summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--.mailmap13
-rw-r--r--CREDITS5
-rw-r--r--Documentation/admin-guide/cifs/usage.rst2
-rw-r--r--Documentation/arch/arm64/booting.rst2
-rw-r--r--Documentation/block/ublk.rst77
-rw-r--r--Documentation/bpf/bpf_devel_QA.rst7
-rw-r--r--Documentation/bpf/map_hash.rst8
-rw-r--r--Documentation/bpf/map_lru_hash_update.dot6
-rw-r--r--Documentation/bpf/standardization/instruction-set.rst6
-rw-r--r--Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml24
-rw-r--r--Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml2
-rw-r--r--Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml2
-rw-r--r--Documentation/devicetree/bindings/pmem/pmem-region.txt65
-rw-r--r--Documentation/devicetree/bindings/pmem/pmem-region.yaml48
-rw-r--r--Documentation/filesystems/porting.rst9
-rw-r--r--Documentation/filesystems/proc.rst4
-rw-r--r--Documentation/gpu/nouveau.rst2
-rw-r--r--Documentation/netlink/genetlink-legacy.yaml15
-rw-r--r--Documentation/netlink/genetlink.yaml17
-rw-r--r--Documentation/netlink/netlink-raw.yaml18
-rw-r--r--Documentation/netlink/specs/devlink.yaml8
-rw-r--r--Documentation/netlink/specs/dpll.yaml2
-rw-r--r--Documentation/netlink/specs/ethtool.yaml9
-rw-r--r--Documentation/netlink/specs/fou.yaml36
-rw-r--r--Documentation/netlink/specs/mptcp_pm.yaml8
-rw-r--r--Documentation/netlink/specs/nfsd.yaml4
-rw-r--r--Documentation/netlink/specs/ovs_flow.yaml6
-rw-r--r--Documentation/netlink/specs/rt-link.yaml4
-rw-r--r--Documentation/netlink/specs/tc.yaml4
-rw-r--r--Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst2
-rw-r--r--Documentation/process/embargoed-hardware-issues.rst1
-rw-r--r--Documentation/sound/codecs/cs35l56.rst24
-rw-r--r--Documentation/virt/kvm/api.rst59
-rw-r--r--MAINTAINERS116
-rw-r--r--Makefile5
-rw-r--r--arch/alpha/include/asm/pgtable.h2
-rw-r--r--arch/arc/include/asm/arcregs.h2
-rw-r--r--arch/arc/include/asm/atomic.h4
-rw-r--r--arch/arc/include/asm/atomic64-arcv2.h15
-rw-r--r--arch/arc/include/asm/bitops.h4
-rw-r--r--arch/arc/include/asm/bug.h4
-rw-r--r--arch/arc/include/asm/cache.h4
-rw-r--r--arch/arc/include/asm/current.h4
-rw-r--r--arch/arc/include/asm/dsp-impl.h2
-rw-r--r--arch/arc/include/asm/dsp.h4
-rw-r--r--arch/arc/include/asm/dwarf.h4
-rw-r--r--arch/arc/include/asm/entry.h4
-rw-r--r--arch/arc/include/asm/irqflags-arcv2.h4
-rw-r--r--arch/arc/include/asm/irqflags-compact.h4
-rw-r--r--arch/arc/include/asm/jump_label.h4
-rw-r--r--arch/arc/include/asm/linkage.h6
-rw-r--r--arch/arc/include/asm/mmu-arcv2.h4
-rw-r--r--arch/arc/include/asm/mmu.h2
-rw-r--r--arch/arc/include/asm/page.h4
-rw-r--r--arch/arc/include/asm/pgtable-bits-arcv2.h6
-rw-r--r--arch/arc/include/asm/pgtable-levels.h4
-rw-r--r--arch/arc/include/asm/pgtable.h4
-rw-r--r--arch/arc/include/asm/processor.h4
-rw-r--r--arch/arc/include/asm/ptrace.h4
-rw-r--r--arch/arc/include/asm/switch_to.h2
-rw-r--r--arch/arc/include/asm/thread_info.h4
-rw-r--r--arch/arc/include/uapi/asm/ptrace.h4
-rw-r--r--arch/arc/kernel/unwind.c11
-rw-r--r--arch/arm/include/asm/pgtable.h2
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h62
-rw-r--r--arch/arm64/include/asm/kvm_host.h38
-rw-r--r--arch/arm64/include/asm/pgtable.h2
-rw-r--r--arch/arm64/kernel/process.c4
-rw-r--r--arch/arm64/kernel/ptrace.c2
-rw-r--r--arch/arm64/kvm/arch_timer.c18
-rw-r--r--arch/arm64/kvm/arm.c3
-rw-r--r--arch/arm64/kvm/debug.c4
-rw-r--r--arch/arm64/kvm/fpsimd.c4
-rw-r--r--arch/arm64/kvm/hyp/exception.c4
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h151
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h6
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c9
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c59
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c111
-rw-r--r--arch/arm64/kvm/hyp/vhe/sysreg-sr.c48
-rw-r--r--arch/arm64/kvm/nested.c2
-rw-r--r--arch/arm64/kvm/pmu-emul.c24
-rw-r--r--arch/arm64/kvm/sys_regs.c60
-rw-r--r--arch/arm64/kvm/sys_regs.h4
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3-nested.c91
-rw-r--r--arch/arm64/lib/crypto/poly1305-glue.c4
-rw-r--r--arch/arm64/mm/mmu.c3
-rw-r--r--arch/arm64/net/bpf_jit.h5
-rw-r--r--arch/arm64/net/bpf_jit_comp.c28
-rw-r--r--arch/csky/include/asm/pgtable.h2
-rw-r--r--arch/hexagon/include/asm/pgtable.h2
-rw-r--r--arch/loongarch/include/asm/pgtable.h2
-rw-r--r--arch/m68k/include/asm/mcf_pgtable.h2
-rw-r--r--arch/m68k/include/asm/motorola_pgtable.h2
-rw-r--r--arch/m68k/include/asm/sun3_pgtable.h2
-rw-r--r--arch/microblaze/include/asm/pgtable.h2
-rw-r--r--arch/mips/include/asm/pgtable.h4
-rw-r--r--arch/nios2/include/asm/pgtable.h2
-rw-r--r--arch/openrisc/include/asm/pgtable.h2
-rw-r--r--arch/parisc/include/asm/pgtable.h2
-rw-r--r--arch/powerpc/boot/dts/microwatt.dts2
-rw-r--r--arch/powerpc/boot/dts/mpc8315erdb.dts10
-rw-r--r--arch/powerpc/include/asm/book3s/32/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/book3s/64/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/nohash/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/ppc_asm.h2
-rw-r--r--arch/powerpc/include/uapi/asm/ioctls.h8
-rw-r--r--arch/powerpc/kernel/eeh.c2
-rw-r--r--arch/powerpc/kernel/vdso/Makefile2
-rw-r--r--arch/powerpc/net/bpf_jit_comp64.c79
-rw-r--r--arch/powerpc/platforms/book3s/vas-api.c9
-rw-r--r--arch/powerpc/platforms/powernv/memtrace.c8
-rw-r--r--arch/riscv/include/asm/pgtable.h2
-rw-r--r--arch/riscv/kvm/vcpu_sbi_replace.c8
-rw-r--r--arch/s390/include/asm/pgtable.h2
-rw-r--r--arch/sh/include/asm/pgtable_32.h2
-rw-r--r--arch/sparc/include/asm/pgtable_32.h2
-rw-r--r--arch/sparc/include/asm/pgtable_64.h2
-rw-r--r--arch/um/drivers/ubd_user.c2
-rw-r--r--arch/um/drivers/vector_kern.c42
-rw-r--r--arch/um/drivers/vfio_kern.c14
-rw-r--r--arch/um/include/asm/pgtable.h2
-rw-r--r--arch/x86/Kconfig2
-rw-r--r--arch/x86/events/intel/core.c2
-rw-r--r--arch/x86/include/asm/module.h8
-rw-r--r--arch/x86/include/asm/pgtable.h2
-rw-r--r--arch/x86/include/asm/shared/tdx.h1
-rw-r--r--arch/x86/include/asm/sighandling.h22
-rw-r--r--arch/x86/include/asm/tdx.h2
-rw-r--r--arch/x86/kernel/alternative.c81
-rw-r--r--arch/x86/kernel/cpu/amd.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c6
-rw-r--r--arch/x86/kernel/signal_32.c4
-rw-r--r--arch/x86/kernel/signal_64.c4
-rw-r--r--arch/x86/kernel/smp.c24
-rw-r--r--arch/x86/kernel/smpboot.c54
-rw-r--r--arch/x86/kvm/mmu/mmu.c9
-rw-r--r--arch/x86/kvm/svm/sev.c44
-rw-r--r--arch/x86/kvm/vmx/tdx.c83
-rw-r--r--arch/x86/mm/init_32.c3
-rw-r--r--arch/x86/mm/init_64.c3
-rw-r--r--arch/x86/mm/pat/set_memory.c3
-rw-r--r--arch/x86/mm/pti.c5
-rw-r--r--arch/x86/power/hibernate.c19
-rw-r--r--arch/x86/um/ptrace.c2
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.c5
-rw-r--r--arch/xtensa/include/asm/pgtable.h2
-rw-r--r--block/blk-merge.c26
-rw-r--r--block/blk-zoned.c8
-rw-r--r--crypto/Kconfig25
-rw-r--r--crypto/ahash.c4
-rw-r--r--crypto/hkdf.c2
-rw-r--r--crypto/testmgr.c15
-rw-r--r--drivers/accel/amdxdna/aie2_psp.c4
-rw-r--r--drivers/acpi/acpi_pad.c2
-rw-r--r--drivers/acpi/acpica/dsmethod.c7
-rw-r--r--drivers/acpi/apei/einj-core.c9
-rw-r--r--drivers/acpi/cppc_acpi.c2
-rw-r--r--drivers/acpi/ec.c17
-rw-r--r--drivers/acpi/internal.h6
-rw-r--r--drivers/acpi/processor_driver.c3
-rw-r--r--drivers/acpi/processor_idle.c8
-rw-r--r--drivers/acpi/resource.c7
-rw-r--r--drivers/ata/ahci.c39
-rw-r--r--drivers/ata/libata-acpi.c24
-rw-r--r--drivers/ata/pata_cs5536.c2
-rw-r--r--drivers/ata/pata_macio.c2
-rw-r--r--drivers/ata/pata_via.c9
-rw-r--r--drivers/atm/atmtcp.c4
-rw-r--r--drivers/atm/idt77252.c5
-rw-r--r--drivers/base/faux.c3
-rw-r--r--drivers/block/aoe/aoe.h1
-rw-r--r--drivers/block/aoe/aoecmd.c8
-rw-r--r--drivers/block/aoe/aoedev.c13
-rw-r--r--drivers/block/loop.c11
-rw-r--r--drivers/block/ublk_drv.c3
-rw-r--r--drivers/bluetooth/btintel_pcie.c64
-rw-r--r--drivers/bluetooth/btintel_pcie.h10
-rw-r--r--drivers/bluetooth/hci_qca.c13
-rw-r--r--drivers/cpufreq/rcpufreq_dt.rs4
-rw-r--r--drivers/dma-buf/dma-buf.c2
-rw-r--r--drivers/dma-buf/udmabuf.c5
-rw-r--r--drivers/edac/amd64_edac.c1
-rw-r--r--drivers/edac/igen6_edac.c24
-rw-r--r--drivers/gpio/gpio-loongson-64bit.c2
-rw-r--r--drivers/gpio/gpio-mlxbf3.c54
-rw-r--r--drivers/gpio/gpio-pca953x.c2
-rw-r--r--drivers/gpio/gpio-spacemit-k1.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c82
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c30
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_job.c12
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_job.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c16
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h16
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c17
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h6
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c5
-rw-r--r--drivers/gpu/drm/amd/amdgpu/imu_v11_0.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_v13_0.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c6
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c2
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_topology.c6
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c55
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc.c33
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc.h8
-rw-r--r--drivers/gpu/drm/amd/display/dc/dc_dp_types.h4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c5
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c28
-rw-r--r--drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c38
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c3
-rw-r--r--drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c3
-rw-r--r--drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c12
-rw-r--r--drivers/gpu/drm/arm/malidp_planes.c2
-rw-r--r--drivers/gpu/drm/ast/ast_mode.c1
-rw-r--r--drivers/gpu/drm/etnaviv/etnaviv_sched.c5
-rw-r--r--drivers/gpu/drm/i915/display/vlv_dsi.c4
-rw-r--r--drivers/gpu/drm/i915/i915_pmu.c4
-rw-r--r--drivers/gpu/drm/meson/meson_encoder_hdmi.c2
-rw-r--r--drivers/gpu/drm/meson/meson_vclk.c55
-rw-r--r--drivers/gpu/drm/mgag200/mgag200_ddc.c1
-rw-r--r--drivers/gpu/drm/msm/adreno/a2xx_gpummu.c5
-rw-r--r--drivers/gpu/drm/msm/adreno/a5xx_gpu.c2
-rw-r--r--drivers/gpu/drm/msm/adreno/a6xx_gpu.c18
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_device.c39
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.c54
-rw-r--r--drivers/gpu/drm/msm/adreno/adreno_gpu.h2
-rw-r--r--drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c14
-rw-r--r--drivers/gpu/drm/msm/dp/dp_display.c7
-rw-r--r--drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c7
-rw-r--r--drivers/gpu/drm/msm/msm_debugfs.c32
-rw-r--r--drivers/gpu/drm/msm/msm_drv.c10
-rw-r--r--drivers/gpu/drm/msm/msm_drv.h23
-rw-r--r--drivers/gpu/drm/msm/msm_gem_submit.c17
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.c20
-rw-r--r--drivers/gpu/drm/msm/msm_gpu.h9
-rw-r--r--drivers/gpu/drm/msm/msm_iommu.c12
-rw-r--r--drivers/gpu/drm/msm/msm_mmu.h2
-rw-r--r--drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml3
-rw-r--r--drivers/gpu/drm/msm/registers/gen_header.py8
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_backlight.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c17
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c2
-rw-r--r--drivers/gpu/drm/sitronix/Kconfig1
-rw-r--r--drivers/gpu/drm/solomon/ssd130x.c2
-rw-r--r--drivers/gpu/drm/v3d/v3d_sched.c8
-rw-r--r--drivers/gpu/drm/vc4/vc4_hdmi.c12
-rw-r--r--drivers/gpu/drm/xe/xe_gt.c2
-rw-r--r--drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c8
-rw-r--r--drivers/gpu/drm/xe/xe_guc_ct.c7
-rw-r--r--drivers/gpu/drm/xe/xe_guc_ct.h5
-rw-r--r--drivers/gpu/drm/xe/xe_guc_pc.c2
-rw-r--r--drivers/gpu/drm/xe/xe_guc_submit.c3
-rw-r--r--drivers/gpu/drm/xe/xe_lrc.c24
-rw-r--r--drivers/gpu/drm/xe/xe_svm.c2
-rw-r--r--drivers/hwmon/ftsteutates.c9
-rw-r--r--drivers/hwmon/ltc4282.c7
-rw-r--r--drivers/hwmon/occ/common.c240
-rw-r--r--drivers/i2c/algos/i2c-algo-bit.c4
-rw-r--r--drivers/i2c/algos/i2c-algo-pca.c4
-rw-r--r--drivers/i2c/algos/i2c-algo-pcf.c4
-rw-r--r--drivers/i2c/busses/i2c-amd-mp2-plat.c2
-rw-r--r--drivers/i2c/busses/i2c-aspeed.c8
-rw-r--r--drivers/i2c/busses/i2c-at91-master.c4
-rw-r--r--drivers/i2c/busses/i2c-axxia.c2
-rw-r--r--drivers/i2c/busses/i2c-bcm-iproc.c2
-rw-r--r--drivers/i2c/busses/i2c-cadence.c10
-rw-r--r--drivers/i2c/busses/i2c-cgbc.c4
-rw-r--r--drivers/i2c/busses/i2c-eg20t.c2
-rw-r--r--drivers/i2c/busses/i2c-emev2.c6
-rw-r--r--drivers/i2c/busses/i2c-exynos5.c6
-rw-r--r--drivers/i2c/busses/i2c-gxp.c6
-rw-r--r--drivers/i2c/busses/i2c-img-scb.c2
-rw-r--r--drivers/i2c/busses/i2c-imx-lpi2c.c8
-rw-r--r--drivers/i2c/busses/i2c-imx.c8
-rw-r--r--drivers/i2c/busses/i2c-k1.c2
-rw-r--r--drivers/i2c/busses/i2c-keba.c2
-rw-r--r--drivers/i2c/busses/i2c-mchp-pci1xxxx.c2
-rw-r--r--drivers/i2c/busses/i2c-meson.c4
-rw-r--r--drivers/i2c/busses/i2c-microchip-corei2c.c2
-rw-r--r--drivers/i2c/busses/i2c-mt65xx.c2
-rw-r--r--drivers/i2c/busses/i2c-mxs.c2
-rw-r--r--drivers/i2c/busses/i2c-nomadik.c4
-rw-r--r--drivers/i2c/busses/i2c-npcm7xx.c6
-rw-r--r--drivers/i2c/busses/i2c-omap.c6
-rw-r--r--drivers/i2c/busses/i2c-pnx.c2
-rw-r--r--drivers/i2c/busses/i2c-pxa.c16
-rw-r--r--drivers/i2c/busses/i2c-qcom-cci.c4
-rw-r--r--drivers/i2c/busses/i2c-qcom-geni.c4
-rw-r--r--drivers/i2c/busses/i2c-qup.c8
-rw-r--r--drivers/i2c/busses/i2c-rcar.c10
-rw-r--r--drivers/i2c/busses/i2c-s3c2410.c6
-rw-r--r--drivers/i2c/busses/i2c-sh7760.c4
-rw-r--r--drivers/i2c/busses/i2c-sh_mobile.c4
-rw-r--r--drivers/i2c/busses/i2c-stm32f7.c4
-rw-r--r--drivers/i2c/busses/i2c-synquacer.c4
-rw-r--r--drivers/i2c/busses/i2c-tegra.c6
-rw-r--r--drivers/i2c/busses/i2c-xiic.c4
-rw-r--r--drivers/i2c/busses/i2c-xlp9xx.c2
-rw-r--r--drivers/i2c/i2c-atr.c2
-rw-r--r--drivers/i2c/i2c-mux.c6
-rw-r--r--drivers/i2c/muxes/i2c-demux-pinctrl.c4
-rw-r--r--drivers/idle/intel_idle.c12
-rw-r--r--drivers/iommu/tegra-smmu.c4
-rw-r--r--drivers/irqchip/irq-ath79-misc.c20
-rw-r--r--drivers/md/bcache/Kconfig1
-rw-r--r--drivers/md/bcache/alloc.c57
-rw-r--r--drivers/md/bcache/bcache.h2
-rw-r--r--drivers/md/bcache/bset.c116
-rw-r--r--drivers/md/bcache/bset.h40
-rw-r--r--drivers/md/bcache/btree.c69
-rw-r--r--drivers/md/bcache/extents.c45
-rw-r--r--drivers/md/bcache/movinggc.c33
-rw-r--r--drivers/md/bcache/super.c3
-rw-r--r--drivers/md/bcache/sysfs.c4
-rw-r--r--drivers/md/bcache/util.h67
-rw-r--r--drivers/md/bcache/writeback.c13
-rw-r--r--drivers/md/dm-crypt.c11
-rw-r--r--drivers/md/dm-raid.c2
-rw-r--r--drivers/mtd/mtdchar.c2
-rw-r--r--drivers/mtd/mtdcore.c152
-rw-r--r--drivers/mtd/mtdcore.h2
-rw-r--r--drivers/mtd/mtdpart.c16
-rw-r--r--drivers/mtd/nand/spi/core.c1
-rw-r--r--drivers/mtd/nand/spi/winbond.c10
-rw-r--r--drivers/net/can/m_can/tcan4x5x-core.c9
-rw-r--r--drivers/net/dsa/b53/b53_common.c6
-rw-r--r--drivers/net/ethernet/airoha/airoha_eth.c27
-rw-r--r--drivers/net/ethernet/airoha/airoha_ppe.c4
-rw-r--r--drivers/net/ethernet/airoha/airoha_regs.h3
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt.c92
-rw-r--r--drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c24
-rw-r--r--drivers/net/ethernet/faraday/Kconfig1
-rw-r--r--drivers/net/ethernet/freescale/enetc/Kconfig6
-rw-r--r--drivers/net/ethernet/freescale/enetc/enetc_hw.h2
-rw-r--r--drivers/net/ethernet/intel/e1000/e1000_main.c8
-rw-r--r--drivers/net/ethernet/intel/e1000e/netdev.c14
-rw-r--r--drivers/net/ethernet/intel/e1000e/ptp.c8
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c11
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_main.c11
-rw-r--r--drivers/net/ethernet/intel/iavf/iavf_virtchnl.c17
-rw-r--r--drivers/net/ethernet/intel/ice/ice_arfs.c48
-rw-r--r--drivers/net/ethernet/intel/ice/ice_eswitch.c6
-rw-r--r--drivers/net/ethernet/intel/ice/ice_ptp.c1
-rw-r--r--drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c4
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c12
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.c21
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/fs_core.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c14
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c19
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h1
-rw-r--r--drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c6
-rw-r--r--drivers/net/ethernet/meta/fbnic/fbnic_fw.c5
-rw-r--r--drivers/net/ethernet/microchip/lan743x_ptp.h4
-rw-r--r--drivers/net/ethernet/microsoft/mana/gdma_main.c3
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_main.c3
-rw-r--r--drivers/net/ethernet/pensando/ionic/ionic_txrx.c12
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c8
-rw-r--r--drivers/net/ethernet/ti/icssg/icssg_common.c19
-rw-r--r--drivers/net/ethernet/wangxun/libwx/wx_lib.c2
-rw-r--r--drivers/net/macsec.c40
-rw-r--r--drivers/net/netconsole.c3
-rw-r--r--drivers/net/netdevsim/netdev.c3
-rw-r--r--drivers/net/phy/mdio_bus.c12
-rw-r--r--drivers/net/phy/phy_caps.c18
-rw-r--r--drivers/net/usb/qmi_wwan.c1
-rw-r--r--drivers/net/usb/r8152.c1
-rw-r--r--drivers/net/veth.c4
-rw-r--r--drivers/net/wireless/ath/ath10k/mac.c33
-rw-r--r--drivers/net/wireless/ath/ath10k/snoc.c4
-rw-r--r--drivers/net/wireless/ath/ath11k/core.c29
-rw-r--r--drivers/net/wireless/ath/ath11k/core.h4
-rw-r--r--drivers/net/wireless/ath/ath11k/debugfs.c148
-rw-r--r--drivers/net/wireless/ath/ath11k/debugfs.h10
-rw-r--r--drivers/net/wireless/ath/ath11k/mac.c127
-rw-r--r--drivers/net/wireless/ath/ath11k/mac.h4
-rw-r--r--drivers/net/wireless/ath/ath11k/wmi.c49
-rw-r--r--drivers/net/wireless/ath/ath12k/core.c14
-rw-r--r--drivers/net/wireless/ath/ath12k/core.h10
-rw-r--r--drivers/net/wireless/ath/ath12k/debugfs.c58
-rw-r--r--drivers/net/wireless/ath/ath12k/debugfs.h7
-rw-r--r--drivers/net/wireless/ath/ath12k/hal.h3
-rw-r--r--drivers/net/wireless/ath/ath12k/hw.c6
-rw-r--r--drivers/net/wireless/ath/ath12k/hw.h2
-rw-r--r--drivers/net/wireless/ath/ath12k/mac.c394
-rw-r--r--drivers/net/wireless/ath/ath12k/mac.h2
-rw-r--r--drivers/net/wireless/ath/ath12k/pci.c6
-rw-r--r--drivers/net/wireless/ath/ath12k/pci.h4
-rw-r--r--drivers/net/wireless/ath/ath12k/wmi.c829
-rw-r--r--drivers/net/wireless/ath/ath12k/wmi.h180
-rw-r--r--drivers/net/wireless/ath/ath6kl/bmi.c4
-rw-r--r--drivers/net/wireless/ath/carl9170/usb.c19
-rw-r--r--drivers/net/wireless/ath/wil6210/interrupt.c26
-rw-r--r--drivers/net/wireless/intel/iwlegacy/4965-rs.c3
-rw-r--r--drivers/net/wireless/intel/iwlwifi/dvm/main.c1
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mld/mld.c1
-rw-r--r--drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c4
-rw-r--r--drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c11
-rw-r--r--drivers/net/wireless/intel/iwlwifi/pcie/drv.c24
-rw-r--r--drivers/net/wireless/marvell/mwifiex/11n.c6
-rw-r--r--drivers/nvme/host/ioctl.c21
-rw-r--r--drivers/pci/hotplug/pciehp_hpc.c2
-rw-r--r--drivers/pci/pci.c5
-rw-r--r--drivers/pinctrl/pinctrl-st.c5
-rw-r--r--drivers/pinctrl/pinctrl-tb10x.c2
-rw-r--r--drivers/pinctrl/qcom/pinctrl-apq8064.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-apq8084.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq4019.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq5018.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq5332.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq5424.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq6018.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq8064.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq8074.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-ipq9574.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-mdm9607.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-mdm9615.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm.c11
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm.h1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8226.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8660.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8909.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8916.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8917.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8953.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8960.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8976.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8994.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8996.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8998.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-msm8x74.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qcm2290.c10
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qcs404.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qcs615.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qcs8300.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qdf2xxx.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-qdu1000.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sa8775p.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sar2130p.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sc7180.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sc7280.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sc8180x.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sc8280xp.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdm660.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdm670.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdm845.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdx55.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdx65.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sdx75.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm4450.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm6115.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm6125.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm6350.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm6375.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm7150.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8150.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8250.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8350.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8450.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8550.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8650.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-sm8750.c1
-rw-r--r--drivers/pinctrl/qcom/pinctrl-x1e80100.c1
-rw-r--r--drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c8
-rw-r--r--drivers/platform/x86/amd/hsmp/hsmp.c14
-rw-r--r--drivers/platform/x86/amd/pmc/pmc-quirks.c9
-rw-r--r--drivers/platform/x86/amd/pmc/pmc.c2
-rw-r--r--drivers/platform/x86/amd/pmf/core.c3
-rw-r--r--drivers/platform/x86/amd/pmf/tee-if.c108
-rw-r--r--drivers/platform/x86/dell/alienware-wmi-wmax.c2
-rw-r--r--drivers/platform/x86/dell/dell_rbu.c10
-rw-r--r--drivers/platform/x86/ideapad-laptop.c19
-rw-r--r--drivers/platform/x86/intel/pmc/core.h7
-rw-r--r--drivers/platform/x86/intel/pmc/ssram_telemetry.c3
-rw-r--r--drivers/platform/x86/intel/tpmi_power_domains.c4
-rw-r--r--drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c2
-rw-r--r--drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c9
-rw-r--r--drivers/platform/x86/samsung-galaxybook.c1
-rw-r--r--drivers/ptp/ptp_clock.c3
-rw-r--r--drivers/ptp/ptp_private.h12
-rw-r--r--drivers/rapidio/rio_cm.c3
-rw-r--r--drivers/regulator/fan53555.c14
-rw-r--r--drivers/regulator/max20086-regulator.c6
-rw-r--r--drivers/s390/scsi/zfcp_sysfs.c2
-rw-r--r--drivers/scsi/elx/efct/efct_hw.c5
-rw-r--r--drivers/scsi/fnic/fdls_disc.c187
-rw-r--r--drivers/scsi/fnic/fnic.h2
-rw-r--r--drivers/scsi/fnic/fnic_fcs.c2
-rw-r--r--drivers/scsi/fnic/fnic_fdls.h1
-rw-r--r--drivers/scsi/fnic/fnic_scsi.c2
-rw-r--r--drivers/scsi/megaraid/megaraid_sas_base.c6
-rw-r--r--drivers/scsi/mvsas/mv_defs.h4
-rw-r--r--drivers/scsi/scsi_error.c3
-rw-r--r--drivers/scsi/scsi_transport_iscsi.c11
-rw-r--r--drivers/scsi/storvsc_drv.c10
-rw-r--r--drivers/spi/spi-cadence-quadspi.c12
-rw-r--r--drivers/spi/spi-loongson-core.c1
-rw-r--r--drivers/spi/spi-offload.c2
-rw-r--r--drivers/spi/spi-omap2-mcspi.c30
-rw-r--r--drivers/spi/spi-pci1xxxx.c4
-rw-r--r--drivers/spi/spi-stm32-ospi.c24
-rw-r--r--drivers/spi/spi-tegra210-quad.c14
-rw-r--r--drivers/target/target_core_pr.c4
-rw-r--r--drivers/ufs/core/ufshcd.c10
-rw-r--r--fs/bcachefs/bcachefs.h1
-rw-r--r--fs/bcachefs/btree_gc.c95
-rw-r--r--fs/bcachefs/btree_io.c26
-rw-r--r--fs/bcachefs/btree_locking.c2
-rw-r--r--fs/bcachefs/btree_locking.h6
-rw-r--r--fs/bcachefs/btree_types.h29
-rw-r--r--fs/bcachefs/btree_update_interior.c33
-rw-r--r--fs/bcachefs/btree_update_interior.h7
-rw-r--r--fs/bcachefs/chardev.c4
-rw-r--r--fs/bcachefs/disk_accounting.c4
-rw-r--r--fs/bcachefs/error.c5
-rw-r--r--fs/bcachefs/fs.c8
-rw-r--r--fs/bcachefs/io_read.c11
-rw-r--r--fs/bcachefs/io_read.h1
-rw-r--r--fs/bcachefs/movinggc.c22
-rw-r--r--fs/bcachefs/namei.c10
-rw-r--r--fs/bcachefs/rcu_pending.c22
-rw-r--r--fs/bcachefs/recovery.c27
-rw-r--r--fs/bcachefs/recovery_passes.c14
-rw-r--r--fs/bcachefs/sb-downgrade.c5
-rw-r--r--fs/bcachefs/sb-errors_format.h10
-rw-r--r--fs/bcachefs/sb-members.c34
-rw-r--r--fs/bcachefs/super.c47
-rw-r--r--fs/bcachefs/util.c10
-rw-r--r--fs/bcachefs/util.h2
-rw-r--r--fs/btrfs/delayed-inode.c5
-rw-r--r--fs/btrfs/disk-io.c27
-rw-r--r--fs/btrfs/extent_io.c2
-rw-r--r--fs/btrfs/free-space-tree.c16
-rw-r--r--fs/btrfs/inode.c87
-rw-r--r--fs/btrfs/ioctl.c2
-rw-r--r--fs/btrfs/scrub.c53
-rw-r--r--fs/btrfs/tree-log.c17
-rw-r--r--fs/btrfs/volumes.c6
-rw-r--r--fs/btrfs/zoned.c86
-rw-r--r--fs/erofs/fileio.c3
-rw-r--r--fs/erofs/zmap.c10
-rw-r--r--fs/f2fs/file.c38
-rw-r--r--fs/f2fs/node.c1
-rw-r--r--fs/file.c8
-rw-r--r--fs/namei.c17
-rw-r--r--fs/namespace.c115
-rw-r--r--fs/nfsd/nfs4callback.c1
-rw-r--r--fs/nfsd/nfsctl.c5
-rw-r--r--fs/overlayfs/namei.c10
-rw-r--r--fs/overlayfs/overlayfs.h8
-rw-r--r--fs/pidfs.c2
-rw-r--r--fs/pnode.h2
-rw-r--r--fs/resctrl/ctrlmondata.c13
-rw-r--r--fs/resctrl/internal.h4
-rw-r--r--fs/resctrl/monitor.c6
-rw-r--r--fs/resctrl/rdtgroup.c6
-rw-r--r--fs/smb/client/cached_dir.c14
-rw-r--r--fs/smb/client/cached_dir.h10
-rw-r--r--fs/smb/client/cifs_debug.c2
-rw-r--r--fs/smb/client/cifs_ioctl.h2
-rw-r--r--fs/smb/client/connect.c11
-rw-r--r--fs/smb/client/file.c17
-rw-r--r--fs/smb/client/ioctl.c2
-rw-r--r--fs/smb/client/readdir.c28
-rw-r--r--fs/smb/client/reparse.c1
-rw-r--r--fs/smb/client/sess.c3
-rw-r--r--fs/smb/client/smbdirect.c5
-rw-r--r--fs/smb/server/connection.c2
-rw-r--r--fs/smb/server/connection.h1
-rw-r--r--fs/smb/server/smb2pdu.c74
-rw-r--r--fs/smb/server/transport_rdma.c10
-rw-r--r--fs/smb/server/transport_tcp.c3
-rw-r--r--fs/smb/server/vfs.c5
-rw-r--r--fs/smb/server/vfs_cache.h1
-rw-r--r--fs/super.c4
-rw-r--r--fs/xattr.c1
-rw-r--r--include/crypto/hash.h2
-rw-r--r--include/crypto/internal/simd.h6
-rw-r--r--include/crypto/md5.h4
-rw-r--r--include/linux/atmdev.h6
-rw-r--r--include/linux/bio.h2
-rw-r--r--include/linux/bpf-cgroup-defs.h1
-rw-r--r--include/linux/bpf.h11
-rw-r--r--include/linux/bpf_verifier.h80
-rw-r--r--include/linux/btf.h2
-rw-r--r--include/linux/bvec.h7
-rw-r--r--include/linux/cpu.h3
-rw-r--r--include/linux/execmem.h8
-rw-r--r--include/linux/filter.h2
-rw-r--r--include/linux/fs.h10
-rw-r--r--include/linux/ieee80211.h18
-rw-r--r--include/linux/key.h2
-rw-r--r--include/linux/libata.h7
-rw-r--r--include/linux/module.h5
-rw-r--r--include/linux/mount.h6
-rw-r--r--include/linux/mtd/partitions.h2
-rw-r--r--include/linux/mtd/spinand.h10
-rw-r--r--include/linux/perf_event.h42
-rw-r--r--include/linux/resctrl.h4
-rw-r--r--include/linux/scatterlist.h4
-rw-r--r--include/linux/tnum.h2
-rw-r--r--include/linux/uaccess.h2
-rw-r--r--include/net/bluetooth/hci_core.h13
-rw-r--r--include/net/bluetooth/hci_sync.h4
-rw-r--r--include/net/sch_generic.h8
-rw-r--r--include/net/sock.h7
-rw-r--r--include/trace/events/erofs.h18
-rw-r--r--include/uapi/linux/bpf.h13
-rw-r--r--include/uapi/linux/ethtool_netlink.h4
-rw-r--r--include/uapi/linux/ethtool_netlink_generated.h4
-rw-r--r--include/uapi/linux/kvm.h22
-rw-r--r--include/uapi/linux/mptcp_pm.h6
-rw-r--r--include/uapi/linux/vm_sockets.h4
-rw-r--r--init/initramfs.c1
-rw-r--r--init/main.c1
-rw-r--r--io_uring/fdinfo.c12
-rw-r--r--io_uring/io-wq.c4
-rw-r--r--io_uring/io_uring.c7
-rw-r--r--io_uring/io_uring.h2
-rw-r--r--io_uring/kbuf.c5
-rw-r--r--io_uring/net.c2
-rw-r--r--io_uring/register.c7
-rw-r--r--io_uring/rsrc.c8
-rw-r--r--io_uring/sqpoll.c49
-rw-r--r--io_uring/sqpoll.h8
-rw-r--r--kernel/audit_tree.c63
-rw-r--r--kernel/bpf/arraymap.c11
-rw-r--r--kernel/bpf/bpf_iter.c11
-rw-r--r--kernel/bpf/bpf_local_storage.c8
-rw-r--r--kernel/bpf/bpf_lru_list.c9
-rw-r--r--kernel/bpf/bpf_lru_list.h1
-rw-r--r--kernel/bpf/btf.c56
-rw-r--r--kernel/bpf/cgroup.c184
-rw-r--r--kernel/bpf/core.c32
-rw-r--r--kernel/bpf/helpers.c382
-rw-r--r--kernel/bpf/local_storage.c9
-rw-r--r--kernel/bpf/syscall.c180
-rw-r--r--kernel/bpf/tnum.c5
-rw-r--r--kernel/bpf/trampoline.c41
-rw-r--r--kernel/bpf/verifier.c1790
-rw-r--r--kernel/cgroup/cgroup.c5
-rw-r--r--kernel/cgroup/legacy_freezer.c3
-rw-r--r--kernel/events/core.c116
-rw-r--r--kernel/exit.c17
-rw-r--r--kernel/futex/core.c14
-rw-r--r--kernel/irq/chip.c8
-rw-r--r--kernel/irq/cpuhotplug.c7
-rw-r--r--kernel/irq/irq_sim.c2
-rw-r--r--kernel/kexec_handover.c29
-rw-r--r--kernel/rcu/tree.c4
-rw-r--r--kernel/sched/core.c4
-rw-r--r--kernel/sched/ext.c17
-rw-r--r--kernel/sched/ext.h2
-rw-r--r--kernel/time/posix-cpu-timers.c9
-rw-r--r--kernel/trace/bpf_trace.c2
-rw-r--r--kernel/trace/trace_events_filter.c4
-rw-r--r--kernel/trace/trace_functions_graph.c6
-rw-r--r--kernel/workqueue.c3
-rw-r--r--lib/Kconfig1
-rw-r--r--lib/crypto/Makefile6
-rw-r--r--lib/crypto/aescfb.c8
-rw-r--r--lib/crypto/aesgcm.c46
-rw-r--r--lib/maple_tree.c4
-rw-r--r--lib/scatterlist.c8
-rw-r--r--mm/damon/Kconfig1
-rw-r--r--mm/execmem.c40
-rw-r--r--mm/gup.c14
-rw-r--r--mm/madvise.c2
-rw-r--r--mm/memory.c20
-rw-r--r--mm/shmem.c6
-rw-r--r--mm/swap.h23
-rw-r--r--mm/userfaultfd.c33
-rw-r--r--mm/util.c40
-rw-r--r--mm/vma.c23
-rw-r--r--mm/vma.h47
-rw-r--r--net/atm/clip.c11
-rw-r--r--net/atm/common.c1
-rw-r--r--net/atm/lec.c12
-rw-r--r--net/atm/raw.c2
-rw-r--r--net/atm/resources.c3
-rw-r--r--net/bluetooth/eir.c17
-rw-r--r--net/bluetooth/eir.h2
-rw-r--r--net/bluetooth/hci_conn.c31
-rw-r--r--net/bluetooth/hci_core.c66
-rw-r--r--net/bluetooth/hci_sync.c45
-rw-r--r--net/bluetooth/iso.c17
-rw-r--r--net/bluetooth/l2cap_core.c9
-rw-r--r--net/bluetooth/mgmt.c140
-rw-r--r--net/bluetooth/mgmt_util.c32
-rw-r--r--net/bluetooth/mgmt_util.h4
-rw-r--r--net/bpf/test_run.c2
-rw-r--r--net/bridge/br_multicast.c9
-rw-r--r--net/core/filter.c19
-rw-r--r--net/core/netpoll.c2
-rw-r--r--net/core/selftests.c5
-rw-r--r--net/core/skbuff.c3
-rw-r--r--net/ethtool/ioctl.c3
-rw-r--r--net/ipv4/tcp_fastopen.c3
-rw-r--r--net/ipv4/tcp_input.c37
-rw-r--r--net/ipv6/calipso.c8
-rw-r--r--net/ipv6/route.c110
-rw-r--r--net/mac80211/debug.h5
-rw-r--r--net/mac80211/link.c6
-rw-r--r--net/mac80211/rx.c4
-rw-r--r--net/mac80211/tx.c29
-rw-r--r--net/mac80211/util.c2
-rw-r--r--net/mpls/af_mpls.c4
-rw-r--r--net/nfc/nci/uart.c8
-rw-r--r--net/openvswitch/actions.c23
-rw-r--r--net/openvswitch/datapath.c42
-rw-r--r--net/openvswitch/datapath.h3
-rw-r--r--net/sched/sch_ets.c2
-rw-r--r--net/sched/sch_prio.c2
-rw-r--r--net/sched/sch_red.c2
-rw-r--r--net/sched/sch_sfq.c15
-rw-r--r--net/sched/sch_taprio.c6
-rw-r--r--net/sched/sch_tbf.c2
-rw-r--r--net/sunrpc/svc.c17
-rw-r--r--net/tipc/udp_media.c4
-rw-r--r--net/unix/af_unix.c34
-rw-r--r--net/wireless/nl80211.c2
-rw-r--r--rust/bindings/bindings_helper.h1
-rw-r--r--rust/helpers/completion.c8
-rw-r--r--rust/helpers/cpu.c8
-rw-r--r--rust/helpers/helpers.c2
-rw-r--r--rust/kernel/cpu.rs125
-rw-r--r--rust/kernel/cpufreq.rs173
-rw-r--r--rust/kernel/cpumask.rs51
-rw-r--r--rust/kernel/devres.rs60
-rw-r--r--rust/kernel/revocable.rs18
-rw-r--r--rust/kernel/sync.rs2
-rw-r--r--rust/kernel/sync/completion.rs112
-rw-r--r--rust/kernel/time/hrtimer.rs2
-rw-r--r--scripts/gendwarfksyms/gendwarfksyms.h14
-rw-r--r--scripts/gendwarfksyms/types.c65
-rwxr-xr-xscripts/misc-check15
-rw-r--r--security/keys/gc.c4
-rw-r--r--security/keys/key.c5
-rw-r--r--security/selinux/ss/services.c16
-rw-r--r--security/selinux/xfrm.c2
-rw-r--r--sound/isa/sb/sb16_main.c7
-rw-r--r--sound/pci/ctxfi/xfi.c4
-rw-r--r--sound/pci/hda/hda_intel.c2
-rw-r--r--sound/pci/hda/patch_realtek.c30
-rw-r--r--sound/soc/amd/yc/acp6x-mach.c14
-rw-r--r--sound/soc/apple/Kconfig1
-rw-r--r--sound/soc/codecs/cs35l56-sdw.c18
-rw-r--r--sound/soc/codecs/cs35l56.c72
-rw-r--r--sound/soc/codecs/cs35l56.h3
-rw-r--r--sound/soc/codecs/cs48l32.c4
-rw-r--r--sound/soc/codecs/es8326.c3
-rw-r--r--sound/soc/codecs/wm_adsp.c27
-rw-r--r--sound/soc/codecs/wm_adsp.h2
-rw-r--r--sound/soc/intel/common/sof-function-topology-lib.c3
-rw-r--r--sound/soc/loongson/loongson_i2s.c1
-rw-r--r--sound/soc/sdw_utils/soc_sdw_utils.c2
-rw-r--r--sound/soc/sof/imx/imx8.c15
-rw-r--r--sound/usb/mixer_maps.c12
-rw-r--r--tools/arch/arm64/include/uapi/asm/kvm.h9
-rw-r--r--tools/arch/x86/include/asm/amd/ibs.h5
-rw-r--r--tools/arch/x86/include/asm/cpufeatures.h14
-rw-r--r--tools/arch/x86/include/asm/msr-index.h16
-rw-r--r--tools/arch/x86/include/uapi/asm/kvm.h71
-rw-r--r--tools/arch/x86/include/uapi/asm/svm.h2
-rw-r--r--tools/arch/x86/include/uapi/asm/vmx.h5
-rw-r--r--tools/arch/x86/lib/memcpy_64.S1
-rw-r--r--tools/arch/x86/lib/memset_64.S1
-rw-r--r--tools/bpf/bpf_jit_disasm.c2
-rw-r--r--tools/bpf/bpftool/btf.c8
-rw-r--r--tools/bpf/bpftool/common.c59
-rw-r--r--tools/bpf/bpftool/iter.c2
-rw-r--r--tools/bpf/bpftool/link.c8
-rw-r--r--tools/bpf/bpftool/main.c6
-rw-r--r--tools/bpf/bpftool/main.h13
-rw-r--r--tools/bpf/bpftool/map.c56
-rw-r--r--tools/bpf/bpftool/map_perf_ring.c3
-rw-r--r--tools/bpf/bpftool/net.c15
-rw-r--r--tools/bpf/bpftool/prog.c4
-rw-r--r--tools/bpf/resolve_btfids/Makefile2
-rw-r--r--tools/include/linux/bits.h57
-rw-r--r--tools/include/linux/build_bug.h10
-rw-r--r--tools/include/linux/compiler.h8
-rw-r--r--tools/include/uapi/drm/drm.h4
-rw-r--r--tools/include/uapi/linux/bpf.h13
-rw-r--r--tools/include/uapi/linux/fscrypt.h6
-rw-r--r--tools/include/uapi/linux/kvm.h4
-rw-r--r--tools/include/uapi/linux/stat.h8
-rw-r--r--tools/lib/bpf/bpf.c44
-rw-r--r--tools/lib/bpf/bpf.h5
-rw-r--r--tools/lib/bpf/btf.c6
-rw-r--r--tools/lib/bpf/btf.h3
-rw-r--r--tools/lib/bpf/btf_dump.c58
-rw-r--r--tools/lib/bpf/libbpf.c38
-rw-r--r--tools/lib/bpf/libbpf.h15
-rw-r--r--tools/lib/bpf/libbpf.map1
-rw-r--r--tools/lib/bpf/usdt.c10
-rw-r--r--tools/net/ynl/pyynl/lib/ynl.py28
-rw-r--r--tools/perf/Documentation/perf-amd-ibs.txt59
-rw-r--r--tools/perf/Documentation/perf-mem.txt50
-rw-r--r--tools/perf/bench/futex-hash.c1
-rw-r--r--tools/perf/bench/futex.c9
-rwxr-xr-xtools/perf/check-headers.sh2
-rwxr-xr-xtools/perf/tests/shell/stat+event_uniquifying.sh12
-rw-r--r--tools/perf/tests/tests-scripts.c1
-rw-r--r--tools/perf/trace/beauty/include/linux/socket.h2
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/fs.h1
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/prctl.h7
-rw-r--r--tools/perf/trace/beauty/include/uapi/linux/stat.h8
-rw-r--r--tools/perf/util/include/linux/linkage.h4
-rw-r--r--tools/perf/util/print-events.c1
-rw-r--r--tools/power/cpupower/Makefile9
-rw-r--r--tools/testing/selftests/bpf/.gitignore1
-rw-r--r--tools/testing/selftests/bpf/Makefile11
-rw-r--r--tools/testing/selftests/bpf/bpf_kfuncs.h2
-rw-r--r--tools/testing/selftests/bpf/config.ppc64el93
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_cookie.c50
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dump.c118
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c617
-rw-r--r--tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c77
-rw-r--r--tools/testing/selftests/bpf/prog_tests/fd_array.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/log_buf.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c9
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf.c4
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sockmap_listen.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/string_kfuncs.c65
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tc_helpers.h28
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_sysctl.c (renamed from tools/testing/selftests/bpf/test_sysctl.c)37
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_veristat.c127
-rw-r--r--tools/testing/selftests/bpf/prog_tests/usdt.c14
-rw-r--r--tools/testing/selftests/bpf/prog_tests/user_ringbuf.c10
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c114
-rw-r--r--tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c13
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c22
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_misc.h18
-rw-r--r--tools/testing/selftests/bpf/progs/cgroup_mprog.c30
-rw-r--r--tools/testing/selftests/bpf/progs/compute_live_registers.c16
-rw-r--r--tools/testing/selftests/bpf/progs/iters.c277
-rw-r--r--tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c136
-rw-r--r--tools/testing/selftests/bpf/progs/rbtree.c14
-rw-r--r--tools/testing/selftests/bpf/progs/rcu_read_lock.c5
-rw-r--r--tools/testing/selftests/bpf/progs/security_bpf_map.c69
-rw-r--r--tools/testing/selftests/bpf/progs/set_global_vars.c56
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c87
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c23
-rw-r--r--tools/testing/selftests/bpf/progs/string_kfuncs_success.c37
-rw-r--r--tools/testing/selftests/bpf/progs/test_global_map_resize.c16
-rw-r--r--tools/testing/selftests/bpf/progs/test_lookup_key.c4
-rw-r--r--tools/testing/selftests/bpf/progs/test_ringbuf_write.c4
-rw-r--r--tools/testing/selftests/bpf/progs/test_sig_in_xattr.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c9
-rw-r--r--tools/testing/selftests/bpf/progs/test_tc_change_tail.c14
-rw-r--r--tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c2
-rw-r--r--tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c8
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_and.c8
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bounds.c222
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c11
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_div_overflow.c4
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_map_in_map.c118
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_movsx.c16
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_precision.c70
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_ref_tracking.c2
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_unpriv.c84
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c38
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_vfs_accept.c18
-rw-r--r--tools/testing/selftests/bpf/progs/verifier_vfs_reject.c15
-rwxr-xr-xtools/testing/selftests/bpf/test_bpftool_map.sh398
-rw-r--r--tools/testing/selftests/bpf/test_loader.c30
-rw-r--r--tools/testing/selftests/bpf/test_lru_map.c105
-rw-r--r--tools/testing/selftests/bpf/test_progs.h28
-rw-r--r--tools/testing/selftests/bpf/unpriv_helpers.c94
-rw-r--r--tools/testing/selftests/bpf/verifier/dead_code.c3
-rw-r--r--tools/testing/selftests/bpf/verifier/jmp32.c33
-rw-r--r--tools/testing/selftests/bpf/verifier/jset.c10
-rw-r--r--tools/testing/selftests/bpf/veristat.c593
-rwxr-xr-xtools/testing/selftests/bpf/vmtest.sh9
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_ctx.py59
-rwxr-xr-xtools/testing/selftests/drivers/net/hw/rss_input_xfrm.py2
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/peer.sh3
-rw-r--r--tools/testing/selftests/futex/functional/futex_numa_mpol.c10
-rw-r--r--tools/testing/selftests/futex/functional/futex_priv_hash.c2
-rw-r--r--tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c55
-rw-r--r--tools/testing/selftests/mm/config3
-rw-r--r--tools/testing/selftests/mm/gup_longterm.c7
-rw-r--r--tools/testing/selftests/mm/merge.c5
-rw-r--r--tools/testing/selftests/mm/settings2
-rw-r--r--tools/testing/selftests/net/.gitignore1
-rw-r--r--tools/testing/selftests/net/Makefile3
-rw-r--r--tools/testing/selftests/net/af_unix/msg_oob.c142
-rwxr-xr-xtools/testing/selftests/net/nat6to4.sh15
-rw-r--r--tools/testing/selftests/net/tfo.c171
-rwxr-xr-xtools/testing/selftests/net/tfo_passive.sh112
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/sigtrap_loop.c101
-rw-r--r--tools/testing/vma/vma_internal.h16
910 files changed, 15031 insertions, 5169 deletions
diff --git a/.mailmap b/.mailmap
index c8a21d72241f..d57531dab08b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -197,6 +197,7 @@ Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
+Danilo Krummrich <dakr@kernel.org> <dakr@redhat.com>
David Brownell <david-b@pacbell.net>
David Collins <quic_collinsd@quicinc.com> <collinsd@codeaurora.org>
David Heidelberg <david@ixit.cz> <d.okias@gmail.com>
@@ -282,6 +283,7 @@ Gustavo Padovan <gustavo@las.ic.unicamp.br>
Gustavo Padovan <padovan@profusion.mobi>
Hamza Mahfooz <hamzamahfooz@linux.microsoft.com> <hamza.mahfooz@amd.com>
Hanjun Guo <guohanjun@huawei.com> <hanjun.guo@linaro.org>
+Hans de Goede <hansg@kernel.org> <hdegoede@redhat.com>
Hans Verkuil <hverkuil@xs4all.nl> <hansverk@cisco.com>
Hans Verkuil <hverkuil@xs4all.nl> <hverkuil-cisco@xs4all.nl>
Harry Yoo <harry.yoo@oracle.com> <42.hyeyoo@gmail.com>
@@ -426,6 +428,9 @@ Krzysztof Wilczyński <kwilczynski@kernel.org> <krzysztof.wilczynski@linux.com>
Krzysztof Wilczyński <kwilczynski@kernel.org> <kw@linux.com>
Kshitiz Godara <quic_kgodara@quicinc.com> <kgodara@codeaurora.org>
Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.com>
+Kuniyuki Iwashima <kuniyu@google.com> <kuniyu@amazon.co.jp>
+Kuniyuki Iwashima <kuniyu@google.com> <kuni1840@gmail.com>
Kuogee Hsieh <quic_khsieh@quicinc.com> <khsieh@codeaurora.org>
Lee Jones <lee@kernel.org> <joneslee@google.com>
Lee Jones <lee@kernel.org> <lee.jones@canonical.com>
@@ -688,9 +693,10 @@ Serge Hallyn <sergeh@kernel.org> <serge.hallyn@canonical.com>
Serge Hallyn <sergeh@kernel.org> <serue@us.ibm.com>
Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com>
Shakeel Butt <shakeel.butt@linux.dev> <shakeelb@google.com>
-Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io>
-Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com>
-Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@amd.com>
+Shannon Nelson <sln@onemain.com> <snelson@pensando.io>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@intel.com>
+Shannon Nelson <sln@onemain.com> <shannon.nelson@oracle.com>
Sharath Chandra Vurukala <quic_sharathv@quicinc.com> <sharathv@codeaurora.org>
Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com>
Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
@@ -719,6 +725,7 @@ Srinivas Ramana <quic_sramana@quicinc.com> <sramana@codeaurora.org>
Sriram R <quic_srirrama@quicinc.com> <srirrama@codeaurora.org>
Sriram Yagnaraman <sriram.yagnaraman@ericsson.com> <sriram.yagnaraman@est.tech>
Stanislav Fomichev <sdf@fomichev.me> <sdf@google.com>
+Stanislav Fomichev <sdf@fomichev.me> <stfomichev@gmail.com>
Stefan Wahren <wahrenst@gmx.net> <stefan.wahren@i2se.com>
Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
Stephen Hemminger <stephen@networkplumber.org> <shemminger@linux-foundation.org>
diff --git a/CREDITS b/CREDITS
index 45446ae322ec..c30b75f9a732 100644
--- a/CREDITS
+++ b/CREDITS
@@ -2981,6 +2981,11 @@ S: 521 Pleasant Valley Road
S: Potsdam, New York 13676
S: USA
+N: Shannon Nelson
+E: sln@onemain.com
+D: Worked on several network drivers including
+D: ixgbe, i40e, ionic, pds_core, pds_vdpa, pds_fwctl
+
N: Dave Neuer
E: dave.neuer@pobox.com
D: Helped implement support for Compaq's H31xx series iPAQs
diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
index c09674a75a9e..d989ae5778ba 100644
--- a/Documentation/admin-guide/cifs/usage.rst
+++ b/Documentation/admin-guide/cifs/usage.rst
@@ -270,6 +270,8 @@ configured for Unix Extensions (and the client has not disabled
illegal Windows/NTFS/SMB characters to a remap range (this mount parameter
is the default for SMB3). This remap (``mapposix``) range is also
compatible with Mac (and "Services for Mac" on some older Windows).
+When POSIX Extensions for SMB 3.1.1 are negotiated, remapping is automatically
+disabled.
CIFS VFS Mount Options
======================
diff --git a/Documentation/arch/arm64/booting.rst b/Documentation/arch/arm64/booting.rst
index dee7b6de864f..ee9b790c0d72 100644
--- a/Documentation/arch/arm64/booting.rst
+++ b/Documentation/arch/arm64/booting.rst
@@ -234,7 +234,7 @@ Before jumping into the kernel, the following conditions must be met:
- If the kernel is entered at EL1:
- - ICC.SRE_EL2.Enable (bit 3) must be initialised to 0b1
+ - ICC_SRE_EL2.Enable (bit 3) must be initialised to 0b1
- ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b1.
- The DT or ACPI tables must describe a GICv3 interrupt controller.
diff --git a/Documentation/block/ublk.rst b/Documentation/block/ublk.rst
index c368e1081b41..8c4030bcabb6 100644
--- a/Documentation/block/ublk.rst
+++ b/Documentation/block/ublk.rst
@@ -352,6 +352,83 @@ For reaching best IO performance, ublk server should align its segment
parameter of `struct ublk_param_segment` with backend for avoiding
unnecessary IO split, which usually hurts io_uring performance.
+Auto Buffer Registration
+------------------------
+
+The ``UBLK_F_AUTO_BUF_REG`` feature automatically handles buffer registration
+and unregistration for I/O requests, which simplifies the buffer management
+process and reduces overhead in the ublk server implementation.
+
+This is another feature flag for using zero copy, and it is compatible with
+``UBLK_F_SUPPORT_ZERO_COPY``.
+
+Feature Overview
+~~~~~~~~~~~~~~~~
+
+This feature automatically registers request buffers to the io_uring context
+before delivering I/O commands to the ublk server and unregisters them when
+completing I/O commands. This eliminates the need for manual buffer
+registration/unregistration via ``UBLK_IO_REGISTER_IO_BUF`` and
+``UBLK_IO_UNREGISTER_IO_BUF`` commands, then IO handling in ublk server
+can avoid dependency on the two uring_cmd operations.
+
+IOs can't be issued concurrently to io_uring if there is any dependency
+among these IOs. So this way not only simplifies ublk server implementation,
+but also makes concurrent IO handling becomes possible by removing the
+dependency on buffer registration & unregistration commands.
+
+Usage Requirements
+~~~~~~~~~~~~~~~~~~
+
+1. The ublk server must create a sparse buffer table on the same ``io_ring_ctx``
+ used for ``UBLK_IO_FETCH_REQ`` and ``UBLK_IO_COMMIT_AND_FETCH_REQ``. If
+ uring_cmd is issued on a different ``io_ring_ctx``, manual buffer
+ unregistration is required.
+
+2. Buffer registration data must be passed via uring_cmd's ``sqe->addr`` with the
+ following structure::
+
+ struct ublk_auto_buf_reg {
+ __u16 index; /* Buffer index for registration */
+ __u8 flags; /* Registration flags */
+ __u8 reserved0; /* Reserved for future use */
+ __u32 reserved1; /* Reserved for future use */
+ };
+
+ ublk_auto_buf_reg_to_sqe_addr() is for converting the above structure into
+ ``sqe->addr``.
+
+3. All reserved fields in ``ublk_auto_buf_reg`` must be zeroed.
+
+4. Optional flags can be passed via ``ublk_auto_buf_reg.flags``.
+
+Fallback Behavior
+~~~~~~~~~~~~~~~~~
+
+If auto buffer registration fails:
+
+1. When ``UBLK_AUTO_BUF_REG_FALLBACK`` is enabled:
+
+ - The uring_cmd is completed
+ - ``UBLK_IO_F_NEED_REG_BUF`` is set in ``ublksrv_io_desc.op_flags``
+ - The ublk server must manually deal with the failure, such as, register
+ the buffer manually, or using user copy feature for retrieving the data
+ for handling ublk IO
+
+2. If fallback is not enabled:
+
+ - The ublk I/O request fails silently
+ - The uring_cmd won't be completed
+
+Limitations
+~~~~~~~~~~~
+
+- Requires same ``io_ring_ctx`` for all operations
+- May require manual buffer management in fallback cases
+- io_ring_ctx buffer table has a max size of 16K, which may not be enough
+ in case that too many ublk devices are handled by this single io_ring_ctx
+ and each one has very large queue depth
+
References
==========
diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index 0acb4c9b8d90..45bc5c5cd793 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -611,9 +611,10 @@ Q: I have added a new BPF instruction to the kernel, how can I integrate
it into LLVM?
A: LLVM has a ``-mcpu`` selector for the BPF back end in order to allow
-the selection of BPF instruction set extensions. By default the
-``generic`` processor target is used, which is the base instruction set
-(v1) of BPF.
+the selection of BPF instruction set extensions. Before llvm version 20,
+the ``generic`` processor target is used, which is the base instruction
+set (v1) of BPF. Since llvm 20, the default processor target has changed
+to instruction set v3.
LLVM has an option to select ``-mcpu=probe`` where it will probe the host
kernel for supported BPF instruction set extensions and selects the
diff --git a/Documentation/bpf/map_hash.rst b/Documentation/bpf/map_hash.rst
index d2343952f2cb..8606bf958a8c 100644
--- a/Documentation/bpf/map_hash.rst
+++ b/Documentation/bpf/map_hash.rst
@@ -233,10 +233,16 @@ attempts in order to enforce the LRU property which have increasing impacts on
other CPUs involved in the following operation attempts:
- Attempt to use CPU-local state to batch operations
-- Attempt to fetch free nodes from global lists
+- Attempt to fetch ``target_free`` free nodes from global lists
- Attempt to pull any node from a global list and remove it from the hashmap
- Attempt to pull any node from any CPU's list and remove it from the hashmap
+The number of nodes to borrow from the global list in a batch, ``target_free``,
+depends on the size of the map. Larger batch size reduces lock contention, but
+may also exhaust the global structure. The value is computed at map init to
+avoid exhaustion, by limiting aggregate reservation by all CPUs to half the map
+size. With a minimum of a single element and maximum budget of 128 at a time.
+
This algorithm is described visually in the following diagram. See the
description in commit 3a08c2fd7634 ("bpf: LRU List") for a full explanation of
the corresponding operations:
diff --git a/Documentation/bpf/map_lru_hash_update.dot b/Documentation/bpf/map_lru_hash_update.dot
index a0fee349d29c..ab10058f5b79 100644
--- a/Documentation/bpf/map_lru_hash_update.dot
+++ b/Documentation/bpf/map_lru_hash_update.dot
@@ -35,18 +35,18 @@ digraph {
fn_bpf_lru_list_pop_free_to_local [shape=rectangle,fillcolor=2,
label="Flush local pending,
Rotate Global list, move
- LOCAL_FREE_TARGET
+ target_free
from global -> local"]
// Also corresponds to:
// fn__local_list_flush()
// fn_bpf_lru_list_rotate()
fn___bpf_lru_node_move_to_free[shape=diamond,fillcolor=2,
- label="Able to free\nLOCAL_FREE_TARGET\nnodes?"]
+ label="Able to free\ntarget_free\nnodes?"]
fn___bpf_lru_list_shrink_inactive [shape=rectangle,fillcolor=3,
label="Shrink inactive list
up to remaining
- LOCAL_FREE_TARGET
+ target_free
(global LRU -> local)"]
fn___bpf_lru_list_shrink [shape=diamond,fillcolor=2,
label="> 0 entries in\nlocal free list?"]
diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst
index fbe975585236..39c74611752b 100644
--- a/Documentation/bpf/standardization/instruction-set.rst
+++ b/Documentation/bpf/standardization/instruction-set.rst
@@ -350,9 +350,9 @@ Underflow and overflow are allowed during arithmetic operations, meaning
the 64-bit or 32-bit value will wrap. If BPF program execution would
result in division by zero, the destination register is instead set to zero.
Otherwise, for ``ALU64``, if execution would result in ``LLONG_MIN``
-dividing -1, the desination register is instead set to ``LLONG_MIN``. For
-``ALU``, if execution would result in ``INT_MIN`` dividing -1, the
-desination register is instead set to ``INT_MIN``.
+divided by -1, the destination register is instead set to ``LLONG_MIN``. For
+``ALU``, if execution would result in ``INT_MIN`` divided by -1, the
+destination register is instead set to ``INT_MIN``.
If execution would result in modulo by zero, for ``ALU64`` the value of
the destination register is unchanged whereas for ``ALU`` the upper
diff --git a/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml b/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
index b57ae6963e62..6b6f6762d122 100644
--- a/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
+++ b/Documentation/devicetree/bindings/i2c/nvidia,tegra20-i2c.yaml
@@ -97,7 +97,10 @@ properties:
resets:
items:
- - description: module reset
+ - description:
+ Module reset. This property is optional for controllers in Tegra194,
+ Tegra234 etc where an internal software reset is available as an
+ alternative.
reset-names:
items:
@@ -116,6 +119,13 @@ properties:
- const: rx
- const: tx
+required:
+ - compatible
+ - reg
+ - interrupts
+ - clocks
+ - clock-names
+
allOf:
- $ref: /schemas/i2c/i2c-controller.yaml
- if:
@@ -169,6 +179,18 @@ allOf:
properties:
power-domains: false
+ - if:
+ not:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - nvidia,tegra194-i2c
+ then:
+ required:
+ - resets
+ - reset-names
+
unevaluatedProperties: false
examples:
diff --git a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
index b470901f5f56..4dbef86bd958 100644
--- a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-aon-pinctrl.yaml
@@ -15,7 +15,7 @@ description: |
Some peripherals such as PWM have their I/O go through the 4 "GPIOs".
maintainers:
- - Jianlong Huang <jianlong.huang@starfivetech.com>
+ - Hal Feng <hal.feng@starfivetech.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
index 222b9e240f8a..e2a25a20f6a6 100644
--- a/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/starfive,jh7110-sys-pinctrl.yaml
@@ -18,7 +18,7 @@ description: |
any GPIO can be set up to be controlled by any of the peripherals.
maintainers:
- - Jianlong Huang <jianlong.huang@starfivetech.com>
+ - Hal Feng <hal.feng@starfivetech.com>
properties:
compatible:
diff --git a/Documentation/devicetree/bindings/pmem/pmem-region.txt b/Documentation/devicetree/bindings/pmem/pmem-region.txt
deleted file mode 100644
index cd79975e85ec..000000000000
--- a/Documentation/devicetree/bindings/pmem/pmem-region.txt
+++ /dev/null
@@ -1,65 +0,0 @@
-Device-tree bindings for persistent memory regions
------------------------------------------------------
-
-Persistent memory refers to a class of memory devices that are:
-
- a) Usable as main system memory (i.e. cacheable), and
- b) Retain their contents across power failure.
-
-Given b) it is best to think of persistent memory as a kind of memory mapped
-storage device. To ensure data integrity the operating system needs to manage
-persistent regions separately to the normal memory pool. To aid with that this
-binding provides a standardised interface for discovering where persistent
-memory regions exist inside the physical address space.
-
-Bindings for the region nodes:
------------------------------
-
-Required properties:
- - compatible = "pmem-region"
-
- - reg = <base, size>;
- The reg property should specify an address range that is
- translatable to a system physical address range. This address
- range should be mappable as normal system memory would be
- (i.e cacheable).
-
- If the reg property contains multiple address ranges
- each address range will be treated as though it was specified
- in a separate device node. Having multiple address ranges in a
- node implies no special relationship between the two ranges.
-
-Optional properties:
- - Any relevant NUMA associativity properties for the target platform.
-
- - volatile; This property indicates that this region is actually
- backed by non-persistent memory. This lets the OS know that it
- may skip the cache flushes required to ensure data is made
- persistent after a write.
-
- If this property is absent then the OS must assume that the region
- is backed by non-volatile memory.
-
-Examples:
---------------------
-
- /*
- * This node specifies one 4KB region spanning from
- * 0x5000 to 0x5fff that is backed by non-volatile memory.
- */
- pmem@5000 {
- compatible = "pmem-region";
- reg = <0x00005000 0x00001000>;
- };
-
- /*
- * This node specifies two 4KB regions that are backed by
- * volatile (normal) memory.
- */
- pmem@6000 {
- compatible = "pmem-region";
- reg = < 0x00006000 0x00001000
- 0x00008000 0x00001000 >;
- volatile;
- };
-
diff --git a/Documentation/devicetree/bindings/pmem/pmem-region.yaml b/Documentation/devicetree/bindings/pmem/pmem-region.yaml
new file mode 100644
index 000000000000..bd0f0c793f03
--- /dev/null
+++ b/Documentation/devicetree/bindings/pmem/pmem-region.yaml
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pmem-region.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+maintainers:
+ - Oliver O'Halloran <oohall@gmail.com>
+
+title: Persistent Memory Regions
+
+description: |
+ Persistent memory refers to a class of memory devices that are:
+
+ a) Usable as main system memory (i.e. cacheable), and
+ b) Retain their contents across power failure.
+
+ Given b) it is best to think of persistent memory as a kind of memory mapped
+ storage device. To ensure data integrity the operating system needs to manage
+ persistent regions separately to the normal memory pool. To aid with that this
+ binding provides a standardised interface for discovering where persistent
+ memory regions exist inside the physical address space.
+
+properties:
+ compatible:
+ const: pmem-region
+
+ reg:
+ maxItems: 1
+
+ volatile:
+ description:
+ Indicates the region is volatile (non-persistent) and the OS can skip
+ cache flushes for writes
+ type: boolean
+
+required:
+ - compatible
+ - reg
+
+additionalProperties: false
+
+examples:
+ - |
+ pmem@5000 {
+ compatible = "pmem-region";
+ reg = <0x00005000 0x00001000>;
+ };
diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 3616d7161dab..a5734bdd1cc7 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1249,3 +1249,12 @@ Using try_lookup_noperm() will require linux/namei.h to be included.
Calling conventions for ->d_automount() have changed; we should *not* grab
an extra reference to new mount - it should be returned with refcount 1.
+
+---
+
+collect_mounts()/drop_collected_mounts()/iterate_mounts() are gone now.
+Replacement is collect_paths()/drop_collected_path(), with no special
+iterator needed. Instead of a cloned mount tree, the new interface returns
+an array of struct path, one for each mount collect_mounts() would've
+created. These struct path point to locations in the caller's namespace
+that would be roots of the cloned mounts.
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 2a17865dfe39..5236cb52e357 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -584,7 +584,6 @@ encoded manner. The codes are the following:
ms may share
gd stack segment growns down
pf pure PFN range
- dw disabled write to the mapped file
lo pages are locked in memory
io memory mapped I/O area
sr sequential read advise provided
@@ -607,8 +606,11 @@ encoded manner. The codes are the following:
mt arm64 MTE allocation tags are enabled
um userfaultfd missing tracking
uw userfaultfd wr-protect tracking
+ ui userfaultfd minor fault
ss shadow/guarded control stack page
sl sealed
+ lf lock on fault pages
+ dp always lazily freeable mapping
== =======================================
Note that there is no guarantee that every flag and associated mnemonic will
diff --git a/Documentation/gpu/nouveau.rst b/Documentation/gpu/nouveau.rst
index b8c801e0068c..cab2e81013bc 100644
--- a/Documentation/gpu/nouveau.rst
+++ b/Documentation/gpu/nouveau.rst
@@ -25,7 +25,7 @@ providing a consistent API to upper layers of the driver stack.
GSP Support
------------------------
-.. kernel-doc:: drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c
+.. kernel-doc:: drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
:doc: GSP message queue element
.. kernel-doc:: drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 4cbfe666e6f5..b29d62eefa16 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema
# Common defines
$defs:
+ name:
+ type: string
+ pattern: ^[0-9a-z-]+$
uint:
type: integer
minimum: 0
@@ -76,7 +79,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
header:
description: For C-compatible languages, header which already defines this value.
type: string
@@ -103,7 +106,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
value:
type: integer
doc:
@@ -132,7 +135,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
type:
description: The netlink attribute type
enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ]
@@ -169,7 +172,7 @@ properties:
name:
description: |
Name used when referring to this space in other definitions, not used outside of the spec.
- type: string
+ $ref: '#/$defs/name'
name-prefix:
description: |
Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -206,7 +209,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
type: &attr-type
description: The netlink attribute type
enum: [ unused, pad, flag, binary, bitfield32,
@@ -348,7 +351,7 @@ properties:
properties:
name:
description: Name of the operation, also defining its C enum value in uAPI.
- type: string
+ $ref: '#/$defs/name'
doc:
description: Documentation for the command.
type: string
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index 40efbbad76ab..7b1ec153e834 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -6,6 +6,9 @@ $schema: https://json-schema.org/draft-07/schema
# Common defines
$defs:
+ name:
+ type: string
+ pattern: ^[0-9a-z-]+$
uint:
type: integer
minimum: 0
@@ -29,7 +32,7 @@ additionalProperties: False
properties:
name:
description: Name of the genetlink family.
- type: string
+ $ref: '#/$defs/name'
doc:
type: string
protocol:
@@ -48,7 +51,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
header:
description: For C-compatible languages, header which already defines this value.
type: string
@@ -75,7 +78,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
value:
type: integer
doc:
@@ -96,7 +99,7 @@ properties:
name:
description: |
Name used when referring to this space in other definitions, not used outside of the spec.
- type: string
+ $ref: '#/$defs/name'
name-prefix:
description: |
Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -121,7 +124,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
type: &attr-type
enum: [ unused, pad, flag, binary,
uint, sint, u8, u16, u32, u64, s8, s16, s32, s64,
@@ -243,7 +246,7 @@ properties:
properties:
name:
description: Name of the operation, also defining its C enum value in uAPI.
- type: string
+ $ref: '#/$defs/name'
doc:
description: Documentation for the command.
type: string
@@ -327,7 +330,7 @@ properties:
name:
description: |
The name for the group, used to form the define and the value of the define.
- type: string
+ $ref: '#/$defs/name'
flags: *cmd_flags
kernel-family:
diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml
index e34bf23897fa..246fa07bccf6 100644
--- a/Documentation/netlink/netlink-raw.yaml
+++ b/Documentation/netlink/netlink-raw.yaml
@@ -6,6 +6,12 @@ $schema: https://json-schema.org/draft-07/schema
# Common defines
$defs:
+ name:
+ type: string
+ pattern: ^[0-9a-z-]+$
+ name-cap:
+ type: string
+ pattern: ^[0-9a-zA-Z-]+$
uint:
type: integer
minimum: 0
@@ -71,7 +77,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
header:
description: For C-compatible languages, header which already defines this value.
type: string
@@ -98,7 +104,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
value:
type: integer
doc:
@@ -124,7 +130,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name-cap'
type:
description: |
The netlink attribute type. Members of type 'binary' or 'pad'
@@ -183,7 +189,7 @@ properties:
name:
description: |
Name used when referring to this space in other definitions, not used outside of the spec.
- type: string
+ $ref: '#/$defs/name'
name-prefix:
description: |
Prefix for the C enum name of the attributes. Default family[name]-set[name]-a-
@@ -220,7 +226,7 @@ properties:
additionalProperties: False
properties:
name:
- type: string
+ $ref: '#/$defs/name'
type: &attr-type
description: The netlink attribute type
enum: [ unused, pad, flag, binary, bitfield32,
@@ -408,7 +414,7 @@ properties:
properties:
name:
description: Name of the operation, also defining its C enum value in uAPI.
- type: string
+ $ref: '#/$defs/name'
doc:
description: Documentation for the command.
type: string
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 05fee1b7fe19..38ddc04f9e6d 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -38,15 +38,15 @@ definitions:
-
name: dsa
-
- name: pci_pf
+ name: pci-pf
-
- name: pci_vf
+ name: pci-vf
-
name: virtual
-
name: unused
-
- name: pci_sf
+ name: pci-sf
-
type: enum
name: port-fn-state
@@ -220,7 +220,7 @@ definitions:
-
name: flag
-
- name: nul_string
+ name: nul-string
value: 10
-
name: binary
diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml
index 8feefeae5376..f434140b538e 100644
--- a/Documentation/netlink/specs/dpll.yaml
+++ b/Documentation/netlink/specs/dpll.yaml
@@ -188,7 +188,7 @@ definitions:
value: 10000
-
type: const
- name: pin-frequency-77_5-khz
+ name: pin-frequency-77-5-khz
value: 77500
-
type: const
diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 9f98715a6512..348c6ad548f5 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -7,6 +7,9 @@ protocol: genetlink-legacy
doc: Partial family for Ethtool Netlink.
uapi-header: linux/ethtool_netlink_generated.h
+c-family-name: ethtool-genl-name
+c-version-name: ethtool-genl-version
+
definitions:
-
name: udp-tunnel-type
@@ -45,7 +48,7 @@ definitions:
name: started
doc: The firmware flashing process has started.
-
- name: in_progress
+ name: in-progress
doc: The firmware flashing process is in progress.
-
name: completed
@@ -1419,7 +1422,7 @@ attribute-sets:
name: hkey
type: binary
-
- name: input_xfrm
+ name: input-xfrm
type: u32
-
name: start-context
@@ -2235,7 +2238,7 @@ operations:
- hfunc
- indir
- hkey
- - input_xfrm
+ - input-xfrm
dump:
request:
attributes:
diff --git a/Documentation/netlink/specs/fou.yaml b/Documentation/netlink/specs/fou.yaml
index 0af5ab842c04..b02ab19817d3 100644
--- a/Documentation/netlink/specs/fou.yaml
+++ b/Documentation/netlink/specs/fou.yaml
@@ -15,7 +15,7 @@ kernel-policy: global
definitions:
-
type: enum
- name: encap_type
+ name: encap-type
name-prefix: fou-encap-
enum-name:
entries: [ unspec, direct, gue ]
@@ -43,26 +43,26 @@ attribute-sets:
name: type
type: u8
-
- name: remcsum_nopartial
+ name: remcsum-nopartial
type: flag
-
- name: local_v4
+ name: local-v4
type: u32
-
- name: local_v6
+ name: local-v6
type: binary
checks:
min-len: 16
-
- name: peer_v4
+ name: peer-v4
type: u32
-
- name: peer_v6
+ name: peer-v6
type: binary
checks:
min-len: 16
-
- name: peer_port
+ name: peer-port
type: u16
byte-order: big-endian
-
@@ -90,12 +90,12 @@ operations:
- port
- ipproto
- type
- - remcsum_nopartial
- - local_v4
- - peer_v4
- - local_v6
- - peer_v6
- - peer_port
+ - remcsum-nopartial
+ - local-v4
+ - peer-v4
+ - local-v6
+ - peer-v6
+ - peer-port
- ifindex
-
@@ -112,11 +112,11 @@ operations:
- af
- ifindex
- port
- - peer_port
- - local_v4
- - peer_v4
- - local_v6
- - peer_v6
+ - peer-port
+ - local-v4
+ - peer-v4
+ - local-v6
+ - peer-v6
-
name: get
diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
index dfd017780d2f..fb57860fe778 100644
--- a/Documentation/netlink/specs/mptcp_pm.yaml
+++ b/Documentation/netlink/specs/mptcp_pm.yaml
@@ -57,21 +57,21 @@ definitions:
doc: >-
A new subflow has been established. 'error' should not be set.
Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
- daddr6, sport, dport, backup, if_idx [, error].
+ daddr6, sport, dport, backup, if-idx [, error].
-
name: sub-closed
doc: >-
A subflow has been closed. An error (copy of sk_err) could be set if an
error has been detected for this subflow.
Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
- daddr6, sport, dport, backup, if_idx [, error].
+ daddr6, sport, dport, backup, if-idx [, error].
-
name: sub-priority
value: 13
doc: >-
The priority of a subflow has changed. 'error' should not be set.
Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
- daddr6, sport, dport, backup, if_idx [, error].
+ daddr6, sport, dport, backup, if-idx [, error].
-
name: listener-created
value: 15
@@ -255,7 +255,7 @@ attribute-sets:
name: timeout
type: u32
-
- name: if_idx
+ name: if-idx
type: u32
-
name: reset-reason
diff --git a/Documentation/netlink/specs/nfsd.yaml b/Documentation/netlink/specs/nfsd.yaml
index c87658114852..8d1a3c01708f 100644
--- a/Documentation/netlink/specs/nfsd.yaml
+++ b/Documentation/netlink/specs/nfsd.yaml
@@ -27,7 +27,7 @@ attribute-sets:
name: proc
type: u32
-
- name: service_time
+ name: service-time
type: s64
-
name: pad
@@ -139,7 +139,7 @@ operations:
- prog
- version
- proc
- - service_time
+ - service-time
- saddr4
- daddr4
- saddr6
diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml
index 46f5d1cd8a5f..7974aa7d8905 100644
--- a/Documentation/netlink/specs/ovs_flow.yaml
+++ b/Documentation/netlink/specs/ovs_flow.yaml
@@ -216,7 +216,7 @@ definitions:
type: struct
members:
-
- name: nd_target
+ name: nd-target
type: binary
len: 16
byte-order: big-endian
@@ -258,12 +258,12 @@ definitions:
type: struct
members:
-
- name: vlan_tpid
+ name: vlan-tpid
type: u16
byte-order: big-endian
doc: Tag protocol identifier (TPID) to push.
-
- name: vlan_tci
+ name: vlan-tci
type: u16
byte-order: big-endian
doc: Tag control identifier (TCI) to push.
diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml
index b41b31eebcae..28c4cf66517c 100644
--- a/Documentation/netlink/specs/rt-link.yaml
+++ b/Documentation/netlink/specs/rt-link.yaml
@@ -603,7 +603,7 @@ definitions:
name: optmask
type: u32
-
- name: if_stats_msg
+ name: if-stats-msg
type: struct
members:
-
@@ -2486,7 +2486,7 @@ operations:
name: getstats
doc: Get / dump link stats.
attribute-set: stats-attrs
- fixed-header: if_stats_msg
+ fixed-header: if-stats-msg
do:
request:
value: 94
diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
index cb7ea7d62e56..42d74c9aeb54 100644
--- a/Documentation/netlink/specs/tc.yaml
+++ b/Documentation/netlink/specs/tc.yaml
@@ -232,7 +232,7 @@ definitions:
type: u8
doc: log(P_max / (qth-max - qth-min))
-
- name: Scell_log
+ name: Scell-log
type: u8
doc: cell size for idle damping
-
@@ -253,7 +253,7 @@ definitions:
name: DPs
type: u32
-
- name: def_DP
+ name: def-DP
type: u32
-
name: grio
diff --git a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
index af7db0e91f6b..a52850602cd8 100644
--- a/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
+++ b/Documentation/networking/device_drivers/ethernet/marvell/octeontx2.rst
@@ -66,7 +66,7 @@ Admin Function driver
As mentioned above RVU PF0 is called the admin function (AF), this driver
supports resource provisioning and configuration of functional blocks.
Doesn't handle any I/O. It sets up few basic stuff but most of the
-funcionality is achieved via configuration requests from PFs and VFs.
+functionality is achieved via configuration requests from PFs and VFs.
PF/VFs communicates with AF via a shared memory region (mailbox). Upon
receiving requests AF does resource provisioning and other HW configuration.
diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst
index da6bf0f6d01e..34e00848e0da 100644
--- a/Documentation/process/embargoed-hardware-issues.rst
+++ b/Documentation/process/embargoed-hardware-issues.rst
@@ -290,6 +290,7 @@ an involved disclosed party. The current ambassadors list:
AMD Tom Lendacky <thomas.lendacky@amd.com>
Ampere Darren Hart <darren@os.amperecomputing.com>
ARM Catalin Marinas <catalin.marinas@arm.com>
+ IBM Power Madhavan Srinivasan <maddy@linux.ibm.com>
IBM Z Christian Borntraeger <borntraeger@de.ibm.com>
Intel Tony Luck <tony.luck@intel.com>
Qualcomm Trilok Soni <quic_tsoni@quicinc.com>
diff --git a/Documentation/sound/codecs/cs35l56.rst b/Documentation/sound/codecs/cs35l56.rst
index 98c6f6c74394..57d1964453e1 100644
--- a/Documentation/sound/codecs/cs35l56.rst
+++ b/Documentation/sound/codecs/cs35l56.rst
@@ -1,8 +1,8 @@
.. SPDX-License-Identifier: GPL-2.0-only
-=====================================================================
-Audio drivers for Cirrus Logic CS35L54/56/57 Boosted Smart Amplifiers
-=====================================================================
+========================================================================
+Audio drivers for Cirrus Logic CS35L54/56/57/63 Boosted Smart Amplifiers
+========================================================================
:Copyright: 2025 Cirrus Logic, Inc. and
Cirrus Logic International Semiconductor Ltd.
@@ -13,11 +13,11 @@ Summary
The high-level summary of this document is:
-**If you have a laptop that uses CS35L54/56/57 amplifiers but audio is not
+**If you have a laptop that uses CS35L54/56/57/63 amplifiers but audio is not
working, DO NOT ATTEMPT TO USE FIRMWARE AND SETTINGS FROM ANOTHER LAPTOP,
EVEN IF THAT LAPTOP SEEMS SIMILAR.**
-The CS35L54/56/57 amplifiers must be correctly configured for the power
+The CS35L54/56/57/63 amplifiers must be correctly configured for the power
supply voltage, speaker impedance, maximum speaker voltage/current, and
other external hardware connections.
