_info("Started all vCPUs\n");
- add_remove_memslot(vm, p->memslot_modification_delay,
- p->nr_memslot_modifications);
+ add_remove_memslot(vm, p->delay, p->nr_iterations);
run_vcpus = false;
- perf_test_join_vcpu_threads(nr_vcpus);
+ memstress_join_vcpu_threads(nr_vcpus);
pr_info("All vCPU threads joined\n");
- perf_test_destroy_vm(vm);
+ memstress_destroy_vm(vm);
}
static void help(char *name)
@@ -144,9 +143,8 @@ int main(int argc, char *argv[])
int max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
int opt;
struct test_params p = {
- .memslot_modification_delay = 0,
- .nr_memslot_modifications =
- DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS,
+ .delay = 0,
+ .nr_iterations = DEFAULT_MEMSLOT_MODIFICATION_ITERATIONS,
.partition_vcpu_memory_access = true
};
@@ -158,16 +156,14 @@ int main(int argc, char *argv[])
guest_modes_cmdline(optarg);
break;
case 'd':
- p.memslot_modification_delay = strtoul(optarg, NULL, 0);
- TEST_ASSERT(p.memslot_modification_delay >= 0,
- "A negative delay is not supported.");
+ p.delay = atoi_non_negative("Delay", optarg);
break;
case 'b':
guest_percpu_mem_size = parse_size(optarg);
break;
case 'v':
- nr_vcpus = atoi(optarg);
- TEST_ASSERT(nr_vcpus > 0 && nr_vcpus <= max_vcpus,
+ nr_vcpus = atoi_positive("Number of vCPUs", optarg);
+ TEST_ASSERT(nr_vcpus <= max_vcpus,
"Invalid number of vcpus, must be between 1 and %d",
max_vcpus);
break;
@@ -175,7 +171,7 @@ int main(int argc, char *argv[])
p.partition_vcpu_memory_access = false;
break;
case 'i':
- p.nr_memslot_modifications = atoi(optarg);
+ p.nr_iterations = atoi_positive("Number of iterations", optarg);
break;
case 'h':
default:
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 44995446d942..36b20abfb948 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -277,7 +277,6 @@ static bool prepare_vm(struct vm_data *data, int nslots, uint64_t *maxslots,
TEST_ASSERT(data->hva_slots, "malloc() fail");
data->vm = __vm_create_with_one_vcpu(&data->vcpu, mempages, guest_code);
- ucall_init(data->vm, NULL);
pr_info_v("Adding slots 1..%i, each slot with %"PRIu64" pages + %"PRIu64" extra pages last\n",
max_mem_slots - 1, data->pages_per_slot, rempages);
@@ -885,40 +884,28 @@ static bool parse_args(int argc, char *argv[],
map_unmap_verify = true;
break;
case 's':
- targs->nslots = atoi(optarg);
+ targs->nslots = atoi_paranoid(optarg);
if (targs->nslots <= 0 && targs->nslots != -1) {
pr_info("Slot count cap has to be positive or -1 for no cap\n");
return false;
}
break;
case 'f':
- targs->tfirst = atoi(optarg);
- if (targs->tfirst < 0) {
- pr_info("First test to run has to be non-negative\n");
- return false;
- }
+ targs->tfirst = atoi_non_negative("First test", optarg);
break;
case 'e':
- targs->tlast = atoi(optarg);
- if (targs->tlast < 0 || targs->tlast >= NTESTS) {
+ targs->tlast = atoi_non_negative("Last test", optarg);
+ if (targs->tlast >= NTESTS) {
pr_info("Last test to run has to be non-negative and less than %zu\n",
NTESTS);
return false;
}
break;
case 'l':
- targs->seconds = atoi(optarg);
- if (targs->seconds < 0) {
- pr_info("Test length in seconds has to be non-negative\n");
- return false;
- }
+ targs->seconds = atoi_non_negative("Test length", optarg);
break;
case 'r':
- targs->runs = atoi(optarg);
- if (targs->runs <= 0) {
- pr_info("Runs per test has to be positive\n");
- return false;
- }
+ targs->runs = atoi_positive("Runs per test", optarg);
break;
}
}
@@ -1007,9 +994,6 @@ int main(int argc, char *argv[])
struct test_result rbestslottime;
int tctr;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
if (!parse_args(argc, argv, &targs))
return -1;
diff --git a/tools/testing/selftests/kvm/rseq_test.c b/tools/testing/selftests/kvm/rseq_test.c
index 6f88da7e60be..3045fdf9bdf5 100644
--- a/tools/testing/selftests/kvm/rseq_test.c
+++ b/tools/testing/selftests/kvm/rseq_test.c
@@ -205,9 +205,6 @@ int main(int argc, char *argv[])
struct kvm_vcpu *vcpu;
u32 cpu, rseq_cpu;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
r = sched_getaffinity(0, sizeof(possible_mask), &possible_mask);
TEST_ASSERT(!r, "sched_getaffinity failed, errno = %d (%s)", errno,
strerror(errno));
@@ -224,7 +221,6 @@ int main(int argc, char *argv[])
* CPU affinity.
*/
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
- ucall_init(vm, NULL);
pthread_create(&migration_thread, NULL, migration_worker,
(void *)(unsigned long)syscall(SYS_gettid));
diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390x/memop.c
index 9113696d5178..3fd81e58f40c 100644
--- a/tools/testing/selftests/kvm/s390x/memop.c
+++ b/tools/testing/selftests/kvm/s390x/memop.c
@@ -760,8 +760,6 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_has_cap(KVM_CAP_S390_MEM_OP));
- setbuf(stdout, NULL); /* Tell stdout not to buffer its content */
-
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(testlist));
diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390x/resets.c
index 19486084eb30..e41e2cb8ffa9 100644
--- a/tools/testing/selftests/kvm/s390x/resets.c
+++ b/tools/testing/selftests/kvm/s390x/resets.c
@@ -296,8 +296,6 @@ int main(int argc, char *argv[])
bool has_s390_vcpu_resets = kvm_check_cap(KVM_CAP_S390_VCPU_RESETS);
int idx;
- setbuf(stdout, NULL); /* Tell stdout not to buffer its content */
-
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(testlist));
diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
index 3fdb6e2598eb..2ddde41c44ba 100644
--- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/s390x/sync_regs_test.c
@@ -231,9 +231,6 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_has_cap(KVM_CAP_SYNC_REGS));
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
ksft_print_header();
ksft_set_plan(ARRAY_SIZE(testlist));
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 0d55f508d595..2ef1d1b72ce4 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -392,9 +392,6 @@ int main(int argc, char *argv[])
int i, loops;
#endif
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
#ifdef __x86_64__
/*
* FIXME: the zero-memslot test fails on aarch64 and s390x because
@@ -407,7 +404,7 @@ int main(int argc, char *argv[])
#ifdef __x86_64__
if (argc > 1)
- loops = atoi(argv[1]);
+ loops = atoi_positive("Number of iterations", argv[1]);
else
loops = 10;
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index db8967f1a17b..c87f38712073 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -266,7 +266,6 @@ int main(int ac, char **av)
gpages = vm_calc_num_guest_pages(VM_MODE_DEFAULT, STEAL_TIME_SIZE * NR_VCPUS);
vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS, ST_GPA_BASE, 1, gpages, 0);
virt_map(vm, ST_GPA_BASE, ST_GPA_BASE, gpages);
- ucall_init(vm, NULL);
TEST_REQUIRE(is_steal_time_supported(vcpus[0]));
diff --git a/tools/testing/selftests/kvm/system_counter_offset_test.c b/tools/testing/selftests/kvm/system_counter_offset_test.c
index 1c274933912b..7f5b330b6a1b 100644
--- a/tools/testing/selftests/kvm/system_counter_offset_test.c
+++ b/tools/testing/selftests/kvm/system_counter_offset_test.c
@@ -121,7 +121,6 @@ int main(void)
vm = vm_create_with_one_vcpu(&vcpu, guest_main);
check_preconditions(vcpu);
- ucall_init(vm, NULL);
enter_guest(vcpu);
kvm_vm_free(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index dadcbad10a1d..21de6ae42086 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -39,11 +39,6 @@
#define XFEATURE_MASK_XTILEDATA (1 << XFEATURE_XTILEDATA)
#define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILECFG | XFEATURE_MASK_XTILEDATA)
-#define TILE_CPUID 0x1d
-#define XSTATE_CPUID 0xd
-#define TILE_PALETTE_CPUID_SUBLEAVE 0x1
-#define XSTATE_USER_STATE_SUBLEAVE 0x0
-
#define XSAVE_HDR_OFFSET 512
struct xsave_data {
@@ -129,71 +124,26 @@ static bool check_xsave_supports_xtile(void)
return __xgetbv(0) & XFEATURE_MASK_XTILE;
}
-static bool enum_xtile_config(void)
-{
- u32 eax, ebx, ecx, edx;
-
- __cpuid(TILE_CPUID, TILE_PALETTE_CPUID_SUBLEAVE, &eax, &ebx, &ecx, &edx);
- if (!eax || !ebx || !ecx)
- return false;
-
- xtile.max_names = ebx >> 16;
- if (xtile.max_names < NUM_TILES)
- return false;
-
- xtile.bytes_per_tile = eax >> 16;
- if (xtile.bytes_per_tile < TILE_SIZE)
- return false;
-
- xtile.bytes_per_row = ebx;
- xtile.max_rows = ecx;
-
- return true;
-}
-
-static bool enum_xsave_tile(void)
-{
- u32 eax, ebx, ecx, edx;
-
- __cpuid(XSTATE_CPUID, XFEATURE_XTILEDATA, &eax, &ebx, &ecx, &edx);
- if (!eax || !ebx)
- return false;
-
- xtile.xsave_offset = ebx;
- xtile.xsave_size = eax;
-
- return true;
-}
-
-static bool check_xsave_size(void)
-{
- u32 eax, ebx, ecx, edx;
- bool valid = false;
-
- __cpuid(XSTATE_CPUID, XSTATE_USER_STATE_SUBLEAVE, &eax, &ebx, &ecx, &edx);
- if (ebx && ebx <= XSAVE_SIZE)
- valid = true;
-
- return valid;
-}
-
-static bool check_xtile_info(void)
+static void check_xtile_info(void)
{
- bool ret = false;
-
- if (!check_xsave_size())
- return ret;
-
- if (!enum_xsave_tile())
- return ret;
-
- if (!enum_xtile_config())
- return ret;
+ GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0));
+ GUEST_ASSERT(this_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE_XCR0) <= XSAVE_SIZE);
- if (sizeof(struct tile_data) >= xtile.xsave_size)
- ret = true;
+ xtile.xsave_offset = this_cpu_property(X86_PROPERTY_XSTATE_TILE_OFFSET);
+ GUEST_ASSERT(xtile.xsave_offset == 2816);
+ xtile.xsave_size = this_cpu_property(X86_PROPERTY_XSTATE_TILE_SIZE);
+ GUEST_ASSERT(xtile.xsave_size == 8192);
+ GUEST_ASSERT(sizeof(struct tile_data) >= xtile.xsave_size);
- return ret;
+ GUEST_ASSERT(this_cpu_has_p(X86_PROPERTY_AMX_NR_TILE_REGS));
+ xtile.max_names = this_cpu_property(X86_PROPERTY_AMX_NR_TILE_REGS);
+ GUEST_ASSERT(xtile.max_names == 8);
+ xtile.bytes_per_tile = this_cpu_property(X86_PROPERTY_AMX_BYTES_PER_TILE);
+ GUEST_ASSERT(xtile.bytes_per_tile == 1024);
+ xtile.bytes_per_row = this_cpu_property(X86_PROPERTY_AMX_BYTES_PER_ROW);
+ GUEST_ASSERT(xtile.bytes_per_row == 64);
+ xtile.max_rows = this_cpu_property(X86_PROPERTY_AMX_MAX_ROWS);
+ GUEST_ASSERT(xtile.max_rows == 16);
}
static void set_tilecfg(struct tile_config *cfg)
@@ -238,16 +188,8 @@ static void __attribute__((__flatten__)) guest_code(struct tile_config *amx_cfg,
{
init_regs();
check_cpuid_xsave();
- GUEST_ASSERT(check_xsave_supports_xtile());
- GUEST_ASSERT(check_xtile_info());
-
- /* check xtile configs */
- GUEST_ASSERT(xtile.xsave_offset == 2816);
- GUEST_ASSERT(xtile.xsave_size == 8192);
- GUEST_ASSERT(xtile.max_names == 8);
- GUEST_ASSERT(xtile.bytes_per_tile == 1024);
- GUEST_ASSERT(xtile.bytes_per_row == 64);
- GUEST_ASSERT(xtile.max_rows == 16);
+ check_xsave_supports_xtile();
+ check_xtile_info();
GUEST_SYNC(1);
/* xfd=0, enable amx */
@@ -317,8 +259,9 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILECFG));
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XTILEDATA));
- /* Get xsave/restore max size */
- xsave_restore_size = kvm_get_supported_cpuid_entry(0xd)->ecx;
+ TEST_ASSERT(kvm_cpu_has_p(X86_PROPERTY_XSTATE_MAX_SIZE),
+ "KVM should enumerate max XSAVE size when XSAVE is supported");
+ xsave_restore_size = kvm_cpu_property(X86_PROPERTY_XSTATE_MAX_SIZE);
run = vcpu->run;
vcpu_regs_get(vcpu, &regs1);
diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
index a6aeee2e62e4..2fc3ad9c887e 100644
--- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cpuid_test.c
@@ -43,15 +43,6 @@ static void test_guest_cpuids(struct kvm_cpuid2 *guest_cpuid)
}
-static void test_cpuid_40000000(struct kvm_cpuid2 *guest_cpuid)
-{
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x40000000, &eax, &ebx, &ecx, &edx);
-
- GUEST_ASSERT(eax == 0x40000001);
-}
-
static void guest_main(struct kvm_cpuid2 *guest_cpuid)
{
GUEST_SYNC(1);
@@ -60,7 +51,7 @@ static void guest_main(struct kvm_cpuid2 *guest_cpuid)
GUEST_SYNC(2);
- test_cpuid_40000000(guest_cpuid);
+ GUEST_ASSERT(this_cpu_property(X86_PROPERTY_MAX_KVM_LEAF) == 0x40000001);
GUEST_DONE();
}
diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
index 4208487652f8..1027a671c7d3 100644
--- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
+++ b/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c
@@ -57,9 +57,6 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_XSAVE));
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
deleted file mode 100644
index 236e11755ba6..000000000000
--- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
+++ /dev/null
@@ -1,193 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2020, Google LLC.
- *
- * Tests for KVM_CAP_EXIT_ON_EMULATION_FAILURE capability.
- */
-
-#define _GNU_SOURCE /* for program_invocation_short_name */
-
-#include "test_util.h"
-#include "kvm_util.h"
-#include "vmx.h"
-
-#define MAXPHYADDR 36
-
-#define MEM_REGION_GVA 0x0000123456789000
-#define MEM_REGION_GPA 0x0000000700000000
-#define MEM_REGION_SLOT 10
-#define MEM_REGION_SIZE PAGE_SIZE
-
-static void guest_code(void)
-{
- __asm__ __volatile__("flds (%[addr])"
- :: [addr]"r"(MEM_REGION_GVA));
-
- GUEST_DONE();
-}
-
-/*
- * Accessors to get R/M, REG, and Mod bits described in the SDM vol 2,
- * figure 2-2 "Table Interpretation of ModR/M Byte (C8H)".