@@ -34,6 +34,7 @@ The cs35l56 drivers support:
* CS35L54
* CS35L56
* CS35L57
+* CS35L63
There are two drivers in the kernel
@@ -104,6 +105,13 @@ In this example the SSID is 10280c63.
The format of the firmware file names is:
+SoundWire (except CS35L56 Rev B0):
+ cs35lxx-b0-dsp1-misc-SSID[-spkidX]-l?u?
+
+SoundWire CS35L56 Rev B0:
+ cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN
+
+Non-SoundWire (HDA and I2S):
cs35lxx-b0-dsp1-misc-SSID[-spkidX]-ampN
Where:
@@ -111,12 +119,18 @@ Where:
* cs35lxx-b0 is the amplifier model and silicon revision. This information
is logged by the driver during initialization.
* SSID is the 8-digit hexadecimal SSID value.
+ * l?u? is the physical address on the SoundWire bus of the amp this
+ file applies to.
* ampN is the amplifier number (for example amp1). This is the same as
the prefix on the ALSA control names except that it is always lower-case
in the file name.
* spkidX is an optional part, used for laptops that have firmware
configurations for different makes and models of internal speakers.
+The CS35L56 Rev B0 continues to use the old filename scheme because a
+large number of firmware files have already been published with these
+names.
+
Sound Open Firmware and ALSA topology files
-------------------------------------------
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 1bd2d42e6424..9abf93ee5f65 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -6645,7 +6645,8 @@ to the byte array.
.. note::
For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR, KVM_EXIT_XEN,
- KVM_EXIT_EPR, KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
+ KVM_EXIT_EPR, KVM_EXIT_HYPERCALL, KVM_EXIT_TDX,
+ KVM_EXIT_X86_RDMSR and KVM_EXIT_X86_WRMSR the corresponding
operations are complete (and guest state is consistent) only after userspace
has re-entered the kernel with KVM_RUN. The kernel side will first finish
incomplete operations and then check for pending signals.
@@ -7176,6 +7177,62 @@ The valid value for 'flags' is:
::
+ /* KVM_EXIT_TDX */
+ struct {
+ __u64 flags;
+ __u64 nr;
+ union {
+ struct {
+ u64 ret;
+ u64 data[5];
+ } unknown;
+ struct {
+ u64 ret;
+ u64 gpa;
+ u64 size;
+ } get_quote;
+ struct {
+ u64 ret;
+ u64 leaf;
+ u64 r11, r12, r13, r14;
+ } get_tdvmcall_info;
+ };
+ } tdx;
+
+Process a TDVMCALL from the guest. KVM forwards select TDVMCALL based
+on the Guest-Hypervisor Communication Interface (GHCI) specification;
+KVM bridges these requests to the userspace VMM with minimal changes,
+placing the inputs in the union and copying them back to the guest
+on re-entry.
+
+Flags are currently always zero, whereas ``nr`` contains the TDVMCALL
+number from register R11. The remaining field of the union provide the
+inputs and outputs of the TDVMCALL. Currently the following values of
+``nr`` are defined:
+
+* ``TDVMCALL_GET_QUOTE``: the guest has requested to generate a TD-Quote
+signed by a service hosting TD-Quoting Enclave operating on the host.
+Parameters and return value are in the ``get_quote`` field of the union.
+The ``gpa`` field and ``size`` specify the guest physical address
+(without the shared bit set) and the size of a shared-memory buffer, in
+which the TDX guest passes a TD Report. The ``ret`` field represents
+the return value of the GetQuote request. When the request has been
+queued successfully, the TDX guest can poll the status field in the
+shared-memory area to check whether the Quote generation is completed or
+not. When completed, the generated Quote is returned via the same buffer.
+
+* ``TDVMCALL_GET_TD_VM_CALL_INFO``: the guest has requested the support
+status of TDVMCALLs. The output values for the given leaf should be
+placed in fields from ``r11`` to ``r14`` of the ``get_tdvmcall_info``
+field of the union.
+
+KVM may add support for more values in the future that may cause a userspace
+exit, even without calls to ``KVM_ENABLE_CAP`` or similar. In this case,
+it will enter with output fields already valid; in the common case, the
+``unknown.ret`` field of the union will be ``TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED``.
+Userspace need not do anything if it does not wish to support a TDVMCALL.
+::
+
/* Fix the size of the union. */
char padding[256];
};
diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..efb51ee92683 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -207,7 +207,7 @@ X: arch/*/include/uapi/
X: include/uapi/
ABIT UGURU 1,2 HARDWARE MONITOR DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-hwmon@vger.kernel.org
S: Maintained
F: drivers/hwmon/abituguru.c
@@ -371,7 +371,7 @@ S: Maintained
F: drivers/platform/x86/quickstart.c
ACPI SERIAL MULTI INSTANTIATE DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
F: drivers/platform/x86/serial-multi-instantiate.c
@@ -1157,7 +1157,6 @@ F: arch/x86/include/asm/amd/node.h
F: arch/x86/kernel/amd_node.c
AMD PDS CORE DRIVER
-M: Shannon Nelson <shannon.nelson@amd.com>
M: Brett Creeley <brett.creeley@amd.com>
L: netdev@vger.kernel.org
S: Maintained
@@ -3551,7 +3550,7 @@ F: arch/arm64/boot/Makefile
F: scripts/make_fit.py
ARM64 PLATFORM DRIVERS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
R: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
L: platform-driver-x86@vger.kernel.org
@@ -3712,7 +3711,7 @@ F: drivers/platform/x86/asus*.c
F: drivers/platform/x86/eeepc*.c
ASUS TF103C DOCK DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
@@ -4555,6 +4554,7 @@ BPF [NETWORKING] (tcx & tc BPF, sock_addr)
M: Martin KaFai Lau <martin.lau@linux.dev>
M: Daniel Borkmann <daniel@iogearbox.net>
R: John Fastabend <john.fastabend@gmail.com>
+R: Stanislav Fomichev <sdf@fomichev.me>
L: bpf@vger.kernel.org
L: netdev@vger.kernel.org
S: Maintained
@@ -5613,14 +5613,14 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/peter.chen/usb.git
F: drivers/usb/chipidea/
CHIPONE ICN8318 I2C TOUCHSCREEN DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml
F: drivers/input/touchscreen/chipone_icn8318.c
CHIPONE ICN8505 I2C TOUCHSCREEN DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: drivers/input/touchscreen/chipone_icn8505.c
@@ -6254,6 +6254,7 @@ F: include/linux/cpuhotplug.h
F: include/linux/smpboot.h
F: kernel/cpu.c
F: kernel/smpboot.*
+F: rust/helper/cpu.c
F: rust/kernel/cpu.rs
CPU IDLE TIME MANAGEMENT FRAMEWORK
@@ -6917,7 +6918,7 @@ F: include/dt-bindings/pmu/exynos_ppmu.h
F: include/linux/devfreq-event.h
DEVICE RESOURCE MANAGEMENT HELPERS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
R: Matti Vaittinen <mazziesaccount@gmail.com>
S: Maintained
F: include/linux/devm-helpers.h
@@ -7516,7 +7517,7 @@ F: drivers/gpu/drm/gud/
F: include/drm/gud.h
DRM DRIVER FOR GRAIN MEDIA GM12U320 PROJECTORS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
S: Maintained
T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
F: drivers/gpu/drm/tiny/gm12u320.c
@@ -7916,7 +7917,7 @@ F: drivers/gpu/drm/ci/xfails/vkms*
F: drivers/gpu/drm/vkms/
DRM DRIVER FOR VIRTUALBOX VIRTUAL GPU
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
@@ -8317,7 +8318,7 @@ F: drivers/gpu/drm/panel/
F: include/drm/drm_panel.h
DRM PRIVACY-SCREEN CLASS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
@@ -9940,7 +9941,6 @@ F: drivers/fwctl/mlx5/
FWCTL PDS DRIVER
M: Brett Creeley <brett.creeley@amd.com>
-R: Shannon Nelson <shannon.nelson@amd.com>
L: linux-kernel@vger.kernel.org
S: Maintained
F: drivers/fwctl/pds/
@@ -10221,7 +10221,7 @@ S: Maintained
F: Documentation/devicetree/bindings/connector/gocontroll,moduline-module-slot.yaml
GOODIX TOUCHSCREEN
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: drivers/input/touchscreen/goodix*
@@ -10260,7 +10260,7 @@ F: include/dt-bindings/clock/google,gs101.h
K: [gG]oogle.?[tT]ensor
GPD POCKET FAN DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
F: drivers/platform/x86/gpd-pocket-fan.c
@@ -10839,7 +10839,7 @@ S: Maintained
F: drivers/dma/hisi_dma.c
HISILICON GPIO DRIVER
-M: Jay Fang <f.fangjian@huawei.com>
+M: Yang Shen <shenyang39@huawei.com>
L: linux-gpio@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/gpio/hisilicon,ascend910-gpio.yaml
@@ -11155,7 +11155,8 @@ F: include/linux/platform_data/huawei-gaokun-ec.h
HUGETLB SUBSYSTEM
M: Muchun Song <muchun.song@linux.dev>
-R: Oscar Salvador <osalvador@suse.de>
+M: Oscar Salvador <osalvador@suse.de>
+R: David Hildenbrand <david@redhat.com>
L: linux-mm@kvack.org
S: Maintained
F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages
@@ -11166,6 +11167,7 @@ F: fs/hugetlbfs/
F: include/linux/hugetlb.h
F: include/trace/events/hugetlbfs.h
F: mm/hugetlb.c
+F: mm/hugetlb_cgroup.c
F: mm/hugetlb_cma.c
F: mm/hugetlb_cma.h
F: mm/hugetlb_vmemmap.c
@@ -11421,7 +11423,7 @@ F: drivers/i2c/busses/i2c-via.c
F: drivers/i2c/busses/i2c-viapro.c
I2C/SMBUS INTEL CHT WHISKEY COVE PMIC DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-i2c@vger.kernel.org
S: Maintained
F: drivers/i2c/busses/i2c-cht-wc.c
@@ -12011,13 +12013,13 @@ S: Supported
F: sound/soc/intel/
INTEL ATOMISP2 DUMMY / POWER-MANAGEMENT DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
F: drivers/platform/x86/intel/atomisp2/pm.c
INTEL ATOMISP2 LED DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
F: drivers/platform/x86/intel/atomisp2/led.c
@@ -13345,6 +13347,7 @@ M: Alexander Graf <graf@amazon.com>
M: Mike Rapoport <rppt@kernel.org>
M: Changyuan Lyu <changyuanl@google.com>
L: kexec@lists.infradead.org
+L: linux-mm@kvack.org
S: Maintained
F: Documentation/admin-guide/mm/kho.rst
F: Documentation/core-api/kho/*
@@ -13678,7 +13681,7 @@ S: Maintained
F: drivers/platform/x86/lenovo-wmi-hotkey-utilities.c
LETSKETCH HID TABLET DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -13728,7 +13731,7 @@ F: drivers/ata/sata_gemini.c
F: drivers/ata/sata_gemini.h
LIBATA SATA AHCI PLATFORM devices support
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-ide@vger.kernel.org
S: Maintained
F: drivers/ata/ahci_platform.c
@@ -13798,7 +13801,7 @@ M: Oliver O'Halloran <oohall@gmail.com>
L: nvdimm@lists.linux.dev
S: Supported
Q: https://patchwork.kernel.org/project/linux-nvdimm/list/
-F: Documentation/devicetree/bindings/pmem/pmem-region.txt
+F: Documentation/devicetree/bindings/pmem/pmem-region.yaml
F: drivers/nvdimm/of_pmem.c
LIBNVDIMM: NON-VOLATILE MEMORY DEVICE SUBSYSTEM
@@ -14098,7 +14101,7 @@ F: Documentation/admin-guide/ldm.rst
F: block/partitions/ldm.*
LOGITECH HID GAMING KEYBOARDS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git
@@ -14780,7 +14783,7 @@ F: Documentation/devicetree/bindings/power/supply/maxim,max17040.yaml
F: drivers/power/supply/max17040_battery.c
MAXIM MAX17042 FAMILY FUEL GAUGE DRIVERS
-R: Hans de Goede <hdegoede@redhat.com>
+R: Hans de Goede <hansg@kernel.org>
R: Krzysztof Kozlowski <krzk@kernel.org>
R: Marek Szyprowski <m.szyprowski@samsung.com>
R: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@puri.sm>
@@ -15582,7 +15585,7 @@ Q: https://patchwork.kernel.org/project/netdevbpf/list/
F: drivers/net/ethernet/mellanox/mlxfw/
MELLANOX HARDWARE PLATFORM SUPPORT
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
M: Vadim Pasternak <vadimp@nvidia.com>
L: platform-driver-x86@vger.kernel.org
@@ -15676,8 +15679,11 @@ S: Maintained
F: Documentation/core-api/boot-time-mm.rst
F: Documentation/core-api/kho/bindings/memblock/*
F: include/linux/memblock.h
+F: mm/bootmem_info.c
F: mm/memblock.c
+F: mm/memtest.c
F: mm/mm_init.c
+F: mm/rodata_test.c
F: tools/testing/memblock/
MEMORY ALLOCATION PROFILING
@@ -15732,7 +15738,6 @@ F: Documentation/admin-guide/mm/
F: Documentation/mm/
F: include/linux/gfp.h
F: include/linux/gfp_types.h
-F: include/linux/memfd.h
F: include/linux/memory_hotplug.h
F: include/linux/memory-tiers.h
F: include/linux/mempolicy.h
@@ -15792,6 +15797,10 @@ S: Maintained
W: http://www.linux-mm.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
F: mm/gup.c
+F: mm/gup_test.c
+F: mm/gup_test.h
+F: tools/testing/selftests/mm/gup_longterm.c
+F: tools/testing/selftests/mm/gup_test.c
MEMORY MANAGEMENT - KSM (Kernel Samepage Merging)
M: Andrew Morton <akpm@linux-foundation.org>
@@ -15868,6 +15877,7 @@ L: linux-mm@kvack.org
S: Maintained
F: mm/pt_reclaim.c
F: mm/vmscan.c
+F: mm/workingset.c
MEMORY MANAGEMENT - RMAP (REVERSE MAPPING)
M: Andrew Morton <akpm@linux-foundation.org>
@@ -15880,6 +15890,7 @@ R: Harry Yoo <harry.yoo@oracle.com>
L: linux-mm@kvack.org
S: Maintained
F: include/linux/rmap.h
+F: mm/page_vma_mapped.c
F: mm/rmap.c
MEMORY MANAGEMENT - SECRETMEM
@@ -15919,6 +15930,7 @@ R: Liam R. Howlett <Liam.Howlett@oracle.com>
R: Nico Pache <npache@redhat.com>
R: Ryan Roberts <ryan.roberts@arm.com>
R: Dev Jain <dev.jain@arm.com>
+R: Barry Song <baohua@kernel.org>
L: linux-mm@kvack.org
S: Maintained
W: http://www.linux-mm.org
@@ -15971,11 +15983,14 @@ S: Maintained
W: http://www.linux-mm.org
T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
F: include/trace/events/mmap.h
+F: mm/mincore.c
F: mm/mlock.c
F: mm/mmap.c
F: mm/mprotect.c
F: mm/mremap.c
F: mm/mseal.c
+F: mm/msync.c
+F: mm/nommu.c
F: mm/vma.c
F: mm/vma.h
F: mm/vma_exec.c
@@ -16538,7 +16553,7 @@ S: Maintained
F: drivers/platform/surface/surface_gpe.c
MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
M: Maximilian Luz <luzmaximilian@gmail.com>
L: platform-driver-x86@vger.kernel.org
@@ -17493,7 +17508,7 @@ F: tools/testing/selftests/net/srv6*
NETWORKING [TCP]
M: Eric Dumazet <edumazet@google.com>
M: Neal Cardwell <ncardwell@google.com>
-R: Kuniyuki Iwashima <kuniyu@amazon.com>
+R: Kuniyuki Iwashima <kuniyu@google.com>
L: netdev@vger.kernel.org
S: Maintained
F: Documentation/networking/net_cachelines/tcp_sock.rst
@@ -17523,7 +17538,7 @@ F: net/tls/*
NETWORKING [SOCKETS]
M: Eric Dumazet <edumazet@google.com>
-M: Kuniyuki Iwashima <kuniyu@amazon.com>
+M: Kuniyuki Iwashima <kuniyu@google.com>
M: Paolo Abeni <pabeni@redhat.com>
M: Willem de Bruijn <willemb@google.com>
S: Maintained
@@ -17538,7 +17553,7 @@ F: net/core/scm.c
F: net/socket.c
NETWORKING [UNIX SOCKETS]
-M: Kuniyuki Iwashima <kuniyu@amazon.com>
+M: Kuniyuki Iwashima <kuniyu@google.com>
S: Maintained
F: include/net/af_unix.h
F: include/net/netns/unix.h
@@ -17706,7 +17721,7 @@ F: tools/include/nolibc/
F: tools/testing/selftests/nolibc/
NOVATEK NVT-TS I2C TOUCHSCREEN DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/input/touchscreen/novatek,nvt-ts.yaml
@@ -19376,7 +19391,7 @@ F: crypto/pcrypt.c
F: include/crypto/pcrypt.h
PDS DSC VIRTIO DATA PATH ACCELERATOR
-R: Shannon Nelson <shannon.nelson@amd.com>
+R: Brett Creeley <brett.creeley@amd.com>
F: drivers/vdpa/pds/
PECI HARDWARE MONITORING DRIVERS
@@ -19398,7 +19413,6 @@ F: include/linux/peci-cpu.h
F: include/linux/peci.h
PENSANDO ETHERNET DRIVERS
-M: Shannon Nelson <shannon.nelson@amd.com>
M: Brett Creeley <brett.creeley@amd.com>
L: netdev@vger.kernel.org
S: Maintained
@@ -22171,7 +22185,7 @@ R: Tejun Heo <tj@kernel.org>
R: David Vernet <void@manifault.com>
R: Andrea Righi <arighi@nvidia.com>
R: Changwoo Min <changwoo@igalia.com>
-L: linux-kernel@vger.kernel.org
+L: sched-ext@lists.linux.dev
S: Maintained
W: https://github.com/sched-ext/scx
T: git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext.git
@@ -22708,7 +22722,7 @@ K: fu[57]40
K: [^@]sifive
SILEAD TOUCHSCREEN DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
L: platform-driver-x86@vger.kernel.org
S: Maintained
@@ -22741,7 +22755,7 @@ F: Documentation/devicetree/bindings/i3c/silvaco,i3c-master.yaml
F: drivers/i3c/master/svc-i3c-master.c
SIMPLEFB FB DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-fbdev@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/display/simple-framebuffer.yaml
@@ -22870,7 +22884,7 @@ F: Documentation/hwmon/emc2103.rst
F: drivers/hwmon/emc2103.c
SMSC SCH5627 HARDWARE MONITOR DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-hwmon@vger.kernel.org
S: Supported
F: Documentation/hwmon/sch5627.rst
@@ -23525,7 +23539,7 @@ S: Supported
F: Documentation/process/stable-kernel-rules.rst
STAGING - ATOMISP DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Mauro Carvalho Chehab <mchehab@kernel.org>
R: Sakari Ailus <sakari.ailus@linux.intel.com>
L: linux-media@vger.kernel.org
@@ -23661,7 +23675,6 @@ F: include/dt-bindings/clock/starfive?jh71*.h
STARFIVE JH71X0 PINCTRL DRIVERS
M: Emil Renner Berthing <kernel@esmil.dk>
-M: Jianlong Huang <jianlong.huang@starfivetech.com>
M: Hal Feng <hal.feng@starfivetech.com>
L: linux-gpio@vger.kernel.org
S: Maintained
@@ -23822,7 +23835,7 @@ F: arch/m68k/sun3*/
F: drivers/net/ethernet/i825xx/sun3*
SUN4I LOW RES ADC ATTACHED TABLET KEYS DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
@@ -25028,8 +25041,11 @@ M: Hugh Dickins <hughd@google.com>
R: Baolin Wang <baolin.wang@linux.alibaba.com>
L: linux-mm@kvack.org
S: Maintained
+F: include/linux/memfd.h
F: include/linux/shmem_fs.h
+F: mm/memfd.c
F: mm/shmem.c
+F: mm/shmem_quota.c
TOMOYO SECURITY MODULE
M: Kentaro Takeda <takedakn@nttdata.co.jp>
@@ -25590,7 +25606,7 @@ F: Documentation/hid/hiddev.rst
F: drivers/hid/usbhid/
USB INTEL XHCI ROLE MUX DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: drivers/usb/roles/intel-xhci-usb-role-switch.c
@@ -25781,7 +25797,7 @@ F: Documentation/firmware-guide/acpi/intel-pmc-mux.rst
F: drivers/usb/typec/mux/intel_pmc_mux.c
USB TYPEC PI3USB30532 MUX DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-usb@vger.kernel.org
S: Maintained
F: drivers/usb/typec/mux/pi3usb30532.c
@@ -25810,7 +25826,7 @@ F: drivers/usb/host/uhci*
USB VIDEO CLASS
M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-media@vger.kernel.org
S: Maintained
W: http://www.ideasonboard.org/uvc/
@@ -26341,7 +26357,7 @@ F: include/uapi/linux/virtio_snd.h
F: sound/virtio/*
VIRTUAL BOX GUEST DEVICE DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Arnd Bergmann <arnd@arndb.de>
M: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
S: Maintained
@@ -26350,7 +26366,7 @@ F: include/linux/vbox_utils.h
F: include/uapi/linux/vbox*.h
VIRTUAL BOX SHARED FOLDER VFS DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-fsdevel@vger.kernel.org
S: Maintained
F: fs/vboxsf/*
@@ -26604,7 +26620,7 @@ F: drivers/mmc/host/wbsd.*
WACOM PROTOCOL 4 SERIAL TABLETS
M: Julian Squires <julian@cipht.net>
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: linux-input@vger.kernel.org
S: Maintained
F: drivers/input/tablet/wacom_serial4.c
@@ -26771,7 +26787,7 @@ F: include/linux/wwan.h
F: include/uapi/linux/wwan.h
X-POWERS AXP288 PMIC DRIVERS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
S: Maintained
F: drivers/acpi/pmic/intel_pmic_xpower.c
N: axp288
@@ -26863,14 +26879,14 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/mm
F: arch/x86/mm/
X86 PLATFORM ANDROID TABLETS DSDT FIXUP DRIVER
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
L: platform-driver-x86@vger.kernel.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/pdx86/platform-drivers-x86.git
F: drivers/platform/x86/x86-android-tablets/
X86 PLATFORM DRIVERS
-M: Hans de Goede <hdegoede@redhat.com>
+M: Hans de Goede <hansg@kernel.org>
M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
L: platform-driver-x86@vger.kernel.org
S: Maintained
@@ -26967,6 +26983,7 @@ M: David S. Miller <davem@davemloft.net>
M: Jakub Kicinski <kuba@kernel.org>
M: Jesper Dangaard Brouer <hawk@kernel.org>
M: John Fastabend <john.fastabend@gmail.com>
+R: Stanislav Fomichev <sdf@fomichev.me>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Supported
@@ -26988,6 +27005,7 @@ M: Björn Töpel <bjorn@kernel.org>
M: Magnus Karlsson <magnus.karlsson@intel.com>
M: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
R: Jonathan Lemon <jonathan.lemon@gmail.com>
+R: Stanislav Fomichev <sdf@fomichev.me>
L: netdev@vger.kernel.org
L: bpf@vger.kernel.org
S: Maintained
diff --git a/Makefile b/Makefile
index 35e6e5240c61..f884dfe10246 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 6
PATCHLEVEL = 16
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
NAME = Baby Opossum Posse
# *DOCUMENTATION*
@@ -1832,12 +1832,9 @@ rustfmtcheck: rustfmt
# Misc
# ---------------------------------------------------------------------------
-# Run misc checks when ${KBUILD_EXTRA_WARN} contains 1
PHONY += misc-check
-ifneq ($(findstring 1,$(KBUILD_EXTRA_WARN)),)
misc-check:
$(Q)$(srctree)/scripts/misc-check
-endif
all: misc-check
diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h
index 2676017f42f1..44e7aedac6e8 100644
--- a/arch/alpha/include/asm/pgtable.h
+++ b/arch/alpha/include/asm/pgtable.h
@@ -327,7 +327,7 @@ extern inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 005d9e4d187a..a31bbf5c8bbc 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -144,7 +144,7 @@
#define ARC_AUX_AGU_MOD2 0x5E2
#define ARC_AUX_AGU_MOD3 0x5E3
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <soc/arc/arc_aux.h>
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 592d7fffc223..e615c42b93ba 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -6,7 +6,7 @@
#ifndef _ASM_ARC_ATOMIC_H
#define _ASM_ARC_ATOMIC_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/types.h>
#include <linux/compiler.h>
@@ -31,6 +31,6 @@
#include <asm/atomic64-arcv2.h>
#endif
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/atomic64-arcv2.h b/arch/arc/include/asm/atomic64-arcv2.h
index 9b5791b85471..73080a664369 100644
--- a/arch/arc/include/asm/atomic64-arcv2.h
+++ b/arch/arc/include/asm/atomic64-arcv2.h
@@ -137,12 +137,9 @@ ATOMIC64_OPS(xor, xor, xor)
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
-static inline s64
-arch_atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
+static inline u64 __arch_cmpxchg64_relaxed(volatile void *ptr, u64 old, u64 new)
{
- s64 prev;
-
- smp_mb();
+ u64 prev;
__asm__ __volatile__(
"1: llockd %0, [%1] \n"
@@ -152,14 +149,12 @@ arch_atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
" bnz 1b \n"
"2: \n"
: "=&r"(prev)
- : "r"(ptr), "ir"(expected), "r"(new)
- : "cc"); /* memory clobber comes from smp_mb() */
-
- smp_mb();
+ : "r"(ptr), "ir"(old), "r"(new)
+ : "memory", "cc");
return prev;
}
-#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
+#define arch_cmpxchg64_relaxed __arch_cmpxchg64_relaxed
static inline s64 arch_atomic64_xchg(atomic64_t *ptr, s64 new)
{
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index f5a936496f06..5340c2871392 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -10,7 +10,7 @@
#error only <linux/bitops.h> can be included directly
#endif
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/types.h>
#include <linux/compiler.h>
@@ -192,6 +192,6 @@ static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
#include <asm-generic/bitops/le.h>
#include <asm-generic/bitops/ext2-atomic-setbit.h>
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/bug.h b/arch/arc/include/asm/bug.h
index 4c453ba96c51..171c16021f70 100644
--- a/arch/arc/include/asm/bug.h
+++ b/arch/arc/include/asm/bug.h
@@ -6,7 +6,7 @@
#ifndef _ASM_ARC_BUG_H
#define _ASM_ARC_BUG_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <asm/ptrace.h>
@@ -29,6 +29,6 @@ void die(const char *str, struct pt_regs *regs, unsigned long address);
#include <asm-generic/bug.h>
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index f0f1fc5d62b6..040a97f4dd82 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -23,7 +23,7 @@
*/
#define ARC_UNCACHED_ADDR_SPACE 0xc0000000
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/build_bug.h>
@@ -65,7 +65,7 @@
extern int ioc_enable;
extern unsigned long perip_base, perip_end;
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
/* Instruction cache related Auxiliary registers */
#define ARC_REG_IC_BCR 0x77 /* Build Config reg */
diff --git a/arch/arc/include/asm/current.h b/arch/arc/include/asm/current.h
index 06be89f6f2f0..03ffd005f3fa 100644
--- a/arch/arc/include/asm/current.h
+++ b/arch/arc/include/asm/current.h
@@ -9,7 +9,7 @@
#ifndef _ASM_ARC_CURRENT_H
#define _ASM_ARC_CURRENT_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#ifdef CONFIG_ARC_CURR_IN_REG
@@ -20,6 +20,6 @@ register struct task_struct *curr_arc asm("gp");
#include <asm-generic/current.h>
#endif /* ! CONFIG_ARC_CURR_IN_REG */
-#endif /* ! __ASSEMBLY__ */
+#endif /* ! __ASSEMBLER__ */
#endif /* _ASM_ARC_CURRENT_H */
diff --git a/arch/arc/include/asm/dsp-impl.h b/arch/arc/include/asm/dsp-impl.h
index cd5636dfeb6f..fd5fdaad90c1 100644
--- a/arch/arc/include/asm/dsp-impl.h
+++ b/arch/arc/include/asm/dsp-impl.h
@@ -11,7 +11,7 @@
#define DSP_CTRL_DISABLED_ALL 0
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
/* clobbers r5 register */
.macro DSP_EARLY_INIT
diff --git a/arch/arc/include/asm/dsp.h b/arch/arc/include/asm/dsp.h
index f496dbc4640b..eeaaf4e4eabd 100644
--- a/arch/arc/include/asm/dsp.h
+++ b/arch/arc/include/asm/dsp.h
@@ -7,7 +7,7 @@
#ifndef __ASM_ARC_DSP_H
#define __ASM_ARC_DSP_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
/*
* DSP-related saved registers - need to be saved only when you are
@@ -24,6 +24,6 @@ struct dsp_callee_regs {
#endif
};
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif /* __ASM_ARC_DSP_H */
diff --git a/arch/arc/include/asm/dwarf.h b/arch/arc/include/asm/dwarf.h
index a0d5ebe1bc3f..1524c5cf8b59 100644
--- a/arch/arc/include/asm/dwarf.h
+++ b/arch/arc/include/asm/dwarf.h
@@ -6,7 +6,7 @@
#ifndef _ASM_ARC_DWARF_H
#define _ASM_ARC_DWARF_H
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
#ifdef ARC_DW2_UNWIND_AS_CFI
@@ -38,6 +38,6 @@
#endif /* !ARC_DW2_UNWIND_AS_CFI */
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif /* _ASM_ARC_DWARF_H */
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 38c35722cebf..f453af251a1a 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -13,7 +13,7 @@
#include <asm/processor.h> /* For VMALLOC_START */
#include <asm/mmu.h>
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
#ifdef CONFIG_ISA_ARCOMPACT
#include <asm/entry-compact.h> /* ISA specific bits */
@@ -146,7 +146,7 @@
#endif /* CONFIG_ARC_CURR_IN_REG */
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
extern void do_signal(struct pt_regs *);
extern void do_notify_resume(struct pt_regs *);
diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h
index fb3c21f1a238..30aea562f8aa 100644
--- a/arch/arc/include/asm/irqflags-arcv2.h
+++ b/arch/arc/include/asm/irqflags-arcv2.h
@@ -50,7 +50,7 @@
#define ISA_INIT_STATUS_BITS (STATUS_IE_MASK | __AD_ENB | \
(ARCV2_IRQ_DEF_PRIO << 1))
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
/*
* Save IRQ state and disable IRQs
@@ -170,6 +170,6 @@ static inline void arc_softirq_clear(int irq)
seti
.endm
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index 936a2f21f315..85c2f6bcde0c 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -40,7 +40,7 @@
#define ISA_INIT_STATUS_BITS STATUS_IE_MASK
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
/******************************************************************
* IRQ Control Macros
@@ -196,6 +196,6 @@ static inline int arch_irqs_disabled(void)
flag \scratch
.endm
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/jump_label.h b/arch/arc/include/asm/jump_label.h
index a339223d9e05..66ead75784d9 100644
--- a/arch/arc/include/asm/jump_label.h
+++ b/arch/arc/include/asm/jump_label.h
@@ -2,7 +2,7 @@
#ifndef _ASM_ARC_JUMP_LABEL_H
#define _ASM_ARC_JUMP_LABEL_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/stringify.h>
#include <linux/types.h>
@@ -68,5 +68,5 @@ struct jump_entry {
jump_label_t key;
};
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/linkage.h b/arch/arc/include/asm/linkage.h
index 8a3fb71e9cfa..ba3cb65b5eaa 100644
--- a/arch/arc/include/asm/linkage.h
+++ b/arch/arc/include/asm/linkage.h
@@ -12,7 +12,7 @@
#define __ALIGN .align 4
#define __ALIGN_STR __stringify(__ALIGN)
-#ifdef __ASSEMBLY__
+#ifdef __ASSEMBLER__
.macro ST2 e, o, off
#ifdef CONFIG_ARC_HAS_LL64
@@ -61,7 +61,7 @@
CFI_ENDPROC ASM_NL \
.size name, .-name
-#else /* !__ASSEMBLY__ */
+#else /* !__ASSEMBLER__ */
#ifdef CONFIG_ARC_HAS_ICCM
#define __arcfp_code __section(".text.arcfp")
@@ -75,6 +75,6 @@
#define __arcfp_data __section(".data")
#endif
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/mmu-arcv2.h b/arch/arc/include/asm/mmu-arcv2.h
index 41412642f279..5e5482026ac9 100644
--- a/arch/arc/include/asm/mmu-arcv2.h
+++ b/arch/arc/include/asm/mmu-arcv2.h
@@ -69,7 +69,7 @@
#define PTE_BITS_NON_RWX_IN_PD1 (PAGE_MASK_PHYS | _PAGE_CACHEABLE)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
struct mm_struct;
extern int pae40_exist_but_not_enab(void);
@@ -100,6 +100,6 @@ static inline void mmu_setup_pgd(struct mm_struct *mm, void *pgd)
sr \reg, [ARC_REG_PID]
.endm
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/mmu.h b/arch/arc/include/asm/mmu.h
index 4ae2db59d494..e3b35ceab582 100644
--- a/arch/arc/include/asm/mmu.h
+++ b/arch/arc/include/asm/mmu.h
@@ -6,7 +6,7 @@
#ifndef _ASM_ARC_MMU_H
#define _ASM_ARC_MMU_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/threads.h> /* NR_CPUS */
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index def0dfb95b43..9720fe6b2c24 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -19,7 +19,7 @@
#endif /* CONFIG_ARC_HAS_PAE40 */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#define clear_page(paddr) memset((paddr), 0, PAGE_SIZE)
#define copy_user_page(to, from, vaddr, pg) copy_page(to, from)
@@ -136,6 +136,6 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
#include <asm-generic/memory_model.h> /* page_to_pfn, pfn_to_page */
#include <asm-generic/getorder.h>
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/pgtable-bits-arcv2.h b/arch/arc/include/asm/pgtable-bits-arcv2.h
index 8ebec1b21d24..4630c5acca05 100644
--- a/arch/arc/include/asm/pgtable-bits-arcv2.h
+++ b/arch/arc/include/asm/pgtable-bits-arcv2.h
@@ -75,7 +75,7 @@
* This is to enable COW mechanism
*/
/* xwr */
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#define pte_write(pte) (pte_val(pte) & _PAGE_WRITE)
#define pte_dirty(pte) (pte_val(pte) & _PAGE_DIRTY)
@@ -130,7 +130,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
@@ -142,6 +142,6 @@ PTE_BIT_FUNC(swp_clear_exclusive, &= ~(_PAGE_SWP_EXCLUSIVE));
#include <asm/hugepage.h>
#endif
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/pgtable-levels.h b/arch/arc/include/asm/pgtable-levels.h
index d1ce4b0f1071..c8f9273372c0 100644
--- a/arch/arc/include/asm/pgtable-levels.h
+++ b/arch/arc/include/asm/pgtable-levels.h
@@ -85,7 +85,7 @@
#define PTRS_PER_PTE BIT(PMD_SHIFT - PAGE_SHIFT)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#if CONFIG_PGTABLE_LEVELS > 3
#include <asm-generic/pgtable-nop4d.h>
@@ -181,6 +181,6 @@
#define pmd_leaf(x) (pmd_val(x) & _PAGE_HW_SZ)
#endif
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 4cf45a99fd79..bd580e2b62d7 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -19,7 +19,7 @@
*/
#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
extern char empty_zero_page[PAGE_SIZE];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
@@ -29,6 +29,6 @@ extern pgd_t swapper_pg_dir[] __aligned(PAGE_SIZE);
/* to cope with aliasing VIPT cache */
#define HAVE_ARCH_UNMAPPED_AREA
-#endif /* __ASSEMBLY__ */
+#endif /* __ASSEMBLER__ */
#endif
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index d606658e2fe7..7f7901ac6643 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -11,7 +11,7 @@
#ifndef __ASM_ARC_PROCESSOR_H
#define __ASM_ARC_PROCESSOR_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <asm/ptrace.h>
#include <asm/dsp.h>
@@ -66,7 +66,7 @@ extern void start_thread(struct pt_regs * regs, unsigned long pc,
extern unsigned int __get_wchan(struct task_struct *p);
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
/*
* Default System Memory Map on ARC
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index cf79df0b2570..f6c052af8f4d 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -10,7 +10,7 @@
#include <uapi/asm/ptrace.h>
#include <linux/compiler.h>
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
typedef union {
struct {
@@ -172,6 +172,6 @@ static inline unsigned long regs_get_register(struct pt_regs *regs,
extern int syscall_trace_enter(struct pt_regs *);
extern void syscall_trace_exit(struct pt_regs *);
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif /* __ASM_PTRACE_H */
diff --git a/arch/arc/include/asm/switch_to.h b/arch/arc/include/asm/switch_to.h
index 1f85de8288b1..5806106a65f9 100644
--- a/arch/arc/include/asm/switch_to.h
+++ b/arch/arc/include/asm/switch_to.h
@@ -6,7 +6,7 @@
#ifndef _ASM_ARC_SWITCH_TO_H
#define _ASM_ARC_SWITCH_TO_H
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/sched.h>
#include <asm/dsp-impl.h>
diff --git a/arch/arc/include/asm/thread_info.h b/arch/arc/include/asm/thread_info.h
index 12daaf3a61ea..255d2c774219 100644
--- a/arch/arc/include/asm/thread_info.h
+++ b/arch/arc/include/asm/thread_info.h
@@ -24,7 +24,7 @@
#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER)
#define THREAD_SHIFT (PAGE_SHIFT << THREAD_SIZE_ORDER)
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
#include <linux/thread_info.h>
@@ -62,7 +62,7 @@ static inline __attribute_const__ struct thread_info *current_thread_info(void)
return (struct thread_info *)(sp & ~(THREAD_SIZE - 1));
}
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
/*
* thread information flags
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 2a6eff57f6dd..3ae832db278c 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -14,7 +14,7 @@
#define PTRACE_GET_THREAD_AREA 25
-#ifndef __ASSEMBLY__
+#ifndef __ASSEMBLER__
/*
* Userspace ABI: Register state needed by
* -ptrace (gdbserver)
@@ -53,6 +53,6 @@ struct user_regs_arcv2 {
unsigned long r30, r58, r59;
};
-#endif /* !__ASSEMBLY__ */
+#endif /* !__ASSEMBLER__ */
#endif /* _UAPI__ASM_ARC_PTRACE_H */
diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c
index d8969dab12d4..789cfb9ea14e 100644
--- a/arch/arc/kernel/unwind.c
+++ b/arch/arc/kernel/unwind.c
@@ -241,15 +241,6 @@ static int cmp_eh_frame_hdr_table_entries(const void *p1, const void *p2)
return (e1->start > e2->start) - (e1->start < e2->start);
}
-static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
-{
- struct eh_frame_hdr_table_entry *e1 = p1;
- struct eh_frame_hdr_table_entry *e2 = p2;
-
- swap(e1->start, e2->start);
- swap(e1->fde, e2->fde);
-}
-
static void init_unwind_hdr(struct unwind_table *table,
void *(*alloc) (unsigned long))
{
@@ -345,7 +336,7 @@ static void init_unwind_hdr(struct unwind_table *table,
sort(header->table,
n,
sizeof(*header->table),
- cmp_eh_frame_hdr_table_entries, swap_eh_frame_hdr_table_entries);
+ cmp_eh_frame_hdr_table_entries, NULL);
table->hdrsz = hdrSize;
smp_wmb();
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 7f1c3b4e3e04..86378eec7757 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -301,7 +301,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(swp) __pte((swp).val)
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_isset(pte, L_PTE_SWP_EXCLUSIVE);
}
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index bd020fc28aa9..0720898f563e 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -561,68 +561,6 @@ static __always_inline void kvm_incr_pc(struct kvm_vcpu *vcpu)
vcpu_set_flag((v), e); \
} while (0)
-#define __build_check_all_or_none(r, bits) \
- BUILD_BUG_ON(((r) & (bits)) && ((r) & (bits)) != (bits))
-
-#define __cpacr_to_cptr_clr(clr, set) \
- ({ \
- u64 cptr = 0; \
- \
- if ((set) & CPACR_EL1_FPEN) \
- cptr |= CPTR_EL2_TFP; \
- if ((set) & CPACR_EL1_ZEN) \
- cptr |= CPTR_EL2_TZ; \
- if ((set) & CPACR_EL1_SMEN) \
- cptr |= CPTR_EL2_TSM; \
- if ((clr) & CPACR_EL1_TTA) \
- cptr |= CPTR_EL2_TTA; \
- if ((clr) & CPTR_EL2_TAM) \
- cptr |= CPTR_EL2_TAM; \
- if ((clr) & CPTR_EL2_TCPAC) \
- cptr |= CPTR_EL2_TCPAC; \
- \
- cptr; \
- })
-
-#define __cpacr_to_cptr_set(clr, set) \
- ({ \
- u64 cptr = 0; \
- \
- if ((clr) & CPACR_EL1_FPEN) \
- cptr |= CPTR_EL2_TFP; \
- if ((clr) & CPACR_EL1_ZEN) \
- cptr |= CPTR_EL2_TZ; \
- if ((clr) & CPACR_EL1_SMEN) \
- cptr |= CPTR_EL2_TSM; \
- if ((set) & CPACR_EL1_TTA) \
- cptr |= CPTR_EL2_TTA; \
- if ((set) & CPTR_EL2_TAM) \
- cptr |= CPTR_EL2_TAM; \
- if ((set) & CPTR_EL2_TCPAC) \
- cptr |= CPTR_EL2_TCPAC; \
- \
- cptr; \
- })
-
-#define cpacr_clear_set(clr, set) \
- do { \
- BUILD_BUG_ON((set) & CPTR_VHE_EL2_RES0); \
- BUILD_BUG_ON((clr) & CPACR_EL1_E0POE); \
- __build_check_all_or_none((clr), CPACR_EL1_FPEN); \
- __build_check_all_or_none((set), CPACR_EL1_FPEN); \
- __build_check_all_or_none((clr), CPACR_EL1_ZEN); \
- __build_check_all_or_none((set), CPACR_EL1_ZEN); \
- __build_check_all_or_none((clr), CPACR_EL1_SMEN); \
- __build_check_all_or_none((set), CPACR_EL1_SMEN); \
- \
- if (has_vhe() || has_hvhe()) \
- sysreg_clear_set(cpacr_el1, clr, set); \
- else \
- sysreg_clear_set(cptr_el2, \
- __cpacr_to_cptr_clr(clr, set), \
- __cpacr_to_cptr_set(clr, set));\
- } while (0)
-
/*
* Returns a 'sanitised' view of CPTR_EL2, translating from nVHE to the VHE
* format if E2H isn't set.
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 6ce2c5173482..d27079968341 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1107,14 +1107,36 @@ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r)
#define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r))
u64 kvm_vcpu_apply_reg_masks(const struct kvm_vcpu *, enum vcpu_sysreg, u64);
+
+#define __vcpu_assign_sys_reg(v, r, val) \
+ do { \
+ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \
+ u64 __v = (val); \
+ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \
+ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \
+ \
+ ctxt_sys_reg(ctxt, (r)) = __v; \
+ } while (0)
+
+#define __vcpu_rmw_sys_reg(v, r, op, val) \
+ do { \
+ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \
+ u64 __v = ctxt_sys_reg(ctxt, (r)); \
+ __v op (val); \
+ if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \
+ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \
+ \
+ ctxt_sys_reg(ctxt, (r)) = __v; \
+ } while (0)
+
#define __vcpu_sys_reg(v,r) \
- (*({ \
+ ({ \
const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \
- u64 *__r = __ctxt_sys_reg(ctxt, (r)); \
+ u64 __v = ctxt_sys_reg(ctxt, (r)); \
if (vcpu_has_nv((v)) && (r) >= __SANITISED_REG_START__) \
- *__r = kvm_vcpu_apply_reg_masks((v), (r), *__r);\
- __r; \
- }))
+ __v = kvm_vcpu_apply_reg_masks((v), (r), __v); \
+ __v; \
+ })
u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg);
void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg);
@@ -1267,9 +1289,8 @@ void kvm_arm_resume_guest(struct kvm *kvm);
})
/*
- * The couple of isb() below are there to guarantee the same behaviour
- * on VHE as on !VHE, where the eret to EL1 acts as a context
- * synchronization event.
+ * The isb() below is there to guarantee the same behaviour on VHE as on !VHE,
+ * where the eret to EL1 acts as a context synchronization event.
*/
#define kvm_call_hyp(f, ...) \
do { \
@@ -1287,7 +1308,6 @@ void kvm_arm_resume_guest(struct kvm *kvm);
\
if (has_vhe()) { \
ret = f(__VA_ARGS__); \
- isb(); \
} else { \
ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \
} \
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 88db8a0c0b37..192d86e1cc76 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -563,7 +563,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE));
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & PTE_SWP_EXCLUSIVE;
}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index a5ca15daeb8a..5954cec19660 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -288,7 +288,9 @@ static void flush_gcs(void)
if (!system_supports_gcs())
return;
- gcs_free(current);
+ current->thread.gcspr_el0 = 0;
+ current->thread.gcs_base = 0;
+ current->thread.gcs_size = 0;
current->thread.gcs_el0_mode = 0;
write_sysreg_s(GCSCRE0_EL1_nTR, SYS_GCSCRE0_EL1);
write_sysreg_s(0, SYS_GCSPR_EL0);
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index a360e52db02f..ee94b72bf8fb 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -141,7 +141,7 @@ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n)
addr += n;
if (regs_within_kernel_stack(regs, (unsigned long)addr))
- return *addr;
+ return READ_ONCE_NOCHECK(*addr);
else
return 0;
}
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index fdbc8beec930..701ea10a63f1 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -108,16 +108,16 @@ static void timer_set_ctl(struct arch_timer_context *ctxt, u32 ctl)
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
- __vcpu_sys_reg(vcpu, CNTV_CTL_EL0) = ctl;
+ __vcpu_assign_sys_reg(vcpu, CNTV_CTL_EL0, ctl);
break;
case TIMER_PTIMER:
- __vcpu_sys_reg(vcpu, CNTP_CTL_EL0) = ctl;
+ __vcpu_assign_sys_reg(vcpu, CNTP_CTL_EL0, ctl);
break;
case TIMER_HVTIMER:
- __vcpu_sys_reg(vcpu, CNTHV_CTL_EL2) = ctl;
+ __vcpu_assign_sys_reg(vcpu, CNTHV_CTL_EL2, ctl);
break;
case TIMER_HPTIMER:
- __vcpu_sys_reg(vcpu, CNTHP_CTL_EL2) = ctl;
+ __vcpu_assign_sys_reg(vcpu, CNTHP_CTL_EL2, ctl);
break;
default:
WARN_ON(1);
@@ -130,16 +130,16 @@ static void timer_set_cval(struct arch_timer_context *ctxt, u64 cval)
switch(arch_timer_ctx_index(ctxt)) {
case TIMER_VTIMER:
- __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0) = cval;
+ __vcpu_assign_sys_reg(vcpu, CNTV_CVAL_EL0, cval);
break;
case TIMER_PTIMER:
- __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = cval;
+ __vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, cval);
break;
case TIMER_HVTIMER:
- __vcpu_sys_reg(vcpu, CNTHV_CVAL_EL2) = cval;
+ __vcpu_assign_sys_reg(vcpu, CNTHV_CVAL_EL2, cval);
break;
case TIMER_HPTIMER:
- __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = cval;
+ __vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, cval);
break;
default:
WARN_ON(1);
@@ -1036,7 +1036,7 @@ void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
if (vcpu_has_nv(vcpu)) {
struct arch_timer_offset *offs = &vcpu_vtimer(vcpu)->offset;
- offs->vcpu_offset = &__vcpu_sys_reg(vcpu, CNTVOFF_EL2);
+ offs->vcpu_offset = __ctxt_sys_reg(&vcpu->arch.ctxt, CNTVOFF_EL2);
offs->vm_offset = &vcpu->kvm->arch.timer_data.poffset;
}
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index de2b4e9c9f9f..38a91bb5d4c7 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2764,7 +2764,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
struct kvm_kernel_irq_routing_entry *new)
{
- if (new->type != KVM_IRQ_ROUTING_MSI)
+ if (old->type != KVM_IRQ_ROUTING_MSI ||
+ new->type != KVM_IRQ_ROUTING_MSI)
return true;
return memcmp(&old->msi, &new->msi, sizeof(new->msi));
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index 0e4c805e7e89..1a7dab333f55 100644
--- a/arch/arm64/kvm/debug.c
+++ b/arch/arm64/kvm/debug.c
@@ -216,9 +216,9 @@ void kvm_debug_set_guest_ownership(struct kvm_vcpu *vcpu)
void kvm_debug_handle_oslar(struct kvm_vcpu *vcpu, u64 val)
{
if (val & OSLAR_EL1_OSLK)
- __vcpu_sys_reg(vcpu, OSLSR_EL1) |= OSLSR_EL1_OSLK;
+ __vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, |=, OSLSR_EL1_OSLK);
else
- __vcpu_sys_reg(vcpu, OSLSR_EL1) &= ~OSLSR_EL1_OSLK;
+ __vcpu_rmw_sys_reg(vcpu, OSLSR_EL1, &=, ~OSLSR_EL1_OSLK);
preempt_disable();
kvm_arch_vcpu_put(vcpu);
diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c
index 7f6e43d25691..8f6c8f57c6b9 100644
--- a/arch/arm64/kvm/fpsimd.c
+++ b/arch/arm64/kvm/fpsimd.c
@@ -103,8 +103,8 @@ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu)
fp_state.sve_state = vcpu->arch.sve_state;
fp_state.sve_vl = vcpu->arch.sve_max_vl;
fp_state.sme_state = NULL;
- fp_state.svcr = &__vcpu_sys_reg(vcpu, SVCR);
- fp_state.fpmr = &__vcpu_sys_reg(vcpu, FPMR);
+ fp_state.svcr = __ctxt_sys_reg(&vcpu->arch.ctxt, SVCR);
+ fp_state.fpmr = __ctxt_sys_reg(&vcpu->arch.ctxt, FPMR);
fp_state.fp_type = &vcpu->arch.fp_type;
if (vcpu_has_sve(vcpu))
diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c
index 424a5107cddb..6a2a899a344e 100644
--- a/arch/arm64/kvm/hyp/exception.c
+++ b/arch/arm64/kvm/hyp/exception.c
@@ -37,7 +37,7 @@ static inline void __vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
if (unlikely(vcpu_has_nv(vcpu)))
vcpu_write_sys_reg(vcpu, val, reg);
else if (!__vcpu_write_sys_reg_to_cpu(val, reg))
- __vcpu_sys_reg(vcpu, reg) = val;
+ __vcpu_assign_sys_reg(vcpu, reg, val);
}
static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
@@ -51,7 +51,7 @@ static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode,
} else if (has_vhe()) {
write_sysreg_el1(val, SYS_SPSR);
} else {
- __vcpu_sys_reg(vcpu, SPSR_EL1) = val;
+ __vcpu_assign_sys_reg(vcpu, SPSR_EL1, val);
}
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index bb9f2eecfb67..2ad57b117385 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -45,7 +45,7 @@ static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu)
if (!vcpu_el1_is_32bit(vcpu))
return;
- __vcpu_sys_reg(vcpu, FPEXC32_EL2) = read_sysreg(fpexc32_el2);
+ __vcpu_assign_sys_reg(vcpu, FPEXC32_EL2, read_sysreg(fpexc32_el2));
}
static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
@@ -65,6 +65,136 @@ static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu)
}
}
+static inline void __activate_cptr_traps_nvhe(struct kvm_vcpu *vcpu)
+{
+ u64 val = CPTR_NVHE_EL2_RES1 | CPTR_EL2_TAM | CPTR_EL2_TTA;
+
+ /*
+ * Always trap SME since it's not supported in KVM.
+ * TSM is RES1 if SME isn't implemented.
+ */
+ val |= CPTR_EL2_TSM;
+
+ if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
+ val |= CPTR_EL2_TZ;
+
+ if (!guest_owns_fp_regs())
+ val |= CPTR_EL2_TFP;
+
+ write_sysreg(val, cptr_el2);
+}
+
+static inline void __activate_cptr_traps_vhe(struct kvm_vcpu *vcpu)
+{
+ /*
+ * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
+ * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
+ * except for some missing controls, such as TAM.
+ * In this case, CPTR_EL2.TAM has the same position with or without
+ * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
+ * shift value for trapping the AMU accesses.
+ */
+ u64 val = CPTR_EL2_TAM | CPACR_EL1_TTA;
+ u64 cptr;
+
+ if (guest_owns_fp_regs()) {
+ val |= CPACR_EL1_FPEN;
+ if (vcpu_has_sve(vcpu))
+ val |= CPACR_EL1_ZEN;
+ }
+
+ if (!vcpu_has_nv(vcpu))
+ goto write;
+
+ /*
+ * The architecture is a bit crap (what a surprise): an EL2 guest
+ * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+ * as they are RES0 in the guest's view. To work around it, trap the
+ * sucker using the very same bit it can't set...
+ */
+ if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+ val |= CPTR_EL2_TCPAC;
+
+ /*
+ * Layer the guest hypervisor's trap configuration on top of our own if
+ * we're in a nested context.
+ */
+ if (is_hyp_ctxt(vcpu))
+ goto write;
+
+ cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+ /*
+ * Pay attention, there's some interesting detail here.
+ *
+ * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
+ * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
+ *
+ * - CPTR_EL2.xEN = x0, traps are enabled
+ * - CPTR_EL2.xEN = x1, traps are disabled
+ *
+ * In other words, bit[0] determines if guest accesses trap or not. In
+ * the interest of simplicity, clear the entire field if the guest
+ * hypervisor has traps enabled to dispel any illusion of something more
+ * complicated taking place.
+ */
+ if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
+ val &= ~CPACR_EL1_FPEN;
+ if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
+ val &= ~CPACR_EL1_ZEN;
+
+ if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+ val |= cptr & CPACR_EL1_E0POE;
+
+ val |= cptr & CPTR_EL2_TCPAC;
+
+write:
+ write_sysreg(val, cpacr_el1);
+}
+
+static inline void __activate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+ if (!guest_owns_fp_regs())
+ __activate_traps_fpsimd32(vcpu);
+
+ if (has_vhe() || has_hvhe())
+ __activate_cptr_traps_vhe(vcpu);
+ else
+ __activate_cptr_traps_nvhe(vcpu);
+}
+
+static inline void __deactivate_cptr_traps_nvhe(struct kvm_vcpu *vcpu)
+{
+ u64 val = CPTR_NVHE_EL2_RES1;
+
+ if (!cpus_have_final_cap(ARM64_SVE))
+ val |= CPTR_EL2_TZ;
+ if (!cpus_have_final_cap(ARM64_SME))
+ val |= CPTR_EL2_TSM;
+
+ write_sysreg(val, cptr_el2);
+}
+
+static inline void __deactivate_cptr_traps_vhe(struct kvm_vcpu *vcpu)
+{
+ u64 val = CPACR_EL1_FPEN;
+
+ if (cpus_have_final_cap(ARM64_SVE))
+ val |= CPACR_EL1_ZEN;
+ if (cpus_have_final_cap(ARM64_SME))
+ val |= CPACR_EL1_SMEN;
+
+ write_sysreg(val, cpacr_el1);
+}
+
+static inline void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+ if (has_vhe() || has_hvhe())
+ __deactivate_cptr_traps_vhe(vcpu);
+ else
+ __deactivate_cptr_traps_nvhe(vcpu);
+}
+
#define reg_to_fgt_masks(reg) \
({ \
struct fgt_masks *m; \
@@ -456,7 +586,7 @@ static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu)
*/
if (vcpu_has_sve(vcpu)) {
zcr_el1 = read_sysreg_el1(SYS_ZCR);
- __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1;
+ __vcpu_assign_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu), zcr_el1);
/*
* The guest's state is always saved using the guest's max VL.
@@ -486,11 +616,6 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu)
*/
if (system_supports_sve()) {
__hyp_sve_save_host();
-
- /* Re-enable SVE traps if not supported for the guest vcpu. */
- if (!vcpu_has_sve(vcpu))
- cpacr_clear_set(CPACR_EL1_ZEN, 0);
-
} else {
__fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs));
}
@@ -541,10 +666,7 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
/* Valid trap. Switch the context: */
/* First disable enough traps to allow us to update the registers */
- if (sve_guest || (is_protected_kvm_enabled() && system_supports_sve()))
- cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN);
- else
- cpacr_clear_set(0, CPACR_EL1_FPEN);
+ __deactivate_cptr_traps(vcpu);
isb();
/* Write out the host state if it's in the registers */
@@ -566,6 +688,13 @@ static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
*host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED;
+ /*
+ * Re-enable traps necessary for the current state of the guest, e.g.
+ * those enabled by a guest hypervisor. The ERET to the guest will
+ * provide the necessary context synchronization.
+ */
+ __activate_cptr_traps(vcpu);
+
return true;
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
index b9cff893bbe0..4d0dbea4c56f 100644
--- a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
+++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h
@@ -307,11 +307,11 @@ static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu)
vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq);
vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq);
- __vcpu_sys_reg(vcpu, DACR32_EL2) = read_sysreg(dacr32_el2);
- __vcpu_sys_reg(vcpu, IFSR32_EL2) = read_sysreg(ifsr32_el2);
+ __vcpu_assign_sys_reg(vcpu, DACR32_EL2, read_sysreg(dacr32_el2));
+ __vcpu_assign_sys_reg(vcpu, IFSR32_EL2, read_sysreg(ifsr32_el2));
if (has_vhe() || kvm_debug_regs_in_use(vcpu))
- __vcpu_sys_reg(vcpu, DBGVCR32_EL2) = read_sysreg(dbgvcr32_el2);
+ __vcpu_assign_sys_reg(vcpu, DBGVCR32_EL2, read_sysreg(dbgvcr32_el2));
}
static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 8e8848de4d47..3206b2c07f82 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -26,7 +26,7 @@ void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt);
static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu)
{
- __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);
+ __vcpu_assign_sys_reg(vcpu, ZCR_EL1, read_sysreg_el1(SYS_ZCR));
/*
* On saving/restoring guest sve state, always use the maximum VL for
* the guest. The layout of the data when saving the sve state depends
@@ -69,7 +69,10 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
if (!guest_owns_fp_regs())
return;
- cpacr_clear_set(0, CPACR_EL1_FPEN | CPACR_EL1_ZEN);
+ /*
+ * Traps have been disabled by __deactivate_cptr_traps(), but there
+ * hasn't necessarily been a context synchronization event yet.
+ */
isb();
if (vcpu_has_sve(vcpu))
@@ -79,7 +82,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu)
has_fpmr = kvm_has_fpmr(kern_hyp_va(vcpu->kvm));
if (has_fpmr)
- __vcpu_sys_reg(vcpu, FPMR) = read_sysreg_s(SYS_FPMR);
+ __vcpu_assign_sys_reg(vcpu, FPMR, read_sysreg_s(SYS_FPMR));
if (system_supports_sve())
__hyp_sve_restore_host();
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index 73affe1333a4..0e752b515d0f 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -47,65 +47,6 @@ struct fgt_masks hdfgwtr2_masks;
extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc);
-static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
-{
- u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */
-
- if (!guest_owns_fp_regs())
- __activate_traps_fpsimd32(vcpu);
-
- if (has_hvhe()) {
- val |= CPACR_EL1_TTA;
-
- if (guest_owns_fp_regs()) {
- val |= CPACR_EL1_FPEN;
- if (vcpu_has_sve(vcpu))
- val |= CPACR_EL1_ZEN;
- }
-
- write_sysreg(val, cpacr_el1);
- } else {
- val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;
-
- /*
- * Always trap SME since it's not supported in KVM.
- * TSM is RES1 if SME isn't implemented.
- */
- val |= CPTR_EL2_TSM;
-
- if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs())
- val |= CPTR_EL2_TZ;
-
- if (!guest_owns_fp_regs())
- val |= CPTR_EL2_TFP;
-
- write_sysreg(val, cptr_el2);
- }
-}
-
-static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
-{
- if (has_hvhe()) {
- u64 val = CPACR_EL1_FPEN;
-
- if (cpus_have_final_cap(ARM64_SVE))
- val |= CPACR_EL1_ZEN;
- if (cpus_have_final_cap(ARM64_SME))
- val |= CPACR_EL1_SMEN;
-
- write_sysreg(val, cpacr_el1);
- } else {
- u64 val = CPTR_NVHE_EL2_RES1;
-
- if (!cpus_have_final_cap(ARM64_SVE))
- val |= CPTR_EL2_TZ;
- if (!cpus_have_final_cap(ARM64_SME))
- val |= CPTR_EL2_TSM;
-
- write_sysreg(val, cptr_el2);
- }
-}
-
static void __activate_traps(struct kvm_vcpu *vcpu)
{
___activate_traps(vcpu, vcpu->arch.hcr_el2);
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index c9b330dc2066..477f1580ffea 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -90,87 +90,6 @@ static u64 __compute_hcr(struct kvm_vcpu *vcpu)
return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE);
}
-static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
-{
- u64 cptr;
-
- /*
- * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
- * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2,
- * except for some missing controls, such as TAM.
- * In this case, CPTR_EL2.TAM has the same position with or without
- * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
- * shift value for trapping the AMU accesses.
- */
- u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM;
-
- if (guest_owns_fp_regs()) {
- val |= CPACR_EL1_FPEN;
- if (vcpu_has_sve(vcpu))
- val |= CPACR_EL1_ZEN;
- } else {
- __activate_traps_fpsimd32(vcpu);
- }
-
- if (!vcpu_has_nv(vcpu))
- goto write;
-
- /*
- * The architecture is a bit crap (what a surprise): an EL2 guest
- * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
- * as they are RES0 in the guest's view. To work around it, trap the
- * sucker using the very same bit it can't set...
- */
- if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
- val |= CPTR_EL2_TCPAC;
-
- /*
- * Layer the guest hypervisor's trap configuration on top of our own if
- * we're in a nested context.
- */
- if (is_hyp_ctxt(vcpu))
- goto write;
-
- cptr = vcpu_sanitised_cptr_el2(vcpu);
-
- /*
- * Pay attention, there's some interesting detail here.
- *
- * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
- * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
- *
- * - CPTR_EL2.xEN = x0, traps are enabled
- * - CPTR_EL2.xEN = x1, traps are disabled
- *
- * In other words, bit[0] determines if guest accesses trap or not. In
- * the interest of simplicity, clear the entire field if the guest
- * hypervisor has traps enabled to dispel any illusion of something more
- * complicated taking place.
- */
- if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
- val &= ~CPACR_EL1_FPEN;
- if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
- val &= ~CPACR_EL1_ZEN;
-
- if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
- val |= cptr & CPACR_EL1_E0POE;
-
- val |= cptr & CPTR_EL2_TCPAC;
-
-write:
- write_sysreg(val, cpacr_el1);
-}
-
-static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
-{
- u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
-
- if (cpus_have_final_cap(ARM64_SME))
- val |= CPACR_EL1_SMEN_EL1EN;
-
- write_sysreg(val, cpacr_el1);
-}
-
static void __activate_traps(struct kvm_vcpu *vcpu)
{
u64 val;
@@ -223,9 +142,9 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
*/
val = read_sysreg_el0(SYS_CNTP_CVAL);
if (map.direct_ptimer == vcpu_ptimer(vcpu))
- __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val;
+ __vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, val);
if (map.direct_ptimer == vcpu_hptimer(vcpu))
- __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
+ __vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, val);
offset = read_sysreg_s(SYS_CNTPOFF_EL2);
@@ -639,10 +558,10 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
host_ctxt = host_data_ptr(host_ctxt);
guest_ctxt = &vcpu->arch.ctxt;
- sysreg_save_host_state_vhe(host_ctxt);
-
fpsimd_lazy_switch_to_guest(vcpu);
+ sysreg_save_host_state_vhe(host_ctxt);
+
/*
* Note that ARM erratum 1165522 requires us to configure both stage 1
* and stage 2 translation for the guest context before we clear
@@ -667,15 +586,23 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
__deactivate_traps(vcpu);
- fpsimd_lazy_switch_to_host(vcpu);
-
sysreg_restore_host_state_vhe(host_ctxt);
+ __debug_switch_to_host(vcpu);
+
+ /*
+ * Ensure that all system register writes above have taken effect
+ * before returning to the host. In VHE mode, CPTR traps for
+ * FPSIMD/SVE/SME also apply to EL2, so FPSIMD/SVE/SME state must be
+ * manipulated after the ISB.
+ */
+ isb();
+
+ fpsimd_lazy_switch_to_host(vcpu);
+
if (guest_owns_fp_regs())
__fpsimd_save_fpexc32(vcpu);
- __debug_switch_to_host(vcpu);
-
return exit_code;
}
NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe);
@@ -705,12 +632,6 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
*/
local_daif_restore(DAIF_PROCCTX_NOIRQ);
- /*
- * When we exit from the guest we change a number of CPU configuration
- * parameters, such as traps. We rely on the isb() in kvm_call_hyp*()
- * to make sure these changes take effect before running the host or
- * additional guests.
- */
return ret;
}
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index 3814b0b2c937..73e4bc7fde9e 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -18,17 +18,17 @@
static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
{
/* These registers are common with EL1 */
- __vcpu_sys_reg(vcpu, PAR_EL1) = read_sysreg(par_el1);
- __vcpu_sys_reg(vcpu, TPIDR_EL1) = read_sysreg(tpidr_el1);
-
- __vcpu_sys_reg(vcpu, ESR_EL2) = read_sysreg_el1(SYS_ESR);
- __vcpu_sys_reg(vcpu, AFSR0_EL2) = read_sysreg_el1(SYS_AFSR0);
- __vcpu_sys_reg(vcpu, AFSR1_EL2) = read_sysreg_el1(SYS_AFSR1);
- __vcpu_sys_reg(vcpu, FAR_EL2) = read_sysreg_el1(SYS_FAR);
- __vcpu_sys_reg(vcpu, MAIR_EL2) = read_sysreg_el1(SYS_MAIR);
- __vcpu_sys_reg(vcpu, VBAR_EL2) = read_sysreg_el1(SYS_VBAR);
- __vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
- __vcpu_sys_reg(vcpu, AMAIR_EL2) = read_sysreg_el1(SYS_AMAIR);
+ __vcpu_assign_sys_reg(vcpu, PAR_EL1, read_sysreg(par_el1));
+ __vcpu_assign_sys_reg(vcpu, TPIDR_EL1, read_sysreg(tpidr_el1));
+
+ __vcpu_assign_sys_reg(vcpu, ESR_EL2, read_sysreg_el1(SYS_ESR));
+ __vcpu_assign_sys_reg(vcpu, AFSR0_EL2, read_sysreg_el1(SYS_AFSR0));
+ __vcpu_assign_sys_reg(vcpu, AFSR1_EL2, read_sysreg_el1(SYS_AFSR1));
+ __vcpu_assign_sys_reg(vcpu, FAR_EL2, read_sysreg_el1(SYS_FAR));
+ __vcpu_assign_sys_reg(vcpu, MAIR_EL2, read_sysreg_el1(SYS_MAIR));
+ __vcpu_assign_sys_reg(vcpu, VBAR_EL2, read_sysreg_el1(SYS_VBAR));
+ __vcpu_assign_sys_reg(vcpu, CONTEXTIDR_EL2, read_sysreg_el1(SYS_CONTEXTIDR));
+ __vcpu_assign_sys_reg(vcpu, AMAIR_EL2, read_sysreg_el1(SYS_AMAIR));
/*
* In VHE mode those registers are compatible between EL1 and EL2,
@@ -46,21 +46,21 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
* are always trapped, ensuring that the in-memory
* copy is always up-to-date. A small blessing...
*/
- __vcpu_sys_reg(vcpu, SCTLR_EL2) = read_sysreg_el1(SYS_SCTLR);
- __vcpu_sys_reg(vcpu, TTBR0_EL2) = read_sysreg_el1(SYS_TTBR0);
- __vcpu_sys_reg(vcpu, TTBR1_EL2) = read_sysreg_el1(SYS_TTBR1);
- __vcpu_sys_reg(vcpu, TCR_EL2) = read_sysreg_el1(SYS_TCR);
+ __vcpu_assign_sys_reg(vcpu, SCTLR_EL2, read_sysreg_el1(SYS_SCTLR));
+ __vcpu_assign_sys_reg(vcpu, TTBR0_EL2, read_sysreg_el1(SYS_TTBR0));
+ __vcpu_assign_sys_reg(vcpu, TTBR1_EL2, read_sysreg_el1(SYS_TTBR1));
+ __vcpu_assign_sys_reg(vcpu, TCR_EL2, read_sysreg_el1(SYS_TCR));
if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
- __vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
+ __vcpu_assign_sys_reg(vcpu, TCR2_EL2, read_sysreg_el1(SYS_TCR2));
if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
- __vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
- __vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
+ __vcpu_assign_sys_reg(vcpu, PIRE0_EL2, read_sysreg_el1(SYS_PIRE0));
+ __vcpu_assign_sys_reg(vcpu, PIR_EL2, read_sysreg_el1(SYS_PIR));
}
if (ctxt_has_s1poe(&vcpu->arch.ctxt))
- __vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
+ __vcpu_assign_sys_reg(vcpu, POR_EL2, read_sysreg_el1(SYS_POR));
}
/*
@@ -70,13 +70,13 @@ static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
*/
val = read_sysreg_el1(SYS_CNTKCTL);
val &= CNTKCTL_VALID_BITS;
- __vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
- __vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
+ __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, &=, ~CNTKCTL_VALID_BITS);
+ __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, |=, val);
}
- __vcpu_sys_reg(vcpu, SP_EL2) = read_sysreg(sp_el1);
- __vcpu_sys_reg(vcpu, ELR_EL2) = read_sysreg_el1(SYS_ELR);
- __vcpu_sys_reg(vcpu, SPSR_EL2) = read_sysreg_el1(SYS_SPSR);
+ __vcpu_assign_sys_reg(vcpu, SP_EL2, read_sysreg(sp_el1));
+ __vcpu_assign_sys_reg(vcpu, ELR_EL2, read_sysreg_el1(SYS_ELR));
+ __vcpu_assign_sys_reg(vcpu, SPSR_EL2, read_sysreg_el1(SYS_SPSR));
}
static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c
index 4a53e4147fb0..5b191f4dc566 100644
--- a/arch/arm64/kvm/nested.c
+++ b/arch/arm64/kvm/nested.c
@@ -1757,7 +1757,7 @@ int kvm_init_nv_sysregs(struct kvm_vcpu *vcpu)
out:
for (enum vcpu_sysreg sr = __SANITISED_REG_START__; sr < NR_SYS_REGS; sr++)
- (void)__vcpu_sys_reg(vcpu, sr);
+ __vcpu_rmw_sys_reg(vcpu, sr, |=, 0);
return 0;
}
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 25c29107f13f..b03dbda7f1ab 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -178,7 +178,7 @@ static void kvm_pmu_set_pmc_value(struct kvm_pmc *pmc, u64 val, bool force)
val |= lower_32_bits(val);
}
- __vcpu_sys_reg(vcpu, reg) = val;
+ __vcpu_assign_sys_reg(vcpu, reg, val);
/* Recreate the perf event to reflect the updated sample_period */
kvm_pmu_create_perf_event(pmc);
@@ -204,7 +204,7 @@ void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
void kvm_pmu_set_counter_value_user(struct kvm_vcpu *vcpu, u64 select_idx, u64 val)
{
kvm_pmu_release_perf_event(kvm_vcpu_idx_to_pmc(vcpu, select_idx));
- __vcpu_sys_reg(vcpu, counter_index_to_reg(select_idx)) = val;
+ __vcpu_assign_sys_reg(vcpu, counter_index_to_reg(select_idx), val);
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
}
@@ -239,7 +239,7 @@ static void kvm_pmu_stop_counter(struct kvm_pmc *pmc)
reg = counter_index_to_reg(pmc->idx);
- __vcpu_sys_reg(vcpu, reg) = val;
+ __vcpu_assign_sys_reg(vcpu, reg, val);
kvm_pmu_release_perf_event(pmc);
}
@@ -503,14 +503,14 @@ static void kvm_pmu_counter_increment(struct kvm_vcpu *vcpu,
reg = __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) + 1;
if (!kvm_pmc_is_64bit(pmc))
reg = lower_32_bits(reg);
- __vcpu_sys_reg(vcpu, counter_index_to_reg(i)) = reg;
+ __vcpu_assign_sys_reg(vcpu, counter_index_to_reg(i), reg);
/* No overflow? move on */
if (kvm_pmc_has_64bit_overflow(pmc) ? reg : lower_32_bits(reg))
continue;
/* Mark overflow */
- __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(i);
+ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(i));
if (kvm_pmu_counter_can_chain(pmc))
kvm_pmu_counter_increment(vcpu, BIT(i + 1),
@@ -556,7 +556,7 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
perf_event->attr.sample_period = period;
perf_event->hw.sample_period = period;
- __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
+ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, BIT(idx));
if (kvm_pmu_counter_can_chain(pmc))
kvm_pmu_counter_increment(vcpu, BIT(idx + 1),
@@ -602,7 +602,7 @@ void kvm_pmu_handle_pmcr(struct kvm_vcpu *vcpu, u64 val)
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
/* The reset bits don't indicate any state, and shouldn't be saved. */
- __vcpu_sys_reg(vcpu, PMCR_EL0) = val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P);
+ __vcpu_assign_sys_reg(vcpu, PMCR_EL0, (val & ~(ARMV8_PMU_PMCR_C | ARMV8_PMU_PMCR_P)));
if (val & ARMV8_PMU_PMCR_C)
kvm_pmu_set_counter_value(vcpu, ARMV8_PMU_CYCLE_IDX, 0);
@@ -779,7 +779,7 @@ void kvm_pmu_set_counter_event_type(struct kvm_vcpu *vcpu, u64 data,
u64 reg;
reg = counter_index_to_evtreg(pmc->idx);
- __vcpu_sys_reg(vcpu, reg) = data & kvm_pmu_evtyper_mask(vcpu->kvm);
+ __vcpu_assign_sys_reg(vcpu, reg, (data & kvm_pmu_evtyper_mask(vcpu->kvm)));
kvm_pmu_create_perf_event(pmc);
}
@@ -914,9 +914,9 @@ void kvm_vcpu_reload_pmu(struct kvm_vcpu *vcpu)
{
u64 mask = kvm_pmu_implemented_counter_mask(vcpu);
- __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= mask;
- __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= mask;
- __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= mask;
+ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, mask);
+ __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, mask);
+ __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, mask);
kvm_pmu_reprogram_counter_mask(vcpu, mask);
}
@@ -1038,7 +1038,7 @@ static void kvm_arm_set_nr_counters(struct kvm *kvm, unsigned int nr)
u64 val = __vcpu_sys_reg(vcpu, MDCR_EL2);
val &= ~MDCR_EL2_HPMN;
val |= FIELD_PREP(MDCR_EL2_HPMN, kvm->arch.nr_pmu_counters);
- __vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+ __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
}
}
}
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index a6cf2888d150..76c2f0da821f 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -228,7 +228,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
* to reverse-translate virtual EL2 system registers for a
* non-VHE guest hypervisor.
*/
- __vcpu_sys_reg(vcpu, reg) = val;
+ __vcpu_assign_sys_reg(vcpu, reg, val);
switch (reg) {
case CNTHCTL_EL2:
@@ -263,7 +263,7 @@ void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg)
return;
memory_write:
- __vcpu_sys_reg(vcpu, reg) = val;
+ __vcpu_assign_sys_reg(vcpu, reg, val);
}
/* CSSELR values; used to index KVM_REG_ARM_DEMUX_ID_CCSIDR */
@@ -605,7 +605,7 @@ static int set_oslsr_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
if ((val ^ rd->val) & ~OSLSR_EL1_OSLK)
return -EINVAL;
- __vcpu_sys_reg(vcpu, rd->reg) = val;
+ __vcpu_assign_sys_reg(vcpu, rd->reg, val);
return 0;
}
@@ -791,7 +791,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
mask |= GENMASK(n - 1, 0);
reset_unknown(vcpu, r);
- __vcpu_sys_reg(vcpu, r->reg) &= mask;
+ __vcpu_rmw_sys_reg(vcpu, r->reg, &=, mask);
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -799,7 +799,7 @@ static u64 reset_pmu_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
static u64 reset_pmevcntr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
reset_unknown(vcpu, r);
- __vcpu_sys_reg(vcpu, r->reg) &= GENMASK(31, 0);
+ __vcpu_rmw_sys_reg(vcpu, r->reg, &=, GENMASK(31, 0));
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -811,7 +811,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
return 0;
reset_unknown(vcpu, r);
- __vcpu_sys_reg(vcpu, r->reg) &= kvm_pmu_evtyper_mask(vcpu->kvm);
+ __vcpu_rmw_sys_reg(vcpu, r->reg, &=, kvm_pmu_evtyper_mask(vcpu->kvm));
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -819,7 +819,7 @@ static u64 reset_pmevtyper(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
static u64 reset_pmselr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
reset_unknown(vcpu, r);
- __vcpu_sys_reg(vcpu, r->reg) &= PMSELR_EL0_SEL_MASK;
+ __vcpu_rmw_sys_reg(vcpu, r->reg, &=, PMSELR_EL0_SEL_MASK);
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -835,7 +835,7 @@ static u64 reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
* The value of PMCR.N field is included when the
* vCPU register is read via kvm_vcpu_read_pmcr().
*/
- __vcpu_sys_reg(vcpu, r->reg) = pmcr;
+ __vcpu_assign_sys_reg(vcpu, r->reg, pmcr);
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -907,7 +907,7 @@ static bool access_pmselr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
return false;
if (p->is_write)
- __vcpu_sys_reg(vcpu, PMSELR_EL0) = p->regval;
+ __vcpu_assign_sys_reg(vcpu, PMSELR_EL0, p->regval);
else
/* return PMSELR.SEL field */
p->regval = __vcpu_sys_reg(vcpu, PMSELR_EL0)
@@ -1076,7 +1076,7 @@ static int set_pmreg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, u64 va
{
u64 mask = kvm_pmu_accessible_counter_mask(vcpu);
- __vcpu_sys_reg(vcpu, r->reg) = val & mask;
+ __vcpu_assign_sys_reg(vcpu, r->reg, val & mask);
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
return 0;
@@ -1103,10 +1103,10 @@ static bool access_pmcnten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
val = p->regval & mask;
if (r->Op2 & 0x1)
/* accessing PMCNTENSET_EL0 */
- __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) |= val;
+ __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, |=, val);
else
/* accessing PMCNTENCLR_EL0 */
- __vcpu_sys_reg(vcpu, PMCNTENSET_EL0) &= ~val;
+ __vcpu_rmw_sys_reg(vcpu, PMCNTENSET_EL0, &=, ~val);
kvm_pmu_reprogram_counter_mask(vcpu, val);
} else {
@@ -1129,10 +1129,10 @@ static bool access_pminten(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (r->Op2 & 0x1)
/* accessing PMINTENSET_EL1 */
- __vcpu_sys_reg(vcpu, PMINTENSET_EL1) |= val;
+ __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, |=, val);
else
/* accessing PMINTENCLR_EL1 */
- __vcpu_sys_reg(vcpu, PMINTENSET_EL1) &= ~val;
+ __vcpu_rmw_sys_reg(vcpu, PMINTENSET_EL1, &=, ~val);
} else {
p->regval = __vcpu_sys_reg(vcpu, PMINTENSET_EL1);
}
@@ -1151,10 +1151,10 @@ static bool access_pmovs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (p->is_write) {
if (r->CRm & 0x2)
/* accessing PMOVSSET_EL0 */
- __vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= (p->regval & mask);
+ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, |=, (p->regval & mask));
else
/* accessing PMOVSCLR_EL0 */
- __vcpu_sys_reg(vcpu, PMOVSSET_EL0) &= ~(p->regval & mask);
+ __vcpu_rmw_sys_reg(vcpu, PMOVSSET_EL0, &=, ~(p->regval & mask));
} else {
p->regval = __vcpu_sys_reg(vcpu, PMOVSSET_EL0);
}
@@ -1185,8 +1185,8 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
if (!vcpu_mode_priv(vcpu))
return undef_access(vcpu, p, r);
- __vcpu_sys_reg(vcpu, PMUSERENR_EL0) =
- p->regval & ARMV8_PMU_USERENR_MASK;
+ __vcpu_assign_sys_reg(vcpu, PMUSERENR_EL0,
+ (p->regval & ARMV8_PMU_USERENR_MASK));
} else {
p->regval = __vcpu_sys_reg(vcpu, PMUSERENR_EL0)
& ARMV8_PMU_USERENR_MASK;
@@ -1237,7 +1237,7 @@ static int set_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
if (!kvm_supports_32bit_el0())
val |= ARMV8_PMU_PMCR_LC;
- __vcpu_sys_reg(vcpu, r->reg) = val;
+ __vcpu_assign_sys_reg(vcpu, r->reg, val);
kvm_make_request(KVM_REQ_RELOAD_PMU, vcpu);
return 0;
@@ -2213,7 +2213,7 @@ static u64 reset_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
if (kvm_has_mte(vcpu->kvm))
clidr |= 2ULL << CLIDR_TTYPE_SHIFT(loc);
- __vcpu_sys_reg(vcpu, r->reg) = clidr;
+ __vcpu_assign_sys_reg(vcpu, r->reg, clidr);
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -2227,7 +2227,7 @@ static int set_clidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
if ((val & CLIDR_EL1_RES0) || (!(ctr_el0 & CTR_EL0_IDC) && idc))
return -EINVAL;
- __vcpu_sys_reg(vcpu, rd->reg) = val;
+ __vcpu_assign_sys_reg(vcpu, rd->reg, val);
return 0;
}
@@ -2404,7 +2404,7 @@ static bool access_sp_el1(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
if (p->is_write)
- __vcpu_sys_reg(vcpu, SP_EL1) = p->regval;
+ __vcpu_assign_sys_reg(vcpu, SP_EL1, p->regval);
else
p->regval = __vcpu_sys_reg(vcpu, SP_EL1);
@@ -2428,7 +2428,7 @@ static bool access_spsr(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
if (p->is_write)
- __vcpu_sys_reg(vcpu, SPSR_EL1) = p->regval;
+ __vcpu_assign_sys_reg(vcpu, SPSR_EL1, p->regval);
else
p->regval = __vcpu_sys_reg(vcpu, SPSR_EL1);
@@ -2440,7 +2440,7 @@ static bool access_cntkctl_el12(struct kvm_vcpu *vcpu,
const struct sys_reg_desc *r)
{
if (p->is_write)
- __vcpu_sys_reg(vcpu, CNTKCTL_EL1) = p->regval;
+ __vcpu_assign_sys_reg(vcpu, CNTKCTL_EL1, p->regval);
else
p->regval = __vcpu_sys_reg(vcpu, CNTKCTL_EL1);
@@ -2454,7 +2454,9 @@ static u64 reset_hcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
if (!cpus_have_final_cap(ARM64_HAS_HCR_NV1))
val |= HCR_E2H;
- return __vcpu_sys_reg(vcpu, r->reg) = val;
+ __vcpu_assign_sys_reg(vcpu, r->reg, val);
+
+ return __vcpu_sys_reg(vcpu, r->reg);
}
static unsigned int __el2_visibility(const struct kvm_vcpu *vcpu,
@@ -2625,7 +2627,7 @@ static bool access_mdcr(struct kvm_vcpu *vcpu,
u64_replace_bits(val, hpmn, MDCR_EL2_HPMN);
}
- __vcpu_sys_reg(vcpu, MDCR_EL2) = val;
+ __vcpu_assign_sys_reg(vcpu, MDCR_EL2, val);
/*
* Request a reload of the PMU to enable/disable the counters
@@ -2754,7 +2756,7 @@ static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r,
static u64 reset_mdcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
- __vcpu_sys_reg(vcpu, r->reg) = vcpu->kvm->arch.nr_pmu_counters;
+ __vcpu_assign_sys_reg(vcpu, r->reg, vcpu->kvm->arch.nr_pmu_counters);
return vcpu->kvm->arch.nr_pmu_counters;
}
@@ -4790,7 +4792,7 @@ void kvm_reset_sys_regs(struct kvm_vcpu *vcpu)
r->reset(vcpu, r);
if (r->reg >= __SANITISED_REG_START__ && r->reg < NR_SYS_REGS)
- (void)__vcpu_sys_reg(vcpu, r->reg);
+ __vcpu_rmw_sys_reg(vcpu, r->reg, |=, 0);
}
set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags);
@@ -5012,7 +5014,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg,
if (r->set_user) {
ret = (r->set_user)(vcpu, r, val);
} else {
- __vcpu_sys_reg(vcpu, r->reg) = val;
+ __vcpu_assign_sys_reg(vcpu, r->reg, val);
ret = 0;
}
diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h
index cc6338d38766..ef97d9fc67cc 100644
--- a/arch/arm64/kvm/sys_regs.h
+++ b/arch/arm64/kvm/sys_regs.h
@@ -137,7 +137,7 @@ static inline u64 reset_unknown(struct kvm_vcpu *vcpu,
{
BUG_ON(!r->reg);
BUG_ON(r->reg >= NR_SYS_REGS);
- __vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL;
+ __vcpu_assign_sys_reg(vcpu, r->reg, 0x1de7ec7edbadc0deULL);
return __vcpu_sys_reg(vcpu, r->reg);
}
@@ -145,7 +145,7 @@ static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
{
BUG_ON(!r->reg);
BUG_ON(r->reg >= NR_SYS_REGS);
- __vcpu_sys_reg(vcpu, r->reg) = r->val;
+ __vcpu_assign_sys_reg(vcpu, r->reg, r->val);
return __vcpu_sys_reg(vcpu, r->reg);
}
diff --git a/arch/arm64/kvm/vgic/vgic-v3-nested.c b/arch/arm64/kvm/vgic/vgic-v3-nested.c
index 4f6954c30674..a50fb7e6841f 100644
--- a/arch/arm64/kvm/vgic/vgic-v3-nested.c
+++ b/arch/arm64/kvm/vgic/vgic-v3-nested.c
@@ -36,6 +36,11 @@ struct shadow_if {
static DEFINE_PER_CPU(struct shadow_if, shadow_if);
+static int lr_map_idx_to_shadow_idx(struct shadow_if *shadow_if, int idx)
+{
+ return hweight16(shadow_if->lr_map & (BIT(idx) - 1));
+}
+
/*
* Nesting GICv3 support
*
@@ -209,6 +214,29 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
return reg;
}
+static u64 translate_lr_pintid(struct kvm_vcpu *vcpu, u64 lr)
+{
+ struct vgic_irq *irq;
+
+ if (!(lr & ICH_LR_HW))
+ return lr;
+
+ /* We have the HW bit set, check for validity of pINTID */
+ irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
+ /* If there was no real mapping, nuke the HW bit */
+ if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI)
+ lr &= ~ICH_LR_HW;
+
+ /* Translate the virtual mapping to the real one, even if invalid */
+ if (irq) {
+ lr &= ~ICH_LR_PHYS_ID_MASK;
+ lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
+ vgic_put_irq(vcpu->kvm, irq);
+ }
+
+ return lr;
+}
+
/*
* For LRs which have HW bit set such as timer interrupts, we modify them to
* have the host hardware interrupt number instead of the virtual one programmed
@@ -217,58 +245,37 @@ u64 vgic_v3_get_misr(struct kvm_vcpu *vcpu)
static void vgic_v3_create_shadow_lr(struct kvm_vcpu *vcpu,
struct vgic_v3_cpu_if *s_cpu_if)
{
- unsigned long lr_map = 0;
- int index = 0;
+ struct shadow_if *shadow_if;
+
+ shadow_if = container_of(s_cpu_if, struct shadow_if, cpuif);
+ shadow_if->lr_map = 0;
for (int i = 0; i < kvm_vgic_global_state.nr_lr; i++) {
u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
- struct vgic_irq *irq;
if (!(lr & ICH_LR_STATE))
- lr = 0;
-
- if (!(lr & ICH_LR_HW))
- goto next;
-
- /* We have the HW bit set, check for validity of pINTID */
- irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
- if (!irq || !irq->hw || irq->intid > VGIC_MAX_SPI ) {
- /* There was no real mapping, so nuke the HW bit */
- lr &= ~ICH_LR_HW;
- if (irq)
- vgic_put_irq(vcpu->kvm, irq);
- goto next;
- }
-
- /* Translate the virtual mapping to the real one */
- lr &= ~ICH_LR_PHYS_ID_MASK;
- lr |= FIELD_PREP(ICH_LR_PHYS_ID_MASK, (u64)irq->hwintid);
+ continue;
- vgic_put_irq(vcpu->kvm, irq);
+ lr = translate_lr_pintid(vcpu, lr);
-next:
- s_cpu_if->vgic_lr[index] = lr;
- if (lr) {
- lr_map |= BIT(i);
- index++;
- }
+ s_cpu_if->vgic_lr[hweight16(shadow_if->lr_map)] = lr;
+ shadow_if->lr_map |= BIT(i);
}
- container_of(s_cpu_if, struct shadow_if, cpuif)->lr_map = lr_map;
- s_cpu_if->used_lrs = index;
+ s_cpu_if->used_lrs = hweight16(shadow_if->lr_map);
}
void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
{
struct shadow_if *shadow_if = get_shadow_if();
- int i, index = 0;
+ int i;
for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
u64 lr = __vcpu_sys_reg(vcpu, ICH_LRN(i));
struct vgic_irq *irq;
if (!(lr & ICH_LR_HW) || !(lr & ICH_LR_STATE))
- goto next;
+ continue;
/*
* If we had a HW lr programmed by the guest hypervisor, we
@@ -277,15 +284,13 @@ void vgic_v3_sync_nested(struct kvm_vcpu *vcpu)
*/
irq = vgic_get_vcpu_irq(vcpu, FIELD_GET(ICH_LR_PHYS_ID_MASK, lr));
if (WARN_ON(!irq)) /* Shouldn't happen as we check on load */
- goto next;
+ continue;
- lr = __gic_v3_get_lr(index);
+ lr = __gic_v3_get_lr(lr_map_idx_to_shadow_idx(shadow_if, i));
if (!(lr & ICH_LR_STATE))
irq->active = false;
vgic_put_irq(vcpu->kvm, irq);
- next:
- index++;
}
}
@@ -356,25 +361,23 @@ void vgic_v3_put_nested(struct kvm_vcpu *vcpu)
val = __vcpu_sys_reg(vcpu, ICH_HCR_EL2);
val &= ~ICH_HCR_EL2_EOIcount_MASK;
val |= (s_cpu_if->vgic_hcr & ICH_HCR_EL2_EOIcount_MASK);
- __vcpu_sys_reg(vcpu, ICH_HCR_EL2) = val;
- __vcpu_sys_reg(vcpu, ICH_VMCR_EL2) = s_cpu_if->vgic_vmcr;
+ __vcpu_assign_sys_reg(vcpu, ICH_HCR_EL2, val);
+ __vcpu_assign_sys_reg(vcpu, ICH_VMCR_EL2, s_cpu_if->vgic_vmcr);
for (i = 0; i < 4; i++) {
- __vcpu_sys_reg(vcpu, ICH_AP0RN(i)) = s_cpu_if->vgic_ap0r[i];
- __vcpu_sys_reg(vcpu, ICH_AP1RN(i)) = s_cpu_if->vgic_ap1r[i];
+ __vcpu_assign_sys_reg(vcpu, ICH_AP0RN(i), s_cpu_if->vgic_ap0r[i]);
+ __vcpu_assign_sys_reg(vcpu, ICH_AP1RN(i), s_cpu_if->vgic_ap1r[i]);
}
for_each_set_bit(i, &shadow_if->lr_map, kvm_vgic_global_state.nr_lr) {
val = __vcpu_sys_reg(vcpu, ICH_LRN(i));
val &= ~ICH_LR_STATE;
- val |= s_cpu_if->vgic_lr[i] & ICH_LR_STATE;
+ val |= s_cpu_if->vgic_lr[lr_map_idx_to_shadow_idx(shadow_if, i)] & ICH_LR_STATE;
- __vcpu_sys_reg(vcpu, ICH_LRN(i)) = val;
- s_cpu_if->vgic_lr[i] = 0;
+ __vcpu_assign_sys_reg(vcpu, ICH_LRN(i), val);
}
- shadow_if->lr_map = 0;
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = 0;
}
diff --git a/arch/arm64/lib/crypto/poly1305-glue.c b/arch/arm64/lib/crypto/poly1305-glue.c
index 6a661cf04821..c9a74766785b 100644
--- a/arch/arm64/lib/crypto/poly1305-glue.c
+++ b/arch/arm64/lib/crypto/poly1305-glue.c
@@ -38,14 +38,14 @@ void poly1305_blocks_arch(struct poly1305_block_state *state, const u8 *src,
unsigned int todo = min_t(unsigned int, len, SZ_4K);
kernel_neon_begin();
- poly1305_blocks_neon(state, src, todo, 1);
+ poly1305_blocks_neon(state, src, todo, padbit);
kernel_neon_end();
len -= todo;
src += todo;
} while (len);
} else
- poly1305_blocks(state, src, len, 1);
+ poly1305_blocks(state, src, len, padbit);
}
EXPORT_SYMBOL_GPL(poly1305_blocks_arch);
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8fcf59ba39db..00ab1d648db6 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1305,7 +1305,8 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
next = addr;
end = addr + PUD_SIZE;
do {
- pmd_free_pte_page(pmdp, next);
+ if (pmd_present(pmdp_get(pmdp)))
+ pmd_free_pte_page(pmdp, next);
} while (pmdp++, next += PMD_SIZE, next != end);
pud_clear(pudp);
diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index a3b0e693a125..bbea4f36f9f2 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -325,4 +325,9 @@
#define A64_MRS_SP_EL0(Rt) \
aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_SP_EL0)
+/* Barriers */
+#define A64_SB aarch64_insn_get_sb_value()
+#define A64_DSB_NSH (aarch64_insn_get_dsb_base_value() | 0x7 << 8)
+#define A64_ISB aarch64_insn_get_isb_value()
+
#endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index da8b89dd2910..b6c42b5c9668 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1630,17 +1630,14 @@ emit_cond_jmp:
return ret;
break;
- /* speculation barrier */
+ /* speculation barrier against v1 and v4 */
case BPF_ST | BPF_NOSPEC:
- /*
- * Nothing required here.
- *
- * In case of arm64, we rely on the firmware mitigation of
- * Speculative Store Bypass as controlled via the ssbd kernel
- * parameter. Whenever the mitigation is enabled, it works
- * for all of the kernel code with no need to provide any
- * additional instructions.
- */
+ if (alternative_has_cap_likely(ARM64_HAS_SB)) {
+ emit(A64_SB, ctx);
+ } else {
+ emit(A64_DSB_NSH, ctx);
+ emit(A64_ISB, ctx);
+ }
break;
/* ST: *(size *)(dst + off) = imm */
@@ -2911,6 +2908,17 @@ bool bpf_jit_supports_percpu_insn(void)
return true;
}
+bool bpf_jit_bypass_spec_v4(void)
+{
+ /* In case of arm64, we rely on the firmware mitigation of Speculative
+ * Store Bypass as controlled via the ssbd kernel parameter. Whenever
+ * the mitigation is enabled, it works for all of the kernel code with
+ * no need to provide any additional instructions. Therefore, skip
+ * inserting nospec insns against Spectre v4.
+ */
+ return true;
+}
+
bool bpf_jit_inlines_helper_call(s32 imm)
{
switch (imm) {
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
index b8378431aeff..5a394be09c35 100644
--- a/arch/csky/include/asm/pgtable.h
+++ b/arch/csky/include/asm/pgtable.h
@@ -200,7 +200,7 @@ static inline pte_t pte_mkyoung(pte_t pte)
return pte;
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/hexagon/include/asm/pgtable.h b/arch/hexagon/include/asm/pgtable.h
index 9fbdfdbc539f..fbf24d1d1ca6 100644
--- a/arch/hexagon/include/asm/pgtable.h
+++ b/arch/hexagon/include/asm/pgtable.h
@@ -387,7 +387,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
(((type & 0x1f) << 1) | \
((offset & 0x3ffff8) << 10) | ((offset & 0x7) << 7)) })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index a3f17914dbab..b30185302c07 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -301,7 +301,7 @@ static inline pte_t mk_swap_pte(unsigned long type, unsigned long offset)
#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) })
#define __swp_entry_to_pmd(x) ((pmd_t) { (x).val | _PAGE_HUGE })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/m68k/include/asm/mcf_pgtable.h b/arch/m68k/include/asm/mcf_pgtable.h
index f5c596b211d4..d79fef609194 100644
--- a/arch/m68k/include/asm/mcf_pgtable.h
+++ b/arch/m68k/include/asm/mcf_pgtable.h
@@ -268,7 +268,7 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) (__pte((x).val))
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/m68k/include/asm/motorola_pgtable.h b/arch/m68k/include/asm/motorola_pgtable.h
index 040ac3bad713..14fee64d3e60 100644
--- a/arch/m68k/include/asm/motorola_pgtable.h
+++ b/arch/m68k/include/asm/motorola_pgtable.h
@@ -185,7 +185,7 @@ extern pgd_t kernel_pg_dir[128];
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/m68k/include/asm/sun3_pgtable.h b/arch/m68k/include/asm/sun3_pgtable.h
index 73745dc0ec0e..858cbe936f5b 100644
--- a/arch/m68k/include/asm/sun3_pgtable.h
+++ b/arch/m68k/include/asm/sun3_pgtable.h
@@ -169,7 +169,7 @@ extern pgd_t kernel_pg_dir[PTRS_PER_PGD];
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/microblaze/include/asm/pgtable.h b/arch/microblaze/include/asm/pgtable.h
index b1bb2c65dd04..bae1abfa6f6b 100644
--- a/arch/microblaze/include/asm/pgtable.h
+++ b/arch/microblaze/include/asm/pgtable.h
@@ -398,7 +398,7 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 2 })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val << 2 })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 4852b005a72d..ae73ecf4c41a 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -534,7 +534,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
#endif
#if defined(CONFIG_PHYS_ADDR_T_64BIT) && defined(CONFIG_CPU_MIPS32)
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte.pte_low & _PAGE_SWP_EXCLUSIVE;
}
@@ -551,7 +551,7 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
return pte;
}
#else
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/nios2/include/asm/pgtable.h b/arch/nios2/include/asm/pgtable.h
index e98578e27e26..844dce55569f 100644
--- a/arch/nios2/include/asm/pgtable.h
+++ b/arch/nios2/include/asm/pgtable.h
@@ -259,7 +259,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
#define __swp_entry_to_pte(swp) ((pte_t) { (swp).val })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/openrisc/include/asm/pgtable.h b/arch/openrisc/include/asm/pgtable.h
index 71bfb8c8c482..5bd6463bd514 100644
--- a/arch/openrisc/include/asm/pgtable.h
+++ b/arch/openrisc/include/asm/pgtable.h
@@ -411,7 +411,7 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 80f5e2a28413..1a86a4370b29 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -425,7 +425,7 @@ static inline void set_ptes(struct mm_struct *mm, unsigned long addr,
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/powerpc/boot/dts/microwatt.dts b/arch/powerpc/boot/dts/microwatt.dts
index c4e4d2a9b460..b7eac4e56019 100644
--- a/arch/powerpc/boot/dts/microwatt.dts
+++ b/arch/powerpc/boot/dts/microwatt.dts
@@ -4,7 +4,7 @@
/ {
#size-cells = <0x02>;
#address-cells = <0x02>;
- model-name = "microwatt";
+ model = "microwatt";
compatible = "microwatt-soc";
aliases {
diff --git a/arch/powerpc/boot/dts/mpc8315erdb.dts b/arch/powerpc/boot/dts/mpc8315erdb.dts
index e09b37d7489d..a89cb3139ca8 100644
--- a/arch/powerpc/boot/dts/mpc8315erdb.dts
+++ b/arch/powerpc/boot/dts/mpc8315erdb.dts
@@ -6,6 +6,7 @@
*/
/dts-v1/;
+#include <dt-bindings/interrupt-controller/irq.h>
/ {
compatible = "fsl,mpc8315erdb";
@@ -358,6 +359,15 @@
interrupt-parent = <&ipic>;
fsl,mpc8313-wakeup-timer = <&gtm1>;
};
+
+ gpio: gpio-controller@c00 {
+ compatible = "fsl,mpc8314-gpio";
+ reg = <0xc00 0x100>;
+ interrupts = <74 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-parent = <&ipic>;
+ gpio-controller;
+ #gpio-cells = <2>;
+ };
};
pci0: pci@e0008500 {
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 42c3af90d1f0..92d21c6faf1e 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -365,7 +365,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) >> 3 })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val << 3 })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 6ed93e290c2f..a2ddcbb3fcb9 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -693,7 +693,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return !!(pte_raw(pte) & cpu_to_be64(_PAGE_SWP_EXCLUSIVE));
}
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 8d1f0b7062eb..7d6b9e5b286e 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -286,7 +286,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 02897f4b0dbf..b891910fce8a 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -183,7 +183,7 @@
/*
* Used to name C functions called from asm
*/
-#ifdef CONFIG_PPC_KERNEL_PCREL
+#if defined(__powerpc64__) && defined(CONFIG_PPC_KERNEL_PCREL)
#define CFUNC(name) name@notoc
#else
#define CFUNC(name) name
diff --git a/arch/powerpc/include/uapi/asm/ioctls.h b/arch/powerpc/include/uapi/asm/ioctls.h
index 2c145da3b774..b5211e413829 100644
--- a/arch/powerpc/include/uapi/asm/ioctls.h
+++ b/arch/powerpc/include/uapi/asm/ioctls.h
@@ -23,10 +23,10 @@
#define TCSETSW _IOW('t', 21, struct termios)
#define TCSETSF _IOW('t', 22, struct termios)
-#define TCGETA _IOR('t', 23, struct termio)
-#define TCSETA _IOW('t', 24, struct termio)
-#define TCSETAW _IOW('t', 25, struct termio)
-#define TCSETAF _IOW('t', 28, struct termio)
+#define TCGETA 0x40147417 /* _IOR('t', 23, struct termio) */
+#define TCSETA 0x80147418 /* _IOW('t', 24, struct termio) */
+#define TCSETAW 0x80147419 /* _IOW('t', 25, struct termio) */
+#define TCSETAF 0x8014741c /* _IOW('t', 28, struct termio) */
#define TCSBRK _IO('t', 29)
#define TCXONC _IO('t', 30)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 83fe99861eb1..ca7f7bb2b478 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1509,6 +1509,8 @@ int eeh_pe_configure(struct eeh_pe *pe)
/* Invalid PE ? */
if (!pe)
return -ENODEV;
+ else
+ ret = eeh_ops->configure_bridge(pe);
return ret;
}
diff --git a/arch/powerpc/kernel/vdso/Makefile b/arch/powerpc/kernel/vdso/Makefile
index e8824f933326..8834dfe9d727 100644
--- a/arch/powerpc/kernel/vdso/Makefile
+++ b/arch/powerpc/kernel/vdso/Makefile
@@ -53,7 +53,7 @@ ldflags-$(CONFIG_LD_ORPHAN_WARN) += -Wl,--orphan-handling=$(CONFIG_LD_ORPHAN_WAR
ldflags-y += $(filter-out $(CC_AUTO_VAR_INIT_ZERO_ENABLER) $(CC_FLAGS_FTRACE) -Wa$(comma)%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
CC32FLAGS := -m32
-CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc
+CC32FLAGSREMOVE := -mcmodel=medium -mabi=elfv1 -mabi=elfv2 -mcall-aixdesc -mpcrel
ifdef CONFIG_CC_IS_CLANG
# This flag is supported by clang for 64-bit but not 32-bit so it will cause
# an unused command line flag warning for this file.
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 5daa77aee7f7..a25a6ffe7d7c 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -370,6 +370,23 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
return 0;
}
+bool bpf_jit_bypass_spec_v1(void)
+{
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
+ return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR));
+#else
+ return true;
+#endif
+}
+
+bool bpf_jit_bypass_spec_v4(void)
+{
+ return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_STF_BARRIER) &&
+ stf_barrier_type_get() != STF_BARRIER_NONE);
+}
+
/*
* We spill into the redzone always, even if the bpf program has its own stackframe.
* Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local()
@@ -397,6 +414,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
u32 *addrs, int pass, bool extra_pass)
{
enum stf_barrier_type stf_barrier = stf_barrier_type_get();
+ bool sync_emitted, ori31_emitted;
const struct bpf_insn *insn = fp->insnsi;
int flen = fp->len;
int i, ret;
@@ -789,30 +807,51 @@ emit_clear:
/*
* BPF_ST NOSPEC (speculation barrier)
+ *
+ * The following must act as a barrier against both Spectre v1
+ * and v4 if we requested both mitigations. Therefore, also emit
+ * 'isync; sync' on E500 or 'ori31' on BOOK3S_64 in addition to
+ * the insns needed for a Spectre v4 barrier.
+ *
+ * If we requested only !bypass_spec_v1 OR only !bypass_spec_v4,
+ * we can skip the respective other barrier type as an
+ * optimization.
*/
case BPF_ST | BPF_NOSPEC:
- if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) ||
- !security_ftr_enabled(SEC_FTR_STF_BARRIER))
- break;
-
- switch (stf_barrier) {
- case STF_BARRIER_EIEIO:
- EMIT(PPC_RAW_EIEIO() | 0x02000000);
- break;
- case STF_BARRIER_SYNC_ORI:
+ sync_emitted = false;
+ ori31_emitted = false;
+ if (IS_ENABLED(CONFIG_PPC_E500) &&
+ !bpf_jit_bypass_spec_v1()) {
+ EMIT(PPC_RAW_ISYNC());
EMIT(PPC_RAW_SYNC());
- EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
- EMIT(PPC_RAW_ORI(_R31, _R31, 0));
- break;
- case STF_BARRIER_FALLBACK:
- ctx->seen |= SEEN_FUNC;
- PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
- EMIT(PPC_RAW_MTCTR(_R12));
- EMIT(PPC_RAW_BCTRL());
- break;
- case STF_BARRIER_NONE:
- break;
+ sync_emitted = true;
}
+ if (!bpf_jit_bypass_spec_v4()) {
+ switch (stf_barrier) {
+ case STF_BARRIER_EIEIO:
+ EMIT(PPC_RAW_EIEIO() | 0x02000000);
+ break;
+ case STF_BARRIER_SYNC_ORI:
+ if (!sync_emitted)
+ EMIT(PPC_RAW_SYNC());
+ EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
+ EMIT(PPC_RAW_ORI(_R31, _R31, 0));
+ ori31_emitted = true;
+ break;
+ case STF_BARRIER_FALLBACK:
+ ctx->seen |= SEEN_FUNC;
+ PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
+ EMIT(PPC_RAW_MTCTR(_R12));
+ EMIT(PPC_RAW_BCTRL());
+ break;
+ case STF_BARRIER_NONE:
+ break;
+ }
+ }
+ if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) &&
+ !bpf_jit_bypass_spec_v1() &&
+ !ori31_emitted)
+ EMIT(PPC_RAW_ORI(_R31, _R31, 0));
break;
/*
diff --git a/arch/powerpc/platforms/book3s/vas-api.c b/arch/powerpc/platforms/book3s/vas-api.c
index 0b6365d85d11..dc6f75d3ac6e 100644
--- a/arch/powerpc/platforms/book3s/vas-api.c
+++ b/arch/powerpc/platforms/book3s/vas-api.c
@@ -521,6 +521,15 @@ static int coproc_mmap(struct file *fp, struct vm_area_struct *vma)
return -EINVAL;
}
+ /*
+ * Map complete page to the paste address. So the user
+ * space should pass 0ULL to the offset parameter.
+ */
+ if (vma->vm_pgoff) {
+ pr_debug("Page offset unsupported to map paste address\n");
+ return -EINVAL;
+ }
+
/* Ensure instance has an open send window */
if (!txwin) {
pr_err("No send window open?\n");
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 4ac9808e55a4..2ea30b343354 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -48,11 +48,15 @@ static ssize_t memtrace_read(struct file *filp, char __user *ubuf,
static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma)
{
struct memtrace_entry *ent = filp->private_data;
+ unsigned long ent_nrpages = ent->size >> PAGE_SHIFT;
+ unsigned long vma_nrpages = vma_pages(vma);
- if (ent->size < vma->vm_end - vma->vm_start)
+ /* The requested page offset should be within object's page count */
+ if (vma->vm_pgoff >= ent_nrpages)
return -EINVAL;
- if (vma->vm_pgoff << PAGE_SHIFT >= ent->size)
+ /* The requested mapping range should remain within the bounds */
+ if (vma_nrpages > ent_nrpages - vma->vm_pgoff)
return -EINVAL;
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index a11816bbf9e7..438ce7df24c3 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -1028,7 +1028,7 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 5fbf3f94f1e8..b17fad091bab 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -103,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
- if (cp->a2 == 0 && cp->a3 == 0)
+ if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask);
else
kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask,
@@ -111,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT);
break;
case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
- if (cp->a2 == 0 && cp->a3 == 0)
+ if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
kvm_riscv_hfence_vvma_asid_all(vcpu->kvm,
hbase, hmask, cp->a4);
else
@@ -127,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
/*
* Until nested virtualization is implemented, the
- * SBI HFENCE calls should be treated as NOPs
+ * SBI HFENCE calls should return not supported
+ * hence fallthrough.
*/
- break;
default:
retdata->err_val = SBI_ERR_NOT_SUPPORTED;
}
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 1c661ac62ce8..6d8bc27a366e 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -915,7 +915,7 @@ static inline int pmd_protnone(pmd_t pmd)
}
#endif
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/sh/include/asm/pgtable_32.h b/arch/sh/include/asm/pgtable_32.h
index 71b18741cc11..5f51af18997b 100644
--- a/arch/sh/include/asm/pgtable_32.h
+++ b/arch/sh/include/asm/pgtable_32.h
@@ -470,7 +470,7 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
/* In both cases, we borrow bit 6 to store the exclusive marker in swap PTEs. */
#define _PAGE_SWP_EXCLUSIVE _PAGE_USER
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte.pte_low & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 1454ebe91539..7c199c003ffe 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -348,7 +348,7 @@ static inline swp_entry_t __swp_entry(unsigned long type, unsigned long offset)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & SRMMU_SWP_EXCLUSIVE;
}
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 4af03e3c161b..669cd02469a1 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -1023,7 +1023,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/um/drivers/ubd_user.c b/arch/um/drivers/ubd_user.c
index c5e6545f6fcf..8e8a8bf518b6 100644
--- a/arch/um/drivers/ubd_user.c
+++ b/arch/um/drivers/ubd_user.c
@@ -41,7 +41,7 @@ int start_io_thread(struct os_helper_thread **td_out, int *fd_out)
*fd_out = fds[1];
err = os_set_fd_block(*fd_out, 0);
- err = os_set_fd_block(kernel_fd, 0);
+ err |= os_set_fd_block(kernel_fd, 0);
if (err) {
printk("start_io_thread - failed to set nonblocking I/O.\n");
goto out_close;
diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c
index f292e0b4ff8b..9bbbddfe866b 100644
--- a/arch/um/drivers/vector_kern.c
+++ b/arch/um/drivers/vector_kern.c
@@ -1625,35 +1625,19 @@ static void vector_eth_configure(
device->dev = dev;
- *vp = ((struct vector_private)
- {
- .list = LIST_HEAD_INIT(vp->list),
- .dev = dev,
- .unit = n,
- .options = get_transport_options(def),
- .rx_irq = 0,
- .tx_irq = 0,
- .parsed = def,
- .max_packet = get_mtu(def) + ETH_HEADER_OTHER,
- /* TODO - we need to calculate headroom so that ip header
- * is 16 byte aligned all the time
- */
- .headroom = get_headroom(def),
- .form_header = NULL,
- .verify_header = NULL,
- .header_rxbuffer = NULL,
- .header_txbuffer = NULL,
- .header_size = 0,
- .rx_header_size = 0,
- .rexmit_scheduled = false,
- .opened = false,
- .transport_data = NULL,
- .in_write_poll = false,
- .coalesce = 2,
- .req_size = get_req_size(def),
- .in_error = false,
- .bpf = NULL
- });
+ INIT_LIST_HEAD(&vp->list);
+ vp->dev = dev;
+ vp->unit = n;
+ vp->options = get_transport_options(def);
+ vp->parsed = def;
+ vp->max_packet = get_mtu(def) + ETH_HEADER_OTHER;
+ /*
+ * TODO - we need to calculate headroom so that ip header
+ * is 16 byte aligned all the time
+ */
+ vp->headroom = get_headroom(def);
+ vp->coalesce = 2;
+ vp->req_size = get_req_size(def);
dev->features = dev->hw_features = (NETIF_F_SG | NETIF_F_FRAGLIST);
INIT_WORK(&vp->reset_tx, vector_reset_tx);
diff --git a/arch/um/drivers/vfio_kern.c b/arch/um/drivers/vfio_kern.c
index b51fc9888ae1..13b971a2bd43 100644
--- a/arch/um/drivers/vfio_kern.c
+++ b/arch/um/drivers/vfio_kern.c
@@ -570,6 +570,17 @@ static void uml_vfio_release_device(struct uml_vfio_device *dev)
kfree(dev);
}
+static struct uml_vfio_device *uml_vfio_find_device(const char *device)
+{
+ struct uml_vfio_device *dev;
+
+ list_for_each_entry(dev, &uml_vfio_devices, list) {
+ if (!strcmp(dev->name, device))
+ return dev;
+ }
+ return NULL;
+}
+
static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *kp)
{
struct uml_vfio_device *dev;
@@ -582,6 +593,9 @@ static int uml_vfio_cmdline_set(const char *device, const struct kernel_param *k
uml_vfio_container.fd = fd;
}
+ if (uml_vfio_find_device(device))
+ return -EEXIST;
+
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return -ENOMEM;
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
index ca2a519d53ab..24fdea6f88c3 100644
--- a/arch/um/include/asm/pgtable.h
+++ b/arch/um/include/asm/pgtable.h
@@ -314,7 +314,7 @@ extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_get_bits(pte, _PAGE_SWP_EXCLUSIVE);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..71019b3b54ea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -89,7 +89,7 @@ config X86
select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN
select ARCH_HAS_EARLY_DEBUG if KGDB
select ARCH_HAS_ELF_RANDOMIZE
- select ARCH_HAS_EXECMEM_ROX if X86_64
+ select ARCH_HAS_EXECMEM_ROX if X86_64 && STRICT_MODULE_RWX
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 741b229f0718..c2fb729c270e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2826,7 +2826,7 @@ static void intel_pmu_read_event(struct perf_event *event)
* If the PEBS counters snapshotting is enabled,
* the topdown event is available in PEBS records.
*/
- if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+ if (is_topdown_count(event) && !is_pebs_counter_event_group(event))
static_call(intel_pmu_update_topdown_event)(event, NULL);
else
intel_pmu_drain_pebs_buffer();
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e988bac0a4a1..3c2de4ce3b10 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,12 +5,20 @@
#include <asm-generic/module.h>
#include <asm/orc_types.h>
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+ void **pages;
+ int num;
+#endif
+};
+
struct mod_arch_specific {
#ifdef CONFIG_UNWINDER_ORC
unsigned int num_orcs;
int *orc_unwind_ip;
struct orc_entry *orc_unwind;
#endif
+ struct its_array its_pages;
};
#endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 774430c3abff..97954c936c54 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1561,7 +1561,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index 2f3820342598..d8525e6ef50a 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -80,6 +80,7 @@
#define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL
#define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL
#define TDVMCALL_STATUS_ALIGN_ERROR 0x8000000000000002ULL
+#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED 0x8000000000000003ULL
/*
* Bitmasks of exposed registers (with VMM).
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index e770c4fc47f4..8727c7e21dd1 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -24,4 +24,26 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
+/*
+ * To prevent immediate repeat of single step trap on return from SIGTRAP
+ * handler if the trap flag (TF) is set without an external debugger attached,
+ * clear the software event flag in the augmented SS, ensuring no single-step
+ * trap is pending upon ERETU completion.
+ *
+ * Note, this function should be called in sigreturn() before the original
+ * state is restored to make sure the TF is read from the entry frame.
+ */
+static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs)
+{
+ /*
+ * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction
+ * is being single-stepped, do not clear the software event flag in the
+ * augmented SS, thus a debugger won't skip over the following instruction.
+ */
+#ifdef CONFIG_X86_FRED
+ if (!(regs->flags & X86_EFLAGS_TF))
+ regs->fred_ss.swevent = 0;
+#endif
+}
+
#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 8b19294600c4..7ddef3a69866 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -106,7 +106,7 @@ void tdx_init(void);
typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
-static inline u64 sc_retry(sc_func_t func, u64 fn,
+static __always_inline u64 sc_retry(sc_func_t func, u64 fn,
struct tdx_module_args *args)
{
int retry = RDRAND_RETRY_LOOPS;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ecfe7b497cad..ea1d984166cd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,24 @@ static struct module *its_mod;
#endif
static void *its_page;
static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+ void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+ if (!page)
+ return NULL;
+
+ void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+ GFP_KERNEL);
+ if (!tmp)
+ return NULL;
+
+ pages->pages = tmp;
+ pages->pages[pages->num++] = page;
+
+ return no_free_ptr(page);
+}
/* Initialize a thunk with the "jmp *reg; int3" instructions. */
static void *its_init_thunk(void *thunk, int reg)
@@ -151,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg)
return thunk + offset;
}
+static void its_pages_protect(struct its_array *pages)
+{
+ for (int i = 0; i < pages->num; i++) {
+ void *page = pages->pages[i];
+ execmem_restore_rox(page, PAGE_SIZE);
+ }
+}
+
+static void its_fini_core(void)
+{
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+ its_pages_protect(&its_pages);
+ kfree(its_pages.pages);
+}
+
#ifdef CONFIG_MODULES
void its_init_mod(struct module *mod)
{
@@ -173,10 +206,8 @@ void its_fini_mod(struct module *mod)
its_page = NULL;
mutex_unlock(&text_mutex);
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
- execmem_restore_rox(page, PAGE_SIZE);
- }
+ if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ its_pages_protect(&mod->arch.its_pages);
}
void its_free_mod(struct module *mod)
@@ -184,37 +215,33 @@ void its_free_mod(struct module *mod)
if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
return;
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
+ for (int i = 0; i < mod->arch.its_pages.num; i++) {
+ void *page = mod->arch.its_pages.pages[i];
execmem_free(page);
}
- kfree(mod->its_page_array);
+ kfree(mod->arch.its_pages.pages);
}
#endif /* CONFIG_MODULES */
static void *its_alloc(void)
{
- void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
-
- if (!page)
- return NULL;
+ struct its_array *pages = &its_pages;
+ void *page;
#ifdef CONFIG_MODULES
- if (its_mod) {
- void *tmp = krealloc(its_mod->its_page_array,
- (its_mod->its_num_pages+1) * sizeof(void *),
- GFP_KERNEL);
- if (!tmp)
- return NULL;
+ if (its_mod)
+ pages = &its_mod->arch.its_pages;
+#endif
- its_mod->its_page_array = tmp;
- its_mod->its_page_array[its_mod->its_num_pages++] = page;
+ page = __its_alloc(pages);
+ if (!page)
+ return NULL;
- execmem_make_temp_rw(page, PAGE_SIZE);
- }
-#endif /* CONFIG_MODULES */
+ execmem_make_temp_rw(page, PAGE_SIZE);
+ if (pages == &its_pages)
+ set_memory_x((unsigned long)page, 1);
- return no_free_ptr(page);
+ return page;
}
static void *its_allocate_thunk(int reg)
@@ -268,7 +295,9 @@ u8 *its_static_thunk(int reg)
return thunk;
}
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
/*
* Nomenclature for variable names to simplify and clarify this code and ease
@@ -2338,6 +2367,8 @@ void __init alternative_instructions(void)
apply_retpolines(__retpoline_sites, __retpoline_sites_end);
apply_returns(__return_sites, __return_sites_end);
+ its_fini_core();
+
/*
* Adjust all CALL instructions to point to func()-10, including
* those in .altinstr_replacement.
@@ -3107,6 +3138,6 @@ void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, c
*/
void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
{
- __smp_text_poke_batch_add(addr, opcode, len, emulate);
+ smp_text_poke_batch_add(addr, opcode, len, emulate);
smp_text_poke_batch_finish();
}
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..b2ad8d13211a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -31,7 +31,7 @@
#include "cpu.h"
-u16 invlpgb_count_max __ro_after_init;
+u16 invlpgb_count_max __ro_after_init = 1;
static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
{
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
struct rdt_hw_mon_domain *hw_dom;
struct rdt_domain_hdr *hdr;
struct rdt_mon_domain *d;
+ struct cacheinfo *ci;
int err;
lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
d = &hw_dom->d_resctrl;
d->hdr.id = id;
d->hdr.type = RESCTRL_MON_DOMAIN;
- d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
- if (!d->ci) {
+ ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!ci) {
pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
mon_domain_free(hw_dom);
return;
}
+ d->ci_id = ci->id;
cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
arch_mon_domain_online(r, d);
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 98123ff10506..42bbc42bd350 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn)
struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask)
@@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn)
struct rt_sigframe_ia32 __user *frame;
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ee9453891901..d483b585c6c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
@@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18266cc3d98c..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+ enum cpuhp_smt_control old = cpu_smt_control;
+ int ret;
+
+ /*
+ * If SMT has been disabled and SMT siblings are in HLT, bring them back
+ * online and offline them again so that they end up in MWAIT proper.
+ *
+ * Called with hotplug enabled.
+ */
+ if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+ return 0;
+
+ ret = cpuhp_smt_enable();
+ if (ret)
+ return ret;
+
+ ret = cpuhp_smt_disable(old);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fc78c2325fd2..58ede3fa6a75 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1244,6 +1244,10 @@ void play_dead_common(void)
local_irq_disable();
}
+/*
+ * We need to flush the caches before going to sleep, lest we have
+ * dirty data in our caches when we come back up.
+ */
void __noreturn mwait_play_dead(unsigned int eax_hint)
{
struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
@@ -1290,50 +1294,6 @@ void __noreturn mwait_play_dead(unsigned int eax_hint)
}
/*
- * We need to flush the caches before going to sleep, lest we have
- * dirty data in our caches when we come back up.
- */
-static inline void mwait_play_dead_cpuid_hint(void)
-{
- unsigned int eax, ebx, ecx, edx;
- unsigned int highest_cstate = 0;
- unsigned int highest_subcstate = 0;
- int i;
-
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
- return;
- if (!this_cpu_has(X86_FEATURE_MWAIT))
- return;
- if (!this_cpu_has(X86_FEATURE_CLFLUSH))
- return;
-
- eax = CPUID_LEAF_MWAIT;
- ecx = 0;
- native_cpuid(&eax, &ebx, &ecx, &edx);
-
- /*
- * eax will be 0 if EDX enumeration is not valid.
- * Initialized below to cstate, sub_cstate value when EDX is valid.
- */
- if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
- eax = 0;
- } else {
- edx >>= MWAIT_SUBSTATE_SIZE;
- for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
- if (edx & MWAIT_SUBSTATE_MASK) {
- highest_cstate = i;
- highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
- }
- }
- eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
- (highest_subcstate - 1);
- }
-
- mwait_play_dead(eax);
-}
-
-/*
* Kick all "offline" CPUs out of mwait on kexec(). See comment in
* mwait_play_dead().
*/
@@ -1383,9 +1343,9 @@ void native_play_dead(void)
play_dead_common();
tboot_shutdown(TB_SHUTDOWN_WFS);
- mwait_play_dead_cpuid_hint();
- if (cpuidle_play_dead())
- hlt_play_dead();
+ /* Below returns only on error. */
+ cpuidle_play_dead();
+ hlt_play_dead();
}
#else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index cbc84c6abc2e..4e06e2e89a8f 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4896,12 +4896,16 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
{
u64 error_code = PFERR_GUEST_FINAL_MASK;
u8 level = PG_LEVEL_4K;
+ u64 direct_bits;
u64 end;
int r;
if (!vcpu->kvm->arch.pre_fault_allowed)
return -EOPNOTSUPP;
+ if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+ return -EINVAL;
+
/*
* reload is efficient when called repeatedly, so we can do it on
* every iteration.
@@ -4910,15 +4914,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
if (r)
return r;
+ direct_bits = 0;
if (kvm_arch_has_private_mem(vcpu->kvm) &&
kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
error_code |= PFERR_PRIVATE_ACCESS;
+ else
+ direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
/*
* Shadow paging uses GVA for kvm page fault, so restrict to
* two-dimensional paging.
*/
- r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+ r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
if (r < 0)
return r;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 5a69b657dae9..459c3b791fd4 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2871,6 +2871,33 @@ void __init sev_set_cpu_caps(void)
}
}
+static bool is_sev_snp_initialized(void)
+{
+ struct sev_user_data_snp_status *status;
+ struct sev_data_snp_addr buf;
+ bool initialized = false;
+ int ret, error = 0;
+
+ status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
+ if (!status)
+ return false;
+
+ buf.address = __psp_pa(status);
+ ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
+ if (ret) {
+ pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
+ ret, error, error);
+ goto out;
+ }
+
+ initialized = !!status->state;
+
+out:
+ snp_free_firmware_page(status);
+
+ return initialized;
+}
+
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
@@ -2975,6 +3002,14 @@ void __init sev_hardware_setup(void)
sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
out:
+ if (sev_enabled) {
+ init_args.probe = true;
+ if (sev_platform_init(&init_args))
+ sev_supported = sev_es_supported = sev_snp_supported = false;
+ else if (sev_snp_supported)
+ sev_snp_supported = is_sev_snp_initialized();
+ }
+
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
@@ -3001,15 +3036,6 @@ out:
sev_supported_vmsa_features = 0;
if (sev_es_debug_swap_enabled)
sev_supported_vmsa_features |= SVM_SEV_FEAT_DEBUG_SWAP;
-
- if (!sev_enabled)
- return;
-
- /*
- * Do both SNP and SEV initialization at KVM module load.
- */
- init_args.probe = true;
- sev_platform_init(&init_args);
}
void sev_hardware_unsetup(void)
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index b952bc673271..1ad20c273f3b 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -1212,11 +1212,13 @@ static int tdx_map_gpa(struct kvm_vcpu *vcpu)
/*
* Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
* userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
- * bit set. If not, the error code is not defined in GHCI for TDX, use
- * TDVMCALL_STATUS_INVALID_OPERAND for this case.
+ * bit set. This is a base call so it should always be supported, but
+ * KVM has no way to ensure that userspace implements the GHCI correctly.
+ * So if KVM_HC_MAP_GPA_RANGE does not cause a VMEXIT, return an error
+ * to the guest.
*/
if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
- ret = TDVMCALL_STATUS_INVALID_OPERAND;
+ ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
goto error;
}
@@ -1449,20 +1451,85 @@ error:
return 1;
}
+static int tdx_complete_get_td_vm_call_info(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.get_tdvmcall_info.ret);
+
+ /*
+ * For now, there is no TDVMCALL beyond GHCI base API supported by KVM
+ * directly without the support from userspace, just set the value
+ * returned from userspace.
+ */
+ tdx->vp_enter_args.r11 = vcpu->run->tdx.get_tdvmcall_info.r11;
+ tdx->vp_enter_args.r12 = vcpu->run->tdx.get_tdvmcall_info.r12;
+ tdx->vp_enter_args.r13 = vcpu->run->tdx.get_tdvmcall_info.r13;
+ tdx->vp_enter_args.r14 = vcpu->run->tdx.get_tdvmcall_info.r14;
+
+ return 1;
+}
+
static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu)
{
struct vcpu_tdx *tdx = to_tdx(vcpu);
- if (tdx->vp_enter_args.r12)
- tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
- else {
+ switch (tdx->vp_enter_args.r12) {
+ case 0:
tdx->vp_enter_args.r11 = 0;
+ tdx->vp_enter_args.r12 = 0;
tdx->vp_enter_args.r13 = 0;
tdx->vp_enter_args.r14 = 0;
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+ return 1;
+ case 1:
+ vcpu->run->tdx.get_tdvmcall_info.leaf = tdx->vp_enter_args.r12;
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_TD_VM_CALL_INFO;
+ vcpu->run->tdx.get_tdvmcall_info.ret = TDVMCALL_STATUS_SUCCESS;
+ vcpu->run->tdx.get_tdvmcall_info.r11 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r12 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r13 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r14 = 0;
+ vcpu->arch.complete_userspace_io = tdx_complete_get_td_vm_call_info;
+ return 0;
+ default:
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
}
+}
+
+static int tdx_complete_simple(struct kvm_vcpu *vcpu)
+{
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.unknown.ret);
return 1;
}
+static int tdx_get_quote(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 gpa = tdx->vp_enter_args.r12;
+ u64 size = tdx->vp_enter_args.r13;
+
+ /* The gpa of buffer must have shared bit set. */
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_QUOTE;
+ vcpu->run->tdx.get_quote.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.get_quote.gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+ vcpu->run->tdx.get_quote.size = size;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
static int handle_tdvmcall(struct kvm_vcpu *vcpu)
{
switch (tdvmcall_leaf(vcpu)) {
@@ -1472,11 +1539,13 @@ static int handle_tdvmcall(struct kvm_vcpu *vcpu)
return tdx_report_fatal_error(vcpu);
case TDVMCALL_GET_TD_VM_CALL_INFO:
return tdx_get_td_vm_call_info(vcpu);
+ case TDVMCALL_GET_QUOTE:
+ return tdx_get_quote(vcpu);
default:
break;
}
- tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED);
return 1;
}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 607d6a2e66e2..8a34fff6ab2b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,7 +30,6 @@
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
-#include <linux/execmem.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
@@ -749,8 +748,6 @@ void mark_rodata_ro(void)
pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee66fae9ebcc..fdb6cab524f0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>
-#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -1392,8 +1391,6 @@ void mark_rodata_ro(void)
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
/*
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index 46edc11726b7..8834c76f91c9 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -1257,6 +1257,9 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
pgprot_t pgprot;
int i = 0;
+ if (!cpu_feature_enabled(X86_FEATURE_PSE))
+ return 0;
+
addr &= PMD_MASK;
pte = pte_offset_kernel(pmd, addr);
first = *pte;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 190299834011..c0c40b67524e 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -98,6 +98,11 @@ void __init pti_check_boottime_disable(void)
return;
setup_force_cpu_cap(X86_FEATURE_PTI);
+
+ if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+ pr_debug("PTI enabled, disabling INVLPGB\n");
+ setup_clear_cpu_cap(X86_FEATURE_INVLPGB);
+ }
}
static int __init pti_parse_cmdline(char *arg)
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index a7c23f2a58c9..a2294c1649f6 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -192,7 +192,8 @@ out:
int arch_resume_nosmt(void)
{
- int ret = 0;
+ int ret;
+
/*
* We reached this while coming out of hibernation. This means
* that SMT siblings are sleeping in hlt, as mwait is not safe
@@ -206,18 +207,10 @@ int arch_resume_nosmt(void)
* Called with hotplug disabled.
*/
cpu_hotplug_enable();
- if (cpu_smt_control == CPU_SMT_DISABLED ||
- cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
- enum cpuhp_smt_control old = cpu_smt_control;
-
- ret = cpuhp_smt_enable();
- if (ret)
- goto out;
- ret = cpuhp_smt_disable(old);
- if (ret)
- goto out;
- }
-out:
+
+ ret = arch_cpu_rescan_dead_smt_siblings();
+
cpu_hotplug_disable();
+
return ret;
}
diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c
index 3275870330fe..fae8aabad10f 100644
--- a/arch/x86/um/ptrace.c
+++ b/arch/x86/um/ptrace.c
@@ -161,7 +161,7 @@ static int fpregs_legacy_set(struct task_struct *target,
from = kbuf;
}
- return um_fxsr_from_i387(fxsave, &buf);
+ return um_fxsr_from_i387(fxsave, from);
}
#endif
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 2457d13c3f9e..c7a9a087ccaf 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -75,8 +75,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err,
args->r9, args->r10, args->r11);
}
-static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
- u64 fn, struct tdx_module_args *args)
+static __always_inline int sc_retry_prerr(sc_func_t func,
+ sc_err_func_t err_func,
+ u64 fn, struct tdx_module_args *args)
{
u64 sret = sc_retry(func, fn, args);
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index cb1725c40e36..d62aa1c316fc 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -349,7 +349,7 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(x) ((pte_t) { (x).val })
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 3af1d284add5..70d704615be5 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -998,20 +998,20 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio,
if (!plug || rq_list_empty(&plug->mq_list))
return false;
- rq_list_for_each(&plug->mq_list, rq) {
- if (rq->q == q) {
- if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
- BIO_MERGE_OK)
- return true;
- break;
- }
+ rq = plug->mq_list.tail;
+ if (rq->q == q)
+ return blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+ BIO_MERGE_OK;
+ else if (!plug->multiple_queues)
+ return false;
- /*
- * Only keep iterating plug list for merges if we have multiple
- * queues
- */
- if (!plug->multiple_queues)
- break;
+ rq_list_for_each(&plug->mq_list, rq) {
+ if (rq->q != q)
+ continue;
+ if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) ==
+ BIO_MERGE_OK)
+ return true;
+ break;
}
return false;
}
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 8f15d1aa6eb8..351d659280e1 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1225,6 +1225,7 @@ void blk_zone_write_plug_bio_endio(struct bio *bio)
if (bio_flagged(bio, BIO_EMULATES_ZONE_APPEND)) {
bio->bi_opf &= ~REQ_OP_MASK;
bio->bi_opf |= REQ_OP_ZONE_APPEND;
+ bio_clear_flag(bio, BIO_EMULATES_ZONE_APPEND);
}
/*
@@ -1306,7 +1307,6 @@ again:
spin_unlock_irqrestore(&zwplug->lock, flags);
bdev = bio->bi_bdev;
- submit_bio_noacct_nocheck(bio);
/*
* blk-mq devices will reuse the extra reference on the request queue
@@ -1314,8 +1314,12 @@ again:
* path for BIO-based devices will not do that. So drop this extra
* reference here.
*/
- if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO))
+ if (bdev_test_flag(bdev, BD_HAS_SUBMIT_BIO)) {
+ bdev->bd_disk->fops->submit_bio(bio);
blk_queue_exit(bdev->bd_disk->queue);
+ } else {
+ blk_mq_submit_bio(bio);
+ }
put_zwplug:
/* Drop the reference we took in disk_zone_wplug_schedule_bio_work(). */
diff --git a/crypto/Kconfig b/crypto/Kconfig
index e9fee7818e27..e1cfd0d4cc8f 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -176,16 +176,33 @@ config CRYPTO_USER
config CRYPTO_SELFTESTS
bool "Enable cryptographic self-tests"
- depends on DEBUG_KERNEL
+ depends on EXPERT
help
Enable the cryptographic self-tests.
The cryptographic self-tests run at boot time, or at algorithm
registration time if algorithms are dynamically loaded later.
- This is primarily intended for developer use. It should not be
- enabled in production kernels, unless you are trying to use these
- tests to fulfill a FIPS testing requirement.
+ There are two main use cases for these tests:
+
+ - Development and pre-release testing. In this case, also enable
+ CRYPTO_SELFTESTS_FULL to get the full set of tests. All crypto code
+ in the kernel is expected to pass the full set of tests.
+
+ - Production kernels, to help prevent buggy drivers from being used
+ and/or meet FIPS 140-3 pre-operational testing requirements. In
+ this case, enable CRYPTO_SELFTESTS but not CRYPTO_SELFTESTS_FULL.
+
+config CRYPTO_SELFTESTS_FULL
+ bool "Enable the full set of cryptographic self-tests"
+ depends on CRYPTO_SELFTESTS
+ help
+ Enable the full set of cryptographic self-tests for each algorithm.
+
+ The full set of tests should be enabled for development and
+ pre-release testing, but not in production kernels.
+
+ All crypto code in the kernel is expected to pass the full tests.
config CRYPTO_NULL
tristate "Null algorithms"
diff --git a/crypto/ahash.c b/crypto/ahash.c
index e10bc2659ae4..bc84a07c924c 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -600,12 +600,14 @@ static void ahash_def_finup_done2(void *data, int err)
static int ahash_def_finup_finish1(struct ahash_request *req, int err)
{
+ struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+
if (err)
goto out;
req->base.complete = ahash_def_finup_done2;
- err = crypto_ahash_final(req);
+ err = crypto_ahash_alg(tfm)->final(req);
if (err == -EINPROGRESS || err == -EBUSY)
return err;
diff --git a/crypto/hkdf.c b/crypto/hkdf.c
index f24c2a8d4df9..82d1b32ca6ce 100644
--- a/crypto/hkdf.c
+++ b/crypto/hkdf.c
@@ -566,7 +566,7 @@ static int __init crypto_hkdf_module_init(void)
static void __exit crypto_hkdf_module_exit(void) {}
-module_init(crypto_hkdf_module_init);
+late_initcall(crypto_hkdf_module_init);
module_exit(crypto_hkdf_module_exit);
MODULE_LICENSE("GPL");
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 72005074a5c2..32f753d6c430 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -45,6 +45,7 @@ static bool notests;
module_param(notests, bool, 0644);
MODULE_PARM_DESC(notests, "disable all crypto self-tests");
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
static bool noslowtests;
module_param(noslowtests, bool, 0644);
MODULE_PARM_DESC(noslowtests, "disable slow crypto self-tests");
@@ -52,6 +53,10 @@ MODULE_PARM_DESC(noslowtests, "disable slow crypto self-tests");
static unsigned int fuzz_iterations = 100;
module_param(fuzz_iterations, uint, 0644);
MODULE_PARM_DESC(fuzz_iterations, "number of fuzz test iterations");
+#else
+#define noslowtests 1
+#define fuzz_iterations 0
+#endif
#ifndef CONFIG_CRYPTO_SELFTESTS
@@ -319,9 +324,9 @@ struct testvec_config {
/*
* The following are the lists of testvec_configs to test for each algorithm
- * type when the fast crypto self-tests are enabled. They aim to provide good
- * test coverage, while keeping the test time much shorter than the full tests
- * so that the fast tests can be used to fulfill FIPS 140 testing requirements.
+ * type when the "fast" crypto self-tests are enabled. They aim to provide good
+ * test coverage, while keeping the test time much shorter than the "full" tests
+ * so that the "fast" tests can be enabled in a wider range of circumstances.
*/
/* Configs for skciphers and aeads */
@@ -1183,14 +1188,18 @@ static void generate_random_testvec_config(struct rnd_state *rng,
static void crypto_disable_simd_for_test(void)
{
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
migrate_disable();
__this_cpu_write(crypto_simd_disabled_for_test, true);
+#endif
}
static void crypto_reenable_simd_for_test(void)
{
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
__this_cpu_write(crypto_simd_disabled_for_test, false);
migrate_enable();
+#endif
}
/*
diff --git a/drivers/accel/amdxdna/aie2_psp.c b/drivers/accel/amdxdna/aie2_psp.c
index dc3a072ce3b6..f28a060a8810 100644
--- a/drivers/accel/amdxdna/aie2_psp.c
+++ b/drivers/accel/amdxdna/aie2_psp.c
@@ -126,8 +126,8 @@ struct psp_device *aie2m_psp_create(struct drm_device *ddev, struct psp_config *
psp->ddev = ddev;
memcpy(psp->psp_regs, conf->psp_regs, sizeof(psp->psp_regs));
- psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN) + PSP_FW_ALIGN;
- psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz, GFP_KERNEL);
+ psp->fw_buf_sz = ALIGN(conf->fw_size, PSP_FW_ALIGN);
+ psp->fw_buffer = drmm_kmalloc(ddev, psp->fw_buf_sz + PSP_FW_ALIGN, GFP_KERNEL);
if (!psp->fw_buffer) {
drm_err(ddev, "no memory for fw buffer");
return NULL;
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index 6f8bbe1247a5..c9a0bcaba2e4 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -33,7 +33,7 @@
static DEFINE_MUTEX(isolated_cpus_lock);
static DEFINE_MUTEX(round_robin_lock);
-static unsigned long power_saving_mwait_eax;
+static unsigned int power_saving_mwait_eax;
static unsigned char tsc_detected_unstable;
static unsigned char tsc_marked_unstable;
diff --git a/drivers/acpi/acpica/dsmethod.c b/drivers/acpi/acpica/dsmethod.c
index c8f37f4e6626..fef6fb29ece4 100644
--- a/drivers/acpi/acpica/dsmethod.c
+++ b/drivers/acpi/acpica/dsmethod.c
@@ -483,6 +483,13 @@ acpi_ds_call_control_method(struct acpi_thread_state *thread,
return_ACPI_STATUS(AE_NULL_OBJECT);
}
+ if (this_walk_state->num_operands < obj_desc->method.param_count) {
+ ACPI_ERROR((AE_INFO, "Missing argument for method [%4.4s]",
+ acpi_ut_get_node_name(method_node)));
+
+ return_ACPI_STATUS(AE_AML_UNINITIALIZED_ARG);
+ }
+
/* Init for new method, possibly wait on method mutex */
status =
diff --git a/drivers/acpi/apei/einj-core.c b/drivers/acpi/apei/einj-core.c
index fea11a35eea3..9b041415a9d0 100644
--- a/drivers/acpi/apei/einj-core.c
+++ b/drivers/acpi/apei/einj-core.c
@@ -883,19 +883,16 @@ static int __init einj_init(void)
}
einj_dev = faux_device_create("acpi-einj", NULL, &einj_device_ops);
- if (!einj_dev)
- return -ENODEV;
- einj_initialized = true;
+ if (einj_dev)
+ einj_initialized = true;
return 0;
}
static void __exit einj_exit(void)
{
- if (einj_initialized)
- faux_device_destroy(einj_dev);
-
+ faux_device_destroy(einj_dev);
}
module_init(einj_init);
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a9ae2fd62863..6b649031808f 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -476,7 +476,7 @@ bool cppc_allow_fast_switch(void)
struct cpc_desc *cpc_ptr;
int cpu;
- for_each_possible_cpu(cpu) {
+ for_each_present_cpu(cpu) {
cpc_ptr = per_cpu(cpc_desc_ptr, cpu);
desired_reg = &cpc_ptr->cpc_regs[DESIRED_PERF];
if (!CPC_IN_SYSTEM_MEMORY(desired_reg) &&
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 6f4203716b53..75c7db8b156a 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -23,8 +23,10 @@
#include <linux/delay.h>
#include <linux/interrupt.h>
#include <linux/list.h>
+#include <linux/printk.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
+#include <linux/string.h>
#include <linux/suspend.h>
#include <linux/acpi.h>
#include <linux/dmi.h>
@@ -2031,6 +2033,21 @@ void __init acpi_ec_ecdt_probe(void)
goto out;
}
+ if (!strstarts(ecdt_ptr->id, "\\")) {
+ /*
+ * The ECDT table on some MSI notebooks contains invalid data, together
+ * with an empty ID string ("").
+ *
+ * Section 5.2.15 of the ACPI specification requires the ID string to be
+ * a "fully qualified reference to the (...) embedded controller device",
+ * so this string always has to start with a backslash.
+ *
+ * By verifying this we can avoid such faulty ECDT tables in a safe way.
+ */
+ pr_err(FW_BUG "Ignoring ECDT due to invalid ID string \"%s\"\n", ecdt_ptr->id);
+ goto out;
+ }
+
ec = acpi_ec_alloc();
if (!ec)
goto out;
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 00910ccd7eda..e2781864fdce 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -175,6 +175,12 @@ bool processor_physically_present(acpi_handle handle);
static inline void acpi_early_processor_control_setup(void) {}
#endif
+#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void);
+#else
+static inline void acpi_idle_rescan_dead_smt_siblings(void) {}
+#endif
+
/* --------------------------------------------------------------------------
Embedded Controller
-------------------------------------------------------------------------- */
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 3b281bc1e73c..65e779be64ff 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -279,6 +279,9 @@ static int __init acpi_processor_driver_init(void)
* after acpi_cppc_processor_probe() has been called for all online CPUs
*/
acpi_processor_init_invariance_cppc();
+
+ acpi_idle_rescan_dead_smt_siblings();
+
return 0;
err:
driver_unregister(&acpi_processor_driver);
diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index e2febca2ec13..2c2dc559e0f8 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -24,6 +24,8 @@
#include <acpi/processor.h>
#include <linux/context_tracking.h>
+#include "internal.h"
+
/*
* Include the apic definitions for x86 to have the APIC timer related defines
* available also for UP (on SMP it gets magically included via linux/smp.h).
@@ -55,6 +57,12 @@ struct cpuidle_driver acpi_idle_driver = {
};
#ifdef CONFIG_ACPI_PROCESSOR_CSTATE
+void acpi_idle_rescan_dead_smt_siblings(void)
+{
+ if (cpuidle_get_driver() == &acpi_idle_driver)
+ arch_cpu_rescan_dead_smt_siblings();
+}
+
static
DEFINE_PER_CPU(struct acpi_processor_cx * [CPUIDLE_STATE_MAX], acpi_cstate);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 7d59c6c9185f..b1ab192d7a08 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -667,6 +667,13 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
},
},
{
+ /* MACHENIKE L16P/L16P */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "MACHENIKE"),
+ DMI_MATCH(DMI_BOARD_NAME, "L16P"),
+ },
+ },
+ {
/*
* TongFang GM5HG0A in case of the SKIKK Vanaheim relabel the
* board-name is changed, so check OEM strings instead. Note
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 163ac909bd06..e5e5c2e81d09 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -1410,8 +1410,15 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
static bool ahci_broken_lpm(struct pci_dev *pdev)
{
+ /*
+ * Platforms with LPM problems.
+ * If driver_data is NULL, there is no existing BIOS version with
+ * functioning LPM.
+ * If driver_data is non-NULL, then driver_data contains the DMI BIOS
+ * build date of the first BIOS version with functioning LPM (i.e. older
+ * BIOS versions have broken LPM).
+ */
static const struct dmi_system_id sysids[] = {
- /* Various Lenovo 50 series have LPM issues with older BIOSen */
{
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
@@ -1438,13 +1445,30 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
},
+ .driver_data = "20180409", /* 2.35 */
+ },
+ {
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "ASUSPRO D840MB_M840SA"),
+ },
+ /* 320 is broken, there is no known good version. */
+ },
+ {
/*
- * Note date based on release notes, 2.35 has been
- * reported to be good, but I've been unable to get
- * a hold of the reporter to get the DMI BIOS date.
- * TODO: fix this.
+ * AMD 500 Series Chipset SATA Controller [1022:43eb]
+ * on this motherboard timeouts on ports 5 and 6 when
+ * LPM is enabled, at least with WDC WD20EFAX-68FB5N0
+ * hard drives. LPM with the same drive works fine on
+ * all other ports on the same controller.
*/
- .driver_data = "20180310", /* 2.35 */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR,
+ "ASUSTeK COMPUTER INC."),
+ DMI_MATCH(DMI_BOARD_NAME,
+ "ROG STRIX B550-F GAMING (WI-FI)"),
+ },
+ /* 3621 is broken, there is no known good version. */
},
{ } /* terminate list */
};
@@ -1455,6 +1479,9 @@ static bool ahci_broken_lpm(struct pci_dev *pdev)
if (!dmi)
return false;
+ if (!dmi->driver_data)
+ return true;
+
dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index b7f0bf795521..f2140fc06ba0 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -514,15 +514,19 @@ unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
EXPORT_SYMBOL_GPL(ata_acpi_gtm_xfermask);
/**
- * ata_acpi_cbl_80wire - Check for 80 wire cable
+ * ata_acpi_cbl_pata_type - Return PATA cable type
* @ap: Port to check
- * @gtm: GTM data to use
*
- * Return 1 if the @gtm indicates the BIOS selected an 80wire mode.
+ * Return ATA_CBL_PATA* according to the transfer mode selected by BIOS
*/
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
+int ata_acpi_cbl_pata_type(struct ata_port *ap)
{
struct ata_device *dev;
+ int ret = ATA_CBL_PATA_UNK;
+ const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
+
+ if (!gtm)
+ return ATA_CBL_PATA40;
ata_for_each_dev(dev, &ap->link, ENABLED) {
unsigned int xfer_mask, udma_mask;
@@ -530,13 +534,17 @@ int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
- if (udma_mask & ~ATA_UDMA_MASK_40C)
- return 1;
+ ret = ATA_CBL_PATA40;
+
+ if (udma_mask & ~ATA_UDMA_MASK_40C) {
+ ret = ATA_CBL_PATA80;
+ break;
+ }
}
- return 0;
+ return ret;
}
-EXPORT_SYMBOL_GPL(ata_acpi_cbl_80wire);
+EXPORT_SYMBOL_GPL(ata_acpi_cbl_pata_type);
static void ata_acpi_gtf_to_tf(struct ata_device *dev,
const struct ata_acpi_gtf *gtf,
diff --git a/drivers/ata/pata_cs5536.c b/drivers/ata/pata_cs5536.c
index b811efd2cc34..73e81e160c91 100644
--- a/drivers/ata/pata_cs5536.c
+++ b/drivers/ata/pata_cs5536.c
@@ -27,7 +27,7 @@
#include <scsi/scsi_host.h>
#include <linux/dmi.h>
-#ifdef CONFIG_X86_32
+#if defined(CONFIG_X86) && defined(CONFIG_X86_32)
#include <asm/msr.h>
static int use_msr;
module_param_named(msr, use_msr, int, 0644);
diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
index fbf5f07ea357..f7a933eefe05 100644
--- a/drivers/ata/pata_macio.c
+++ b/drivers/ata/pata_macio.c
@@ -1298,7 +1298,7 @@ static int pata_macio_pci_attach(struct pci_dev *pdev,
priv->dev = &pdev->dev;
/* Get MMIO regions */
- if (pci_request_regions(pdev, "pata-macio")) {
+ if (pcim_request_all_regions(pdev, "pata-macio")) {
dev_err(&pdev->dev,
"Cannot obtain PCI resources\n");
return -EBUSY;
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index 696b99720dcb..bb80e7800dcb 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -201,11 +201,9 @@ static int via_cable_detect(struct ata_port *ap) {
two drives */
if (ata66 & (0x10100000 >> (16 * ap->port_no)))
return ATA_CBL_PATA80;
+
/* Check with ACPI so we can spot BIOS reported SATA bridges */
- if (ata_acpi_init_gtm(ap) &&
- ata_acpi_cbl_80wire(ap, ata_acpi_init_gtm(ap)))
- return ATA_CBL_PATA80;
- return ATA_CBL_PATA40;
+ return ata_acpi_cbl_pata_type(ap);
}
static int via_pre_reset(struct ata_link *link, unsigned long deadline)
@@ -368,7 +366,8 @@ static unsigned int via_mode_filter(struct ata_device *dev, unsigned int mask)
}
if (dev->class == ATA_DEV_ATAPI &&
- dmi_check_system(no_atapi_dma_dmi_table)) {
+ (dmi_check_system(no_atapi_dma_dmi_table) ||
+ config->id == PCI_DEVICE_ID_VIA_6415)) {
ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n");
mask &= ATA_MASK_PIO;
}
diff --git a/drivers/atm/atmtcp.c b/drivers/atm/atmtcp.c
index d4aa0f353b6c..eeae160c898d 100644
--- a/drivers/atm/atmtcp.c
+++ b/drivers/atm/atmtcp.c
@@ -288,7 +288,9 @@ static int atmtcp_c_send(struct atm_vcc *vcc,struct sk_buff *skb)
struct sk_buff *new_skb;
int result = 0;
- if (!skb->len) return 0;
+ if (skb->len < sizeof(struct atmtcp_hdr))
+ goto done;
+
dev = vcc->dev_data;
hdr = (struct atmtcp_hdr *) skb->data;
if (hdr->length == ATMTCP_HDR_MAGIC) {
diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
index 1206ab764ba9..f2e91b7d79f0 100644
--- a/drivers/atm/idt77252.c
+++ b/drivers/atm/idt77252.c
@@ -852,6 +852,8 @@ queue_skb(struct idt77252_dev *card, struct vc_map *vc,
IDT77252_PRV_PADDR(skb) = dma_map_single(&card->pcidev->dev, skb->data,
skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(&card->pcidev->dev, IDT77252_PRV_PADDR(skb)))
+ return -ENOMEM;
error = -EINVAL;
@@ -1857,6 +1859,8 @@ add_rx_skb(struct idt77252_dev *card, int queue,
paddr = dma_map_single(&card->pcidev->dev, skb->data,
skb_end_pointer(skb) - skb->data,
DMA_FROM_DEVICE);
+ if (dma_mapping_error(&card->pcidev->dev, paddr))
+ goto outpoolrm;
IDT77252_PRV_PADDR(skb) = paddr;
if (push_rx_skb(card, skb, queue)) {
@@ -1871,6 +1875,7 @@ outunmap:
dma_unmap_single(&card->pcidev->dev, IDT77252_PRV_PADDR(skb),
skb_end_pointer(skb) - skb->data, DMA_FROM_DEVICE);
+outpoolrm:
handle = IDT77252_PRV_POOL(skb);
card->sbpool[POOL_QUEUE(handle)].skb[POOL_INDEX(handle)] = NULL;
diff --git a/drivers/base/faux.c b/drivers/base/faux.c
index 9054d346bd7f..f5fbda0a9a44 100644
--- a/drivers/base/faux.c
+++ b/drivers/base/faux.c
@@ -86,6 +86,7 @@ static struct device_driver faux_driver = {
.name = "faux_driver",
.bus = &faux_bus_type,
.probe_type = PROBE_FORCE_SYNCHRONOUS,
+ .suppress_bind_attrs = true,
};
static void faux_device_release(struct device *dev)
@@ -169,7 +170,7 @@ struct faux_device *faux_device_create_with_groups(const char *name,
* successful is almost impossible to determine by the caller.
*/
if (!dev->driver) {
- dev_err(dev, "probe did not succeed, tearing down the device\n");
+ dev_dbg(dev, "probe did not succeed, tearing down the device\n");
faux_device_destroy(faux_dev);
faux_dev = NULL;
}
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index 749ae1246f4c..d35caa3c69e1 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -80,6 +80,7 @@ enum {
DEVFL_NEWSIZE = (1<<6), /* need to update dev size in block layer */
DEVFL_FREEING = (1<<7), /* set when device is being cleaned up */
DEVFL_FREED = (1<<8), /* device has been cleaned up */
+ DEVFL_DEAD = (1<<9), /* device has timed out of aoe_deadsecs */
};
enum {
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 50cc90f6ab35..6298f8e271e3 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -754,7 +754,7 @@ rexmit_timer(struct timer_list *timer)
utgts = count_targets(d, NULL);
- if (d->flags & DEVFL_TKILL) {
+ if (d->flags & (DEVFL_TKILL | DEVFL_DEAD)) {
spin_unlock_irqrestore(&d->lock, flags);
return;
}
@@ -786,7 +786,8 @@ rexmit_timer(struct timer_list *timer)
* to clean up.
*/
list_splice(&flist, &d->factive[0]);
- aoedev_downdev(d);
+ d->flags |= DEVFL_DEAD;
+ queue_work(aoe_wq, &d->work);
goto out;
}
@@ -898,6 +899,9 @@ aoecmd_sleepwork(struct work_struct *work)
{
struct aoedev *d = container_of(work, struct aoedev, work);
+ if (d->flags & DEVFL_DEAD)
+ aoedev_downdev(d);
+
if (d->flags & DEVFL_GDALLOC)
aoeblk_gdalloc(d);
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index bba05f0c5bbd..3a240755045b 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -198,9 +198,13 @@ aoedev_downdev(struct aoedev *d)
{
struct aoetgt *t, **tt, **te;
struct list_head *head, *pos, *nx;
+ struct request *rq, *rqnext;
int i;
+ unsigned long flags;
- d->flags &= ~DEVFL_UP;
+ spin_lock_irqsave(&d->lock, flags);
+ d->flags &= ~(DEVFL_UP | DEVFL_DEAD);
+ spin_unlock_irqrestore(&d->lock, flags);
/* clean out active and to-be-retransmitted buffers */
for (i = 0; i < NFACTIVE; i++) {
@@ -223,6 +227,13 @@ aoedev_downdev(struct aoedev *d)
/* clean out the in-process request (if any) */
aoe_failip(d);
+ /* clean out any queued block requests */
+ list_for_each_entry_safe(rq, rqnext, &d->rq_list, queuelist) {
+ list_del_init(&rq->queuelist);
+ blk_mq_start_request(rq);
+ blk_mq_end_request(rq, BLK_STS_IOERR);
+ }
+
/* fast fail all pending I/O */
if (d->blkq) {
/* UP is cleared, freeze+quiesce to insure all are errored */
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index f8d136684109..500840e4a74e 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1248,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS;
lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS);
- if (size_changed) {
- loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
- lo->lo_backing_file);
- loop_set_size(lo, new_size);
- }
-
/* update the direct I/O flag if lo_offset changed */
loop_update_dio(lo);
@@ -1261,6 +1255,11 @@ out_unfreeze:
blk_mq_unfreeze_queue(lo->lo_queue, memflags);
if (partscan)
clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state);
+ if (!err && size_changed) {
+ loff_t new_size = get_size(lo->lo_offset, lo->lo_sizelimit,
+ lo->lo_backing_file);
+ loop_set_size(lo, new_size);
+ }
out_unlock:
mutex_unlock(&lo->lo_mutex);
if (partscan)
diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index c637ea010d34..d36f44f5ee80 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2825,6 +2825,9 @@ static int ublk_ctrl_add_dev(const struct ublksrv_ctrl_cmd *header)
if (copy_from_user(&info, argp, sizeof(info)))
return -EFAULT;
+ if (info.queue_depth > UBLK_MAX_QUEUE_DEPTH || info.nr_hw_queues > UBLK_MAX_NR_QUEUES)
+ return -EINVAL;
+
if (capable(CAP_SYS_ADMIN))
info.flags &= ~UBLK_F_UNPRIVILEGED_DEV;
else if (!(info.flags & UBLK_F_UNPRIVILEGED_DEV))
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 50fe17f1e1d1..e1c688dd2d45 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -396,8 +396,13 @@ static int btintel_pcie_submit_rx(struct btintel_pcie_data *data)
static int btintel_pcie_start_rx(struct btintel_pcie_data *data)
{
int i, ret;
+ struct rxq *rxq = &data->rxq;
+
+ /* Post (BTINTEL_PCIE_RX_DESCS_COUNT - 3) buffers to overcome the
+ * hardware issues leading to race condition at the firmware.
+ */
- for (i = 0; i < BTINTEL_PCIE_RX_MAX_QUEUE; i++) {
+ for (i = 0; i < rxq->count - 3; i++) {
ret = btintel_pcie_submit_rx(data);
if (ret)
return ret;
@@ -1782,8 +1787,8 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
* + size of index * Number of queues(2) * type of index array(4)
* + size of context information
*/
- total = (sizeof(struct tfd) + sizeof(struct urbd0) + sizeof(struct frbd)
- + sizeof(struct urbd1)) * BTINTEL_DESCS_COUNT;
+ total = (sizeof(struct tfd) + sizeof(struct urbd0)) * BTINTEL_PCIE_TX_DESCS_COUNT;
+ total += (sizeof(struct frbd) + sizeof(struct urbd1)) * BTINTEL_PCIE_RX_DESCS_COUNT;
/* Add the sum of size of index array and size of ci struct */
total += (sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4) + sizeof(struct ctx_info);
@@ -1808,36 +1813,36 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
data->dma_v_addr = v_addr;
/* Setup descriptor count */
- data->txq.count = BTINTEL_DESCS_COUNT;
- data->rxq.count = BTINTEL_DESCS_COUNT;
+ data->txq.count = BTINTEL_PCIE_TX_DESCS_COUNT;
+ data->rxq.count = BTINTEL_PCIE_RX_DESCS_COUNT;
/* Setup tfds */
data->txq.tfds_p_addr = p_addr;
data->txq.tfds = v_addr;
- p_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
- v_addr += (sizeof(struct tfd) * BTINTEL_DESCS_COUNT);
+ p_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
+ v_addr += (sizeof(struct tfd) * BTINTEL_PCIE_TX_DESCS_COUNT);
/* Setup urbd0 */
data->txq.urbd0s_p_addr = p_addr;
data->txq.urbd0s = v_addr;
- p_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
- v_addr += (sizeof(struct urbd0) * BTINTEL_DESCS_COUNT);
+ p_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
+ v_addr += (sizeof(struct urbd0) * BTINTEL_PCIE_TX_DESCS_COUNT);
/* Setup FRBD*/
data->rxq.frbds_p_addr = p_addr;
data->rxq.frbds = v_addr;
- p_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
- v_addr += (sizeof(struct frbd) * BTINTEL_DESCS_COUNT);
+ p_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
+ v_addr += (sizeof(struct frbd) * BTINTEL_PCIE_RX_DESCS_COUNT);
/* Setup urbd1 */
data->rxq.urbd1s_p_addr = p_addr;
data->rxq.urbd1s = v_addr;
- p_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
- v_addr += (sizeof(struct urbd1) * BTINTEL_DESCS_COUNT);
+ p_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
+ v_addr += (sizeof(struct urbd1) * BTINTEL_PCIE_RX_DESCS_COUNT);
/* Setup data buffers for txq */
err = btintel_pcie_setup_txq_bufs(data, &data->txq);
@@ -2028,6 +2033,28 @@ static void btintel_pcie_release_hdev(struct btintel_pcie_data *data)
data->hdev = NULL;
}
+static void btintel_pcie_disable_interrupts(struct btintel_pcie_data *data)
+{
+ spin_lock(&data->irq_lock);
+ btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, data->fh_init_mask);
+ btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, data->hw_init_mask);
+ spin_unlock(&data->irq_lock);
+}
+
+static void btintel_pcie_enable_interrupts(struct btintel_pcie_data *data)
+{
+ spin_lock(&data->irq_lock);
+ btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK, ~data->fh_init_mask);
+ btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK, ~data->hw_init_mask);
+ spin_unlock(&data->irq_lock);
+}
+
+static void btintel_pcie_synchronize_irqs(struct btintel_pcie_data *data)
+{
+ for (int i = 0; i < data->alloc_vecs; i++)
+ synchronize_irq(data->msix_entries[i].vector);
+}
+
static int btintel_pcie_setup_internal(struct hci_dev *hdev)
{
struct btintel_pcie_data *data = hci_get_drvdata(hdev);
@@ -2147,6 +2174,8 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
bt_dev_err(hdev, "Firmware download retry count: %d",
fw_dl_retry);
btintel_pcie_dump_debug_registers(hdev);
+ btintel_pcie_disable_interrupts(data);
+ btintel_pcie_synchronize_irqs(data);
err = btintel_pcie_reset_bt(data);
if (err) {
bt_dev_err(hdev, "Failed to do shr reset: %d", err);
@@ -2154,6 +2183,7 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
}
usleep_range(10000, 12000);
btintel_pcie_reset_ia(data);
+ btintel_pcie_enable_interrupts(data);
btintel_pcie_config_msix(data);
err = btintel_pcie_enable_bt(data);
if (err) {
@@ -2286,6 +2316,12 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
data = pci_get_drvdata(pdev);
+ btintel_pcie_disable_interrupts(data);
+
+ btintel_pcie_synchronize_irqs(data);
+
+ flush_work(&data->rx_work);
+
btintel_pcie_reset_bt(data);
for (int i = 0; i < data->alloc_vecs; i++) {
struct msix_entry *msix_entry;
@@ -2298,8 +2334,6 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
btintel_pcie_release_hdev(data);
- flush_work(&data->rx_work);
-
destroy_workqueue(data->workqueue);
btintel_pcie_free(data);
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index 21b964b15c1c..7dad4523236c 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -154,8 +154,11 @@ enum msix_mbox_int_causes {
/* Default interrupt timeout in msec */
#define BTINTEL_DEFAULT_INTR_TIMEOUT_MS 3000
-/* The number of descriptors in TX/RX queues */
-#define BTINTEL_DESCS_COUNT 16
+/* The number of descriptors in TX queues */
+#define BTINTEL_PCIE_TX_DESCS_COUNT 32
+
+/* The number of descriptors in RX queues */
+#define BTINTEL_PCIE_RX_DESCS_COUNT 64
/* Number of Queue for TX and RX
* It indicates the index of the IA(Index Array)
@@ -177,9 +180,6 @@ enum {
/* Doorbell vector for TFD */
#define BTINTEL_PCIE_TX_DB_VEC 0
-/* Number of pending RX requests for downlink */
-#define BTINTEL_PCIE_RX_MAX_QUEUE 6
-
/* Doorbell vector for FRBD */
#define BTINTEL_PCIE_RX_DB_VEC 513
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 5fe5879881f5..3ec0be496820 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2392,10 +2392,17 @@ static int qca_serdev_probe(struct serdev_device *serdev)
*/
qcadev->bt_power->pwrseq = devm_pwrseq_get(&serdev->dev,
"bluetooth");
- if (IS_ERR(qcadev->bt_power->pwrseq))
- return PTR_ERR(qcadev->bt_power->pwrseq);
- break;
+ /*
+ * Some modules have BT_EN enabled via a hardware pull-up,
+ * meaning it is not defined in the DTS and is not controlled
+ * through the power sequence. In such cases, fall through
+ * to follow the legacy flow.
+ */
+ if (IS_ERR(qcadev->bt_power->pwrseq))
+ qcadev->bt_power->pwrseq = NULL;
+ else
+ break;
}
fallthrough;
case QCA_WCN3950:
diff --git a/drivers/cpufreq/rcpufreq_dt.rs b/drivers/cpufreq/rcpufreq_dt.rs
index 94ed81644fe1..43c87d0259b6 100644
--- a/drivers/cpufreq/rcpufreq_dt.rs
+++ b/drivers/cpufreq/rcpufreq_dt.rs
@@ -26,9 +26,9 @@ fn find_supply_name_exact(dev: &Device, name: &str) -> Option<CString> {
}
/// Finds supply name for the CPU from DT.
-fn find_supply_names(dev: &Device, cpu: u32) -> Option<KVec<CString>> {
+fn find_supply_names(dev: &Device, cpu: cpu::CpuId) -> Option<KVec<CString>> {
// Try "cpu0" for older DTs, fallback to "cpu".
- let name = (cpu == 0)
+ let name = (cpu.as_u32() == 0)
.then(|| find_supply_name_exact(dev, "cpu0"))
.flatten()
.or_else(|| find_supply_name_exact(dev, "cpu"))?;
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 890ecac04dac..2bcf9ceca997 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -1118,7 +1118,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
* Catch exporters making buffers inaccessible even when
* attachments preventing that exist.