- */
-#define GET_RM(insn_byte) (insn_byte & 0x7)
-#define GET_REG(insn_byte) ((insn_byte & 0x38) >> 3)
-#define GET_MOD(insn_byte) ((insn_byte & 0xc) >> 6)
-
-/* Ensure we are dealing with a simple 2-byte flds instruction. */
-static bool is_flds(uint8_t *insn_bytes, uint8_t insn_size)
-{
- return insn_size >= 2 &&
- insn_bytes[0] == 0xd9 &&
- GET_REG(insn_bytes[1]) == 0x0 &&
- GET_MOD(insn_bytes[1]) == 0x0 &&
- /* Ensure there is no SIB byte. */
- GET_RM(insn_bytes[1]) != 0x4 &&
- /* Ensure there is no displacement byte. */
- GET_RM(insn_bytes[1]) != 0x5;
-}
-
-static void process_exit_on_emulation_error(struct kvm_vcpu *vcpu)
-{
- struct kvm_run *run = vcpu->run;
- struct kvm_regs regs;
- uint8_t *insn_bytes;
- uint8_t insn_size;
- uint64_t flags;
-
- TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
- "Unexpected exit reason: %u (%s)",
- run->exit_reason,
- exit_reason_str(run->exit_reason));
-
- TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
- "Unexpected suberror: %u",
- run->emulation_failure.suberror);
-
- if (run->emulation_failure.ndata >= 1) {
- flags = run->emulation_failure.flags;
- if ((flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES) &&
- run->emulation_failure.ndata >= 3) {
- insn_size = run->emulation_failure.insn_size;
- insn_bytes = run->emulation_failure.insn_bytes;
-
- TEST_ASSERT(insn_size <= 15 && insn_size > 0,
- "Unexpected instruction size: %u",
- insn_size);
-
- TEST_ASSERT(is_flds(insn_bytes, insn_size),
- "Unexpected instruction. Expected 'flds' (0xd9 /0)");
-
- /*
- * If is_flds() succeeded then the instruction bytes
- * contained an flds instruction that is 2-bytes in
- * length (ie: no prefix, no SIB, no displacement).
- */
- vcpu_regs_get(vcpu, &regs);
- regs.rip += 2;
- vcpu_regs_set(vcpu, &regs);
- }
- }
-}
-
-static void do_guest_assert(struct ucall *uc)
-{
- REPORT_GUEST_ASSERT(*uc);
-}
-
-static void check_for_guest_assert(struct kvm_vcpu *vcpu)
-{
- struct ucall uc;
-
- if (vcpu->run->exit_reason == KVM_EXIT_IO &&
- get_ucall(vcpu, &uc) == UCALL_ABORT) {
- do_guest_assert(&uc);
- }
-}
-
-static void process_ucall_done(struct kvm_vcpu *vcpu)
-{
- struct kvm_run *run = vcpu->run;
- struct ucall uc;
-
- check_for_guest_assert(vcpu);
-
- TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Unexpected exit reason: %u (%s)",
- run->exit_reason,
- exit_reason_str(run->exit_reason));
-
- TEST_ASSERT(get_ucall(vcpu, &uc) == UCALL_DONE,
- "Unexpected ucall command: %lu, expected UCALL_DONE (%d)",
- uc.cmd, UCALL_DONE);
-}
-
-static uint64_t process_ucall(struct kvm_vcpu *vcpu)
-{
- struct kvm_run *run = vcpu->run;
- struct ucall uc;
-
- TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
- "Unexpected exit reason: %u (%s)",
- run->exit_reason,
- exit_reason_str(run->exit_reason));
-
- switch (get_ucall(vcpu, &uc)) {
- case UCALL_SYNC:
- break;
- case UCALL_ABORT:
- do_guest_assert(&uc);
- break;
- case UCALL_DONE:
- process_ucall_done(vcpu);
- break;
- default:
- TEST_ASSERT(false, "Unexpected ucall");
- }
-
- return uc.cmd;
-}
-
-int main(int argc, char *argv[])
-{
- struct kvm_vcpu *vcpu;
- struct kvm_vm *vm;
- uint64_t gpa, pte;
- uint64_t *hva;
- int rc;
-
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
- TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR));
-
- vm = vm_create_with_one_vcpu(&vcpu, guest_code);
-
- vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR);
-
- rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
- TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
- vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1);
-
- vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
- MEM_REGION_GPA, MEM_REGION_SLOT,
- MEM_REGION_SIZE / PAGE_SIZE, 0);
- gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
- MEM_REGION_GPA, MEM_REGION_SLOT);
- TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
- virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
- hva = addr_gpa2hva(vm, MEM_REGION_GPA);
- memset(hva, 0, PAGE_SIZE);
- pte = vm_get_page_table_entry(vm, vcpu, MEM_REGION_GVA);
- vm_set_page_table_entry(vm, vcpu, MEM_REGION_GVA, pte | (1ull << 36));
-
- vcpu_run(vcpu);
- process_exit_on_emulation_error(vcpu);
- vcpu_run(vcpu);
-
- TEST_ASSERT(process_ucall(vcpu) == UCALL_DONE, "Expected UCALL_DONE");
-
- kvm_vm_free(vm);
-
- return 0;
-}
diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
new file mode 100644
index 000000000000..37c61f712fd5
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022, Google LLC.
+ *
+ * Test for KVM_CAP_EXIT_ON_EMULATION_FAILURE.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+
+#include "flds_emulation.h"
+
+#include "test_util.h"
+
+#define MMIO_GPA 0x700000000
+#define MMIO_GVA MMIO_GPA
+
+static void guest_code(void)
+{
+ /* Execute flds with an MMIO address to force KVM to emulate it. */
+ flds(MMIO_GVA);
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE));
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1);
+ virt_map(vm, MMIO_GVA, MMIO_GPA, 1);
+
+ vcpu_run(vcpu);
+ handle_flds_emulation_failure_exit(vcpu);
+ vcpu_run(vcpu);
+ ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_DONE);
+
+ kvm_vm_free(vm);
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
new file mode 100644
index 000000000000..e43a7df25f2c
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/flds_emulation.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef SELFTEST_KVM_FLDS_EMULATION_H
+#define SELFTEST_KVM_FLDS_EMULATION_H
+
+#include "kvm_util.h"
+
+#define FLDS_MEM_EAX ".byte 0xd9, 0x00"
+
+/*
+ * flds is an instruction that the KVM instruction emulator is known not to
+ * support. This can be used in guest code along with a mechanism to force
+ * KVM to emulate the instruction (e.g. by providing an MMIO address) to
+ * exercise emulation failures.
+ */
+static inline void flds(uint64_t address)
+{
+ __asm__ __volatile__(FLDS_MEM_EAX :: "a"(address));
+}
+
+static inline void handle_flds_emulation_failure_exit(struct kvm_vcpu *vcpu)
+{
+ struct kvm_run *run = vcpu->run;
+ struct kvm_regs regs;
+ uint8_t *insn_bytes;
+ uint64_t flags;
+
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_INTERNAL_ERROR,
+ "Unexpected exit reason: %u (%s)",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ TEST_ASSERT(run->emulation_failure.suberror == KVM_INTERNAL_ERROR_EMULATION,
+ "Unexpected suberror: %u",
+ run->emulation_failure.suberror);
+
+ flags = run->emulation_failure.flags;
+ TEST_ASSERT(run->emulation_failure.ndata >= 3 &&
+ flags & KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES,
+ "run->emulation_failure is missing instruction bytes");
+
+ TEST_ASSERT(run->emulation_failure.insn_size >= 2,
+ "Expected a 2-byte opcode for 'flds', got %d bytes",
+ run->emulation_failure.insn_size);
+
+ insn_bytes = run->emulation_failure.insn_bytes;
+ TEST_ASSERT(insn_bytes[0] == 0xd9 && insn_bytes[1] == 0,
+ "Expected 'flds [eax]', opcode '0xd9 0x00', got opcode 0x%02x 0x%02x\n",
+ insn_bytes[0], insn_bytes[1]);
+
+ vcpu_regs_get(vcpu, &regs);
+ regs.rip += 2;
+ vcpu_regs_set(vcpu, &regs);
+}
+
+#endif /* !SELFTEST_KVM_FLDS_EMULATION_H */
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index e804eb08dff9..5c27efbf405e 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -134,9 +134,6 @@ int main(int argc, char *argv[])
const struct kvm_cpuid2 *hv_cpuid_entries;
struct kvm_vcpu *vcpu;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID));
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/evmcs_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
index 99bc202243d2..ba09d300c953 100644
--- a/tools/testing/selftests/kvm/x86_64/evmcs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c
@@ -16,6 +16,7 @@
#include "kvm_util.h"
+#include "hyperv.h"
#include "vmx.h"
static int ud_count;
@@ -30,24 +31,19 @@ static void guest_nmi_handler(struct ex_regs *regs)
{
}
-/* Exits to L1 destroy GRPs! */
-static inline void rdmsr_fs_base(void)
+static inline void rdmsr_from_l2(uint32_t msr)
{
- __asm__ __volatile__ ("mov $0xc0000100, %%rcx; rdmsr" : : :
- "rax", "rbx", "rcx", "rdx",
- "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
- "r13", "r14", "r15");
-}
-static inline void rdmsr_gs_base(void)
-{
- __asm__ __volatile__ ("mov $0xc0000101, %%rcx; rdmsr" : : :
- "rax", "rbx", "rcx", "rdx",
- "rsi", "rdi", "r8", "r9", "r10", "r11", "r12",
- "r13", "r14", "r15");
+ /* Currently, L1 doesn't preserve GPRs during vmexits. */
+ __asm__ __volatile__ ("rdmsr" : : "c"(msr) :
+ "rax", "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
}
+/* Exit to L1 from L2 with RDMSR instruction */
void l2_guest_code(void)
{
+ u64 unused;
+
GUEST_SYNC(7);
GUEST_SYNC(8);
@@ -58,42 +54,58 @@ void l2_guest_code(void)
vmcall();
/* MSR-Bitmap tests */
- rdmsr_fs_base(); /* intercepted */
- rdmsr_fs_base(); /* intercepted */
- rdmsr_gs_base(); /* not intercepted */
+ rdmsr_from_l2(MSR_FS_BASE); /* intercepted */
+ rdmsr_from_l2(MSR_FS_BASE); /* intercepted */
+ rdmsr_from_l2(MSR_GS_BASE); /* not intercepted */
vmcall();
- rdmsr_gs_base(); /* intercepted */
+ rdmsr_from_l2(MSR_GS_BASE); /* intercepted */
+
+ /* L2 TLB flush tests */
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | HV_FLUSH_ALL_PROCESSORS);
+ rdmsr_from_l2(MSR_FS_BASE);
+ /*
+ * Note: hypercall status (RAX) is not preserved correctly by L1 after
+ * synthetic vmexit, use unchecked version.
+ */
+ __hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES | HV_FLUSH_ALL_PROCESSORS,
+ &unused);
/* Done, exit to L1 and never come back. */
vmcall();
}
-void guest_code(struct vmx_pages *vmx_pages)
+void guest_code(struct vmx_pages *vmx_pages, struct hyperv_test_pages *hv_pages,
+ vm_vaddr_t hv_hcall_page_gpa)
{
#define L2_GUEST_STACK_SIZE 64
unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+ wrmsr(HV_X64_MSR_HYPERCALL, hv_hcall_page_gpa);
+
x2apic_enable();
GUEST_SYNC(1);
GUEST_SYNC(2);
- enable_vp_assist(vmx_pages->vp_assist_gpa, vmx_pages->vp_assist);
+ enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist);
+ evmcs_enable();
- GUEST_ASSERT(vmx_pages->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
GUEST_SYNC(3);
- GUEST_ASSERT(load_vmcs(vmx_pages));
- GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_ASSERT(load_evmcs(hv_pages));
+ GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa);
GUEST_SYNC(4);
- GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa);
prepare_vmcs(vmx_pages, l2_guest_code,
&l2_guest_stack[L2_GUEST_STACK_SIZE]);
GUEST_SYNC(5);
- GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa);
current_evmcs->revision_id = -1u;
GUEST_ASSERT(vmlaunch());
current_evmcs->revision_id = EVMCS_VERSION;
@@ -102,8 +114,18 @@ void guest_code(struct vmx_pages *vmx_pages)
vmwrite(PIN_BASED_VM_EXEC_CONTROL, vmreadz(PIN_BASED_VM_EXEC_CONTROL) |
PIN_BASED_NMI_EXITING);
+ /* L2 TLB flush setup */
+ current_evmcs->partition_assist_page = hv_pages->partition_assist_gpa;
+ current_evmcs->hv_enlightenments_control.nested_flush_hypercall = 1;
+ current_evmcs->hv_vm_id = 1;
+ current_evmcs->hv_vp_id = 1;
+ current_vp_assist->nested_control.features.directhypercall = 1;
+ *(u32 *)(hv_pages->partition_assist) = 0;
+
GUEST_ASSERT(!vmlaunch());
- GUEST_ASSERT(vmptrstz() == vmx_pages->enlightened_vmcs_gpa);
+ GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
+ GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), NMI_VECTOR);
+ GUEST_ASSERT(vmptrstz() == hv_pages->enlightened_vmcs_gpa);
/*
* NMI forces L2->L1 exit, resuming L2 and hope that EVMCS is
@@ -146,12 +168,24 @@ void guest_code(struct vmx_pages *vmx_pages)
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
current_evmcs->guest_rip += 2; /* rdmsr */
+ /*
+ * L2 TLB flush test. First VMCALL should be handled directly by L0,
+ * no VMCALL exit expected.