*/
- WARN_ON_ONCE(ret == EBUSY);
+ WARN_ON_ONCE(ret == -EBUSY);
if (ret)
return ERR_PTR(ret);
}
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
index 7eee3eb47a8e..c9d0c68d2fcb 100644
--- a/drivers/dma-buf/udmabuf.c
+++ b/drivers/dma-buf/udmabuf.c
@@ -264,8 +264,7 @@ static int begin_cpu_udmabuf(struct dma_buf *buf,
ubuf->sg = NULL;
}
} else {
- dma_sync_sg_for_cpu(dev, ubuf->sg->sgl, ubuf->sg->nents,
- direction);
+ dma_sync_sgtable_for_cpu(dev, ubuf->sg, direction);
}
return ret;
@@ -280,7 +279,7 @@ static int end_cpu_udmabuf(struct dma_buf *buf,
if (!ubuf->sg)
return -EINVAL;
- dma_sync_sg_for_device(dev, ubuf->sg->sgl, ubuf->sg->nents, direction);
+ dma_sync_sgtable_for_device(dev, ubuf->sg, direction);
return 0;
}
diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index 58b1482a0fbb..b681c0663203 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -3879,6 +3879,7 @@ static int per_family_init(struct amd64_pvt *pvt)
break;
case 0x70 ... 0x7f:
pvt->ctl_name = "F19h_M70h";
+ pvt->max_mcs = 4;
pvt->flags.zn_regs_v2 = 1;
break;
case 0x90 ... 0x9f:
diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
index 1930dc00c791..1cb5c67e78ae 100644
--- a/drivers/edac/igen6_edac.c
+++ b/drivers/edac/igen6_edac.c
@@ -125,7 +125,7 @@
#define MEM_SLICE_HASH_MASK(v) (GET_BITFIELD(v, 6, 19) << 6)
#define MEM_SLICE_HASH_LSB_MASK_BIT(v) GET_BITFIELD(v, 24, 26)
-static const struct res_config {
+static struct res_config {
bool machine_check;
/* The number of present memory controllers. */
int num_imc;
@@ -479,7 +479,7 @@ static u64 rpl_p_err_addr(u64 ecclog)
return ECC_ERROR_LOG_ADDR45(ecclog);
}
-static const struct res_config ehl_cfg = {
+static struct res_config ehl_cfg = {
.num_imc = 1,
.imc_base = 0x5000,
.ibecc_base = 0xdc00,
@@ -489,7 +489,7 @@ static const struct res_config ehl_cfg = {
.err_addr_to_imc_addr = ehl_err_addr_to_imc_addr,
};
-static const struct res_config icl_cfg = {
+static struct res_config icl_cfg = {
.num_imc = 1,
.imc_base = 0x5000,
.ibecc_base = 0xd800,
@@ -499,7 +499,7 @@ static const struct res_config icl_cfg = {
.err_addr_to_imc_addr = ehl_err_addr_to_imc_addr,
};
-static const struct res_config tgl_cfg = {
+static struct res_config tgl_cfg = {
.machine_check = true,
.num_imc = 2,
.imc_base = 0x5000,
@@ -513,7 +513,7 @@ static const struct res_config tgl_cfg = {
.err_addr_to_imc_addr = tgl_err_addr_to_imc_addr,
};
-static const struct res_config adl_cfg = {
+static struct res_config adl_cfg = {
.machine_check = true,
.num_imc = 2,
.imc_base = 0xd800,
@@ -524,7 +524,7 @@ static const struct res_config adl_cfg = {
.err_addr_to_imc_addr = adl_err_addr_to_imc_addr,
};
-static const struct res_config adl_n_cfg = {
+static struct res_config adl_n_cfg = {
.machine_check = true,
.num_imc = 1,
.imc_base = 0xd800,
@@ -535,7 +535,7 @@ static const struct res_config adl_n_cfg = {
.err_addr_to_imc_addr = adl_err_addr_to_imc_addr,
};
-static const struct res_config rpl_p_cfg = {
+static struct res_config rpl_p_cfg = {
.machine_check = true,
.num_imc = 2,
.imc_base = 0xd800,
@@ -547,7 +547,7 @@ static const struct res_config rpl_p_cfg = {
.err_addr_to_imc_addr = adl_err_addr_to_imc_addr,
};
-static const struct res_config mtl_ps_cfg = {
+static struct res_config mtl_ps_cfg = {
.machine_check = true,
.num_imc = 2,
.imc_base = 0xd800,
@@ -558,7 +558,7 @@ static const struct res_config mtl_ps_cfg = {
.err_addr_to_imc_addr = adl_err_addr_to_imc_addr,
};
-static const struct res_config mtl_p_cfg = {
+static struct res_config mtl_p_cfg = {
.machine_check = true,
.num_imc = 2,
.imc_base = 0xd800,
@@ -569,7 +569,7 @@ static const struct res_config mtl_p_cfg = {
.err_addr_to_imc_addr = adl_err_addr_to_imc_addr,
};
-static const struct pci_device_id igen6_pci_tbl[] = {
+static struct pci_device_id igen6_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, DID_EHL_SKU5), (kernel_ulong_t)&ehl_cfg },
{ PCI_VDEVICE(INTEL, DID_EHL_SKU6), (kernel_ulong_t)&ehl_cfg },
{ PCI_VDEVICE(INTEL, DID_EHL_SKU7), (kernel_ulong_t)&ehl_cfg },
@@ -1350,9 +1350,11 @@ static int igen6_register_mcis(struct pci_dev *pdev, u64 mchbar)
return -ENODEV;
}
- if (lmc < res_cfg->num_imc)
+ if (lmc < res_cfg->num_imc) {
igen6_printk(KERN_WARNING, "Expected %d mcs, but only %d detected.",
res_cfg->num_imc, lmc);
+ res_cfg->num_imc = lmc;
+ }
return 0;
diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c
index 26227669f026..70a01c5b8ad1 100644
--- a/drivers/gpio/gpio-loongson-64bit.c
+++ b/drivers/gpio/gpio-loongson-64bit.c
@@ -268,7 +268,7 @@ static const struct loongson_gpio_chip_data loongson_gpio_ls7a2000_data0 = {
/* LS7A2000 ACPI GPIO */
static const struct loongson_gpio_chip_data loongson_gpio_ls7a2000_data1 = {
.label = "ls7a2000_gpio",
- .mode = BYTE_CTRL_MODE,
+ .mode = BIT_CTRL_MODE,
.conf_offset = 0x4,
.in_offset = 0x8,
.out_offset = 0x0,
diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
index 10ea71273c89..9875e34bde72 100644
--- a/drivers/gpio/gpio-mlxbf3.c
+++ b/drivers/gpio/gpio-mlxbf3.c
@@ -190,7 +190,9 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
struct mlxbf3_gpio_context *gs;
struct gpio_irq_chip *girq;
struct gpio_chip *gc;
+ char *colon_ptr;
int ret, irq;
+ long num;
gs = devm_kzalloc(dev, sizeof(*gs), GFP_KERNEL);
if (!gs)
@@ -227,25 +229,39 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
gc->owner = THIS_MODULE;
gc->add_pin_ranges = mlxbf3_gpio_add_pin_ranges;
- irq = platform_get_irq(pdev, 0);
- if (irq >= 0) {
- girq = &gs->gc.irq;
- gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip);
- girq->default_type = IRQ_TYPE_NONE;
- /* This will let us handle the parent IRQ in the driver */
- girq->num_parents = 0;
- girq->parents = NULL;
- girq->parent_handler = NULL;
- girq->handler = handle_bad_irq;
-
- /*
- * Directly request the irq here instead of passing
- * a flow-handler because the irq is shared.
- */
- ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler,
- IRQF_SHARED, dev_name(dev), gs);
- if (ret)
- return dev_err_probe(dev, ret, "failed to request IRQ");
+ colon_ptr = strchr(dev_name(dev), ':');
+ if (!colon_ptr) {
+ dev_err(dev, "invalid device name format\n");
+ return -EINVAL;
+ }
+
+ ret = kstrtol(++colon_ptr, 16, &num);
+ if (ret) {
+ dev_err(dev, "invalid device instance\n");
+ return ret;
+ }
+
+ if (!num) {
+ irq = platform_get_irq(pdev, 0);
+ if (irq >= 0) {
+ girq = &gs->gc.irq;
+ gpio_irq_chip_set_chip(girq, &gpio_mlxbf3_irqchip);
+ girq->default_type = IRQ_TYPE_NONE;
+ /* This will let us handle the parent IRQ in the driver */
+ girq->num_parents = 0;
+ girq->parents = NULL;
+ girq->parent_handler = NULL;
+ girq->handler = handle_bad_irq;
+
+ /*
+ * Directly request the irq here instead of passing
+ * a flow-handler because the irq is shared.
+ */
+ ret = devm_request_irq(dev, irq, mlxbf3_gpio_irq_handler,
+ IRQF_SHARED, dev_name(dev), gs);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to request IRQ");
+ }
}
platform_set_drvdata(pdev, gs);
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index b852e4997629..e80a96f39788 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -974,7 +974,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip, int irq_base)
IRQF_ONESHOT | IRQF_SHARED, dev_name(dev),
chip);
if (ret)
- return dev_err_probe(dev, client->irq, "failed to request irq\n");
+ return dev_err_probe(dev, ret, "failed to request irq\n");
return 0;
}
diff --git a/drivers/gpio/gpio-spacemit-k1.c b/drivers/gpio/gpio-spacemit-k1.c
index f027066365ff..3cc75c701ec4 100644
--- a/drivers/gpio/gpio-spacemit-k1.c
+++ b/drivers/gpio/gpio-spacemit-k1.c
@@ -278,6 +278,7 @@ static const struct of_device_id spacemit_gpio_dt_ids[] = {
{ .compatible = "spacemit,k1-gpio" },
{ /* sentinel */ }
};
+MODULE_DEVICE_TABLE(of, spacemit_gpio_dt_ids);
static struct platform_driver spacemit_gpio_driver = {
.probe = spacemit_gpio_probe,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 8e626f50b362..f81608330a3d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -1902,7 +1902,7 @@ no_preempt:
continue;
}
job = to_amdgpu_job(s_job);
- if (preempted && (&job->hw_fence) == fence)
+ if (preempted && (&job->hw_fence.base) == fence)
/* mark the job as preempted */
job->preemption_status |= AMDGPU_IB_PREEMPTED;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e1bab6a96cb6..78f8755996f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -6019,16 +6019,12 @@ static int amdgpu_device_health_check(struct list_head *device_list_handle)
return ret;
}
-static int amdgpu_device_halt_activities(struct amdgpu_device *adev,
- struct amdgpu_job *job,
- struct amdgpu_reset_context *reset_context,
- struct list_head *device_list,
- struct amdgpu_hive_info *hive,
- bool need_emergency_restart)
+static int amdgpu_device_recovery_prepare(struct amdgpu_device *adev,
+ struct list_head *device_list,
+ struct amdgpu_hive_info *hive)
{
- struct list_head *device_list_handle = NULL;
struct amdgpu_device *tmp_adev = NULL;
- int i, r = 0;
+ int r;
/*
* Build list of devices to reset.
@@ -6045,26 +6041,54 @@ static int amdgpu_device_halt_activities(struct amdgpu_device *adev,
}
if (!list_is_first(&adev->reset_list, device_list))
list_rotate_to_front(&adev->reset_list, device_list);
- device_list_handle = device_list;
} else {
list_add_tail(&adev->reset_list, device_list);
- device_list_handle = device_list;
}
if (!amdgpu_sriov_vf(adev) && (!adev->pcie_reset_ctx.occurs_dpc)) {
- r = amdgpu_device_health_check(device_list_handle);
+ r = amdgpu_device_health_check(device_list);
if (r)
return r;
}
- /* We need to lock reset domain only once both for XGMI and single device */
- tmp_adev = list_first_entry(device_list_handle, struct amdgpu_device,
- reset_list);
+ return 0;
+}
+
+static void amdgpu_device_recovery_get_reset_lock(struct amdgpu_device *adev,
+ struct list_head *device_list)
+{
+ struct amdgpu_device *tmp_adev = NULL;
+
+ if (list_empty(device_list))
+ return;
+ tmp_adev =
+ list_first_entry(device_list, struct amdgpu_device, reset_list);
amdgpu_device_lock_reset_domain(tmp_adev->reset_domain);
+}
- /* block all schedulers and reset given job's ring */
- list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
+static void amdgpu_device_recovery_put_reset_lock(struct amdgpu_device *adev,
+ struct list_head *device_list)
+{
+ struct amdgpu_device *tmp_adev = NULL;
+ if (list_empty(device_list))
+ return;
+ tmp_adev =
+ list_first_entry(device_list, struct amdgpu_device, reset_list);
+ amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
+}
+
+static int amdgpu_device_halt_activities(
+ struct amdgpu_device *adev, struct amdgpu_job *job,
+ struct amdgpu_reset_context *reset_context,
+ struct list_head *device_list, struct amdgpu_hive_info *hive,
+ bool need_emergency_restart)
+{
+ struct amdgpu_device *tmp_adev = NULL;
+ int i, r = 0;
+
+ /* block all schedulers and reset given job's ring */
+ list_for_each_entry(tmp_adev, device_list, reset_list) {
amdgpu_device_set_mp1_state(tmp_adev);
/*
@@ -6252,11 +6276,6 @@ static void amdgpu_device_gpu_resume(struct amdgpu_device *adev,
amdgpu_ras_set_error_query_ready(tmp_adev, true);
}
-
- tmp_adev = list_first_entry(device_list, struct amdgpu_device,
- reset_list);
- amdgpu_device_unlock_reset_domain(tmp_adev->reset_domain);
-
}
@@ -6324,10 +6343,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
reset_context->hive = hive;
INIT_LIST_HEAD(&device_list);
+ if (amdgpu_device_recovery_prepare(adev, &device_list, hive))
+ goto end_reset;
+
+ /* We need to lock reset domain only once both for XGMI and single device */
+ amdgpu_device_recovery_get_reset_lock(adev, &device_list);
+
r = amdgpu_device_halt_activities(adev, job, reset_context, &device_list,
hive, need_emergency_restart);
if (r)
- goto end_reset;
+ goto reset_unlock;
if (need_emergency_restart)
goto skip_sched_resume;
@@ -6337,7 +6362,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
*
* job->base holds a reference to parent fence
*/
- if (job && dma_fence_is_signaled(&job->hw_fence)) {
+ if (job && dma_fence_is_signaled(&job->hw_fence.base)) {
job_signaled = true;
dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
goto skip_hw_reset;
@@ -6345,13 +6370,15 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
r = amdgpu_device_asic_reset(adev, &device_list, reset_context);
if (r)
- goto end_reset;
+ goto reset_unlock;
skip_hw_reset:
r = amdgpu_device_sched_resume(&device_list, reset_context, job_signaled);
if (r)
- goto end_reset;
+ goto reset_unlock;
skip_sched_resume:
amdgpu_device_gpu_resume(adev, &device_list, need_emergency_restart);
+reset_unlock:
+ amdgpu_device_recovery_put_reset_lock(adev, &device_list);
end_reset:
if (hive) {
mutex_unlock(&hive->hive_lock);
@@ -6763,6 +6790,8 @@ pci_ers_result_t amdgpu_pci_error_detected(struct pci_dev *pdev, pci_channel_sta
memset(&reset_context, 0, sizeof(reset_context));
INIT_LIST_HEAD(&device_list);
+ amdgpu_device_recovery_prepare(adev, &device_list, hive);
+ amdgpu_device_recovery_get_reset_lock(adev, &device_list);
r = amdgpu_device_halt_activities(adev, NULL, &reset_context, &device_list,
hive, false);
if (hive) {
@@ -6880,8 +6909,8 @@ out:
if (hive) {
list_for_each_entry(tmp_adev, &device_list, reset_list)
amdgpu_device_unset_mp1_state(tmp_adev);
- amdgpu_device_unlock_reset_domain(adev->reset_domain);
}
+ amdgpu_device_recovery_put_reset_lock(adev, &device_list);
}
if (hive) {
@@ -6927,6 +6956,7 @@ void amdgpu_pci_resume(struct pci_dev *pdev)
amdgpu_device_sched_resume(&device_list, NULL, NULL);
amdgpu_device_gpu_resume(adev, &device_list, false);
+ amdgpu_device_recovery_put_reset_lock(adev, &device_list);
adev->pcie_reset_ctx.occurs_dpc = false;
if (hive) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 8cecf25996ed..5fec808d7f54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -41,22 +41,6 @@
#include "amdgpu_trace.h"
#include "amdgpu_reset.h"
-/*
- * Fences mark an event in the GPUs pipeline and are used
- * for GPU/CPU synchronization. When the fence is written,
- * it is expected that all buffers associated with that fence
- * are no longer in use by the associated ring on the GPU and
- * that the relevant GPU caches have been flushed.
- */
-
-struct amdgpu_fence {
- struct dma_fence base;
-
- /* RB, DMA, etc. */
- struct amdgpu_ring *ring;
- ktime_t start_timestamp;
-};
-
static struct kmem_cache *amdgpu_fence_slab;
int amdgpu_fence_slab_init(void)
@@ -151,12 +135,12 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
am_fence = kmem_cache_alloc(amdgpu_fence_slab, GFP_ATOMIC);
if (am_fence == NULL)
return -ENOMEM;
- fence = &am_fence->base;
- am_fence->ring = ring;
} else {
/* take use of job-embedded fence */
- fence = &job->hw_fence;
+ am_fence = &job->hw_fence;
}
+ fence = &am_fence->base;
+ am_fence->ring = ring;
seq = ++ring->fence_drv.sync_seq;
if (job && job->job_run_counter) {
@@ -718,7 +702,7 @@ void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
* it right here or we won't be able to track them in fence_drv
* and they will remain unsignaled during sa_bo free.
*/
- job = container_of(old, struct amdgpu_job, hw_fence);
+ job = container_of(old, struct amdgpu_job, hw_fence.base);
if (!job->base.s_fence && !dma_fence_is_signaled(old))
dma_fence_signal(old);
RCU_INIT_POINTER(*ptr, NULL);
@@ -780,7 +764,7 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
{
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+ struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
return (const char *)to_amdgpu_ring(job->base.sched)->name;
}
@@ -810,7 +794,7 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
*/
static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
{
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+ struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
@@ -845,7 +829,7 @@ static void amdgpu_job_fence_free(struct rcu_head *rcu)
struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
/* free job if fence has a parent job */
- kfree(container_of(f, struct amdgpu_job, hw_fence));
+ kfree(container_of(f, struct amdgpu_job, hw_fence.base));
}
/**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index acb21fc8b3ce..ddb9d3269357 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -272,8 +272,8 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
/* Check if any fences where initialized */
if (job->base.s_fence && job->base.s_fence->finished.ops)
f = &job->base.s_fence->finished;
- else if (job->hw_fence.ops)
- f = &job->hw_fence;
+ else if (job->hw_fence.base.ops)
+ f = &job->hw_fence.base;
else
f = NULL;
@@ -290,10 +290,10 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
amdgpu_sync_free(&job->explicit_sync);
/* only put the hw fence if has embedded fence */
- if (!job->hw_fence.ops)
+ if (!job->hw_fence.base.ops)
kfree(job);
else
- dma_fence_put(&job->hw_fence);
+ dma_fence_put(&job->hw_fence.base);
}
void amdgpu_job_set_gang_leader(struct amdgpu_job *job,
@@ -322,10 +322,10 @@ void amdgpu_job_free(struct amdgpu_job *job)
if (job->gang_submit != &job->base.s_fence->scheduled)
dma_fence_put(job->gang_submit);
- if (!job->hw_fence.ops)
+ if (!job->hw_fence.base.ops)
kfree(job);
else
- dma_fence_put(&job->hw_fence);
+ dma_fence_put(&job->hw_fence.base);
}
struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index f2c049129661..931fed8892cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -48,7 +48,7 @@ struct amdgpu_job {
struct drm_sched_job base;
struct amdgpu_vm *vm;
struct amdgpu_sync explicit_sync;
- struct dma_fence hw_fence;
+ struct amdgpu_fence hw_fence;
struct dma_fence *gang_submit;
uint32_t preamble_status;
uint32_t preemption_status;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index e6f0b035e20b..c14f63cefe67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -3522,8 +3522,12 @@ int psp_init_sos_microcode(struct psp_context *psp, const char *chip_name)
uint8_t *ucode_array_start_addr;
int err = 0;
- err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
- "amdgpu/%s_sos.bin", chip_name);
+ if (amdgpu_is_kicker_fw(adev))
+ err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_sos_kicker.bin", chip_name);
+ else
+ err = amdgpu_ucode_request(adev, &adev->psp.sos_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_sos.bin", chip_name);
if (err)
goto out;
@@ -3799,8 +3803,12 @@ int psp_init_ta_microcode(struct psp_context *psp, const char *chip_name)
struct amdgpu_device *adev = psp->adev;
int err;
- err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
- "amdgpu/%s_ta.bin", chip_name);
+ if (amdgpu_is_kicker_fw(adev))
+ err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_ta_kicker.bin", chip_name);
+ else
+ err = amdgpu_ucode_request(adev, &adev->psp.ta_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_ta.bin", chip_name);
if (err)
return err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index b95b47110769..e1f25218943a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -127,6 +127,22 @@ struct amdgpu_fence_driver {
struct dma_fence **fences;
};
+/*
+ * Fences mark an event in the GPUs pipeline and are used
+ * for GPU/CPU synchronization. When the fence is written,
+ * it is expected that all buffers associated with that fence
+ * are no longer in use by the associated ring on the GPU and
+ * that the relevant GPU caches have been flushed.
+ */
+
+struct amdgpu_fence {
+ struct dma_fence base;
+
+ /* RB, DMA, etc. */
+ struct amdgpu_ring *ring;
+ ktime_t start_timestamp;
+};
+
extern const struct drm_sched_backend_ops amdgpu_sched_ops;
void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 6716ac281c49..9b54a1ece447 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -540,8 +540,10 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
case IP_VERSION(4, 4, 2):
case IP_VERSION(4, 4, 4):
case IP_VERSION(4, 4, 5):
- /* For SDMA 4.x, use the existing DPM interface for backward compatibility */
- r = amdgpu_dpm_reset_sdma(adev, 1 << instance_id);
+ /* For SDMA 4.x, use the existing DPM interface for backward compatibility,
+ * we need to convert the logical instance ID to physical instance ID before reset.
+ */
+ r = amdgpu_dpm_reset_sdma(adev, 1 << GET_INST(SDMA0, instance_id));
break;
case IP_VERSION(5, 0, 0):
case IP_VERSION(5, 0, 1):
@@ -568,7 +570,7 @@ static int amdgpu_sdma_soft_reset(struct amdgpu_device *adev, u32 instance_id)
/**
* amdgpu_sdma_reset_engine - Reset a specific SDMA engine
* @adev: Pointer to the AMDGPU device
- * @instance_id: ID of the SDMA engine instance to reset
+ * @instance_id: Logical ID of the SDMA engine instance to reset
*
* Returns: 0 on success, or a negative error code on failure.
*/
@@ -601,7 +603,7 @@ int amdgpu_sdma_reset_engine(struct amdgpu_device *adev, uint32_t instance_id)
/* Perform the SDMA reset for the specified instance */
ret = amdgpu_sdma_soft_reset(adev, instance_id);
if (ret) {
- dev_err(adev->dev, "Failed to reset SDMA instance %u\n", instance_id);
+ dev_err(adev->dev, "Failed to reset SDMA logical instance %u\n", instance_id);
goto exit;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 2505c46a9c3d..eaddc441c51a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -30,6 +30,10 @@
#define AMDGPU_UCODE_NAME_MAX (128)
+static const struct kicker_device kicker_device_list[] = {
+ {0x744B, 0x00},
+};
+
static void amdgpu_ucode_print_common_hdr(const struct common_firmware_header *hdr)
{
DRM_DEBUG("size_bytes: %u\n", le32_to_cpu(hdr->size_bytes));
@@ -1387,6 +1391,19 @@ static const char *amdgpu_ucode_legacy_naming(struct amdgpu_device *adev, int bl
return NULL;
}
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(kicker_device_list); i++) {
+ if (adev->pdev->device == kicker_device_list[i].device &&
+ adev->pdev->revision == kicker_device_list[i].revision)
+ return true;
+ }
+
+ return false;
+}
+
void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len)
{
int maj, min, rev;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 9e89c3487be5..6349aad6da35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -605,6 +605,11 @@ struct amdgpu_firmware {
uint32_t pldm_version;
};
+struct kicker_device{
+ unsigned short device;
+ u8 revision;
+};
+
void amdgpu_ucode_print_mc_hdr(const struct common_firmware_header *hdr);
void amdgpu_ucode_print_smc_hdr(const struct common_firmware_header *hdr);
void amdgpu_ucode_print_imu_hdr(const struct common_firmware_header *hdr);
@@ -632,5 +637,6 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type);
const char *amdgpu_ucode_name(enum AMDGPU_UCODE_ID ucode_id);
void amdgpu_ucode_ip_version_decode(struct amdgpu_device *adev, int block_type, char *ucode_prefix, int len);
+bool amdgpu_is_kicker_fw(struct amdgpu_device *adev);
#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index afd6d59164bf..ec9b84f92d46 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -85,6 +85,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_0_pfp.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_0_me.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_0_mec.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_kicker.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_0_rlc_1.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_0_toc.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_1_pfp.bin");
@@ -759,6 +760,10 @@ static int gfx_v11_0_init_microcode(struct amdgpu_device *adev)
err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
AMDGPU_UCODE_REQUIRED,
"amdgpu/gc_11_0_0_rlc_1.bin");
+ else if (amdgpu_is_kicker_fw(adev))
+ err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
+ AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_rlc_kicker.bin", ucode_prefix);
else
err = amdgpu_ucode_request(adev, &adev->gfx.rlc_fw,
AMDGPU_UCODE_REQUIRED,
diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
index cfa91d709d49..cc626036ed9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c
@@ -32,6 +32,7 @@
#include "gc/gc_11_0_0_sh_mask.h"
MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu.bin");
+MODULE_FIRMWARE("amdgpu/gc_11_0_0_imu_kicker.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_1_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_2_imu.bin");
MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin");
@@ -51,8 +52,12 @@ static int imu_v11_0_init_microcode(struct amdgpu_device *adev)
DRM_DEBUG("\n");
amdgpu_ucode_ip_version_decode(adev, GC_HWIP, ucode_prefix, sizeof(ucode_prefix));
- err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
- "amdgpu/%s_imu.bin", ucode_prefix);
+ if (amdgpu_is_kicker_fw(adev))
+ err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_imu_kicker.bin", ucode_prefix);
+ else
+ err = amdgpu_ucode_request(adev, &adev->gfx.imu_fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_imu.bin", ucode_prefix);
if (err)
goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
index df612fd9cc50..ead616c11705 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c
@@ -42,7 +42,9 @@ MODULE_FIRMWARE("amdgpu/psp_13_0_5_ta.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_8_toc.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_8_ta.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_sos_kicker.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta.bin");
+MODULE_FIRMWARE("amdgpu/psp_13_0_0_ta_kicker.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_7_sos.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_7_ta.bin");
MODULE_FIRMWARE("amdgpu/psp_13_0_10_sos.bin");
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 9c169112a5e7..cef68df4c663 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -490,7 +490,7 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
{
struct amdgpu_ring *sdma[AMDGPU_MAX_SDMA_INSTANCES];
u32 doorbell_offset, doorbell;
- u32 rb_cntl, ib_cntl;
+ u32 rb_cntl, ib_cntl, sdma_cntl;
int i;
for_each_inst(i, inst_mask) {
@@ -502,6 +502,9 @@ static void sdma_v4_4_2_inst_gfx_stop(struct amdgpu_device *adev,
ib_cntl = RREG32_SDMA(i, regSDMA_GFX_IB_CNTL);
ib_cntl = REG_SET_FIELD(ib_cntl, SDMA_GFX_IB_CNTL, IB_ENABLE, 0);
WREG32_SDMA(i, regSDMA_GFX_IB_CNTL, ib_cntl);
+ sdma_cntl = RREG32_SDMA(i, regSDMA_CNTL);
+ sdma_cntl = REG_SET_FIELD(sdma_cntl, SDMA_CNTL, UTC_L1_ENABLE, 0);
+ WREG32_SDMA(i, regSDMA_CNTL, sdma_cntl);
if (sdma[i]->use_doorbell) {
doorbell = RREG32_SDMA(i, regSDMA_GFX_DOORBELL);
@@ -995,6 +998,7 @@ static int sdma_v4_4_2_inst_start(struct amdgpu_device *adev,
/* set utc l1 enable flag always to 1 */
temp = RREG32_SDMA(i, regSDMA_CNTL);
temp = REG_SET_FIELD(temp, SDMA_CNTL, UTC_L1_ENABLE, 1);
+ WREG32_SDMA(i, regSDMA_CNTL, temp);
if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) < IP_VERSION(4, 4, 5)) {
/* enable context empty interrupt during initialization */
@@ -1670,7 +1674,7 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
{
struct amdgpu_device *adev = ring->adev;
- u32 id = GET_INST(SDMA0, ring->me);
+ u32 id = ring->me;
int r;
if (!(adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
@@ -1686,7 +1690,7 @@ static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v4_4_2_stop_queue(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
- u32 instance_id = GET_INST(SDMA0, ring->me);
+ u32 instance_id = ring->me;
u32 inst_mask;
uint64_t rptr;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index 9505ae96fbec..1813c3ed0aa6 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -1399,6 +1399,7 @@ static int sdma_v5_0_sw_init(struct amdgpu_ip_block *ip_block)
return r;
for (i = 0; i < adev->sdma.num_instances; i++) {
+ mutex_init(&adev->sdma.instance[i].engine_reset_mutex);
adev->sdma.instance[i].funcs = &sdma_v5_0_sdma_funcs;
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
index a6e612b4a892..23f97da62808 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
@@ -1318,6 +1318,7 @@ static int sdma_v5_2_sw_init(struct amdgpu_ip_block *ip_block)
}
for (i = 0; i < adev->sdma.num_instances; i++) {
+ mutex_init(&adev->sdma.instance[i].engine_reset_mutex);
adev->sdma.instance[i].funcs = &sdma_v5_2_sdma_funcs;
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
index 338cf43c45fe..cdefd7fcb0da 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_1.c
@@ -669,6 +669,9 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
if (indirect)
amdgpu_vcn_psp_update_sram(adev, inst_idx, AMDGPU_UCODE_ID_VCN0_RAM);
+ /* resetting ring, fw should not check RB ring */
+ fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+
/* Pause dpg */
vcn_v5_0_1_pause_dpg_mode(vinst, &state);
@@ -681,7 +684,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
tmp &= ~(VCN_RB_ENABLE__RB1_EN_MASK);
WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
- fw_shared->sq.queue_mode |= FW_QUEUE_RING_RESET;
+
WREG32_SOC15(VCN, vcn_inst, regUVD_RB_RPTR, 0);
WREG32_SOC15(VCN, vcn_inst, regUVD_RB_WPTR, 0);
@@ -692,6 +695,7 @@ static int vcn_v5_0_1_start_dpg_mode(struct amdgpu_vcn_inst *vinst,
tmp = RREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE);
tmp |= VCN_RB_ENABLE__RB1_EN_MASK;
WREG32_SOC15(VCN, vcn_inst, regVCN_RB_ENABLE, tmp);
+ /* resetting done, fw can check RB ring */
fw_shared->sq.queue_mode &= ~(FW_QUEUE_RING_RESET | FW_QUEUE_DPG_HOLD_OFF);
WREG32_SOC15(VCN, vcn_inst, regVCN_RB1_DB_CTRL,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 8fa6489b6f5d..505036968a77 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -240,7 +240,7 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
packet->bitfields2.engine_sel =
engine_sel__mes_map_queues__compute_vi;
- packet->bitfields2.gws_control_queue = q->gws ? 1 : 0;
+ packet->bitfields2.gws_control_queue = q->properties.is_gws ? 1 : 0;
packet->bitfields2.extended_engine_sel =
extended_engine_sel__mes_map_queues__legacy_engine_sel;
packet->bitfields2.queue_type =
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index baa2374acdeb..4ec73f33535e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -510,6 +510,10 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
dev->node_props.capability |=
HSA_CAP_AQL_QUEUE_DOUBLE_MAP;
+ if (KFD_GC_VERSION(dev->gpu) < IP_VERSION(10, 0, 0) &&
+ (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE))
+ dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
+
sysfs_show_32bit_prop(buffer, offs, "max_engine_clk_fcompute",
dev->node_props.max_engine_clk_fcompute);
@@ -2008,8 +2012,6 @@ static void kfd_topology_set_capabilities(struct kfd_topology_device *dev)
if (!amdgpu_sriov_vf(dev->gpu->adev))
dev->node_props.capability |= HSA_CAP_PER_QUEUE_RESET_SUPPORTED;
- if (dev->gpu->adev->sdma.supported_reset & AMDGPU_RESET_TYPE_PER_QUEUE)
- dev->node_props.capability2 |= HSA_CAP2_PER_SDMA_QUEUE_RESET_SUPPORTED;
} else {
dev->node_props.debug_prop |= HSA_DBG_WATCH_ADDR_MASK_LO_BIT_GFX10 |
HSA_DBG_WATCH_ADDR_MASK_HI_BIT;
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 d3100f641ac6..bc4cd11bfc79 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4718,9 +4718,23 @@ static int get_brightness_range(const struct amdgpu_dm_backlight_caps *caps,
return 1;
}
+/* Rescale from [min..max] to [0..AMDGPU_MAX_BL_LEVEL] */
+static inline u32 scale_input_to_fw(int min, int max, u64 input)
+{
+ return DIV_ROUND_CLOSEST_ULL(input * AMDGPU_MAX_BL_LEVEL, max - min);
+}
+
+/* Rescale from [0..AMDGPU_MAX_BL_LEVEL] to [min..max] */
+static inline u32 scale_fw_to_input(int min, int max, u64 input)
+{
+ return min + DIV_ROUND_CLOSEST_ULL(input * (max - min), AMDGPU_MAX_BL_LEVEL);
+}
+
static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *caps,
- uint32_t *brightness)
+ unsigned int min, unsigned int max,
+ uint32_t *user_brightness)
{
+ u32 brightness = scale_input_to_fw(min, max, *user_brightness);
u8 prev_signal = 0, prev_lum = 0;
int i = 0;
@@ -4731,7 +4745,7 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
return;
/* choose start to run less interpolation steps */
- if (caps->luminance_data[caps->data_points/2].input_signal > *brightness)
+ if (caps->luminance_data[caps->data_points/2].input_signal > brightness)
i = caps->data_points/2;
do {
u8 signal = caps->luminance_data[i].input_signal;
@@ -4742,17 +4756,18 @@ static void convert_custom_brightness(const struct amdgpu_dm_backlight_caps *cap
* brightness < signal: interpolate between previous and current luminance numerator
* brightness > signal: find next data point
*/
- if (*brightness > signal) {
+ if (brightness > signal) {
prev_signal = signal;
prev_lum = lum;
i++;
continue;
}
- if (*brightness < signal)
+ if (brightness < signal)
lum = prev_lum + DIV_ROUND_CLOSEST((lum - prev_lum) *
- (*brightness - prev_signal),
+ (brightness - prev_signal),
signal - prev_signal);
- *brightness = DIV_ROUND_CLOSEST(lum * *brightness, 101);
+ *user_brightness = scale_fw_to_input(min, max,
+ DIV_ROUND_CLOSEST(lum * brightness, 101));
return;
} while (i < caps->data_points);
}
@@ -4765,11 +4780,10 @@ static u32 convert_brightness_from_user(const struct amdgpu_dm_backlight_caps *c
if (!get_brightness_range(caps, &min, &max))
return brightness;
- convert_custom_brightness(caps, &brightness);
+ convert_custom_brightness(caps, min, max, &brightness);
- // Rescale 0..255 to min..max
- return min + DIV_ROUND_CLOSEST((max - min) * brightness,
- AMDGPU_MAX_BL_LEVEL);
+ // Rescale 0..max to min..max
+ return min + DIV_ROUND_CLOSEST_ULL((u64)(max - min) * brightness, max);
}
static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *caps,
@@ -4782,8 +4796,8 @@ static u32 convert_brightness_to_user(const struct amdgpu_dm_backlight_caps *cap
if (brightness < min)
return 0;
- // Rescale min..max to 0..255
- return DIV_ROUND_CLOSEST(AMDGPU_MAX_BL_LEVEL * (brightness - min),
+ // Rescale min..max to 0..max
+ return DIV_ROUND_CLOSEST_ULL((u64)max * (brightness - min),
max - min);
}
@@ -4908,7 +4922,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
struct drm_device *drm = aconnector->base.dev;
struct amdgpu_display_manager *dm = &drm_to_adev(drm)->dm;
struct backlight_properties props = { 0 };
- struct amdgpu_dm_backlight_caps caps = { 0 };
+ struct amdgpu_dm_backlight_caps *caps;
char bl_name[16];
int min, max;
@@ -4922,22 +4936,21 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
return;
}
- amdgpu_acpi_get_backlight_caps(&caps);
- if (caps.caps_valid && get_brightness_range(&caps, &min, &max)) {
+ caps = &dm->backlight_caps[aconnector->bl_idx];
+ if (get_brightness_range(caps, &min, &max)) {
if (power_supply_is_system_supplied() > 0)
- props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.ac_level, 100);
+ props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->ac_level, 100);
else
- props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps.dc_level, 100);
+ props.brightness = (max - min) * DIV_ROUND_CLOSEST(caps->dc_level, 100);
/* min is zero, so max needs to be adjusted */
props.max_brightness = max - min;
drm_dbg(drm, "Backlight caps: min: %d, max: %d, ac %d, dc %d\n", min, max,
- caps.ac_level, caps.dc_level);
+ caps->ac_level, caps->dc_level);
} else
- props.brightness = AMDGPU_MAX_BL_LEVEL;
+ props.brightness = props.max_brightness = AMDGPU_MAX_BL_LEVEL;
- if (caps.data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
+ if (caps->data_points && !(amdgpu_dc_debug_mask & DC_DISABLE_CUSTOM_BRIGHTNESS_CURVE))
drm_info(drm, "Using custom brightness curve\n");
- props.max_brightness = AMDGPU_MAX_BL_LEVEL;
props.type = BACKLIGHT_RAW;
snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 56d011a1323c..b34b5b52236d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -241,6 +241,7 @@ static bool create_links(
DC_LOG_DC("BIOS object table - end");
/* Create a link for each usb4 dpia port */
+ dc->lowest_dpia_link_index = MAX_LINKS;
for (i = 0; i < dc->res_pool->usb4_dpia_count; i++) {
struct link_init_data link_init_params = {0};
struct dc_link *link;
@@ -253,6 +254,9 @@ static bool create_links(
link = dc->link_srv->create_link(&link_init_params);
if (link) {
+ if (dc->lowest_dpia_link_index > dc->link_count)
+ dc->lowest_dpia_link_index = dc->link_count;
+
dc->links[dc->link_count] = link;
link->dc = dc;
++dc->link_count;
@@ -6376,6 +6380,35 @@ unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context)
else
return 0;
}
+/**
+ ***********************************************************************************************
+ * dc_get_host_router_index: Get index of host router from a dpia link
+ *
+ * This function return a host router index of the target link. If the target link is dpia link.
+ *
+ * @param [in] link: target link
+ * @param [out] host_router_index: host router index of the target link
+ *
+ * @return: true if the host router index is found and valid.
+ *
+ ***********************************************************************************************
+ */
+bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index)
+{
+ struct dc *dc = link->ctx->dc;
+
+ if (link->ep_type != DISPLAY_ENDPOINT_USB4_DPIA)
+ return false;
+
+ if (link->link_index < dc->lowest_dpia_link_index)
+ return false;
+
+ *host_router_index = (link->link_index - dc->lowest_dpia_link_index) / dc->caps.num_of_dpias_per_host_router;
+ if (*host_router_index < dc->caps.num_of_host_routers)
+ return true;
+ else
+ return false;
+}
bool dc_is_cursor_limit_pending(struct dc *dc)
{
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1d917be36fc4..f41073c0147e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -66,7 +66,8 @@ struct dmub_notification;
#define MAX_STREAMS 6
#define MIN_VIEWPORT_SIZE 12
#define MAX_NUM_EDP 2
-#define MAX_HOST_ROUTERS_NUM 2
+#define MAX_HOST_ROUTERS_NUM 3
+#define MAX_DPIA_PER_HOST_ROUTER 2
/* Display Core Interfaces */
struct dc_versions {
@@ -305,6 +306,8 @@ struct dc_caps {
/* Conservative limit for DCC cases which require ODM4:1 to support*/
uint32_t dcc_plane_width_limit;
struct dc_scl_caps scl_caps;
+ uint8_t num_of_host_routers;
+ uint8_t num_of_dpias_per_host_router;
};
struct dc_bug_wa {
@@ -1603,6 +1606,7 @@ struct dc {
uint8_t link_count;
struct dc_link *links[MAX_LINKS];
+ uint8_t lowest_dpia_link_index;
struct link_service *link_srv;
struct dc_state *current_state;
@@ -2595,6 +2599,8 @@ struct dc_power_profile dc_get_power_profile_for_dc_state(const struct dc_state
unsigned int dc_get_det_buffer_size_from_state(const struct dc_state *context);
+bool dc_get_host_router_index(const struct dc_link *link, unsigned int *host_router_index);
+
/* DSC Interfaces */
#include "dc_dsc.h"
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 0bad8304ccf6..d346f8ae1634 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -1172,8 +1172,8 @@ struct dc_lttpr_caps {
union dp_128b_132b_supported_lttpr_link_rates supported_128b_132b_rates;
union dp_alpm_lttpr_cap alpm;
uint8_t aux_rd_interval[MAX_REPEATER_CNT - 1];
- uint8_t lttpr_ieee_oui[3];
- uint8_t lttpr_device_id[6];
+ uint8_t lttpr_ieee_oui[3]; // Always read from closest LTTPR to host
+ uint8_t lttpr_device_id[6]; // Always read from closest LTTPR to host
};
struct dc_dongle_dfp_cap_ext {
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
index d47cacfdb695..2aa6d44bb359 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/dml21_translation_helper.c
@@ -788,6 +788,7 @@ static void populate_dml21_plane_config_from_plane_state(struct dml2_context *dm
plane->pixel_format = dml2_420_10;
break;
case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+ case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
plane->pixel_format = dml2_444_64;
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
index c4dad7164d31..5b62cd19d979 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_core/dml2_core_dcn4_calcs.c
@@ -4685,7 +4685,10 @@ static void calculate_tdlut_setting(
//the tdlut is fetched during the 2 row times of prefetch.
if (p->setup_for_tdlut) {
*p->tdlut_groups_per_2row_ub = (unsigned int)math_ceil2((double) *p->tdlut_bytes_per_frame / *p->tdlut_bytes_per_group, 1);
- *p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+ if (*p->tdlut_bytes_per_frame > p->cursor_buffer_size * 1024)
+ *p->tdlut_opt_time = (*p->tdlut_bytes_per_frame - p->cursor_buffer_size * 1024) / tdlut_drain_rate;
+ else
+ *p->tdlut_opt_time = 0;
*p->tdlut_drain_time = p->cursor_buffer_size * 1024 / tdlut_drain_rate;
*p->tdlut_bytes_to_deliver = (unsigned int) (p->cursor_buffer_size * 1024.0);
}
diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
index 5de775fd8fce..208630754c8a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
@@ -953,6 +953,7 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
out->SourcePixelFormat[location] = dml_420_10;
break;
case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616:
+ case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616:
case SURFACE_PIXEL_FORMAT_GRPH_ARGB16161616F:
case SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F:
out->SourcePixelFormat[location] = dml_444_64;
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
index e8730cc40edb..38e17b1796e1 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
@@ -1225,7 +1225,7 @@ void dce110_blank_stream(struct pipe_ctx *pipe_ctx)
return;
if (link->local_sink && link->local_sink->sink_signal == SIGNAL_TYPE_EDP) {
- if (!link->skip_implict_edp_power_control)
+ if (!link->skip_implict_edp_power_control && hws)
hws->funcs.edp_backlight_control(link, false);
link->dc->hwss.set_abm_immediate_disable(pipe_ctx);
}
diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
index c814d957305a..a267f574b619 100644
--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
@@ -1047,6 +1047,15 @@ void dcn35_calc_blocks_to_gate(struct dc *dc, struct dc_state *context,
if (dc->caps.sequential_ono) {
update_state->pg_pipe_res_update[PG_HUBP][pipe_ctx->stream_res.dsc->inst] = false;
update_state->pg_pipe_res_update[PG_DPP][pipe_ctx->stream_res.dsc->inst] = false;
+
+ /* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+ if (!pipe_ctx->top_pipe && pipe_ctx->plane_res.hubp &&
+ pipe_ctx->plane_res.hubp->inst != pipe_ctx->stream_res.dsc->inst) {
+ for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+ update_state->pg_pipe_res_update[PG_HUBP][j] = false;
+ update_state->pg_pipe_res_update[PG_DPP][j] = false;
+ }
+ }
}
}
@@ -1193,6 +1202,25 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
update_state->pg_pipe_res_update[PG_HDMISTREAM][0] = true;
if (dc->caps.sequential_ono) {
+ for (i = 0; i < dc->res_pool->pipe_count; i++) {
+ struct pipe_ctx *new_pipe = &context->res_ctx.pipe_ctx[i];
+
+ if (new_pipe->stream_res.dsc && !new_pipe->top_pipe &&
+ update_state->pg_pipe_res_update[PG_DSC][new_pipe->stream_res.dsc->inst]) {
+ update_state->pg_pipe_res_update[PG_HUBP][new_pipe->stream_res.dsc->inst] = true;
+ update_state->pg_pipe_res_update[PG_DPP][new_pipe->stream_res.dsc->inst] = true;
+
+ /* All HUBP/DPP instances must be powered if the DSC inst != HUBP inst */
+ if (new_pipe->plane_res.hubp &&
+ new_pipe->plane_res.hubp->inst != new_pipe->stream_res.dsc->inst) {
+ for (j = 0; j < dc->res_pool->pipe_count; ++j) {
+ update_state->pg_pipe_res_update[PG_HUBP][j] = true;
+ update_state->pg_pipe_res_update[PG_DPP][j] = true;
+ }
+ }
+ }
+ }
+
for (i = dc->res_pool->pipe_count - 1; i >= 0; i--) {
if (update_state->pg_pipe_res_update[PG_HUBP][i] &&
update_state->pg_pipe_res_update[PG_DPP][i]) {
diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
index a5127c2d47ef..0f965380a9b4 100644
--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
@@ -385,9 +385,15 @@ bool dp_is_128b_132b_signal(struct pipe_ctx *pipe_ctx)
bool dp_is_lttpr_present(struct dc_link *link)
{
/* Some sink devices report invalid LTTPR revision, so don't validate against that cap */
- return (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) != 0 &&
+ uint32_t lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+ bool is_lttpr_present = (lttpr_count > 0 &&
link->dpcd_caps.lttpr_caps.max_lane_count > 0 &&
link->dpcd_caps.lttpr_caps.max_lane_count <= 4);
+
+ if (lttpr_count > 0 && !is_lttpr_present)
+ DC_LOG_ERROR("LTTPR count is nonzero but invalid lane count reported. Assuming no LTTPR present.\n");
+
+ return is_lttpr_present;
}
/* in DP compliance test, DPR-120 may have
@@ -1551,6 +1557,8 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
uint8_t lttpr_dpcd_data[10] = {0};
enum dc_status status;
bool is_lttpr_present;
+ uint32_t lttpr_count;
+ uint32_t closest_lttpr_offset;
/* Logic to determine LTTPR support*/
bool vbios_lttpr_interop = link->dc->caps.vbios_lttpr_aware;
@@ -1602,20 +1610,22 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
lttpr_dpcd_data[DP_LTTPR_ALPM_CAPABILITIES -
DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV];
+ lttpr_count = dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
+
/* If this chip cap is set, at least one retimer must exist in the chain
* Override count to 1 if we receive a known bad count (0 or an invalid value) */
if (((link->chip_caps & AMD_EXT_DISPLAY_PATH_CAPS__EXT_CHIP_MASK) == AMD_EXT_DISPLAY_PATH_CAPS__DP_FIXED_VS_EN) &&
- (dp_parse_lttpr_repeater_count(link->dpcd_caps.lttpr_caps.phy_repeater_cnt) == 0)) {
+ lttpr_count == 0) {
/* If you see this message consistently, either the host platform has FIXED_VS flag
* incorrectly configured or the sink device is returning an invalid count.
*/
DC_LOG_ERROR("lttpr_caps phy_repeater_cnt is 0x%x, forcing it to 0x80.",
link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
link->dpcd_caps.lttpr_caps.phy_repeater_cnt = 0x80;
+ lttpr_count = 1;
DC_LOG_DC("lttpr_caps forced phy_repeater_cnt = %d\n", link->dpcd_caps.lttpr_caps.phy_repeater_cnt);
}
- /* Attempt to train in LTTPR transparent mode if repeater count exceeds 8. */
is_lttpr_present = dp_is_lttpr_present(link);
DC_LOG_DC("is_lttpr_present = %d\n", is_lttpr_present);
@@ -1623,11 +1633,25 @@ enum dc_status dp_retrieve_lttpr_cap(struct dc_link *link)
if (is_lttpr_present) {
CONN_DATA_DETECT(link, lttpr_dpcd_data, sizeof(lttpr_dpcd_data), "LTTPR Caps: ");
- core_link_read_dpcd(link, DP_LTTPR_IEEE_OUI, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui));
- CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui), "LTTPR IEEE OUI: ");
+ // Identify closest LTTPR to determine if workarounds required for known embedded LTTPR
+ closest_lttpr_offset = dp_get_closest_lttpr_offset(lttpr_count);
- core_link_read_dpcd(link, DP_LTTPR_DEVICE_ID, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id));
- CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id), "LTTPR Device ID: ");
+ core_link_read_dpcd(link, (DP_LTTPR_IEEE_OUI + closest_lttpr_offset),
+ link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui));
+ core_link_read_dpcd(link, (DP_LTTPR_DEVICE_ID + closest_lttpr_offset),
+ link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id));
+
+ if (lttpr_count > 1) {
+ CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui),
+ "Closest LTTPR To Host's IEEE OUI: ");
+ CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id),
+ "Closest LTTPR To Host's LTTPR Device ID: ");
+ } else {
+ CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_ieee_oui, sizeof(link->dpcd_caps.lttpr_caps.lttpr_ieee_oui),
+ "LTTPR IEEE OUI: ");
+ CONN_DATA_DETECT(link, link->dpcd_caps.lttpr_caps.lttpr_device_id, sizeof(link->dpcd_caps.lttpr_caps.lttpr_device_id),
+ "LTTPR Device ID: ");
+ }
}
return status;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
index 7e0af5297dc4..51ca0b2959fc 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
@@ -1954,6 +1954,9 @@ static bool dcn31_resource_construct(
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ dc->caps.num_of_host_routers = 2;
+ dc->caps.num_of_dpias_per_host_router = 2;
+
/* Use pipe context based otg sync logic */
dc->config.use_pipe_ctx_sync_logic = true;
dc->config.disable_hbr_audio_dp2 = true;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
index d96bc6cb73ad..8383e2e59be5 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
@@ -1885,6 +1885,9 @@ static bool dcn314_resource_construct(
dc->caps.max_disp_clock_khz_at_vmin = 650000;
+ dc->caps.num_of_host_routers = 2;
+ dc->caps.num_of_dpias_per_host_router = 2;
+
/* Use pipe context based otg sync logic */
dc->config.use_pipe_ctx_sync_logic = true;
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
index 72c6cf047db0..e01aa2f2e13e 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
@@ -1894,6 +1894,9 @@ static bool dcn35_resource_construct(
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ dc->caps.num_of_host_routers = 2;
+ dc->caps.num_of_dpias_per_host_router = 2;
+
/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
* to provide some margin.
* It's expected for furture ASIC to have equal or higher value, in order to
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
index 989a270f7dea..4ebe4e00a4f8 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
@@ -1866,6 +1866,9 @@ static bool dcn351_resource_construct(
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ dc->caps.num_of_host_routers = 2;
+ dc->caps.num_of_dpias_per_host_router = 2;
+
/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
* to provide some margin.
* It's expected for furture ASIC to have equal or higher value, in order to
diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
index 48e1f234185f..db36b8f9ce65 100644
--- a/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/resource/dcn36/dcn36_resource.c
@@ -1867,6 +1867,9 @@ static bool dcn36_resource_construct(
dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
dc->caps.color.mpc.ocsc = 1;
+ dc->caps.num_of_host_routers = 2;
+ dc->caps.num_of_dpias_per_host_router = 2;
+
/* max_disp_clock_khz_at_vmin is slightly lower than the STA value in order
* to provide some margin.
* It's expected for furture ASIC to have equal or higher value, in order to
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 a7167668d189..1c7235935d14 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
@@ -58,6 +58,7 @@
MODULE_FIRMWARE("amdgpu/aldebaran_smc.bin");
MODULE_FIRMWARE("amdgpu/smu_13_0_0.bin");
+MODULE_FIRMWARE("amdgpu/smu_13_0_0_kicker.bin");
MODULE_FIRMWARE("amdgpu/smu_13_0_7.bin");
MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
@@ -92,7 +93,7 @@ const int pmfw_decoded_link_width[7] = {0, 1, 2, 4, 8, 12, 16};
int smu_v13_0_init_microcode(struct smu_context *smu)
{
struct amdgpu_device *adev = smu->adev;
- char ucode_prefix[15];
+ char ucode_prefix[30];
int err = 0;
const struct smc_firmware_header_v1_0 *hdr;
const struct common_firmware_header *header;
@@ -103,8 +104,13 @@ int smu_v13_0_init_microcode(struct smu_context *smu)
return 0;
amdgpu_ucode_ip_version_decode(adev, MP1_HWIP, ucode_prefix, sizeof(ucode_prefix));
- err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
- "amdgpu/%s.bin", ucode_prefix);
+
+ if (amdgpu_is_kicker_fw(adev))
+ err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s_kicker.bin", ucode_prefix);
+ else
+ err = amdgpu_ucode_request(adev, &adev->pm.fw, AMDGPU_UCODE_REQUIRED,
+ "amdgpu/%s.bin", ucode_prefix);
if (err)
goto out;
diff --git a/drivers/gpu/drm/arm/malidp_planes.c b/drivers/gpu/drm/arm/malidp_planes.c
index 34547edf1ee3..87f2e5ee8790 100644
--- a/drivers/gpu/drm/arm/malidp_planes.c
+++ b/drivers/gpu/drm/arm/malidp_planes.c
@@ -159,7 +159,7 @@ bool malidp_format_mod_supported(struct drm_device *drm,
}
if (!fourcc_mod_is_vendor(modifier, ARM)) {
- DRM_ERROR("Unknown modifier (not Arm)\n");
+ DRM_DEBUG_KMS("Unknown modifier (not Arm)\n");
return false;
}
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 1de832964e92..031980d8f3ab 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -29,7 +29,6 @@
*/
#include <linux/delay.h>
-#include <linux/export.h>
#include <linux/pci.h>
#include <drm/drm_atomic.h>
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 76a3a3e517d8..71e2e6b9d713 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -35,6 +35,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
*sched_job)
{
struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
+ struct drm_gpu_scheduler *sched = sched_job->sched;
struct etnaviv_gpu *gpu = submit->gpu;
u32 dma_addr, primid = 0;
int change;
@@ -89,7 +90,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
return DRM_GPU_SCHED_STAT_NOMINAL;
out_no_timeout:
- list_add(&sched_job->list, &sched_job->sched->pending_list);
+ spin_lock(&sched->job_list_lock);
+ list_add(&sched_job->list, &sched->pending_list);
+ spin_unlock(&sched->job_list_lock);
return DRM_GPU_SCHED_STAT_NOMINAL;
}
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 346737f15fa9..21c1e10caf68 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1056,7 +1056,7 @@ static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
BXT_MIPI_TRANS_VACTIVE(port));
adjusted_mode->crtc_vtotal =
intel_de_read(display,
- BXT_MIPI_TRANS_VTOTAL(port));
+ BXT_MIPI_TRANS_VTOTAL(port)) + 1;
hactive = adjusted_mode->crtc_hdisplay;
hfp = intel_de_read(display, MIPI_HFP_COUNT(display, port));
@@ -1260,7 +1260,7 @@ static void set_dsi_timings(struct intel_encoder *encoder,
intel_de_write(display, BXT_MIPI_TRANS_VACTIVE(port),
adjusted_mode->crtc_vdisplay);
intel_de_write(display, BXT_MIPI_TRANS_VTOTAL(port),
- adjusted_mode->crtc_vtotal);
+ adjusted_mode->crtc_vtotal - 1);
}
intel_de_write(display, MIPI_HACTIVE_AREA_COUNT(display, port),
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index e5a188ce3185..990bfaba3ce4 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -112,7 +112,7 @@ static u32 config_mask(const u64 config)
{
unsigned int bit = config_bit(config);
- if (__builtin_constant_p(config))
+ if (__builtin_constant_p(bit))
BUILD_BUG_ON(bit >
BITS_PER_TYPE(typeof_member(struct i915_pmu,
enable)) - 1);
@@ -121,7 +121,7 @@ static u32 config_mask(const u64 config)
BITS_PER_TYPE(typeof_member(struct i915_pmu,
enable)) - 1);
- return BIT(config_bit(config));
+ return BIT(bit);
}
static bool is_engine_event(struct perf_event *event)
diff --git a/drivers/gpu/drm/meson/meson_encoder_hdmi.c b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
index 47136bbbe8c6..ab08d690d882 100644
--- a/drivers/gpu/drm/meson/meson_encoder_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_encoder_hdmi.c
@@ -109,7 +109,7 @@ static void meson_encoder_hdmi_set_vclk(struct meson_encoder_hdmi *encoder_hdmi,
venc_freq /= 2;
dev_dbg(priv->dev,
- "vclk:%lluHz phy=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
+ "phy:%lluHz vclk=%lluHz venc=%lluHz hdmi=%lluHz enci=%d\n",
phy_freq, vclk_freq, venc_freq, hdmi_freq,
priv->venc.hdmi_use_enci);
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index 3325580d885d..dfe0c28a0f05 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -110,10 +110,7 @@
#define HDMI_PLL_LOCK BIT(31)
#define HDMI_PLL_LOCK_G12A (3 << 30)
-#define PIXEL_FREQ_1000_1001(_freq) \
- DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
-#define PHY_FREQ_1000_1001(_freq) \
- (PIXEL_FREQ_1000_1001(DIV_ROUND_DOWN_ULL(_freq, 10ULL)) * 10)
+#define FREQ_1000_1001(_freq) DIV_ROUND_CLOSEST_ULL((_freq) * 1000ULL, 1001ULL)
/* VID PLL Dividers */
enum {
@@ -772,6 +769,36 @@ static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
pll_freq);
}
+static bool meson_vclk_freqs_are_matching_param(unsigned int idx,
+ unsigned long long phy_freq,
+ unsigned long long vclk_freq)
+{
+ DRM_DEBUG_DRIVER("i = %d vclk_freq = %lluHz alt = %lluHz\n",
+ idx, params[idx].vclk_freq,
+ FREQ_1000_1001(params[idx].vclk_freq));
+ DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
+ idx, params[idx].phy_freq,
+ FREQ_1000_1001(params[idx].phy_freq));
+
+ /* Match strict frequency */
+ if (phy_freq == params[idx].phy_freq &&
+ vclk_freq == params[idx].vclk_freq)
+ return true;
+
+ /* Match 1000/1001 variant: vclk deviation has to be less than 1kHz
+ * (drm EDID is defined in 1kHz steps, so everything smaller must be
+ * rounding error) and the PHY freq deviation has to be less than
+ * 10kHz (as the TMDS clock is 10 times the pixel clock, so anything
+ * smaller must be rounding error as well).
+ */
+ if (abs(vclk_freq - FREQ_1000_1001(params[idx].vclk_freq)) < 1000 &&
+ abs(phy_freq - FREQ_1000_1001(params[idx].phy_freq)) < 10000)
+ return true;
+
+ /* no match */
+ return false;
+}
+
enum drm_mode_status
meson_vclk_vic_supported_freq(struct meson_drm *priv,
unsigned long long phy_freq,
@@ -790,19 +817,7 @@ meson_vclk_vic_supported_freq(struct meson_drm *priv,
}
for (i = 0 ; params[i].pixel_freq ; ++i) {
- DRM_DEBUG_DRIVER("i = %d pixel_freq = %lluHz alt = %lluHz\n",
- i, params[i].pixel_freq,
- PIXEL_FREQ_1000_1001(params[i].pixel_freq));
- DRM_DEBUG_DRIVER("i = %d phy_freq = %lluHz alt = %lluHz\n",
- i, params[i].phy_freq,
- PHY_FREQ_1000_1001(params[i].phy_freq));
- /* Match strict frequency */
- if (phy_freq == params[i].phy_freq &&
- vclk_freq == params[i].vclk_freq)
- return MODE_OK;
- /* Match 1000/1001 variant */
- if (phy_freq == PHY_FREQ_1000_1001(params[i].phy_freq) &&
- vclk_freq == PIXEL_FREQ_1000_1001(params[i].vclk_freq))
+ if (meson_vclk_freqs_are_matching_param(i, phy_freq, vclk_freq))
return MODE_OK;
}
@@ -1075,10 +1090,8 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
}
for (freq = 0 ; params[freq].pixel_freq ; ++freq) {
- if ((phy_freq == params[freq].phy_freq ||
- phy_freq == PHY_FREQ_1000_1001(params[freq].phy_freq)) &&
- (vclk_freq == params[freq].vclk_freq ||
- vclk_freq == PIXEL_FREQ_1000_1001(params[freq].vclk_freq))) {
+ if (meson_vclk_freqs_are_matching_param(freq, phy_freq,
+ vclk_freq)) {
if (vclk_freq != params[freq].vclk_freq)
vic_alternate_clock = true;
else
diff --git a/drivers/gpu/drm/mgag200/mgag200_ddc.c b/drivers/gpu/drm/mgag200/mgag200_ddc.c
index 6d81ea8931e8..c31673eaa554 100644
--- a/drivers/gpu/drm/mgag200/mgag200_ddc.c
+++ b/drivers/gpu/drm/mgag200/mgag200_ddc.c
@@ -26,7 +26,6 @@
* Authors: Dave Airlie <airlied@redhat.com>
*/
-#include <linux/export.h>
#include <linux/i2c-algo-bit.h>
#include <linux/i2c.h>
#include <linux/pci.h>
diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
index 39641551eeb6..4280f71e472a 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
+++ b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
@@ -71,10 +71,6 @@ static int a2xx_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
return 0;
}
-static void a2xx_gpummu_resume_translation(struct msm_mmu *mmu)
-{
-}
-
static void a2xx_gpummu_destroy(struct msm_mmu *mmu)
{
struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu);
@@ -90,7 +86,6 @@ static const struct msm_mmu_funcs funcs = {
.map = a2xx_gpummu_map,
.unmap = a2xx_gpummu_unmap,
.destroy = a2xx_gpummu_destroy,
- .resume_translation = a2xx_gpummu_resume_translation,
};
struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 650e5bac225f..60aef0796236 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -131,6 +131,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned int i, ibs = 0;
+ adreno_check_and_reenable_stall(adreno_gpu);
+
if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) {
ring->cur_ctx_seqno = 0;
a5xx_submit_in_rb(gpu, submit);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index bf3758f010f4..491fde0083a2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
OUT_RING(ring, submit->seqno - 1);
+
+ OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+ OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+ /* Reset state used to synchronize BR and BV */
+ OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1);
+ OUT_RING(ring,
+ CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS |
+ CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE |
+ CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER |
+ CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS);
+
+ OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+ OUT_RING(ring, CP_SET_THREAD_BR);
}
if (!sysprof) {
@@ -212,6 +226,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned int i, ibs = 0;
+ adreno_check_and_reenable_stall(adreno_gpu);
+
a6xx_set_pagetable(a6xx_gpu, ring, submit);
get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -335,6 +351,8 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
struct msm_ringbuffer *ring = submit->ring;
unsigned int i, ibs = 0;
+ adreno_check_and_reenable_stall(adreno_gpu);
+
/*
* Toggle concurrent binning for pagetable switch and set the thread to
* BR since only it can execute the pagetable switch packets.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index f5e1490d07c1..16e7ac444efd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -137,9 +137,8 @@ err_disable_rpm:
return NULL;
}
-static int find_chipid(struct device *dev, uint32_t *chipid)
+static int find_chipid(struct device_node *node, uint32_t *chipid)
{
- struct device_node *node = dev->of_node;
const char *compat;
int ret;
@@ -173,15 +172,36 @@ static int find_chipid(struct device *dev, uint32_t *chipid)
/* and if that fails, fall back to legacy "qcom,chipid" property: */
ret = of_property_read_u32(node, "qcom,chipid", chipid);
if (ret) {
- DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret);
+ DRM_ERROR("%pOF: could not parse qcom,chipid: %d\n",
+ node, ret);
return ret;
}
- dev_warn(dev, "Using legacy qcom,chipid binding!\n");
+ pr_warn("%pOF: Using legacy qcom,chipid binding!\n", node);
return 0;
}
+bool adreno_has_gpu(struct device_node *node)
+{
+ const struct adreno_info *info;
+ uint32_t chip_id;
+ int ret;
+
+ ret = find_chipid(node, &chip_id);
+ if (ret)
+ return false;
+
+ info = adreno_info(chip_id);
+ if (!info) {
+ pr_warn("%pOF: Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
+ node, ADRENO_CHIPID_ARGS(chip_id));
+ return false;
+ }
+
+ return true;
+}
+
static int adreno_bind(struct device *dev, struct device *master, void *data)
{
static struct adreno_platform_config config = {};
@@ -191,19 +211,18 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
struct msm_gpu *gpu;
int ret;
- ret = find_chipid(dev, &config.chip_id);
- if (ret)
+ ret = find_chipid(dev->of_node, &config.chip_id);
+ /* We shouldn't have gotten this far if we can't parse the chip_id */
+ if (WARN_ON(ret))
return ret;
dev->platform_data = &config;
priv->gpu_pdev = to_platform_device(dev);
info = adreno_info(config.chip_id);
- if (!info) {
- dev_warn(drm->dev, "Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
- ADRENO_CHIPID_ARGS(config.chip_id));
+ /* We shouldn't have gotten this far if we don't recognize the GPU: */
+ if (WARN_ON(!info))
return -ENXIO;
- }
config.info = info;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 2348ffb35f7e..86bff915c3e7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -259,24 +259,54 @@ u64 adreno_private_address_space_size(struct msm_gpu *gpu)
return BIT(ttbr1_cfg->ias) - ADRENO_VM_START;
}
+void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu)
+{
+ struct msm_gpu *gpu = &adreno_gpu->base;
+ struct msm_drm_private *priv = gpu->dev->dev_private;
+ unsigned long flags;
+
+ /*
+ * Wait until the cooldown period has passed and we would actually
+ * collect a crashdump to re-enable stall-on-fault.
+ */
+ spin_lock_irqsave(&priv->fault_stall_lock, flags);
+ if (!priv->stall_enabled &&
+ ktime_after(ktime_get(), priv->stall_reenable_time) &&
+ !READ_ONCE(gpu->crashstate)) {
+ priv->stall_enabled = true;
+
+ gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, true);
+ }
+ spin_unlock_irqrestore(&priv->fault_stall_lock, flags);
+}
+
#define ARM_SMMU_FSR_TF BIT(1)
#define ARM_SMMU_FSR_PF BIT(3)
#define ARM_SMMU_FSR_EF BIT(4)
+#define ARM_SMMU_FSR_SS BIT(30)
int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
struct adreno_smmu_fault_info *info, const char *block,
u32 scratch[4])
{
+ struct msm_drm_private *priv = gpu->dev->dev_private;
const char *type = "UNKNOWN";
- bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
+ bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) &&
+ !READ_ONCE(gpu->crashstate);
+ unsigned long irq_flags;
/*
- * If we aren't going to be resuming later from fault_worker, then do
- * it now.
+ * In case there is a subsequent storm of pagefaults, disable
+ * stall-on-fault for at least half a second.
*/
- if (!do_devcoredump) {
- gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
+ spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+ if (priv->stall_enabled) {
+ priv->stall_enabled = false;
+
+ gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, false);
}
+ priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500);
+ spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
/*
* Print a default message if we couldn't get the data from the
@@ -304,16 +334,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
scratch[0], scratch[1], scratch[2], scratch[3]);
if (do_devcoredump) {
+ struct msm_gpu_fault_info fault_info = {};
+
/* Turn off the hangcheck timer to keep it from bothering us */
timer_delete(&gpu->hangcheck_timer);
- gpu->fault_info.ttbr0 = info->ttbr0;
- gpu->fault_info.iova = iova;
- gpu->fault_info.flags = flags;
- gpu->fault_info.type = type;
- gpu->fault_info.block = block;
+ fault_info.ttbr0 = info->ttbr0;
+ fault_info.iova = iova;
+ fault_info.flags = flags;
+ fault_info.type = type;
+ fault_info.block = block;
- kthread_queue_work(gpu->worker, &gpu->fault_work);
+ msm_gpu_fault_crashstate_capture(gpu, &fault_info);
}
return 0;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index a8f4bf416e64..bc063594a359 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -636,6 +636,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
struct adreno_smmu_fault_info *info, const char *block,
u32 scratch[4]);
+void adreno_check_and_reenable_stall(struct adreno_gpu *gpu);
+
int adreno_read_speedbin(struct device *dev, u32 *speedbin);
/*
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index 8a618841e3ea..1c468ca5d692 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params(
timing->vsync_polarity = 0;
}
- /* for DP/EDP, Shift timings to align it to bottom right */
- if (phys_enc->hw_intf->cap->type == INTF_DP) {
+ timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+ timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
+
+ /*
+ * For DP/EDP, Shift timings to align it to bottom right.
+ * wide_bus_en is set for everything excluding SDM845 &
+ * porch changes cause DisplayPort failure and HDMI tearing.
+ */
+ if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) {
timing->h_back_porch += timing->h_front_porch;
timing->h_front_porch = 0;
timing->v_back_porch += timing->v_front_porch;
timing->v_front_porch = 0;
}
- timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
- timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
-
/*
* for DP, divide the horizonal parameters by 2 when
* widebus is enabled
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 386c4669c831..a48e6db4f156 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -128,6 +128,11 @@ static const struct msm_dp_desc msm_dp_desc_sa8775p[] = {
{}
};
+static const struct msm_dp_desc msm_dp_desc_sdm845[] = {
+ { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 },
+ {}
+};
+
static const struct msm_dp_desc msm_dp_desc_sc7180[] = {
{ .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
{}
@@ -180,7 +185,7 @@ static const struct of_device_id msm_dp_dt_match[] = {
{ .compatible = "qcom,sc8180x-edp", .data = &msm_dp_desc_sc8180x },
{ .compatible = "qcom,sc8280xp-dp", .data = &msm_dp_desc_sc8280xp },
{ .compatible = "qcom,sc8280xp-edp", .data = &msm_dp_desc_sc8280xp },
- { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sc7180 },
+ { .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sdm845 },
{ .compatible = "qcom,sm8350-dp", .data = &msm_dp_desc_sc7180 },
{ .compatible = "qcom,sm8650-dp", .data = &msm_dp_desc_sm8650 },
{ .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 },
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 9812b4d69197..af2e30f3f842 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
@@ -704,6 +704,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy)
/* TODO: Remove this when we have proper display handover support */
msm_dsi_phy_pll_save_state(phy);
+ /*
+ * Store also proper vco_current_rate, because its value will be used in
+ * dsi_10nm_pll_restore_state().
+ */
+ if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE))
+ pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate;
+
return 0;
}
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 7ab607252d18..6af72162cda4 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -208,6 +208,35 @@ DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops,
shrink_get, shrink_set,
"0x%08llx\n");
+/*
+ * Return the number of microseconds to wait until stall-on-fault is
+ * re-enabled. If 0 then it is already enabled or will be re-enabled on the
+ * next submit (unless there's a leftover devcoredump). This is useful for
+ * kernel tests that intentionally produce a fault and check the devcoredump to
+ * wait until the cooldown period is over.
+ */
+
+static int
+stall_reenable_time_get(void *data, u64 *val)
+{
+ struct msm_drm_private *priv = data;
+ unsigned long irq_flags;
+
+ spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+
+ if (priv->stall_enabled)
+ *val = 0;
+ else
+ *val = max(ktime_us_delta(priv->stall_reenable_time, ktime_get()), 0);
+
+ spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
+
+ return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(stall_reenable_time_fops,
+ stall_reenable_time_get, NULL,
+ "%lld\n");
static int msm_gem_show(struct seq_file *m, void *arg)
{
@@ -319,6 +348,9 @@ static void msm_debugfs_gpu_init(struct drm_minor *minor)
debugfs_create_bool("disable_err_irq", 0600, minor->debugfs_root,
&priv->disable_err_irq);
+ debugfs_create_file("stall_reenable_time_us", 0400, minor->debugfs_root,
+ priv, &stall_reenable_time_fops);
+
gpu_devfreq = debugfs_create_dir("devfreq", minor->debugfs_root);
debugfs_create_bool("idle_clamp",0600, gpu_devfreq,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index f316e6776f67..d007687c2446 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -245,6 +245,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock);
drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock);
+ /* Initialize stall-on-fault */
+ spin_lock_init(&priv->fault_stall_lock);
+ priv->stall_enabled = true;
+
/* Teach lockdep about lock ordering wrt. shrinker: */
fs_reclaim_acquire(GFP_KERNEL);
might_lock(&priv->lru.lock);
@@ -926,7 +930,7 @@ static const struct drm_driver msm_driver = {
* is no external component that we need to add since LVDS is within MDP4
* itself.
*/
-static int add_components_mdp(struct device *master_dev,
+static int add_mdp_components(struct device *master_dev,
struct component_match **matchptr)
{
struct device_node *np = master_dev->of_node;
@@ -1030,7 +1034,7 @@ static int add_gpu_components(struct device *dev,
if (!np)
return 0;
- if (of_device_is_available(np))
+ if (of_device_is_available(np) && adreno_has_gpu(np))
drm_of_component_match_add(dev, matchptr, component_compare_of, np);
of_node_put(np);
@@ -1071,7 +1075,7 @@ int msm_drv_probe(struct device *master_dev,
/* Add mdp components if we have KMS. */
if (kms_init) {
- ret = add_components_mdp(master_dev, &match);
+ ret = add_mdp_components(master_dev, &match);
if (ret)
return ret;
}
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index a65077855201..c8afb1ea6040 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -222,6 +222,29 @@ struct msm_drm_private {
* the sw hangcheck mechanism.
*/
bool disable_err_irq;
+
+ /**
+ * @fault_stall_lock:
+ *
+ * Serialize changes to stall-on-fault state.
+ */
+ spinlock_t fault_stall_lock;
+
+ /**
+ * @fault_stall_reenable_time:
+ *
+ * If stall_enabled is false, when to reenable stall-on-fault.
+ * Protected by @fault_stall_lock.
+ */
+ ktime_t stall_reenable_time;
+
+ /**
+ * @stall_enabled:
+ *
+ * Whether stall-on-fault is currently enabled. Protected by
+ * @fault_stall_lock.
+ */
+ bool stall_enabled;
};
const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3e9aa2cc38ef..d4f71bb54e84 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref)
container_of(kref, struct msm_gem_submit, ref);
unsigned i;
+ /*
+ * In error paths, we could unref the submit without calling
+ * drm_sched_entity_push_job(), so msm_job_free() will never
+ * get called. Since drm_sched_job_cleanup() will NULL out
+ * s_fence, we can use that to detect this case.
+ */
+ if (submit->base.s_fence)
+ drm_sched_job_cleanup(&submit->base);
+
if (submit->fence_id) {
spin_lock(&submit->queue->idr_lock);
idr_remove(&submit->queue->fence_idr, submit->fence_id);
@@ -649,6 +658,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
struct msm_ringbuffer *ring;
struct msm_submit_post_dep *post_deps = NULL;
struct drm_syncobj **syncobjs_to_reset = NULL;
+ struct sync_file *sync_file = NULL;
int out_fence_fd = -1;
unsigned i;
int ret;
@@ -858,7 +868,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
}
if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
- struct sync_file *sync_file = sync_file_create(submit->user_fence);
+ sync_file = sync_file_create(submit->user_fence);
if (!sync_file) {
ret = -ENOMEM;
} else {
@@ -892,8 +902,11 @@ out:
out_unlock:
mutex_unlock(&queue->lock);
out_post_unlock:
- if (ret && (out_fence_fd >= 0))
+ if (ret && (out_fence_fd >= 0)) {
put_unused_fd(out_fence_fd);
+ if (sync_file)
+ fput(sync_file->file);
+ }
if (!IS_ERR_OR_NULL(submit)) {
msm_gem_submit_put(submit);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 197871fdf508..3947f7ba1421 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -257,7 +257,8 @@ out:
}
static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
- struct msm_gem_submit *submit, char *comm, char *cmd)
+ struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+ char *comm, char *cmd)
{
struct msm_gpu_state *state;
@@ -276,7 +277,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
/* Fill in the additional crash state information */
state->comm = kstrdup(comm, GFP_KERNEL);
state->cmd = kstrdup(cmd, GFP_KERNEL);
- state->fault_info = gpu->fault_info;
+ if (fault_info)
+ state->fault_info = *fault_info;
if (submit) {
int i;
@@ -308,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
}
#else
static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
- struct msm_gem_submit *submit, char *comm, char *cmd)
+ struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+ char *comm, char *cmd)
{
}
#endif
@@ -405,7 +408,7 @@ static void recover_worker(struct kthread_work *work)
/* Record the crash state */
pm_runtime_get_sync(&gpu->pdev->dev);
- msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+ msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd);
kfree(cmd);
kfree(comm);
@@ -459,9 +462,8 @@ out_unlock:
msm_gpu_retire(gpu);
}
-static void fault_worker(struct kthread_work *work)
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info)
{
- struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work);
struct msm_gem_submit *submit;
struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
char *comm = NULL, *cmd = NULL;
@@ -484,16 +486,13 @@ static void fault_worker(struct kthread_work *work)
/* Record the crash state */
pm_runtime_get_sync(&gpu->pdev->dev);
- msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+ msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd);
pm_runtime_put_sync(&gpu->pdev->dev);
kfree(cmd);
kfree(comm);
resume_smmu:
- memset(&gpu->fault_info, 0, sizeof(gpu->fault_info));
- gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-
mutex_unlock(&gpu->lock);
}
@@ -882,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
init_waitqueue_head(&gpu->retire_event);
kthread_init_work(&gpu->retire_work, retire_worker);
kthread_init_work(&gpu->recover_work, recover_worker);
- kthread_init_work(&gpu->fault_work, fault_worker);
priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD;
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index e25009150579..5bf7cd985b9c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -253,12 +253,6 @@ struct msm_gpu {
#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3
struct timer_list hangcheck_timer;
- /* Fault info for most recent iova fault: */
- struct msm_gpu_fault_info fault_info;
-
- /* work for handling GPU ioval faults: */
- struct kthread_work fault_work;
-
/* work for handling GPU recovery: */
struct kthread_work recover_work;
@@ -668,6 +662,7 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *ta
void msm_gpu_cleanup(struct msm_gpu *gpu);
struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
+bool adreno_has_gpu(struct device_node *node);
void __init adreno_register(void);
void __exit adreno_unregister(void);
@@ -705,6 +700,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
mutex_unlock(&gpu->lock);
}
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info);
+
/*
* Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
* support expanded privileges
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index fd73dcd3f30e..739ce2c283a4 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -345,7 +345,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
unsigned long iova, int flags, void *arg)
{
struct msm_iommu *iommu = arg;
- struct msm_mmu *mmu = &iommu->base;
struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev);
struct adreno_smmu_fault_info info, *ptr = NULL;
@@ -359,9 +358,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
- if (mmu->funcs->resume_translation)
- mmu->funcs->resume_translation(mmu);
-
return 0;
}
@@ -376,12 +372,12 @@ static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *de
return -ENOSYS;
}
-static void msm_iommu_resume_translation(struct msm_mmu *mmu)
+static void msm_iommu_set_stall(struct msm_mmu *mmu, bool enable)
{
struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev);
- if (adreno_smmu->resume_translation)
- adreno_smmu->resume_translation(adreno_smmu->cookie, true);
+ if (adreno_smmu->set_stall)
+ adreno_smmu->set_stall(adreno_smmu->cookie, enable);
}
static void msm_iommu_detach(struct msm_mmu *mmu)
@@ -431,7 +427,7 @@ static const struct msm_mmu_funcs funcs = {
.map = msm_iommu_map,
.unmap = msm_iommu_unmap,
.destroy = msm_iommu_destroy,
- .resume_translation = msm_iommu_resume_translation,
+ .set_stall = msm_iommu_set_stall,
};
struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index daf91529e02b..0c694907140d 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -15,7 +15,7 @@ struct msm_mmu_funcs {
size_t len, int prot);
int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len);
void (*destroy)(struct msm_mmu *mmu);
- void (*resume_translation)(struct msm_mmu *mmu);
+ void (*set_stall)(struct msm_mmu *mmu, bool enable);
};
enum msm_mmu_type {
diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index 5a6ae9fc3194..462713401622 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2255,7 +2255,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords)
<reg32 offset="0" name="0">
<bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/>
<bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/>
- <bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/>
+ <bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/>
+ <bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/>
</reg32>
</domain>
diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py
index 3926485bb197..a409404627c7 100644
--- a/drivers/gpu/drm/msm/registers/gen_header.py
+++ b/drivers/gpu/drm/msm/registers/gen_header.py
@@ -11,6 +11,7 @@ import collections
import argparse
import time
import datetime
+import re
class Error(Exception):
def __init__(self, message):
@@ -877,13 +878,14 @@ The rules-ng-ng source files this header was generated from are:
""")
maxlen = 0
for filepath in p.xml_files:
- maxlen = max(maxlen, len(filepath))
+ new_filepath = re.sub("^.+drivers","drivers",filepath)
+ maxlen = max(maxlen, len(new_filepath))
for filepath in p.xml_files:
- pad = " " * (maxlen - len(filepath))
+ pad = " " * (maxlen - len(new_filepath))
filesize = str(os.path.getsize(filepath))
filesize = " " * (7 - len(filesize)) + filesize
filetime = time.ctime(os.path.getmtime(filepath))
- print("- " + filepath + pad + " (" + filesize + " bytes, from " + filetime + ")")
+ print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)")
if p.copyright_year:
current_year = str(datetime.date.today().year)
print()
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index d47442125fa1..9aae26eb7d8f 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -42,7 +42,7 @@
#include "nouveau_acpi.h"
static struct ida bl_ida;
-#define BL_NAME_SIZE 15 // 12 for name + 2 for digits + 1 for '\0'
+#define BL_NAME_SIZE 24 // 12 for name + 11 for digits + 1 for '\0'
static bool
nouveau_get_backlight_name(char backlight_name[BL_NAME_SIZE],
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
index 5acb98d137bd..9d06ff722fea 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/rpc.c
@@ -637,12 +637,18 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
if (payload_size > max_payload_size) {
const u32 fn = rpc->function;
u32 remain_payload_size = payload_size;
+ void *next;
- /* Adjust length, and send initial RPC. */
- rpc->length = sizeof(*rpc) + max_payload_size;
- msg->checksum = rpc->length;
+ /* Send initial RPC. */
+ next = r535_gsp_rpc_get(gsp, fn, max_payload_size);
+ if (IS_ERR(next)) {
+ repv = next;
+ goto done;
+ }
- repv = r535_gsp_rpc_send(gsp, payload, NVKM_GSP_RPC_REPLY_NOWAIT, 0);
+ memcpy(next, payload, max_payload_size);
+
+ repv = r535_gsp_rpc_send(gsp, next, NVKM_GSP_RPC_REPLY_NOWAIT, 0);
if (IS_ERR(repv))
goto done;
@@ -653,7 +659,6 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
while (remain_payload_size) {
u32 size = min(remain_payload_size,
max_payload_size);
- void *next;
next = r535_gsp_rpc_get(gsp, NV_VGPU_MSG_FUNCTION_CONTINUATION_RECORD, size);
if (IS_ERR(next)) {
@@ -674,6 +679,8 @@ r535_gsp_rpc_push(struct nvkm_gsp *gsp, void *payload,
/* Wait for reply. */
repv = r535_gsp_rpc_handle_reply(gsp, fn, policy, payload_size +
sizeof(*rpc));
+ if (!IS_ERR(repv))
+ kvfree(msg);
} else {
repv = r535_gsp_rpc_send(gsp, payload, policy, gsp_rpc_len);
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
index 52f2e5f14517..f25ea610cd99 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/rm/r535/vmm.c
@@ -121,7 +121,7 @@ r535_mmu_vaspace_new(struct nvkm_vmm *vmm, u32 handle, bool external)
page_shift -= desc->bits;
ctrl->levels[i].physAddress = pd->pt[0]->addr;
- ctrl->levels[i].size = (1 << desc->bits) * desc->size;
+ ctrl->levels[i].size = BIT_ULL(desc->bits) * desc->size;
ctrl->levels[i].aperture = 1;
ctrl->levels[i].pageShift = page_shift;
diff --git a/drivers/gpu/drm/sitronix/Kconfig b/drivers/gpu/drm/sitronix/Kconfig
index c069d0d41775..741d1bb4b83f 100644
--- a/drivers/gpu/drm/sitronix/Kconfig
+++ b/drivers/gpu/drm/sitronix/Kconfig
@@ -5,6 +5,7 @@ config DRM_ST7571_I2C
select DRM_GEM_SHMEM_HELPER
select DRM_KMS_HELPER
select REGMAP_I2C
+ select VIDEOMODE_HELPERS
help
DRM driver for Sitronix ST7571 panels controlled over I2C.
diff --git a/drivers/gpu/drm/solomon/ssd130x.c b/drivers/gpu/drm/solomon/ssd130x.c
index dd2006d51c7a..eec43d1a5595 100644
--- a/drivers/gpu/drm/solomon/ssd130x.c
+++ b/drivers/gpu/drm/solomon/ssd130x.c
@@ -974,7 +974,7 @@ static void ssd130x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
static void ssd132x_clear_screen(struct ssd130x_device *ssd130x, u8 *data_array)
{
- unsigned int columns = DIV_ROUND_UP(ssd130x->height, SSD132X_SEGMENT_WIDTH);
+ unsigned int columns = DIV_ROUND_UP(ssd130x->width, SSD132X_SEGMENT_WIDTH);
unsigned int height = ssd130x->height;
memset(data_array, 0, columns * height);
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 35f131a46d07..42df9d3567e7 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -199,7 +199,6 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
struct v3d_dev *v3d = job->v3d;
struct v3d_file_priv *file = job->file->driver_priv;
struct v3d_stats *global_stats = &v3d->queue[queue].stats;
- struct v3d_stats *local_stats = &file->stats[queue];
u64 now = local_clock();
unsigned long flags;
@@ -209,7 +208,12 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
else
preempt_disable();
- v3d_stats_update(local_stats, now);
+ /* Don't update the local stats if the file context has already closed */
+ if (file)
+ v3d_stats_update(&file->stats[queue], now);
+ else
+ drm_dbg(&v3d->drm, "The file descriptor was closed before job completion\n");
+
v3d_stats_update(global_stats, now);
if (IS_ENABLED(CONFIG_LOCKDEP))
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index a29a6ef266f9..163d092bd973 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -560,12 +560,6 @@ static int vc4_hdmi_connector_init(struct drm_device *dev,
if (ret)
return ret;
- ret = drm_connector_hdmi_audio_init(connector, dev->dev,
- &vc4_hdmi_audio_funcs,
- 8, false, -1);
- if (ret)
- return ret;
-
drm_connector_helper_add(connector, &vc4_hdmi_connector_helper_funcs);
/*
@@ -2291,6 +2285,12 @@ static int vc4_hdmi_audio_init(struct vc4_hdmi *vc4_hdmi)
return ret;
}
+ ret = drm_connector_hdmi_audio_init(&vc4_hdmi->connector, dev,
+ &vc4_hdmi_audio_funcs, 8, false,
+ -1);
+ if (ret)
+ return ret;
+
dai_link->cpus = &vc4_hdmi->audio.cpu;
dai_link->codecs = &vc4_hdmi->audio.codec;
dai_link->platforms = &vc4_hdmi->audio.platform;
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 0e5d243c9451..6c4cb9576fb6 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -118,7 +118,7 @@ static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
xe_gt_mcr_multicast_write(gt, XE2_GAMREQSTRM_CTRL, reg);
}
- xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0x3);
+ xe_gt_mcr_multicast_write(gt, XEHPC_L3CLOS_MASK(3), 0xF);
xe_force_wake_put(gt_to_fw(gt), fw_ref);
}
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 084cbdeba8ea..e1362e608146 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -138,6 +138,14 @@ void xe_gt_tlb_invalidation_reset(struct xe_gt *gt)
int pending_seqno;
/*
+ * we can get here before the CTs are even initialized if we're wedging
+ * very early, in which case there are not going to be any pending
+ * fences so we can bail immediately.
+ */
+ if (!xe_guc_ct_initialized(&gt->uc.guc.ct))
+ return;
+
+ /*
* CT channel is already disabled at this point. No new TLB requests can
* appear.
*/
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 2447de0ebedf..d0ac48d8f4f7 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -514,6 +514,9 @@ void xe_guc_ct_disable(struct xe_guc_ct *ct)
*/
void xe_guc_ct_stop(struct xe_guc_ct *ct)
{
+ if (!xe_guc_ct_initialized(ct))
+ return;
+
xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_STOPPED);
stop_g2h_handler(ct);
}
@@ -760,7 +763,7 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action,
u16 seqno;
int ret;
- xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+ xe_gt_assert(gt, xe_guc_ct_initialized(ct));
xe_gt_assert(gt, !g2h_len || !g2h_fence);
xe_gt_assert(gt, !num_g2h || !g2h_fence);
xe_gt_assert(gt, !g2h_len || num_g2h);
@@ -1344,7 +1347,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
u32 action;
u32 *hxg;
- xe_gt_assert(gt, ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED);
+ xe_gt_assert(gt, xe_guc_ct_initialized(ct));
lockdep_assert_held(&ct->fast_lock);
if (ct->state == XE_GUC_CT_STATE_DISABLED)
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
index 82c4ae458dda..582aac106469 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.h
+++ b/drivers/gpu/drm/xe/xe_guc_ct.h
@@ -22,6 +22,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot, struct drm_pr
void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool want_ctb);
+static inline bool xe_guc_ct_initialized(struct xe_guc_ct *ct)
+{
+ return ct->state != XE_GUC_CT_STATE_NOT_INITIALIZED;
+}
+
static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct)
{
return ct->state == XE_GUC_CT_STATE_ENABLED;
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index 18c623992035..3beaaa7b25c1 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -1068,7 +1068,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
goto out;
}
- memset(pc->bo->vmap.vaddr, 0, size);
+ xe_map_memset(xe, &pc->bo->vmap, 0, 0, size);
slpc_shared_data_write(pc, header.size, size);
earlier = ktime_get();
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 6d84a52b660a..9567f6700cf2 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1762,6 +1762,9 @@ int xe_guc_submit_reset_prepare(struct xe_guc *guc)
{
int ret;
+ if (!guc->submission_state.initialized)
+ return 0;
+
/*
* Using an atomic here rather than submission_state.lock as this
* function can be called while holding the CT lock (engine reset
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 63d74e27f54c..bf7c3981897d 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -941,11 +941,18 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
* store it in the PPHSWP.
*/
#define CONTEXT_ACTIVE 1ULL
-static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
{
- u32 *cmd;
+ u32 *cmd, *buf = NULL;
- cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+ if (lrc->bb_per_ctx_bo->vmap.is_iomem) {
+ buf = kmalloc(lrc->bb_per_ctx_bo->size, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+ cmd = buf;
+ } else {
+ cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+ }
*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
*cmd++ = ENGINE_ID(0).addr;
@@ -966,9 +973,16 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
*cmd++ = MI_BATCH_BUFFER_END;
+ if (buf) {
+ xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bb_per_ctx_bo->vmap, 0,
+ buf, (cmd - buf) * sizeof(*cmd));
+ kfree(buf);
+ }
+
xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
+ return 0;
}
#define PVC_CTX_ASID (0x2e + 1)
@@ -1125,7 +1139,9 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
map = __xe_lrc_start_seqno_map(lrc);
xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
- xe_lrc_setup_utilization(lrc);
+ err = xe_lrc_setup_utilization(lrc);
+ if (err)
+ goto err_lrc_finish;
return 0;
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 6345896585de..f0b167b3fb6a 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -764,7 +764,7 @@ static bool xe_svm_range_needs_migrate_to_vram(struct xe_svm_range *range,
return false;
}
- if (range_size <= SZ_64K && !supports_4K_migration(vm->xe)) {
+ if (range_size < SZ_64K && !supports_4K_migration(vm->xe)) {
drm_dbg(&vm->xe->drm, "Platform doesn't support SZ_4K range migration\n");
return false;
}
diff --git a/drivers/hwmon/ftsteutates.c b/drivers/hwmon/ftsteutates.c
index a3a07662e491..8aeec16a7a90 100644
--- a/drivers/hwmon/ftsteutates.c
+++ b/drivers/hwmon/ftsteutates.c
@@ -423,13 +423,16 @@ static int fts_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
break;
case hwmon_pwm:
switch (attr) {
- case hwmon_pwm_auto_channels_temp:
- if (data->fan_source[channel] == FTS_FAN_SOURCE_INVALID)
+ case hwmon_pwm_auto_channels_temp: {
+ u8 fan_source = data->fan_source[channel];
+
+ if (fan_source == FTS_FAN_SOURCE_INVALID || fan_source >= BITS_PER_LONG)
*val = 0;
else
- *val = BIT(data->fan_source[channel]);
+ *val = BIT(fan_source);
return 0;
+ }
default:
break;
}
diff --git a/drivers/hwmon/ltc4282.c b/drivers/hwmon/ltc4282.c
index 7f38d2696239..f607fe8f7937 100644
--- a/drivers/hwmon/ltc4282.c
+++ b/drivers/hwmon/ltc4282.c
@@ -1512,13 +1512,6 @@ static int ltc4282_setup(struct ltc4282_state *st, struct device *dev)
}
if (device_property_read_bool(dev, "adi,fault-log-enable")) {
- ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL,
- LTC4282_FAULT_LOG_EN_MASK);
- if (ret)
- return ret;
- }
-
- if (device_property_read_bool(dev, "adi,fault-log-enable")) {
ret = regmap_set_bits(st->map, LTC4282_ADC_CTRL, LTC4282_FAULT_LOG_EN_MASK);
if (ret)
return ret;
diff --git a/drivers/hwmon/occ/common.c b/drivers/hwmon/occ/common.c
index 9486db249c64..b3694a4209b9 100644
--- a/drivers/hwmon/occ/common.c
+++ b/drivers/hwmon/occ/common.c
@@ -459,12 +459,10 @@ static ssize_t occ_show_power_1(struct device *dev,
return sysfs_emit(buf, "%llu\n", val);
}
-static u64 occ_get_powr_avg(u64 *accum, u32 *samples)
+static u64 occ_get_powr_avg(u64 accum, u32 samples)
{
- u64 divisor = get_unaligned_be32(samples);
-
- return (divisor == 0) ? 0 :
- div64_u64(get_unaligned_be64(accum) * 1000000ULL, divisor);
+ return (samples == 0) ? 0 :
+ mul_u64_u32_div(accum, 1000000UL, samples);
}
static ssize_t occ_show_power_2(struct device *dev,
@@ -489,8 +487,8 @@ static ssize_t occ_show_power_2(struct device *dev,
get_unaligned_be32(&power->sensor_id),
power->function_id, power->apss_channel);
case 1:
- val = occ_get_powr_avg(&power->accumulator,
- &power->update_tag);
+ val = occ_get_powr_avg(get_unaligned_be64(&power->accumulator),
+ get_unaligned_be32(&power->update_tag));
break;
case 2:
val = (u64)get_unaligned_be32(&power->update_tag) *
@@ -527,8 +525,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
return sysfs_emit(buf, "%u_system\n",
get_unaligned_be32(&power->sensor_id));
case 1:
- val = occ_get_powr_avg(&power->system.accumulator,
- &power->system.update_tag);
+ val = occ_get_powr_avg(get_unaligned_be64(&power->system.accumulator),
+ get_unaligned_be32(&power->system.update_tag));
break;
case 2:
val = (u64)get_unaligned_be32(&power->system.update_tag) *
@@ -541,8 +539,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
return sysfs_emit(buf, "%u_proc\n",
get_unaligned_be32(&power->sensor_id));
case 5:
- val = occ_get_powr_avg(&power->proc.accumulator,
- &power->proc.update_tag);
+ val = occ_get_powr_avg(get_unaligned_be64(&power->proc.accumulator),
+ get_unaligned_be32(&power->proc.update_tag));
break;
case 6:
val = (u64)get_unaligned_be32(&power->proc.update_tag) *
@@ -555,8 +553,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
return sysfs_emit(buf, "%u_vdd\n",
get_unaligned_be32(&power->sensor_id));
case 9:
- val = occ_get_powr_avg(&power->vdd.accumulator,
- &power->vdd.update_tag);
+ val = occ_get_powr_avg(get_unaligned_be64(&power->vdd.accumulator),
+ get_unaligned_be32(&power->vdd.update_tag));
break;
case 10:
val = (u64)get_unaligned_be32(&power->vdd.update_tag) *
@@ -569,8 +567,8 @@ static ssize_t occ_show_power_a0(struct device *dev,
return sysfs_emit(buf, "%u_vdn\n",
get_unaligned_be32(&power->sensor_id));
case 13:
- val = occ_get_powr_avg(&power->vdn.accumulator,
- &power->vdn.update_tag);
+ val = occ_get_powr_avg(get_unaligned_be64(&power->vdn.accumulator),
+ get_unaligned_be32(&power->vdn.update_tag));
break;
case 14:
val = (u64)get_unaligned_be32(&power->vdn.update_tag) *
@@ -747,29 +745,30 @@ static ssize_t occ_show_extended(struct device *dev,
}
/*
- * Some helper macros to make it easier to define an occ_attribute. Since these
- * are dynamically allocated, we shouldn't use the existing kernel macros which
+ * A helper to make it easier to define an occ_attribute. Since these
+ * are dynamically allocated, we cannot use the existing kernel macros which
* stringify the name argument.
*/
-#define ATTR_OCC(_name, _mode, _show, _store) { \
- .attr = { \
- .name = _name, \
- .mode = VERIFY_OCTAL_PERMISSIONS(_mode), \
- }, \
- .show = _show, \
- .store = _store, \
-}
-
-#define SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index) { \
- .dev_attr = ATTR_OCC(_name, _mode, _show, _store), \
- .index = _index, \
- .nr = _nr, \
+static void occ_init_attribute(struct occ_attribute *attr, int mode,
+ ssize_t (*show)(struct device *dev, struct device_attribute *attr, char *buf),
+ ssize_t (*store)(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count),
+ int nr, int index, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ vsnprintf(attr->name, sizeof(attr->name), fmt, args);
+ va_end(args);
+
+ attr->sensor.dev_attr.attr.name = attr->name;
+ attr->sensor.dev_attr.attr.mode = mode;
+ attr->sensor.dev_attr.show = show;
+ attr->sensor.dev_attr.store = store;
+ attr->sensor.index = index;
+ attr->sensor.nr = nr;
}
-#define OCC_INIT_ATTR(_name, _mode, _show, _store, _nr, _index) \
- ((struct sensor_device_attribute_2) \
- SENSOR_ATTR_OCC(_name, _mode, _show, _store, _nr, _index))
-
/*
* Allocate and instatiate sensor_device_attribute_2s. It's most efficient to
* use our own instead of the built-in hwmon attribute types.
@@ -855,14 +854,15 @@ static int occ_setup_sensor_attrs(struct occ *occ)
sensors->extended.num_sensors = 0;
}
- occ->attrs = devm_kzalloc(dev, sizeof(*occ->attrs) * num_attrs,
+ occ->attrs = devm_kcalloc(dev, num_attrs, sizeof(*occ->attrs),
GFP_KERNEL);
if (!occ->attrs)
return -ENOMEM;
/* null-terminated list */
- occ->group.attrs = devm_kzalloc(dev, sizeof(*occ->group.attrs) *
- num_attrs + 1, GFP_KERNEL);
+ occ->group.attrs = devm_kcalloc(dev, num_attrs + 1,
+ sizeof(*occ->group.attrs),
+ GFP_KERNEL);
if (!occ->group.attrs)
return -ENOMEM;
@@ -872,43 +872,33 @@ static int occ_setup_sensor_attrs(struct occ *occ)
s = i + 1;
temp = ((struct temp_sensor_2 *)sensors->temp.data) + i;
- snprintf(attr->name, sizeof(attr->name), "temp%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
- 0, i);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 0, i, "temp%d_label", s);
attr++;
if (sensors->temp.version == 2 &&
temp->fru_type == OCC_FRU_TYPE_VRM) {
- snprintf(attr->name, sizeof(attr->name),
- "temp%d_alarm", s);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 1, i, "temp%d_alarm", s);
} else {
- snprintf(attr->name, sizeof(attr->name),
- "temp%d_input", s);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 1, i, "temp%d_input", s);
}
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_temp, NULL,
- 1, i);
attr++;
if (sensors->temp.version > 1) {
- snprintf(attr->name, sizeof(attr->name),
- "temp%d_fru_type", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_temp, NULL, 2, i);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 2, i, "temp%d_fru_type", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "temp%d_fault", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_temp, NULL, 3, i);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 3, i, "temp%d_fault", s);
attr++;
if (sensors->temp.version == 0x10) {
- snprintf(attr->name, sizeof(attr->name),
- "temp%d_max", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_temp, NULL,
- 4, i);
+ occ_init_attribute(attr, 0444, show_temp, NULL,
+ 4, i, "temp%d_max", s);
attr++;
}
}
@@ -917,14 +907,12 @@ static int occ_setup_sensor_attrs(struct occ *occ)
for (i = 0; i < sensors->freq.num_sensors; ++i) {
s = i + 1;
- snprintf(attr->name, sizeof(attr->name), "freq%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
- 0, i);
+ occ_init_attribute(attr, 0444, show_freq, NULL,
+ 0, i, "freq%d_label", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "freq%d_input", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_freq, NULL,
- 1, i);
+ occ_init_attribute(attr, 0444, show_freq, NULL,
+ 1, i, "freq%d_input", s);
attr++;
}
@@ -940,32 +928,24 @@ static int occ_setup_sensor_attrs(struct occ *occ)
s = (i * 4) + 1;
for (j = 0; j < 4; ++j) {
- snprintf(attr->name, sizeof(attr->name),
- "power%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL,
- nr++, i);
+ occ_init_attribute(attr, 0444, show_power,
+ NULL, nr++, i,
+ "power%d_label", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_average", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL,
- nr++, i);
+ occ_init_attribute(attr, 0444, show_power,
+ NULL, nr++, i,
+ "power%d_average", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_average_interval", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL,
- nr++, i);
+ occ_init_attribute(attr, 0444, show_power,
+ NULL, nr++, i,
+ "power%d_average_interval", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_input", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL,
- nr++, i);
+ occ_init_attribute(attr, 0444, show_power,
+ NULL, nr++, i,
+ "power%d_input", s);
attr++;
s++;
@@ -977,28 +957,20 @@ static int occ_setup_sensor_attrs(struct occ *occ)
for (i = 0; i < sensors->power.num_sensors; ++i) {
s = i + 1;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL, 0, i);
+ occ_init_attribute(attr, 0444, show_power, NULL,
+ 0, i, "power%d_label", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_average", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL, 1, i);
+ occ_init_attribute(attr, 0444, show_power, NULL,
+ 1, i, "power%d_average", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_average_interval", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL, 2, i);
+ occ_init_attribute(attr, 0444, show_power, NULL,
+ 2, i, "power%d_average_interval", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_input", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_power, NULL, 3, i);
+ occ_init_attribute(attr, 0444, show_power, NULL,
+ 3, i, "power%d_input", s);
attr++;
}
@@ -1006,56 +978,43 @@ static int occ_setup_sensor_attrs(struct occ *occ)
}
if (sensors->caps.num_sensors >= 1) {
- snprintf(attr->name, sizeof(attr->name), "power%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 0, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 0, 0, "power%d_label", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "power%d_cap", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 1, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 1, 0, "power%d_cap", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "power%d_input", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 2, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 2, 0, "power%d_input", s);
attr++;
- snprintf(attr->name, sizeof(attr->name),
- "power%d_cap_not_redundant", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 3, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 3, 0, "power%d_cap_not_redundant", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "power%d_cap_max", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 4, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 4, 0, "power%d_cap_max", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "power%d_cap_min", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444, show_caps, NULL,
- 5, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 5, 0, "power%d_cap_min", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "power%d_cap_user",
- s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0644, show_caps,
- occ_store_caps_user, 6, 0);
+ occ_init_attribute(attr, 0644, show_caps, occ_store_caps_user,
+ 6, 0, "power%d_cap_user", s);
attr++;
if (sensors->caps.version > 1) {
- snprintf(attr->name, sizeof(attr->name),
- "power%d_cap_user_source", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_caps, NULL, 7, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 7, 0, "power%d_cap_user_source", s);
attr++;
if (sensors->caps.version > 2) {
- snprintf(attr->name, sizeof(attr->name),
- "power%d_cap_min_soft", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- show_caps, NULL,
- 8, 0);
+ occ_init_attribute(attr, 0444, show_caps, NULL,
+ 8, 0,
+ "power%d_cap_min_soft", s);
attr++;
}
}
@@ -1064,19 +1023,16 @@ static int occ_setup_sensor_attrs(struct occ *occ)
for (i = 0; i < sensors->extended.num_sensors; ++i) {
s = i + 1;
- snprintf(attr->name, sizeof(attr->name), "extn%d_label", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- occ_show_extended, NULL, 0, i);
+ occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+ 0, i, "extn%d_label", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "extn%d_flags", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- occ_show_extended, NULL, 1, i);
+ occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+ 1, i, "extn%d_flags", s);
attr++;
- snprintf(attr->name, sizeof(attr->name), "extn%d_input", s);
- attr->sensor = OCC_INIT_ATTR(attr->name, 0444,
- occ_show_extended, NULL, 2, i);
+ occ_init_attribute(attr, 0444, occ_show_extended, NULL,
+ 2, i, "extn%d_input", s);
attr++;
}
diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index eddf25b90ca8..6544d27e4419 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -619,8 +619,8 @@ static u32 bit_func(struct i2c_adapter *adap)
/* -----exported algorithm data: ------------------------------------- */
const struct i2c_algorithm i2c_bit_algo = {
- .master_xfer = bit_xfer,
- .master_xfer_atomic = bit_xfer_atomic,
+ .xfer = bit_xfer,
+ .xfer_atomic = bit_xfer_atomic,
.functionality = bit_func,
};
EXPORT_SYMBOL(i2c_bit_algo);
diff --git a/drivers/i2c/algos/i2c-algo-pca.c b/drivers/i2c/algos/i2c-algo-pca.c
index 384af88e58ad..74b66aec33d4 100644
--- a/drivers/i2c/algos/i2c-algo-pca.c
+++ b/drivers/i2c/algos/i2c-algo-pca.c
@@ -361,8 +361,8 @@ static u32 pca_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm pca_algo = {
- .master_xfer = pca_xfer,
- .functionality = pca_func,
+ .xfer = pca_xfer,
+ .functionality = pca_func,
};
static unsigned int pca_probe_chip(struct i2c_adapter *adap)
diff --git a/drivers/i2c/algos/i2c-algo-pcf.c b/drivers/i2c/algos/i2c-algo-pcf.c
index 740066ceaea3..fd563e845d4b 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.c
+++ b/drivers/i2c/algos/i2c-algo-pcf.c
@@ -389,8 +389,8 @@ static u32 pcf_func(struct i2c_adapter *adap)
/* exported algorithm data: */
static const struct i2c_algorithm pcf_algo = {
- .master_xfer = pcf_xfer,
- .functionality = pcf_func,
+ .xfer = pcf_xfer,
+ .functionality = pcf_func,
};
/*
diff --git a/drivers/i2c/busses/i2c-amd-mp2-plat.c b/drivers/i2c/busses/i2c-amd-mp2-plat.c
index d9dd0e475d1a..188e24cc4d35 100644
--- a/drivers/i2c/busses/i2c-amd-mp2-plat.c
+++ b/drivers/i2c/busses/i2c-amd-mp2-plat.c
@@ -179,7 +179,7 @@ static u32 i2c_amd_func(struct i2c_adapter *a)
}
static const struct i2c_algorithm i2c_amd_algorithm = {
- .master_xfer = i2c_amd_xfer,
+ .xfer = i2c_amd_xfer,
.functionality = i2c_amd_func,
};
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index 1550d3d552ae..a26b74c71206 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -814,11 +814,11 @@ static int aspeed_i2c_unreg_slave(struct i2c_client *client)
#endif /* CONFIG_I2C_SLAVE */
static const struct i2c_algorithm aspeed_i2c_algo = {
- .master_xfer = aspeed_i2c_master_xfer,
- .functionality = aspeed_i2c_functionality,
+ .xfer = aspeed_i2c_master_xfer,
+ .functionality = aspeed_i2c_functionality,
#if IS_ENABLED(CONFIG_I2C_SLAVE)
- .reg_slave = aspeed_i2c_reg_slave,
- .unreg_slave = aspeed_i2c_unreg_slave,
+ .reg_slave = aspeed_i2c_reg_slave,
+ .unreg_slave = aspeed_i2c_unreg_slave,
#endif /* CONFIG_I2C_SLAVE */
};
diff --git a/drivers/i2c/busses/i2c-at91-master.c b/drivers/i2c/busses/i2c-at91-master.c
index 374fc50bb205..59795c1c24ff 100644
--- a/drivers/i2c/busses/i2c-at91-master.c
+++ b/drivers/i2c/busses/i2c-at91-master.c
@@ -739,8 +739,8 @@ static u32 at91_twi_func(struct i2c_adapter *adapter)
}
static const struct i2c_algorithm at91_twi_algorithm = {
- .master_xfer = at91_twi_xfer,
- .functionality = at91_twi_func,
+ .xfer = at91_twi_xfer,
+ .functionality = at91_twi_func,
};
static int at91_twi_configure_dma(struct at91_twi_dev *dev, u32 phy_addr)
diff --git a/drivers/i2c/busses/i2c-axxia.c b/drivers/i2c/busses/i2c-axxia.c
index 50030256cd85..0555eeb6903a 100644
--- a/drivers/i2c/busses/i2c-axxia.c
+++ b/drivers/i2c/busses/i2c-axxia.c
@@ -706,7 +706,7 @@ static int axxia_i2c_unreg_slave(struct i2c_client *slave)
}
static const struct i2c_algorithm axxia_i2c_algo = {
- .master_xfer = axxia_i2c_xfer,
+ .xfer = axxia_i2c_xfer,
.functionality = axxia_i2c_func,
.reg_slave = axxia_i2c_reg_slave,
.unreg_slave = axxia_i2c_unreg_slave,
diff --git a/drivers/i2c/busses/i2c-bcm-iproc.c b/drivers/i2c/busses/i2c-bcm-iproc.c
index 63bc3c8f49d3..e418a4f23f15 100644
--- a/drivers/i2c/busses/i2c-bcm-iproc.c
+++ b/drivers/i2c/busses/i2c-bcm-iproc.c
@@ -1041,7 +1041,7 @@ static int bcm_iproc_i2c_unreg_slave(struct i2c_client *slave)
}
static struct i2c_algorithm bcm_iproc_algo = {
- .master_xfer = bcm_iproc_i2c_xfer,
+ .xfer = bcm_iproc_i2c_xfer,
.functionality = bcm_iproc_i2c_functionality,
.reg_slave = bcm_iproc_i2c_reg_slave,
.unreg_slave = bcm_iproc_i2c_unreg_slave,
diff --git a/drivers/i2c/busses/i2c-cadence.c b/drivers/i2c/busses/i2c-cadence.c
index 8df63aaf2a80..697d095afbe4 100644
--- a/drivers/i2c/busses/i2c-cadence.c
+++ b/drivers/i2c/busses/i2c-cadence.c
@@ -1231,12 +1231,12 @@ static int cdns_unreg_slave(struct i2c_client *slave)
#endif
static const struct i2c_algorithm cdns_i2c_algo = {
- .master_xfer = cdns_i2c_master_xfer,
- .master_xfer_atomic = cdns_i2c_master_xfer_atomic,
- .functionality = cdns_i2c_func,
+ .xfer = cdns_i2c_master_xfer,
+ .xfer_atomic = cdns_i2c_master_xfer_atomic,
+ .functionality = cdns_i2c_func,
#if IS_ENABLED(CONFIG_I2C_SLAVE)
- .reg_slave = cdns_reg_slave,
- .unreg_slave = cdns_unreg_slave,
+ .reg_slave = cdns_reg_slave,
+ .unreg_slave = cdns_unreg_slave,
#endif
};
diff --git a/drivers/i2c/busses/i2c-cgbc.c b/drivers/i2c/busses/i2c-cgbc.c
index f054d167ac47..25a74fa51aa0 100644
--- a/drivers/i2c/busses/i2c-cgbc.c
+++ b/drivers/i2c/busses/i2c-cgbc.c
@@ -331,8 +331,8 @@ static u32 cgbc_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm cgbc_i2c_algorithm = {
- .master_xfer = cgbc_i2c_xfer,
- .functionality = cgbc_i2c_func,
+ .xfer = cgbc_i2c_xfer,
+ .functionality = cgbc_i2c_func,
};
static struct i2c_algo_cgbc_data cgbc_i2c_algo_data[] = {
diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c
index efdaddf99f9e..27ea3c130a16 100644
--- a/drivers/i2c/busses/i2c-eg20t.c
+++ b/drivers/i2c/busses/i2c-eg20t.c
@@ -690,7 +690,7 @@ static u32 pch_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm pch_algorithm = {
- .master_xfer = pch_i2c_xfer,
+ .xfer = pch_i2c_xfer,
.functionality = pch_i2c_func
};
diff --git a/drivers/i2c/busses/i2c-emev2.c b/drivers/i2c/busses/i2c-emev2.c
index 2512cef8e2a2..ece019b3d066 100644
--- a/drivers/i2c/busses/i2c-emev2.c
+++ b/drivers/i2c/busses/i2c-emev2.c
@@ -351,10 +351,10 @@ static int em_i2c_unreg_slave(struct i2c_client *slave)
}
static const struct i2c_algorithm em_i2c_algo = {
- .master_xfer = em_i2c_xfer,
+ .xfer = em_i2c_xfer,
.functionality = em_i2c_func,
- .reg_slave = em_i2c_reg_slave,
- .unreg_slave = em_i2c_unreg_slave,
+ .reg_slave = em_i2c_reg_slave,
+ .unreg_slave = em_i2c_unreg_slave,
};
static int em_i2c_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-exynos5.c b/drivers/i2c/busses/i2c-exynos5.c
index 02f24479aa07..9c1c5f3c09f6 100644
--- a/drivers/i2c/busses/i2c-exynos5.c
+++ b/drivers/i2c/busses/i2c-exynos5.c
@@ -879,9 +879,9 @@ static u32 exynos5_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm exynos5_i2c_algorithm = {
- .master_xfer = exynos5_i2c_xfer,
- .master_xfer_atomic = exynos5_i2c_xfer_atomic,
- .functionality = exynos5_i2c_func,
+ .xfer = exynos5_i2c_xfer,
+ .xfer_atomic = exynos5_i2c_xfer_atomic,
+ .functionality = exynos5_i2c_func,
};
static int exynos5_i2c_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-gxp.c b/drivers/i2c/busses/i2c-gxp.c
index 0fc39caa6c87..2d117e7e3cb6 100644
--- a/drivers/i2c/busses/i2c-gxp.c
+++ b/drivers/i2c/busses/i2c-gxp.c
@@ -184,11 +184,11 @@ static int gxp_i2c_unreg_slave(struct i2c_client *slave)
#endif
static const struct i2c_algorithm gxp_i2c_algo = {
- .master_xfer = gxp_i2c_master_xfer,
+ .xfer = gxp_i2c_master_xfer,
.functionality = gxp_i2c_func,
#if IS_ENABLED(CONFIG_I2C_SLAVE)
- .reg_slave = gxp_i2c_reg_slave,
- .unreg_slave = gxp_i2c_unreg_slave,
+ .reg_slave = gxp_i2c_reg_slave,
+ .unreg_slave = gxp_i2c_unreg_slave,
#endif
};
diff --git a/drivers/i2c/busses/i2c-img-scb.c b/drivers/i2c/busses/i2c-img-scb.c
index 3278707bb885..a454f9f25146 100644
--- a/drivers/i2c/busses/i2c-img-scb.c
+++ b/drivers/i2c/busses/i2c-img-scb.c
@@ -1143,7 +1143,7 @@ static u32 img_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm img_i2c_algo = {
- .master_xfer = img_i2c_xfer,
+ .xfer = img_i2c_xfer,
.functionality = img_i2c_func,
};
diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c
index 342d47e67586..064bc83840a6 100644
--- a/drivers/i2c/busses/i2c-imx-lpi2c.c
+++ b/drivers/i2c/busses/i2c-imx-lpi2c.c
@@ -1268,10 +1268,10 @@ static u32 lpi2c_imx_func(struct i2c_adapter *adapter)
}
static const struct i2c_algorithm lpi2c_imx_algo = {
- .master_xfer = lpi2c_imx_xfer,
- .functionality = lpi2c_imx_func,
- .reg_target = lpi2c_imx_register_target,
- .unreg_target = lpi2c_imx_unregister_target,
+ .xfer = lpi2c_imx_xfer,
+ .functionality = lpi2c_imx_func,
+ .reg_target = lpi2c_imx_register_target,
+ .unreg_target = lpi2c_imx_unregister_target,
};
static const struct of_device_id lpi2c_imx_of_match[] = {
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index de01dfecb16e..e5732b0557fb 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1692,11 +1692,11 @@ static u32 i2c_imx_func(struct i2c_adapter *adapter)
}
static const struct i2c_algorithm i2c_imx_algo = {
- .master_xfer = i2c_imx_xfer,
- .master_xfer_atomic = i2c_imx_xfer_atomic,
+ .xfer = i2c_imx_xfer,
+ .xfer_atomic = i2c_imx_xfer_atomic,
.functionality = i2c_imx_func,
- .reg_slave = i2c_imx_reg_slave,
- .unreg_slave = i2c_imx_unreg_slave,
+ .reg_slave = i2c_imx_reg_slave,
+ .unreg_slave = i2c_imx_unreg_slave,
};
static int i2c_imx_probe(struct platform_device *pdev)
diff --git a/drivers/i2c/busses/i2c-k1.c b/drivers/i2c/busses/i2c-k1.c
index 5965b4cf6220..b68a21fff0b5 100644
--- a/drivers/i2c/busses/i2c-k1.c
+++ b/drivers/i2c/busses/i2c-k1.c
@@ -477,7 +477,7 @@ static int spacemit_i2c_xfer(struct i2c_adapter *adapt, struct i2c_msg *msgs, in
ret = spacemit_i2c_wait_bus_idle(i2c);
if (!ret)
- spacemit_i2c_xfer_msg(i2c);
+ ret = spacemit_i2c_xfer_msg(i2c);
else if (ret < 0)
dev_dbg(i2c->dev, "i2c transfer error: %d\n", ret);
else
diff --git a/drivers/i2c/busses/i2c-keba.c b/drivers/i2c/busses/i2c-keba.c
index 7b9ed2592f5b..9420c8b342b5 100644
--- a/drivers/i2c/busses/i2c-keba.c
+++ b/drivers/i2c/busses/i2c-keba.c
@@ -500,7 +500,7 @@ static u32 ki2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm ki2c_algo = {
- .master_xfer = ki2c_xfer,
+ .xfer = ki2c_xfer,
.functionality = ki2c_func,
};
diff --git a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
index 5ef136c3ecb1..bc0f1a0c8ee1 100644
--- a/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
+++ b/drivers/i2c/busses/i2c-mchp-pci1xxxx.c
@@ -1048,7 +1048,7 @@ static u32 pci1xxxx_i2c_get_funcs(struct i2c_adapter *adap)
}
static const struct i2c_algorithm pci1xxxx_i2c_algo = {
- .master_xfer = pci1xxxx_i2c_xfer,
+ .xfer = pci1xxxx_i2c_xfer,
.functionality = pci1xxxx_i2c_get_funcs,
};
diff --git a/drivers/i2c/busses/i2c-meson.c b/drivers/i2c/busses/i2c-meson.c
index e1d69537353b..0d9032953e48 100644
--- a/drivers/i2c/busses/i2c-meson.c
+++ b/drivers/i2c/busses/i2c-meson.c
@@ -448,8 +448,8 @@ static u32 meson_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm meson_i2c_algorithm = {
- .master_xfer = meson_i2c_xfer,
- .master_xfer_atomic = meson_i2c_xfer_atomic,
+ .xfer = meson_i2c_xfer,
+ .xfer_atomic = meson_i2c_xfer_atomic,
.functionality = meson_i2c_func,
};
diff --git a/drivers/i2c/busses/i2c-microchip-corei2c.c b/drivers/i2c/busses/i2c-microchip-corei2c.c
index 492bf4c34722..f173bda1c98c 100644
--- a/drivers/i2c/busses/i2c-microchip-corei2c.c
+++ b/drivers/i2c/busses/i2c-microchip-corei2c.c
@@ -526,7 +526,7 @@ static int mchp_corei2c_smbus_xfer(struct i2c_adapter *adap, u16 addr, unsigned
}
static const struct i2c_algorithm mchp_corei2c_algo = {
- .master_xfer = mchp_corei2c_xfer,
+ .xfer = mchp_corei2c_xfer,
.functionality = mchp_corei2c_func,
.smbus_xfer = mchp_corei2c_smbus_xfer,
};
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 5bd342047d59..ab456c3717db 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -1342,7 +1342,7 @@ static u32 mtk_i2c_functionality(struct i2c_adapter *adap)
}
static const struct i2c_algorithm mtk_i2c_algorithm = {
- .master_xfer = mtk_i2c_transfer,
+ .xfer = mtk_i2c_transfer,
.functionality = mtk_i2c_functionality,
};
diff --git a/drivers/i2c/busses/i2c-mxs.c b/drivers/i2c/busses/i2c-mxs.c
index ad62d56b2186..08c9091a1e35 100644
--- a/drivers/i2c/busses/i2c-mxs.c
+++ b/drivers/i2c/busses/i2c-mxs.c
@@ -687,7 +687,7 @@ static irqreturn_t mxs_i2c_isr(int this_irq, void *dev_id)
}
static const struct i2c_algorithm mxs_i2c_algo = {
- .master_xfer = mxs_i2c_xfer,
+ .xfer = mxs_i2c_xfer,
.functionality = mxs_i2c_func,
};
diff --git a/drivers/i2c/busses/i2c-nomadik.c b/drivers/i2c/busses/i2c-nomadik.c
index d2877e4cc28d..19b648fc094d 100644
--- a/drivers/i2c/busses/i2c-nomadik.c
+++ b/drivers/i2c/busses/i2c-nomadik.c
@@ -996,8 +996,8 @@ static unsigned int nmk_i2c_functionality(struct i2c_adapter *adap)
}
static const struct i2c_algorithm nmk_i2c_algo = {
- .master_xfer = nmk_i2c_xfer,
- .functionality = nmk_i2c_functionality
+ .xfer = nmk_i2c_xfer,
+ .functionality = nmk_i2c_functionality
};
static void nmk_i2c_of_probe(struct device_node *np,
diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 892e2d2988a7..8b7e15240fb0 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2470,11 +2470,11 @@ static const struct i2c_adapter_quirks npcm_i2c_quirks = {
};
static const struct i2c_algorithm npcm_i2c_algo = {
- .master_xfer = npcm_i2c_master_xfer,
+ .xfer = npcm_i2c_master_xfer,
.functionality = npcm_i2c_functionality,
#if IS_ENABLED(CONFIG_I2C_SLAVE)
- .reg_slave = npcm_i2c_reg_slave,
- .unreg_slave = npcm_i2c_unreg_slave,
+ .reg_slave = npcm_i2c_reg_slave,
+ .unreg_slave = npcm_i2c_unreg_slave,
#endif
};
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 876791d20ed5..f1cc26ac5b80 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1201,9 +1201,9 @@ omap_i2c_isr_thread(int this_irq, void *dev_id)
}
static const struct i2c_algorithm omap_i2c_algo = {
- .master_xfer = omap_i2c_xfer_irq,
- .master_xfer_atomic = omap_i2c_xfer_polling,
- .functionality = omap_i2c_func,
+ .xfer = omap_i2c_xfer_irq,
+ .xfer_atomic = omap_i2c_xfer_polling,
+ .functionality = omap_i2c_func,
};
static const struct i2c_adapter_quirks omap_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c
index 9a1af5bbd604..8daa0008bd05 100644
--- a/drivers/i2c/busses/i2c-pnx.c
+++ b/drivers/i2c/busses/i2c-pnx.c
@@ -580,7 +580,7 @@ static u32 i2c_pnx_func(struct i2c_adapter *adapter)
}
static const struct i2c_algorithm pnx_algorithm = {
- .master_xfer = i2c_pnx_xfer,
+ .xfer = i2c_pnx_xfer,
.functionality = i2c_pnx_func,
};
diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c
index 4415a29f749b..968a8b8794da 100644
--- a/drivers/i2c/busses/i2c-pxa.c
+++ b/drivers/i2c/busses/i2c-pxa.c
@@ -1154,11 +1154,11 @@ static u32 i2c_pxa_functionality(struct i2c_adapter *adap)
}
static const struct i2c_algorithm i2c_pxa_algorithm = {
- .master_xfer = i2c_pxa_xfer,
- .functionality = i2c_pxa_functionality,
+ .xfer = i2c_pxa_xfer,
+ .functionality = i2c_pxa_functionality,
#ifdef CONFIG_I2C_PXA_SLAVE
- .reg_slave = i2c_pxa_slave_reg,
- .unreg_slave = i2c_pxa_slave_unreg,
+ .reg_slave = i2c_pxa_slave_reg,
+ .unreg_slave = i2c_pxa_slave_unreg,
#endif
};
@@ -1244,11 +1244,11 @@ static int i2c_pxa_pio_xfer(struct i2c_adapter *adap,
}
static const struct i2c_algorithm i2c_pxa_pio_algorithm = {
- .master_xfer = i2c_pxa_pio_xfer,
- .functionality = i2c_pxa_functionality,
+ .xfer = i2c_pxa_pio_xfer,
+ .functionality = i2c_pxa_functionality,
#ifdef CONFIG_I2C_PXA_SLAVE
- .reg_slave = i2c_pxa_slave_reg,
- .unreg_slave = i2c_pxa_slave_unreg,
+ .reg_slave = i2c_pxa_slave_reg,
+ .unreg_slave = i2c_pxa_slave_unreg,
#endif
};
diff --git a/drivers/i2c/busses/i2c-qcom-cci.c b/drivers/i2c/busses/i2c-qcom-cci.c
index 05b73326afd4..a3afa11a71a1 100644
--- a/drivers/i2c/busses/i2c-qcom-cci.c
+++ b/drivers/i2c/busses/i2c-qcom-cci.c
@@ -462,8 +462,8 @@ static u32 cci_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm cci_algo = {
- .master_xfer = cci_xfer,
- .functionality = cci_func,
+ .xfer = cci_xfer,
+ .functionality = cci_func,
};
static int cci_enable_clocks(struct cci *cci)
diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
index ccea575fb783..13889f52b6f7 100644
--- a/drivers/i2c/busses/i2c-qcom-geni.c
+++ b/drivers/i2c/busses/i2c-qcom-geni.c
@@ -727,8 +727,8 @@ static u32 geni_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm geni_i2c_algo = {
- .master_xfer = geni_i2c_xfer,
- .functionality = geni_i2c_func,
+ .xfer = geni_i2c_xfer,
+ .functionality = geni_i2c_func,
};
#ifdef CONFIG_ACPI
diff --git a/drivers/i2c/busses/i2c-qup.c b/drivers/i2c/busses/i2c-qup.c
index 3a36d682ed57..6059f585843e 100644
--- a/drivers/i2c/busses/i2c-qup.c
+++ b/drivers/i2c/busses/i2c-qup.c
@@ -1634,13 +1634,13 @@ static u32 qup_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm qup_i2c_algo = {
- .master_xfer = qup_i2c_xfer,
- .functionality = qup_i2c_func,
+ .xfer = qup_i2c_xfer,
+ .functionality = qup_i2c_func,
};
static const struct i2c_algorithm qup_i2c_algo_v2 = {
- .master_xfer = qup_i2c_xfer_v2,
- .functionality = qup_i2c_func,
+ .xfer = qup_i2c_xfer_v2,
+ .functionality = qup_i2c_func,
};
/*
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 5693a38da7b5..d51884ab99f4 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -1084,11 +1084,11 @@ static u32 rcar_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm rcar_i2c_algo = {
- .master_xfer = rcar_i2c_master_xfer,
- .master_xfer_atomic = rcar_i2c_master_xfer_atomic,
- .functionality = rcar_i2c_func,
- .reg_slave = rcar_reg_slave,
- .unreg_slave = rcar_unreg_slave,
+ .xfer = rcar_i2c_master_xfer,
+ .xfer_atomic = rcar_i2c_master_xfer_atomic,
+ .functionality = rcar_i2c_func,
+ .reg_slave = rcar_reg_slave,
+ .unreg_slave = rcar_unreg_slave,
};
static const struct i2c_adapter_quirks rcar_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c
index 0f3cf500df68..f4fa4703acbd 100644
--- a/drivers/i2c/busses/i2c-s3c2410.c
+++ b/drivers/i2c/busses/i2c-s3c2410.c
@@ -800,9 +800,9 @@ static u32 s3c24xx_i2c_func(struct i2c_adapter *adap)
/* i2c bus registration info */
static const struct i2c_algorithm s3c24xx_i2c_algorithm = {
- .master_xfer = s3c24xx_i2c_xfer,
- .master_xfer_atomic = s3c24xx_i2c_xfer_atomic,
- .functionality = s3c24xx_i2c_func,
+ .xfer = s3c24xx_i2c_xfer,
+ .xfer_atomic = s3c24xx_i2c_xfer_atomic,
+ .functionality = s3c24xx_i2c_func,
};
/*
diff --git a/drivers/i2c/busses/i2c-sh7760.c b/drivers/i2c/busses/i2c-sh7760.c
index 620f12596763..43f33988b98f 100644
--- a/drivers/i2c/busses/i2c-sh7760.c
+++ b/drivers/i2c/busses/i2c-sh7760.c
@@ -379,8 +379,8 @@ static u32 sh7760_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm sh7760_i2c_algo = {
- .master_xfer = sh7760_i2c_master_xfer,
- .functionality = sh7760_i2c_func,
+ .xfer = sh7760_i2c_master_xfer,
+ .functionality = sh7760_i2c_func,
};
/* calculate CCR register setting for a desired scl clock. SCL clock is
diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c
index adfcee6c9fdc..dae8967f8749 100644
--- a/drivers/i2c/busses/i2c-sh_mobile.c
+++ b/drivers/i2c/busses/i2c-sh_mobile.c
@@ -740,8 +740,8 @@ static u32 sh_mobile_i2c_func(struct i2c_adapter *adapter)
static const struct i2c_algorithm sh_mobile_i2c_algorithm = {
.functionality = sh_mobile_i2c_func,
- .master_xfer = sh_mobile_i2c_xfer,
- .master_xfer_atomic = sh_mobile_i2c_xfer_atomic,
+ .xfer = sh_mobile_i2c_xfer,
+ .xfer_atomic = sh_mobile_i2c_xfer_atomic,
};
static const struct i2c_adapter_quirks sh_mobile_i2c_quirks = {
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 973a3a8c6d4a..e4aaeb2262d0 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -2151,8 +2151,8 @@ static u32 stm32f7_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm stm32f7_i2c_algo = {
- .master_xfer = stm32f7_i2c_xfer,
- .master_xfer_atomic = stm32f7_i2c_xfer_atomic,
+ .xfer = stm32f7_i2c_xfer,
+ .xfer_atomic = stm32f7_i2c_xfer_atomic,
.smbus_xfer = stm32f7_i2c_smbus_xfer,
.functionality = stm32f7_i2c_func,
.reg_slave = stm32f7_i2c_reg_slave,
diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c
index 31f8d08e32a4..1230f51e1624 100644
--- a/drivers/i2c/busses/i2c-synquacer.c
+++ b/drivers/i2c/busses/i2c-synquacer.c
@@ -520,8 +520,8 @@ static u32 synquacer_i2c_functionality(struct i2c_adapter *adap)
}
static const struct i2c_algorithm synquacer_i2c_algo = {
- .master_xfer = synquacer_i2c_xfer,
- .functionality = synquacer_i2c_functionality,
+ .xfer = synquacer_i2c_xfer,
+ .functionality = synquacer_i2c_functionality,
};
static const struct i2c_adapter synquacer_i2c_ops = {
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 049b4d154c23..0862b98007f5 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -1440,9 +1440,9 @@ static u32 tegra_i2c_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm tegra_i2c_algo = {
- .master_xfer = tegra_i2c_xfer,
- .master_xfer_atomic = tegra_i2c_xfer_atomic,
- .functionality = tegra_i2c_func,
+ .xfer = tegra_i2c_xfer,
+ .xfer_atomic = tegra_i2c_xfer_atomic,
+ .functionality = tegra_i2c_func,
};
/* payload size is only 12 bit */
diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c
index 6bc1575cea6c..607026c921d6 100644
--- a/drivers/i2c/busses/i2c-xiic.c
+++ b/drivers/i2c/busses/i2c-xiic.c
@@ -1398,8 +1398,8 @@ static u32 xiic_func(struct i2c_adapter *adap)
}
static const struct i2c_algorithm xiic_algorithm = {
- .master_xfer = xiic_xfer,
- .master_xfer_atomic = xiic_xfer_atomic,
+ .xfer = xiic_xfer,
+ .xfer_atomic = xiic_xfer_atomic,
.functionality = xiic_func,
};
diff --git a/drivers/i2c/busses/i2c-xlp9xx.c b/drivers/i2c/busses/i2c-xlp9xx.c
index 4d5e49b6321b..ddb1c3e8bc9d 100644
--- a/drivers/i2c/busses/i2c-xlp9xx.c
+++ b/drivers/i2c/busses/i2c-xlp9xx.c
@@ -452,7 +452,7 @@ static u32 xlp9xx_i2c_functionality(struct i2c_adapter *adapter)
}
static const struct i2c_algorithm xlp9xx_i2c_algo = {
- .master_xfer = xlp9xx_i2c_xfer,
+ .xfer = xlp9xx_i2c_xfer,
.functionality = xlp9xx_i2c_functionality,
};
diff --git a/drivers/i2c/i2c-atr.c b/drivers/i2c/i2c-atr.c
index be7d6d41e0b2..dd194476b118 100644
--- a/drivers/i2c/i2c-atr.c
+++ b/drivers/i2c/i2c-atr.c
@@ -738,7 +738,7 @@ struct i2c_atr *i2c_atr_new(struct i2c_adapter *parent, struct device *dev,
atr->flags = flags;
if (parent->algo->master_xfer)
- atr->algo.master_xfer = i2c_atr_master_xfer;
+ atr->algo.xfer = i2c_atr_master_xfer;
if (parent->algo->smbus_xfer)
atr->algo.smbus_xfer = i2c_atr_smbus_xfer;
atr->algo.functionality = i2c_atr_functionality;
diff --git a/drivers/i2c/i2c-mux.c b/drivers/i2c/i2c-mux.c
index fda72e8be885..4d8690981a55 100644
--- a/drivers/i2c/i2c-mux.c
+++ b/drivers/i2c/i2c-mux.c
@@ -293,12 +293,12 @@ int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
*/
if (parent->algo->master_xfer) {
if (muxc->mux_locked)
- priv->algo.master_xfer = i2c_mux_master_xfer;
+ priv->algo.xfer = i2c_mux_master_xfer;
else
- priv->algo.master_xfer = __i2c_mux_master_xfer;
+ priv->algo.xfer = __i2c_mux_master_xfer;
}
if (parent->algo->master_xfer_atomic)
- priv->algo.master_xfer_atomic = priv->algo.master_xfer;
+ priv->algo.xfer_atomic = priv->algo.master_xfer;
if (parent->algo->smbus_xfer) {
if (muxc->mux_locked)
diff --git a/drivers/i2c/muxes/i2c-demux-pinctrl.c b/drivers/i2c/muxes/i2c-demux-pinctrl.c
index 77a740561fd7..f2a1f4744978 100644
--- a/drivers/i2c/muxes/i2c-demux-pinctrl.c
+++ b/drivers/i2c/muxes/i2c-demux-pinctrl.c
@@ -95,9 +95,9 @@ static int i2c_demux_activate_master(struct i2c_demux_pinctrl_priv *priv, u32 ne
priv->cur_chan = new_chan;
/* Now fill out current adapter structure. cur_chan must be up to date */
- priv->algo.master_xfer = i2c_demux_master_xfer;
+ priv->algo.xfer = i2c_demux_master_xfer;
if (adap->algo->master_xfer_atomic)
- priv->algo.master_xfer_atomic = i2c_demux_master_xfer;
+ priv->algo.xfer_atomic = i2c_demux_master_xfer;
priv->algo.functionality = i2c_demux_functionality;
snprintf(priv->cur_adap.name, sizeof(priv->cur_adap.name),
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 8ccb483204fa..73747d20df85 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -152,8 +152,8 @@ static __always_inline int __intel_idle(struct cpuidle_device *dev,
int index, bool irqoff)
{
struct cpuidle_state *state = &drv->states[index];
- unsigned long eax = flg2MWAIT(state->flags);
- unsigned long ecx = 1*irqoff; /* break on interrupt flag */
+ unsigned int eax = flg2MWAIT(state->flags);
+ unsigned int ecx = 1*irqoff; /* break on interrupt flag */
mwait_idle_with_hints(eax, ecx);
@@ -226,9 +226,9 @@ static __cpuidle int intel_idle_xstate(struct cpuidle_device *dev,
static __cpuidle int intel_idle_s2idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
- unsigned long ecx = 1; /* break on interrupt flag */
struct cpuidle_state *state = &drv->states[index];
- unsigned long eax = flg2MWAIT(state->flags);
+ unsigned int eax = flg2MWAIT(state->flags);
+ unsigned int ecx = 1; /* break on interrupt flag */
if (state->flags & CPUIDLE_FLAG_INIT_XSTATE)
fpu_idle_fpregs();
@@ -2507,6 +2507,8 @@ static int __init intel_idle_init(void)
pr_debug("Local APIC timer is reliable in %s\n",
boot_cpu_has(X86_FEATURE_ARAT) ? "all C-states" : "C1");
+ arch_cpu_rescan_dead_smt_siblings();
+
return 0;
hp_setup_fail:
@@ -2518,7 +2520,7 @@ init_driver_fail:
return retval;
}
-device_initcall(intel_idle_init);
+subsys_initcall_sync(intel_idle_init);
/*
* We are not really modular, but we used to support that. Meaning we also
diff --git a/drivers/iommu/tegra-smmu.c b/drivers/iommu/tegra-smmu.c
index 61897d50162d..e58fe9d8b9e7 100644
--- a/drivers/iommu/tegra-smmu.c
+++ b/drivers/iommu/tegra-smmu.c
@@ -559,11 +559,11 @@ static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova,
{
unsigned int pd_index = iova_pd_index(iova);
struct tegra_smmu *smmu = as->smmu;
- struct tegra_pd *pd = as->pd;
+ u32 *pd = &as->pd->val[pd_index];
unsigned long offset = pd_index * sizeof(*pd);
/* Set the page directory entry first */
- pd->val[pd_index] = value;
+ *pd = value;
/* The flush the page directory entry from caches */
dma_sync_single_range_for_device(smmu->dev, as->pd_dma, offset,
diff --git a/drivers/irqchip/irq-ath79-misc.c b/drivers/irqchip/irq-ath79-misc.c
index 268cc18b781f..258b8e9a2d57 100644
--- a/drivers/irqchip/irq-ath79-misc.c
+++ b/drivers/irqchip/irq-ath79-misc.c
@@ -15,6 +15,8 @@
#include <linux/of_address.h>
#include <linux/of_irq.h>
+#include <asm/time.h>
+
#define AR71XX_RESET_REG_MISC_INT_STATUS 0
#define AR71XX_RESET_REG_MISC_INT_ENABLE 4
@@ -177,21 +179,3 @@ static int __init ar7240_misc_intc_of_init(
IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
ar7240_misc_intc_of_init);
-
-void __init ath79_misc_irq_init(void __iomem *regs, int irq,
- int irq_base, bool is_ar71xx)
-{
- struct irq_domain *domain;
-
- if (is_ar71xx)
- ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
- else
- ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
-
- domain = irq_domain_create_legacy(NULL, ATH79_MISC_IRQ_COUNT,
- irq_base, 0, &misc_irq_domain_ops, regs);
- if (!domain)
- panic("Failed to create MISC irqdomain");
-
- ath79_misc_intc_domain_init(domain, irq);
-}
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index d4697e79d5a3..b2d10063d35f 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -5,7 +5,6 @@ config BCACHE
select BLOCK_HOLDER_DEPRECATED if SYSFS
select CRC64
select CLOSURES
- select MIN_HEAP
help
Allows a block device to be used as cache for other devices; uses
a btree for indexing and the layout is optimized for SSDs.
diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c
index 8998e61efa40..48ce750bf70a 100644
--- a/drivers/md/bcache/alloc.c
+++ b/drivers/md/bcache/alloc.c
@@ -164,61 +164,40 @@ static void bch_invalidate_one_bucket(struct cache *ca, struct bucket *b)
* prio is worth 1/8th of what INITIAL_PRIO is worth.
*/
-static inline unsigned int new_bucket_prio(struct cache *ca, struct bucket *b)
-{
- unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8;
-
- return (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b);
-}
-
-static inline bool new_bucket_max_cmp(const void *l, const void *r, void *args)
-{
- struct bucket **lhs = (struct bucket **)l;
- struct bucket **rhs = (struct bucket **)r;
- struct cache *ca = args;
-
- return new_bucket_prio(ca, *lhs) > new_bucket_prio(ca, *rhs);
-}
-
-static inline bool new_bucket_min_cmp(const void *l, const void *r, void *args)
-{
- struct bucket **lhs = (struct bucket **)l;
- struct bucket **rhs = (struct bucket **)r;
- struct cache *ca = args;
+#define bucket_prio(b) \
+({ \
+ unsigned int min_prio = (INITIAL_PRIO - ca->set->min_prio) / 8; \
+ \
+ (b->prio - ca->set->min_prio + min_prio) * GC_SECTORS_USED(b); \
+})
- return new_bucket_prio(ca, *lhs) < new_bucket_prio(ca, *rhs);
-}
+#define bucket_max_cmp(l, r) (bucket_prio(l) < bucket_prio(r))
+#define bucket_min_cmp(l, r) (bucket_prio(l) > bucket_prio(r))
static void invalidate_buckets_lru(struct cache *ca)
{
struct bucket *b;
- const struct min_heap_callbacks bucket_max_cmp_callback = {
- .less = new_bucket_max_cmp,
- .swp = NULL,
- };
- const struct min_heap_callbacks bucket_min_cmp_callback = {
- .less = new_bucket_min_cmp,
- .swp = NULL,
- };
+ ssize_t i;
- ca->heap.nr = 0;
+ ca->heap.used = 0;
for_each_bucket(b, ca) {
if (!bch_can_invalidate_bucket(ca, b))
continue;
- if (!min_heap_full(&ca->heap))
- min_heap_push(&ca->heap, &b, &bucket_max_cmp_callback, ca);
- else if (!new_bucket_max_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+ if (!heap_full(&ca->heap))
+ heap_add(&ca->heap, b, bucket_max_cmp);
+ else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
ca->heap.data[0] = b;
- min_heap_sift_down(&ca->heap, 0, &bucket_max_cmp_callback, ca);
+ heap_sift(&ca->heap, 0, bucket_max_cmp);
}
}
- min_heapify_all(&ca->heap, &bucket_min_cmp_callback, ca);
+ for (i = ca->heap.used / 2 - 1; i >= 0; --i)
+ heap_sift(&ca->heap, i, bucket_min_cmp);
while (!fifo_full(&ca->free_inc)) {
- if (!ca->heap.nr) {
+ if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
/*
* We don't want to be calling invalidate_buckets()
* multiple times when it can't do anything
@@ -227,8 +206,6 @@ static void invalidate_buckets_lru(struct cache *ca)
wake_up_gc(ca->set);
return;
}
- b = min_heap_peek(&ca->heap)[0];
- min_heap_pop(&ca->heap, &bucket_min_cmp_callback, ca);
bch_invalidate_one_bucket(ca, b);
}
diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 785b0d9008fa..1d33e40d26ea 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -458,7 +458,7 @@ struct cache {
/* Allocation stuff: */
struct bucket *buckets;
- DEFINE_MIN_HEAP(struct bucket *, cache_heap) heap;
+ DECLARE_HEAP(struct bucket *, heap);
/*
* If nonzero, we know we aren't going to find any buckets to invalidate
diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index 68258a16e125..463eb13bd0b2 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -54,11 +54,9 @@ void bch_dump_bucket(struct btree_keys *b)
int __bch_count_data(struct btree_keys *b)
{
unsigned int ret = 0;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct bkey *k;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
if (b->ops->is_extents)
for_each_key(b, k, &iter)
ret += KEY_SIZE(k);
@@ -69,11 +67,9 @@ void __bch_check_keys(struct btree_keys *b, const char *fmt, ...)
{
va_list args;
struct bkey *k, *p = NULL;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
const char *err;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
for_each_key(b, k, &iter) {
if (b->ops->is_extents) {
err = "Keys out of order";
@@ -114,9 +110,9 @@ bug:
static void bch_btree_iter_next_check(struct btree_iter *iter)
{
- struct bkey *k = iter->heap.data->k, *next = bkey_next(k);
+ struct bkey *k = iter->data->k, *next = bkey_next(k);
- if (next < iter->heap.data->end &&
+ if (next < iter->data->end &&
bkey_cmp(k, iter->b->ops->is_extents ?
&START_KEY(next) : next) > 0) {
bch_dump_bucket(iter->b);
@@ -883,14 +879,12 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
unsigned int status = BTREE_INSERT_STATUS_NO_INSERT;
struct bset *i = bset_tree_last(b)->data;
struct bkey *m, *prev = NULL;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct bkey preceding_key_on_stack = ZERO_KEY;
struct bkey *preceding_key_p = &preceding_key_on_stack;
BUG_ON(b->ops->is_extents && !KEY_SIZE(k));
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
/*
* If k has preceding key, preceding_key_p will be set to address
* of k's preceding key; otherwise preceding_key_p will be set
@@ -901,9 +895,9 @@ unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
else
preceding_key(k, &preceding_key_p);
- m = bch_btree_iter_init(b, &iter, preceding_key_p);
+ m = bch_btree_iter_stack_init(b, &iter, preceding_key_p);
- if (b->ops->insert_fixup(b, k, &iter, replace_key))
+ if (b->ops->insert_fixup(b, k, &iter.iter, replace_key))
return status;
status = BTREE_INSERT_STATUS_INSERT;
@@ -1083,94 +1077,79 @@ struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
/* Btree iterator */
-typedef bool (new_btree_iter_cmp_fn)(const void *, const void *, void *);
+typedef bool (btree_iter_cmp_fn)(struct btree_iter_set,
+ struct btree_iter_set);
-static inline bool new_btree_iter_cmp(const void *l, const void *r, void __always_unused *args)
+static inline bool btree_iter_cmp(struct btree_iter_set l,
+ struct btree_iter_set r)
{
- const struct btree_iter_set *_l = l;
- const struct btree_iter_set *_r = r;
-
- return bkey_cmp(_l->k, _r->k) <= 0;
+ return bkey_cmp(l.k, r.k) > 0;
}
static inline bool btree_iter_end(struct btree_iter *iter)
{
- return !iter->heap.nr;
+ return !iter->used;
}
void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
struct bkey *end)
{
- const struct min_heap_callbacks callbacks = {
- .less = new_btree_iter_cmp,
- .swp = NULL,
- };
-
if (k != end)
- BUG_ON(!min_heap_push(&iter->heap,
- &((struct btree_iter_set) { k, end }),
- &callbacks,
- NULL));
+ BUG_ON(!heap_add(iter,
+ ((struct btree_iter_set) { k, end }),
+ btree_iter_cmp));
}
-static struct bkey *__bch_btree_iter_init(struct btree_keys *b,
- struct btree_iter *iter,
- struct bkey *search,
- struct bset_tree *start)
+static struct bkey *__bch_btree_iter_stack_init(struct btree_keys *b,
+ struct btree_iter_stack *iter,
+ struct bkey *search,
+ struct bset_tree *start)
{
struct bkey *ret = NULL;
- iter->heap.size = ARRAY_SIZE(iter->heap.preallocated);
- iter->heap.nr = 0;
+ iter->iter.size = ARRAY_SIZE(iter->stack_data);
+ iter->iter.used = 0;
#ifdef CONFIG_BCACHE_DEBUG
- iter->b = b;
+ iter->iter.b = b;
#endif
for (; start <= bset_tree_last(b); start++) {
ret = bch_bset_search(b, start, search);
- bch_btree_iter_push(iter, ret, bset_bkey_last(start->data));
+ bch_btree_iter_push(&iter->iter, ret, bset_bkey_last(start->data));
}
return ret;
}
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
- struct btree_iter *iter,
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+ struct btree_iter_stack *iter,
struct bkey *search)
{
- return __bch_btree_iter_init(b, iter, search, b->set);
+ return __bch_btree_iter_stack_init(b, iter, search, b->set);
}
static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
- new_btree_iter_cmp_fn *cmp)
+ btree_iter_cmp_fn *cmp)
{
struct btree_iter_set b __maybe_unused;
struct bkey *ret = NULL;
- const struct min_heap_callbacks callbacks = {
- .less = cmp,
- .swp = NULL,
- };
if (!btree_iter_end(iter)) {
bch_btree_iter_next_check(iter);
- ret = iter->heap.data->k;
- iter->heap.data->k = bkey_next(iter->heap.data->k);
+ ret = iter->data->k;
+ iter->data->k = bkey_next(iter->data->k);
- if (iter->heap.data->k > iter->heap.data->end) {
+ if (iter->data->k > iter->data->end) {
WARN_ONCE(1, "bset was corrupt!\n");
- iter->heap.data->k = iter->heap.data->end;
+ iter->data->k = iter->data->end;
}
- if (iter->heap.data->k == iter->heap.data->end) {
- if (iter->heap.nr) {
- b = min_heap_peek(&iter->heap)[0];
- min_heap_pop(&iter->heap, &callbacks, NULL);
- }
- }
+ if (iter->data->k == iter->data->end)
+ heap_pop(iter, b, cmp);
else
- min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+ heap_sift(iter, 0, cmp);
}
return ret;
@@ -1178,7 +1157,7 @@ static inline struct bkey *__bch_btree_iter_next(struct btree_iter *iter,
struct bkey *bch_btree_iter_next(struct btree_iter *iter)
{
- return __bch_btree_iter_next(iter, new_btree_iter_cmp);
+ return __bch_btree_iter_next(iter, btree_iter_cmp);
}
@@ -1216,18 +1195,16 @@ static void btree_mergesort(struct btree_keys *b, struct bset *out,
struct btree_iter *iter,
bool fixup, bool remove_stale)
{
+ int i;
struct bkey *k, *last = NULL;
BKEY_PADDED(k) tmp;
bool (*bad)(struct btree_keys *, const struct bkey *) = remove_stale
? bch_ptr_bad
: bch_ptr_invalid;
- const struct min_heap_callbacks callbacks = {
- .less = b->ops->sort_cmp,
- .swp = NULL,
- };
/* Heapify the iterator, using our comparison function */
- min_heapify_all(&iter->heap, &callbacks, NULL);
+ for (i = iter->used / 2 - 1; i >= 0; --i)
+ heap_sift(iter, i, b->ops->sort_cmp);
while (!btree_iter_end(iter)) {
if (b->ops->sort_fixup && fixup)
@@ -1316,11 +1293,10 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
struct bset_sort_state *state)
{
size_t order = b->page_order, keys = 0;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
int oldsize = bch_count_data(b);
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
- __bch_btree_iter_init(b, &iter, NULL, &b->set[start]);
+ __bch_btree_iter_stack_init(b, &iter, NULL, &b->set[start]);
if (start) {
unsigned int i;
@@ -1331,7 +1307,7 @@ void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
order = get_order(__set_bytes(b->set->data, keys));
}
- __btree_sort(b, &iter, start, order, false, state);
+ __btree_sort(b, &iter.iter, start, order, false, state);
EBUG_ON(oldsize >= 0 && bch_count_data(b) != oldsize);
}
@@ -1347,13 +1323,11 @@ void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
struct bset_sort_state *state)
{
uint64_t start_time = local_clock();
- struct btree_iter iter;
-
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
+ struct btree_iter_stack iter;
- bch_btree_iter_init(b, &iter, NULL);
+ bch_btree_iter_stack_init(b, &iter, NULL);
- btree_mergesort(b, new->set->data, &iter, false, true);
+ btree_mergesort(b, new->set->data, &iter.iter, false, true);
bch_time_stats_update(&state->time, start_time);
diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h
index f79441acd4c1..011f6062c4c0 100644
--- a/drivers/md/bcache/bset.h
+++ b/drivers/md/bcache/bset.h
@@ -187,9 +187,8 @@ struct bset_tree {
};
struct btree_keys_ops {
- bool (*sort_cmp)(const void *l,
- const void *r,
- void *args);
+ bool (*sort_cmp)(struct btree_iter_set l,
+ struct btree_iter_set r);
struct bkey *(*sort_fixup)(struct btree_iter *iter,
struct bkey *tmp);
bool (*insert_fixup)(struct btree_keys *b,
@@ -313,17 +312,23 @@ enum {
BTREE_INSERT_STATUS_FRONT_MERGE,
};
-struct btree_iter_set {
- struct bkey *k, *end;
-};
-
/* Btree key iteration */
struct btree_iter {
+ size_t size, used;
#ifdef CONFIG_BCACHE_DEBUG
struct btree_keys *b;
#endif
- MIN_HEAP_PREALLOCATED(struct btree_iter_set, btree_iter_heap, MAX_BSETS) heap;
+ struct btree_iter_set {
+ struct bkey *k, *end;
+ } data[];
+};
+
+/* Fixed-size btree_iter that can be allocated on the stack */
+
+struct btree_iter_stack {
+ struct btree_iter iter;
+ struct btree_iter_set stack_data[MAX_BSETS];
};
typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);
@@ -335,9 +340,9 @@ struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
struct bkey *end);
-struct bkey *bch_btree_iter_init(struct btree_keys *b,
- struct btree_iter *iter,
- struct bkey *search);
+struct bkey *bch_btree_iter_stack_init(struct btree_keys *b,
+ struct btree_iter_stack *iter,
+ struct bkey *search);
struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
const struct bkey *search);
@@ -352,13 +357,14 @@ static inline struct bkey *bch_bset_search(struct btree_keys *b,
return search ? __bch_bset_search(b, t, search) : t->data->start;
}
-#define for_each_key_filter(b, k, iter, filter) \
- for (bch_btree_iter_init((b), (iter), NULL); \
- ((k) = bch_btree_iter_next_filter((iter), (b), filter));)
+#define for_each_key_filter(b, k, stack_iter, filter) \
+ for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+ ((k) = bch_btree_iter_next_filter(&((stack_iter)->iter), (b), \
+ filter));)
-#define for_each_key(b, k, iter) \
- for (bch_btree_iter_init((b), (iter), NULL); \
- ((k) = bch_btree_iter_next(iter));)
+#define for_each_key(b, k, stack_iter) \
+ for (bch_btree_iter_stack_init((b), (stack_iter), NULL); \
+ ((k) = bch_btree_iter_next(&((stack_iter)->iter)));)
/* Sorting */
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 1d0100677357..210b59007d98 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -148,19 +148,19 @@ void bch_btree_node_read_done(struct btree *b)
{
const char *err = "bad btree header";
struct bset *i = btree_bset_first(b);
- struct btree_iter iter;
+ struct btree_iter *iter;
/*
* c->fill_iter can allocate an iterator with more memory space
* than static MAX_BSETS.
* See the comment arount cache_set->fill_iter.
*/
- iter.heap.data = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
- iter.heap.size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
- iter.heap.nr = 0;
+ iter = mempool_alloc(&b->c->fill_iter, GFP_NOIO);
+ iter->size = b->c->cache->sb.bucket_size / b->c->cache->sb.block_size;
+ iter->used = 0;
#ifdef CONFIG_BCACHE_DEBUG
- iter.b = &b->keys;
+ iter->b = &b->keys;
#endif
if (!i->seq)
@@ -198,7 +198,7 @@ void bch_btree_node_read_done(struct btree *b)
if (i != b->keys.set[0].data && !i->keys)
goto err;
- bch_btree_iter_push(&iter, i->start, bset_bkey_last(i));
+ bch_btree_iter_push(iter, i->start, bset_bkey_last(i));
b->written += set_blocks(i, block_bytes(b->c->cache));
}
@@ -210,7 +210,7 @@ void bch_btree_node_read_done(struct btree *b)
if (i->seq == b->keys.set[0].data->seq)
goto err;
- bch_btree_sort_and_fix_extents(&b->keys, &iter, &b->c->sort);
+ bch_btree_sort_and_fix_extents(&b->keys, iter, &b->c->sort);
i = b->keys.set[0].data;
err = "short btree key";
@@ -222,7 +222,7 @@ void bch_btree_node_read_done(struct btree *b)
bch_bset_init_next(&b->keys, write_block(b),
bset_magic(&b->c->cache->sb));
out:
- mempool_free(iter.heap.data, &b->c->fill_iter);
+ mempool_free(iter, &b->c->fill_iter);
return;
err:
set_btree_node_io_error(b);
@@ -1306,11 +1306,9 @@ static bool btree_gc_mark_node(struct btree *b, struct gc_stat *gc)
uint8_t stale = 0;
unsigned int keys = 0, good_keys = 0;
struct bkey *k;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct bset_tree *t;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
gc->nodes++;
for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid) {
@@ -1569,11 +1567,9 @@ static int btree_gc_rewrite_node(struct btree *b, struct btree_op *op,
static unsigned int btree_gc_count_keys(struct btree *b)
{
struct bkey *k;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
unsigned int ret = 0;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
for_each_key_filter(&b->keys, k, &iter, bch_ptr_bad)
ret += bkey_u64s(k);
@@ -1612,18 +1608,18 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
int ret = 0;
bool should_rewrite;
struct bkey *k;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct gc_merge_info r[GC_MERGE_NODES];
struct gc_merge_info *i, *last = r + ARRAY_SIZE(r) - 1;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
- bch_btree_iter_init(&b->keys, &iter, &b->c->gc_done);
+ bch_btree_iter_stack_init(&b->keys, &iter, &b->c->gc_done);
for (i = r; i < r + ARRAY_SIZE(r); i++)
i->b = ERR_PTR(-EINTR);
while (1) {
- k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad);
+ k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+ bch_ptr_bad);
if (k) {
r->b = bch_btree_node_get(b->c, op, k, b->level - 1,
true, b);
@@ -1918,9 +1914,7 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
{
int ret = 0;
struct bkey *k, *p = NULL;
- struct btree_iter iter;
-
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
+ struct btree_iter_stack iter;
for_each_key_filter(&b->keys, k, &iter, bch_ptr_invalid)
bch_initial_mark_key(b->c, b->level, k);
@@ -1928,10 +1922,10 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
bch_initial_mark_key(b->c, b->level + 1, &b->key);
if (b->level) {
- bch_btree_iter_init(&b->keys, &iter, NULL);
+ bch_btree_iter_stack_init(&b->keys, &iter, NULL);
do {
- k = bch_btree_iter_next_filter(&iter, &b->keys,
+ k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
bch_ptr_bad);
if (k) {
btree_node_prefetch(b, k);
@@ -1959,7 +1953,7 @@ static int bch_btree_check_thread(void *arg)
struct btree_check_info *info = arg;
struct btree_check_state *check_state = info->state;
struct cache_set *c = check_state->c;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct bkey *k, *p;
int cur_idx, prev_idx, skip_nr;
@@ -1967,11 +1961,9 @@ static int bch_btree_check_thread(void *arg)
cur_idx = prev_idx = 0;
ret = 0;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
/* root node keys are checked before thread created */
- bch_btree_iter_init(&c->root->keys, &iter, NULL);
- k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+ bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+ k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
BUG_ON(!k);
p = k;
@@ -1989,7 +1981,7 @@ static int bch_btree_check_thread(void *arg)
skip_nr = cur_idx - prev_idx;
while (skip_nr) {
- k = bch_btree_iter_next_filter(&iter,
+ k = bch_btree_iter_next_filter(&iter.iter,
&c->root->keys,
bch_ptr_bad);
if (k)
@@ -2062,11 +2054,9 @@ int bch_btree_check(struct cache_set *c)
int ret = 0;
int i;
struct bkey *k = NULL;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct btree_check_state check_state;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
/* check and mark root node keys */
for_each_key_filter(&c->root->keys, k, &iter, bch_ptr_invalid)
bch_initial_mark_key(c, c->root->level, k);
@@ -2560,12 +2550,11 @@ static int bch_btree_map_nodes_recurse(struct btree *b, struct btree_op *op,
if (b->level) {
struct bkey *k;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
- bch_btree_iter_init(&b->keys, &iter, from);
+ bch_btree_iter_stack_init(&b->keys, &iter, from);
- while ((k = bch_btree_iter_next_filter(&iter, &b->keys,
+ while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
bch_ptr_bad))) {
ret = bcache_btree(map_nodes_recurse, k, b,
op, from, fn, flags);
@@ -2594,12 +2583,12 @@ int bch_btree_map_keys_recurse(struct btree *b, struct btree_op *op,
{
int ret = MAP_CONTINUE;
struct bkey *k;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
- bch_btree_iter_init(&b->keys, &iter, from);
+ bch_btree_iter_stack_init(&b->keys, &iter, from);
- while ((k = bch_btree_iter_next_filter(&iter, &b->keys, bch_ptr_bad))) {
+ while ((k = bch_btree_iter_next_filter(&iter.iter, &b->keys,
+ bch_ptr_bad))) {
ret = !b->level
? fn(op, b, k)
: bcache_btree(map_keys_recurse, k,
diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c
index 4b84fda1530a..d626ffcbecb9 100644
--- a/drivers/md/bcache/extents.c
+++ b/drivers/md/bcache/extents.c
@@ -33,16 +33,15 @@ static void sort_key_next(struct btree_iter *iter,
i->k = bkey_next(i->k);
if (i->k == i->end)
- *i = iter->heap.data[--iter->heap.nr];
+ *i = iter->data[--iter->used];
}
-static bool new_bch_key_sort_cmp(const void *l, const void *r, void *args)
+static bool bch_key_sort_cmp(struct btree_iter_set l,
+ struct btree_iter_set r)
{
- struct btree_iter_set *_l = (struct btree_iter_set *)l;
- struct btree_iter_set *_r = (struct btree_iter_set *)r;
- int64_t c = bkey_cmp(_l->k, _r->k);
+ int64_t c = bkey_cmp(l.k, r.k);
- return !(c ? c > 0 : _l->k < _r->k);
+ return c ? c > 0 : l.k < r.k;
}
static bool __ptr_invalid(struct cache_set *c, const struct bkey *k)
@@ -239,7 +238,7 @@ static bool bch_btree_ptr_insert_fixup(struct btree_keys *bk,
}
const struct btree_keys_ops bch_btree_keys_ops = {
- .sort_cmp = new_bch_key_sort_cmp,
+ .sort_cmp = bch_key_sort_cmp,
.insert_fixup = bch_btree_ptr_insert_fixup,
.key_invalid = bch_btree_ptr_invalid,
.key_bad = bch_btree_ptr_bad,
@@ -256,28 +255,22 @@ const struct btree_keys_ops bch_btree_keys_ops = {
* Necessary for btree_sort_fixup() - if there are multiple keys that compare
* equal in different sets, we have to process them newest to oldest.