+ */
+ GUEST_ASSERT(!vmresume());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_MSR_READ);
+ current_evmcs->guest_rip += 2; /* rdmsr */
+ /* Enable synthetic vmexit */
+ *(u32 *)(hv_pages->partition_assist) = 1;
+ GUEST_ASSERT(!vmresume());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH);
+
GUEST_ASSERT(!vmresume());
GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
GUEST_SYNC(11);
/* Try enlightened vmptrld with an incorrect GPA */
- evmcs_vmptrld(0xdeadbeef, vmx_pages->enlightened_vmcs);
+ evmcs_vmptrld(0xdeadbeef, hv_pages->enlightened_vmcs);
GUEST_ASSERT(vmlaunch());
GUEST_ASSERT(ud_count == 1);
GUEST_DONE();
@@ -198,7 +232,8 @@ static struct kvm_vcpu *save_restore_vm(struct kvm_vm *vm,
int main(int argc, char *argv[])
{
- vm_vaddr_t vmx_pages_gva = 0;
+ vm_vaddr_t vmx_pages_gva = 0, hv_pages_gva = 0;
+ vm_vaddr_t hcall_page;
struct kvm_vcpu *vcpu;
struct kvm_vm *vm;
@@ -212,11 +247,16 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_has_cap(KVM_CAP_NESTED_STATE));
TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS));
+ hcall_page = vm_vaddr_alloc_pages(vm, 1);
+ memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize());
+
vcpu_set_hv_cpuid(vcpu);
vcpu_enable_evmcs(vcpu);
vcpu_alloc_vmx(vm, &vmx_pages_gva);
- vcpu_args_set(vcpu, 1, vmx_pages_gva);
+ vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva);
+ vcpu_args_set(vcpu, 3, vmx_pages_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page));
+ vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id);
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vcpu);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 05b32e550a80..3163c3e8db0a 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -13,25 +13,6 @@
#include "processor.h"
#include "hyperv.h"
-#define LINUX_OS_ID ((u64)0x8100 << 48)
-
-static inline uint8_t hypercall(u64 control, vm_vaddr_t input_address,
- vm_vaddr_t output_address, uint64_t *hv_status)
-{
- uint8_t vector;
-
- /* Note both the hypercall and the "asm safe" clobber r9-r11. */
- asm volatile("mov %[output_address], %%r8\n\t"
- KVM_ASM_SAFE("vmcall")
- : "=a" (*hv_status),
- "+c" (control), "+d" (input_address),
- KVM_ASM_SAFE_OUTPUTS(vector)
- : [output_address] "r"(output_address),
- "a" (-EFAULT)
- : "cc", "memory", "r8", KVM_ASM_SAFE_CLOBBERS);
- return vector;
-}
-
struct msr_data {
uint32_t idx;
bool available;
@@ -71,7 +52,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
GUEST_ASSERT(hcall->control);
- wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID);
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) {
@@ -81,7 +62,7 @@ static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
input = output = 0;
}
- vector = hypercall(hcall->control, input, output, &res);
+ vector = __hyperv_hypercall(hcall->control, input, output, &res);
if (hcall->ud_expected) {
GUEST_ASSERT_2(vector == UD_VECTOR, hcall->control, vector);
} else {
@@ -169,7 +150,7 @@ static void guest_test_msrs_access(void)
*/
msr->idx = HV_X64_MSR_GUEST_OS_ID;
msr->write = 1;
- msr->write_val = LINUX_OS_ID;
+ msr->write_val = HYPERV_LINUX_OS_ID;
msr->available = 1;
break;
case 3:
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
new file mode 100644
index 000000000000..8b791eac7d5a
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c
@@ -0,0 +1,314 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyper-V HvCallSendSyntheticClusterIpi{,Ex} tests
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <pthread.h>
+#include <inttypes.h>
+
+#include "kvm_util.h"
+#include "hyperv.h"
+#include "test_util.h"
+#include "vmx.h"
+
+#define RECEIVER_VCPU_ID_1 2
+#define RECEIVER_VCPU_ID_2 65
+
+#define IPI_VECTOR 0xfe
+
+static volatile uint64_t ipis_rcvd[RECEIVER_VCPU_ID_2 + 1];
+
+struct hv_vpset {
+ u64 format;
+ u64 valid_bank_mask;
+ u64 bank_contents[2];
+};
+
+enum HV_GENERIC_SET_FORMAT {
+ HV_GENERIC_SET_SPARSE_4K,
+ HV_GENERIC_SET_ALL,
+};
+
+/* HvCallSendSyntheticClusterIpi hypercall */
+struct hv_send_ipi {
+ u32 vector;
+ u32 reserved;
+ u64 cpu_mask;
+};
+
+/* HvCallSendSyntheticClusterIpiEx hypercall */
+struct hv_send_ipi_ex {
+ u32 vector;
+ u32 reserved;
+ struct hv_vpset vp_set;
+};
+
+static inline void hv_init(vm_vaddr_t pgs_gpa)
+{
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+ wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
+}
+
+static void receiver_code(void *hcall_page, vm_vaddr_t pgs_gpa)
+{
+ u32 vcpu_id;
+
+ x2apic_enable();
+ hv_init(pgs_gpa);
+
+ vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX);
+
+ /* Signal sender vCPU we're ready */
+ ipis_rcvd[vcpu_id] = (u64)-1;
+
+ for (;;)
+ asm volatile("sti; hlt; cli");
+}
+
+static void guest_ipi_handler(struct ex_regs *regs)
+{
+ u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX);
+
+ ipis_rcvd[vcpu_id]++;
+ wrmsr(HV_X64_MSR_EOI, 1);
+}
+
+static inline void nop_loop(void)
+{
+ int i;
+
+ for (i = 0; i < 100000000; i++)
+ asm volatile("nop");
+}
+
+static void sender_guest_code(void *hcall_page, vm_vaddr_t pgs_gpa)
+{
+ struct hv_send_ipi *ipi = (struct hv_send_ipi *)hcall_page;
+ struct hv_send_ipi_ex *ipi_ex = (struct hv_send_ipi_ex *)hcall_page;
+ int stage = 1, ipis_expected[2] = {0};
+
+ hv_init(pgs_gpa);
+ GUEST_SYNC(stage++);
+
+ /* Wait for receiver vCPUs to come up */
+ while (!ipis_rcvd[RECEIVER_VCPU_ID_1] || !ipis_rcvd[RECEIVER_VCPU_ID_2])
+ nop_loop();
+ ipis_rcvd[RECEIVER_VCPU_ID_1] = ipis_rcvd[RECEIVER_VCPU_ID_2] = 0;
+
+ /* 'Slow' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */
+ ipi->vector = IPI_VECTOR;
+ ipi->cpu_mask = 1 << RECEIVER_VCPU_ID_1;
+ hyperv_hypercall(HVCALL_SEND_IPI, pgs_gpa, pgs_gpa + 4096);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
+ GUEST_SYNC(stage++);
+ /* 'Fast' HvCallSendSyntheticClusterIpi to RECEIVER_VCPU_ID_1 */
+ hyperv_hypercall(HVCALL_SEND_IPI | HV_HYPERCALL_FAST_BIT,
+ IPI_VECTOR, 1 << RECEIVER_VCPU_ID_1);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
+ GUEST_SYNC(stage++);
+
+ /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */
+ memset(hcall_page, 0, 4096);
+ ipi_ex->vector = IPI_VECTOR;
+ ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ ipi_ex->vp_set.valid_bank_mask = 1 << 0;
+ ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ pgs_gpa, pgs_gpa + 4096);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
+ GUEST_SYNC(stage++);
+ /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_1 */
+ hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 1);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ipis_expected[1]);
+ GUEST_SYNC(stage++);
+
+ /* 'Slow' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */
+ memset(hcall_page, 0, 4096);
+ ipi_ex->vector = IPI_VECTOR;
+ ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ ipi_ex->vp_set.valid_bank_mask = 1 << 1;
+ ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_2 - 64);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ pgs_gpa, pgs_gpa + 4096);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+ /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to RECEIVER_VCPU_ID_2 */
+ hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 1);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+
+ /* 'Slow' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1,2} */
+ memset(hcall_page, 0, 4096);
+ ipi_ex->vector = IPI_VECTOR;
+ ipi_ex->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ ipi_ex->vp_set.valid_bank_mask = 1 << 1 | 1;
+ ipi_ex->vp_set.bank_contents[0] = BIT(RECEIVER_VCPU_ID_1);
+ ipi_ex->vp_set.bank_contents[1] = BIT(RECEIVER_VCPU_ID_2 - 64);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | (2 << HV_HYPERCALL_VARHEAD_OFFSET),
+ pgs_gpa, pgs_gpa + 4096);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+ /* 'XMM Fast' HvCallSendSyntheticClusterIpiEx to both RECEIVER_VCPU_ID_{1, 2} */
+ hyperv_write_xmm_input(&ipi_ex->vp_set.valid_bank_mask, 2);
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT |
+ (2 << HV_HYPERCALL_VARHEAD_OFFSET),
+ IPI_VECTOR, HV_GENERIC_SET_SPARSE_4K);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+
+ /* 'Slow' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL */
+ memset(hcall_page, 0, 4096);
+ ipi_ex->vector = IPI_VECTOR;
+ ipi_ex->vp_set.format = HV_GENERIC_SET_ALL;
+ hyperv_hypercall(HVCALL_SEND_IPI_EX, pgs_gpa, pgs_gpa + 4096);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+ /*
+ * 'XMM Fast' HvCallSendSyntheticClusterIpiEx to HV_GENERIC_SET_ALL.
+ * Nothing to write anything to XMM regs.
+ */
+ hyperv_hypercall(HVCALL_SEND_IPI_EX | HV_HYPERCALL_FAST_BIT,
+ IPI_VECTOR, HV_GENERIC_SET_ALL);
+ nop_loop();
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_1] == ++ipis_expected[0]);
+ GUEST_ASSERT(ipis_rcvd[RECEIVER_VCPU_ID_2] == ++ipis_expected[1]);
+ GUEST_SYNC(stage++);
+
+ GUEST_DONE();
+}
+
+static void *vcpu_thread(void *arg)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)arg;
+ int old, r;
+
+ r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old);
+ TEST_ASSERT(!r, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d",
+ vcpu->id, r);
+
+ vcpu_run(vcpu);
+
+ TEST_FAIL("vCPU %u exited unexpectedly", vcpu->id);
+
+ return NULL;
+}
+
+static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu)
+{
+ void *retval;
+ int r;
+
+ r = pthread_cancel(thread);
+ TEST_ASSERT(!r, "pthread_cancel on vcpu_id=%d failed with errno=%d",
+ vcpu->id, r);
+
+ r = pthread_join(thread, &retval);
+ TEST_ASSERT(!r, "pthread_join on vcpu_id=%d failed with errno=%d",
+ vcpu->id, r);
+ TEST_ASSERT(retval == PTHREAD_CANCELED,
+ "expected retval=%p, got %p", PTHREAD_CANCELED,
+ retval);
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ struct kvm_vcpu *vcpu[3];
+ unsigned int exit_reason;
+ vm_vaddr_t hcall_page;
+ pthread_t threads[2];
+ int stage = 1, r;
+ struct ucall uc;
+
+ vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
+
+ /* Hypercall input/output */
+ hcall_page = vm_vaddr_alloc_pages(vm, 2);
+ memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
+
+ vm_init_descriptor_tables(vm);
+
+ vcpu[1] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_1, receiver_code);
+ vcpu_init_descriptor_tables(vcpu[1]);
+ vcpu_args_set(vcpu[1], 2, hcall_page, addr_gva2gpa(vm, hcall_page));
+ vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_1);
+ vcpu_set_hv_cpuid(vcpu[1]);
+
+ vcpu[2] = vm_vcpu_add(vm, RECEIVER_VCPU_ID_2, receiver_code);
+ vcpu_init_descriptor_tables(vcpu[2]);
+ vcpu_args_set(vcpu[2], 2, hcall_page, addr_gva2gpa(vm, hcall_page));
+ vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, RECEIVER_VCPU_ID_2);
+ vcpu_set_hv_cpuid(vcpu[2]);
+
+ vm_install_exception_handler(vm, IPI_VECTOR, guest_ipi_handler);
+
+ vcpu_args_set(vcpu[0], 2, hcall_page, addr_gva2gpa(vm, hcall_page));
+ vcpu_set_hv_cpuid(vcpu[0]);
+
+ r = pthread_create(&threads[0], NULL, vcpu_thread, vcpu[1]);
+ TEST_ASSERT(!r, "pthread_create failed errno=%d", r);
+
+ r = pthread_create(&threads[1], NULL, vcpu_thread, vcpu[2]);
+ TEST_ASSERT(!r, "pthread_create failed errno=%d", errno);
+
+ while (true) {
+ vcpu_run(vcpu[0]);
+
+ exit_reason = vcpu[0]->run->exit_reason;
+ TEST_ASSERT(exit_reason == KVM_EXIT_IO,
+ "unexpected exit reason: %u (%s)",
+ exit_reason, exit_reason_str(exit_reason));
+
+ switch (get_ucall(vcpu[0], &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT(uc.args[1] == stage,
+ "Unexpected stage: %ld (%d expected)\n",
+ uc.args[1], stage);
+ break;
+ case UCALL_DONE:
+ goto done;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ /* NOT REACHED */
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ stage++;
+ }
+
+done:
+ cancel_join_vcpu_thread(threads[0], vcpu[1]);
+ cancel_join_vcpu_thread(threads[1], vcpu[2]);
+ kvm_vm_free(vm);
+
+ return r;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index a380ad7bb9b3..3b3cc94ba8e4 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -23,59 +23,78 @@
#define L2_GUEST_STACK_SIZE 256
-struct hv_enlightenments {
- struct __packed hv_enlightenments_control {
- u32 nested_flush_hypercall:1;
- u32 msr_bitmap:1;
- u32 enlightened_npt_tlb: 1;
- u32 reserved:29;
- } __packed hv_enlightenments_control;
- u32 hv_vp_id;
- u64 hv_vm_id;
- u64 partition_assist_page;
- u64 reserved;
-} __packed;
-
-/*
- * Hyper-V uses the software reserved clean bit in VMCB
- */
-#define VMCB_HV_NESTED_ENLIGHTENMENTS (1U << 31)
+/* Exit to L1 from L2 with RDMSR instruction */
+static inline void rdmsr_from_l2(uint32_t msr)
+{
+ /* Currently, L1 doesn't preserve GPRs during vmexits. */
+ __asm__ __volatile__ ("rdmsr" : : "c"(msr) :
+ "rax", "rbx", "rdx", "rsi", "rdi", "r8", "r9",
+ "r10", "r11", "r12", "r13", "r14", "r15");
+}
void l2_guest_code(void)
{
+ u64 unused;
+
GUEST_SYNC(3);
/* Exit to L1 */
vmmcall();
/* MSR-Bitmap tests */
- rdmsr(MSR_FS_BASE); /* intercepted */
- rdmsr(MSR_FS_BASE); /* intercepted */
- rdmsr(MSR_GS_BASE); /* not intercepted */
+ rdmsr_from_l2(MSR_FS_BASE); /* intercepted */
+ rdmsr_from_l2(MSR_FS_BASE); /* intercepted */
+ rdmsr_from_l2(MSR_GS_BASE); /* not intercepted */
vmmcall();
- rdmsr(MSR_GS_BASE); /* intercepted */
+ rdmsr_from_l2(MSR_GS_BASE); /* intercepted */
GUEST_SYNC(5);
+ /* L2 TLB flush tests */
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE |
+ HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS);
+ rdmsr_from_l2(MSR_FS_BASE);
+ /*
+ * Note: hypercall status (RAX) is not preserved correctly by L1 after
+ * synthetic vmexit, use unchecked version.
+ */
+ __hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE |
+ HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS, &unused);
+
/* Done, exit to L1 and never come back. */
vmmcall();
}
-static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm)
+static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm,
+ struct hyperv_test_pages *hv_pages,
+ vm_vaddr_t pgs_gpa)
{
unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
struct vmcb *vmcb = svm->vmcb;
- struct hv_enlightenments *hve =
- (struct hv_enlightenments *)vmcb->control.reserved_sw;
+ struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
GUEST_SYNC(1);
- wrmsr(HV_X64_MSR_GUEST_OS_ID, (u64)0x8100 << 48);
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+ wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
+ enable_vp_assist(hv_pages->vp_assist_gpa, hv_pages->vp_assist);
GUEST_ASSERT(svm->vmcb_gpa);
/* Prepare for L2 execution. */
generic_svm_setup(svm, l2_guest_code,
&l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ /* L2 TLB flush setup */
+ hve->partition_assist_page = hv_pages->partition_assist_gpa;
+ hve->hv_enlightenments_control.nested_flush_hypercall = 1;
+ hve->hv_vm_id = 1;
+ hve->hv_vp_id = 1;
+ current_vp_assist->nested_control.features.directhypercall = 1;
+ *(u32 *)(hv_pages->partition_assist) = 0;
+
GUEST_SYNC(2);
run_guest(vmcb, svm->vmcb_gpa);
GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
@@ -98,18 +117,32 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm)
/* Intercept RDMSR 0xc0000101 without telling KVM about it */
set_bit(2 * (MSR_GS_BASE & 0x1fff), svm->msr + 0x800);
/* Make sure HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP is set */
- vmcb->control.clean |= VMCB_HV_NESTED_ENLIGHTENMENTS;
+ vmcb->control.clean |= HV_VMCB_NESTED_ENLIGHTENMENTS;
run_guest(vmcb, svm->vmcb_gpa);
/* Make sure we don't see SVM_EXIT_MSR here so eMSR bitmap works */
GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
vmcb->save.rip += 3; /* vmcall */
/* Now tell KVM we've changed MSR-Bitmap */
- vmcb->control.clean &= ~VMCB_HV_NESTED_ENLIGHTENMENTS;
+ vmcb->control.clean &= ~HV_VMCB_NESTED_ENLIGHTENMENTS;
run_guest(vmcb, svm->vmcb_gpa);
GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
vmcb->save.rip += 2; /* rdmsr */
+
+ /*
+ * L2 TLB flush test. First VMCALL should be handled directly by L0,
+ * no VMCALL exit expected.
+ */
+ run_guest(vmcb, svm->vmcb_gpa);
+ GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_MSR);
+ vmcb->save.rip += 2; /* rdmsr */
+ /* Enable synthetic vmexit */
+ *(u32 *)(hv_pages->partition_assist) = 1;
+ run_guest(vmcb, svm->vmcb_gpa);
+ GUEST_ASSERT(vmcb->control.exit_code == HV_SVM_EXITCODE_ENL);
+ GUEST_ASSERT(vmcb->control.exit_info_1 == HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH);
+
run_guest(vmcb, svm->vmcb_gpa);
GUEST_ASSERT(vmcb->control.exit_code == SVM_EXIT_VMMCALL);
GUEST_SYNC(6);
@@ -119,8 +152,8 @@ static void __attribute__((__flatten__)) guest_code(struct svm_test_data *svm)
int main(int argc, char *argv[])
{
- vm_vaddr_t nested_gva = 0;
-
+ vm_vaddr_t nested_gva = 0, hv_pages_gva = 0;
+ vm_vaddr_t hcall_page;
struct kvm_vcpu *vcpu;
struct kvm_vm *vm;
struct kvm_run *run;
@@ -134,7 +167,13 @@ int main(int argc, char *argv[])
vcpu_set_hv_cpuid(vcpu);
run = vcpu->run;
vcpu_alloc_svm(vm, &nested_gva);
- vcpu_args_set(vcpu, 1, nested_gva);
+ vcpu_alloc_hyperv_test_pages(vm, &hv_pages_gva);
+
+ hcall_page = vm_vaddr_alloc_pages(vm, 1);
+ memset(addr_gva2hva(vm, hcall_page), 0x0, getpagesize());
+
+ vcpu_args_set(vcpu, 3, nested_gva, hv_pages_gva, addr_gva2gpa(vm, hcall_page));
+ vcpu_set_msr(vcpu, HV_X64_MSR_VP_INDEX, vcpu->id);
for (stage = 1;; stage++) {
vcpu_run(vcpu);
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
new file mode 100644
index 000000000000..68f97ff720a7
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c
@@ -0,0 +1,690 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyper-V HvFlushVirtualAddress{List,Space}{,Ex} tests
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <asm/barrier.h>
+#include <pthread.h>
+#include <inttypes.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "hyperv.h"
+#include "test_util.h"
+#include "vmx.h"
+
+#define WORKER_VCPU_ID_1 2
+#define WORKER_VCPU_ID_2 65
+
+#define NTRY 100
+#define NTEST_PAGES 2
+
+struct hv_vpset {
+ u64 format;
+ u64 valid_bank_mask;
+ u64 bank_contents[];
+};
+
+enum HV_GENERIC_SET_FORMAT {
+ HV_GENERIC_SET_SPARSE_4K,
+ HV_GENERIC_SET_ALL,
+};
+
+#define HV_FLUSH_ALL_PROCESSORS BIT(0)
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES BIT(1)
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY BIT(2)
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT BIT(3)
+
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_tlb_flush {
+ u64 address_space;
+ u64 flags;
+ u64 processor_mask;
+ u64 gva_list[];
+} __packed;
+
+/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
+struct hv_tlb_flush_ex {
+ u64 address_space;
+ u64 flags;
+ struct hv_vpset hv_vp_set;
+ u64 gva_list[];
+} __packed;
+
+/*
+ * Pass the following info to 'workers' and 'sender'
+ * - Hypercall page's GVA
+ * - Hypercall page's GPA
+ * - Test pages GVA
+ * - GVAs of the test pages' PTEs
+ */
+struct test_data {
+ vm_vaddr_t hcall_gva;
+ vm_paddr_t hcall_gpa;
+ vm_vaddr_t test_pages;
+ vm_vaddr_t test_pages_pte[NTEST_PAGES];
+};
+
+/* 'Worker' vCPU code checking the contents of the test page */
+static void worker_guest_code(vm_vaddr_t test_data)
+{
+ struct test_data *data = (struct test_data *)test_data;
+ u32 vcpu_id = rdmsr(HV_X64_MSR_VP_INDEX);
+ void *exp_page = (void *)data->test_pages + PAGE_SIZE * NTEST_PAGES;
+ u64 *this_cpu = (u64 *)(exp_page + vcpu_id * sizeof(u64));
+ u64 expected, val;
+
+ x2apic_enable();
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+
+ for (;;) {
+ cpu_relax();
+
+ expected = READ_ONCE(*this_cpu);
+
+ /*
+ * Make sure the value in the test page is read after reading
+ * the expectation for the first time. Pairs with wmb() in
+ * prepare_to_test().
+ */
+ rmb();
+
+ val = READ_ONCE(*(u64 *)data->test_pages);
+
+ /*
+ * Make sure the value in the test page is read after before
+ * reading the expectation for the second time. Pairs with wmb()
+ * post_test().
+ */
+ rmb();
+
+ /*
+ * '0' indicates the sender is between iterations, wait until
+ * the sender is ready for this vCPU to start checking again.
+ */
+ if (!expected)
+ continue;
+
+ /*
+ * Re-read the per-vCPU byte to ensure the sender didn't move
+ * onto a new iteration.
+ */
+ if (expected != READ_ONCE(*this_cpu))
+ continue;
+
+ GUEST_ASSERT(val == expected);
+ }
+}
+
+/*
+ * Write per-CPU info indicating what each 'worker' CPU is supposed to see in
+ * test page. '0' means don't check.
+ */
+static void set_expected_val(void *addr, u64 val, int vcpu_id)
+{
+ void *exp_page = addr + PAGE_SIZE * NTEST_PAGES;
+
+ *(u64 *)(exp_page + vcpu_id * sizeof(u64)) = val;
+}
+
+/*
+ * Update PTEs swapping two test pages.
+ * TODO: use swap()/xchg() when these are provided.
+ */
+static void swap_two_test_pages(vm_paddr_t pte_gva1, vm_paddr_t pte_gva2)
+{
+ uint64_t tmp = *(uint64_t *)pte_gva1;
+
+ *(uint64_t *)pte_gva1 = *(uint64_t *)pte_gva2;
+ *(uint64_t *)pte_gva2 = tmp;
+}
+
+/*
+ * TODO: replace the silly NOP loop with a proper udelay() implementation.
+ */
+static inline void do_delay(void)
+{
+ int i;
+
+ for (i = 0; i < 1000000; i++)
+ asm volatile("nop");
+}
+
+/*
+ * Prepare to test: 'disable' workers by setting the expectation to '0',
+ * clear hypercall input page and then swap two test pages.
+ */
+static inline void prepare_to_test(struct test_data *data)
+{
+ /* Clear hypercall input page */
+ memset((void *)data->hcall_gva, 0, PAGE_SIZE);
+
+ /* 'Disable' workers */
+ set_expected_val((void *)data->test_pages, 0x0, WORKER_VCPU_ID_1);
+ set_expected_val((void *)data->test_pages, 0x0, WORKER_VCPU_ID_2);
+
+ /* Make sure workers are 'disabled' before we swap PTEs. */
+ wmb();
+
+ /* Make sure workers have enough time to notice */
+ do_delay();
+
+ /* Swap test page mappings */
+ swap_two_test_pages(data->test_pages_pte[0], data->test_pages_pte[1]);
+}
+
+/*
+ * Finalize the test: check hypercall resule set the expected val for
+ * 'worker' CPUs and give them some time to test.
+ */
+static inline void post_test(struct test_data *data, u64 exp1, u64 exp2)
+{
+ /* Make sure we change the expectation after swapping PTEs */
+ wmb();
+
+ /* Set the expectation for workers, '0' means don't test */
+ set_expected_val((void *)data->test_pages, exp1, WORKER_VCPU_ID_1);
+ set_expected_val((void *)data->test_pages, exp2, WORKER_VCPU_ID_2);
+
+ /* Make sure workers have enough time to test */
+ do_delay();
+}
+
+#define TESTVAL1 0x0101010101010101
+#define TESTVAL2 0x0202020202020202
+
+/* Main vCPU doing the test */
+static void sender_guest_code(vm_vaddr_t test_data)
+{
+ struct test_data *data = (struct test_data *)test_data;
+ struct hv_tlb_flush *flush = (struct hv_tlb_flush *)data->hcall_gva;
+ struct hv_tlb_flush_ex *flush_ex = (struct hv_tlb_flush_ex *)data->hcall_gva;
+ vm_paddr_t hcall_gpa = data->hcall_gpa;
+ int i, stage = 1;
+
+ wrmsr(HV_X64_MSR_GUEST_OS_ID, HYPERV_LINUX_OS_ID);
+ wrmsr(HV_X64_MSR_HYPERCALL, data->hcall_gpa);
+
+ /* "Slow" hypercalls */
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for WORKER_VCPU_ID_1 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush->processor_mask = BIT(WORKER_VCPU_ID_1);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, hcall_gpa,
+ hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for WORKER_VCPU_ID_1 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush->processor_mask = BIT(WORKER_VCPU_ID_1);
+ flush->gva_list[0] = (u64)data->test_pages;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for HV_FLUSH_ALL_PROCESSORS */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS;
+ flush->processor_mask = 0;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE, hcall_gpa,
+ hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for HV_FLUSH_ALL_PROCESSORS */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS;
+ flush->gva_list[0] = (u64)data->test_pages;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for WORKER_VCPU_ID_2 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for WORKER_VCPU_ID_2 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ /* bank_contents and gva_list occupy the same space, thus [1] */
+ flush_ex->gva_list[1] = (u64)data->test_pages;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET) |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for both vCPUs */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64) |
+ BIT_ULL(WORKER_VCPU_ID_1 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64);
+ flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX |
+ (2 << HV_HYPERCALL_VARHEAD_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for both vCPUs */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_1 / 64) |
+ BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64);
+ flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ /* bank_contents and gva_list occupy the same space, thus [2] */
+ flush_ex->gva_list[2] = (u64)data->test_pages;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ (2 << HV_HYPERCALL_VARHEAD_OFFSET) |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for HV_GENERIC_SET_ALL */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX,
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for HV_GENERIC_SET_ALL */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL;
+ flush_ex->gva_list[0] = (u64)data->test_pages;
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ hcall_gpa, hcall_gpa + PAGE_SIZE);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ /* "Fast" hypercalls */
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for WORKER_VCPU_ID_1 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->processor_mask = BIT(WORKER_VCPU_ID_1);
+ hyperv_write_xmm_input(&flush->processor_mask, 1);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE |
+ HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for WORKER_VCPU_ID_1 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->processor_mask = BIT(WORKER_VCPU_ID_1);
+ flush->gva_list[0] = (u64)data->test_pages;
+ hyperv_write_xmm_input(&flush->processor_mask, 1);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST |
+ HV_HYPERCALL_FAST_BIT |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2, 0x0);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE for HV_FLUSH_ALL_PROCESSORS */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ hyperv_write_xmm_input(&flush->processor_mask, 1);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE |
+ HV_HYPERCALL_FAST_BIT, 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST for HV_FLUSH_ALL_PROCESSORS */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush->gva_list[0] = (u64)data->test_pages;
+ hyperv_write_xmm_input(&flush->processor_mask, 1);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST |
+ HV_HYPERCALL_FAST_BIT |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET), 0x0,
+ HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES |
+ HV_FLUSH_ALL_PROCESSORS);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for WORKER_VCPU_ID_2 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX |
+ HV_HYPERCALL_FAST_BIT |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for WORKER_VCPU_ID_2 */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ /* bank_contents and gva_list occupy the same space, thus [1] */
+ flush_ex->gva_list[1] = (u64)data->test_pages;
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ HV_HYPERCALL_FAST_BIT |
+ (1 << HV_HYPERCALL_VARHEAD_OFFSET) |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, 0x0, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for both vCPUs */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_2 / 64) |
+ BIT_ULL(WORKER_VCPU_ID_1 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64);
+ flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX |
+ HV_HYPERCALL_FAST_BIT |
+ (2 << HV_HYPERCALL_VARHEAD_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 :
+ TESTVAL2, i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for both vCPUs */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+ flush_ex->hv_vp_set.valid_bank_mask = BIT_ULL(WORKER_VCPU_ID_1 / 64) |
+ BIT_ULL(WORKER_VCPU_ID_2 / 64);
+ flush_ex->hv_vp_set.bank_contents[0] = BIT_ULL(WORKER_VCPU_ID_1 % 64);
+ flush_ex->hv_vp_set.bank_contents[1] = BIT_ULL(WORKER_VCPU_ID_2 % 64);
+ /* bank_contents and gva_list occupy the same space, thus [2] */
+ flush_ex->gva_list[2] = (u64)data->test_pages;
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 3);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ HV_HYPERCALL_FAST_BIT |
+ (2 << HV_HYPERCALL_VARHEAD_OFFSET) |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX for HV_GENERIC_SET_ALL */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL;
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX |
+ HV_HYPERCALL_FAST_BIT,
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_SYNC(stage++);
+
+ /* HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX for HV_GENERIC_SET_ALL */
+ for (i = 0; i < NTRY; i++) {
+ prepare_to_test(data);
+ flush_ex->flags = HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES;
+ flush_ex->hv_vp_set.format = HV_GENERIC_SET_ALL;
+ flush_ex->gva_list[0] = (u64)data->test_pages;
+ hyperv_write_xmm_input(&flush_ex->hv_vp_set, 2);
+ hyperv_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX |
+ HV_HYPERCALL_FAST_BIT |
+ (1UL << HV_HYPERCALL_REP_COMP_OFFSET),
+ 0x0, HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES);
+ post_test(data, i % 2 ? TESTVAL1 : TESTVAL2,
+ i % 2 ? TESTVAL1 : TESTVAL2);
+ }
+
+ GUEST_DONE();
+}
+
+static void *vcpu_thread(void *arg)
+{
+ struct kvm_vcpu *vcpu = (struct kvm_vcpu *)arg;
+ struct ucall uc;
+ int old;
+ int r;
+ unsigned int exit_reason;
+
+ r = pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, &old);
+ TEST_ASSERT(!r, "pthread_setcanceltype failed on vcpu_id=%u with errno=%d",
+ vcpu->id, r);
+
+ vcpu_run(vcpu);
+ exit_reason = vcpu->run->exit_reason;
+
+ TEST_ASSERT(exit_reason == KVM_EXIT_IO,
+ "vCPU %u exited with unexpected exit reason %u-%s, expected KVM_EXIT_IO",
+ vcpu->id, exit_reason, exit_reason_str(exit_reason));
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ /* NOT REACHED */
+ default:
+ TEST_FAIL("Unexpected ucall %lu, vCPU %d", uc.cmd, vcpu->id);
+ }
+
+ return NULL;
+}
+
+static void cancel_join_vcpu_thread(pthread_t thread, struct kvm_vcpu *vcpu)
+{
+ void *retval;
+ int r;
+
+ r = pthread_cancel(thread);
+ TEST_ASSERT(!r, "pthread_cancel on vcpu_id=%d failed with errno=%d",
+ vcpu->id, r);
+
+ r = pthread_join(thread, &retval);
+ TEST_ASSERT(!r, "pthread_join on vcpu_id=%d failed with errno=%d",
+ vcpu->id, r);
+ TEST_ASSERT(retval == PTHREAD_CANCELED,
+ "expected retval=%p, got %p", PTHREAD_CANCELED,
+ retval);
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ struct kvm_vcpu *vcpu[3];
+ unsigned int exit_reason;
+ pthread_t threads[2];
+ vm_vaddr_t test_data_page, gva;
+ vm_paddr_t gpa;
+ uint64_t *pte;
+ struct test_data *data;
+ struct ucall uc;
+ int stage = 1, r, i;
+
+ vm = vm_create_with_one_vcpu(&vcpu[0], sender_guest_code);
+
+ /* Test data page */
+ test_data_page = vm_vaddr_alloc_page(vm);
+ data = (struct test_data *)addr_gva2hva(vm, test_data_page);
+
+ /* Hypercall input/output */
+ data->hcall_gva = vm_vaddr_alloc_pages(vm, 2);
+ data->hcall_gpa = addr_gva2gpa(vm, data->hcall_gva);
+ memset(addr_gva2hva(vm, data->hcall_gva), 0x0, 2 * PAGE_SIZE);
+
+ /*
+ * Test pages: the first one is filled with '0x01's, the second with '0x02's
+ * and the test will swap their mappings. The third page keeps the indication
+ * about the current state of mappings.
+ */
+ data->test_pages = vm_vaddr_alloc_pages(vm, NTEST_PAGES + 1);
+ for (i = 0; i < NTEST_PAGES; i++)
+ memset(addr_gva2hva(vm, data->test_pages + PAGE_SIZE * i),
+ (u8)(i + 1), PAGE_SIZE);
+ set_expected_val(addr_gva2hva(vm, data->test_pages), 0x0, WORKER_VCPU_ID_1);
+ set_expected_val(addr_gva2hva(vm, data->test_pages), 0x0, WORKER_VCPU_ID_2);
+
+ /*
+ * Get PTE pointers for test pages and map them inside the guest.
+ * Use separate page for each PTE for simplicity.
+ */
+ gva = vm_vaddr_unused_gap(vm, NTEST_PAGES * PAGE_SIZE, KVM_UTIL_MIN_VADDR);
+ for (i = 0; i < NTEST_PAGES; i++) {
+ pte = vm_get_page_table_entry(vm, data->test_pages + i * PAGE_SIZE);
+ gpa = addr_hva2gpa(vm, pte);
+ __virt_pg_map(vm, gva + PAGE_SIZE * i, gpa & PAGE_MASK, PG_LEVEL_4K);
+ data->test_pages_pte[i] = gva + (gpa & ~PAGE_MASK);
+ }
+
+ /*
+ * Sender vCPU which performs the test: swaps test pages, sets expectation
+ * for 'workers' and issues TLB flush hypercalls.