*/
-
-static bool new_bch_extent_sort_cmp(const void *l, const void *r, void __always_unused *args)
+static bool bch_extent_sort_cmp(struct btree_iter_set l,
+ struct btree_iter_set r)
{
- struct btree_iter_set *_l = (struct btree_iter_set *)l;
- struct btree_iter_set *_r = (struct btree_iter_set *)r;
- int64_t c = bkey_cmp(&START_KEY(_l->k), &START_KEY(_r->k));
+ int64_t c = bkey_cmp(&START_KEY(l.k), &START_KEY(r.k));
- return !(c ? c > 0 : _l->k < _r->k);
+ return c ? c > 0 : l.k < r.k;
}
static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
struct bkey *tmp)
{
- const struct min_heap_callbacks callbacks = {
- .less = new_bch_extent_sort_cmp,
- .swp = NULL,
- };
- while (iter->heap.nr > 1) {
- struct btree_iter_set *top = iter->heap.data, *i = top + 1;
-
- if (iter->heap.nr > 2 &&
- !new_bch_extent_sort_cmp(&i[0], &i[1], NULL))
+ while (iter->used > 1) {
+ struct btree_iter_set *top = iter->data, *i = top + 1;
+
+ if (iter->used > 2 &&
+ bch_extent_sort_cmp(i[0], i[1]))
i++;
if (bkey_cmp(top->k, &START_KEY(i->k)) <= 0)
@@ -285,7 +278,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
if (!KEY_SIZE(i->k)) {
sort_key_next(iter, i);
- min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+ heap_sift(iter, i - top, bch_extent_sort_cmp);
continue;
}
@@ -295,7 +288,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
else
bch_cut_front(top->k, i->k);
- min_heap_sift_down(&iter->heap, i - top, &callbacks, NULL);
+ heap_sift(iter, i - top, bch_extent_sort_cmp);
} else {
/* can't happen because of comparison func */
BUG_ON(!bkey_cmp(&START_KEY(top->k), &START_KEY(i->k)));
@@ -305,7 +298,7 @@ static struct bkey *bch_extent_sort_fixup(struct btree_iter *iter,
bch_cut_back(&START_KEY(i->k), tmp);
bch_cut_front(i->k, top->k);
- min_heap_sift_down(&iter->heap, 0, &callbacks, NULL);
+ heap_sift(iter, 0, bch_extent_sort_cmp);
return tmp;
} else {
@@ -625,7 +618,7 @@ static bool bch_extent_merge(struct btree_keys *bk,
}
const struct btree_keys_ops bch_extent_keys_ops = {
- .sort_cmp = new_bch_extent_sort_cmp,
+ .sort_cmp = bch_extent_sort_cmp,
.sort_fixup = bch_extent_sort_fixup,
.insert_fixup = bch_extent_insert_fixup,
.key_invalid = bch_extent_invalid,
diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c
index 45ca134cbf02..26a6a535ec32 100644
--- a/drivers/md/bcache/movinggc.c
+++ b/drivers/md/bcache/movinggc.c
@@ -182,19 +182,16 @@ err: if (!IS_ERR_OR_NULL(w->private))
closure_sync(&cl);
}
-static bool new_bucket_cmp(const void *l, const void *r, void __always_unused *args)
+static bool bucket_cmp(struct bucket *l, struct bucket *r)
{
- struct bucket **_l = (struct bucket **)l;
- struct bucket **_r = (struct bucket **)r;
-
- return GC_SECTORS_USED(*_l) >= GC_SECTORS_USED(*_r);
+ return GC_SECTORS_USED(l) < GC_SECTORS_USED(r);
}
static unsigned int bucket_heap_top(struct cache *ca)
{
struct bucket *b;
- return (b = min_heap_peek(&ca->heap)[0]) ? GC_SECTORS_USED(b) : 0;
+ return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0;
}
void bch_moving_gc(struct cache_set *c)
@@ -202,10 +199,6 @@ void bch_moving_gc(struct cache_set *c)
struct cache *ca = c->cache;
struct bucket *b;
unsigned long sectors_to_move, reserve_sectors;
- const struct min_heap_callbacks callbacks = {
- .less = new_bucket_cmp,
- .swp = NULL,
- };
if (!c->copy_gc_enabled)
return;
@@ -216,7 +209,7 @@ void bch_moving_gc(struct cache_set *c)
reserve_sectors = ca->sb.bucket_size *
fifo_used(&ca->free[RESERVE_MOVINGGC]);
- ca->heap.nr = 0;
+ ca->heap.used = 0;
for_each_bucket(b, ca) {
if (GC_MARK(b) == GC_MARK_METADATA ||
@@ -225,31 +218,25 @@ void bch_moving_gc(struct cache_set *c)
atomic_read(&b->pin))
continue;
- if (!min_heap_full(&ca->heap)) {
+ if (!heap_full(&ca->heap)) {
sectors_to_move += GC_SECTORS_USED(b);
- min_heap_push(&ca->heap, &b, &callbacks, NULL);
- } else if (!new_bucket_cmp(&b, min_heap_peek(&ca->heap), ca)) {
+ heap_add(&ca->heap, b, bucket_cmp);
+ } else if (bucket_cmp(b, heap_peek(&ca->heap))) {
sectors_to_move -= bucket_heap_top(ca);
sectors_to_move += GC_SECTORS_USED(b);
ca->heap.data[0] = b;
- min_heap_sift_down(&ca->heap, 0, &callbacks, NULL);
+ heap_sift(&ca->heap, 0, bucket_cmp);
}
}
while (sectors_to_move > reserve_sectors) {
- if (ca->heap.nr) {
- b = min_heap_peek(&ca->heap)[0];
- min_heap_pop(&ca->heap, &callbacks, NULL);
- }
+ heap_pop(&ca->heap, b, bucket_cmp);
sectors_to_move -= GC_SECTORS_USED(b);
}
- while (ca->heap.nr) {
- b = min_heap_peek(&ca->heap)[0];
- min_heap_pop(&ca->heap, &callbacks, NULL);
+ while (heap_pop(&ca->heap, b, bucket_cmp))
SET_GC_MOVE(b, 1);
- }
mutex_unlock(&c->bucket_lock);
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1efb768b2890..2ea490b9d370 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1912,7 +1912,8 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
INIT_LIST_HEAD(&c->btree_cache_freed);
INIT_LIST_HEAD(&c->data_buckets);
- iter_size = ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
+ iter_size = sizeof(struct btree_iter) +
+ ((meta_bucket_pages(sb) * PAGE_SECTORS) / sb->block_size) *
sizeof(struct btree_iter_set);
c->devices = kcalloc(c->nr_uuids, sizeof(void *), GFP_KERNEL);
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index e8f696cb58c0..826b14cae4e5 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -660,9 +660,7 @@ static unsigned int bch_root_usage(struct cache_set *c)
unsigned int bytes = 0;
struct bkey *k;
struct btree *b;
- struct btree_iter iter;
-
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
+ struct btree_iter_stack iter;
goto lock_root;
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index 539454d8e2d0..f61ab1bada6c 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -9,7 +9,6 @@
#include <linux/kernel.h>
#include <linux/sched/clock.h>
#include <linux/llist.h>
-#include <linux/min_heap.h>
#include <linux/ratelimit.h>
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
@@ -31,10 +30,16 @@ struct closure;
#endif
+#define DECLARE_HEAP(type, name) \
+ struct { \
+ size_t size, used; \
+ type *data; \
+ } name
+
#define init_heap(heap, _size, gfp) \
({ \
size_t _bytes; \
- (heap)->nr = 0; \
+ (heap)->used = 0; \
(heap)->size = (_size); \
_bytes = (heap)->size * sizeof(*(heap)->data); \
(heap)->data = kvmalloc(_bytes, (gfp) & GFP_KERNEL); \
@@ -47,6 +52,64 @@ do { \
(heap)->data = NULL; \
} while (0)
+#define heap_swap(h, i, j) swap((h)->data[i], (h)->data[j])
+
+#define heap_sift(h, i, cmp) \
+do { \
+ size_t _r, _j = i; \
+ \
+ for (; _j * 2 + 1 < (h)->used; _j = _r) { \
+ _r = _j * 2 + 1; \
+ if (_r + 1 < (h)->used && \
+ cmp((h)->data[_r], (h)->data[_r + 1])) \
+ _r++; \
+ \
+ if (cmp((h)->data[_r], (h)->data[_j])) \
+ break; \
+ heap_swap(h, _r, _j); \
+ } \
+} while (0)
+
+#define heap_sift_down(h, i, cmp) \
+do { \
+ while (i) { \
+ size_t p = (i - 1) / 2; \
+ if (cmp((h)->data[i], (h)->data[p])) \
+ break; \
+ heap_swap(h, i, p); \
+ i = p; \
+ } \
+} while (0)
+
+#define heap_add(h, d, cmp) \
+({ \
+ bool _r = !heap_full(h); \
+ if (_r) { \
+ size_t _i = (h)->used++; \
+ (h)->data[_i] = d; \
+ \
+ heap_sift_down(h, _i, cmp); \
+ heap_sift(h, _i, cmp); \
+ } \
+ _r; \
+})
+
+#define heap_pop(h, d, cmp) \
+({ \
+ bool _r = (h)->used; \
+ if (_r) { \
+ (d) = (h)->data[0]; \
+ (h)->used--; \
+ heap_swap(h, 0, (h)->used); \
+ heap_sift(h, 0, cmp); \
+ } \
+ _r; \
+})
+
+#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL)
+
+#define heap_full(h) ((h)->used == (h)->size)
+
#define DECLARE_FIFO(type, name) \
struct { \
size_t front, back, size, mask; \
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 453efbbdc8ee..302e75f1fc4b 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -908,16 +908,15 @@ static int bch_dirty_init_thread(void *arg)
struct dirty_init_thrd_info *info = arg;
struct bch_dirty_init_state *state = info->state;
struct cache_set *c = state->c;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct bkey *k, *p;
int cur_idx, prev_idx, skip_nr;
k = p = NULL;
prev_idx = 0;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
- bch_btree_iter_init(&c->root->keys, &iter, NULL);
- k = bch_btree_iter_next_filter(&iter, &c->root->keys, bch_ptr_bad);
+ bch_btree_iter_stack_init(&c->root->keys, &iter, NULL);
+ k = bch_btree_iter_next_filter(&iter.iter, &c->root->keys, bch_ptr_bad);
BUG_ON(!k);
p = k;
@@ -931,7 +930,7 @@ static int bch_dirty_init_thread(void *arg)
skip_nr = cur_idx - prev_idx;
while (skip_nr) {
- k = bch_btree_iter_next_filter(&iter,
+ k = bch_btree_iter_next_filter(&iter.iter,
&c->root->keys,
bch_ptr_bad);
if (k)
@@ -980,13 +979,11 @@ void bch_sectors_dirty_init(struct bcache_device *d)
int i;
struct btree *b = NULL;
struct bkey *k = NULL;
- struct btree_iter iter;
+ struct btree_iter_stack iter;
struct sectors_dirty_init op;
struct cache_set *c = d->c;
struct bch_dirty_init_state state;
- min_heap_init(&iter.heap, NULL, MAX_BSETS);
-
retry_lock:
b = c->root;
rw_lock(0, b, b->level);
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9dfdb63220d7..17157c4216a5 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -517,7 +517,10 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
{
struct iv_lmk_private *lmk = &cc->iv_gen_private.lmk;
SHASH_DESC_ON_STACK(desc, lmk->hash_tfm);
- struct md5_state md5state;
+ union {
+ struct md5_state md5state;
+ u8 state[CRYPTO_MD5_STATESIZE];
+ } u;
__le32 buf[4];
int i, r;
@@ -548,13 +551,13 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv,
return r;
/* No MD5 padding here */
- r = crypto_shash_export(desc, &md5state);
+ r = crypto_shash_export(desc, &u.md5state);
if (r)
return r;
for (i = 0; i < MD5_HASH_WORDS; i++)
- __cpu_to_le32s(&md5state.hash[i]);
- memcpy(iv, &md5state.hash, cc->iv_size);
+ __cpu_to_le32s(&u.md5state.hash[i]);
+ memcpy(iv, &u.md5state.hash, cc->iv_size);
return 0;
}
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index d296770478b2..e8c0a8c6fb51 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2407,7 +2407,7 @@ static int super_init_validation(struct raid_set *rs, struct md_rdev *rdev)
*/
sb_retrieve_failed_devices(sb, failed_devices);
rdev_for_each(r, mddev) {
- if (test_bit(Journal, &rdev->flags) ||
+ if (test_bit(Journal, &r->flags) ||
!r->sb_page)
continue;
sb2 = page_address(r->sb_page);
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 391d81ad960c..8dc4f5c493fc 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -559,7 +559,7 @@ static int mtdchar_blkpg_ioctl(struct mtd_info *mtd,
/* Sanitize user input */
p.devname[BLKPG_DEVNAMELTH - 1] = '\0';
- return mtd_add_partition(mtd, p.devname, p.start, p.length, NULL);
+ return mtd_add_partition(mtd, p.devname, p.start, p.length);
case BLKPG_DEL_PARTITION:
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 429d8c16baf0..5ba9a741f5ac 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -68,13 +68,7 @@ static struct class mtd_class = {
.pm = MTD_CLS_PM_OPS,
};
-static struct class mtd_master_class = {
- .name = "mtd_master",
- .pm = MTD_CLS_PM_OPS,
-};
-
static DEFINE_IDR(mtd_idr);
-static DEFINE_IDR(mtd_master_idr);
/* These are exported solely for the purpose of mtd_blkdevs.c. You
should not use them for _anything_ else */
@@ -89,9 +83,8 @@ EXPORT_SYMBOL_GPL(__mtd_next_device);
static LIST_HEAD(mtd_notifiers);
-#define MTD_MASTER_DEVS 255
+
#define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2)
-static dev_t mtd_master_devt;
/* REVISIT once MTD uses the driver model better, whoever allocates
* the mtd_info will probably want to use the release() hook...
@@ -111,17 +104,6 @@ static void mtd_release(struct device *dev)
device_destroy(&mtd_class, index + 1);
}
-static void mtd_master_release(struct device *dev)
-{
- struct mtd_info *mtd = dev_get_drvdata(dev);
-
- idr_remove(&mtd_master_idr, mtd->index);
- of_node_put(mtd_get_of_node(mtd));
-
- if (mtd_is_partition(mtd))
- release_mtd_partition(mtd);
-}
-
static void mtd_device_release(struct kref *kref)
{
struct mtd_info *mtd = container_of(kref, struct mtd_info, refcnt);
@@ -385,11 +367,6 @@ static const struct device_type mtd_devtype = {
.release = mtd_release,
};
-static const struct device_type mtd_master_devtype = {
- .name = "mtd_master",
- .release = mtd_master_release,
-};
-
static bool mtd_expert_analysis_mode;
#ifdef CONFIG_DEBUG_FS
@@ -657,13 +634,13 @@ exit_parent:
/**
* add_mtd_device - register an MTD device
* @mtd: pointer to new MTD device info structure
- * @partitioned: create partitioned device
*
* Add a device to the list of MTD devices present in the system, and
* notify each currently active MTD 'user' of its arrival. Returns
* zero on success or non-zero on failure.
*/
-int add_mtd_device(struct mtd_info *mtd, bool partitioned)
+
+int add_mtd_device(struct mtd_info *mtd)
{
struct device_node *np = mtd_get_of_node(mtd);
struct mtd_info *master = mtd_get_master(mtd);
@@ -710,17 +687,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
ofidx = -1;
if (np)
ofidx = of_alias_get_id(np, "mtd");
- if (partitioned) {
- if (ofidx >= 0)
- i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
- else
- i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
- } else {
- if (ofidx >= 0)
- i = idr_alloc(&mtd_master_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
- else
- i = idr_alloc(&mtd_master_idr, mtd, 0, 0, GFP_KERNEL);
- }
+ if (ofidx >= 0)
+ i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
+ else
+ i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
if (i < 0) {
error = i;
goto fail_locked;
@@ -768,18 +738,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
/* Caller should have set dev.parent to match the
* physical device, if appropriate.
*/
- if (partitioned) {
- mtd->dev.type = &mtd_devtype;
- mtd->dev.class = &mtd_class;
- mtd->dev.devt = MTD_DEVT(i);
- dev_set_name(&mtd->dev, "mtd%d", i);
- error = dev_set_name(&mtd->dev, "mtd%d", i);
- } else {
- mtd->dev.type = &mtd_master_devtype;
- mtd->dev.class = &mtd_master_class;
- mtd->dev.devt = MKDEV(MAJOR(mtd_master_devt), i);
- error = dev_set_name(&mtd->dev, "mtd_master%d", i);
- }
+ mtd->dev.type = &mtd_devtype;
+ mtd->dev.class = &mtd_class;
+ mtd->dev.devt = MTD_DEVT(i);
+ error = dev_set_name(&mtd->dev, "mtd%d", i);
if (error)
goto fail_devname;
dev_set_drvdata(&mtd->dev, mtd);
@@ -787,7 +749,6 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
of_node_get(mtd_get_of_node(mtd));
error = device_register(&mtd->dev);
if (error) {
- pr_err("mtd: %s device_register fail %d\n", mtd->name, error);
put_device(&mtd->dev);
goto fail_added;
}
@@ -799,13 +760,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
mtd_debugfs_populate(mtd);
- if (partitioned) {
- device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
- "mtd%dro", i);
- }
+ device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
+ "mtd%dro", i);
- pr_debug("mtd: Giving out %spartitioned device %d to %s\n",
- partitioned ? "" : "un-", i, mtd->name);
+ pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name);
/* No need to get a refcount on the module containing
the notifier, since we hold the mtd_table_mutex */
list_for_each_entry(not, &mtd_notifiers, list)
@@ -813,16 +771,13 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
mutex_unlock(&mtd_table_mutex);
- if (partitioned) {
- if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
- if (IS_BUILTIN(CONFIG_MTD)) {
- pr_info("mtd: setting mtd%d (%s) as root device\n",
- mtd->index, mtd->name);
- ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
- } else {
- pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
- mtd->index, mtd->name);
- }
+ if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
+ if (IS_BUILTIN(CONFIG_MTD)) {
+ pr_info("mtd: setting mtd%d (%s) as root device\n", mtd->index, mtd->name);
+ ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
+ } else {
+ pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
+ mtd->index, mtd->name);
}
}
@@ -838,10 +793,7 @@ fail_nvmem_add:
fail_added:
of_node_put(mtd_get_of_node(mtd));
fail_devname:
- if (partitioned)
- idr_remove(&mtd_idr, i);
- else
- idr_remove(&mtd_master_idr, i);
+ idr_remove(&mtd_idr, i);
fail_locked:
mutex_unlock(&mtd_table_mutex);
return error;
@@ -859,14 +811,12 @@ fail_locked:
int del_mtd_device(struct mtd_info *mtd)
{
- struct mtd_notifier *not;
- struct idr *idr;
int ret;
+ struct mtd_notifier *not;
mutex_lock(&mtd_table_mutex);
- idr = mtd->dev.class == &mtd_class ? &mtd_idr : &mtd_master_idr;
- if (idr_find(idr, mtd->index) != mtd) {
+ if (idr_find(&mtd_idr, mtd->index) != mtd) {
ret = -ENODEV;
goto out_error;
}
@@ -1106,7 +1056,6 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
const struct mtd_partition *parts,
int nr_parts)
{
- struct mtd_info *parent;
int ret, err;
mtd_set_dev_defaults(mtd);
@@ -1115,30 +1064,25 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
if (ret)
goto out;
- ret = add_mtd_device(mtd, false);
- if (ret)
- goto out;
-
if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) {
- ret = mtd_add_partition(mtd, mtd->name, 0, MTDPART_SIZ_FULL, &parent);
+ ret = add_mtd_device(mtd);
if (ret)
goto out;
-
- } else {
- parent = mtd;
}
/* Prefer parsed partitions over driver-provided fallback */
- ret = parse_mtd_partitions(parent, types, parser_data);
+ ret = parse_mtd_partitions(mtd, types, parser_data);
if (ret == -EPROBE_DEFER)
goto out;
if (ret > 0)
ret = 0;
else if (nr_parts)
- ret = add_mtd_partitions(parent, parts, nr_parts);
- else if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
- ret = mtd_add_partition(parent, mtd->name, 0, MTDPART_SIZ_FULL, NULL);
+ ret = add_mtd_partitions(mtd, parts, nr_parts);
+ else if (!device_is_registered(&mtd->dev))
+ ret = add_mtd_device(mtd);
+ else
+ ret = 0;
if (ret)
goto out;
@@ -1158,14 +1102,13 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
register_reboot_notifier(&mtd->reboot_notifier);
}
- return 0;
out:
- nvmem_unregister(mtd->otp_user_nvmem);
- nvmem_unregister(mtd->otp_factory_nvmem);
-
- del_mtd_partitions(mtd);
+ if (ret) {
+ nvmem_unregister(mtd->otp_user_nvmem);
+ nvmem_unregister(mtd->otp_factory_nvmem);
+ }
- if (device_is_registered(&mtd->dev)) {
+ if (ret && device_is_registered(&mtd->dev)) {
err = del_mtd_device(mtd);
if (err)
pr_err("Error when deleting MTD device (%d)\n", err);
@@ -1324,7 +1267,8 @@ int __get_mtd_device(struct mtd_info *mtd)
mtd = mtd->parent;
}
- kref_get(&master->refcnt);
+ if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+ kref_get(&master->refcnt);
return 0;
}
@@ -1418,7 +1362,8 @@ void __put_mtd_device(struct mtd_info *mtd)
mtd = parent;
}
- kref_put(&master->refcnt, mtd_device_release);
+ if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+ kref_put(&master->refcnt, mtd_device_release);
module_put(master->owner);
@@ -2585,16 +2530,6 @@ static int __init init_mtd(void)
if (ret)
goto err_reg;
- ret = class_register(&mtd_master_class);
- if (ret)
- goto err_reg2;
-
- ret = alloc_chrdev_region(&mtd_master_devt, 0, MTD_MASTER_DEVS, "mtd_master");
- if (ret < 0) {
- pr_err("unable to allocate char dev region\n");
- goto err_chrdev;
- }
-
mtd_bdi = mtd_bdi_init("mtd");
if (IS_ERR(mtd_bdi)) {
ret = PTR_ERR(mtd_bdi);
@@ -2619,10 +2554,6 @@ out_procfs:
bdi_unregister(mtd_bdi);
bdi_put(mtd_bdi);
err_bdi:
- unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
-err_chrdev:
- class_unregister(&mtd_master_class);
-err_reg2:
class_unregister(&mtd_class);
err_reg:
pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -2636,12 +2567,9 @@ static void __exit cleanup_mtd(void)
if (proc_mtd)
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
- class_unregister(&mtd_master_class);
- unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
bdi_unregister(mtd_bdi);
bdi_put(mtd_bdi);
idr_destroy(&mtd_idr);
- idr_destroy(&mtd_master_idr);
}
module_init(init_mtd);
diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h
index 2258d31c5aa6..b014861a06a6 100644
--- a/drivers/mtd/mtdcore.h
+++ b/drivers/mtd/mtdcore.h
@@ -8,7 +8,7 @@ extern struct mutex mtd_table_mutex;
extern struct backing_dev_info *mtd_bdi;
struct mtd_info *__mtd_next_device(int i);
-int __must_check add_mtd_device(struct mtd_info *mtd, bool partitioned);
+int __must_check add_mtd_device(struct mtd_info *mtd);
int del_mtd_device(struct mtd_info *mtd);
int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
int del_mtd_partitions(struct mtd_info *);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 5a3db36d734e..994e8c51e674 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -86,7 +86,8 @@ static struct mtd_info *allocate_partition(struct mtd_info *parent,
* parent conditional on that option. Note, this is a way to
* distinguish between the parent and its partitions in sysfs.
*/
- child->dev.parent = &parent->dev;
+ child->dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) || mtd_is_partition(parent) ?
+ &parent->dev : parent->dev.parent;
child->dev.of_node = part->of_node;
child->parent = parent;
child->part.offset = part->offset;
@@ -242,7 +243,7 @@ static int mtd_add_partition_attrs(struct mtd_info *new)
}
int mtd_add_partition(struct mtd_info *parent, const char *name,
- long long offset, long long length, struct mtd_info **out)
+ long long offset, long long length)
{
struct mtd_info *master = mtd_get_master(parent);
u64 parent_size = mtd_is_partition(parent) ?
@@ -275,15 +276,12 @@ int mtd_add_partition(struct mtd_info *parent, const char *name,
list_add_tail(&child->part.node, &parent->partitions);
mutex_unlock(&master->master.partitions_lock);
- ret = add_mtd_device(child, true);
+ ret = add_mtd_device(child);
if (ret)
goto err_remove_part;
mtd_add_partition_attrs(child);
- if (out)
- *out = child;
-
return 0;
err_remove_part:
@@ -415,7 +413,7 @@ int add_mtd_partitions(struct mtd_info *parent,
list_add_tail(&child->part.node, &parent->partitions);
mutex_unlock(&master->master.partitions_lock);
- ret = add_mtd_device(child, true);
+ ret = add_mtd_device(child);
if (ret) {
mutex_lock(&master->master.partitions_lock);
list_del(&child->part.node);
@@ -592,6 +590,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
int ret, err = 0;
dev = &master->dev;
+ /* Use parent device (controller) if the top level MTD is not registered */
+ if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) && !mtd_is_partition(master))
+ dev = master->dev.parent;
np = mtd_get_of_node(master);
if (mtd_is_partition(master))
@@ -710,7 +711,6 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
if (ret < 0 && !err)
err = ret;
}
-
return err;
}
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 7099db7a62be..c411fe9be3ef 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1585,6 +1585,7 @@ static void spinand_cleanup(struct spinand_device *spinand)
{
struct nand_device *nand = spinand_to_nand(spinand);
+ nanddev_ecc_engine_cleanup(nand);
nanddev_cleanup(nand);
spinand_manufacturer_cleanup(spinand);
kfree(spinand->databuf);
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 19f8dd4a6370..b7a28f001a38 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -25,7 +25,7 @@
static SPINAND_OP_VARIANTS(read_cache_octal_variants,
SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(0, 2, NULL, 0, 105 * HZ_PER_MHZ),
- SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 86 * HZ_PER_MHZ),
+ SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 162 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(0, 1, NULL, 0, 133 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
@@ -42,11 +42,11 @@ static SPINAND_OP_VARIANTS(update_cache_octal_variants,
static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants,
SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
- SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
+ SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 104 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
- SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
+ SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 104 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
@@ -289,7 +289,7 @@ static const struct spinand_info winbond_spinand_table[] = {
SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
SPINAND_INFO("W35N02JW", /* 1.8V */
SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x22),
- NAND_MEMORG(1, 4096, 128, 64, 512, 10, 2, 1, 1),
+ NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 2, 1),
NAND_ECCREQ(1, 512),
SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants,
&write_cache_octal_variants,
@@ -298,7 +298,7 @@ static const struct spinand_info winbond_spinand_table[] = {
SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
SPINAND_INFO("W35N04JW", /* 1.8V */
SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x23),
- NAND_MEMORG(1, 4096, 128, 64, 512, 10, 4, 1, 1),
+ NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 4, 1),
NAND_ECCREQ(1, 512),
SPINAND_INFO_OP_VARIANTS(&read_cache_octal_variants,
&write_cache_octal_variants,
diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c
index e5c162f8c589..8edaa339d590 100644
--- a/drivers/net/can/m_can/tcan4x5x-core.c
+++ b/drivers/net/can/m_can/tcan4x5x-core.c
@@ -411,10 +411,11 @@ static int tcan4x5x_can_probe(struct spi_device *spi)
priv = cdev_to_priv(mcan_class);
priv->power = devm_regulator_get_optional(&spi->dev, "vsup");
- if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
- ret = -EPROBE_DEFER;
- goto out_m_can_class_free_dev;
- } else {
+ if (IS_ERR(priv->power)) {
+ if (PTR_ERR(priv->power) == -EPROBE_DEFER) {
+ ret = -EPROBE_DEFER;
+ goto out_m_can_class_free_dev;
+ }
priv->power = NULL;
}
diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 862bdccb7439..dc2f4adac9bc 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -2034,9 +2034,6 @@ int b53_br_join(struct dsa_switch *ds, int port, struct dsa_bridge bridge,
b53_get_vlan_entry(dev, pvid, vl);
vl->members &= ~BIT(port);
- if (vl->members == BIT(cpu_port))
- vl->members &= ~BIT(cpu_port);
- vl->untag = vl->members;
b53_set_vlan_entry(dev, pvid, vl);
}
@@ -2115,8 +2112,7 @@ void b53_br_leave(struct dsa_switch *ds, int port, struct dsa_bridge bridge)
}
b53_get_vlan_entry(dev, pvid, vl);
- vl->members |= BIT(port) | BIT(cpu_port);
- vl->untag |= BIT(port) | BIT(cpu_port);
+ vl->members |= BIT(port);
b53_set_vlan_entry(dev, pvid, vl);
}
}
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index a7ec609d64de..06dea3a13e77 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1065,23 +1065,18 @@ static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q)
static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
{
+ int size, index, num_desc = HW_DSCP_NUM;
struct airoha_eth *eth = qdma->eth;
int id = qdma - &eth->qdma[0];
+ u32 status, buf_size;
dma_addr_t dma_addr;
const char *name;
- int size, index;
- u32 status;
-
- size = HW_DSCP_NUM * sizeof(struct airoha_qdma_fwd_desc);
- if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
- return -ENOMEM;
-
- airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
name = devm_kasprintf(eth->dev, GFP_KERNEL, "qdma%d-buf", id);
if (!name)
return -ENOMEM;
+ buf_size = id ? AIROHA_MAX_PACKET_SIZE / 2 : AIROHA_MAX_PACKET_SIZE;
index = of_property_match_string(eth->dev->of_node,
"memory-region-names", name);
if (index >= 0) {
@@ -1099,8 +1094,12 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
rmem = of_reserved_mem_lookup(np);
of_node_put(np);
dma_addr = rmem->base;
+ /* Compute the number of hw descriptors according to the
+ * reserved memory size and the payload buffer size
+ */
+ num_desc = div_u64(rmem->size, buf_size);
} else {
- size = AIROHA_MAX_PACKET_SIZE * HW_DSCP_NUM;
+ size = buf_size * num_desc;
if (!dmam_alloc_coherent(eth->dev, size, &dma_addr,
GFP_KERNEL))
return -ENOMEM;
@@ -1108,15 +1107,21 @@ static int airoha_qdma_init_hfwd_queues(struct airoha_qdma *qdma)
airoha_qdma_wr(qdma, REG_FWD_BUF_BASE, dma_addr);
+ size = num_desc * sizeof(struct airoha_qdma_fwd_desc);
+ if (!dmam_alloc_coherent(eth->dev, size, &dma_addr, GFP_KERNEL))
+ return -ENOMEM;
+
+ airoha_qdma_wr(qdma, REG_FWD_DSCP_BASE, dma_addr);
+ /* QDMA0: 2KB. QDMA1: 1KB */
airoha_qdma_rmw(qdma, REG_HW_FWD_DSCP_CFG,
HW_FWD_DSCP_PAYLOAD_SIZE_MASK,
- FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, 0));
+ FIELD_PREP(HW_FWD_DSCP_PAYLOAD_SIZE_MASK, !!id));
airoha_qdma_rmw(qdma, REG_FWD_DSCP_LOW_THR, FWD_DSCP_LOW_THR_MASK,
FIELD_PREP(FWD_DSCP_LOW_THR_MASK, 128));
airoha_qdma_rmw(qdma, REG_LMGR_INIT_CFG,
LMGR_INIT_START | LMGR_SRAM_MODE_MASK |
HW_FWD_DESC_NUM_MASK,
- FIELD_PREP(HW_FWD_DESC_NUM_MASK, HW_DSCP_NUM) |
+ FIELD_PREP(HW_FWD_DESC_NUM_MASK, num_desc) |
LMGR_INIT_START | LMGR_SRAM_MODE_MASK);
return read_poll_timeout(airoha_qdma_rr, status,
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 9067d2fc7706..0e217acfc5ef 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -809,8 +809,10 @@ airoha_ppe_foe_flow_l2_entry_update(struct airoha_ppe *ppe,
int idle;
hwe = airoha_ppe_foe_get_entry(ppe, iter->hash);
- ib1 = READ_ONCE(hwe->ib1);
+ if (!hwe)
+ continue;
+ ib1 = READ_ONCE(hwe->ib1);
state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, ib1);
if (state != AIROHA_FOE_STATE_BIND) {
iter->hash = 0xffff;
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 04187eb40ec6..150c85995cc1 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -614,8 +614,9 @@
RX19_DONE_INT_MASK | RX18_DONE_INT_MASK | \
RX17_DONE_INT_MASK | RX16_DONE_INT_MASK)
-#define RX_DONE_INT_MASK (RX_DONE_HIGH_INT_MASK | RX_DONE_LOW_INT_MASK)
#define RX_DONE_HIGH_OFFSET fls(RX_DONE_HIGH_INT_MASK)
+#define RX_DONE_INT_MASK \
+ ((RX_DONE_HIGH_INT_MASK << RX_DONE_HIGH_OFFSET) | RX_DONE_LOW_INT_MASK)
#define INT_RX2_MASK(_n) \
((RX_NO_CPU_DSCP_HIGH_INT_MASK & (_n)) | \
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 869580b6f70d..ae89a981e052 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2989,6 +2989,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
{
struct bnxt_napi *bnapi = cpr->bnapi;
u32 raw_cons = cpr->cp_raw_cons;
+ bool flush_xdp = false;
u32 cons;
int rx_pkts = 0;
u8 event = 0;
@@ -3042,6 +3043,8 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
else
rc = bnxt_force_rx_discard(bp, cpr, &raw_cons,
&event);
+ if (event & BNXT_REDIRECT_EVENT)
+ flush_xdp = true;
if (likely(rc >= 0))
rx_pkts += rc;
/* Increment rx_pkts when rc is -ENOMEM to count towards
@@ -3066,7 +3069,7 @@ static int __bnxt_poll_work(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
}
}
- if (event & BNXT_REDIRECT_EVENT) {
+ if (flush_xdp) {
xdp_do_flush();
event &= ~BNXT_REDIRECT_EVENT;
}
@@ -10780,6 +10783,72 @@ void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
bp->num_rss_ctx--;
}
+static bool bnxt_vnic_has_rx_ring(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+ int rxr_id)
+{
+ u16 tbl_size = bnxt_get_rxfh_indir_size(bp->dev);
+ int i, vnic_rx;
+
+ /* Ntuple VNIC always has all the rx rings. Any change of ring id
+ * must be updated because a future filter may use it.
+ */
+ if (vnic->flags & BNXT_VNIC_NTUPLE_FLAG)
+ return true;
+
+ for (i = 0; i < tbl_size; i++) {
+ if (vnic->flags & BNXT_VNIC_RSSCTX_FLAG)
+ vnic_rx = ethtool_rxfh_context_indir(vnic->rss_ctx)[i];
+ else
+ vnic_rx = bp->rss_indir_tbl[i];
+
+ if (rxr_id == vnic_rx)
+ return true;
+ }
+
+ return false;
+}
+
+static int bnxt_set_vnic_mru_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic,
+ u16 mru, int rxr_id)
+{
+ int rc;
+
+ if (!bnxt_vnic_has_rx_ring(bp, vnic, rxr_id))
+ return 0;
+
+ if (mru) {
+ rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
+ if (rc) {
+ netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
+ vnic->vnic_id, rc);
+ return rc;
+ }
+ }
+ vnic->mru = mru;
+ bnxt_hwrm_vnic_update(bp, vnic,
+ VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+ return 0;
+}
+
+static int bnxt_set_rss_ctx_vnic_mru(struct bnxt *bp, u16 mru, int rxr_id)
+{
+ struct ethtool_rxfh_context *ctx;
+ unsigned long context;
+ int rc;
+
+ xa_for_each(&bp->dev->ethtool->rss_ctx, context, ctx) {
+ struct bnxt_rss_ctx *rss_ctx = ethtool_rxfh_context_priv(ctx);
+ struct bnxt_vnic_info *vnic = &rss_ctx->vnic;
+
+ rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, rxr_id);
+ if (rc)
+ return rc;
+ }
+
+ return 0;
+}
+
static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
{
bool set_tpa = !!(bp->flags & BNXT_FLAG_TPA);
@@ -15927,6 +15996,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
struct bnxt_vnic_info *vnic;
struct bnxt_napi *bnapi;
int i, rc;
+ u16 mru;
rxr = &bp->rx_ring[idx];
clone = qmem;
@@ -15977,21 +16047,15 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
napi_enable_locked(&bnapi->napi);
bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
+ mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
for (i = 0; i < bp->nr_vnics; i++) {
vnic = &bp->vnic_info[i];
- rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
- if (rc) {
- netdev_err(bp->dev, "hwrm vnic %d set rss failure rc: %d\n",
- vnic->vnic_id, rc);
+ rc = bnxt_set_vnic_mru_p5(bp, vnic, mru, idx);
+ if (rc)
return rc;
- }
- vnic->mru = bp->dev->mtu + ETH_HLEN + VLAN_HLEN;
- bnxt_hwrm_vnic_update(bp, vnic,
- VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
}
-
- return 0;
+ return bnxt_set_rss_ctx_vnic_mru(bp, mru, idx);
err_reset:
netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
@@ -16013,10 +16077,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
for (i = 0; i < bp->nr_vnics; i++) {
vnic = &bp->vnic_info[i];
- vnic->mru = 0;
- bnxt_hwrm_vnic_update(bp, vnic,
- VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
+
+ bnxt_set_vnic_mru_p5(bp, vnic, 0, idx);
}
+ bnxt_set_rss_ctx_vnic_mru(bp, 0, idx);
/* Make sure NAPI sees that the VNIC is disabled */
synchronize_net();
rxr = &bp->rx_ring[idx];
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 84c4812414fd..2450a369b792 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -231,10 +231,9 @@ void bnxt_ulp_stop(struct bnxt *bp)
return;
mutex_lock(&edev->en_dev_lock);
- if (!bnxt_ulp_registered(edev)) {
- mutex_unlock(&edev->en_dev_lock);
- return;
- }
+ if (!bnxt_ulp_registered(edev) ||
+ (edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+ goto ulp_stop_exit;
edev->flags |= BNXT_EN_FLAG_ULP_STOPPED;
if (aux_priv) {
@@ -250,6 +249,7 @@ void bnxt_ulp_stop(struct bnxt *bp)
adrv->suspend(adev, pm);
}
}
+ulp_stop_exit:
mutex_unlock(&edev->en_dev_lock);
}
@@ -258,19 +258,13 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
struct bnxt_aux_priv *aux_priv = bp->aux_priv;
struct bnxt_en_dev *edev = bp->edev;
- if (!edev)
- return;
-
- edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
-
- if (err)
+ if (!edev || err)
return;
mutex_lock(&edev->en_dev_lock);
- if (!bnxt_ulp_registered(edev)) {
- mutex_unlock(&edev->en_dev_lock);
- return;
- }
+ if (!bnxt_ulp_registered(edev) ||
+ !(edev->flags & BNXT_EN_FLAG_ULP_STOPPED))
+ goto ulp_start_exit;
if (edev->ulp_tbl->msix_requested)
bnxt_fill_msix_vecs(bp, edev->msix_entries);
@@ -287,6 +281,8 @@ void bnxt_ulp_start(struct bnxt *bp, int err)
adrv->resume(adev);
}
}
+ulp_start_exit:
+ edev->flags &= ~BNXT_EN_FLAG_ULP_STOPPED;
mutex_unlock(&edev->en_dev_lock);
}
diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig
index c699bd6bcbb9..474073c7f94d 100644
--- a/drivers/net/ethernet/faraday/Kconfig
+++ b/drivers/net/ethernet/faraday/Kconfig
@@ -31,6 +31,7 @@ config FTGMAC100
depends on ARM || COMPILE_TEST
depends on !64BIT || BROKEN
select PHYLIB
+ select FIXED_PHY
select MDIO_ASPEED if MACH_ASPEED_G6
select CRC32
help
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
index e917132d3714..54b0f0a5a6bb 100644
--- a/drivers/net/ethernet/freescale/enetc/Kconfig
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
config FSL_ENETC_CORE
tristate
+ select NXP_NETC_LIB if NXP_NTMP
help
This module supports common functionality between the PF and VF
drivers for the NXP ENETC controller.
@@ -22,6 +23,9 @@ config NXP_NETC_LIB
Switch, such as NETC Table Management Protocol (NTMP) 2.0, common tc
flower and debugfs interfaces and so on.
+config NXP_NTMP
+ bool
+
config FSL_ENETC
tristate "ENETC PF driver"
depends on PCI_MSI
@@ -45,7 +49,7 @@ config NXP_ENETC4
select FSL_ENETC_CORE
select FSL_ENETC_MDIO
select NXP_ENETC_PF_COMMON
- select NXP_NETC_LIB
+ select NXP_NTMP
select PHYLINK
select DIMLIB
help
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
index 4098f01479bc..53e8d18c7a34 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -507,7 +507,7 @@ static inline u64 _enetc_rd_reg64(void __iomem *reg)
tmp = ioread32(reg + 4);
} while (high != tmp);
- return le64_to_cpu((__le64)high << 32 | low);
+ return (u64)high << 32 | low;
}
#endif
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3f089c3d47b2..d8595e84326d 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -477,10 +477,6 @@ static void e1000_down_and_stop(struct e1000_adapter *adapter)
cancel_delayed_work_sync(&adapter->phy_info_task);
cancel_delayed_work_sync(&adapter->fifo_stall_task);
-
- /* Only kill reset task if adapter is not resetting */
- if (!test_bit(__E1000_RESETTING, &adapter->flags))
- cancel_work_sync(&adapter->reset_task);
}
void e1000_down(struct e1000_adapter *adapter)
@@ -1266,6 +1262,10 @@ static void e1000_remove(struct pci_dev *pdev)
unregister_netdev(netdev);
+ /* Only kill reset task if adapter is not resetting */
+ if (!test_bit(__E1000_RESETTING, &adapter->flags))
+ cancel_work_sync(&adapter->reset_task);
+
e1000_phy_hw_reset(hw);
kfree(adapter->tx_ring);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index a96f4cfa6e17..7719e15813ee 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -3534,9 +3534,6 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
case e1000_pch_cnp:
case e1000_pch_tgp:
case e1000_pch_adp:
- case e1000_pch_mtp:
- case e1000_pch_lnp:
- case e1000_pch_ptp:
case e1000_pch_nvp:
if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
/* Stable 24MHz frequency */
@@ -3552,6 +3549,17 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca)
adapter->cc.shift = shift;
}
break;
+ case e1000_pch_mtp:
+ case e1000_pch_lnp:
+ case e1000_pch_ptp:
+ /* System firmware can misreport this value, so set it to a
+ * stable 38400KHz frequency.
+ */
+ incperiod = INCPERIOD_38400KHZ;
+ incvalue = INCVALUE_38400KHZ;
+ shift = INCVALUE_SHIFT_38400KHZ;
+ adapter->cc.shift = shift;
+ break;
case e1000_82574:
case e1000_82583:
/* Stable 25MHz frequency */
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 89d57dd911dc..ea3c3eb2ef20 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -295,15 +295,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
case e1000_pch_cnp:
case e1000_pch_tgp:
case e1000_pch_adp:
- case e1000_pch_mtp:
- case e1000_pch_lnp:
- case e1000_pch_ptp:
case e1000_pch_nvp:
if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
else
adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
break;
+ case e1000_pch_mtp:
+ case e1000_pch_lnp:
+ case e1000_pch_ptp:
+ adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
+ break;
case e1000_82574:
case e1000_82583:
adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 1120f8e4bb67..88e6bef69342 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1546,8 +1546,8 @@ static void i40e_cleanup_reset_vf(struct i40e_vf *vf)
* @vf: pointer to the VF structure
* @flr: VFLR was issued or not
*
- * Returns true if the VF is in reset, resets successfully, or resets
- * are disabled and false otherwise.
+ * Return: True if reset was performed successfully or if resets are disabled.
+ * False if reset is already in progress.
**/
bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
{
@@ -1566,7 +1566,7 @@ bool i40e_reset_vf(struct i40e_vf *vf, bool flr)
/* 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;
+ return false;
i40e_trigger_vf_reset(vf, flr);
@@ -4328,7 +4328,10 @@ int i40e_vc_process_vflr_event(struct i40e_pf *pf)
reg = rd32(hw, I40E_GLGEN_VFLRSTAT(reg_idx));
if (reg & BIT(bit_idx))
/* i40e_reset_vf will clear the bit in GLGEN_VFLRSTAT */
- i40e_reset_vf(vf, true);
+ if (!i40e_reset_vf(vf, true)) {
+ /* At least one VF did not finish resetting, retry next time */
+ set_bit(__I40E_VFLR_EVENT_PENDING, pf->state);
+ }
}
return 0;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2c0bb41809a4..81d7249d1149 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3209,6 +3209,17 @@ static void iavf_reset_task(struct work_struct *work)
}
continue_reset:
+ /* If we are still early in the state machine, just restart. */
+ if (adapter->state <= __IAVF_INIT_FAILED) {
+ iavf_shutdown_adminq(hw);
+ iavf_change_state(adapter, __IAVF_STARTUP);
+ iavf_startup(adapter);
+ queue_delayed_work(adapter->wq, &adapter->watchdog_task,
+ msecs_to_jiffies(30));
+ netdev_unlock(netdev);
+ return;
+ }
+
/* We don't use netif_running() because it may be true prior to
* ndo_open() returning, so we can't assume it means all our open
* tasks have finished, since we're not holding the rtnl_lock here.
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index a6f0e5990be2..07f0d0a0f1e2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -79,6 +79,23 @@ iavf_poll_virtchnl_msg(struct iavf_hw *hw, struct iavf_arq_event_info *event,
return iavf_status_to_errno(status);
received_op =
(enum virtchnl_ops)le32_to_cpu(event->desc.cookie_high);
+
+ if (received_op == VIRTCHNL_OP_EVENT) {
+ struct iavf_adapter *adapter = hw->back;
+ struct virtchnl_pf_event *vpe =
+ (struct virtchnl_pf_event *)event->msg_buf;
+
+ if (vpe->event != VIRTCHNL_EVENT_RESET_IMPENDING)
+ continue;
+
+ dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n");
+ if (!(adapter->flags & IAVF_FLAG_RESET_PENDING))
+ iavf_schedule_reset(adapter,
+ IAVF_FLAG_RESET_PENDING);
+
+ return -EIO;
+ }
+
if (op_to_poll == received_op)
break;
}
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 2bc5c7f59844..1f7834c03550 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -378,6 +378,50 @@ ice_arfs_is_perfect_flow_set(struct ice_hw *hw, __be16 l3_proto, u8 l4_proto)
}
/**
+ * ice_arfs_cmp - Check if aRFS filter matches this flow.
+ * @fltr_info: filter info of the saved ARFS entry.
+ * @fk: flow dissector keys.
+ * @n_proto: One of htons(ETH_P_IP) or htons(ETH_P_IPV6).
+ * @ip_proto: One of IPPROTO_TCP or IPPROTO_UDP.
+ *
+ * Since this function assumes limited values for n_proto and ip_proto, it
+ * is meant to be called only from ice_rx_flow_steer().
+ *
+ * Return:
+ * * true - fltr_info refers to the same flow as fk.
+ * * false - fltr_info and fk refer to different flows.
+ */
+static bool
+ice_arfs_cmp(const struct ice_fdir_fltr *fltr_info, const struct flow_keys *fk,
+ __be16 n_proto, u8 ip_proto)
+{
+ /* Determine if the filter is for IPv4 or IPv6 based on flow_type,
+ * which is one of ICE_FLTR_PTYPE_NONF_IPV{4,6}_{TCP,UDP}.
+ */
+ bool is_v4 = fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_TCP ||
+ fltr_info->flow_type == ICE_FLTR_PTYPE_NONF_IPV4_UDP;
+
+ /* Following checks are arranged in the quickest and most discriminative
+ * fields first for early failure.
+ */
+ if (is_v4)
+ return n_proto == htons(ETH_P_IP) &&
+ fltr_info->ip.v4.src_port == fk->ports.src &&
+ fltr_info->ip.v4.dst_port == fk->ports.dst &&
+ fltr_info->ip.v4.src_ip == fk->addrs.v4addrs.src &&
+ fltr_info->ip.v4.dst_ip == fk->addrs.v4addrs.dst &&
+ fltr_info->ip.v4.proto == ip_proto;
+
+ return fltr_info->ip.v6.src_port == fk->ports.src &&
+ fltr_info->ip.v6.dst_port == fk->ports.dst &&
+ fltr_info->ip.v6.proto == ip_proto &&
+ !memcmp(&fltr_info->ip.v6.src_ip, &fk->addrs.v6addrs.src,
+ sizeof(struct in6_addr)) &&
+ !memcmp(&fltr_info->ip.v6.dst_ip, &fk->addrs.v6addrs.dst,
+ sizeof(struct in6_addr));
+}
+
+/**
* ice_rx_flow_steer - steer the Rx flow to where application is being run
* @netdev: ptr to the netdev being adjusted
* @skb: buffer with required header information
@@ -448,6 +492,10 @@ ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
continue;
fltr_info = &arfs_entry->fltr_info;
+
+ if (!ice_arfs_cmp(fltr_info, &fk, n_proto, ip_proto))
+ continue;
+
ret = fltr_info->fltr_id;
if (fltr_info->q_index == rxq_idx ||
diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index 6aae03771746..2e4f0969035f 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -508,10 +508,14 @@ err_create_repr:
*/
int ice_eswitch_attach_vf(struct ice_pf *pf, struct ice_vf *vf)
{
- struct ice_repr *repr = ice_repr_create_vf(vf);
struct devlink *devlink = priv_to_devlink(pf);
+ struct ice_repr *repr;
int err;
+ if (!ice_is_eswitch_mode_switchdev(pf))
+ return 0;
+
+ repr = ice_repr_create_vf(vf);
if (IS_ERR(repr))
return PTR_ERR(repr);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index b79a148ed0f2..55cad824c5b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2299,6 +2299,7 @@ static int ice_capture_crosststamp(ktime_t *device,
ts = ((u64)ts_hi << 32) | ts_lo;
system->cycles = ts;
system->cs_id = CSID_X86_ART;
+ system->use_nsecs = true;
/* Read Device source clock time */
ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 6f572589f1e5..6b5c9536d26d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1822,7 +1822,7 @@ int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable)
req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
req->bpid_per_chan = 1;
} else {
- req->chan_cnt = 1;
+ req->chan_cnt = pfvf->hw.rx_chan_cnt;
req->bpid_per_chan = 0;
}
@@ -1847,7 +1847,7 @@ int otx2_nix_cpt_config_bp(struct otx2_nic *pfvf, bool enable)
req->chan_cnt = IEEE_8021QAZ_MAX_TCS;
req->bpid_per_chan = 1;
} else {
- req->chan_cnt = 1;
+ req->chan_cnt = pfvf->hw.rx_chan_cnt;
req->bpid_per_chan = 0;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ea078c9f5d15..3cb8d3bf9044 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -43,7 +43,6 @@
#include "en/fs_ethtool.h"
#define LANES_UNKNOWN 0
-#define MAX_LANES 8
void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
struct ethtool_drvinfo *drvinfo)
@@ -1098,10 +1097,8 @@ static void get_link_properties(struct net_device *netdev,
speed = info->speed;
lanes = info->lanes;
duplex = DUPLEX_FULL;
- } else if (data_rate_oper) {
+ } else if (data_rate_oper)
speed = 100 * data_rate_oper;
- lanes = MAX_LANES;
- }
out:
link_ksettings->base.duplex = duplex;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f1d908f61134..fef418e1ed1a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2028,9 +2028,8 @@ err_out:
return err;
}
-static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow)
+static bool mlx5_flow_has_geneve_opt(struct mlx5_flow_spec *spec)
{
- struct mlx5_flow_spec *spec = &flow->attr->parse_attr->spec;
void *headers_v = MLX5_ADDR_OF(fte_match_param,
spec->match_value,
misc_parameters_3);
@@ -2069,7 +2068,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
}
complete_all(&flow->del_hw_done);
- if (mlx5_flow_has_geneve_opt(flow))
+ if (mlx5_flow_has_geneve_opt(&attr->parse_attr->spec))
mlx5_geneve_tlv_option_del(priv->mdev->geneve);
if (flow->decap_route)
@@ -2574,12 +2573,13 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
err = mlx5e_tc_tun_parse(filter_dev, priv, tmp_spec, f, match_level);
if (err) {
- kvfree(tmp_spec);
NL_SET_ERR_MSG_MOD(extack, "Failed to parse tunnel attributes");
netdev_warn(priv->netdev, "Failed to parse tunnel attributes");
- return err;
+ } else {
+ err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
}
- err = mlx5e_tc_set_attr_rx_tun(flow, tmp_spec);
+ if (mlx5_flow_has_geneve_opt(tmp_spec))
+ mlx5_geneve_tlv_option_del(priv->mdev->geneve);
kvfree(tmp_spec);
if (err)
return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 7fb8a3381f84..4917d185d0c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1295,12 +1295,15 @@ mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
ret = mlx5_eswitch_load_pf_vf_vport(esw, MLX5_VPORT_ECPF, enabled_events);
if (ret)
goto ecpf_err;
- if (mlx5_core_ec_sriov_enabled(esw->dev)) {
- ret = mlx5_eswitch_load_ec_vf_vports(esw, esw->esw_funcs.num_ec_vfs,
- enabled_events);
- if (ret)
- goto ec_vf_err;
- }
+ }
+
+ /* Enable ECVF vports */
+ if (mlx5_core_ec_sriov_enabled(esw->dev)) {
+ ret = mlx5_eswitch_load_ec_vf_vports(esw,
+ esw->esw_funcs.num_ec_vfs,
+ enabled_events);
+ if (ret)
+ goto ec_vf_err;
}
/* Enable VF vports */
@@ -1331,9 +1334,11 @@ void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw)
{
mlx5_eswitch_unload_vf_vports(esw, esw->esw_funcs.num_vfs);
+ if (mlx5_core_ec_sriov_enabled(esw->dev))
+ mlx5_eswitch_unload_ec_vf_vports(esw,
+ esw->esw_funcs.num_ec_vfs);
+
if (mlx5_ecpf_vport_exists(esw->dev)) {
- if (mlx5_core_ec_sriov_enabled(esw->dev))
- mlx5_eswitch_unload_ec_vf_vports(esw, esw->esw_funcs.num_vfs);
mlx5_eswitch_unload_pf_vf_vport(esw, MLX5_VPORT_ECPF);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 23a7e8e7adfa..a8046200d376 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -2228,6 +2228,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
struct mlx5_flow_handle *rule;
struct match_list *iter;
bool take_write = false;
+ bool try_again = false;
struct fs_fte *fte;
u64 version = 0;
int err;
@@ -2292,6 +2293,7 @@ skip_search:
nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
if (!g->node.active) {
+ try_again = true;
up_write_ref_node(&g->node, false);
continue;
}
@@ -2313,7 +2315,8 @@ skip_search:
tree_put_node(&fte->node, false);
return rule;
}
- rule = ERR_PTR(-ENOENT);
+ err = try_again ? -EAGAIN : -ENOENT;
+ rule = ERR_PTR(err);
out:
kmem_cache_free(steering->ftes_cache, fte);
return rule;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index 972e8e9df585..9bc9bd83c232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -291,7 +291,7 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr, u32 function)
static int alloc_system_page(struct mlx5_core_dev *dev, u32 function)
{
struct device *device = mlx5_core_dma_dev(dev);
- int nid = dev_to_node(device);
+ int nid = dev->priv.numa_node;
struct page *page;
u64 zero_addr = 1;
u64 addr;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index fb62f3bc4bd4..447ea3f8722c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -1370,8 +1370,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
struct mlx5hws_cmd_forward_tbl *fw_island;
struct mlx5hws_action *action;
- u32 i /*, packet_reformat_id*/;
- int ret;
+ int ret, last_dest_idx = -1;
+ u32 i;
if (num_dest <= 1) {
mlx5hws_err(ctx, "Action must have multiple dests\n");
@@ -1401,11 +1401,8 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
dest_list[i].destination_id = dests[i].dest->dest_obj.obj_id;
fte_attr.action_flags |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
fte_attr.ignore_flow_level = ignore_flow_level;
- /* ToDo: In SW steering we have a handling of 'go to WIRE'
- * destination here by upper layer setting 'is_wire_ft' flag
- * if the destination is wire.
- * This is because uplink should be last dest in the list.
- */
+ if (dests[i].is_wire_ft)
+ last_dest_idx = i;
break;
case MLX5HWS_ACTION_TYP_VPORT:
dest_list[i].destination_type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
@@ -1429,6 +1426,9 @@ mlx5hws_action_create_dest_array(struct mlx5hws_context *ctx,
}
}
+ if (last_dest_idx != -1)
+ swap(dest_list[last_dest_idx], dest_list[num_dest - 1]);
+
fte_attr.dests_num = num_dest;
fte_attr.dests = dest_list;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index 70768953a4f6..ca7501c57468 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -1070,7 +1070,7 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
struct mlx5hws_bwc_complex_rule_hash_node *node, *old_node;
struct rhashtable *refcount_hash;
- int i;
+ int ret, i;
bwc_rule->complex_hash_node = NULL;
@@ -1078,7 +1078,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
if (unlikely(!node))
return -ENOMEM;
- node->tag = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+ ret = ida_alloc(&bwc_matcher->complex->metadata_ida, GFP_KERNEL);
+ if (ret < 0)
+ goto err_free_node;
+ node->tag = ret;
+
refcount_set(&node->refcount, 1);
/* Clear match buffer - turn off all the unrelated fields
@@ -1094,6 +1098,11 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
old_node = rhashtable_lookup_get_insert_fast(refcount_hash,
&node->hash_node,
hws_refcount_hash);
+ if (IS_ERR(old_node)) {
+ ret = PTR_ERR(old_node);
+ goto err_free_ida;
+ }
+
if (old_node) {
/* Rule with the same tag already exists - update refcount */
refcount_inc(&old_node->refcount);
@@ -1112,6 +1121,12 @@ hws_bwc_rule_complex_hash_node_get(struct mlx5hws_bwc_rule *bwc_rule,
bwc_rule->complex_hash_node = node;
return 0;
+
+err_free_ida:
+ ida_free(&bwc_matcher->complex->metadata_ida, node->tag);
+err_free_node:
+ kfree(node);
+ return ret;
}
static void
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 5cc0dc002ac1..d45e1145d197 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -785,6 +785,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
HWS_SET_HDR(fc, match_param, IP_PROTOCOL_O,
outer_headers.ip_protocol,
eth_l3_outer.protocol_next_header);
+ HWS_SET_HDR(fc, match_param, IP_VERSION_O,
+ outer_headers.ip_version,
+ eth_l3_outer.ip_version);
HWS_SET_HDR(fc, match_param, IP_TTL_O,
outer_headers.ttl_hoplimit,
eth_l3_outer.time_to_live_hop_limit);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 9d1c0e4b224a..bf4643d0ce17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -966,6 +966,9 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
switch (attr->type) {
case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE:
dest_action = mlx5_fs_get_dest_action_ft(fs_ctx, dst);
+ if (dst->dest_attr.ft->flags &
+ MLX5_FLOW_TABLE_UPLINK_VPORT)
+ dest_actions[num_dest_actions].is_wire_ft = true;
break;
case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE_NUM:
dest_action = mlx5_fs_get_dest_action_table_num(fs_ctx,
@@ -1357,6 +1360,7 @@ mlx5_cmd_hws_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns,
pkt_reformat->fs_hws_action.pr_data = pr_data;
}
+ mutex_init(&pkt_reformat->fs_hws_action.lock);
pkt_reformat->owner = MLX5_FLOW_RESOURCE_OWNER_HWS;
pkt_reformat->fs_hws_action.hws_action = hws_action;
return 0;
@@ -1503,7 +1507,6 @@ static int mlx5_cmd_hws_modify_header_alloc(struct mlx5_flow_root_namespace *ns,
err = -ENOMEM;
goto release_mh;
}
- mutex_init(&modify_hdr->fs_hws_action.lock);
modify_hdr->fs_hws_action.mh_data = mh_data;
modify_hdr->fs_hws_action.fs_pool = pool;
modify_hdr->owner = MLX5_FLOW_RESOURCE_OWNER_SW;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
index 9bbadc4d8a0b..d8ac6c196211 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/mlx5hws.h
@@ -213,6 +213,7 @@ struct mlx5hws_action_dest_attr {
struct mlx5hws_action *dest;
/* Optional reformat action */
struct mlx5hws_action *reformat;
+ bool is_wire_ft;
};
/**
diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
index fb2e5b844c15..d76d7a945899 100644
--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
@@ -447,8 +447,10 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
priv->llu_plu_irq = platform_get_irq(pdev, MLXBF_GIGE_LLU_PLU_INTR_IDX);
phy_irq = acpi_dev_gpio_irq_get_by(ACPI_COMPANION(&pdev->dev), "phy", 0);
- if (phy_irq < 0) {
- dev_err(&pdev->dev, "Error getting PHY irq. Use polling instead");
+ if (phy_irq == -EPROBE_DEFER) {
+ err = -EPROBE_DEFER;
+ goto out;
+ } else if (phy_irq < 0) {
phy_irq = PHY_POLL;
}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index e2368075ab8c..4521d0483d18 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -127,11 +127,8 @@ static int fbnic_mbx_map_msg(struct fbnic_dev *fbd, int mbx_idx,
return -EBUSY;
addr = dma_map_single(fbd->dev, msg, PAGE_SIZE, direction);
- if (dma_mapping_error(fbd->dev, addr)) {
- free_page((unsigned long)msg);
-
+ if (dma_mapping_error(fbd->dev, addr))
return -ENOSPC;
- }
mbx->buf_info[tail].msg = msg;
mbx->buf_info[tail].addr = addr;
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index e8d073bfa2ca..f33dc83c5700 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -18,9 +18,9 @@
*/
#define LAN743X_PTP_N_EVENT_CHAN 2
#define LAN743X_PTP_N_PEROUT LAN743X_PTP_N_EVENT_CHAN
-#define LAN743X_PTP_N_EXTTS 4
-#define LAN743X_PTP_N_PPS 0
#define PCI11X1X_PTP_IO_MAX_CHANNELS 8
+#define LAN743X_PTP_N_EXTTS PCI11X1X_PTP_IO_MAX_CHANNELS
+#define LAN743X_PTP_N_PPS 0
#define PTP_CMD_CTL_TIMEOUT_CNT 50
struct lan743x_adapter;
diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 3504507477c6..52cf7112762c 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -31,6 +31,9 @@ static void mana_gd_init_pf_regs(struct pci_dev *pdev)
gc->db_page_base = gc->bar0_va +
mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+ gc->phys_db_page_base = gc->bar0_pa +
+ mana_gd_r64(gc, GDMA_PF_REG_DB_PAGE_OFF);
+
sriov_base_off = mana_gd_r64(gc, GDMA_SRIOV_REG_CFG_BASE_OFF);
sriov_base_va = gc->bar0_va + sriov_base_off;
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index daf1e82cb76b..0e60a6bef99a 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -516,9 +516,9 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
unsigned long start_time;
unsigned long max_wait;
unsigned long duration;
- int done = 0;
bool fw_up;
int opcode;
+ bool done;
int err;
/* Wait for dev cmd to complete, retrying if we get EAGAIN,
@@ -526,6 +526,7 @@ static int __ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds,
*/
max_wait = jiffies + (max_seconds * HZ);
try_again:
+ done = false;
opcode = idev->opcode;
start_time = jiffies;
for (fw_up = ionic_is_fw_running(idev);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
index 2ac59564ded1..d10b58ebf603 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c
@@ -321,7 +321,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
len, DMA_TO_DEVICE);
} else /* XDP_REDIRECT */ {
dma_addr = ionic_tx_map_single(q, frame->data, len);
- if (!dma_addr)
+ if (dma_addr == DMA_MAPPING_ERROR)
return -EIO;
}
@@ -357,7 +357,7 @@ static int ionic_xdp_post_frame(struct ionic_queue *q, struct xdp_frame *frame,
} else {
dma_addr = ionic_tx_map_frag(q, frag, 0,
skb_frag_size(frag));
- if (dma_mapping_error(q->dev, dma_addr)) {
+ if (dma_addr == DMA_MAPPING_ERROR) {
ionic_tx_desc_unmap_bufs(q, desc_info);
return -EIO;
}
@@ -1083,7 +1083,7 @@ static dma_addr_t ionic_tx_map_single(struct ionic_queue *q,
net_warn_ratelimited("%s: DMA single map failed on %s!\n",
dev_name(dev), q->name);
q_to_tx_stats(q)->dma_map_err++;
- return 0;
+ return DMA_MAPPING_ERROR;
}
return dma_addr;
}
@@ -1100,7 +1100,7 @@ static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q,
net_warn_ratelimited("%s: DMA frag map failed on %s!\n",
dev_name(dev), q->name);
q_to_tx_stats(q)->dma_map_err++;
- return 0;
+ return DMA_MAPPING_ERROR;
}
return dma_addr;
}
@@ -1116,7 +1116,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
int frag_idx;
dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb));
- if (!dma_addr)
+ if (dma_addr == DMA_MAPPING_ERROR)
return -EIO;
buf_info->dma_addr = dma_addr;
buf_info->len = skb_headlen(skb);
@@ -1126,7 +1126,7 @@ static int ionic_tx_map_skb(struct ionic_queue *q, struct sk_buff *skb,
nfrags = skb_shinfo(skb)->nr_frags;
for (frag_idx = 0; frag_idx < nfrags; frag_idx++, frag++) {
dma_addr = ionic_tx_map_frag(q, frag, 0, skb_frag_size(frag));
- if (!dma_addr)
+ if (dma_addr == DMA_MAPPING_ERROR)
goto dma_fail;
buf_info->dma_addr = dma_addr;
buf_info->len = skb_frag_size(frag);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
index f55eed092f25..7d78f072b0a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mng_tlv.c
@@ -242,7 +242,7 @@ static int qed_mfw_get_tlv_group(u8 tlv_type, u8 *tlv_group)
}
/* Returns size of the data buffer or, -1 in case TLV data is not available. */
-static int
+static noinline_for_stack int
qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
struct qed_mfw_tlv_generic *p_drv_buf,
struct qed_tlv_parsed_buf *p_buf)
@@ -304,7 +304,7 @@ qed_mfw_get_gen_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
return -1;
}
-static int
+static noinline_for_stack int
qed_mfw_get_eth_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
struct qed_mfw_tlv_eth *p_drv_buf,
struct qed_tlv_parsed_buf *p_buf)
@@ -438,7 +438,7 @@ qed_mfw_get_tlv_time_value(struct qed_mfw_tlv_time *p_time,
return QED_MFW_TLV_TIME_SIZE;
}
-static int
+static noinline_for_stack int
qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
struct qed_mfw_tlv_fcoe *p_drv_buf,
struct qed_tlv_parsed_buf *p_buf)
@@ -1073,7 +1073,7 @@ qed_mfw_get_fcoe_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
return -1;
}
-static int
+static noinline_for_stack int
qed_mfw_get_iscsi_tlv_value(struct qed_drv_tlv_hdr *p_tlv,
struct qed_mfw_tlv_iscsi *p_drv_buf,
struct qed_tlv_parsed_buf *p_buf)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 5b8fdb882172..12f25cec6255 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -98,20 +98,11 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
{
struct cppi5_host_desc_t *first_desc, *next_desc;
dma_addr_t buf_dma, next_desc_dma;
- struct prueth_swdata *swdata;
- struct page *page;
u32 buf_dma_len;
first_desc = desc;
next_desc = first_desc;
- swdata = cppi5_hdesc_get_swdata(desc);
- if (swdata->type == PRUETH_SWDATA_PAGE) {
- page = swdata->data.page;
- page_pool_recycle_direct(page->pp, swdata->data.page);
- goto free_desc;
- }
-
cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
@@ -135,7 +126,6 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
}
-free_desc:
k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
}
EXPORT_SYMBOL_GPL(prueth_xmit_free);
@@ -612,13 +602,8 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len);
swdata = cppi5_hdesc_get_swdata(first_desc);
- if (page) {
- swdata->type = PRUETH_SWDATA_PAGE;
- swdata->data.page = page;
- } else {
- swdata->type = PRUETH_SWDATA_XDPF;
- swdata->data.xdpf = xdpf;
- }
+ swdata->type = PRUETH_SWDATA_XDPF;
+ swdata->data.xdpf = xdpf;
/* Report BQL before sending the packet */
netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 7f2e6cddfeb1..c57cc4f27249 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -2623,7 +2623,7 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring)
struct page_pool_params pp_params = {
.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
.order = 0,
- .pool_size = rx_ring->size,
+ .pool_size = rx_ring->count,
.nid = dev_to_node(rx_ring->dev),
.dev = rx_ring->dev,
.dma_dir = DMA_FROM_DEVICE,
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 3d315e30ee47..7edbe76b5455 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -247,15 +247,39 @@ static sci_t make_sci(const u8 *addr, __be16 port)
return sci;
}
-static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present)
+static sci_t macsec_active_sci(struct macsec_secy *secy)
{
- sci_t sci;
+ struct macsec_rx_sc *rx_sc = rcu_dereference_bh(secy->rx_sc);
+
+ /* Case single RX SC */
+ if (rx_sc && !rcu_dereference_bh(rx_sc->next))
+ return (rx_sc->active) ? rx_sc->sci : 0;
+ /* Case no RX SC or multiple */
+ else
+ return 0;
+}
+
+static sci_t macsec_frame_sci(struct macsec_eth_header *hdr, bool sci_present,
+ struct macsec_rxh_data *rxd)
+{
+ struct macsec_dev *macsec;
+ sci_t sci = 0;
- if (sci_present)
+ /* SC = 1 */
+ if (sci_present) {
memcpy(&sci, hdr->secure_channel_id,
sizeof(hdr->secure_channel_id));
- else
+ /* SC = 0; ES = 0 */
+ } else if ((!(hdr->tci_an & (MACSEC_TCI_ES | MACSEC_TCI_SC))) &&
+ (list_is_singular(&rxd->secys))) {
+ /* Only one SECY should exist on this scenario */
+ macsec = list_first_or_null_rcu(&rxd->secys, struct macsec_dev,
+ secys);
+ if (macsec)
+ return macsec_active_sci(&macsec->secy);
+ } else {
sci = make_sci(hdr->eth.h_source, MACSEC_PORT_ES);
+ }
return sci;
}
@@ -1109,7 +1133,7 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
struct macsec_rxh_data *rxd;
struct macsec_dev *macsec;
unsigned int len;
- sci_t sci;
+ sci_t sci = 0;
u32 hdr_pn;
bool cbit;
struct pcpu_rx_sc_stats *rxsc_stats;
@@ -1156,11 +1180,14 @@ static rx_handler_result_t macsec_handle_frame(struct sk_buff **pskb)
macsec_skb_cb(skb)->has_sci = !!(hdr->tci_an & MACSEC_TCI_SC);
macsec_skb_cb(skb)->assoc_num = hdr->tci_an & MACSEC_AN_MASK;
- sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci);
rcu_read_lock();
rxd = macsec_data_rcu(skb->dev);
+ sci = macsec_frame_sci(hdr, macsec_skb_cb(skb)->has_sci, rxd);
+ if (!sci)
+ goto drop_nosc;
+
list_for_each_entry_rcu(macsec, &rxd->secys, secys) {
struct macsec_rx_sc *sc = find_rx_sc(&macsec->secy, sci);
@@ -1283,6 +1310,7 @@ drop:
macsec_rxsa_put(rx_sa);
drop_nosa:
macsec_rxsc_put(rx_sc);
+drop_nosc:
rcu_read_unlock();
drop_direct:
kfree_skb(skb);
diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 4289ccd3e41b..176935a8645f 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1252,7 +1252,6 @@ static int sysdata_append_release(struct netconsole_target *nt, int offset)
*/
static int prepare_extradata(struct netconsole_target *nt)
{
- u32 fields = SYSDATA_CPU_NR | SYSDATA_TASKNAME;
int extradata_len;
/* userdata was appended when configfs write helper was called
@@ -1260,7 +1259,7 @@ static int prepare_extradata(struct netconsole_target *nt)
*/
extradata_len = nt->userdata_length;
- if (!(nt->sysdata_fields & fields))
+ if (!nt->sysdata_fields)
goto out;
if (nt->sysdata_fields & SYSDATA_CPU_NR)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index af545d42961c..fa5fbd97ad69 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -371,7 +371,8 @@ static int nsim_poll(struct napi_struct *napi, int budget)
int done;
done = nsim_rcv(rq, budget);
- napi_complete(napi);
+ if (done < budget)
+ napi_complete_done(napi, done);
return done;
}
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index a6bcb0fee863..fda2e27c1810 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -445,6 +445,9 @@ int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum)
lockdep_assert_held_once(&bus->mdio_lock);
+ if (addr >= PHY_MAX_ADDR)
+ return -ENXIO;
+
if (bus->read)
retval = bus->read(bus, addr, regnum);
else
@@ -474,6 +477,9 @@ int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val)
lockdep_assert_held_once(&bus->mdio_lock);
+ if (addr >= PHY_MAX_ADDR)
+ return -ENXIO;
+
if (bus->write)
err = bus->write(bus, addr, regnum, val);
else
@@ -535,6 +541,9 @@ int __mdiobus_c45_read(struct mii_bus *bus, int addr, int devad, u32 regnum)
lockdep_assert_held_once(&bus->mdio_lock);
+ if (addr >= PHY_MAX_ADDR)
+ return -ENXIO;
+
if (bus->read_c45)
retval = bus->read_c45(bus, addr, devad, regnum);
else
@@ -566,6 +575,9 @@ int __mdiobus_c45_write(struct mii_bus *bus, int addr, int devad, u32 regnum,
lockdep_assert_held_once(&bus->mdio_lock);
+ if (addr >= PHY_MAX_ADDR)
+ return -ENXIO;
+
if (bus->write_c45)
err = bus->write_c45(bus, addr, devad, regnum, val);
else
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 703321689726..38417e288611 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -188,6 +188,9 @@ phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only)
* When @exact is not set, we return either an exact match, or matching capabilities
* at lower speed, or the lowest matching speed, or NULL.
*
+ * Non-exact matches will try to return an exact speed and duplex match, but may
+ * return matching capabilities with same speed but a different duplex.
+ *
* Returns: a matched link_capabilities according to the above process, NULL
* otherwise.
*/
@@ -195,7 +198,7 @@ const struct link_capabilities *
phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
bool exact)
{
- const struct link_capabilities *lcap, *last = NULL;
+ const struct link_capabilities *lcap, *match = NULL, *last = NULL;
for_each_link_caps_desc_speed(lcap) {
if (linkmode_intersects(lcap->linkmodes, supported)) {
@@ -204,16 +207,19 @@ phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
if (lcap->speed == speed && lcap->duplex == duplex) {
return lcap;
} else if (!exact) {
- if (lcap->speed <= speed)
- return lcap;
+ if (!match && lcap->speed <= speed)
+ match = lcap;
+
+ if (lcap->speed < speed)
+ break;
}
}
}
- if (!exact)
- return last;
+ if (!match && !exact)
+ match = last;
- return NULL;
+ return match;
}
EXPORT_SYMBOL_GPL(phy_caps_lookup);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index b586b1c13a47..f5647ee0adde 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1426,6 +1426,7 @@ static const struct usb_device_id products[] = {
{QMI_QUIRK_SET_DTR(0x22de, 0x9051, 2)}, /* Hucom Wireless HM-211S/K */
{QMI_FIXED_INTF(0x22de, 0x9061, 3)}, /* WeTelecom WPD-600N */
{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)}, /* SIMCom 7100E, 7230E, 7600E ++ */
+ {QMI_QUIRK_SET_DTR(0x1e0e, 0x9071, 3)}, /* SIMCom 8230C ++ */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */
{QMI_QUIRK_SET_DTR(0x2c7c, 0x0195, 4)}, /* Quectel EG95 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index d6589b24c68d..44cba7acfe7d 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10054,6 +10054,7 @@ static const struct usb_device_id rtl8152_table[] = {
{ USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) },
{ USB_DEVICE(VENDOR_ID_NVIDIA, 0x09ff) },
{ USB_DEVICE(VENDOR_ID_TPLINK, 0x0601) },
+ { USB_DEVICE(VENDOR_ID_TPLINK, 0x0602) },
{ USB_DEVICE(VENDOR_ID_DLINK, 0xb301) },
{ USB_DEVICE(VENDOR_ID_DELL, 0xb097) },
{ USB_DEVICE(VENDOR_ID_ASUS, 0x1976) },
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index e58a0f1b5c5b..a3046142cb8e 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -909,7 +909,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
/* NAPI functions as RCU section */
peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held());
- peer_txq = netdev_get_tx_queue(peer_dev, queue_idx);
+ peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL;
for (i = 0; i < budget; i++) {
void *ptr = __ptr_ring_consume(&rq->xdp_ring);
@@ -959,7 +959,7 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget,
rq->stats.vs.xdp_packets += done;
u64_stats_update_end(&rq->stats.syncp);
- if (unlikely(netif_tx_queue_stopped(peer_txq)))
+ if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq)))
netif_tx_wake_queue(peer_txq);
return done;
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 8c7ffea0fa44..07fe05384cdf 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4,6 +4,7 @@
* Copyright (c) 2011-2017 Qualcomm Atheros, Inc.
* Copyright (c) 2018-2019, The Linux Foundation. All rights reserved.
* Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
*/
#include "mac.h"
@@ -1022,6 +1023,26 @@ static inline int ath10k_vdev_setup_sync(struct ath10k *ar)
return ar->last_wmi_vdev_start_status;
}
+static inline int ath10k_vdev_delete_sync(struct ath10k *ar)
+{
+ unsigned long time_left;
+
+ lockdep_assert_held(&ar->conf_mutex);
+
+ if (!test_bit(WMI_SERVICE_SYNC_DELETE_CMDS, ar->wmi.svc_map))
+ return 0;
+
+ if (test_bit(ATH10K_FLAG_CRASH_FLUSH, &ar->dev_flags))
+ return -ESHUTDOWN;
+
+ time_left = wait_for_completion_timeout(&ar->vdev_delete_done,
+ ATH10K_VDEV_DELETE_TIMEOUT_HZ);
+ if (time_left == 0)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
static int ath10k_monitor_vdev_start(struct ath10k *ar, int vdev_id)
{
struct cfg80211_chan_def *chandef = NULL;
@@ -5900,7 +5921,6 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
struct ath10k *ar = hw->priv;
struct ath10k_vif *arvif = (void *)vif->drv_priv;
struct ath10k_peer *peer;
- unsigned long time_left;
int ret;
int i;
@@ -5940,13 +5960,10 @@ static void ath10k_remove_interface(struct ieee80211_hw *hw,
ath10k_warn(ar, "failed to delete WMI vdev %i: %d\n",
arvif->vdev_id, ret);
- if (test_bit(WMI_SERVICE_SYNC_DELETE_CMDS, ar->wmi.svc_map)) {
- time_left = wait_for_completion_timeout(&ar->vdev_delete_done,
- ATH10K_VDEV_DELETE_TIMEOUT_HZ);
- if (time_left == 0) {
- ath10k_warn(ar, "Timeout in receiving vdev delete response\n");
- goto out;
- }
+ ret = ath10k_vdev_delete_sync(ar);
+ if (ret) {
+ ath10k_warn(ar, "Error in receiving vdev delete response: %d\n", ret);
+ goto out;
}
/* Some firmware revisions don't notify host about self-peer removal
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index b2bf9d72b92f..d51f2e5a79a4 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -938,7 +938,9 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
dev_set_threaded(ar->napi_dev, true);
ath10k_core_napi_enable(ar);
- ath10k_snoc_irq_enable(ar);
+ /* IRQs are left enabled when we restart due to a firmware crash */
+ if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
+ ath10k_snoc_irq_enable(ar);
ath10k_snoc_rx_post(ar);
clear_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags);
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 2e9f8a5e61e4..22a101136135 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -990,6 +990,7 @@ void ath11k_fw_stats_init(struct ath11k *ar)
INIT_LIST_HEAD(&ar->fw_stats.bcn);
init_completion(&ar->fw_stats_complete);
+ init_completion(&ar->fw_stats_done);
}
void ath11k_fw_stats_free(struct ath11k_fw_stats *stats)
@@ -2134,6 +2135,20 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
{
int ret;
+ switch (ath11k_crypto_mode) {
+ case ATH11K_CRYPT_MODE_SW:
+ set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+ set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+ break;
+ case ATH11K_CRYPT_MODE_HW:
+ clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
+ clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
+ break;
+ default:
+ ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
+ return -EINVAL;
+ }
+
ret = ath11k_core_start_firmware(ab, ab->fw_mode);
if (ret) {
ath11k_err(ab, "failed to start firmware: %d\n", ret);
@@ -2152,20 +2167,6 @@ int ath11k_core_qmi_firmware_ready(struct ath11k_base *ab)
goto err_firmware_stop;
}
- switch (ath11k_crypto_mode) {
- case ATH11K_CRYPT_MODE_SW:
- set_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
- set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
- break;
- case ATH11K_CRYPT_MODE_HW:
- clear_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags);
- clear_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
- break;
- default:
- ath11k_info(ab, "invalid crypto_mode: %d\n", ath11k_crypto_mode);
- return -EINVAL;
- }
-
if (ath11k_frame_mode == ATH11K_HW_TXRX_RAW)
set_bit(ATH11K_FLAG_RAW_MODE, &ab->dev_flags);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 339d4fca1ed5..6b2f207975e3 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -600,6 +600,8 @@ struct ath11k_fw_stats {
struct list_head pdevs;
struct list_head vdevs;
struct list_head bcn;
+ u32 num_vdev_recvd;
+ u32 num_bcn_recvd;
};
struct ath11k_dbg_htt_stats {
@@ -784,7 +786,7 @@ struct ath11k {
u8 alpha2[REG_ALPHA2_LEN + 1];
struct ath11k_fw_stats fw_stats;
struct completion fw_stats_complete;
- bool fw_stats_done;
+ struct completion fw_stats_done;
/* protected by conf_mutex */
bool ps_state_enable;
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.c b/drivers/net/wireless/ath/ath11k/debugfs.c
index bf192529e3fe..5d46f8e4c231 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.c
+++ b/drivers/net/wireless/ath/ath11k/debugfs.c
@@ -1,7 +1,7 @@
// SPDX-License-Identifier: BSD-3-Clause-Clear
/*
* Copyright (c) 2018-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
*/
#include <linux/vmalloc.h>
@@ -93,57 +93,14 @@ void ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
spin_unlock_bh(&dbr_data->lock);
}
-static void ath11k_debugfs_fw_stats_reset(struct ath11k *ar)
-{
- spin_lock_bh(&ar->data_lock);
- ar->fw_stats_done = false;
- ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
- ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
- spin_unlock_bh(&ar->data_lock);
-}
-
void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats)
{
struct ath11k_base *ab = ar->ab;
- struct ath11k_pdev *pdev;
- bool is_end;
- static unsigned int num_vdev, num_bcn;
- size_t total_vdevs_started = 0;
- int i;
-
- /* WMI_REQUEST_PDEV_STAT request has been already processed */
-
- if (stats->stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
- ar->fw_stats_done = true;
- return;
- }
-
- if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
- if (list_empty(&stats->vdevs)) {
- ath11k_warn(ab, "empty vdev stats");
- return;
- }
- /* FW sends all the active VDEV stats irrespective of PDEV,
- * hence limit until the count of all VDEVs started
- */
- for (i = 0; i < ab->num_radios; i++) {
- pdev = rcu_dereference(ab->pdevs_active[i]);
- if (pdev && pdev->ar)
- total_vdevs_started += ar->num_started_vdevs;
- }
-
- is_end = ((++num_vdev) == total_vdevs_started);
-
- list_splice_tail_init(&stats->vdevs,
- &ar->fw_stats.vdevs);
-
- if (is_end) {
- ar->fw_stats_done = true;
- num_vdev = 0;
- }
- return;
- }
+ bool is_end = true;
+ /* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_RSSI_PER_CHAIN_STAT and
+ * WMI_REQUEST_VDEV_STAT requests have been already processed.
+ */
if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
if (list_empty(&stats->bcn)) {
ath11k_warn(ab, "empty bcn stats");
@@ -152,97 +109,18 @@ void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *
/* Mark end until we reached the count of all started VDEVs
* within the PDEV
*/
- is_end = ((++num_bcn) == ar->num_started_vdevs);
+ if (ar->num_started_vdevs)
+ is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+ ar->num_started_vdevs);
list_splice_tail_init(&stats->bcn,
&ar->fw_stats.bcn);
- if (is_end) {
- ar->fw_stats_done = true;
- num_bcn = 0;
- }
+ if (is_end)
+ complete(&ar->fw_stats_done);
}
}
-static int ath11k_debugfs_fw_stats_request(struct ath11k *ar,
- struct stats_request_params *req_param)
-{
- struct ath11k_base *ab = ar->ab;
- unsigned long timeout, time_left;
- int ret;
-
- lockdep_assert_held(&ar->conf_mutex);
-
- /* FW stats can get split when exceeding the stats data buffer limit.