+ */
+ vcpu_args_set(vcpu[0], 1, test_data_page);
+ vcpu_set_hv_cpuid(vcpu[0]);
+
+ /* Create worker vCPUs which check the contents of the test pages */
+ vcpu[1] = vm_vcpu_add(vm, WORKER_VCPU_ID_1, worker_guest_code);
+ vcpu_args_set(vcpu[1], 1, test_data_page);
+ vcpu_set_msr(vcpu[1], HV_X64_MSR_VP_INDEX, WORKER_VCPU_ID_1);
+ vcpu_set_hv_cpuid(vcpu[1]);
+
+ vcpu[2] = vm_vcpu_add(vm, WORKER_VCPU_ID_2, worker_guest_code);
+ vcpu_args_set(vcpu[2], 1, test_data_page);
+ vcpu_set_msr(vcpu[2], HV_X64_MSR_VP_INDEX, WORKER_VCPU_ID_2);
+ vcpu_set_hv_cpuid(vcpu[2]);
+
+ r = pthread_create(&threads[0], NULL, vcpu_thread, vcpu[1]);
+ TEST_ASSERT(!r, "pthread_create() failed");
+
+ r = pthread_create(&threads[1], NULL, vcpu_thread, vcpu[2]);
+ TEST_ASSERT(!r, "pthread_create() failed");
+
+ while (true) {
+ vcpu_run(vcpu[0]);
+ exit_reason = vcpu[0]->run->exit_reason;
+
+ TEST_ASSERT(exit_reason == KVM_EXIT_IO,
+ "unexpected exit reason: %u (%s)",
+ exit_reason, exit_reason_str(exit_reason));
+
+ switch (get_ucall(vcpu[0], &uc)) {
+ case UCALL_SYNC:
+ TEST_ASSERT(uc.args[1] == stage,
+ "Unexpected stage: %ld (%d expected)\n",
+ uc.args[1], stage);
+ break;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ /* NOT REACHED */
+ case UCALL_DONE:
+ goto done;
+ default:
+ TEST_FAIL("Unknown ucall %lu", uc.cmd);
+ }
+
+ stage++;
+ }
+
+done:
+ cancel_join_vcpu_thread(threads[0], vcpu[1]);
+ cancel_join_vcpu_thread(threads[1], vcpu[2]);
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 59ffe7fd354f..ea0978f22db8 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -241,10 +241,10 @@ int main(int argc, char **argv)
while ((opt = getopt(argc, argv, "hp:t:r")) != -1) {
switch (opt) {
case 'p':
- reclaim_period_ms = atoi(optarg);
+ reclaim_period_ms = atoi_non_negative("Reclaim period", optarg);
break;
case 't':
- token = atoi(optarg);
+ token = atoi_paranoid(optarg);
break;
case 'r':
reboot_permissions = true;
@@ -257,7 +257,6 @@ int main(int argc, char **argv)
}
TEST_REQUIRE(kvm_has_cap(KVM_CAP_VM_DISABLE_NX_HUGE_PAGES));
- TEST_REQUIRE(reclaim_period_ms > 0);
__TEST_REQUIRE(token == MAGIC_TOKEN,
"This test must be run with the magic token %d.\n"
diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
index 76417c7d687b..310a104d94f0 100644
--- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c
+++ b/tools/testing/selftests/kvm/x86_64/platform_info_test.c
@@ -72,9 +72,6 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
uint64_t msr_platform_info;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
TEST_REQUIRE(kvm_has_cap(KVM_CAP_MSR_PLATFORM_INFO));
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index ea4e259a1e2e..2de98fce7edd 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -21,29 +21,6 @@
#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17)
#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22)
-union cpuid10_eax {
- struct {
- unsigned int version_id:8;
- unsigned int num_counters:8;
- unsigned int bit_width:8;
- unsigned int mask_length:8;
- } split;
- unsigned int full;
-};
-
-union cpuid10_ebx {
- struct {
- unsigned int no_unhalted_core_cycles:1;
- unsigned int no_instructions_retired:1;
- unsigned int no_unhalted_reference_cycles:1;
- unsigned int no_llc_reference:1;
- unsigned int no_llc_misses:1;
- unsigned int no_branch_instruction_retired:1;
- unsigned int no_branch_misses_retired:1;
- } split;
- unsigned int full;
-};
-
/* End of stuff taken from perf_event.h. */
/* Oddly, this isn't in perf_event.h. */
@@ -380,46 +357,31 @@ static void test_pmu_config_disable(void (*guest_code)(void))
}
/*
- * Check for a non-zero PMU version, at least one general-purpose
- * counter per logical processor, an EBX bit vector of length greater
- * than 5, and EBX[5] clear.
- */
-static bool check_intel_pmu_leaf(const struct kvm_cpuid_entry2 *entry)
-{
- union cpuid10_eax eax = { .full = entry->eax };
- union cpuid10_ebx ebx = { .full = entry->ebx };
-
- return eax.split.version_id && eax.split.num_counters > 0 &&
- eax.split.mask_length > ARCH_PERFMON_BRANCHES_RETIRED &&
- !ebx.split.no_branch_instruction_retired;
-}
-
-/*
- * Note that CPUID leaf 0xa is Intel-specific. This leaf should be
- * clear on AMD hardware.
+ * On Intel, check for a non-zero PMU version, at least one general-purpose
+ * counter per logical processor, and support for counting the number of branch
+ * instructions retired.
*/
static bool use_intel_pmu(void)
{
- const struct kvm_cpuid_entry2 *entry;
-
- entry = kvm_get_supported_cpuid_entry(0xa);
- return is_intel_cpu() && check_intel_pmu_leaf(entry);
+ return is_intel_cpu() &&
+ kvm_cpu_property(X86_PROPERTY_PMU_VERSION) &&
+ kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS) &&
+ kvm_pmu_has(X86_PMU_FEATURE_BRANCH_INSNS_RETIRED);
}
-static bool is_zen1(uint32_t eax)
+static bool is_zen1(uint32_t family, uint32_t model)
{
- return x86_family(eax) == 0x17 && x86_model(eax) <= 0x0f;
+ return family == 0x17 && model <= 0x0f;
}
-static bool is_zen2(uint32_t eax)
+static bool is_zen2(uint32_t family, uint32_t model)
{
- return x86_family(eax) == 0x17 &&
- x86_model(eax) >= 0x30 && x86_model(eax) <= 0x3f;
+ return family == 0x17 && model >= 0x30 && model <= 0x3f;
}
-static bool is_zen3(uint32_t eax)
+static bool is_zen3(uint32_t family, uint32_t model)
{
- return x86_family(eax) == 0x19 && x86_model(eax) <= 0x0f;
+ return family == 0x19 && model <= 0x0f;
}
/*
@@ -432,13 +394,13 @@ static bool is_zen3(uint32_t eax)
*/
static bool use_amd_pmu(void)
{
- const struct kvm_cpuid_entry2 *entry;
+ uint32_t family = kvm_cpu_family();
+ uint32_t model = kvm_cpu_model();
- entry = kvm_get_supported_cpuid_entry(1);
return is_amd_cpu() &&
- (is_zen1(entry->eax) ||
- is_zen2(entry->eax) ||
- is_zen3(entry->eax));
+ (is_zen1(family, model) ||
+ is_zen2(family, model) ||
+ is_zen3(family, model));
}
int main(int argc, char *argv[])
@@ -447,9 +409,6 @@ int main(int argc, char *argv[])
struct kvm_vcpu *vcpu;
struct kvm_vm *vm;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
TEST_REQUIRE(kvm_has_cap(KVM_CAP_PMU_EVENT_FILTER));
TEST_REQUIRE(use_intel_pmu() || use_amd_pmu());
diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
index 2bb08bf2125d..a284fcef6ed7 100644
--- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/set_sregs_test.c
@@ -82,9 +82,6 @@ int main(int argc, char *argv[])
uint64_t cr4;
int rc;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
/*
* Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and
* use it to verify all supported CR4 bits can be set prior to defining
diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
new file mode 100644
index 000000000000..06edf00a97d6
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Test that KVM emulates instructions in response to EPT violations when
+ * allow_smaller_maxphyaddr is enabled and guest.MAXPHYADDR < host.MAXPHYADDR.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+
+#include "flds_emulation.h"
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "vmx.h"
+
+#define MAXPHYADDR 36
+
+#define MEM_REGION_GVA 0x0000123456789000
+#define MEM_REGION_GPA 0x0000000700000000
+#define MEM_REGION_SLOT 10
+#define MEM_REGION_SIZE PAGE_SIZE
+
+static void guest_code(bool tdp_enabled)
+{
+ uint64_t error_code;
+ uint64_t vector;
+
+ vector = kvm_asm_safe_ec(FLDS_MEM_EAX, error_code, "a"(MEM_REGION_GVA));
+
+ /*
+ * When TDP is enabled, flds will trigger an emulation failure, exit to
+ * userspace, and then the selftest host "VMM" skips the instruction.
+ *
+ * When TDP is disabled, no instruction emulation is required so flds
+ * should generate #PF(RSVD).
+ */
+ if (tdp_enabled) {
+ GUEST_ASSERT(!vector);
+ } else {
+ GUEST_ASSERT_EQ(vector, PF_VECTOR);
+ GUEST_ASSERT(error_code & PFERR_RSVD_MASK);
+ }
+
+ GUEST_DONE();
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+ struct ucall uc;
+ uint64_t *pte;
+ uint64_t *hva;
+ uint64_t gpa;
+ int rc;
+
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_SMALLER_MAXPHYADDR));
+
+ vm = vm_create_with_one_vcpu(&vcpu, guest_code);
+ vcpu_args_set(vcpu, 1, kvm_is_tdp_enabled());
+
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vcpu);
+
+ vcpu_set_cpuid_maxphyaddr(vcpu, MAXPHYADDR);
+
+ rc = kvm_check_cap(KVM_CAP_EXIT_ON_EMULATION_FAILURE);
+ TEST_ASSERT(rc, "KVM_CAP_EXIT_ON_EMULATION_FAILURE is unavailable");
+ vm_enable_cap(vm, KVM_CAP_EXIT_ON_EMULATION_FAILURE, 1);
+
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ MEM_REGION_GPA, MEM_REGION_SLOT,
+ MEM_REGION_SIZE / PAGE_SIZE, 0);
+ gpa = vm_phy_pages_alloc(vm, MEM_REGION_SIZE / PAGE_SIZE,
+ MEM_REGION_GPA, MEM_REGION_SLOT);
+ TEST_ASSERT(gpa == MEM_REGION_GPA, "Failed vm_phy_pages_alloc\n");
+ virt_map(vm, MEM_REGION_GVA, MEM_REGION_GPA, 1);
+ hva = addr_gpa2hva(vm, MEM_REGION_GPA);
+ memset(hva, 0, PAGE_SIZE);
+
+ pte = vm_get_page_table_entry(vm, MEM_REGION_GVA);
+ *pte |= BIT_ULL(MAXPHYADDR);
+
+ vcpu_run(vcpu);
+
+ /*
+ * When TDP is enabled, KVM must emulate in response the guest physical
+ * address that is illegal from the guest's perspective, but is legal
+ * from hardware's perspeective. This should result in an emulation
+ * failure exit to userspace since KVM doesn't support emulating flds.
+ */
+ if (kvm_is_tdp_enabled()) {
+ handle_flds_emulation_failure_exit(vcpu);
+ vcpu_run(vcpu);
+ }
+
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ break;
+ case UCALL_DONE:
+ break;
+ default:
+ TEST_FAIL("Unrecognized ucall: %lu\n", uc.cmd);
+ }
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index 1f136a81858e..cb38a478e1f6 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -137,6 +137,8 @@ int main(int argc, char *argv[])
struct kvm_x86_state *state;
int stage, stage_reported;
+ TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_SMM));
+
/* Create VM */
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c
new file mode 100644
index 000000000000..e73fcdef47bb
--- /dev/null
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * svm_nested_shutdown_test
+ *
+ * Copyright (C) 2022, Red Hat, Inc.