- * In that case, since there is no end marking for the back-to-back
- * received 'update stats' event, we keep a 3 seconds timeout in case,
- * fw_stats_done is not marked yet
- */
- timeout = jiffies + secs_to_jiffies(3);
-
- ath11k_debugfs_fw_stats_reset(ar);
-
- reinit_completion(&ar->fw_stats_complete);
-
- ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
-
- if (ret) {
- ath11k_warn(ab, "could not request fw stats (%d)\n",
- ret);
- return ret;
- }
-
- time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
- if (!time_left)
- return -ETIMEDOUT;
-
- for (;;) {
- if (time_after(jiffies, timeout))
- break;
-
- spin_lock_bh(&ar->data_lock);
- if (ar->fw_stats_done) {
- spin_unlock_bh(&ar->data_lock);
- break;
- }
- spin_unlock_bh(&ar->data_lock);
- }
- return 0;
-}
-
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
- u32 vdev_id, u32 stats_id)
-{
- struct ath11k_base *ab = ar->ab;
- struct stats_request_params req_param;
- int ret;
-
- mutex_lock(&ar->conf_mutex);
-
- if (ar->state != ATH11K_STATE_ON) {
- ret = -ENETDOWN;
- goto err_unlock;
- }
-
- req_param.pdev_id = pdev_id;
- req_param.vdev_id = vdev_id;
- req_param.stats_id = stats_id;
-
- ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
- if (ret)
- ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
-
- ath11k_dbg(ab, ATH11K_DBG_WMI,
- "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
- pdev_id, vdev_id, stats_id);
-
-err_unlock:
- mutex_unlock(&ar->conf_mutex);
-
- return ret;
-}
-
static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
{
struct ath11k *ar = inode->i_private;
@@ -268,7 +146,7 @@ static int ath11k_open_pdev_stats(struct inode *inode, struct file *file)
req_param.vdev_id = 0;
req_param.stats_id = WMI_REQUEST_PDEV_STAT;
- ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+ ret = ath11k_mac_fw_stats_request(ar, &req_param);
if (ret) {
ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
goto err_free;
@@ -339,7 +217,7 @@ static int ath11k_open_vdev_stats(struct inode *inode, struct file *file)
req_param.vdev_id = 0;
req_param.stats_id = WMI_REQUEST_VDEV_STAT;
- ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+ ret = ath11k_mac_fw_stats_request(ar, &req_param);
if (ret) {
ath11k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
goto err_free;
@@ -415,7 +293,7 @@ static int ath11k_open_bcn_stats(struct inode *inode, struct file *file)
continue;
req_param.vdev_id = arvif->vdev_id;
- ret = ath11k_debugfs_fw_stats_request(ar, &req_param);
+ ret = ath11k_mac_fw_stats_request(ar, &req_param);
if (ret) {
ath11k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
goto err_free;
diff --git a/drivers/net/wireless/ath/ath11k/debugfs.h b/drivers/net/wireless/ath/ath11k/debugfs.h
index a39e458637b0..ed7fec177588 100644
--- a/drivers/net/wireless/ath/ath11k/debugfs.h
+++ b/drivers/net/wireless/ath/ath11k/debugfs.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: BSD-3-Clause-Clear */
/*
* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
*/
#ifndef _ATH11K_DEBUGFS_H_
@@ -273,8 +273,6 @@ void ath11k_debugfs_unregister(struct ath11k *ar);
void ath11k_debugfs_fw_stats_process(struct ath11k *ar, struct ath11k_fw_stats *stats);
void ath11k_debugfs_fw_stats_init(struct ath11k *ar);
-int ath11k_debugfs_get_fw_stats(struct ath11k *ar, u32 pdev_id,
- u32 vdev_id, u32 stats_id);
static inline bool ath11k_debugfs_is_pktlog_lite_mode_enabled(struct ath11k *ar)
{
@@ -381,12 +379,6 @@ static inline int ath11k_debugfs_rx_filter(struct ath11k *ar)
return 0;
}
-static inline int ath11k_debugfs_get_fw_stats(struct ath11k *ar,
- u32 pdev_id, u32 vdev_id, u32 stats_id)
-{
- return 0;
-}
-
static inline void
ath11k_debugfs_add_dbring_entry(struct ath11k *ar,
enum wmi_direct_buffer_module id,
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 08d7b136851f..13301ca317a5 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -8997,6 +8997,81 @@ static void ath11k_mac_put_chain_rssi(struct station_info *sinfo,
}
}
+static void ath11k_mac_fw_stats_reset(struct ath11k *ar)
+{
+ spin_lock_bh(&ar->data_lock);
+ ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
+ ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+ ar->fw_stats.num_vdev_recvd = 0;
+ ar->fw_stats.num_bcn_recvd = 0;
+ spin_unlock_bh(&ar->data_lock);
+}
+
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+ struct stats_request_params *req_param)
+{
+ struct ath11k_base *ab = ar->ab;
+ unsigned long time_left;
+ int ret;
+
+ lockdep_assert_held(&ar->conf_mutex);
+
+ ath11k_mac_fw_stats_reset(ar);
+
+ reinit_completion(&ar->fw_stats_complete);
+ reinit_completion(&ar->fw_stats_done);
+
+ ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
+
+ if (ret) {
+ ath11k_warn(ab, "could not request fw stats (%d)\n",
+ ret);
+ return ret;
+ }
+
+ time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
+ if (!time_left)
+ return -ETIMEDOUT;
+
+ /* FW stats can get split when exceeding the stats data buffer limit.
+ * In that case, since there is no end marking for the back-to-back
+ * received 'update stats' event, we keep a 3 seconds timeout in case,
+ * fw_stats_done is not marked yet
+ */
+ time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+ if (!time_left)
+ return -ETIMEDOUT;
+
+ return 0;
+}
+
+static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id,
+ u32 vdev_id, u32 stats_id)
+{
+ struct ath11k_base *ab = ar->ab;
+ struct stats_request_params req_param;
+ int ret;
+
+ lockdep_assert_held(&ar->conf_mutex);
+
+ if (ar->state != ATH11K_STATE_ON)
+ return -ENETDOWN;
+
+ req_param.pdev_id = pdev_id;
+ req_param.vdev_id = vdev_id;
+ req_param.stats_id = stats_id;
+
+ ret = ath11k_mac_fw_stats_request(ar, &req_param);
+ if (ret)
+ ath11k_warn(ab, "failed to request fw stats: %d\n", ret);
+
+ ath11k_dbg(ab, ATH11K_DBG_WMI,
+ "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n",
+ pdev_id, vdev_id, stats_id);
+
+ return ret;
+}
+
static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ieee80211_sta *sta,
@@ -9031,11 +9106,12 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
ath11k_mac_put_chain_rssi(sinfo, arsta, "ppdu", false);
+ mutex_lock(&ar->conf_mutex);
if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) &&
arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
ar->ab->hw_params.supports_rssi_stats &&
- !ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
- WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
+ !ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+ WMI_REQUEST_RSSI_PER_CHAIN_STAT)) {
ath11k_mac_put_chain_rssi(sinfo, arsta, "fw stats", true);
}
@@ -9043,9 +9119,10 @@ static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw,
if (!signal &&
arsta->arvif->vdev_type == WMI_VDEV_TYPE_STA &&
ar->ab->hw_params.supports_rssi_stats &&
- !(ath11k_debugfs_get_fw_stats(ar, ar->pdev->pdev_id, 0,
- WMI_REQUEST_VDEV_STAT)))
+ !(ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+ WMI_REQUEST_VDEV_STAT)))
signal = arsta->rssi_beacon;
+ mutex_unlock(&ar->conf_mutex);
ath11k_dbg(ar->ab, ATH11K_DBG_MAC,
"sta statistics db2dbm %u rssi comb %d rssi beacon %d\n",
@@ -9380,38 +9457,6 @@ exit:
return ret;
}
-static int ath11k_fw_stats_request(struct ath11k *ar,
- struct stats_request_params *req_param)
-{
- struct ath11k_base *ab = ar->ab;
- unsigned long time_left;
- int ret;
-
- lockdep_assert_held(&ar->conf_mutex);
-
- spin_lock_bh(&ar->data_lock);
- ar->fw_stats_done = false;
- ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
- spin_unlock_bh(&ar->data_lock);
-
- reinit_completion(&ar->fw_stats_complete);
-
- ret = ath11k_wmi_send_stats_request_cmd(ar, req_param);
- if (ret) {
- ath11k_warn(ab, "could not request fw stats (%d)\n",
- ret);
- return ret;
- }
-
- time_left = wait_for_completion_timeout(&ar->fw_stats_complete,
- 1 * HZ);
-
- if (!time_left)
- return -ETIMEDOUT;
-
- return 0;
-}
-
static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
unsigned int link_id,
@@ -9419,7 +9464,6 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
{
struct ath11k *ar = hw->priv;
struct ath11k_base *ab = ar->ab;
- struct stats_request_params req_param = {0};
struct ath11k_fw_stats_pdev *pdev;
int ret;
@@ -9431,9 +9475,6 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
*/
mutex_lock(&ar->conf_mutex);
- if (ar->state != ATH11K_STATE_ON)
- goto err_fallback;
-
/* Firmware doesn't provide Tx power during CAC hence no need to fetch
* the stats.
*/
@@ -9442,10 +9483,8 @@ static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw,
return -EAGAIN;
}
- req_param.pdev_id = ar->pdev->pdev_id;
- req_param.stats_id = WMI_REQUEST_PDEV_STAT;
-
- ret = ath11k_fw_stats_request(ar, &req_param);
+ ret = ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+ WMI_REQUEST_PDEV_STAT);
if (ret) {
ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
goto err_fallback;
diff --git a/drivers/net/wireless/ath/ath11k/mac.h b/drivers/net/wireless/ath/ath11k/mac.h
index f5800fbecff8..5e61eea1bb03 100644
--- a/drivers/net/wireless/ath/ath11k/mac.h
+++ b/drivers/net/wireless/ath/ath11k/mac.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: BSD-3-Clause-Clear */
/*
* Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
*/
#ifndef ATH11K_MAC_H
@@ -179,4 +179,6 @@ int ath11k_mac_vif_set_keepalive(struct ath11k_vif *arvif,
void ath11k_mac_fill_reg_tpc_info(struct ath11k *ar,
struct ieee80211_vif *vif,
struct ieee80211_chanctx_conf *ctx);
+int ath11k_mac_fw_stats_request(struct ath11k *ar,
+ struct stats_request_params *req_param);
#endif
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index d7f852bebf4a..56af2e9634f4 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -8158,6 +8158,11 @@ static void ath11k_peer_assoc_conf_event(struct ath11k_base *ab, struct sk_buff
static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *skb)
{
struct ath11k_fw_stats stats = {};
+ size_t total_vdevs_started = 0;
+ struct ath11k_pdev *pdev;
+ bool is_end = true;
+ int i;
+
struct ath11k *ar;
int ret;
@@ -8184,25 +8189,57 @@ static void ath11k_update_stats_event(struct ath11k_base *ab, struct sk_buff *sk
spin_lock_bh(&ar->data_lock);
- /* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
+ /* WMI_REQUEST_PDEV_STAT, WMI_REQUEST_VDEV_STAT and
+ * WMI_REQUEST_RSSI_PER_CHAIN_STAT can be requested via mac ops or via
* debugfs fw stats. Therefore, processing it separately.
*/
if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
- ar->fw_stats_done = true;
+ complete(&ar->fw_stats_done);
+ goto complete;
+ }
+
+ if (stats.stats_id == WMI_REQUEST_RSSI_PER_CHAIN_STAT) {
+ complete(&ar->fw_stats_done);
goto complete;
}
- /* WMI_REQUEST_VDEV_STAT, WMI_REQUEST_BCN_STAT and WMI_REQUEST_RSSI_PER_CHAIN_STAT
- * are currently requested only via debugfs fw stats. Hence, processing these
- * in debugfs context
+ if (stats.stats_id == WMI_REQUEST_VDEV_STAT) {
+ if (list_empty(&stats.vdevs)) {
+ ath11k_warn(ab, "empty vdev stats");
+ goto complete;
+ }
+ /* FW sends all the active VDEV stats irrespective of PDEV,
+ * hence limit until the count of all VDEVs started
+ */
+ for (i = 0; i < ab->num_radios; i++) {
+ pdev = rcu_dereference(ab->pdevs_active[i]);
+ if (pdev && pdev->ar)
+ total_vdevs_started += ar->num_started_vdevs;
+ }
+
+ if (total_vdevs_started)
+ is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+ total_vdevs_started);
+
+ list_splice_tail_init(&stats.vdevs,
+ &ar->fw_stats.vdevs);
+
+ if (is_end)
+ complete(&ar->fw_stats_done);
+
+ goto complete;
+ }
+
+ /* WMI_REQUEST_BCN_STAT is currently requested only via debugfs fw stats.
+ * Hence, processing it in debugfs context
*/
ath11k_debugfs_fw_stats_process(ar, &stats);
complete:
complete(&ar->fw_stats_complete);
- rcu_read_unlock();
spin_unlock_bh(&ar->data_lock);
+ rcu_read_unlock();
/* Since the stats's pdev, vdev and beacon list are spliced and reinitialised
* at this point, no need to free the individual list.
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 31d851d8e688..89ae80934b30 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1216,6 +1216,7 @@ void ath12k_fw_stats_init(struct ath12k *ar)
INIT_LIST_HEAD(&ar->fw_stats.pdevs);
INIT_LIST_HEAD(&ar->fw_stats.bcn);
init_completion(&ar->fw_stats_complete);
+ init_completion(&ar->fw_stats_done);
}
void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
@@ -1228,8 +1229,9 @@ void ath12k_fw_stats_free(struct ath12k_fw_stats *stats)
void ath12k_fw_stats_reset(struct ath12k *ar)
{
spin_lock_bh(&ar->data_lock);
- ar->fw_stats.fw_stats_done = false;
ath12k_fw_stats_free(&ar->fw_stats);
+ ar->fw_stats.num_vdev_recvd = 0;
+ ar->fw_stats.num_bcn_recvd = 0;
spin_unlock_bh(&ar->data_lock);
}
@@ -2129,7 +2131,8 @@ int ath12k_core_init(struct ath12k_base *ab)
if (!ag) {
mutex_unlock(&ath12k_hw_group_mutex);
ath12k_warn(ab, "unable to get hw group\n");
- return -ENODEV;
+ ret = -ENODEV;
+ goto err_unregister_notifier;
}
mutex_unlock(&ath12k_hw_group_mutex);
@@ -2144,7 +2147,7 @@ int ath12k_core_init(struct ath12k_base *ab)
if (ret) {
mutex_unlock(&ag->mutex);
ath12k_warn(ab, "unable to create hw group\n");
- goto err;
+ goto err_destroy_hw_group;
}
}
@@ -2152,9 +2155,12 @@ int ath12k_core_init(struct ath12k_base *ab)
return 0;
-err:
+err_destroy_hw_group:
ath12k_core_hw_group_destroy(ab->ag);
ath12k_core_hw_group_unassign(ab);
+err_unregister_notifier:
+ ath12k_core_panic_notifier_unregister(ab);
+
return ret;
}
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 941db6e49d6e..7bcd9c70309f 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -601,6 +601,12 @@ struct ath12k_sta {
#define ATH12K_NUM_CHANS 101
#define ATH12K_MAX_5GHZ_CHAN 173
+static inline bool ath12k_is_2ghz_channel_freq(u32 freq)
+{
+ return freq >= ATH12K_MIN_2GHZ_FREQ &&
+ freq <= ATH12K_MAX_2GHZ_FREQ;
+}
+
enum ath12k_hw_state {
ATH12K_HW_STATE_OFF,
ATH12K_HW_STATE_ON,
@@ -626,7 +632,8 @@ struct ath12k_fw_stats {
struct list_head pdevs;
struct list_head vdevs;
struct list_head bcn;
- bool fw_stats_done;
+ u32 num_vdev_recvd;
+ u32 num_bcn_recvd;
};
struct ath12k_dbg_htt_stats {
@@ -806,6 +813,7 @@ struct ath12k {
bool regdom_set_by_user;
struct completion fw_stats_complete;
+ struct completion fw_stats_done;
struct completion mlo_setup_done;
u32 mlo_setup_status;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index dd624d73b8b2..23da93afaa5c 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -1251,64 +1251,6 @@ void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
*/
}
-void
-ath12k_debugfs_fw_stats_process(struct ath12k *ar,
- struct ath12k_fw_stats *stats)
-{
- struct ath12k_base *ab = ar->ab;
- struct ath12k_pdev *pdev;
- bool is_end;
- static unsigned int num_vdev, num_bcn;
- size_t total_vdevs_started = 0;
- int i;
-
- if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
- if (list_empty(&stats->vdevs)) {
- ath12k_warn(ab, "empty vdev stats");
- return;
- }
- /* FW sends all the active VDEV stats irrespective of PDEV,
- * hence limit until the count of all VDEVs started
- */
- rcu_read_lock();
- for (i = 0; i < ab->num_radios; i++) {
- pdev = rcu_dereference(ab->pdevs_active[i]);
- if (pdev && pdev->ar)
- total_vdevs_started += pdev->ar->num_started_vdevs;
- }
- rcu_read_unlock();
-
- is_end = ((++num_vdev) == total_vdevs_started);
-
- list_splice_tail_init(&stats->vdevs,
- &ar->fw_stats.vdevs);
-
- if (is_end) {
- ar->fw_stats.fw_stats_done = true;
- num_vdev = 0;
- }
- return;
- }
- if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
- if (list_empty(&stats->bcn)) {
- ath12k_warn(ab, "empty beacon stats");
- return;
- }
- /* Mark end until we reached the count of all started VDEVs
- * within the PDEV
- */
- is_end = ((++num_bcn) == ar->num_started_vdevs);
-
- list_splice_tail_init(&stats->bcn,
- &ar->fw_stats.bcn);
-
- if (is_end) {
- ar->fw_stats.fw_stats_done = true;
- num_bcn = 0;
- }
- }
-}
-
static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
{
struct ath12k *ar = inode->i_private;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index ebef7dace344..21641a8a0346 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -12,8 +12,6 @@ void ath12k_debugfs_soc_create(struct ath12k_base *ab);
void ath12k_debugfs_soc_destroy(struct ath12k_base *ab);
void ath12k_debugfs_register(struct ath12k *ar);
void ath12k_debugfs_unregister(struct ath12k *ar);
-void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
- struct ath12k_fw_stats *stats);
void ath12k_debugfs_op_vif_add(struct ieee80211_hw *hw,
struct ieee80211_vif *vif);
void ath12k_debugfs_pdev_create(struct ath12k_base *ab);
@@ -126,11 +124,6 @@ static inline void ath12k_debugfs_unregister(struct ath12k *ar)
{
}
-static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
- struct ath12k_fw_stats *stats)
-{
-}
-
static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
{
return false;
diff --git a/drivers/net/wireless/ath/ath12k/hal.h b/drivers/net/wireless/ath/ath12k/hal.h
index 0ee9c6b26dab..c1750b5dc03c 100644
--- a/drivers/net/wireless/ath/ath12k/hal.h
+++ b/drivers/net/wireless/ath/ath12k/hal.h
@@ -585,7 +585,8 @@ enum hal_reo_cmd_type {
* or cache was blocked
* @HAL_REO_CMD_FAILED: Command execution failed, could be due to
* invalid queue desc
- * @HAL_REO_CMD_RESOURCE_BLOCKED:
+ * @HAL_REO_CMD_RESOURCE_BLOCKED: Command could not be executed because
+ * one or more descriptors were blocked
* @HAL_REO_CMD_DRAIN:
*/
enum hal_reo_cmd_status {
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 7e2cf0fb2085..8254dc10b53b 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -951,6 +951,8 @@ static const struct ath12k_hw_regs qcn9274_v1_regs = {
.hal_umac_ce0_dest_reg_base = 0x01b81000,
.hal_umac_ce1_src_reg_base = 0x01b82000,
.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+ .gcc_gcc_pcie_hot_rst = 0x1e38338,
};
static const struct ath12k_hw_regs qcn9274_v2_regs = {
@@ -1042,6 +1044,8 @@ static const struct ath12k_hw_regs qcn9274_v2_regs = {
.hal_umac_ce0_dest_reg_base = 0x01b81000,
.hal_umac_ce1_src_reg_base = 0x01b82000,
.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+ .gcc_gcc_pcie_hot_rst = 0x1e38338,
};
static const struct ath12k_hw_regs ipq5332_regs = {
@@ -1215,6 +1219,8 @@ static const struct ath12k_hw_regs wcn7850_regs = {
.hal_umac_ce0_dest_reg_base = 0x01b81000,
.hal_umac_ce1_src_reg_base = 0x01b82000,
.hal_umac_ce1_dest_reg_base = 0x01b83000,
+
+ .gcc_gcc_pcie_hot_rst = 0x1e40304,
};
static const struct ath12k_hw_hal_params ath12k_hw_hal_params_qcn9274 = {
diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
index 0fbc17649df4..0a75bc5abfa2 100644
--- a/drivers/net/wireless/ath/ath12k/hw.h
+++ b/drivers/net/wireless/ath/ath12k/hw.h
@@ -375,6 +375,8 @@ struct ath12k_hw_regs {
u32 hal_reo_cmd_ring_base;
u32 hal_reo_status_ring_base;
+
+ u32 gcc_gcc_pcie_hot_rst;
};
static inline const char *ath12k_bd_ie_type_str(enum ath12k_bd_ie_type type)
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 88b59f3ff87a..59ec422992d3 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4360,7 +4360,7 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
{
struct ath12k_base *ab = ar->ab;
struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
- unsigned long timeout, time_left;
+ unsigned long time_left;
int ret;
guard(mutex)(&ah->hw_mutex);
@@ -4368,19 +4368,13 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
if (ah->state != ATH12K_HW_STATE_ON)
return -ENETDOWN;
- /* FW stats can get split when exceeding the stats data buffer limit.
- * In that case, since there is no end marking for the back-to-back
- * received 'update stats' event, we keep a 3 seconds timeout in case,
- * fw_stats_done is not marked yet
- */
- timeout = jiffies + msecs_to_jiffies(3 * 1000);
ath12k_fw_stats_reset(ar);
reinit_completion(&ar->fw_stats_complete);
+ reinit_completion(&ar->fw_stats_done);
ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
param->vdev_id, param->pdev_id);
-
if (ret) {
ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
return ret;
@@ -4391,7 +4385,6 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
param->pdev_id, param->vdev_id, param->stats_id);
time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
-
if (!time_left) {
ath12k_warn(ab, "time out while waiting for get fw stats\n");
return -ETIMEDOUT;
@@ -4400,20 +4393,15 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar,
/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
* when stats data buffer limit is reached. fw_stats_complete
* is completed once host receives first event from firmware, but
- * still end might not be marked in the TLV.
- * Below loop is to confirm that firmware completed sending all the event
- * and fw_stats_done is marked true when end is marked in the TLV.
+ * still there could be more events following. Below is to wait
+ * until firmware completes sending all the events.
*/
- for (;;) {
- if (time_after(jiffies, timeout))
- break;
- spin_lock_bh(&ar->data_lock);
- if (ar->fw_stats.fw_stats_done) {
- spin_unlock_bh(&ar->data_lock);
- break;
- }
- spin_unlock_bh(&ar->data_lock);
+ time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ);
+ if (!time_left) {
+ ath12k_warn(ab, "time out while waiting for fw stats done\n");
+ return -ETIMEDOUT;
}
+
return 0;
}
@@ -5890,6 +5878,327 @@ exit:
return ret;
}
+static bool ath12k_mac_is_freq_on_mac(struct ath12k_hw_mode_freq_range_arg *freq_range,
+ u32 freq, u8 mac_id)
+{
+ return (freq >= freq_range[mac_id].low_2ghz_freq &&
+ freq <= freq_range[mac_id].high_2ghz_freq) ||
+ (freq >= freq_range[mac_id].low_5ghz_freq &&
+ freq <= freq_range[mac_id].high_5ghz_freq);
+}
+
+static bool
+ath12k_mac_2_freq_same_mac_in_freq_range(struct ath12k_base *ab,
+ struct ath12k_hw_mode_freq_range_arg *freq_range,
+ u32 freq_link1, u32 freq_link2)
+{
+ u8 i;
+
+ for (i = 0; i < MAX_RADIOS; i++) {
+ if (ath12k_mac_is_freq_on_mac(freq_range, freq_link1, i) &&
+ ath12k_mac_is_freq_on_mac(freq_range, freq_link2, i))
+ return true;
+ }
+
+ return false;
+}
+
+static bool ath12k_mac_is_hw_dbs_capable(struct ath12k_base *ab)
+{
+ return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+ ab->wmi_ab.svc_map) &&
+ ab->wmi_ab.hw_mode_info.support_dbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_dbs(struct ath12k_base *ab,
+ u32 freq_link1, u32 freq_link2)
+{
+ struct ath12k_hw_mode_freq_range_arg *freq_range;
+
+ if (!ath12k_mac_is_hw_dbs_capable(ab))
+ return true;
+
+ freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[ATH12K_HW_MODE_DBS];
+ return ath12k_mac_2_freq_same_mac_in_freq_range(ab, freq_range,
+ freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_is_hw_sbs_capable(struct ath12k_base *ab)
+{
+ return test_bit(WMI_TLV_SERVICE_DUAL_BAND_SIMULTANEOUS_SUPPORT,
+ ab->wmi_ab.svc_map) &&
+ ab->wmi_ab.hw_mode_info.support_sbs;
+}
+
+static bool ath12k_mac_2_freq_same_mac_in_sbs(struct ath12k_base *ab,
+ u32 freq_link1, u32 freq_link2)
+{
+ struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *sbs_uppr_share;
+ struct ath12k_hw_mode_freq_range_arg *sbs_low_share;
+ struct ath12k_hw_mode_freq_range_arg *sbs_range;
+
+ if (!ath12k_mac_is_hw_sbs_capable(ab))
+ return true;
+
+ if (ab->wmi_ab.sbs_lower_band_end_freq) {
+ sbs_uppr_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+ sbs_low_share = info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+ return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_low_share,
+ freq_link1, freq_link2) ||
+ ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_uppr_share,
+ freq_link1, freq_link2);
+ }
+
+ sbs_range = info->freq_range_caps[ATH12K_HW_MODE_SBS];
+ return ath12k_mac_2_freq_same_mac_in_freq_range(ab, sbs_range,
+ freq_link1, freq_link2);
+}
+
+static bool ath12k_mac_freqs_on_same_mac(struct ath12k_base *ab,
+ u32 freq_link1, u32 freq_link2)
+{
+ return ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_link1, freq_link2) &&
+ ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_link1, freq_link2);
+}
+
+static int ath12k_mac_mlo_sta_set_link_active(struct ath12k_base *ab,
+ enum wmi_mlo_link_force_reason reason,
+ enum wmi_mlo_link_force_mode mode,
+ u8 *mlo_vdev_id_lst,
+ u8 num_mlo_vdev,
+ u8 *mlo_inactive_vdev_lst,
+ u8 num_mlo_inactive_vdev)
+{
+ struct wmi_mlo_link_set_active_arg param = {0};
+ u32 entry_idx, entry_offset, vdev_idx;
+ u8 vdev_id;
+
+ param.reason = reason;
+ param.force_mode = mode;
+
+ for (vdev_idx = 0; vdev_idx < num_mlo_vdev; vdev_idx++) {
+ vdev_id = mlo_vdev_id_lst[vdev_idx];
+ entry_idx = vdev_id / 32;
+ entry_offset = vdev_id % 32;
+ if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+ ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+ entry_idx, num_mlo_vdev, vdev_id);
+ return -EINVAL;
+ }
+ param.vdev_bitmap[entry_idx] |= 1 << entry_offset;
+ /* update entry number if entry index changed */
+ if (param.num_vdev_bitmap < entry_idx + 1)
+ param.num_vdev_bitmap = entry_idx + 1;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_MAC,
+ "num_vdev_bitmap %d vdev_bitmap[0] = 0x%x, vdev_bitmap[1] = 0x%x",
+ param.num_vdev_bitmap, param.vdev_bitmap[0], param.vdev_bitmap[1]);
+
+ if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+ for (vdev_idx = 0; vdev_idx < num_mlo_inactive_vdev; vdev_idx++) {
+ vdev_id = mlo_inactive_vdev_lst[vdev_idx];
+ entry_idx = vdev_id / 32;
+ entry_offset = vdev_id % 32;
+ if (entry_idx >= WMI_MLO_LINK_NUM_SZ) {
+ ath12k_warn(ab, "Invalid entry_idx %d num_mlo_vdev %d vdev %d",
+ entry_idx, num_mlo_inactive_vdev, vdev_id);
+ return -EINVAL;
+ }
+ param.inactive_vdev_bitmap[entry_idx] |= 1 << entry_offset;
+ /* update entry number if entry index changed */
+ if (param.num_inactive_vdev_bitmap < entry_idx + 1)
+ param.num_inactive_vdev_bitmap = entry_idx + 1;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_MAC,
+ "num_vdev_bitmap %d inactive_vdev_bitmap[0] = 0x%x, inactive_vdev_bitmap[1] = 0x%x",
+ param.num_inactive_vdev_bitmap,
+ param.inactive_vdev_bitmap[0],
+ param.inactive_vdev_bitmap[1]);
+ }
+
+ if (mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM ||
+ mode == WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM) {
+ param.num_link_entry = 1;
+ param.link_num[0].num_of_link = num_mlo_vdev - 1;
+ }
+
+ return ath12k_wmi_send_mlo_link_set_active_cmd(ab, &param);
+}
+
+static int ath12k_mac_mlo_sta_update_link_active(struct ath12k_base *ab,
+ struct ieee80211_hw *hw,
+ struct ath12k_vif *ahvif)
+{
+ u8 mlo_vdev_id_lst[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+ u32 mlo_freq_list[IEEE80211_MLD_MAX_NUM_LINKS] = {0};
+ unsigned long links = ahvif->links_map;
+ enum wmi_mlo_link_force_reason reason;
+ struct ieee80211_chanctx_conf *conf;
+ enum wmi_mlo_link_force_mode mode;
+ struct ieee80211_bss_conf *info;
+ struct ath12k_link_vif *arvif;
+ u8 num_mlo_vdev = 0;
+ u8 link_id;
+
+ for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+ arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+ /* make sure vdev is created on this device */
+ if (!arvif || !arvif->is_created || arvif->ar->ab != ab)
+ continue;
+
+ info = ath12k_mac_get_link_bss_conf(arvif);
+ conf = wiphy_dereference(hw->wiphy, info->chanctx_conf);
+ mlo_freq_list[num_mlo_vdev] = conf->def.chan->center_freq;
+
+ mlo_vdev_id_lst[num_mlo_vdev] = arvif->vdev_id;
+ num_mlo_vdev++;
+ }
+
+ /* It is not allowed to activate more links than a single device
+ * supported. Something goes wrong if we reach here.
+ */
+ if (num_mlo_vdev > ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+ WARN_ON_ONCE(1);
+ return -EINVAL;
+ }
+
+ /* if 2 links are established and both link channels fall on the
+ * same hardware MAC, send command to firmware to deactivate one
+ * of them.
+ */
+ if (num_mlo_vdev == 2 &&
+ ath12k_mac_freqs_on_same_mac(ab, mlo_freq_list[0],
+ mlo_freq_list[1])) {
+ mode = WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM;
+ reason = WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT;
+ return ath12k_mac_mlo_sta_set_link_active(ab, reason, mode,
+ mlo_vdev_id_lst, num_mlo_vdev,
+ NULL, 0);
+ }
+
+ return 0;
+}
+
+static bool ath12k_mac_are_sbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+ if (!ath12k_mac_is_hw_sbs_capable(ab))
+ return false;
+
+ if (ath12k_is_2ghz_channel_freq(freq_1) ||
+ ath12k_is_2ghz_channel_freq(freq_2))
+ return false;
+
+ return !ath12k_mac_2_freq_same_mac_in_sbs(ab, freq_1, freq_2);
+}
+
+static bool ath12k_mac_are_dbs_chan(struct ath12k_base *ab, u32 freq_1, u32 freq_2)
+{
+ if (!ath12k_mac_is_hw_dbs_capable(ab))
+ return false;
+
+ return !ath12k_mac_2_freq_same_mac_in_dbs(ab, freq_1, freq_2);
+}
+
+static int ath12k_mac_select_links(struct ath12k_base *ab,
+ struct ieee80211_vif *vif,
+ struct ieee80211_hw *hw,
+ u16 *selected_links)
+{
+ unsigned long useful_links = ieee80211_vif_usable_links(vif);
+ struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+ u8 num_useful_links = hweight_long(useful_links);
+ struct ieee80211_chanctx_conf *chanctx;
+ struct ath12k_link_vif *assoc_arvif;
+ u32 assoc_link_freq, partner_freq;
+ u16 sbs_links = 0, dbs_links = 0;
+ struct ieee80211_bss_conf *info;
+ struct ieee80211_channel *chan;
+ struct ieee80211_sta *sta;
+ struct ath12k_sta *ahsta;
+ u8 link_id;
+
+ /* activate all useful links if less than max supported */
+ if (num_useful_links <= ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE) {
+ *selected_links = useful_links;
+ return 0;
+ }
+
+ /* only in station mode we can get here, so it's safe
+ * to use ap_addr
+ */
+ rcu_read_lock();
+ sta = ieee80211_find_sta(vif, vif->cfg.ap_addr);
+ if (!sta) {
+ rcu_read_unlock();
+ ath12k_warn(ab, "failed to find sta with addr %pM\n", vif->cfg.ap_addr);
+ return -EINVAL;
+ }
+
+ ahsta = ath12k_sta_to_ahsta(sta);
+ assoc_arvif = wiphy_dereference(hw->wiphy, ahvif->link[ahsta->assoc_link_id]);
+ info = ath12k_mac_get_link_bss_conf(assoc_arvif);
+ chanctx = rcu_dereference(info->chanctx_conf);
+ assoc_link_freq = chanctx->def.chan->center_freq;
+ rcu_read_unlock();
+ ath12k_dbg(ab, ATH12K_DBG_MAC, "assoc link %u freq %u\n",
+ assoc_arvif->link_id, assoc_link_freq);
+
+ /* assoc link is already activated and has to be kept active,
+ * only need to select a partner link from others.
+ */
+ useful_links &= ~BIT(assoc_arvif->link_id);
+ for_each_set_bit(link_id, &useful_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+ info = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
+ if (!info) {
+ ath12k_warn(ab, "failed to get link info for link: %u\n",
+ link_id);
+ return -ENOLINK;
+ }
+
+ chan = info->chanreq.oper.chan;
+ if (!chan) {
+ ath12k_warn(ab, "failed to get chan for link: %u\n", link_id);
+ return -EINVAL;
+ }
+
+ partner_freq = chan->center_freq;
+ if (ath12k_mac_are_sbs_chan(ab, assoc_link_freq, partner_freq)) {
+ sbs_links |= BIT(link_id);
+ ath12k_dbg(ab, ATH12K_DBG_MAC, "new SBS link %u freq %u\n",
+ link_id, partner_freq);
+ continue;
+ }
+
+ if (ath12k_mac_are_dbs_chan(ab, assoc_link_freq, partner_freq)) {
+ dbs_links |= BIT(link_id);
+ ath12k_dbg(ab, ATH12K_DBG_MAC, "new DBS link %u freq %u\n",
+ link_id, partner_freq);
+ continue;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_MAC, "non DBS/SBS link %u freq %u\n",
+ link_id, partner_freq);
+ }
+
+ /* choose the first candidate no matter how many is in the list */
+ if (sbs_links)
+ link_id = __ffs(sbs_links);
+ else if (dbs_links)
+ link_id = __ffs(dbs_links);
+ else
+ link_id = ffs(useful_links) - 1;
+
+ ath12k_dbg(ab, ATH12K_DBG_MAC, "select partner link %u\n", link_id);
+
+ *selected_links = BIT(assoc_arvif->link_id) | BIT(link_id);
+
+ return 0;
+}
+
static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
struct ieee80211_vif *vif,
struct ieee80211_sta *sta,
@@ -5899,10 +6208,13 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta);
struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
+ struct ath12k_base *prev_ab = NULL, *ab;
struct ath12k_link_vif *arvif;
struct ath12k_link_sta *arsta;
unsigned long valid_links;
- u8 link_id = 0;
+ u16 selected_links = 0;
+ u8 link_id = 0, i;
+ struct ath12k *ar;
int ret;
lockdep_assert_wiphy(hw->wiphy);
@@ -5972,8 +6284,24 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
* about to move to the associated state.
*/
if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
- old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC)
- ieee80211_set_active_links(vif, ieee80211_vif_usable_links(vif));
+ old_state == IEEE80211_STA_AUTH && new_state == IEEE80211_STA_ASSOC) {
+ /* TODO: for now only do link selection for single device
+ * MLO case. Other cases would be handled in the future.
+ */
+ ab = ah->radio[0].ab;
+ if (ab->ag->num_devices == 1) {
+ ret = ath12k_mac_select_links(ab, vif, hw, &selected_links);
+ if (ret) {
+ ath12k_warn(ab,
+ "failed to get selected links: %d\n", ret);
+ goto exit;
+ }
+ } else {
+ selected_links = ieee80211_vif_usable_links(vif);
+ }
+
+ ieee80211_set_active_links(vif, selected_links);
+ }
/* Handle all the other state transitions in generic way */
valid_links = ahsta->links_map;
@@ -5997,6 +6325,24 @@ static int ath12k_mac_op_sta_state(struct ieee80211_hw *hw,
}
}
+ if (ieee80211_vif_is_mld(vif) && vif->type == NL80211_IFTYPE_STATION &&
+ old_state == IEEE80211_STA_ASSOC && new_state == IEEE80211_STA_AUTHORIZED) {
+ for_each_ar(ah, ar, i) {
+ ab = ar->ab;
+ if (prev_ab == ab)
+ continue;
+
+ ret = ath12k_mac_mlo_sta_update_link_active(ab, hw, ahvif);
+ if (ret) {
+ ath12k_warn(ab,
+ "failed to update link active state on connect %d\n",
+ ret);
+ goto exit;
+ }
+
+ prev_ab = ab;
+ }
+ }
/* IEEE80211_STA_NONE -> IEEE80211_STA_NOTEXIST:
* Remove the station from driver (handle ML sta here since that
* needs special handling. Normal sta will be handled in generic
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index e6e74b45bfa4..cc81b1f5680f 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -54,6 +54,8 @@ struct ath12k_generic_iter {
#define ATH12K_DEFAULT_SCAN_LINK IEEE80211_MLD_MAX_NUM_LINKS
#define ATH12K_NUM_MAX_LINKS (IEEE80211_MLD_MAX_NUM_LINKS + 1)
+#define ATH12K_NUM_MAX_ACTIVE_LINKS_PER_DEVICE 2
+
enum ath12k_supported_bw {
ATH12K_BW_20 = 0,
ATH12K_BW_40 = 1,
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 489d546390fc..1f3cfd9b89fd 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -292,10 +292,10 @@ static void ath12k_pci_enable_ltssm(struct ath12k_base *ab)
ath12k_dbg(ab, ATH12K_DBG_PCI, "pci ltssm 0x%x\n", val);
- val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+ val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
val |= GCC_GCC_PCIE_HOT_RST_VAL;
- ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST, val);
- val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST);
+ ath12k_pci_write32(ab, GCC_GCC_PCIE_HOT_RST(ab), val);
+ val = ath12k_pci_read32(ab, GCC_GCC_PCIE_HOT_RST(ab));
ath12k_dbg(ab, ATH12K_DBG_PCI, "pci pcie_hot_rst 0x%x\n", val);
diff --git a/drivers/net/wireless/ath/ath12k/pci.h b/drivers/net/wireless/ath/ath12k/pci.h
index 0b4c459d6d8e..d1ec8aad7f6c 100644
--- a/drivers/net/wireless/ath/ath12k/pci.h
+++ b/drivers/net/wireless/ath/ath12k/pci.h
@@ -28,7 +28,9 @@
#define PCIE_PCIE_PARF_LTSSM 0x1e081b0
#define PARM_LTSSM_VALUE 0x111
-#define GCC_GCC_PCIE_HOT_RST 0x1e38338
+#define GCC_GCC_PCIE_HOT_RST(ab) \
+ ((ab)->hw_params->regs->gcc_gcc_pcie_hot_rst)
+
#define GCC_GCC_PCIE_HOT_RST_VAL 0x10
#define PCIE_PCIE_INT_ALL_CLEAR 0x1e08228
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 60e2444fe08c..465f877fc0fb 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -91,6 +91,11 @@ struct ath12k_wmi_svc_rdy_ext2_parse {
bool dma_ring_cap_done;
bool spectral_bin_scaling_done;
bool mac_phy_caps_ext_done;
+ bool hal_reg_caps_ext2_done;
+ bool scan_radio_caps_ext2_done;
+ bool twt_caps_done;
+ bool htt_msdu_idx_to_qtype_map_done;
+ bool dbs_or_sbs_cap_ext_done;
};
struct ath12k_wmi_rdy_parse {
@@ -4395,6 +4400,7 @@ static int ath12k_wmi_hw_mode_caps_parse(struct ath12k_base *soc,
static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
u16 len, const void *ptr, void *data)
{
+ struct ath12k_svc_ext_info *svc_ext_info = &soc->wmi_ab.svc_ext_info;
struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext = data;
const struct ath12k_wmi_hw_mode_cap_params *hw_mode_caps;
enum wmi_host_hw_mode_config_type mode, pref;
@@ -4427,8 +4433,11 @@ static int ath12k_wmi_hw_mode_caps(struct ath12k_base *soc,
}
}
- ath12k_dbg(soc, ATH12K_DBG_WMI, "preferred_hw_mode:%d\n",
- soc->wmi_ab.preferred_hw_mode);
+ svc_ext_info->num_hw_modes = svc_rdy_ext->n_hw_mode_caps;
+
+ ath12k_dbg(soc, ATH12K_DBG_WMI, "num hw modes %u preferred_hw_mode %d\n",
+ svc_ext_info->num_hw_modes, soc->wmi_ab.preferred_hw_mode);
+
if (soc->wmi_ab.preferred_hw_mode == WMI_HOST_HW_MODE_MAX)
return -EINVAL;
@@ -4658,6 +4667,65 @@ free_dir_buff:
return ret;
}
+static void
+ath12k_wmi_save_mac_phy_info(struct ath12k_base *ab,
+ const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap,
+ struct ath12k_svc_ext_mac_phy_info *mac_phy_info)
+{
+ mac_phy_info->phy_id = __le32_to_cpu(mac_phy_cap->phy_id);
+ mac_phy_info->supported_bands = __le32_to_cpu(mac_phy_cap->supported_bands);
+ mac_phy_info->hw_freq_range.low_2ghz_freq =
+ __le32_to_cpu(mac_phy_cap->low_2ghz_chan_freq);
+ mac_phy_info->hw_freq_range.high_2ghz_freq =
+ __le32_to_cpu(mac_phy_cap->high_2ghz_chan_freq);
+ mac_phy_info->hw_freq_range.low_5ghz_freq =
+ __le32_to_cpu(mac_phy_cap->low_5ghz_chan_freq);
+ mac_phy_info->hw_freq_range.high_5ghz_freq =
+ __le32_to_cpu(mac_phy_cap->high_5ghz_chan_freq);
+}
+
+static void
+ath12k_wmi_save_all_mac_phy_info(struct ath12k_base *ab,
+ struct ath12k_wmi_svc_rdy_ext_parse *svc_rdy_ext)
+{
+ struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+ const struct ath12k_wmi_mac_phy_caps_params *mac_phy_cap;
+ const struct ath12k_wmi_hw_mode_cap_params *hw_mode_cap;
+ struct ath12k_svc_ext_mac_phy_info *mac_phy_info;
+ u32 hw_mode_id, phy_bit_map;
+ u8 hw_idx;
+
+ mac_phy_info = &svc_ext_info->mac_phy_info[0];
+ mac_phy_cap = svc_rdy_ext->mac_phy_caps;
+
+ for (hw_idx = 0; hw_idx < svc_ext_info->num_hw_modes; hw_idx++) {
+ hw_mode_cap = &svc_rdy_ext->hw_mode_caps[hw_idx];
+ hw_mode_id = __le32_to_cpu(hw_mode_cap->hw_mode_id);
+ phy_bit_map = __le32_to_cpu(hw_mode_cap->phy_id_map);
+
+ while (phy_bit_map) {
+ ath12k_wmi_save_mac_phy_info(ab, mac_phy_cap, mac_phy_info);
+ mac_phy_info->hw_mode_config_type =
+ le32_get_bits(hw_mode_cap->hw_mode_config_type,
+ WMI_HW_MODE_CAP_CFG_TYPE);
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "hw_idx %u hw_mode_id %u hw_mode_config_type %u supported_bands %u phy_id %u 2 GHz [%u - %u] 5 GHz [%u - %u]\n",
+ hw_idx, hw_mode_id,
+ mac_phy_info->hw_mode_config_type,
+ mac_phy_info->supported_bands, mac_phy_info->phy_id,
+ mac_phy_info->hw_freq_range.low_2ghz_freq,
+ mac_phy_info->hw_freq_range.high_2ghz_freq,
+ mac_phy_info->hw_freq_range.low_5ghz_freq,
+ mac_phy_info->hw_freq_range.high_5ghz_freq);
+
+ mac_phy_cap++;
+ mac_phy_info++;
+
+ phy_bit_map >>= 1;
+ }
+ }
+}
+
static int ath12k_wmi_svc_rdy_ext_parse(struct ath12k_base *ab,
u16 tag, u16 len,
const void *ptr, void *data)
@@ -4706,6 +4774,8 @@ static int ath12k_wmi_svc_rdy_ext_parse(struct ath12k_base *ab,
return ret;
}
+ ath12k_wmi_save_all_mac_phy_info(ab, svc_rdy_ext);
+
svc_rdy_ext->mac_phy_done = true;
} else if (!svc_rdy_ext->ext_hal_reg_done) {
ret = ath12k_wmi_ext_hal_reg_caps(ab, len, ptr, svc_rdy_ext);
@@ -4922,10 +4992,449 @@ static int ath12k_wmi_tlv_mac_phy_caps_ext(struct ath12k_base *ab, u16 tag,
return 0;
}
+static void
+ath12k_wmi_update_freq_info(struct ath12k_base *ab,
+ struct ath12k_svc_ext_mac_phy_info *mac_cap,
+ enum ath12k_hw_mode mode,
+ u32 phy_id)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *mac_range;
+
+ mac_range = &hw_mode_info->freq_range_caps[mode][phy_id];
+
+ if (mac_cap->supported_bands & WMI_HOST_WLAN_2GHZ_CAP) {
+ mac_range->low_2ghz_freq = max_t(u32,
+ mac_cap->hw_freq_range.low_2ghz_freq,
+ ATH12K_MIN_2GHZ_FREQ);
+ mac_range->high_2ghz_freq = mac_cap->hw_freq_range.high_2ghz_freq ?
+ min_t(u32,
+ mac_cap->hw_freq_range.high_2ghz_freq,
+ ATH12K_MAX_2GHZ_FREQ) :
+ ATH12K_MAX_2GHZ_FREQ;
+ }
+
+ if (mac_cap->supported_bands & WMI_HOST_WLAN_5GHZ_CAP) {
+ mac_range->low_5ghz_freq = max_t(u32,
+ mac_cap->hw_freq_range.low_5ghz_freq,
+ ATH12K_MIN_5GHZ_FREQ);
+ mac_range->high_5ghz_freq = mac_cap->hw_freq_range.high_5ghz_freq ?
+ min_t(u32,
+ mac_cap->hw_freq_range.high_5ghz_freq,
+ ATH12K_MAX_6GHZ_FREQ) :
+ ATH12K_MAX_6GHZ_FREQ;
+ }
+}
+
+static bool
+ath12k_wmi_all_phy_range_updated(struct ath12k_base *ab,
+ enum ath12k_hw_mode hwmode)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *mac_range;
+ u8 phy_id;
+
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ mac_range = &hw_mode_info->freq_range_caps[hwmode][phy_id];
+ /* modify SBS/DBS range only when both phy for DBS are filled */
+ if (!mac_range->low_2ghz_freq && !mac_range->low_5ghz_freq)
+ return false;
+ }
+
+ return true;
+}
+
+static void ath12k_wmi_update_dbs_freq_info(struct ath12k_base *ab)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *mac_range;
+ u8 phy_id;
+
+ mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_DBS];
+ /* Reset 5 GHz range for shared mac for DBS */
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ if (mac_range[phy_id].low_2ghz_freq &&
+ mac_range[phy_id].low_5ghz_freq) {
+ mac_range[phy_id].low_5ghz_freq = 0;
+ mac_range[phy_id].high_5ghz_freq = 0;
+ }
+ }
+}
+
+static u32
+ath12k_wmi_get_highest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+ u32 highest_freq = 0;
+ u8 phy_id;
+
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ if (range[phy_id].high_5ghz_freq > highest_freq)
+ highest_freq = range[phy_id].high_5ghz_freq;
+ }
+
+ return highest_freq ? highest_freq : ATH12K_MAX_6GHZ_FREQ;
+}
+
+static u32
+ath12k_wmi_get_lowest_5ghz_freq_from_range(struct ath12k_hw_mode_freq_range_arg *range)
+{
+ u32 lowest_freq = 0;
+ u8 phy_id;
+
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ if ((!lowest_freq && range[phy_id].low_5ghz_freq) ||
+ range[phy_id].low_5ghz_freq < lowest_freq)
+ lowest_freq = range[phy_id].low_5ghz_freq;
+ }
+
+ return lowest_freq ? lowest_freq : ATH12K_MIN_5GHZ_FREQ;
+}
+
+static void
+ath12k_wmi_fill_upper_share_sbs_freq(struct ath12k_base *ab,
+ u16 sbs_range_sep,
+ struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *upper_sbs_freq_range;
+ u8 phy_id;
+
+ upper_sbs_freq_range =
+ hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_UPPER_SHARE];
+
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ upper_sbs_freq_range[phy_id].low_2ghz_freq =
+ ref_freq[phy_id].low_2ghz_freq;
+ upper_sbs_freq_range[phy_id].high_2ghz_freq =
+ ref_freq[phy_id].high_2ghz_freq;
+
+ /* update for shared mac */
+ if (upper_sbs_freq_range[phy_id].low_2ghz_freq) {
+ upper_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+ upper_sbs_freq_range[phy_id].high_5ghz_freq =
+ ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+ } else {
+ upper_sbs_freq_range[phy_id].low_5ghz_freq =
+ ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+ upper_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+ }
+ }
+}
+
+static void
+ath12k_wmi_fill_lower_share_sbs_freq(struct ath12k_base *ab,
+ u16 sbs_range_sep,
+ struct ath12k_hw_mode_freq_range_arg *ref_freq)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *lower_sbs_freq_range;
+ u8 phy_id;
+
+ lower_sbs_freq_range =
+ hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS_LOWER_SHARE];
+
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ lower_sbs_freq_range[phy_id].low_2ghz_freq =
+ ref_freq[phy_id].low_2ghz_freq;
+ lower_sbs_freq_range[phy_id].high_2ghz_freq =
+ ref_freq[phy_id].high_2ghz_freq;
+
+ /* update for shared mac */
+ if (lower_sbs_freq_range[phy_id].low_2ghz_freq) {
+ lower_sbs_freq_range[phy_id].low_5ghz_freq =
+ ath12k_wmi_get_lowest_5ghz_freq_from_range(ref_freq);
+ lower_sbs_freq_range[phy_id].high_5ghz_freq = sbs_range_sep;
+ } else {
+ lower_sbs_freq_range[phy_id].low_5ghz_freq = sbs_range_sep + 10;
+ lower_sbs_freq_range[phy_id].high_5ghz_freq =
+ ath12k_wmi_get_highest_5ghz_freq_from_range(ref_freq);
+ }
+ }
+}
+
+static const char *ath12k_wmi_hw_mode_to_str(enum ath12k_hw_mode hw_mode)
+{
+ static const char * const mode_str[] = {
+ [ATH12K_HW_MODE_SMM] = "SMM",
+ [ATH12K_HW_MODE_DBS] = "DBS",
+ [ATH12K_HW_MODE_SBS] = "SBS",
+ [ATH12K_HW_MODE_SBS_UPPER_SHARE] = "SBS_UPPER_SHARE",
+ [ATH12K_HW_MODE_SBS_LOWER_SHARE] = "SBS_LOWER_SHARE",
+ };
+
+ if (hw_mode >= ARRAY_SIZE(mode_str))
+ return "Unknown";
+
+ return mode_str[hw_mode];
+}
+
+static void
+ath12k_wmi_dump_freq_range_per_mac(struct ath12k_base *ab,
+ struct ath12k_hw_mode_freq_range_arg *freq_range,
+ enum ath12k_hw_mode hw_mode)
+{
+ u8 i;
+
+ for (i = 0; i < MAX_RADIOS; i++)
+ if (freq_range[i].low_2ghz_freq || freq_range[i].low_5ghz_freq)
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "frequency range: %s(%d) mac %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+ ath12k_wmi_hw_mode_to_str(hw_mode),
+ hw_mode, i,
+ freq_range[i].low_2ghz_freq,
+ freq_range[i].high_2ghz_freq,
+ freq_range[i].low_5ghz_freq,
+ freq_range[i].high_5ghz_freq);
+}
+
+static void ath12k_wmi_dump_freq_range(struct ath12k_base *ab)
+{
+ struct ath12k_hw_mode_freq_range_arg *freq_range;
+ u8 i;
+
+ for (i = ATH12K_HW_MODE_SMM; i < ATH12K_HW_MODE_MAX; i++) {
+ freq_range = ab->wmi_ab.hw_mode_info.freq_range_caps[i];
+ ath12k_wmi_dump_freq_range_per_mac(ab, freq_range, i);
+ }
+}
+
+static int ath12k_wmi_modify_sbs_freq(struct ath12k_base *ab, u8 phy_id)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *sbs_mac_range, *shared_mac_range;
+ struct ath12k_hw_mode_freq_range_arg *non_shared_range;
+ u8 shared_phy_id;
+
+ sbs_mac_range = &hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][phy_id];
+
+ /* if SBS mac range has both 2.4 and 5 GHz ranges, i.e. shared phy_id
+ * keep the range as it is in SBS
+ */
+ if (sbs_mac_range->low_2ghz_freq && sbs_mac_range->low_5ghz_freq)
+ return 0;
+
+ if (sbs_mac_range->low_2ghz_freq && !sbs_mac_range->low_5ghz_freq) {
+ ath12k_err(ab, "Invalid DBS/SBS mode with only 2.4Ghz");
+ ath12k_wmi_dump_freq_range_per_mac(ab, sbs_mac_range, ATH12K_HW_MODE_SBS);
+ return -EINVAL;
+ }
+
+ non_shared_range = sbs_mac_range;
+ /* if SBS mac range has only 5 GHz then it's the non-shared phy, so
+ * modify the range as per the shared mac.
+ */
+ shared_phy_id = phy_id ? 0 : 1;
+ shared_mac_range =
+ &hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS][shared_phy_id];
+
+ if (shared_mac_range->low_5ghz_freq > non_shared_range->low_5ghz_freq) {
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "high 5 GHz shared");
+ /* If the shared mac lower 5 GHz frequency is greater than
+ * non-shared mac lower 5 GHz frequency then the shared mac has
+ * high 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz high
+ * freq should be less than the shared mac's low 5 GHz freq.
+ */
+ if (non_shared_range->high_5ghz_freq >=
+ shared_mac_range->low_5ghz_freq)
+ non_shared_range->high_5ghz_freq =
+ max_t(u32, shared_mac_range->low_5ghz_freq - 10,
+ non_shared_range->low_5ghz_freq);
+ } else if (shared_mac_range->high_5ghz_freq <
+ non_shared_range->high_5ghz_freq) {
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "low 5 GHz shared");
+ /* If the shared mac high 5 GHz frequency is less than
+ * non-shared mac high 5 GHz frequency then the shared mac has
+ * low 5 GHz shared with 2.4 GHz. So non-shared mac's 5 GHz low
+ * freq should be greater than the shared mac's high 5 GHz freq.
+ */
+ if (shared_mac_range->high_5ghz_freq >=
+ non_shared_range->low_5ghz_freq)
+ non_shared_range->low_5ghz_freq =
+ min_t(u32, shared_mac_range->high_5ghz_freq + 10,
+ non_shared_range->high_5ghz_freq);
+ } else {
+ ath12k_warn(ab, "invalid SBS range with all 5 GHz shared");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void ath12k_wmi_update_sbs_freq_info(struct ath12k_base *ab)
+{
+ struct ath12k_hw_mode_info *hw_mode_info = &ab->wmi_ab.hw_mode_info;
+ struct ath12k_hw_mode_freq_range_arg *mac_range;
+ u16 sbs_range_sep;
+ u8 phy_id;
+ int ret;
+
+ mac_range = hw_mode_info->freq_range_caps[ATH12K_HW_MODE_SBS];
+
+ /* If sbs_lower_band_end_freq has a value, then the frequency range
+ * will be split using that value.
+ */
+ sbs_range_sep = ab->wmi_ab.sbs_lower_band_end_freq;
+ if (sbs_range_sep) {
+ ath12k_wmi_fill_upper_share_sbs_freq(ab, sbs_range_sep,
+ mac_range);
+ ath12k_wmi_fill_lower_share_sbs_freq(ab, sbs_range_sep,
+ mac_range);
+ /* Hardware specifies the range boundary with sbs_range_sep,
+ * (i.e. the boundary between 5 GHz high and 5 GHz low),
+ * reset the original one to make sure it will not get used.
+ */
+ memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+ return;
+ }
+
+ /* If sbs_lower_band_end_freq is not set that means firmware will send one
+ * shared mac range and one non-shared mac range. so update that freq.
+ */
+ for (phy_id = 0; phy_id < MAX_RADIOS; phy_id++) {
+ ret = ath12k_wmi_modify_sbs_freq(ab, phy_id);
+ if (ret) {
+ memset(mac_range, 0, sizeof(*mac_range) * MAX_RADIOS);
+ break;
+ }
+ }
+}
+
+static void
+ath12k_wmi_update_mac_freq_info(struct ath12k_base *ab,
+ enum wmi_host_hw_mode_config_type hw_config_type,
+ u32 phy_id,
+ struct ath12k_svc_ext_mac_phy_info *mac_cap)
+{
+ if (phy_id >= MAX_RADIOS) {
+ ath12k_err(ab, "mac more than two not supported: %d", phy_id);
+ return;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "hw_mode_cfg %d mac %d band 0x%x SBS cutoff freq %d 2 GHz [%d - %d] 5 GHz [%d - %d]",
+ hw_config_type, phy_id, mac_cap->supported_bands,
+ ab->wmi_ab.sbs_lower_band_end_freq,
+ mac_cap->hw_freq_range.low_2ghz_freq,
+ mac_cap->hw_freq_range.high_2ghz_freq,
+ mac_cap->hw_freq_range.low_5ghz_freq,
+ mac_cap->hw_freq_range.high_5ghz_freq);
+
+ switch (hw_config_type) {
+ case WMI_HOST_HW_MODE_SINGLE:
+ if (phy_id) {
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "mac phy 1 is not supported");
+ break;
+ }
+ ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SMM, phy_id);
+ break;
+
+ case WMI_HOST_HW_MODE_DBS:
+ if (!ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+ ath12k_wmi_update_freq_info(ab, mac_cap,
+ ATH12K_HW_MODE_DBS, phy_id);
+ break;
+ case WMI_HOST_HW_MODE_DBS_SBS:
+ case WMI_HOST_HW_MODE_DBS_OR_SBS:
+ ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_DBS, phy_id);
+ if (ab->wmi_ab.sbs_lower_band_end_freq ||
+ mac_cap->hw_freq_range.low_5ghz_freq ||
+ mac_cap->hw_freq_range.low_2ghz_freq)
+ ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS,
+ phy_id);
+
+ if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_DBS))
+ ath12k_wmi_update_dbs_freq_info(ab);
+ if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+ ath12k_wmi_update_sbs_freq_info(ab);
+ break;
+ case WMI_HOST_HW_MODE_SBS:
+ case WMI_HOST_HW_MODE_SBS_PASSIVE:
+ ath12k_wmi_update_freq_info(ab, mac_cap, ATH12K_HW_MODE_SBS, phy_id);
+ if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS))
+ ath12k_wmi_update_sbs_freq_info(ab);
+
+ break;
+ default:
+ break;
+ }
+}
+
+static bool ath12k_wmi_sbs_range_present(struct ath12k_base *ab)
+{
+ if (ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS) ||
+ (ab->wmi_ab.sbs_lower_band_end_freq &&
+ ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_LOWER_SHARE) &&
+ ath12k_wmi_all_phy_range_updated(ab, ATH12K_HW_MODE_SBS_UPPER_SHARE)))
+ return true;
+
+ return false;
+}
+
+static int ath12k_wmi_update_hw_mode_list(struct ath12k_base *ab)
+{
+ struct ath12k_svc_ext_info *svc_ext_info = &ab->wmi_ab.svc_ext_info;
+ struct ath12k_hw_mode_info *info = &ab->wmi_ab.hw_mode_info;
+ enum wmi_host_hw_mode_config_type hw_config_type;
+ struct ath12k_svc_ext_mac_phy_info *tmp;
+ bool dbs_mode = false, sbs_mode = false;
+ u32 i, j = 0;
+
+ if (!svc_ext_info->num_hw_modes) {
+ ath12k_err(ab, "invalid number of hw modes");
+ return -EINVAL;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "updated HW mode list: num modes %d",
+ svc_ext_info->num_hw_modes);
+
+ memset(info->freq_range_caps, 0, sizeof(info->freq_range_caps));
+
+ for (i = 0; i < svc_ext_info->num_hw_modes; i++) {
+ if (j >= ATH12K_MAX_MAC_PHY_CAP)
+ return -EINVAL;
+
+ /* Update for MAC0 */
+ tmp = &svc_ext_info->mac_phy_info[j++];
+ hw_config_type = tmp->hw_mode_config_type;
+ ath12k_wmi_update_mac_freq_info(ab, hw_config_type, tmp->phy_id, tmp);
+
+ /* SBS and DBS have dual MAC. Up to 2 MACs are considered. */
+ if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+ hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+ hw_config_type == WMI_HOST_HW_MODE_SBS ||
+ hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS) {
+ if (j >= ATH12K_MAX_MAC_PHY_CAP)
+ return -EINVAL;
+ /* Update for MAC1 */
+ tmp = &svc_ext_info->mac_phy_info[j++];
+ ath12k_wmi_update_mac_freq_info(ab, hw_config_type,
+ tmp->phy_id, tmp);
+
+ if (hw_config_type == WMI_HOST_HW_MODE_DBS ||
+ hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS)
+ dbs_mode = true;
+
+ if (ath12k_wmi_sbs_range_present(ab) &&
+ (hw_config_type == WMI_HOST_HW_MODE_SBS_PASSIVE ||
+ hw_config_type == WMI_HOST_HW_MODE_SBS ||
+ hw_config_type == WMI_HOST_HW_MODE_DBS_OR_SBS))
+ sbs_mode = true;
+ }
+ }
+
+ info->support_dbs = dbs_mode;
+ info->support_sbs = sbs_mode;
+
+ ath12k_wmi_dump_freq_range(ab);
+
+ return 0;
+}
+
static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
u16 tag, u16 len,
const void *ptr, void *data)
{
+ const struct ath12k_wmi_dbs_or_sbs_cap_params *dbs_or_sbs_caps;
struct ath12k_wmi_pdev *wmi_handle = &ab->wmi_ab.wmi[0];
struct ath12k_wmi_svc_rdy_ext2_parse *parse = data;
int ret;
@@ -4967,7 +5476,32 @@ static int ath12k_wmi_svc_rdy_ext2_parse(struct ath12k_base *ab,
}
parse->mac_phy_caps_ext_done = true;
+ } else if (!parse->hal_reg_caps_ext2_done) {
+ parse->hal_reg_caps_ext2_done = true;
+ } else if (!parse->scan_radio_caps_ext2_done) {
+ parse->scan_radio_caps_ext2_done = true;
+ } else if (!parse->twt_caps_done) {
+ parse->twt_caps_done = true;
+ } else if (!parse->htt_msdu_idx_to_qtype_map_done) {
+ parse->htt_msdu_idx_to_qtype_map_done = true;
+ } else if (!parse->dbs_or_sbs_cap_ext_done) {
+ dbs_or_sbs_caps = ptr;
+ ab->wmi_ab.sbs_lower_band_end_freq =
+ __le32_to_cpu(dbs_or_sbs_caps->sbs_lower_band_end_freq);
+
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "sbs_lower_band_end_freq %u\n",
+ ab->wmi_ab.sbs_lower_band_end_freq);
+
+ ret = ath12k_wmi_update_hw_mode_list(ab);
+ if (ret) {
+ ath12k_warn(ab, "failed to update hw mode list: %d\n",
+ ret);
+ return ret;
+ }
+
+ parse->dbs_or_sbs_cap_ext_done = true;
}
+
break;
default:
break;
@@ -7626,6 +8160,64 @@ static int ath12k_wmi_pull_fw_stats(struct ath12k_base *ab, struct sk_buff *skb,
&parse);
}
+static void ath12k_wmi_fw_stats_process(struct ath12k *ar,
+ struct ath12k_fw_stats *stats)
+{
+ struct ath12k_base *ab = ar->ab;
+ struct ath12k_pdev *pdev;
+ bool is_end = true;
+ size_t total_vdevs_started = 0;
+ int i;
+
+ if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
+ if (list_empty(&stats->vdevs)) {
+ ath12k_warn(ab, "empty vdev stats");
+ return;
+ }
+ /* FW sends all the active VDEV stats irrespective of PDEV,
+ * hence limit until the count of all VDEVs started
+ */
+ rcu_read_lock();
+ for (i = 0; i < ab->num_radios; i++) {
+ pdev = rcu_dereference(ab->pdevs_active[i]);
+ if (pdev && pdev->ar)
+ total_vdevs_started += pdev->ar->num_started_vdevs;
+ }
+ rcu_read_unlock();
+
+ if (total_vdevs_started)
+ is_end = ((++ar->fw_stats.num_vdev_recvd) ==
+ total_vdevs_started);
+
+ list_splice_tail_init(&stats->vdevs,
+ &ar->fw_stats.vdevs);
+
+ if (is_end)
+ complete(&ar->fw_stats_done);
+
+ return;
+ }
+
+ if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
+ if (list_empty(&stats->bcn)) {
+ ath12k_warn(ab, "empty beacon stats");
+ return;
+ }
+ /* Mark end until we reached the count of all started VDEVs
+ * within the PDEV
+ */
+ if (ar->num_started_vdevs)
+ is_end = ((++ar->fw_stats.num_bcn_recvd) ==
+ ar->num_started_vdevs);
+
+ list_splice_tail_init(&stats->bcn,
+ &ar->fw_stats.bcn);
+
+ if (is_end)
+ complete(&ar->fw_stats_done);
+ }
+}
+
static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *skb)
{
struct ath12k_fw_stats stats = {};
@@ -7655,19 +8247,15 @@ static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *sk
spin_lock_bh(&ar->data_lock);
- /* WMI_REQUEST_PDEV_STAT can be requested via .get_txpower mac ops or via
- * debugfs fw stats. Therefore, processing it separately.
- */
+ /* Handle WMI_REQUEST_PDEV_STAT status update */
if (stats.stats_id == WMI_REQUEST_PDEV_STAT) {
list_splice_tail_init(&stats.pdevs, &ar->fw_stats.pdevs);
- ar->fw_stats.fw_stats_done = true;
+ complete(&ar->fw_stats_done);
goto complete;
}
- /* WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT are currently requested only
- * via debugfs fw stats. Hence, processing these in debugfs context.
- */
- ath12k_debugfs_fw_stats_process(ar, &stats);
+ /* Handle WMI_REQUEST_VDEV_STAT and WMI_REQUEST_BCN_STAT updates. */
+ ath12k_wmi_fw_stats_process(ar, &stats);
complete:
complete(&ar->fw_stats_complete);
@@ -9911,3 +10499,224 @@ int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
return 0;
}
+
+static int
+ath12k_wmi_fill_disallowed_bmap(struct ath12k_base *ab,
+ struct wmi_disallowed_mlo_mode_bitmap_params *dislw_bmap,
+ struct wmi_mlo_link_set_active_arg *arg)
+{
+ struct wmi_ml_disallow_mode_bmap_arg *dislw_bmap_arg;
+ u8 i;
+
+ if (arg->num_disallow_mode_comb >
+ ARRAY_SIZE(arg->disallow_bmap)) {
+ ath12k_warn(ab, "invalid num_disallow_mode_comb: %d",
+ arg->num_disallow_mode_comb);
+ return -EINVAL;
+ }
+
+ dislw_bmap_arg = &arg->disallow_bmap[0];
+ for (i = 0; i < arg->num_disallow_mode_comb; i++) {
+ dislw_bmap->tlv_header =
+ ath12k_wmi_tlv_cmd_hdr(0, sizeof(*dislw_bmap));
+ dislw_bmap->disallowed_mode_bitmap =
+ cpu_to_le32(dislw_bmap_arg->disallowed_mode);
+ dislw_bmap->ieee_link_id_comb =
+ le32_encode_bits(dislw_bmap_arg->ieee_link_id[0],
+ WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1) |
+ le32_encode_bits(dislw_bmap_arg->ieee_link_id[1],
+ WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2) |
+ le32_encode_bits(dislw_bmap_arg->ieee_link_id[2],
+ WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3) |
+ le32_encode_bits(dislw_bmap_arg->ieee_link_id[3],
+ WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4);
+
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "entry %d disallowed_mode %d ieee_link_id_comb 0x%x",
+ i, dislw_bmap_arg->disallowed_mode,
+ dislw_bmap_arg->ieee_link_id_comb);
+ dislw_bmap++;
+ dislw_bmap_arg++;
+ }
+
+ return 0;
+}
+
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+ struct wmi_mlo_link_set_active_arg *arg)
+{
+ struct wmi_disallowed_mlo_mode_bitmap_params *disallowed_mode_bmap;
+ struct wmi_mlo_set_active_link_number_params *link_num_param;
+ u32 num_link_num_param = 0, num_vdev_bitmap = 0;
+ struct ath12k_wmi_base *wmi_ab = &ab->wmi_ab;
+ struct wmi_mlo_link_set_active_cmd *cmd;
+ u32 num_inactive_vdev_bitmap = 0;
+ u32 num_disallow_mode_comb = 0;
+ struct wmi_tlv *tlv;
+ struct sk_buff *skb;
+ __le32 *vdev_bitmap;
+ void *buf_ptr;
+ int i, ret;
+ u32 len;
+
+ if (!arg->num_vdev_bitmap && !arg->num_link_entry) {
+ ath12k_warn(ab, "Invalid num_vdev_bitmap and num_link_entry");
+ return -EINVAL;
+ }
+
+ switch (arg->force_mode) {
+ case WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM:
+ case WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM:
+ num_link_num_param = arg->num_link_entry;
+ fallthrough;
+ case WMI_MLO_LINK_FORCE_MODE_ACTIVE:
+ case WMI_MLO_LINK_FORCE_MODE_INACTIVE:
+ case WMI_MLO_LINK_FORCE_MODE_NO_FORCE:
+ num_vdev_bitmap = arg->num_vdev_bitmap;
+ break;
+ case WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE:
+ num_vdev_bitmap = arg->num_vdev_bitmap;
+ num_inactive_vdev_bitmap = arg->num_inactive_vdev_bitmap;
+ break;
+ default:
+ ath12k_warn(ab, "Invalid force mode: %u", arg->force_mode);
+ return -EINVAL;
+ }
+
+ num_disallow_mode_comb = arg->num_disallow_mode_comb;
+ len = sizeof(*cmd) +
+ TLV_HDR_SIZE + sizeof(*link_num_param) * num_link_num_param +
+ TLV_HDR_SIZE + sizeof(*vdev_bitmap) * num_vdev_bitmap +
+ TLV_HDR_SIZE + TLV_HDR_SIZE + TLV_HDR_SIZE +
+ TLV_HDR_SIZE + sizeof(*disallowed_mode_bmap) * num_disallow_mode_comb;
+ if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE)
+ len += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+
+ skb = ath12k_wmi_alloc_skb(wmi_ab, len);
+ if (!skb)
+ return -ENOMEM;
+
+ cmd = (struct wmi_mlo_link_set_active_cmd *)skb->data;
+ cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_MLO_LINK_SET_ACTIVE_CMD,
+ sizeof(*cmd));
+ cmd->force_mode = cpu_to_le32(arg->force_mode);
+ cmd->reason = cpu_to_le32(arg->reason);
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "mode %d reason %d num_link_num_param %d num_vdev_bitmap %d inactive %d num_disallow_mode_comb %d",
+ arg->force_mode, arg->reason, num_link_num_param,
+ num_vdev_bitmap, num_inactive_vdev_bitmap,
+ num_disallow_mode_comb);
+
+ buf_ptr = skb->data + sizeof(*cmd);
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+ sizeof(*link_num_param) * num_link_num_param);
+ buf_ptr += TLV_HDR_SIZE;
+
+ if (num_link_num_param) {
+ cmd->ctrl_flags =
+ le32_encode_bits(arg->ctrl_flags.dync_force_link_num ? 1 : 0,
+ CRTL_F_DYNC_FORCE_LINK_NUM);
+
+ link_num_param = buf_ptr;
+ for (i = 0; i < num_link_num_param; i++) {
+ link_num_param->tlv_header =
+ ath12k_wmi_tlv_cmd_hdr(0, sizeof(*link_num_param));
+ link_num_param->num_of_link =
+ cpu_to_le32(arg->link_num[i].num_of_link);
+ link_num_param->vdev_type =
+ cpu_to_le32(arg->link_num[i].vdev_type);
+ link_num_param->vdev_subtype =
+ cpu_to_le32(arg->link_num[i].vdev_subtype);
+ link_num_param->home_freq =
+ cpu_to_le32(arg->link_num[i].home_freq);
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "entry %d num_of_link %d vdev type %d subtype %d freq %d control_flags %d",
+ i, arg->link_num[i].num_of_link,
+ arg->link_num[i].vdev_type,
+ arg->link_num[i].vdev_subtype,
+ arg->link_num[i].home_freq,
+ __le32_to_cpu(cmd->ctrl_flags));
+ link_num_param++;
+ }
+
+ buf_ptr += sizeof(*link_num_param) * num_link_num_param;
+ }
+
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+ sizeof(*vdev_bitmap) * num_vdev_bitmap);
+ buf_ptr += TLV_HDR_SIZE;
+
+ if (num_vdev_bitmap) {
+ vdev_bitmap = buf_ptr;
+ for (i = 0; i < num_vdev_bitmap; i++) {
+ vdev_bitmap[i] = cpu_to_le32(arg->vdev_bitmap[i]);
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "entry %d vdev_id_bitmap 0x%x",
+ i, arg->vdev_bitmap[i]);
+ }
+
+ buf_ptr += sizeof(*vdev_bitmap) * num_vdev_bitmap;
+ }
+
+ if (arg->force_mode == WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE) {
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32,
+ sizeof(*vdev_bitmap) *
+ num_inactive_vdev_bitmap);
+ buf_ptr += TLV_HDR_SIZE;
+
+ if (num_inactive_vdev_bitmap) {
+ vdev_bitmap = buf_ptr;
+ for (i = 0; i < num_inactive_vdev_bitmap; i++) {
+ vdev_bitmap[i] =
+ cpu_to_le32(arg->inactive_vdev_bitmap[i]);
+ ath12k_dbg(ab, ATH12K_DBG_WMI,
+ "entry %d inactive_vdev_id_bitmap 0x%x",
+ i, arg->inactive_vdev_bitmap[i]);
+ }
+
+ buf_ptr += sizeof(*vdev_bitmap) * num_inactive_vdev_bitmap;
+ }
+ } else {
+ /* add empty vdev bitmap2 tlv */
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+ buf_ptr += TLV_HDR_SIZE;
+ }
+
+ /* add empty ieee_link_id_bitmap tlv */
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+ buf_ptr += TLV_HDR_SIZE;
+
+ /* add empty ieee_link_id_bitmap2 tlv */
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+ buf_ptr += TLV_HDR_SIZE;
+
+ tlv = buf_ptr;
+ tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_STRUCT,
+ sizeof(*disallowed_mode_bmap) *
+ arg->num_disallow_mode_comb);
+ buf_ptr += TLV_HDR_SIZE;
+
+ ret = ath12k_wmi_fill_disallowed_bmap(ab, buf_ptr, arg);
+ if (ret)
+ goto free_skb;
+
+ ret = ath12k_wmi_cmd_send(&wmi_ab->wmi[0], skb, WMI_MLO_LINK_SET_ACTIVE_CMDID);
+ if (ret) {
+ ath12k_warn(ab,
+ "failed to send WMI_MLO_LINK_SET_ACTIVE_CMDID: %d\n", ret);
+ goto free_skb;
+ }
+
+ ath12k_dbg(ab, ATH12K_DBG_WMI, "WMI mlo link set active cmd");
+
+ return ret;
+
+free_skb:
+ dev_kfree_skb(skb);
+ return ret;
+}
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index ac18f75e0449..c640ffa180c8 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1974,6 +1974,7 @@ enum wmi_tlv_tag {
WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT,
WMI_TAG_VDEV_SET_TPC_POWER_CMD = 0x3B5,
WMI_TAG_VDEV_CH_POWER_INFO,
+ WMI_TAG_MLO_LINK_SET_ACTIVE_CMD = 0x3BE,
WMI_TAG_EHT_RATE_SET = 0x3C4,
WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5,
WMI_TAG_MLO_TX_SEND_PARAMS,
@@ -2617,6 +2618,8 @@ struct ath12k_wmi_soc_mac_phy_hw_mode_caps_params {
__le32 num_chainmask_tables;
} __packed;
+#define WMI_HW_MODE_CAP_CFG_TYPE GENMASK(27, 0)
+
struct ath12k_wmi_hw_mode_cap_params {
__le32 tlv_header;
__le32 hw_mode_id;
@@ -2666,6 +2669,12 @@ struct ath12k_wmi_mac_phy_caps_params {
__le32 he_cap_info_2g_ext;
__le32 he_cap_info_5g_ext;
__le32 he_cap_info_internal;
+ __le32 wireless_modes;
+ __le32 low_2ghz_chan_freq;
+ __le32 high_2ghz_chan_freq;
+ __le32 low_5ghz_chan_freq;
+ __le32 high_5ghz_chan_freq;
+ __le32 nss_ratio;
} __packed;
struct ath12k_wmi_hal_reg_caps_ext_params {
@@ -2739,6 +2748,11 @@ struct wmi_service_ready_ext2_event {
__le32 default_num_msduq_supported_per_tid;
} __packed;
+struct ath12k_wmi_dbs_or_sbs_cap_params {
+ __le32 hw_mode_id;
+ __le32 sbs_lower_band_end_freq;
+} __packed;
+
struct ath12k_wmi_caps_ext_params {
__le32 hw_mode_id;
__le32 pdev_and_hw_link_ids;
@@ -5049,6 +5063,53 @@ struct ath12k_wmi_pdev {
u32 rx_decap_mode;
};
+struct ath12k_hw_mode_freq_range_arg {
+ u32 low_2ghz_freq;
+ u32 high_2ghz_freq;
+ u32 low_5ghz_freq;
+ u32 high_5ghz_freq;
+};
+
+struct ath12k_svc_ext_mac_phy_info {
+ enum wmi_host_hw_mode_config_type hw_mode_config_type;
+ u32 phy_id;
+ u32 supported_bands;
+ struct ath12k_hw_mode_freq_range_arg hw_freq_range;
+};
+
+#define ATH12K_MAX_MAC_PHY_CAP 8
+
+struct ath12k_svc_ext_info {
+ u32 num_hw_modes;
+ struct ath12k_svc_ext_mac_phy_info mac_phy_info[ATH12K_MAX_MAC_PHY_CAP];
+};
+
+/**
+ * enum ath12k_hw_mode - enum for host mode
+ * @ATH12K_HW_MODE_SMM: Single mac mode
+ * @ATH12K_HW_MODE_DBS: DBS mode
+ * @ATH12K_HW_MODE_SBS: SBS mode with either high share or low share
+ * @ATH12K_HW_MODE_SBS_UPPER_SHARE: Higher 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_SBS_LOWER_SHARE: Lower 5 GHz shared with 2.4 GHz
+ * @ATH12K_HW_MODE_MAX: Max, used to indicate invalid mode
+ */
+enum ath12k_hw_mode {
+ ATH12K_HW_MODE_SMM,
+ ATH12K_HW_MODE_DBS,
+ ATH12K_HW_MODE_SBS,
+ ATH12K_HW_MODE_SBS_UPPER_SHARE,
+ ATH12K_HW_MODE_SBS_LOWER_SHARE,
+ ATH12K_HW_MODE_MAX,
+};
+
+struct ath12k_hw_mode_info {
+ bool support_dbs:1;
+ bool support_sbs:1;
+
+ struct ath12k_hw_mode_freq_range_arg freq_range_caps[ATH12K_HW_MODE_MAX]
+ [MAX_RADIOS];
+};
+
struct ath12k_wmi_base {
struct ath12k_base *ab;
struct ath12k_wmi_pdev wmi[MAX_RADIOS];
@@ -5066,6 +5127,10 @@ struct ath12k_wmi_base {
enum wmi_host_hw_mode_config_type preferred_hw_mode;
struct ath12k_wmi_target_cap_arg *targ_cap;
+
+ struct ath12k_svc_ext_info svc_ext_info;
+ u32 sbs_lower_band_end_freq;
+ struct ath12k_hw_mode_info hw_mode_info;
};
struct wmi_pdev_set_bios_interface_cmd {
@@ -5997,6 +6062,118 @@ struct wmi_vdev_set_tpc_power_cmd {
*/
} __packed;
+#define CRTL_F_DYNC_FORCE_LINK_NUM GENMASK(3, 2)
+
+struct wmi_mlo_link_set_active_cmd {
+ __le32 tlv_header;
+ __le32 force_mode;
+ __le32 reason;
+ __le32 use_ieee_link_id_bitmap;
+ struct ath12k_wmi_mac_addr_params ap_mld_mac_addr;
+ __le32 ctrl_flags;
+} __packed;
+
+struct wmi_mlo_set_active_link_number_params {
+ __le32 tlv_header;
+ __le32 num_of_link;
+ __le32 vdev_type;
+ __le32 vdev_subtype;
+ __le32 home_freq;
+} __packed;
+
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_1 GENMASK(7, 0)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_2 GENMASK(15, 8)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_3 GENMASK(23, 16)
+#define WMI_DISALW_MLO_MODE_BMAP_IEEE_LINK_ID_COMB_4 GENMASK(31, 24)
+
+struct wmi_disallowed_mlo_mode_bitmap_params {
+ __le32 tlv_header;
+ __le32 disallowed_mode_bitmap;
+ __le32 ieee_link_id_comb;
+} __packed;
+
+enum wmi_mlo_link_force_mode {
+ WMI_MLO_LINK_FORCE_MODE_ACTIVE = 1,
+ WMI_MLO_LINK_FORCE_MODE_INACTIVE = 2,
+ WMI_MLO_LINK_FORCE_MODE_ACTIVE_LINK_NUM = 3,
+ WMI_MLO_LINK_FORCE_MODE_INACTIVE_LINK_NUM = 4,
+ WMI_MLO_LINK_FORCE_MODE_NO_FORCE = 5,
+ WMI_MLO_LINK_FORCE_MODE_ACTIVE_INACTIVE = 6,
+ WMI_MLO_LINK_FORCE_MODE_NON_FORCE_UPDATE = 7,
+};
+
+enum wmi_mlo_link_force_reason {
+ WMI_MLO_LINK_FORCE_REASON_NEW_CONNECT = 1,
+ WMI_MLO_LINK_FORCE_REASON_NEW_DISCONNECT = 2,
+ WMI_MLO_LINK_FORCE_REASON_LINK_REMOVAL = 3,
+ WMI_MLO_LINK_FORCE_REASON_TDLS = 4,
+ WMI_MLO_LINK_FORCE_REASON_REVERT_FAILURE = 5,
+ WMI_MLO_LINK_FORCE_REASON_LINK_DELETE = 6,
+ WMI_MLO_LINK_FORCE_REASON_SINGLE_LINK_EMLSR_OP = 7,
+};
+
+struct wmi_mlo_link_num_arg {
+ u32 num_of_link;
+ u32 vdev_type;
+ u32 vdev_subtype;
+ u32 home_freq;
+};
+
+struct wmi_mlo_control_flags_arg {
+ bool overwrite_force_active_bitmap;
+ bool overwrite_force_inactive_bitmap;
+ bool dync_force_link_num;
+ bool post_re_evaluate;
+ u8 post_re_evaluate_loops;
+ bool dont_reschedule_workqueue;
+};
+
+struct wmi_ml_link_force_cmd_arg {
+ u8 ap_mld_mac_addr[ETH_ALEN];
+ u16 ieee_link_id_bitmap;
+ u16 ieee_link_id_bitmap2;
+ u8 link_num;
+};
+
+struct wmi_ml_disallow_mode_bmap_arg {
+ u32 disallowed_mode;
+ union {
+ u32 ieee_link_id_comb;
+ u8 ieee_link_id[4];
+ };
+};
+
+/* maximum size of link number param array
+ * for MLO link set active command
+ */
+#define WMI_MLO_LINK_NUM_SZ 2
+
+/* maximum size of vdev bitmap array for
+ * MLO link set active command
+ */
+#define WMI_MLO_VDEV_BITMAP_SZ 2
+
+/* Max number of disallowed bitmap combination
+ * sent to firmware
+ */
+#define WMI_ML_MAX_DISALLOW_BMAP_COMB 4
+
+struct wmi_mlo_link_set_active_arg {
+ enum wmi_mlo_link_force_mode force_mode;
+ enum wmi_mlo_link_force_reason reason;
+ u32 num_link_entry;
+ u32 num_vdev_bitmap;
+ u32 num_inactive_vdev_bitmap;
+ struct wmi_mlo_link_num_arg link_num[WMI_MLO_LINK_NUM_SZ];
+ u32 vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+ u32 inactive_vdev_bitmap[WMI_MLO_VDEV_BITMAP_SZ];
+ struct wmi_mlo_control_flags_arg ctrl_flags;
+ bool use_ieee_link_id;
+ struct wmi_ml_link_force_cmd_arg force_cmd;
+ u32 num_disallow_mode_comb;
+ struct wmi_ml_disallow_mode_bmap_arg disallow_bmap[WMI_ML_MAX_DISALLOW_BMAP_COMB];
+};
+
void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
struct ath12k_wmi_resource_config_arg *config);
void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -6195,5 +6372,6 @@ bool ath12k_wmi_supports_6ghz_cc_ext(struct ath12k *ar);
int ath12k_wmi_send_vdev_set_tpc_power(struct ath12k *ar,
u32 vdev_id,
struct ath12k_reg_tpc_power_info *param);
-
+int ath12k_wmi_send_mlo_link_set_active_cmd(struct ath12k_base *ab,
+ struct wmi_mlo_link_set_active_arg *param);
#endif
diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index af98e871199d..5a9e93fd1ef4 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -87,7 +87,9 @@ int ath6kl_bmi_get_target_info(struct ath6kl *ar,
* We need to do some backwards compatibility to make this work.