+ *
+ * Nested SVM testing: test that unintercepted shutdown in L2 doesn't crash the host
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+#include "svm_util.h"
+
+static void l2_guest_code(struct svm_test_data *svm)
+{
+ __asm__ __volatile__("ud2");
+}
+
+static void l1_guest_code(struct svm_test_data *svm, struct idt_entry *idt)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ struct vmcb *vmcb = svm->vmcb;
+
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN));
+
+ idt[6].p = 0; // #UD is intercepted but its injection will cause #NP
+ idt[11].p = 0; // #NP is not intercepted and will cause another
+ // #NP that will be converted to #DF
+ idt[8].p = 0; // #DF will cause #NP which will cause SHUTDOWN
+
+ run_guest(vmcb, svm->vmcb_gpa);
+
+ /* should not reach here */
+ GUEST_ASSERT(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_run *run;
+ vm_vaddr_t svm_gva;
+ struct kvm_vm *vm;
+
+ TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
+
+ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vcpu);
+
+ vcpu_alloc_svm(vm, &svm_gva);
+
+ vcpu_args_set(vcpu, 2, svm_gva, vm->idt);
+ run = vcpu->run;
+
+ vcpu_run(vcpu);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+ "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ kvm_vm_free(vm);
+}
diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
index e637d7736012..e497ace629c1 100644
--- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
+++ b/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c
@@ -194,9 +194,6 @@ done:
int main(int argc, char *argv[])
{
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_SVM));
TEST_ASSERT(kvm_cpu_has(X86_FEATURE_NRIPS),
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 9b6db0b0b13e..d2f9b5bdfab2 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -90,9 +90,6 @@ int main(int argc, char *argv[])
struct kvm_vcpu_events events;
int rv, cap;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
TEST_REQUIRE((cap & TEST_SYNC_FIELDS) == TEST_SYNC_FIELDS);
TEST_REQUIRE(!(cap & INVALID_SYNC_FIELD));
diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
index 70b44f0b52fe..ead5d878a71c 100644
--- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
+++ b/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c
@@ -3,6 +3,7 @@
#include "kvm_util.h"
#include "processor.h"
#include "vmx.h"
+#include "svm_util.h"
#include <string.h>
#include <sys/ioctl.h>
@@ -20,10 +21,11 @@ static void l2_guest_code(void)
: : [port] "d" (ARBITRARY_IO_PORT) : "rax");
}
-void l1_guest_code(struct vmx_pages *vmx)
-{
#define L2_GUEST_STACK_SIZE 64
- unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+
+void l1_guest_code_vmx(struct vmx_pages *vmx)
+{
GUEST_ASSERT(vmx->vmcs_gpa);
GUEST_ASSERT(prepare_for_vmx_operation(vmx));
@@ -38,24 +40,53 @@ void l1_guest_code(struct vmx_pages *vmx)
GUEST_DONE();
}
+void l1_guest_code_svm(struct svm_test_data *svm)
+{
+ struct vmcb *vmcb = svm->vmcb;
+
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+
+ /* don't intercept shutdown to test the case of SVM allowing to do so */
+ vmcb->control.intercept &= ~(BIT(INTERCEPT_SHUTDOWN));
+
+ run_guest(vmcb, svm->vmcb_gpa);
+
+ /* should not reach here, L1 should crash */
+ GUEST_ASSERT(0);
+}
+
int main(void)
{
struct kvm_vcpu *vcpu;
struct kvm_run *run;
struct kvm_vcpu_events events;
- vm_vaddr_t vmx_pages_gva;
struct ucall uc;
- TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+ bool has_vmx = kvm_cpu_has(X86_FEATURE_VMX);
+ bool has_svm = kvm_cpu_has(X86_FEATURE_SVM);
+
+ TEST_REQUIRE(has_vmx || has_svm);
TEST_REQUIRE(kvm_has_cap(KVM_CAP_X86_TRIPLE_FAULT_EVENT));
- vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
- vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1);
+ if (has_vmx) {
+ vm_vaddr_t vmx_pages_gva;
+
+ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_vmx);
+ vcpu_alloc_vmx(vm, &vmx_pages_gva);
+ vcpu_args_set(vcpu, 1, vmx_pages_gva);
+ } else {
+ vm_vaddr_t svm_gva;
+
+ vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code_svm);
+ vcpu_alloc_svm(vm, &svm_gva);
+ vcpu_args_set(vcpu, 1, svm_gva);
+ }
+
+ vm_enable_cap(vm, KVM_CAP_X86_TRIPLE_FAULT_EVENT, 1);
run = vcpu->run;
- vcpu_alloc_vmx(vm, &vmx_pages_gva);
- vcpu_args_set(vcpu, 1, vmx_pages_gva);
vcpu_run(vcpu);
TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
@@ -78,13 +109,21 @@ int main(void)
"No triple fault pending");
vcpu_run(vcpu);
- switch (get_ucall(vcpu, &uc)) {
- case UCALL_DONE:
- break;
- case UCALL_ABORT:
- REPORT_GUEST_ASSERT(uc);
- default:
- TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
- }
+ if (has_svm) {
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_SHUTDOWN,
+ "Got exit_reason other than KVM_EXIT_SHUTDOWN: %u (%s)\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ } else {
+ switch (get_ucall(vcpu, &uc)) {
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ REPORT_GUEST_ASSERT(uc);
+ default:
+ TEST_FAIL("Unexpected ucall: %lu", uc.cmd);
+ }
+ }
+ return 0;
}
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
index 7316521428f8..91076c9787b4 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_io_test.c
@@ -56,9 +56,6 @@ int main(int argc, char *argv[])
struct kvm_vm *vm;
struct ucall uc;
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
-
vm = vm_create_with_one_vcpu(&vcpu, guest_code);
run = vcpu->run;
diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
index a4f06370a245..25fa55344a10 100644
--- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
+++ b/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c
@@ -733,16 +733,98 @@ static void test_msr_permission_bitmap(void)
kvm_vm_free(vm);
}
-int main(int argc, char *argv[])
+#define test_user_exit_msr_ioctl(vm, cmd, arg, flag, valid_mask) \
+({ \
+ int r = __vm_ioctl(vm, cmd, arg); \
+ \
+ if (flag & valid_mask) \
+ TEST_ASSERT(!r, __KVM_IOCTL_ERROR(#cmd, r)); \
+ else \
+ TEST_ASSERT(r == -1 && errno == EINVAL, \
+ "Wanted EINVAL for %s with flag = 0x%llx, got rc: %i errno: %i (%s)", \
+ #cmd, flag, r, errno, strerror(errno)); \
+})
+
+static void run_user_space_msr_flag_test(struct kvm_vm *vm)
{
- /* Tell stdout not to buffer its content */
- setbuf(stdout, NULL);
+ struct kvm_enable_cap cap = { .cap = KVM_CAP_X86_USER_SPACE_MSR };
+ int nflags = sizeof(cap.args[0]) * BITS_PER_BYTE;
+ int rc;
+ int i;
+
+ rc = kvm_check_cap(KVM_CAP_X86_USER_SPACE_MSR);
+ TEST_ASSERT(rc, "KVM_CAP_X86_USER_SPACE_MSR is available");
+
+ for (i = 0; i < nflags; i++) {
+ cap.args[0] = BIT_ULL(i);
+ test_user_exit_msr_ioctl(vm, KVM_ENABLE_CAP, &cap,
+ BIT_ULL(i), KVM_MSR_EXIT_REASON_VALID_MASK);
+ }
+}
+
+static void run_msr_filter_flag_test(struct kvm_vm *vm)
+{
+ u64 deny_bits = 0;
+ struct kvm_msr_filter filter = {
+ .flags = KVM_MSR_FILTER_DEFAULT_ALLOW,
+ .ranges = {
+ {
+ .flags = KVM_MSR_FILTER_READ,
+ .nmsrs = 1,
+ .base = 0,
+ .bitmap = (uint8_t *)&deny_bits,
+ },
+ },
+ };
+ int nflags;
+ int rc;
+ int i;
+
+ rc = kvm_check_cap(KVM_CAP_X86_MSR_FILTER);
+ TEST_ASSERT(rc, "KVM_CAP_X86_MSR_FILTER is available");
+
+ nflags = sizeof(filter.flags) * BITS_PER_BYTE;
+ for (i = 0; i < nflags; i++) {
+ filter.flags = BIT_ULL(i);
+ test_user_exit_msr_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter,
+ BIT_ULL(i), KVM_MSR_FILTER_VALID_MASK);
+ }
+ filter.flags = KVM_MSR_FILTER_DEFAULT_ALLOW;
+ nflags = sizeof(filter.ranges[0].flags) * BITS_PER_BYTE;
+ for (i = 0; i < nflags; i++) {
+ filter.ranges[0].flags = BIT_ULL(i);
+ test_user_exit_msr_ioctl(vm, KVM_X86_SET_MSR_FILTER, &filter,
+ BIT_ULL(i), KVM_MSR_FILTER_RANGE_VALID_MASK);
+ }
+}
+
+/* Test that attempts to write to the unused bits in a flag fails. */
+static void test_user_exit_msr_flags(void)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvm_vm *vm;
+
+ vm = vm_create_with_one_vcpu(&vcpu, NULL);
+
+ /* Test flags for KVM_CAP_X86_USER_SPACE_MSR. */
+ run_user_space_msr_flag_test(vm);
+
+ /* Test flags and range flags for KVM_X86_SET_MSR_FILTER. */
+ run_msr_filter_flag_test(vm);
+
+ kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
test_msr_filter_allow();
test_msr_filter_deny();
test_msr_permission_bitmap();
+ test_user_exit_msr_flags();
+
return 0;
}
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 2d8c23d639f7..f0456fb031b1 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -78,6 +78,7 @@ int main(int argc, char *argv[])
bool done = false;
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_VMX));
+ TEST_REQUIRE(kvm_cpu_has_ept());
/* Create VM */
vm = vm_create_with_one_vcpu(&vcpu, l1_guest_code);
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
index 069589c52f41..c280ba1e6572 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c
@@ -20,16 +20,6 @@
#define PMU_CAP_FW_WRITES (1ULL << 13)
#define PMU_CAP_LBR_FMT 0x3f
-union cpuid10_eax {
- struct {
- unsigned int version_id:8;
- unsigned int num_counters:8;
- unsigned int bit_width:8;
- unsigned int mask_length:8;
- } split;
- unsigned int full;
-};
-
union perf_capabilities {
struct {
u64 lbr_format:6;
@@ -53,11 +43,9 @@ static void guest_code(void)
int main(int argc, char *argv[])
{
- const struct kvm_cpuid_entry2 *entry_a_0;
struct kvm_vm *vm;
struct kvm_vcpu *vcpu;
int ret;
- union cpuid10_eax eax;
union perf_capabilities host_cap;
uint64_t val;
@@ -69,11 +57,8 @@ int main(int argc, char *argv[])
TEST_REQUIRE(kvm_cpu_has(X86_FEATURE_PDCM));
- TEST_REQUIRE(kvm_get_cpuid_max_basic() >= 0xa);
- entry_a_0 = kvm_get_supported_cpuid_entry(0xa);
-
- eax.full = entry_a_0->eax;
- __TEST_REQUIRE(eax.split.version_id, "PMU is not supported by the vCPU");
+ TEST_REQUIRE(kvm_cpu_has_p(X86_PROPERTY_PMU_VERSION));
+ TEST_REQUIRE(kvm_cpu_property(X86_PROPERTY_PMU_VERSION) > 0);
/* testcase 1, set capabilities when we have PDCM bit */
vcpu_set_msr(vcpu, MSR_IA32_PERF_CAPABILITIES, PMU_CAP_FW_WRITES);
diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
index 6f7a5ef66718..d7d37dae3eeb 100644
--- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xapic_state_test.c
@@ -114,7 +114,9 @@ static void test_icr(struct xapic_vcpu *x)
* vCPUs, not vcpu.id + 1. Arbitrarily use vector 0xff.
*/
icr = APIC_INT_ASSERT | 0xff;
- for (i = vcpu->id + 1; i < 0xff; i++) {
+ for (i = 0; i < 0xff; i++) {
+ if (i == vcpu->id)
+ continue;
for (j = 0; j < 8; j++)
__test_icr(x, i << (32 + 24) | icr | (j << 8));
}
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 8a5cb800f50e..2a5727188c8d 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -15,9 +15,13 @@
#include <time.h>
#include <sched.h>
#include <signal.h>
+#include <pthread.h>
#include <sys/eventfd.h>
+/* Defined in include/linux/kvm_types.h */
+#define GPA_INVALID (~(ulong)0)
+
#define SHINFO_REGION_GVA 0xc0000000ULL
#define SHINFO_REGION_GPA 0xc0000000ULL
#define SHINFO_REGION_SLOT 10
@@ -44,6 +48,8 @@
#define MIN_STEAL_TIME 50000
+#define SHINFO_RACE_TIMEOUT 2 /* seconds */
+
#define __HYPERVISOR_set_timer_op 15
#define __HYPERVISOR_sched_op 29
#define __HYPERVISOR_event_channel_op 32
@@ -126,7 +132,7 @@ struct {
struct kvm_irq_routing_entry entries[2];
} irq_routes;
-bool guest_saw_irq;
+static volatile bool guest_saw_irq;
static void evtchn_handler(struct ex_regs *regs)
{
@@ -148,6 +154,7 @@ static void guest_wait_for_irq(void)
static void guest_code(void)
{
struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
+ int i;
__asm__ __volatile__(
"sti\n"
@@ -325,6 +332,49 @@ static void guest_code(void)
guest_wait_for_irq();
GUEST_SYNC(21);
+ /* Racing host ioctls */
+
+ guest_wait_for_irq();
+
+ GUEST_SYNC(22);
+ /* Racing vmcall against host ioctl */
+
+ ports[0] = 0;
+
+ p = (struct sched_poll) {
+ .ports = ports,
+ .nr_ports = 1,
+ .timeout = 0
+ };
+
+wait_for_timer:
+ /*
+ * Poll for a timer wake event while the worker thread is mucking with
+ * the shared info. KVM XEN drops timer IRQs if the shared info is
+ * invalid when the timer expires. Arbitrarily poll 100 times before
+ * giving up and asking the VMM to re-arm the timer. 100 polls should
+ * consume enough time to beat on KVM without taking too long if the
+ * timer IRQ is dropped due to an invalid event channel.
+ */
+ for (i = 0; i < 100 && !guest_saw_irq; i++)
+ asm volatile("vmcall"
+ : "=a" (rax)
+ : "a" (__HYPERVISOR_sched_op),
+ "D" (SCHEDOP_poll),
+ "S" (&p)
+ : "memory");
+
+ /*
+ * Re-send the timer IRQ if it was (likely) dropped due to the timer
+ * expiring while the event channel was invalid.
+ */
+ if (!guest_saw_irq) {
+ GUEST_SYNC(23);
+ goto wait_for_timer;
+ }
+ guest_saw_irq = false;
+
+ GUEST_SYNC(24);
}
static int cmp_timespec(struct timespec *a, struct timespec *b)
@@ -352,11 +402,36 @@ static void handle_alrm(int sig)
TEST_FAIL("IRQ delivery timed out");
}
+static void *juggle_shinfo_state(void *arg)
+{
+ struct kvm_vm *vm = (struct kvm_vm *)arg;
+
+ struct kvm_xen_hvm_attr cache_init = {
+ .type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+ .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE
+ };
+
+ struct kvm_xen_hvm_attr cache_destroy = {
+ .type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
+ .u.shared_info.gfn = GPA_INVALID
+ };
+
+ for (;;) {
+ __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_init);
+ __vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &cache_destroy);
+ pthread_testcancel();
+ };
+
+ return NULL;
+}
+
int main(int argc, char *argv[])
{
struct timespec min_ts, max_ts, vm_ts;
struct kvm_vm *vm;
+ pthread_t thread;
bool verbose;
+ int ret;
verbose = argc > 1 && (!strncmp(argv[1], "-v", 3) ||
!strncmp(argv[1], "--verbose", 10));
@@ -785,6 +860,71 @@ int main(int argc, char *argv[])
case 21:
TEST_ASSERT(!evtchn_irq_expected,
"Expected event channel IRQ but it didn't happen");
+ alarm(0);
+
+ if (verbose)
+ printf("Testing shinfo lock corruption (KVM_XEN_HVM_EVTCHN_SEND)\n");
+
+ ret = pthread_create(&thread, NULL, &juggle_shinfo_state, (void *)vm);
+ TEST_ASSERT(ret == 0, "pthread_create() failed: %s", strerror(ret));
+
+ struct kvm_irq_routing_xen_evtchn uxe = {
+ .port = 1,
+ .vcpu = vcpu->id,
+ .priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL
+ };
+
+ evtchn_irq_expected = true;
+ for (time_t t = time(NULL) + SHINFO_RACE_TIMEOUT; time(NULL) < t;)
+ __vm_ioctl(vm, KVM_XEN_HVM_EVTCHN_SEND, &uxe);
+ break;
+
+ case 22:
+ TEST_ASSERT(!evtchn_irq_expected,
+ "Expected event channel IRQ but it didn't happen");
+
+ if (verbose)
+ printf("Testing shinfo lock corruption (SCHEDOP_poll)\n");
+
+ shinfo->evtchn_pending[0] = 1;
+
+ evtchn_irq_expected = true;
+ tmr.u.timer.expires_ns = rs->state_entry_time +
+ SHINFO_RACE_TIMEOUT * 1000000000ULL;
+ vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
+ break;
+
+ case 23:
+ /*
+ * Optional and possibly repeated sync point.
+ * Injecting the timer IRQ may fail if the
+ * shinfo is invalid when the timer expires.
+ * If the timer has expired but the IRQ hasn't
+ * been delivered, rearm the timer and retry.
+ */
+ vcpu_ioctl(vcpu, KVM_XEN_VCPU_GET_ATTR, &tmr);
+
+ /* Resume the guest if the timer is still pending. */
+ if (tmr.u.timer.expires_ns)
+ break;
+
+ /* All done if the IRQ was delivered. */
+ if (!evtchn_irq_expected)
+ break;
+
+ tmr.u.timer.expires_ns = rs->state_entry_time +
+ SHINFO_RACE_TIMEOUT * 1000000000ULL;
+ vcpu_ioctl(vcpu, KVM_XEN_VCPU_SET_ATTR, &tmr);
+ break;
+ case 24:
+ TEST_ASSERT(!evtchn_irq_expected,
+ "Expected event channel IRQ but it didn't happen");
+
+ ret = pthread_cancel(thread);
+ TEST_ASSERT(ret == 0, "pthread_cancel() failed: %s", strerror(ret));
+
+ ret = pthread_join(thread, 0);
+ TEST_ASSERT(ret == 0, "pthread_join() failed: %s", strerror(ret));
goto done;
case 0x20:
diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile
index 6632bfff486b..348e2dbdb4e0 100644
--- a/tools/testing/selftests/landlock/Makefile
+++ b/tools/testing/selftests/landlock/Makefile
@@ -3,7 +3,6 @@
# First run: make -C ../../../.. headers_install
CFLAGS += -Wall -O2 $(KHDR_INCLUDES)
-LDLIBS += -lcap
LOCAL_HDRS += common.h
@@ -13,10 +12,12 @@ TEST_GEN_PROGS := $(src_test:.c=)
TEST_GEN_PROGS_EXTENDED := true
-# Static linking for short targets:
+# Short targets:
+$(TEST_GEN_PROGS): LDLIBS += -lcap
$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static
include ../lib.mk
-# Static linking for targets with $(OUTPUT)/ prefix:
+# Targets with $(OUTPUT)/ prefix:
+$(TEST_GEN_PROGS): LDLIBS += -lcap
$(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 9d4cb94cf437..a3ea3d4a206d 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -70,7 +70,7 @@ endef
run_tests: all
ifdef building_out_of_srctree
@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then \
- rsync -aq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
+ rsync -aLq $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(OUTPUT); \
fi
@if [ "X$(TEST_PROGS)" != "X" ]; then \
$(call RUN_TESTS, $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) \
@@ -84,7 +84,7 @@ endif
define INSTALL_SINGLE_RULE
$(if $(INSTALL_LIST),@mkdir -p $(INSTALL_PATH))
- $(if $(INSTALL_LIST),rsync -a $(INSTALL_LIST) $(INSTALL_PATH)/)
+ $(if $(INSTALL_LIST),rsync -aL $(INSTALL_LIST) $(INSTALL_PATH)/)
endef
define INSTALL_RULE
diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
index 74ee5067a8ce..611be86eaf3d 100755
--- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
+++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
@@ -138,7 +138,6 @@ online_all_offline_memory()
{
for memory in `hotpluggable_offline_memory`; do
if ! online_memory_expect_success $memory; then
- echo "$FUNCNAME $memory: unexpected fail" >&2
retval=1
fi
done
diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile
new file mode 100644
index 000000000000..2f1508abc826
--- /dev/null
+++ b/tools/testing/selftests/net/openvswitch/Makefile
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+top_srcdir = ../../../../..
+
+CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES)
+
+TEST_PROGS := openvswitch.sh
+
+TEST_FILES := ovs-dpctl.py
+
+EXTRA_CLEAN := test_netlink_checks
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
new file mode 100755
index 000000000000..7ce46700a3ae
--- /dev/null
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -0,0 +1,218 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# OVS kernel module self tests
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+PAUSE_ON_FAIL=no
+VERBOSE=0
+TRACING=0
+
+tests="
+ netlink_checks ovsnl: validate netlink attrs and settings"
+
+info() {
+ [ $VERBOSE = 0 ] || echo $*
+}
+
+ovs_base=`pwd`
+sbxs=
+sbx_add () {
+ info "adding sandbox '$1'"
+
+ sbxs="$sbxs $1"
+
+ NO_BIN=0
+
+ # Create sandbox.
+ local d="$ovs_base"/$1
+ if [ -e $d ]; then
+ info "removing $d"
+ rm -rf "$d"
+ fi
+ mkdir "$d" || return 1
+ ovs_setenv $1
+}
+
+ovs_exit_sig() {
+ [ -e ${ovs_dir}/cleanup ] && . "$ovs_dir/cleanup"
+}
+
+on_exit() {
+ echo "$1" > ${ovs_dir}/cleanup.tmp
+ cat ${ovs_dir}/cleanup >> ${ovs_dir}/cleanup.tmp
+ mv ${ovs_dir}/cleanup.tmp ${ovs_dir}/cleanup
+}
+
+ovs_setenv() {
+ sandbox=$1
+
+ ovs_dir=$ovs_base${1:+/$1}; export ovs_dir
+
+ test -e ${ovs_dir}/cleanup || : > ${ovs_dir}/cleanup
+}
+
+ovs_sbx() {
+ if test "X$2" != X; then
+ (ovs_setenv $1; shift; "$@" >> ${ovs_dir}/debug.log)
+ else
+ ovs_setenv $1
+ fi
+}
+
+ovs_add_dp () {
+ info "Adding DP/Bridge IF: sbx:$1 dp:$2 {$3, $4, $5}"
+ sbxname="$1"
+ shift
+ ovs_sbx "$sbxname" python3 $ovs_base/ovs-dpctl.py add-dp $*
+ on_exit "ovs_sbx $sbxname python3 $ovs_base/ovs-dpctl.py del-dp $1;"
+}
+
+usage() {
+ echo
+ echo "$0 [OPTIONS] [TEST]..."
+ echo "If no TEST argument is given, all tests will be run."
+ echo
+ echo "Options"
+ echo " -t: capture traffic via tcpdump"
+ echo " -v: verbose"
+ echo " -p: pause on failure"
+ echo
+ echo "Available tests${tests}"
+ exit 1
+}
+
+# netlink_validation
+# - Create a dp
+# - check no warning with "old version" simulation
+test_netlink_checks () {
+ sbx_add "test_netlink_checks" || return 1
+
+ info "setting up new DP"
+ ovs_add_dp "test_netlink_checks" nv0 || return 1
+ # now try again
+ PRE_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+")
+ ovs_add_dp "test_netlink_checks" nv0 -V 0 || return 1
+ POST_TEST=$(dmesg | grep -E "RIP: [0-9a-fA-Fx]+:ovs_dp_cmd_new\+")
+ if [ "$PRE_TEST" != "$POST_TEST" ]; then
+ info "failed - gen warning"
+ return 1
+ fi
+
+ return 0
+}
+
+run_test() {
+ (
+ tname="$1"
+ tdesc="$2"
+
+ if ! lsmod | grep openvswitch >/dev/null 2>&1; then
+ stdbuf -o0 printf "TEST: %-60s [NOMOD]\n" "${tdesc}"
+ return $ksft_skip
+ fi
+
+ if python3 ovs-dpctl.py -h 2>&1 | \
+ grep "Need to install the python" >/dev/null 2>&1; then
+ stdbuf -o0 printf "TEST: %-60s [PYLIB]\n" "${tdesc}"
+ return $ksft_skip
+ fi
+ printf "TEST: %-60s [START]\n" "${tname}"
+
+ unset IFS
+
+ eval test_${tname}
+ ret=$?
+
+ if [ $ret -eq 0 ]; then
+ printf "TEST: %-60s [ OK ]\n" "${tdesc}"
+ ovs_exit_sig
+ rm -rf "$ovs_dir"
+ elif [ $ret -eq 1 ]; then
+ printf "TEST: %-60s [FAIL]\n" "${tdesc}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "Pausing. Logs in $ovs_dir/. Hit enter to continue"
+ read a
+ fi
+ ovs_exit_sig
+ [ "${PAUSE_ON_FAIL}" = "yes" ] || rm -rf "$ovs_dir"
+ exit 1
+ elif [ $ret -eq $ksft_skip ]; then
+ printf "TEST: %-60s [SKIP]\n" "${tdesc}"
+ elif [ $ret -eq 2 ]; then
+ rm -rf test_${tname}
+ run_test "$1" "$2"
+ fi
+
+ return $ret
+ )
+ ret=$?
+ case $ret in
+ 0)
+ [ $all_skipped = true ] && [ $exitcode=$ksft_skip ] && exitcode=0
+ all_skipped=false
+ ;;
+ $ksft_skip)
+ [ $all_skipped = true ] && exitcode=$ksft_skip
+ ;;
+ *)
+ all_skipped=false
+ exitcode=1
+ ;;
+ esac
+
+ return $ret
+}
+
+
+exitcode=0
+desc=0
+all_skipped=true
+
+while getopts :pvt o
+do
+ case $o in
+ p) PAUSE_ON_FAIL=yes;;
+ v) VERBOSE=1;;
+ t) if which tcpdump > /dev/null 2>&1; then
+ TRACING=1
+ else
+ echo "=== tcpdump not available, tracing disabled"
+ fi
+ ;;
+ *) usage;;
+ esac
+done
+shift $(($OPTIND-1))
+
+IFS="
+"
+
+for arg do
+ # Check first that all requested tests are available before running any
+ command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; }
+done
+
+name=""
+desc=""
+for t in ${tests}; do
+ [ "${name}" = "" ] && name="${t}" && continue
+ [ "${desc}" = "" ] && desc="${t}"
+
+ run_this=1
+ for arg do
+ [ "${arg}" != "${arg#--*}" ] && continue
+ [ "${arg}" = "${name}" ] && run_this=1 && break
+ run_this=0
+ done
+ if [ $run_this -eq 1 ]; then
+ run_test "${name}" "${desc}"
+ fi
+ name=""
+ desc=""
+done
+
+exit ${exitcode}
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
new file mode 100644
index 000000000000..3243c90d449e
--- /dev/null
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -0,0 +1,351 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+# Controls the openvswitch module. Part of the kselftest suite, but
+# can be used for some diagnostic purpose as well.
+
+import argparse
+import errno
+import sys
+
+try:
+ from pyroute2 import NDB
+
+ from pyroute2.netlink import NLM_F_ACK
+ from pyroute2.netlink import NLM_F_REQUEST
+ from pyroute2.netlink import genlmsg
+ from pyroute2.netlink import nla
+ from pyroute2.netlink.exceptions import NetlinkError
+ from pyroute2.netlink.generic import GenericNetlinkSocket
+except ModuleNotFoundError:
+ print("Need to install the python pyroute2 package.")
+ sys.exit(0)
+
+
+OVS_DATAPATH_FAMILY = "ovs_datapath"
+OVS_VPORT_FAMILY = "ovs_vport"
+OVS_FLOW_FAMILY = "ovs_flow"
+OVS_PACKET_FAMILY = "ovs_packet"
+OVS_METER_FAMILY = "ovs_meter"
+OVS_CT_LIMIT_FAMILY = "ovs_ct_limit"
+
+OVS_DATAPATH_VERSION = 2
+OVS_DP_CMD_NEW = 1
+OVS_DP_CMD_DEL = 2
+OVS_DP_CMD_GET = 3
+OVS_DP_CMD_SET = 4
+
+OVS_VPORT_CMD_NEW = 1
+OVS_VPORT_CMD_DEL = 2
+OVS_VPORT_CMD_GET = 3
+OVS_VPORT_CMD_SET = 4
+
+
+class ovs_dp_msg(genlmsg):
+ # include the OVS version
+ # We need a custom header rather than just being able to rely on
+ # genlmsg because fields ends up not expressing everything correctly
+ # if we use the canonical example of setting fields = (('customfield',),)
+ fields = genlmsg.fields + (("dpifindex", "I"),)
+
+
+class OvsDatapath(GenericNetlinkSocket):
+
+ OVS_DP_F_VPORT_PIDS = 1 << 1
+ OVS_DP_F_DISPATCH_UPCALL_PER_CPU = 1 << 3
+
+ class dp_cmd_msg(ovs_dp_msg):
+ """
+ Message class that will be used to communicate with the kernel module.
+ """
+
+ nla_map = (
+ ("OVS_DP_ATTR_UNSPEC", "none"),
+ ("OVS_DP_ATTR_NAME", "asciiz"),
+ ("OVS_DP_ATTR_UPCALL_PID", "uint32"),
+ ("OVS_DP_ATTR_STATS", "dpstats"),
+ ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"),
+ ("OVS_DP_ATTR_USER_FEATURES", "uint32"),
+ ("OVS_DP_ATTR_PAD", "none"),
+ ("OVS_DP_ATTR_MASKS_CACHE_SIZE", "uint32"),
+ ("OVS_DP_ATTR_PER_CPU_PIDS", "array(uint32)"),
+ )
+
+ class dpstats(nla):
+ fields = (
+ ("hit", "=Q"),
+ ("missed", "=Q"),
+ ("lost", "=Q"),
+ ("flows", "=Q"),
+ )
+
+ class megaflowstats(nla):
+ fields = (
+ ("mask_hit", "=Q"),
+ ("masks", "=I"),
+ ("padding", "=I"),
+ ("cache_hits", "=Q"),
+ ("pad1", "=Q"),
+ )
+
+ def __init__(self):
+ GenericNetlinkSocket.__init__(self)
+ self.bind(OVS_DATAPATH_FAMILY, OvsDatapath.dp_cmd_msg)
+
+ def info(self, dpname, ifindex=0):
+ msg = OvsDatapath.dp_cmd_msg()
+ msg["cmd"] = OVS_DP_CMD_GET
+ msg["version"] = OVS_DATAPATH_VERSION
+ msg["reserved"] = 0
+ msg["dpifindex"] = ifindex
+ msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname])
+
+ try:
+ reply = self.nlm_request(
+ msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST
+ )
+ reply = reply[0]
+ except NetlinkError as ne:
+ if ne.code == errno.ENODEV:
+ reply = None
+ else:
+ raise ne
+
+ return reply
+
+ def create(self, dpname, shouldUpcall=False, versionStr=None):
+ msg = OvsDatapath.dp_cmd_msg()
+ msg["cmd"] = OVS_DP_CMD_NEW
+ if versionStr is None:
+ msg["version"] = OVS_DATAPATH_VERSION
+ else:
+ msg["version"] = int(versionStr.split(":")[0], 0)
+ msg["reserved"] = 0
+ msg["dpifindex"] = 0
+ msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname])
+
+ dpfeatures = 0
+ if versionStr is not None and versionStr.find(":") != -1:
+ dpfeatures = int(versionStr.split(":")[1], 0)
+ else:
+ dpfeatures = OvsDatapath.OVS_DP_F_VPORT_PIDS
+
+ msg["attrs"].append(["OVS_DP_ATTR_USER_FEATURES", dpfeatures])
+ if not shouldUpcall:
+ msg["attrs"].append(["OVS_DP_ATTR_UPCALL_PID", 0])
+
+ try:
+ reply = self.nlm_request(
+ msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK
+ )
+ reply = reply[0]
+ except NetlinkError as ne:
+ if ne.code == errno.EEXIST:
+ reply = None
+ else:
+ raise ne
+
+ return reply
+
+ def destroy(self, dpname):
+ msg = OvsDatapath.dp_cmd_msg()
+ msg["cmd"] = OVS_DP_CMD_DEL
+ msg["version"] = OVS_DATAPATH_VERSION
+ msg["reserved"] = 0
+ msg["dpifindex"] = 0
+ msg["attrs"].append(["OVS_DP_ATTR_NAME", dpname])
+
+ try:
+ reply = self.nlm_request(
+ msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST | NLM_F_ACK
+ )
+ reply = reply[0]
+ except NetlinkError as ne:
+ if ne.code == errno.ENODEV:
+ reply = None
+ else:
+ raise ne
+
+ return reply
+
+
+class OvsVport(GenericNetlinkSocket):
+ class ovs_vport_msg(ovs_dp_msg):
+ nla_map = (
+ ("OVS_VPORT_ATTR_UNSPEC", "none"),
+ ("OVS_VPORT_ATTR_PORT_NO", "uint32"),
+ ("OVS_VPORT_ATTR_TYPE", "uint32"),
+ ("OVS_VPORT_ATTR_NAME", "asciiz"),
+ ("OVS_VPORT_ATTR_OPTIONS", "none"),
+ ("OVS_VPORT_ATTR_UPCALL_PID", "array(uint32)"),
+ ("OVS_VPORT_ATTR_STATS", "vportstats"),
+ ("OVS_VPORT_ATTR_PAD", "none"),
+ ("OVS_VPORT_ATTR_IFINDEX", "uint32"),
+ ("OVS_VPORT_ATTR_NETNSID", "uint32"),
+ )
+
+ class vportstats(nla):
+ fields = (
+ ("rx_packets", "=Q"),
+ ("tx_packets", "=Q"),
+ ("rx_bytes", "=Q"),
+ ("tx_bytes", "=Q"),
+ ("rx_errors", "=Q"),
+ ("tx_errors", "=Q"),
+ ("rx_dropped", "=Q"),
+ ("tx_dropped", "=Q"),
+ )
+
+ def type_to_str(vport_type):
+ if vport_type == 1:
+ return "netdev"
+ elif vport_type == 2:
+ return "internal"
+ elif vport_type == 3:
+ return "gre"
+ elif vport_type == 4:
+ return "vxlan"
+ elif vport_type == 5:
+ return "geneve"
+ return "unknown:%d" % vport_type
+
+ def __init__(self):
+ GenericNetlinkSocket.__init__(self)
+ self.bind(OVS_VPORT_FAMILY, OvsVport.ovs_vport_msg)
+
+ def info(self, vport_name, dpifindex=0, portno=None):
+ msg = OvsVport.ovs_vport_msg()
+
+ msg["cmd"] = OVS_VPORT_CMD_GET
+ msg["version"] = OVS_DATAPATH_VERSION
+ msg["reserved"] = 0
+ msg["dpifindex"] = dpifindex
+
+ if portno is None:
+ msg["attrs"].append(["OVS_VPORT_ATTR_NAME", vport_name])
+ else:
+ msg["attrs"].append(["OVS_VPORT_ATTR_PORT_NO", portno])
+
+ try:
+ reply = self.nlm_request(
+ msg, msg_type=self.prid, msg_flags=NLM_F_REQUEST
+ )
+ reply = reply[0]
+ except NetlinkError as ne:
+ if ne.code == errno.ENODEV:
+ reply = None
+ else:
+ raise ne
+ return reply
+
+
+def print_ovsdp_full(dp_lookup_rep, ifindex, ndb=NDB()):
+ dp_name = dp_lookup_rep.get_attr("OVS_DP_ATTR_NAME")
+ base_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_STATS")
+ megaflow_stats = dp_lookup_rep.get_attr("OVS_DP_ATTR_MEGAFLOW_STATS")
+ user_features = dp_lookup_rep.get_attr("OVS_DP_ATTR_USER_FEATURES")
+ masks_cache_size = dp_lookup_rep.get_attr("OVS_DP_ATTR_MASKS_CACHE_SIZE")
+
+ print("%s:" % dp_name)
+ print(
+ " lookups: hit:%d missed:%d lost:%d"
+ % (base_stats["hit"], base_stats["missed"], base_stats["lost"])
+ )
+ print(" flows:%d" % base_stats["flows"])
+ pkts = base_stats["hit"] + base_stats["missed"]
+ avg = (megaflow_stats["mask_hit"] / pkts) if pkts != 0 else 0.0
+ print(
+ " masks: hit:%d total:%d hit/pkt:%f"
+ % (megaflow_stats["mask_hit"], megaflow_stats["masks"], avg)
+ )
+ print(" caches:")
+ print(" masks-cache: size:%d" % masks_cache_size)
+
+ if user_features is not None:
+ print(" features: 0x%X" % user_features)
+
+ # port print out
+ vpl = OvsVport()
+ for iface in ndb.interfaces:
+ rep = vpl.info(iface.ifname, ifindex)
+ if rep is not None:
+ print(
+ " port %d: %s (%s)"
+ % (
+ rep.get_attr("OVS_VPORT_ATTR_PORT_NO"),
+ rep.get_attr("OVS_VPORT_ATTR_NAME"),
+ OvsVport.type_to_str(rep.get_attr("OVS_VPORT_ATTR_TYPE")),
+ )
+ )
+
+
+def main(argv):
+ parser = argparse.ArgumentParser()
+ parser.add_argument(
+ "-v",
+ "--verbose",
+ action="count",
+ help="Increment 'verbose' output counter.",
+ )
+ subparsers = parser.add_subparsers()
+
+ showdpcmd = subparsers.add_parser("show")
+ showdpcmd.add_argument(
+ "showdp", metavar="N", type=str, nargs="?", help="Datapath Name"
+ )
+
+ adddpcmd = subparsers.add_parser("add-dp")
+ adddpcmd.add_argument("adddp", help="Datapath Name")
+ adddpcmd.add_argument(
+ "-u",
+ "--upcall",
+ action="store_true",
+ help="Leave open a reader for upcalls",
+ )
+ adddpcmd.add_argument(
+ "-V",
+ "--versioning",
+ required=False,
+ help="Specify a custom version / feature string",
+ )
+
+ deldpcmd = subparsers.add_parser("del-dp")
+ deldpcmd.add_argument("deldp", help="Datapath Name")
+
+ args = parser.parse_args()
+
+ ovsdp = OvsDatapath()
+ ndb = NDB()
+
+ if hasattr(args, "showdp"):
+ found = False
+ for iface in ndb.interfaces:
+ rep = None
+ if args.showdp is None:
+ rep = ovsdp.info(iface.ifname, 0)
+ elif args.showdp == iface.ifname:
+ rep = ovsdp.info(iface.ifname, 0)
+
+ if rep is not None:
+ found = True
+ print_ovsdp_full(rep, iface.index, ndb)
+
+ if not found:
+ msg = "No DP found"
+ if args.showdp is not None:
+ msg += ":'%s'" % args.showdp
+ print(msg)
+ elif hasattr(args, "adddp"):
+ rep = ovsdp.create(args.adddp, args.upcall, args.versioning)
+ if rep is None:
+ print("DP '%s' already exists" % args.adddp)
+ else:
+ print("DP '%s' added" % args.adddp)
+ elif hasattr(args, "deldp"):
+ ovsdp.destroy(args.deldp)
+
+ return 0
+
+
+if __name__ == "__main__":
+ sys.exit(main(sys.argv))
diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile
index f4a2f28f926b..778b6cdc8aed 100644
--- a/tools/testing/selftests/pidfd/Makefile
+++ b/tools/testing/selftests/pidfd/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
-CFLAGS += -g -I../../../../usr/include/ -pthread
+CFLAGS += -g -I../../../../usr/include/ -pthread -Wall
TEST_GEN_PROGS := pidfd_test pidfd_fdinfo_test pidfd_open_test \
pidfd_poll_test pidfd_wait pidfd_getfd_test pidfd_setns_test
diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c
index 9a2d64901d59..e2dd4ed84984 100644
--- a/tools/testing/selftests/pidfd/pidfd_test.c
+++ b/tools/testing/selftests/pidfd/pidfd_test.c
@@ -413,7 +413,7 @@ static void poll_pidfd(const char *test_name, int pidfd)
c = epoll_wait(epoll_fd, events, MAX_EVENTS, 5000);
if (c != 1 || !(events[0].events & EPOLLIN))
- ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) ",
+ ksft_exit_fail_msg("%s test: Unexpected epoll_wait result (c=%d, events=%x) "
"(errno %d)\n",
test_name, c, events[0].events, errno);
@@ -435,6 +435,8 @@ static int child_poll_exec_test(void *args)
*/
while (1)
sleep(1);
+
+ return 0;
}
static void test_pidfd_poll_exec(int use_waitpid)
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index 070c1c876df1..0dcb8365ddc3 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -95,20 +95,28 @@ TEST(wait_states)
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
.exit_signal = SIGCHLD,
};
+ int pfd[2];
pid_t pid;
siginfo_t info = {
.si_signo = 0,
};
+ ASSERT_EQ(pipe(pfd), 0);
pid = sys_clone3(&args);
ASSERT_GE(pid, 0);
if (pid == 0) {
+ char buf[2];
+
+ close(pfd[1]);
kill(getpid(), SIGSTOP);
+ ASSERT_EQ(read(pfd[0], buf, 1), 1);
+ close(pfd[0]);
kill(getpid(), SIGSTOP);
exit(EXIT_SUCCESS);
}
+ close(pfd[0]);
ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL), 0);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_STOPPED);
@@ -117,6 +125,8 @@ TEST(wait_states)
ASSERT_EQ(sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0), 0);
ASSERT_EQ(sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL), 0);
+ ASSERT_EQ(write(pfd[1], "C", 1), 1);
+ close(pfd[1]);
ASSERT_EQ(info.si_signo, SIGCHLD);
ASSERT_EQ(info.si_code, CLD_CONTINUED);
ASSERT_EQ(info.si_pid, parent_tid);
@@ -138,7 +148,7 @@ TEST(wait_states)
TEST(wait_nonblock)
{
- int pidfd, status = 0;
+ int pidfd;
unsigned int flags = 0;
pid_t parent_tid = -1;
struct clone_args args = {
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 58e4f88b2b9f..1e567d1f6d3d 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -17,7 +17,6 @@
#include <linux/srcu.h>
#include <linux/export.h>
#include <trace/events/kvm.h>
-#include "irq.h"
int kvm_irq_map_gsi(struct kvm *kvm,
struct kvm_kernel_irq_routing_entry *entries, int gsi)
@@ -50,7 +49,7 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
{
struct kvm_kernel_irq_routing_entry route;
- if (!irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
+ if (!kvm_arch_irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
return -EINVAL;
route.msi.address_lo = msi->address_lo;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1376a47fedee..1782c4555d94 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1641,6 +1641,8 @@ static void kvm_commit_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
+ int old_flags = old ? old->flags : 0;
+ int new_flags = new ? new->flags : 0;
/*
* Update the total number of memslot pages before calling the arch
* hook so that architectures can consume the result directly.
@@ -1650,6 +1652,12 @@ static void kvm_commit_memory_region(struct kvm *kvm,
else if (change == KVM_MR_CREATE)
kvm->nr_memslot_pages += new->npages;
+ if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) {
+ int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1;
+ atomic_set(&kvm->nr_memslots_dirty_logging,
+ atomic_read(&kvm->nr_memslots_dirty_logging) + change);
+ }
+
kvm_arch_commit_memory_region(kvm, old, new, change);
switch (change) {
@@ -2514,7 +2522,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
* 1 indicates success, -errno is returned if error is detected.
*/
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
- bool *writable, kvm_pfn_t *pfn)
+ bool interruptible, bool *writable, kvm_pfn_t *pfn)
{
unsigned int flags = FOLL_HWPOISON;
struct page *page;
@@ -2529,6 +2537,8 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
flags |= FOLL_WRITE;
if (async)
flags |= FOLL_NOWAIT;
+ if (interruptible)
+ flags |= FOLL_INTERRUPTIBLE;
npages = get_user_pages_unlocked(addr, 1, &page, flags);
if (npages != 1)
@@ -2638,6 +2648,7 @@ out:
* Pin guest page in memory and return its pfn.
* @addr: host virtual address which maps memory to the guest
* @atomic: whether this function can sleep
+ * @interruptible: whether the process can be interrupted by non-fatal signals
* @async: whether this function need to wait IO complete if the
* host page is not in the memory
* @write_fault: whether we should get a writable host page
@@ -2648,8 +2659,8 @@ out:
* 2): @write_fault = false && @writable, @writable will tell the caller
* whether the mapping is writable.
*/
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable)
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+ bool *async, bool write_fault, bool *writable)
{
struct vm_area_struct *vma;
kvm_pfn_t pfn;
@@ -2664,9 +2675,12 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
if (atomic)
return KVM_PFN_ERR_FAULT;
- npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+ npages = hva_to_pfn_slow(addr, async, write_fault, interruptible,
+ writable, &pfn);
if (npages == 1)
return pfn;
+ if (npages == -EINTR)
+ return KVM_PFN_ERR_SIGPENDING;
mmap_read_lock(current->mm);
if (npages == -EHWPOISON ||
@@ -2697,8 +2711,8 @@ exit:
}
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool atomic, bool *async, bool write_fault,
- bool *writable, hva_t *hva)
+ bool atomic, bool interruptible, bool *async,
+ bool write_fault, bool *writable, hva_t *hva)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
@@ -2723,7 +2737,7 @@ kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
writable = NULL;
}
- return hva_to_pfn(addr, atomic, async, write_fault,
+ return hva_to_pfn(addr, atomic, interruptible, async, write_fault,
writable);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
@@ -2731,20 +2745,22 @@ EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
- return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
- write_fault, writable, NULL);
+ return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false,
+ NULL, write_fault, writable, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+ return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true,
+ NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
+ return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true,
+ NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
@@ -4585,6 +4601,9 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
}
case KVM_CAP_DIRTY_LOG_RING:
case KVM_CAP_DIRTY_LOG_RING_ACQ_REL:
+ if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap))
+ return -EINVAL;
+
return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
default:
return kvm_vm_ioctl_enable_cap(kvm, cap);
@@ -5409,6 +5428,7 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
int (*get)(void *, u64 *), int (*set)(void *, u64),
const char *fmt)
{
+ int ret;
struct kvm_stat_data *stat_data = (struct kvm_stat_data *)
inode->i_private;
@@ -5420,15 +5440,13 @@ static int kvm_debugfs_open(struct inode *inode, struct file *file,
if (!kvm_get_kvm_safe(stat_data->kvm))
return -ENOENT;
- if (simple_attr_open(inode, file, get,
- kvm_stats_debugfs_mode(stat_data->desc) & 0222
- ? set : NULL,
- fmt)) {
+ ret = simple_attr_open(inode, file, get,
+ kvm_stats_debugfs_mode(stat_data->desc) & 0222
+ ? set : NULL, fmt);
+ if (ret)
kvm_put_kvm(stat_data->kvm);
- return -ENOMEM;
- }
- return 0;
+ return ret;
}
static int kvm_debugfs_release(struct inode *inode, struct file *file)
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 41da467d99c9..a1ab15006af3 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -24,8 +24,8 @@
#define KVM_MMU_READ_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
#endif /* KVM_HAVE_MMU_RWLOCK */
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable);
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+ bool *async, bool write_fault, bool *writable);
#ifdef CONFIG_HAVE_KVM_PFNCACHE
void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 68ff41d39545..5f83321bfd2a 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -81,6 +81,9 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
{
struct kvm_memslots *slots = kvm_memslots(kvm);
+ if (!gpc->active)
+ return false;
+
if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE)
return false;
@@ -182,7 +185,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
}
/* We always request a writeable mapping */
- new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
+ new_pfn = hva_to_pfn(gpc->uhva, false, false, NULL, true, NULL);
if (is_error_noslot_pfn(new_pfn))
goto out_error;
@@ -240,10 +243,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
{
struct kvm_memslots *slots = kvm_memslots(kvm);
unsigned long page_offset = gpa & ~PAGE_MASK;
- kvm_pfn_t old_pfn, new_pfn;
+ bool unmap_old = false;
unsigned long old_uhva;
+ kvm_pfn_t old_pfn;
void *old_khva;
- int ret = 0;
+ int ret;
/*
* If must fit within a single page. The 'len' argument is
@@ -261,6 +265,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
write_lock_irq(&gpc->lock);
+ if (!gpc->active) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
old_pfn = gpc->pfn;
old_khva = gpc->khva - offset_in_page(gpc->khva);
old_uhva = gpc->uhva;
@@ -288,9 +297,15 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
if (!gpc->valid || old_uhva != gpc->uhva) {
ret = hva_to_pfn_retry(kvm, gpc);
} else {
- /* If the HVA→PFN mapping was already valid, don't unmap it. */
+ /*
+ * If the HVA→PFN mapping was already valid, don't unmap it.
+ * But do update gpc->khva because the offset within the page
+ * may have changed.
+ */
+ gpc->khva = old_khva + page_offset;
old_pfn = KVM_PFN_ERR_FAULT;
old_khva = NULL;
+ ret = 0;
}
out:
@@ -305,14 +320,15 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
gpc->khva = NULL;
}
- /* Snapshot the new pfn before dropping the lock! */
- new_pfn = gpc->pfn;
+ /* Detect a pfn change before dropping the lock! */
+ unmap_old = (old_pfn != gpc->pfn);
+out_unlock:
write_unlock_irq(&gpc->lock);
mutex_unlock(&gpc->refresh_lock);
- if (old_pfn != new_pfn)
+ if (unmap_old)
gpc_unmap_khva(kvm, old_pfn, old_khva);
return ret;
@@ -346,42 +362,61 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap);
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc)
+{
+ rwlock_init(&gpc->lock);
+ mutex_init(&gpc->refresh_lock);
+}
+EXPORT_SYMBOL_GPL(kvm_gpc_init);
-int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
- struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
- gpa_t gpa, unsigned long len)
+int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+ struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+ gpa_t gpa, unsigned long len)
{
WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
if (!gpc->active) {
- rwlock_init(&gpc->lock);
- mutex_init(&gpc->refresh_lock);
-
gpc->khva = NULL;
gpc->pfn = KVM_PFN_ERR_FAULT;
gpc->uhva = KVM_HVA_ERR_BAD;
gpc->vcpu = vcpu;
gpc->usage = usage;
gpc->valid = false;
- gpc->active = true;
spin_lock(&kvm->gpc_lock);
list_add(&gpc->list, &kvm->gpc_list);
spin_unlock(&kvm->gpc_lock);
+
+ /*
+ * Activate the cache after adding it to the list, a concurrent
+ * refresh must not establish a mapping until the cache is
+ * reachable by mmu_notifier events.
+ */
+ write_lock_irq(&gpc->lock);
+ gpc->active = true;
+ write_unlock_irq(&gpc->lock);
}
return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len);
}
-EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_init);
+EXPORT_SYMBOL_GPL(kvm_gpc_activate);
-void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
{
if (gpc->active) {
+ /*
+ * Deactivate the cache before removing it from the list, KVM
+ * must stall mmu_notifier events until all users go away, i.e.
+ * until gpc->lock is dropped and refresh is guaranteed to fail.
+ */
+ write_lock_irq(&gpc->lock);
+ gpc->active = false;
+ write_unlock_irq(&gpc->lock);
+
spin_lock(&kvm->gpc_lock);
list_del(&gpc->list);
spin_unlock(&kvm->gpc_lock);
kvm_gfn_to_pfn_cache_unmap(kvm, gpc);
- gpc->active = false;
}
}
-EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_destroy);
+EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);