*/
if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) {
- WARN_ON(1);
+ ath6kl_err("mismatched byte count %d vs. expected %zd\n",
+ le32_to_cpu(targ_info->byte_count),
+ sizeof(*targ_info));
return -EINVAL;
}
diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c
index a3e03580cd9f..564ca6a61985 100644
--- a/drivers/net/wireless/ath/carl9170/usb.c
+++ b/drivers/net/wireless/ath/carl9170/usb.c
@@ -438,14 +438,21 @@ static void carl9170_usb_rx_complete(struct urb *urb)
if (atomic_read(&ar->rx_anch_urbs) == 0) {
/*
- * The system is too slow to cope with
- * the enormous workload. We have simply
- * run out of active rx urbs and this
- * unfortunately leads to an unpredictable
- * device.
+ * At this point, either the system is too slow to
+ * cope with the enormous workload (so we have simply
+ * run out of active rx urbs and this unfortunately
+ * leads to an unpredictable device), or the device
+ * is not fully functional after an unsuccessful
+ * firmware loading attempts (so it doesn't pass
+ * ieee80211_register_hw() and there is no internal
+ * workqueue at all).
*/
- ieee80211_queue_work(ar->hw, &ar->ping_work);
+ if (ar->registered)
+ ieee80211_queue_work(ar->hw, &ar->ping_work);
+ else
+ pr_warn_once("device %s is not registered\n",
+ dev_name(&ar->udev->dev));
}
} else {
/*
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 67172385a5d6..89d4394cedcf 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -179,9 +179,11 @@ void wil_mask_irq(struct wil6210_priv *wil)
wil_dbg_irq(wil, "mask_irq\n");
wil6210_mask_irq_tx(wil);
- wil6210_mask_irq_tx_edma(wil);
+ if (wil->use_enhanced_dma_hw)
+ wil6210_mask_irq_tx_edma(wil);
wil6210_mask_irq_rx(wil);
- wil6210_mask_irq_rx_edma(wil);
+ if (wil->use_enhanced_dma_hw)
+ wil6210_mask_irq_rx_edma(wil);
wil6210_mask_irq_misc(wil, true);
wil6210_mask_irq_pseudo(wil);
}
@@ -190,10 +192,12 @@ void wil_unmask_irq(struct wil6210_priv *wil)
{
wil_dbg_irq(wil, "unmask_irq\n");
- wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, ICC),
- WIL_ICR_ICC_VALUE);
- wil_w(wil, RGF_DMA_EP_TX_ICR + offsetof(struct RGF_ICR, ICC),
- WIL_ICR_ICC_VALUE);
+ if (wil->use_enhanced_dma_hw) {
+ wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, ICC),
+ WIL_ICR_ICC_VALUE);
+ wil_w(wil, RGF_DMA_EP_TX_ICR + offsetof(struct RGF_ICR, ICC),
+ WIL_ICR_ICC_VALUE);
+ }
wil_w(wil, RGF_DMA_EP_MISC_ICR + offsetof(struct RGF_ICR, ICC),
WIL_ICR_ICC_MISC_VALUE);
wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, ICC),
@@ -845,10 +849,12 @@ void wil6210_clear_irq(struct wil6210_priv *wil)
offsetof(struct RGF_ICR, ICR));
wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_TX_ICR) +
offsetof(struct RGF_ICR, ICR));
- wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
- offsetof(struct RGF_ICR, ICR));
- wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
- offsetof(struct RGF_ICR, ICR));
+ if (wil->use_enhanced_dma_hw) {
+ wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
+ offsetof(struct RGF_ICR, ICR));
+ wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
+ offsetof(struct RGF_ICR, ICR));
+ }
wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_MISC_ICR) +
offsetof(struct RGF_ICR, ICR));
wmb(); /* make sure write completed */
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index 0e5130d1fccd..031d88bf6393 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -203,7 +203,8 @@ il4965_rs_extract_rate(u32 rate_n_flags)
return (u8) (rate_n_flags & 0xFF);
}
-static void
+/* noinline works around https://github.com/llvm/llvm-project/issues/143908 */
+static noinline_for_stack void
il4965_rs_rate_scale_clear_win(struct il_rate_scale_data *win)
{
win->data = 0;
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
index dbfd45948e8b..66211426aa3a 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c
@@ -1316,6 +1316,7 @@ static struct iwl_op_mode *iwl_op_mode_dvm_start(struct iwl_trans *trans,
sizeof(trans->conf.no_reclaim_cmds));
memcpy(trans->conf.no_reclaim_cmds, no_reclaim_cmds,
sizeof(no_reclaim_cmds));
+ trans->conf.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds);
switch (iwlwifi_mod_params.amsdu_size) {
case IWL_AMSDU_DEF:
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index e8820e7cf8fa..1774bb84dd3f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -77,6 +77,7 @@ void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
/* Setup async RX handling */
spin_lock_init(&mld->async_handlers_lock);
+ INIT_LIST_HEAD(&mld->async_handlers_list);
wiphy_work_init(&mld->async_handlers_wk,
iwl_mld_async_handlers_wk);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
index 81ca9ff67be9..3f8b840871d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac.c
@@ -32,9 +32,9 @@ static void iwl_mvm_mld_mac_ctxt_cmd_common(struct iwl_mvm *mvm,
unsigned int link_id;
int cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
WIDE_ID(MAC_CONF_GROUP,
- MAC_CONFIG_CMD), 0);
+ MAC_CONFIG_CMD), 1);
- if (WARN_ON(cmd_ver < 1 && cmd_ver > 3))
+ if (WARN_ON(cmd_ver > 3))
return;
cmd->id_and_color = cpu_to_le32(mvmvif->id);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index cb36baac14da..4f2be0c1bd97 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -166,7 +166,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
struct iwl_context_info *ctxt_info;
struct iwl_context_info_rbd_cfg *rx_cfg;
- u32 control_flags = 0, rb_size;
+ u32 control_flags = 0, rb_size, cb_size;
dma_addr_t phys;
int ret;
@@ -202,11 +202,12 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
rb_size = IWL_CTXT_INFO_RB_SIZE_4K;
}
- WARN_ON(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)) > 12);
+ cb_size = RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans));
+ if (WARN_ON(cb_size > 12))
+ cb_size = 12;
+
control_flags = IWL_CTXT_INFO_TFD_FORMAT_LONG;
- control_flags |=
- u32_encode_bits(RX_QUEUE_CB_SIZE(iwl_trans_get_num_rbds(trans)),
- IWL_CTXT_INFO_RB_CB_SIZE);
+ control_flags |= u32_encode_bits(cb_size, IWL_CTXT_INFO_RB_CB_SIZE);
control_flags |= u32_encode_bits(rb_size, IWL_CTXT_INFO_RB_SIZE);
ctxt_info->control.control_flags = cpu_to_le32(control_flags);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 656f8b06c27b..0a9e0dbb58fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1501,11 +1501,27 @@ static int _iwl_pci_resume(struct device *device, bool restore)
* Scratch value was altered, this means the device was powered off, we
* need to reset it completely.
* Note: MAC (bits 0:7) will be cleared upon suspend even with wowlan,
- * so assume that any bits there mean that the device is usable.
+ * but not bits [15:8]. So if we have bits set in lower word, assume
+ * the device is alive.
+ * For older devices, just try silently to grab the NIC.
*/
- if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ &&
- !iwl_read32(trans, CSR_FUNC_SCRATCH))
- device_was_powered_off = true;
+ if (trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ) {
+ if (!(iwl_read32(trans, CSR_FUNC_SCRATCH) &
+ CSR_FUNC_SCRATCH_POWER_OFF_MASK))
+ device_was_powered_off = true;
+ } else {
+ /*
+ * bh are re-enabled by iwl_trans_pcie_release_nic_access,
+ * so re-enable them if _iwl_trans_pcie_grab_nic_access fails.
+ */
+ local_bh_disable();
+ if (_iwl_trans_pcie_grab_nic_access(trans, true)) {
+ iwl_trans_pcie_release_nic_access(trans);
+ } else {
+ device_was_powered_off = true;
+ local_bh_enable();
+ }
+ }
if (restore || device_was_powered_off) {
trans->state = IWL_TRANS_NO_FW;
diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 738bafc3749b..66f0f5377ac1 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -403,14 +403,12 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv,
if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 &&
bss_desc->bcn_ht_oper->ht_param &
- IEEE80211_HT_PARAM_CHAN_WIDTH_ANY) {
- chan_list->chan_scan_param[0].radio_type |=
- CHAN_BW_40MHZ << 2;
+ IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)
SET_SECONDARYCHAN(chan_list->chan_scan_param[0].
radio_type,
(bss_desc->bcn_ht_oper->ht_param &
IEEE80211_HT_PARAM_CHA_SEC_OFFSET));
- }
+
*buffer += struct_size(chan_list, chan_scan_param, 1);
ret_len += struct_size(chan_list, chan_scan_param, 1);
}
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 0b50da2f1175..6b3ac8ae3f34 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -429,21 +429,14 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
/*
- * For iopoll, complete it directly. Note that using the uring_cmd
- * helper for this is safe only because we check blk_rq_is_poll().
- * As that returns false if we're NOT on a polled queue, then it's
- * safe to use the polled completion helper.
- *
- * Otherwise, move the completion to task work.
+ * IOPOLL could potentially complete this request directly, but
+ * if multiple rings are polling on the same queue, then it's possible
+ * for one ring to find completions for another ring. Punting the
+ * completion via task_work will always direct it to the right
+ * location, rather than potentially complete requests for ringA
+ * under iopoll invocations from ringB.
*/
- if (blk_rq_is_poll(req)) {
- if (pdu->bio)
- blk_rq_unmap_user(pdu->bio);
- io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
- } else {
- io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
- }
-
+ io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
return RQ_END_IO_FREE;
}
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index ebd342bda235..91d2d92717d9 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -771,7 +771,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
u16 ignored_events = PCI_EXP_SLTSTA_DLLSC;
if (!ctrl->inband_presence_disabled)
- ignored_events |= events & PCI_EXP_SLTSTA_PDC;
+ ignored_events |= PCI_EXP_SLTSTA_PDC;
events &= ~ignored_events;
pciehp_ignore_link_change(ctrl, pdev, irq, ignored_events);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9448d55113b..9e42090fb108 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3217,14 +3217,14 @@ void pci_pm_init(struct pci_dev *dev)
/* find PCI PM capability in list */
pm = pci_find_capability(dev, PCI_CAP_ID_PM);
if (!pm)
- return;
+ goto poweron;
/* Check device's ability to generate PME# */
pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc);
if ((pmc & PCI_PM_CAP_VER_MASK) > 3) {
pci_err(dev, "unsupported PM cap regs version (%u)\n",
pmc & PCI_PM_CAP_VER_MASK);
- return;
+ goto poweron;
}
dev->pm_cap = pm;
@@ -3269,6 +3269,7 @@ void pci_pm_init(struct pci_dev *dev)
pci_read_config_word(dev, PCI_STATUS, &status);
if (status & PCI_STATUS_IMM_READY)
dev->imm_ready = 1;
+poweron:
pci_pm_power_up_and_verify_state(dev);
pm_runtime_forbid(&dev->dev);
pm_runtime_set_active(&dev->dev);
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index fe2d52e434db..8a2ef74862d3 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -374,11 +374,6 @@ static struct st_pio_control *st_get_pio_control(
}
/* Low level functions.. */
-static inline int st_gpio_bank(int gpio)
-{
- return gpio/ST_GPIO_PINS_PER_BANK;
-}
-
static inline int st_gpio_pin(int gpio)
{
return gpio%ST_GPIO_PINS_PER_BANK;
diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c
index d6bb8f58978d..4edb20e61951 100644
--- a/drivers/pinctrl/pinctrl-tb10x.c
+++ b/drivers/pinctrl/pinctrl-tb10x.c
@@ -823,7 +823,7 @@ static struct platform_driver tb10x_pinctrl_pdrv = {
.remove = tb10x_pinctrl_remove,
.driver = {
.name = "tb10x_pinctrl",
- .of_match_table = of_match_ptr(tb10x_pinctrl_dt_ids),
+ .of_match_table = tb10x_pinctrl_dt_ids,
}
};
diff --git a/drivers/pinctrl/qcom/pinctrl-apq8064.c b/drivers/pinctrl/qcom/pinctrl-apq8064.c
index 20c3b9025044..3654913f1ae5 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8064.c
@@ -629,7 +629,6 @@ static struct platform_driver apq8064_pinctrl_driver = {
.of_match_table = apq8064_pinctrl_of_match,
},
.probe = apq8064_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init apq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-apq8084.c b/drivers/pinctrl/qcom/pinctrl-apq8084.c
index 3fc0a40762b6..27693cd64881 100644
--- a/drivers/pinctrl/qcom/pinctrl-apq8084.c
+++ b/drivers/pinctrl/qcom/pinctrl-apq8084.c
@@ -1207,7 +1207,6 @@ static struct platform_driver apq8084_pinctrl_driver = {
.of_match_table = apq8084_pinctrl_of_match,
},
.probe = apq8084_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init apq8084_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq4019.c b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
index 1f7944dd829d..6ede3149b6e1 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq4019.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq4019.c
@@ -710,7 +710,6 @@ static struct platform_driver ipq4019_pinctrl_driver = {
.of_match_table = ipq4019_pinctrl_of_match,
},
.probe = ipq4019_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq4019_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5018.c b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
index e2951f81c3ee..10b99d5d8a11 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5018.c
@@ -754,7 +754,6 @@ static struct platform_driver ipq5018_pinctrl_driver = {
.of_match_table = ipq5018_pinctrl_of_match,
},
.probe = ipq5018_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq5018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5332.c b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
index 625f8014051f..1ac2fc09c119 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5332.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5332.c
@@ -834,7 +834,6 @@ static struct platform_driver ipq5332_pinctrl_driver = {
.of_match_table = ipq5332_pinctrl_of_match,
},
.probe = ipq5332_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq5332_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq5424.c b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
index 0d610b076da3..7ff1f8acc1a3 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq5424.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq5424.c
@@ -791,7 +791,6 @@ static struct platform_driver ipq5424_pinctrl_driver = {
.of_match_table = ipq5424_pinctrl_of_match,
},
.probe = ipq5424_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq5424_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq6018.c b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
index 0ad08647dbcd..a4ba980252e1 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq6018.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq6018.c
@@ -1080,7 +1080,6 @@ static struct platform_driver ipq6018_pinctrl_driver = {
.of_match_table = ipq6018_pinctrl_of_match,
},
.probe = ipq6018_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq6018_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8064.c b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
index e2bb94e86aef..0a9e357e64c6 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8064.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8064.c
@@ -631,7 +631,6 @@ static struct platform_driver ipq8064_pinctrl_driver = {
.of_match_table = ipq8064_pinctrl_of_match,
},
.probe = ipq8064_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq8064_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq8074.c b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
index 337f3a1c92c1..482f13282fc2 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq8074.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq8074.c
@@ -1041,7 +1041,6 @@ static struct platform_driver ipq8074_pinctrl_driver = {
.of_match_table = ipq8074_pinctrl_of_match,
},
.probe = ipq8074_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq8074_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-ipq9574.c b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
index e2491617b236..89c05d8eb550 100644
--- a/drivers/pinctrl/qcom/pinctrl-ipq9574.c
+++ b/drivers/pinctrl/qcom/pinctrl-ipq9574.c
@@ -799,7 +799,6 @@ static struct platform_driver ipq9574_pinctrl_driver = {
.of_match_table = ipq9574_pinctrl_of_match,
},
.probe = ipq9574_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init ipq9574_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9607.c b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
index e7cd3ef1cf3e..3e18ba124fed 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9607.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9607.c
@@ -1059,7 +1059,6 @@ static struct platform_driver mdm9607_pinctrl_driver = {
.of_match_table = mdm9607_pinctrl_of_match,
},
.probe = mdm9607_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init mdm9607_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-mdm9615.c b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
index 0a2ae383d3d5..bea1ca3d1b7f 100644
--- a/drivers/pinctrl/qcom/pinctrl-mdm9615.c
+++ b/drivers/pinctrl/qcom/pinctrl-mdm9615.c
@@ -446,7 +446,6 @@ static struct platform_driver mdm9615_pinctrl_driver = {
.of_match_table = mdm9615_pinctrl_of_match,
},
.probe = mdm9615_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init mdm9615_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f012ea88aa22..5c4687de1464 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -1442,7 +1442,7 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
girq->handler = handle_bad_irq;
girq->parents[0] = pctrl->irq;
- ret = gpiochip_add_data(&pctrl->chip, pctrl);
+ ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl);
if (ret) {
dev_err(pctrl->dev, "Failed register gpiochip\n");
return ret;
@@ -1463,7 +1463,6 @@ static int msm_gpio_init(struct msm_pinctrl *pctrl)
dev_name(pctrl->dev), 0, 0, chip->ngpio);
if (ret) {
dev_err(pctrl->dev, "Failed to add pin range\n");
- gpiochip_remove(&pctrl->chip);
return ret;
}
}
@@ -1599,13 +1598,5 @@ int msm_pinctrl_probe(struct platform_device *pdev,
}
EXPORT_SYMBOL(msm_pinctrl_probe);
-void msm_pinctrl_remove(struct platform_device *pdev)
-{
- struct msm_pinctrl *pctrl = platform_get_drvdata(pdev);
-
- gpiochip_remove(&pctrl->chip);
-}
-EXPORT_SYMBOL(msm_pinctrl_remove);
-
MODULE_DESCRIPTION("Qualcomm Technologies, Inc. TLMM driver");
MODULE_LICENSE("GPL v2");
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.h b/drivers/pinctrl/qcom/pinctrl-msm.h
index 63852ed70295..d7dc0947bb16 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.h
+++ b/drivers/pinctrl/qcom/pinctrl-msm.h
@@ -171,6 +171,5 @@ extern const struct dev_pm_ops msm_pinctrl_dev_pm_ops;
int msm_pinctrl_probe(struct platform_device *pdev,
const struct msm_pinctrl_soc_data *soc_data);
-void msm_pinctrl_remove(struct platform_device *pdev);
#endif
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8226.c b/drivers/pinctrl/qcom/pinctrl-msm8226.c
index 64fee70f1772..f9a957347340 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8226.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8226.c
@@ -654,7 +654,6 @@ static struct platform_driver msm8226_pinctrl_driver = {
.of_match_table = msm8226_pinctrl_of_match,
},
.probe = msm8226_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8226_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8660.c b/drivers/pinctrl/qcom/pinctrl-msm8660.c
index 999a5f867eb5..4dbc19ffd80e 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8660.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8660.c
@@ -981,7 +981,6 @@ static struct platform_driver msm8660_pinctrl_driver = {
.of_match_table = msm8660_pinctrl_of_match,
},
.probe = msm8660_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8909.c b/drivers/pinctrl/qcom/pinctrl-msm8909.c
index 756856d20d6b..0aa4f77b774f 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8909.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8909.c
@@ -929,7 +929,6 @@ static struct platform_driver msm8909_pinctrl_driver = {
.of_match_table = msm8909_pinctrl_of_match,
},
.probe = msm8909_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8909_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8916.c b/drivers/pinctrl/qcom/pinctrl-msm8916.c
index cea5c54f92fe..0dfc6dd33d58 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8916.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8916.c
@@ -969,7 +969,6 @@ static struct platform_driver msm8916_pinctrl_driver = {
.of_match_table = msm8916_pinctrl_of_match,
},
.probe = msm8916_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8916_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8917.c b/drivers/pinctrl/qcom/pinctrl-msm8917.c
index 350636807b07..2e1a94ab18b2 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8917.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8917.c
@@ -1607,7 +1607,6 @@ static struct platform_driver msm8917_pinctrl_driver = {
.of_match_table = msm8917_pinctrl_of_match,
},
.probe = msm8917_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8917_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8953.c b/drivers/pinctrl/qcom/pinctrl-msm8953.c
index 998351bdfee1..956383341a7a 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8953.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8953.c
@@ -1816,7 +1816,6 @@ static struct platform_driver msm8953_pinctrl_driver = {
.of_match_table = msm8953_pinctrl_of_match,
},
.probe = msm8953_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8953_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8960.c b/drivers/pinctrl/qcom/pinctrl-msm8960.c
index ebe230b3b437..a937ea867de7 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8960.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8960.c
@@ -1246,7 +1246,6 @@ static struct platform_driver msm8960_pinctrl_driver = {
.of_match_table = msm8960_pinctrl_of_match,
},
.probe = msm8960_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8960_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8976.c b/drivers/pinctrl/qcom/pinctrl-msm8976.c
index c30d80e4e98c..3bcb03387781 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8976.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8976.c
@@ -1096,7 +1096,6 @@ static struct platform_driver msm8976_pinctrl_driver = {
.of_match_table = msm8976_pinctrl_of_match,
},
.probe = msm8976_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8976_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8994.c b/drivers/pinctrl/qcom/pinctrl-msm8994.c
index b1a6759ab4a5..7a3b6cbccb68 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8994.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8994.c
@@ -1343,7 +1343,6 @@ static struct platform_driver msm8994_pinctrl_driver = {
.of_match_table = msm8994_pinctrl_of_match,
},
.probe = msm8994_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8994_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8996.c b/drivers/pinctrl/qcom/pinctrl-msm8996.c
index 1b5d80eaab83..d86d83106d3b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8996.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8996.c
@@ -1920,7 +1920,6 @@ static struct platform_driver msm8996_pinctrl_driver = {
.of_match_table = msm8996_pinctrl_of_match,
},
.probe = msm8996_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8996_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8998.c b/drivers/pinctrl/qcom/pinctrl-msm8998.c
index b7cbf32b3125..1daee815888f 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8998.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8998.c
@@ -1535,7 +1535,6 @@ static struct platform_driver msm8998_pinctrl_driver = {
.of_match_table = msm8998_pinctrl_of_match,
},
.probe = msm8998_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8998_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-msm8x74.c b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
index 238c83f6ec4f..8253aa25775b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm8x74.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm8x74.c
@@ -1083,7 +1083,6 @@ static struct platform_driver msm8x74_pinctrl_driver = {
.of_match_table = msm8x74_pinctrl_of_match,
},
.probe = msm8x74_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init msm8x74_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcm2290.c b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
index f885af571ec9..eeeec6434f6a 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcm2290.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcm2290.c
@@ -167,6 +167,10 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
PINCTRL_PIN(62, "GPIO_62"),
PINCTRL_PIN(63, "GPIO_63"),
PINCTRL_PIN(64, "GPIO_64"),
+ PINCTRL_PIN(65, "GPIO_65"),
+ PINCTRL_PIN(66, "GPIO_66"),
+ PINCTRL_PIN(67, "GPIO_67"),
+ PINCTRL_PIN(68, "GPIO_68"),
PINCTRL_PIN(69, "GPIO_69"),
PINCTRL_PIN(70, "GPIO_70"),
PINCTRL_PIN(71, "GPIO_71"),
@@ -181,12 +185,17 @@ static const struct pinctrl_pin_desc qcm2290_pins[] = {
PINCTRL_PIN(80, "GPIO_80"),
PINCTRL_PIN(81, "GPIO_81"),
PINCTRL_PIN(82, "GPIO_82"),
+ PINCTRL_PIN(83, "GPIO_83"),
+ PINCTRL_PIN(84, "GPIO_84"),
+ PINCTRL_PIN(85, "GPIO_85"),
PINCTRL_PIN(86, "GPIO_86"),
PINCTRL_PIN(87, "GPIO_87"),
PINCTRL_PIN(88, "GPIO_88"),
PINCTRL_PIN(89, "GPIO_89"),
PINCTRL_PIN(90, "GPIO_90"),
PINCTRL_PIN(91, "GPIO_91"),
+ PINCTRL_PIN(92, "GPIO_92"),
+ PINCTRL_PIN(93, "GPIO_93"),
PINCTRL_PIN(94, "GPIO_94"),
PINCTRL_PIN(95, "GPIO_95"),
PINCTRL_PIN(96, "GPIO_96"),
@@ -1125,7 +1134,6 @@ static struct platform_driver qcm2290_pinctrl_driver = {
.of_match_table = qcm2290_pinctrl_of_match,
},
.probe = qcm2290_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qcm2290_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs404.c b/drivers/pinctrl/qcom/pinctrl-qcs404.c
index ae7224012f8a..54e3b4435349 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs404.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs404.c
@@ -1644,7 +1644,6 @@ static struct platform_driver qcs404_pinctrl_driver = {
.of_match_table = qcs404_pinctrl_of_match,
},
.probe = qcs404_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qcs404_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs615.c b/drivers/pinctrl/qcom/pinctrl-qcs615.c
index 17ca743c2210..2a943bc46a62 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs615.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs615.c
@@ -1087,7 +1087,6 @@ static struct platform_driver qcs615_tlmm_driver = {
.of_match_table = qcs615_tlmm_of_match,
},
.probe = qcs615_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qcs615_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qcs8300.c b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
index 5f5f7c4ac644..d6437e26392b 100644
--- a/drivers/pinctrl/qcom/pinctrl-qcs8300.c
+++ b/drivers/pinctrl/qcom/pinctrl-qcs8300.c
@@ -1227,7 +1227,6 @@ static struct platform_driver qcs8300_pinctrl_driver = {
.of_match_table = qcs8300_pinctrl_of_match,
},
.probe = qcs8300_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qcs8300_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
index b5808fcfb13c..9ecc4d40e4dc 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdf2xxx.c
@@ -145,7 +145,6 @@ static struct platform_driver qdf2xxx_pinctrl_driver = {
.acpi_match_table = qdf2xxx_acpi_ids,
},
.probe = qdf2xxx_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qdf2xxx_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-qdu1000.c b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
index 47bc529ef550..eacb89fa3888 100644
--- a/drivers/pinctrl/qcom/pinctrl-qdu1000.c
+++ b/drivers/pinctrl/qcom/pinctrl-qdu1000.c
@@ -1248,7 +1248,6 @@ static struct platform_driver qdu1000_tlmm_driver = {
.of_match_table = qdu1000_tlmm_of_match,
},
.probe = qdu1000_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init qdu1000_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sa8775p.c b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
index a5b38221aea8..1b62eb3e6620 100644
--- a/drivers/pinctrl/qcom/pinctrl-sa8775p.c
+++ b/drivers/pinctrl/qcom/pinctrl-sa8775p.c
@@ -1540,7 +1540,6 @@ static struct platform_driver sa8775p_pinctrl_driver = {
.of_match_table = sa8775p_pinctrl_of_match,
},
.probe = sa8775p_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sa8775p_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sar2130p.c b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
index 19a2e37826c7..3dd1b5e5cfee 100644
--- a/drivers/pinctrl/qcom/pinctrl-sar2130p.c
+++ b/drivers/pinctrl/qcom/pinctrl-sar2130p.c
@@ -1486,7 +1486,6 @@ static struct platform_driver sar2130p_tlmm_driver = {
.of_match_table = sar2130p_tlmm_of_match,
},
.probe = sar2130p_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sar2130p_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7180.c b/drivers/pinctrl/qcom/pinctrl-sc7180.c
index 6eb0c73791c0..c43fe10b71ad 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7180.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7180.c
@@ -1159,7 +1159,6 @@ static struct platform_driver sc7180_pinctrl_driver = {
.of_match_table = sc7180_pinctrl_of_match,
},
.probe = sc7180_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sc7180_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc7280.c b/drivers/pinctrl/qcom/pinctrl-sc7280.c
index 0c10eeb60b55..1b070e9d41f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc7280.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc7280.c
@@ -1505,7 +1505,6 @@ static struct platform_driver sc7280_pinctrl_driver = {
.of_match_table = sc7280_pinctrl_of_match,
},
.probe = sc7280_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sc7280_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8180x.c b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
index d6a79ad41a40..26dd165d1543 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8180x.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8180x.c
@@ -1720,7 +1720,6 @@ static struct platform_driver sc8180x_pinctrl_driver = {
.acpi_match_table = sc8180x_pinctrl_acpi_match,
},
.probe = sc8180x_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sc8180x_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
index 96f4fb5a5d29..6ccd7e5648d4 100644
--- a/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
+++ b/drivers/pinctrl/qcom/pinctrl-sc8280xp.c
@@ -1926,7 +1926,6 @@ static struct platform_driver sc8280xp_pinctrl_driver = {
.of_match_table = sc8280xp_pinctrl_of_match,
},
.probe = sc8280xp_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sc8280xp_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660.c b/drivers/pinctrl/qcom/pinctrl-sdm660.c
index 907e4ffca5e7..1a78288f1bc8 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm660.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm660.c
@@ -1442,7 +1442,6 @@ static struct platform_driver sdm660_pinctrl_driver = {
.of_match_table = sdm660_pinctrl_of_match,
},
.probe = sdm660_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdm660_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm670.c b/drivers/pinctrl/qcom/pinctrl-sdm670.c
index c76183ba95e1..0fe1fa94cd6d 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm670.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm670.c
@@ -1337,7 +1337,6 @@ static struct platform_driver sdm670_pinctrl_driver = {
.of_match_table = sdm670_pinctrl_of_match,
},
.probe = sdm670_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdm670_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdm845.c b/drivers/pinctrl/qcom/pinctrl-sdm845.c
index cc05c415ed15..0446e291aa48 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdm845.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdm845.c
@@ -1351,7 +1351,6 @@ static struct platform_driver sdm845_pinctrl_driver = {
.acpi_match_table = ACPI_PTR(sdm845_pinctrl_acpi_match),
},
.probe = sdm845_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdm845_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx55.c b/drivers/pinctrl/qcom/pinctrl-sdx55.c
index 8826db9d21d0..2c17bf889146 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx55.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx55.c
@@ -990,7 +990,6 @@ static struct platform_driver sdx55_pinctrl_driver = {
.of_match_table = sdx55_pinctrl_of_match,
},
.probe = sdx55_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdx55_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx65.c b/drivers/pinctrl/qcom/pinctrl-sdx65.c
index f6f319c997fc..85b5c0206dbd 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx65.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx65.c
@@ -939,7 +939,6 @@ static struct platform_driver sdx65_pinctrl_driver = {
.of_match_table = sdx65_pinctrl_of_match,
},
.probe = sdx65_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdx65_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sdx75.c b/drivers/pinctrl/qcom/pinctrl-sdx75.c
index 3cfe8c7f04df..ab13a3a57a83 100644
--- a/drivers/pinctrl/qcom/pinctrl-sdx75.c
+++ b/drivers/pinctrl/qcom/pinctrl-sdx75.c
@@ -1124,7 +1124,6 @@ static struct platform_driver sdx75_pinctrl_driver = {
.of_match_table = sdx75_pinctrl_of_match,
},
.probe = sdx75_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sdx75_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm4450.c b/drivers/pinctrl/qcom/pinctrl-sm4450.c
index 622f20e6f6f8..1ecdf1ab4f27 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm4450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm4450.c
@@ -994,7 +994,6 @@ static struct platform_driver sm4450_tlmm_driver = {
.of_match_table = sm4450_tlmm_of_match,
},
.probe = sm4450_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
MODULE_DEVICE_TABLE(of, sm4450_tlmm_of_match);
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6115.c b/drivers/pinctrl/qcom/pinctrl-sm6115.c
index 4e91c75ad952..c273efa43996 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6115.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6115.c
@@ -907,7 +907,6 @@ static struct platform_driver sm6115_tlmm_driver = {
.of_match_table = sm6115_tlmm_of_match,
},
.probe = sm6115_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm6115_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6125.c b/drivers/pinctrl/qcom/pinctrl-sm6125.c
index c188842047aa..5092f20e0c1b 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6125.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6125.c
@@ -1266,7 +1266,6 @@ static struct platform_driver sm6125_tlmm_driver = {
.of_match_table = sm6125_tlmm_of_match,
},
.probe = sm6125_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm6125_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6350.c b/drivers/pinctrl/qcom/pinctrl-sm6350.c
index f3828c07b134..ba4686c86c54 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6350.c
@@ -1373,7 +1373,6 @@ static struct platform_driver sm6350_tlmm_driver = {
.of_match_table = sm6350_tlmm_of_match,
},
.probe = sm6350_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm6350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm6375.c b/drivers/pinctrl/qcom/pinctrl-sm6375.c
index c82c8516932e..49031571e65e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm6375.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm6375.c
@@ -1516,7 +1516,6 @@ static struct platform_driver sm6375_tlmm_driver = {
.of_match_table = sm6375_tlmm_of_match,
},
.probe = sm6375_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm6375_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm7150.c b/drivers/pinctrl/qcom/pinctrl-sm7150.c
index 3c7fd8af6635..6e89966cd70e 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm7150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm7150.c
@@ -1255,7 +1255,6 @@ static struct platform_driver sm7150_tlmm_driver = {
.of_match_table = sm7150_tlmm_of_match,
},
.probe = sm7150_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm7150_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8150.c b/drivers/pinctrl/qcom/pinctrl-sm8150.c
index 01aea9c70b7a..794ed99463f7 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8150.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8150.c
@@ -1542,7 +1542,6 @@ static struct platform_driver sm8150_pinctrl_driver = {
.of_match_table = sm8150_pinctrl_of_match,
},
.probe = sm8150_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8150_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8250.c b/drivers/pinctrl/qcom/pinctrl-sm8250.c
index e9961a49ff98..fb6f005d64f5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8250.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8250.c
@@ -1351,7 +1351,6 @@ static struct platform_driver sm8250_pinctrl_driver = {
.of_match_table = sm8250_pinctrl_of_match,
},
.probe = sm8250_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8250_pinctrl_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8350.c b/drivers/pinctrl/qcom/pinctrl-sm8350.c
index 9c69458bd910..c8a3f39ce6f1 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8350.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8350.c
@@ -1642,7 +1642,6 @@ static struct platform_driver sm8350_tlmm_driver = {
.of_match_table = sm8350_tlmm_of_match,
},
.probe = sm8350_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8350_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8450.c b/drivers/pinctrl/qcom/pinctrl-sm8450.c
index d11bb1ee9e3d..f2e52d5a0f93 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8450.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8450.c
@@ -1677,7 +1677,6 @@ static struct platform_driver sm8450_tlmm_driver = {
.of_match_table = sm8450_tlmm_of_match,
},
.probe = sm8450_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8450_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8550.c b/drivers/pinctrl/qcom/pinctrl-sm8550.c
index 3c847d9cb5d9..1b4496cb39eb 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8550.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8550.c
@@ -1762,7 +1762,6 @@ static struct platform_driver sm8550_tlmm_driver = {
.of_match_table = sm8550_tlmm_of_match,
},
.probe = sm8550_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8550_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8650.c b/drivers/pinctrl/qcom/pinctrl-sm8650.c
index 104708252d12..449a0077f4b1 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8650.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8650.c
@@ -1742,7 +1742,6 @@ static struct platform_driver sm8650_tlmm_driver = {
.of_match_table = sm8650_tlmm_of_match,
},
.probe = sm8650_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8650_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-sm8750.c b/drivers/pinctrl/qcom/pinctrl-sm8750.c
index b94fb4ee0ec3..8516693d1db5 100644
--- a/drivers/pinctrl/qcom/pinctrl-sm8750.c
+++ b/drivers/pinctrl/qcom/pinctrl-sm8750.c
@@ -1711,7 +1711,6 @@ static struct platform_driver sm8750_tlmm_driver = {
.of_match_table = sm8750_tlmm_of_match,
},
.probe = sm8750_tlmm_probe,
- .remove = msm_pinctrl_remove,
};
static int __init sm8750_tlmm_init(void)
diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
index 419cb8facb2f..d4b215f34c39 100644
--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
@@ -1861,7 +1861,6 @@ static struct platform_driver x1e80100_pinctrl_driver = {
.of_match_table = x1e80100_pinctrl_of_match,
},
.probe = x1e80100_pinctrl_probe,
- .remove = msm_pinctrl_remove,
};
static int __init x1e80100_pinctrl_init(void)
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c b/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
index 1833078f6877..4e34b0cd3b73 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi-dt.c
@@ -143,7 +143,7 @@ static struct sunxi_desc_pin *init_pins_table(struct device *dev,
*/
static int prepare_function_table(struct device *dev, struct device_node *pnode,
struct sunxi_desc_pin *pins, int npins,
- const u8 *irq_bank_muxes)
+ unsigned pin_base, const u8 *irq_bank_muxes)
{
struct device_node *node;
struct property *prop;
@@ -166,7 +166,7 @@ static int prepare_function_table(struct device *dev, struct device_node *pnode,
*/
for (i = 0; i < npins; i++) {
struct sunxi_desc_pin *pin = &pins[i];
- int bank = pin->pin.number / PINS_PER_BANK;
+ int bank = (pin->pin.number - pin_base) / PINS_PER_BANK;
if (irq_bank_muxes[bank]) {
pin->variant++;
@@ -211,7 +211,7 @@ static int prepare_function_table(struct device *dev, struct device_node *pnode,
last_bank = 0;
for (i = 0; i < npins; i++) {
struct sunxi_desc_pin *pin = &pins[i];
- int bank = pin->pin.number / PINS_PER_BANK;
+ int bank = (pin->pin.number - pin_base) / PINS_PER_BANK;
int lastfunc = pin->variant + 1;
int irq_mux = irq_bank_muxes[bank];
@@ -353,7 +353,7 @@ int sunxi_pinctrl_dt_table_init(struct platform_device *pdev,
return PTR_ERR(pins);
ret = prepare_function_table(&pdev->dev, pnode, pins, desc->npins,
- irq_bank_muxes);
+ desc->pin_base, irq_bank_muxes);
if (ret)
return ret;
diff --git a/drivers/platform/x86/amd/hsmp/hsmp.c b/drivers/platform/x86/amd/hsmp/hsmp.c
index 538b36b97095..885e2f8136fd 100644
--- a/drivers/platform/x86/amd/hsmp/hsmp.c
+++ b/drivers/platform/x86/amd/hsmp/hsmp.c
@@ -97,7 +97,7 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms
short_sleep = jiffies + msecs_to_jiffies(HSMP_SHORT_SLEEP);
timeout = jiffies + msecs_to_jiffies(HSMP_MSG_TIMEOUT);
- while (time_before(jiffies, timeout)) {
+ while (true) {
ret = sock->amd_hsmp_rdwr(sock, mbinfo->msg_resp_off, &mbox_status, HSMP_RD);
if (ret) {
dev_err(sock->dev, "Error %d reading mailbox status\n", ret);
@@ -106,6 +106,10 @@ static int __hsmp_send_message(struct hsmp_socket *sock, struct hsmp_message *ms
if (mbox_status != HSMP_STATUS_NOT_READY)
break;
+
+ if (!time_before(jiffies, timeout))
+ break;
+
if (time_before(jiffies, short_sleep))
usleep_range(50, 100);
else
@@ -210,13 +214,7 @@ int hsmp_send_message(struct hsmp_message *msg)
return -ENODEV;
sock = &hsmp_pdev.sock[msg->sock_ind];
- /*
- * The time taken by smu operation to complete is between
- * 10us to 1ms. Sometime it may take more time.
- * In SMP system timeout of 100 millisecs should
- * be enough for the previous thread to finish the operation
- */
- ret = down_timeout(&sock->hsmp_sem, msecs_to_jiffies(HSMP_MSG_TIMEOUT));
+ ret = down_interruptible(&sock->hsmp_sem);
if (ret < 0)
return ret;
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index 5c7c01f66cde..f292111bd065 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -225,6 +225,15 @@ static const struct dmi_system_id fwbug_list[] = {
DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"),
}
},
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=220116 */
+ {
+ .ident = "PCSpecialist Lafite Pro V 14M",
+ .driver_data = &quirk_spurious_8042,
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Lafite Pro V 14M"),
+ }
+ },
{}
};
diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c
index 37c7a57afee5..0b9b23eb7c2c 100644
--- a/drivers/platform/x86/amd/pmc/pmc.c
+++ b/drivers/platform/x86/amd/pmc/pmc.c
@@ -157,6 +157,8 @@ static int amd_pmc_setup_smu_logging(struct amd_pmc_dev *dev)
return -ENOMEM;
}
+ memset_io(dev->smu_virt_addr, 0, sizeof(struct smu_metrics));
+
/* Start the logging */
amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_RESET, false);
amd_pmc_send_cmd(dev, 0, NULL, SMU_MSG_LOG_START, false);
diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 76910601cac8..ef988605c4da 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -280,7 +280,7 @@ int amd_pmf_set_dram_addr(struct amd_pmf_dev *dev, bool alloc_buffer)
dev_err(dev->dev, "Invalid CPU id: 0x%x", dev->cpu_id);
}
- dev->buf = kzalloc(dev->mtable_size, GFP_KERNEL);
+ dev->buf = devm_kzalloc(dev->dev, dev->mtable_size, GFP_KERNEL);
if (!dev->buf)
return -ENOMEM;
}
@@ -493,7 +493,6 @@ static void amd_pmf_remove(struct platform_device *pdev)
mutex_destroy(&dev->lock);
mutex_destroy(&dev->update_mutex);
mutex_destroy(&dev->cb_mutex);
- kfree(dev->buf);
}
static const struct attribute_group *amd_pmf_driver_groups[] = {
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index d3bd12ad036a..4f626ebcb619 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -358,30 +358,28 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf,
return -EINVAL;
/* re-alloc to the new buffer length of the policy binary */
- new_policy_buf = memdup_user(buf, length);
- if (IS_ERR(new_policy_buf))
- return PTR_ERR(new_policy_buf);
+ new_policy_buf = devm_kzalloc(dev->dev, length, GFP_KERNEL);
+ if (!new_policy_buf)
+ return -ENOMEM;
+
+ if (copy_from_user(new_policy_buf, buf, length)) {
+ devm_kfree(dev->dev, new_policy_buf);
+ return -EFAULT;
+ }
- kfree(dev->policy_buf);
+ devm_kfree(dev->dev, dev->policy_buf);
dev->policy_buf = new_policy_buf;
dev->policy_sz = length;
- if (!amd_pmf_pb_valid(dev)) {
- ret = -EINVAL;
- goto cleanup;
- }
+ if (!amd_pmf_pb_valid(dev))
+ return -EINVAL;
amd_pmf_hex_dump_pb(dev);
ret = amd_pmf_start_policy_engine(dev);
if (ret < 0)
- goto cleanup;
+ return ret;
return length;
-
-cleanup:
- kfree(dev->policy_buf);
- dev->policy_buf = NULL;
- return ret;
}
static const struct file_operations pb_fops = {
@@ -422,12 +420,12 @@ static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id, const uuid_
rc = tee_client_open_session(ctx, &sess_arg, NULL);
if (rc < 0 || sess_arg.ret != 0) {
pr_err("Failed to open TEE session err:%#x, rc:%d\n", sess_arg.ret, rc);
- return rc;
+ return rc ?: -EINVAL;
}
*id = sess_arg.session;
- return rc;
+ return 0;
}
static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
@@ -462,7 +460,9 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid)
dev->tee_ctx = tee_client_open_context(NULL, amd_pmf_amdtee_ta_match, NULL, NULL);
if (IS_ERR(dev->tee_ctx)) {
dev_err(dev->dev, "Failed to open TEE context\n");
- return PTR_ERR(dev->tee_ctx);
+ ret = PTR_ERR(dev->tee_ctx);
+ dev->tee_ctx = NULL;
+ return ret;
}
ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
@@ -502,9 +502,12 @@ out_ctx:
static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
{
+ if (!dev->tee_ctx)
+ return;
tee_shm_free(dev->fw_shm_pool);
tee_client_close_session(dev->tee_ctx, dev->session_id);
tee_client_close_context(dev->tee_ctx);
+ dev->tee_ctx = NULL;
}
int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
@@ -527,64 +530,45 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
ret = amd_pmf_set_dram_addr(dev, true);
if (ret)
- goto err_cancel_work;
+ return ret;
dev->policy_base = devm_ioremap_resource(dev->dev, dev->res);
- if (IS_ERR(dev->policy_base)) {
- ret = PTR_ERR(dev->policy_base);
- goto err_free_dram_buf;
- }
+ if (IS_ERR(dev->policy_base))
+ return PTR_ERR(dev->policy_base);
- dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
- if (!dev->policy_buf) {
- ret = -ENOMEM;
- goto err_free_dram_buf;
- }
+ dev->policy_buf = devm_kzalloc(dev->dev, dev->policy_sz, GFP_KERNEL);
+ if (!dev->policy_buf)
+ return -ENOMEM;
memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
if (!amd_pmf_pb_valid(dev)) {
dev_info(dev->dev, "No Smart PC policy present\n");
- ret = -EINVAL;
- goto err_free_policy;
+ return -EINVAL;
}
amd_pmf_hex_dump_pb(dev);
- dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
- if (!dev->prev_data) {
- ret = -ENOMEM;
- goto err_free_policy;
- }
+ dev->prev_data = devm_kzalloc(dev->dev, sizeof(*dev->prev_data), GFP_KERNEL);
+ if (!dev->prev_data)
+ return -ENOMEM;
for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
if (ret)
- goto err_free_prev_data;
+ return ret;
ret = amd_pmf_start_policy_engine(dev);
- switch (ret) {
- case TA_PMF_TYPE_SUCCESS:
- status = true;
- break;
- case TA_ERROR_CRYPTO_INVALID_PARAM:
- case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
- amd_pmf_tee_deinit(dev);
- status = false;
- break;
- default:
- ret = -EINVAL;
- amd_pmf_tee_deinit(dev);
- goto err_free_prev_data;
- }
-
+ dev_dbg(dev->dev, "start policy engine ret: %d\n", ret);
+ status = ret == TA_PMF_TYPE_SUCCESS;
if (status)
break;
+ amd_pmf_tee_deinit(dev);
}
if (!status && !pb_side_load) {
ret = -EINVAL;
- goto err_free_prev_data;
+ goto err;
}
if (pb_side_load)
@@ -592,22 +576,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
ret = amd_pmf_register_input_device(dev);
if (ret)
- goto err_pmf_remove_pb;
+ goto err;
return 0;
-err_pmf_remove_pb:
- if (pb_side_load && dev->esbin)
- amd_pmf_remove_pb(dev);
- amd_pmf_tee_deinit(dev);
-err_free_prev_data:
- kfree(dev->prev_data);
-err_free_policy:
- kfree(dev->policy_buf);
-err_free_dram_buf:
- kfree(dev->buf);
-err_cancel_work:
- cancel_delayed_work_sync(&dev->pb_work);
+err:
+ amd_pmf_deinit_smart_pc(dev);
return ret;
}
@@ -621,11 +595,5 @@ void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev)
amd_pmf_remove_pb(dev);
cancel_delayed_work_sync(&dev->pb_work);
- kfree(dev->prev_data);
- dev->prev_data = NULL;
- kfree(dev->policy_buf);
- dev->policy_buf = NULL;
- kfree(dev->buf);
- dev->buf = NULL;
amd_pmf_tee_deinit(dev);
}
diff --git a/drivers/platform/x86/dell/alienware-wmi-wmax.c b/drivers/platform/x86/dell/alienware-wmi-wmax.c
index c42f9228b0b2..20ec122a9fe0 100644
--- a/drivers/platform/x86/dell/alienware-wmi-wmax.c
+++ b/drivers/platform/x86/dell/alienware-wmi-wmax.c
@@ -119,7 +119,7 @@ static const struct dmi_system_id awcc_dmi_table[] __initconst = {
DMI_MATCH(DMI_SYS_VENDOR, "Alienware"),
DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m16 R1 AMD"),
},
- .driver_data = &g_series_quirks,
+ .driver_data = &generic_quirks,
},
{
.ident = "Alienware m16 R2",
diff --git a/drivers/platform/x86/dell/dell_rbu.c b/drivers/platform/x86/dell/dell_rbu.c
index e30ca325938c..9dd9f2cb074f 100644
--- a/drivers/platform/x86/dell/dell_rbu.c
+++ b/drivers/platform/x86/dell/dell_rbu.c
@@ -45,7 +45,7 @@
MODULE_AUTHOR("Abhay Salunke <abhay_salunke@dell.com>");
MODULE_DESCRIPTION("Driver for updating BIOS image on DELL systems");
MODULE_LICENSE("GPL");
-MODULE_VERSION("3.2");
+MODULE_VERSION("3.3");
#define BIOS_SCAN_LIMIT 0xffffffff
#define MAX_IMAGE_LENGTH 16
@@ -91,7 +91,7 @@ static void init_packet_head(void)
rbu_data.imagesize = 0;
}
-static int create_packet(void *data, size_t length)
+static int create_packet(void *data, size_t length) __must_hold(&rbu_data.lock)
{
struct packet_data *newpacket;
int ordernum = 0;
@@ -292,7 +292,7 @@ static int packet_read_list(char *data, size_t * pread_length)
remaining_bytes = *pread_length;
bytes_read = rbu_data.packet_read_count;
- list_for_each_entry(newpacket, (&packet_data_head.list)->next, list) {
+ list_for_each_entry(newpacket, &packet_data_head.list, list) {
bytes_copied = do_packet_read(pdest, newpacket,
remaining_bytes, bytes_read, &temp_count);
remaining_bytes -= bytes_copied;
@@ -315,14 +315,14 @@ static void packet_empty_list(void)
{
struct packet_data *newpacket, *tmp;
- list_for_each_entry_safe(newpacket, tmp, (&packet_data_head.list)->next, list) {
+ list_for_each_entry_safe(newpacket, tmp, &packet_data_head.list, list) {
list_del(&newpacket->list);
/*
* zero out the RBU packet memory before freeing
* to make sure there are no stale RBU packets left in memory
*/
- memset(newpacket->data, 0, rbu_data.packetsize);
+ memset(newpacket->data, 0, newpacket->length);
set_memory_wb((unsigned long)newpacket->data,
1 << newpacket->ordernum);
free_pages((unsigned long) newpacket->data,
diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
index ede483573fe0..b5e4da6a6779 100644
--- a/drivers/platform/x86/ideapad-laptop.c
+++ b/drivers/platform/x86/ideapad-laptop.c
@@ -15,6 +15,7 @@
#include <linux/bug.h>
#include <linux/cleanup.h>
#include <linux/debugfs.h>
+#include <linux/delay.h>
#include <linux/device.h>
#include <linux/dmi.h>
#include <linux/i8042.h>
@@ -267,6 +268,20 @@ static void ideapad_shared_exit(struct ideapad_private *priv)
*/
#define IDEAPAD_EC_TIMEOUT 200 /* in ms */
+/*
+ * Some models (e.g., ThinkBook since 2024) have a low tolerance for being
+ * polled too frequently. Doing so may break the state machine in the EC,
+ * resulting in a hard shutdown.
+ *
+ * It is also observed that frequent polls may disturb the ongoing operation
+ * and notably delay the availability of EC response.
+ *
+ * These values are used as the delay before the first poll and the interval
+ * between subsequent polls to solve the above issues.
+ */
+#define IDEAPAD_EC_POLL_MIN_US 150
+#define IDEAPAD_EC_POLL_MAX_US 300
+
static int eval_int(acpi_handle handle, const char *name, unsigned long *res)
{
unsigned long long result;
@@ -383,7 +398,7 @@ static int read_ec_data(acpi_handle handle, unsigned long cmd, unsigned long *da
end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
while (time_before(jiffies, end_jiffies)) {
- schedule();
+ usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
err = eval_vpcr(handle, 1, &val);
if (err)
@@ -414,7 +429,7 @@ static int write_ec_cmd(acpi_handle handle, unsigned long cmd, unsigned long dat
end_jiffies = jiffies + msecs_to_jiffies(IDEAPAD_EC_TIMEOUT) + 1;
while (time_before(jiffies, end_jiffies)) {
- schedule();
+ usleep_range(IDEAPAD_EC_POLL_MIN_US, IDEAPAD_EC_POLL_MAX_US);
err = eval_vpcr(handle, 1, &val);
if (err)
diff --git a/drivers/platform/x86/intel/pmc/core.h b/drivers/platform/x86/intel/pmc/core.h
index e136d18b1d38..4a94a4ee031e 100644
--- a/drivers/platform/x86/intel/pmc/core.h
+++ b/drivers/platform/x86/intel/pmc/core.h
@@ -299,6 +299,13 @@ enum ppfear_regs {
#define PTL_PCD_PMC_MMIO_REG_LEN 0x31A8
/* SSRAM PMC Device ID */
+/* LNL */
+#define PMC_DEVID_LNL_SOCM 0xa87f
+
+/* PTL */
+#define PMC_DEVID_PTL_PCDH 0xe37f
+#define PMC_DEVID_PTL_PCDP 0xe47f
+
/* ARL */
#define PMC_DEVID_ARL_SOCM 0x777f
#define PMC_DEVID_ARL_SOCS 0xae7f
diff --git a/drivers/platform/x86/intel/pmc/ssram_telemetry.c b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
index b207247eb5dd..93579152188e 100644
--- a/drivers/platform/x86/intel/pmc/ssram_telemetry.c
+++ b/drivers/platform/x86/intel/pmc/ssram_telemetry.c
@@ -187,6 +187,9 @@ static const struct pci_device_id intel_pmc_ssram_telemetry_pci_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_MTL_SOCM) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCS) },
{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_ARL_SOCM) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_LNL_SOCM) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDH) },
+ { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PMC_DEVID_PTL_PCDP) },
{ }
};
MODULE_DEVICE_TABLE(pci, intel_pmc_ssram_telemetry_pci_ids);
diff --git a/drivers/platform/x86/intel/tpmi_power_domains.c b/drivers/platform/x86/intel/tpmi_power_domains.c
index 0c5c88eb7baf..9d8247bb9cfa 100644
--- a/drivers/platform/x86/intel/tpmi_power_domains.c
+++ b/drivers/platform/x86/intel/tpmi_power_domains.c
@@ -228,8 +228,10 @@ static int __init tpmi_init(void)
domain_die_map = kcalloc(size_mul(topology_max_packages(), MAX_POWER_DOMAINS),
sizeof(*domain_die_map), GFP_KERNEL);
- if (!domain_die_map)
+ if (!domain_die_map) {
+ ret = -ENOMEM;
goto free_domain_mask;
+ }
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
"platform/x86/tpmi_power_domains:online",
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
index 0f8aea18275b..65897fae17df 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c
@@ -58,7 +58,7 @@ static ssize_t show_agent_types(struct kobject *kobj, struct kobj_attribute *att
if (length)
length += sysfs_emit_at(buf, length, " ");
- length += sysfs_emit_at(buf, length, agent_name[agent]);
+ length += sysfs_emit_at(buf, length, "%s", agent_name[agent]);
}
length += sysfs_emit_at(buf, length, "\n");
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 1c7b2f2716ca..44d9948ed224 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -511,10 +511,13 @@ static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_
/* Get the package ID from the TPMI core */
plat_info = tpmi_get_platform_data(auxdev);
- if (plat_info)
- pkg = plat_info->package_id;
- else
+ if (unlikely(!plat_info)) {
dev_info(&auxdev->dev, "Platform information is NULL\n");
+ ret = -ENODEV;
+ goto err_rem_common;
+ }
+
+ pkg = plat_info->package_id;
for (i = 0; i < num_resources; ++i) {
struct tpmi_uncore_power_domain_info *pd_info;
diff --git a/drivers/platform/x86/samsung-galaxybook.c b/drivers/platform/x86/samsung-galaxybook.c
index 5878a351993e..3c13e13d4885 100644
--- a/drivers/platform/x86/samsung-galaxybook.c
+++ b/drivers/platform/x86/samsung-galaxybook.c
@@ -1403,6 +1403,7 @@ static int galaxybook_probe(struct platform_device *pdev)
}
static const struct acpi_device_id galaxybook_device_ids[] = {
+ { "SAM0426" },
{ "SAM0427" },
{ "SAM0428" },
{ "SAM0429" },
diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c
index 35a5994bf64f..36f57d7b4a66 100644
--- a/drivers/ptp/ptp_clock.c
+++ b/drivers/ptp/ptp_clock.c
@@ -121,7 +121,8 @@ static int ptp_clock_adjtime(struct posix_clock *pc, struct __kernel_timex *tx)
struct ptp_clock_info *ops;
int err = -EOPNOTSUPP;
- if (ptp_clock_freerun(ptp)) {
+ if (tx->modes & (ADJ_SETOFFSET | ADJ_FREQUENCY | ADJ_OFFSET) &&
+ ptp_clock_freerun(ptp)) {
pr_err("ptp: physical clock is free running\n");
return -EBUSY;
}
diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h
index 18934e28469e..a6aad743c282 100644
--- a/drivers/ptp/ptp_private.h
+++ b/drivers/ptp/ptp_private.h
@@ -100,10 +100,20 @@ static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
{
bool in_use = false;
+ /* Virtual clocks can't be stacked on top of virtual clocks.
+ * Avoid acquiring the n_vclocks_mux on virtual clocks, to allow this
+ * function to be called from code paths where the n_vclocks_mux of the
+ * parent physical clock is already held. Functionally that's not an
+ * issue, but lockdep would complain, because they have the same lock
+ * class.
+ */
+ if (ptp->is_virtual_clock)
+ return false;
+
if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
return true;
- if (!ptp->is_virtual_clock && ptp->n_vclocks)
+ if (ptp->n_vclocks)
in_use = true;
mutex_unlock(&ptp->n_vclocks_mux);
diff --git a/drivers/rapidio/rio_cm.c b/drivers/rapidio/rio_cm.c
index 97287e838ce1..66464674223f 100644
--- a/drivers/rapidio/rio_cm.c
+++ b/drivers/rapidio/rio_cm.c
@@ -783,6 +783,9 @@ static int riocm_ch_send(u16 ch_id, void *buf, int len)
if (buf == NULL || ch_id == 0 || len == 0 || len > RIO_MAX_MSG_SIZE)
return -EINVAL;
+ if (len < sizeof(struct rio_ch_chan_hdr))
+ return -EINVAL; /* insufficient data from user */
+
ch = riocm_get_channel(ch_id);
if (!ch) {
riocm_error("%s(%d) ch_%d not found", current->comm,
diff --git a/drivers/regulator/fan53555.c b/drivers/regulator/fan53555.c
index bd9447dac596..c282236959b1 100644
--- a/drivers/regulator/fan53555.c
+++ b/drivers/regulator/fan53555.c
@@ -147,6 +147,7 @@ struct fan53555_device_info {
unsigned int slew_mask;
const unsigned int *ramp_delay_table;
unsigned int n_ramp_values;
+ unsigned int enable_time;
unsigned int slew_rate;
};
@@ -282,6 +283,7 @@ static int fan53526_voltages_setup_fairchild(struct fan53555_device_info *di)
di->slew_mask = CTL_SLEW_MASK;
di->ramp_delay_table = slew_rates;
di->n_ramp_values = ARRAY_SIZE(slew_rates);
+ di->enable_time = 250;
di->vsel_count = FAN53526_NVOLTAGES;
return 0;
@@ -296,10 +298,12 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
case FAN53555_CHIP_REV_00:
di->vsel_min = 600000;
di->vsel_step = 10000;
+ di->enable_time = 400;
break;
case FAN53555_CHIP_REV_13:
di->vsel_min = 800000;
di->vsel_step = 10000;
+ di->enable_time = 400;
break;
default:
dev_err(di->dev,
@@ -311,13 +315,19 @@ static int fan53555_voltages_setup_fairchild(struct fan53555_device_info *di)
case FAN53555_CHIP_ID_01:
case FAN53555_CHIP_ID_03:
case FAN53555_CHIP_ID_05:
+ di->vsel_min = 600000;
+ di->vsel_step = 10000;
+ di->enable_time = 400;
+ break;
case FAN53555_CHIP_ID_08:
di->vsel_min = 600000;
di->vsel_step = 10000;
+ di->enable_time = 175;
break;
case FAN53555_CHIP_ID_04:
di->vsel_min = 603000;
di->vsel_step = 12826;
+ di->enable_time = 400;
break;
default:
dev_err(di->dev,
@@ -350,6 +360,7 @@ static int fan53555_voltages_setup_rockchip(struct fan53555_device_info *di)
di->slew_mask = CTL_SLEW_MASK;
di->ramp_delay_table = slew_rates;
di->n_ramp_values = ARRAY_SIZE(slew_rates);
+ di->enable_time = 360;
di->vsel_count = FAN53555_NVOLTAGES;
return 0;
@@ -372,6 +383,7 @@ static int rk8602_voltages_setup_rockchip(struct fan53555_device_info *di)
di->slew_mask = CTL_SLEW_MASK;
di->ramp_delay_table = slew_rates;
di->n_ramp_values = ARRAY_SIZE(slew_rates);
+ di->enable_time = 360;
di->vsel_count = RK8602_NVOLTAGES;
return 0;
@@ -395,6 +407,7 @@ static int fan53555_voltages_setup_silergy(struct fan53555_device_info *di)
di->slew_mask = CTL_SLEW_MASK;
di->ramp_delay_table = slew_rates;
di->n_ramp_values = ARRAY_SIZE(slew_rates);
+ di->enable_time = 400;
di->vsel_count = FAN53555_NVOLTAGES;
return 0;
@@ -594,6 +607,7 @@ static int fan53555_regulator_register(struct fan53555_device_info *di,
rdesc->ramp_mask = di->slew_mask;
rdesc->ramp_delay_table = di->ramp_delay_table;
rdesc->n_ramp_values = di->n_ramp_values;
+ rdesc->enable_time = di->enable_time;
rdesc->owner = THIS_MODULE;
rdev = devm_regulator_register(di->dev, &di->desc, config);
diff --git a/drivers/regulator/max20086-regulator.c b/drivers/regulator/max20086-regulator.c
index b4fe76e33ff2..fcdd2d0317a5 100644
--- a/drivers/regulator/max20086-regulator.c
+++ b/drivers/regulator/max20086-regulator.c
@@ -5,6 +5,7 @@
// Copyright (C) 2022 Laurent Pinchart <laurent.pinchart@idesonboard.com>
// Copyright (C) 2018 Avnet, Inc.
+#include <linux/cleanup.h>
#include <linux/err.h>
#include <linux/gpio/consumer.h>
#include <linux/i2c.h>
@@ -133,11 +134,11 @@ static int max20086_regulators_register(struct max20086 *chip)
static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
{
struct of_regulator_match *matches;
- struct device_node *node;
unsigned int i;
int ret;
- node = of_get_child_by_name(chip->dev->of_node, "regulators");
+ struct device_node *node __free(device_node) =
+ of_get_child_by_name(chip->dev->of_node, "regulators");
if (!node) {
dev_err(chip->dev, "regulators node not found\n");
return -ENODEV;
@@ -153,7 +154,6 @@ static int max20086_parse_regulators_dt(struct max20086 *chip, bool *boot_on)
ret = of_regulator_match(chip->dev, node, matches,
chip->info->num_outputs);
- of_node_put(node);
if (ret < 0) {
dev_err(chip->dev, "Failed to match regulators\n");
return -EINVAL;
diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c
index 41e36af35488..90a84ae98b97 100644
--- a/drivers/s390/scsi/zfcp_sysfs.c
+++ b/drivers/s390/scsi/zfcp_sysfs.c
@@ -449,6 +449,8 @@ static ssize_t zfcp_sysfs_unit_add_store(struct device *dev,
if (kstrtoull(buf, 0, (unsigned long long *) &fcp_lun))
return -EINVAL;
+ flush_work(&port->rport_work);
+
retval = zfcp_unit_add(port, fcp_lun);
if (retval)
return retval;
diff --git a/drivers/scsi/elx/efct/efct_hw.c b/drivers/scsi/elx/efct/efct_hw.c
index 5a5525054d71..5b079b8b7a08 100644
--- a/drivers/scsi/elx/efct/efct_hw.c
+++ b/drivers/scsi/elx/efct/efct_hw.c
@@ -1120,7 +1120,7 @@ int
efct_hw_parse_filter(struct efct_hw *hw, void *value)
{
int rc = 0;
- char *p = NULL;
+ char *p = NULL, *pp = NULL;
char *token;
u32 idx = 0;
@@ -1132,6 +1132,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
efc_log_err(hw->os, "p is NULL\n");
return -ENOMEM;
}
+ pp = p;
idx = 0;
while ((token = strsep(&p, ",")) && *token) {
@@ -1144,7 +1145,7 @@ efct_hw_parse_filter(struct efct_hw *hw, void *value)
if (idx == ARRAY_SIZE(hw->config.filter_def))
break;
}
- kfree(p);
+ kfree(pp);
return rc;
}
diff --git a/drivers/scsi/fnic/fdls_disc.c b/drivers/scsi/fnic/fdls_disc.c
index f8ab69c51dab..ae37f85f618b 100644
--- a/drivers/scsi/fnic/fdls_disc.c
+++ b/drivers/scsi/fnic/fdls_disc.c
@@ -763,50 +763,86 @@ static void fdls_send_fabric_abts(struct fnic_iport_s *iport)
iport->fabric.timer_pending = 1;
}
-static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
+static uint8_t *fdls_alloc_init_fdmi_abts_frame(struct fnic_iport_s *iport,
+ uint16_t oxid)
{
- uint8_t *frame;
+ struct fc_frame_header *pfdmi_abts;
uint8_t d_id[3];
+ uint8_t *frame;
struct fnic *fnic = iport->fnic;
- struct fc_frame_header *pfabric_abts;
- unsigned long fdmi_tov;
- uint16_t oxid;
- uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
- sizeof(struct fc_frame_header);
frame = fdls_alloc_frame(iport);
if (frame == NULL) {
FNIC_FCS_DBG(KERN_ERR, fnic->host, fnic->fnic_num,
"Failed to allocate frame to send FDMI ABTS");
- return;
+ return NULL;
}
- pfabric_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
+ pfdmi_abts = (struct fc_frame_header *) (frame + FNIC_ETH_FCOE_HDRS_OFFSET);
fdls_init_fabric_abts_frame(frame, iport);
hton24(d_id, FC_FID_MGMT_SERV);
- FNIC_STD_SET_D_ID(*pfabric_abts, d_id);
+ FNIC_STD_SET_D_ID(*pfdmi_abts, d_id);
+ FNIC_STD_SET_OX_ID(*pfdmi_abts, oxid);
+
+ return frame;
+}
+
+static void fdls_send_fdmi_abts(struct fnic_iport_s *iport)
+{
+ uint8_t *frame;
+ struct fnic *fnic = iport->fnic;
+ unsigned long fdmi_tov;
+ uint16_t frame_size = FNIC_ETH_FCOE_HDRS_OFFSET +
+ sizeof(struct fc_frame_header);
if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
- oxid = iport->active_oxid_fdmi_plogi;
- FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+ frame = fdls_alloc_init_fdmi_abts_frame(iport,
+ iport->active_oxid_fdmi_plogi);
+ if (frame == NULL)
+ return;
+
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: FDLS send FDMI PLOGI abts. iport->fabric.state: %d oxid: 0x%x",
+ iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_plogi);
fnic_send_fcoe_frame(iport, frame, frame_size);
} else {
if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
- oxid = iport->active_oxid_fdmi_rhba;
- FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+ frame = fdls_alloc_init_fdmi_abts_frame(iport,
+ iport->active_oxid_fdmi_rhba);
+ if (frame == NULL)
+ return;
+
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: FDLS send FDMI RHBA abts. iport->fabric.state: %d oxid: 0x%x",
+ iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rhba);
fnic_send_fcoe_frame(iport, frame, frame_size);
}
if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
- oxid = iport->active_oxid_fdmi_rpa;
- FNIC_STD_SET_OX_ID(*pfabric_abts, oxid);
+ frame = fdls_alloc_init_fdmi_abts_frame(iport,
+ iport->active_oxid_fdmi_rpa);
+ if (frame == NULL) {
+ if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)
+ goto arm_timer;
+ else
+ return;
+ }
+
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: FDLS send FDMI RPA abts. iport->fabric.state: %d oxid: 0x%x",
+ iport->fcid, iport->fabric.state, iport->active_oxid_fdmi_rpa);
fnic_send_fcoe_frame(iport, frame, frame_size);
}
}
+arm_timer:
fdmi_tov = jiffies + msecs_to_jiffies(2 * iport->e_d_tov);
mod_timer(&iport->fabric.fdmi_timer, round_jiffies(fdmi_tov));
iport->fabric.fdmi_pending |= FDLS_FDMI_ABORT_PENDING;
+
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
}
static void fdls_send_fabric_flogi(struct fnic_iport_s *iport)
@@ -2245,6 +2281,21 @@ void fdls_fabric_timer_callback(struct timer_list *t)
spin_unlock_irqrestore(&fnic->fnic_lock, flags);
}
+void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport)
+{
+ struct fnic *fnic = iport->fnic;
+
+ iport->fabric.fdmi_pending = 0;
+ /* If max retries not exhausted, start over from fdmi plogi */
+ if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) {
+ iport->fabric.fdmi_retry++;
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "Retry FDMI PLOGI. FDMI retry: %d",
+ iport->fabric.fdmi_retry);
+ fdls_send_fdmi_plogi(iport);
+ }
+}
+
void fdls_fdmi_timer_callback(struct timer_list *t)
{
struct fnic_fdls_fabric_s *fabric = timer_container_of(fabric, t,
@@ -2257,7 +2308,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
spin_lock_irqsave(&fnic->fnic_lock, flags);
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+ "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
if (!iport->fabric.fdmi_pending) {
/* timer expired after fdmi responses received. */
@@ -2265,7 +2316,7 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
return;
}
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+ "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
/* if not abort pending, send an abort */
if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) {
@@ -2274,33 +2325,37 @@ void fdls_fdmi_timer_callback(struct timer_list *t)
return;
}
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+ "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
/* ABTS pending for an active fdmi request that is pending.
* That means FDMI ABTS timed out
* Schedule to free the OXID after 2*r_a_tov and proceed
*/
if (iport->fabric.fdmi_pending & FDLS_FDMI_PLOGI_PENDING) {
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "FDMI PLOGI ABTS timed out. Schedule oxid free: 0x%x\n",
+ iport->active_oxid_fdmi_plogi);
fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_plogi);
} else {
- if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING)
+ if (iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING) {
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "FDMI RHBA ABTS timed out. Schedule oxid free: 0x%x\n",
+ iport->active_oxid_fdmi_rhba);
fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rhba);
- if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING)
+ }
+ if (iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING) {
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "FDMI RPA ABTS timed out. Schedule oxid free: 0x%x\n",
+ iport->active_oxid_fdmi_rpa);
fdls_schedule_oxid_free(iport, &iport->active_oxid_fdmi_rpa);
+ }
}
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+ "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
- iport->fabric.fdmi_pending = 0;
- /* If max retries not exhaused, start over from fdmi plogi */
- if (iport->fabric.fdmi_retry < FDLS_FDMI_MAX_RETRY) {
- iport->fabric.fdmi_retry++;
- FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "retry fdmi timer %d", iport->fabric.fdmi_retry);
- fdls_send_fdmi_plogi(iport);
- }
+ fdls_fdmi_retry_plogi(iport);
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
- "fdmi timer callback : 0x%x\n", iport->fabric.fdmi_pending);
+ "iport->fabric.fdmi_pending: 0x%x\n", iport->fabric.fdmi_pending);
spin_unlock_irqrestore(&fnic->fnic_lock, flags);
}
@@ -3715,13 +3770,60 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
switch (FNIC_FRAME_TYPE(oxid)) {
case FNIC_FRAME_TYPE_FDMI_PLOGI:
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "Received FDMI PLOGI ABTS rsp with oxid: 0x%x", oxid);
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_plogi);
+
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_PLOGI_PENDING;
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
break;
case FNIC_FRAME_TYPE_FDMI_RHBA:
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "Received FDMI RHBA ABTS rsp with oxid: 0x%x", oxid);
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
+
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_REG_HBA_PENDING;
+
+ /* If RPA is still pending, don't turn off ABORT PENDING.
+ * We count on the timer to detect the ABTS timeout and take
+ * corrective action.
+ */
+ if (!(iport->fabric.fdmi_pending & FDLS_FDMI_RPA_PENDING))
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+
fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rhba);
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
break;
case FNIC_FRAME_TYPE_FDMI_RPA:
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "Received FDMI RPA ABTS rsp with oxid: 0x%x", oxid);
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
+
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_RPA_PENDING;
+
+ /* If RHBA is still pending, don't turn off ABORT PENDING.
+ * We count on the timer to detect the ABTS timeout and take
+ * corrective action.
+ */
+ if (!(iport->fabric.fdmi_pending & FDLS_FDMI_REG_HBA_PENDING))
+ iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
+
fdls_free_oxid(iport, oxid, &iport->active_oxid_fdmi_rpa);
+ FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ "0x%x: iport->fabric.fdmi_pending: 0x%x",
+ iport->fcid, iport->fabric.fdmi_pending);
break;
default:
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
@@ -3730,10 +3832,16 @@ static void fdls_process_fdmi_abts_rsp(struct fnic_iport_s *iport,
break;
}
- timer_delete_sync(&iport->fabric.fdmi_timer);
- iport->fabric.fdmi_pending &= ~FDLS_FDMI_ABORT_PENDING;
-
- fdls_send_fdmi_plogi(iport);
+ /*
+ * Only if ABORT PENDING is off, delete the timer, and if no other
+ * operations are pending, retry FDMI.
+ * Otherwise, let the timer pop and take the appropriate action.
+ */
+ if (!(iport->fabric.fdmi_pending & FDLS_FDMI_ABORT_PENDING)) {
+ timer_delete_sync(&iport->fabric.fdmi_timer);
+ if (!iport->fabric.fdmi_pending)
+ fdls_fdmi_retry_plogi(iport);
+ }
}
static void
@@ -4972,9 +5080,12 @@ void fnic_fdls_link_down(struct fnic_iport_s *iport)
fdls_delete_tport(iport, tport);
}
- if ((fnic_fdmi_support == 1) && (iport->fabric.fdmi_pending > 0)) {
- timer_delete_sync(&iport->fabric.fdmi_timer);
- iport->fabric.fdmi_pending = 0;
+ if (fnic_fdmi_support == 1) {
+ if (iport->fabric.fdmi_pending > 0) {
+ timer_delete_sync(&iport->fabric.fdmi_timer);
+ iport->fabric.fdmi_pending = 0;
+ }
+ iport->flags &= ~FNIC_FDMI_ACTIVE;
}
FNIC_FCS_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 6c5f6046b1f5..c2fdc6553e62 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -30,7 +30,7 @@
#define DRV_NAME "fnic"
#define DRV_DESCRIPTION "Cisco FCoE HBA Driver"
-#define DRV_VERSION "1.8.0.0"
+#define DRV_VERSION "1.8.0.2"
#define PFX DRV_NAME ": "
#define DFX DRV_NAME "%d: "
diff --git a/drivers/scsi/fnic/fnic_fcs.c b/drivers/scsi/fnic/fnic_fcs.c
index 1e8cd64f9a5c..103ab6f1f7cd 100644
--- a/drivers/scsi/fnic/fnic_fcs.c
+++ b/drivers/scsi/fnic/fnic_fcs.c
@@ -636,6 +636,8 @@ static int fnic_send_frame(struct fnic *fnic, void *frame, int frame_len)
unsigned long flags;
pa = dma_map_single(&fnic->pdev->dev, frame, frame_len, DMA_TO_DEVICE);
+ if (dma_mapping_error(&fnic->pdev->dev, pa))
+ return -ENOMEM;
if ((fnic_fc_trace_set_data(fnic->fnic_num,
FNIC_FC_SEND | 0x80, (char *) frame,
diff --git a/drivers/scsi/fnic/fnic_fdls.h b/drivers/scsi/fnic/fnic_fdls.h
index 8e610b65ad57..531d0b37e450 100644
--- a/drivers/scsi/fnic/fnic_fdls.h
+++ b/drivers/scsi/fnic/fnic_fdls.h
@@ -394,6 +394,7 @@ void fdls_send_tport_abts(struct fnic_iport_s *iport,
bool fdls_delete_tport(struct fnic_iport_s *iport,
struct fnic_tport_s *tport);
void fdls_fdmi_timer_callback(struct timer_list *t);
+void fdls_fdmi_retry_plogi(struct fnic_iport_s *iport);
/* fnic_fcs.c */
void fnic_fdls_init(struct fnic *fnic, int usefip);
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 7133b254cbe4..75b29a018d1f 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -1046,7 +1046,7 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, unsigned int cq_ind
if (icmnd_cmpl->scsi_status == SAM_STAT_TASK_SET_FULL)
atomic64_inc(&fnic_stats->misc_stats.queue_fulls);
- FNIC_SCSI_DBG(KERN_INFO, fnic->host, fnic->fnic_num,
+ FNIC_SCSI_DBG(KERN_DEBUG, fnic->host, fnic->fnic_num,
"xfer_len: %llu", xfer_len);
break;
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 3aac0e17cb00..9179f8aee964 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -5910,7 +5910,11 @@ megasas_set_high_iops_queue_affinity_and_hint(struct megasas_instance *instance)
const struct cpumask *mask;
if (instance->perf_mode == MR_BALANCED_PERF_MODE) {
- mask = cpumask_of_node(dev_to_node(&instance->pdev->dev));
+ int nid = dev_to_node(&instance->pdev->dev);
+
+ if (nid == NUMA_NO_NODE)
+ nid = 0;
+ mask = cpumask_of_node(nid);
for (i = 0; i < instance->low_latency_index_start; i++) {
irq = pci_irq_vector(instance->pdev, i);
diff --git a/drivers/scsi/mvsas/mv_defs.h b/drivers/scsi/mvsas/mv_defs.h
index 8ef174cd4d37..3e4124177b2a 100644
--- a/drivers/scsi/mvsas/mv_defs.h
+++ b/drivers/scsi/mvsas/mv_defs.h
@@ -215,7 +215,7 @@ enum hw_register_bits {
/* MVS_Px_INT_STAT, MVS_Px_INT_MASK (per-phy events) */
PHYEV_DEC_ERR = (1U << 24), /* Phy Decoding Error */
- PHYEV_DCDR_ERR = (1U << 23), /* STP Deocder Error */
+ PHYEV_DCDR_ERR = (1U << 23), /* STP Decoder Error */
PHYEV_CRC_ERR = (1U << 22), /* STP CRC Error */
PHYEV_UNASSOC_FIS = (1U << 19), /* unassociated FIS rx'd */
PHYEV_AN = (1U << 18), /* SATA async notification */
@@ -347,7 +347,7 @@ enum sas_cmd_port_registers {
CMD_SATA_PORT_MEM_CTL0 = 0x158, /* SATA Port Memory Control 0 */
CMD_SATA_PORT_MEM_CTL1 = 0x15c, /* SATA Port Memory Control 1 */
CMD_XOR_MEM_BIST_CTL = 0x160, /* XOR Memory BIST Control */
- CMD_XOR_MEM_BIST_STAT = 0x164, /* XOR Memroy BIST Status */
+ CMD_XOR_MEM_BIST_STAT = 0x164, /* XOR Memory BIST Status */
CMD_DMA_MEM_BIST_CTL = 0x168, /* DMA Memory BIST Control */
CMD_DMA_MEM_BIST_STAT = 0x16c, /* DMA Memory BIST Status */
CMD_PORT_MEM_BIST_CTL = 0x170, /* Port Memory BIST Control */
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 376b8897ab90..746ff6a1f309 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -665,7 +665,8 @@ enum scsi_disposition scsi_check_sense(struct scsi_cmnd *scmd)
* if the device is in the process of becoming ready, we
* should retry.
*/
- if ((sshdr.asc == 0x04) && (sshdr.ascq == 0x01))
+ if ((sshdr.asc == 0x04) &&
+ (sshdr.ascq == 0x01 || sshdr.ascq == 0x0a))
return NEEDS_RETRY;
/*
* if the device is not started, we need to wake
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 0b8c91bf793f..c75a806496d6 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -3499,7 +3499,7 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
pr_err("%s could not find host no %u\n",
__func__, ev->u.new_flashnode.host_no);
err = -ENODEV;
- goto put_host;
+ goto exit_new_fnode;
}
index = transport->new_flashnode(shost, data, len);
@@ -3509,7 +3509,6 @@ static int iscsi_new_flashnode(struct iscsi_transport *transport,
else
err = -EIO;
-put_host:
scsi_host_put(shost);
exit_new_fnode:
@@ -3534,7 +3533,7 @@ static int iscsi_del_flashnode(struct iscsi_transport *transport,
pr_err("%s could not find host no %u\n",
__func__, ev->u.del_flashnode.host_no);
err = -ENODEV;
- goto put_host;
+ goto exit_del_fnode;
}
idx = ev->u.del_flashnode.flashnode_idx;
@@ -3576,7 +3575,7 @@ static int iscsi_login_flashnode(struct iscsi_transport *transport,
pr_err("%s could not find host no %u\n",
__func__, ev->u.login_flashnode.host_no);
err = -ENODEV;
- goto put_host;
+ goto exit_login_fnode;
}
idx = ev->u.login_flashnode.flashnode_idx;
@@ -3628,7 +3627,7 @@ static int iscsi_logout_flashnode(struct iscsi_transport *transport,
pr_err("%s could not find host no %u\n",
__func__, ev->u.logout_flashnode.host_no);
err = -ENODEV;
- goto put_host;
+ goto exit_logout_fnode;
}
idx = ev->u.logout_flashnode.flashnode_idx;
@@ -3678,7 +3677,7 @@ static int iscsi_logout_flashnode_sid(struct iscsi_transport *transport,
pr_err("%s could not find host no %u\n",
__func__, ev->u.logout_flashnode.host_no);
err = -ENODEV;
- goto put_host;
+ goto exit_logout_sid;
}
session = iscsi_session_lookup(ev->u.logout_flashnode_sid.sid);
diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c
index 2e6b2412d2c9..d9e59204a9c3 100644
--- a/drivers/scsi/storvsc_drv.c
+++ b/drivers/scsi/storvsc_drv.c
@@ -362,7 +362,7 @@ MODULE_PARM_DESC(ring_avail_percent_lowater,
/*
* Timeout in seconds for all devices managed by this driver.
*/
-static int storvsc_timeout = 180;
+static const int storvsc_timeout = 180;
#if IS_ENABLED(CONFIG_SCSI_FC_ATTRS)
static struct scsi_transport_template *fc_transport_template;
@@ -768,7 +768,7 @@ static void handle_multichannel_storage(struct hv_device *device, int max_chns)
return;
}
- t = wait_for_completion_timeout(&request->wait_event, 10*HZ);
+ t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
if (t == 0) {
dev_err(dev, "Failed to create sub-channel: timed out\n");
return;
@@ -833,7 +833,7 @@ static int storvsc_execute_vstor_op(struct hv_device *device,
if (ret != 0)
return ret;
- t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+ t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
if (t == 0)
return -ETIMEDOUT;
@@ -1350,6 +1350,8 @@ static int storvsc_connect_to_vsp(struct hv_device *device, u32 ring_size,
return ret;
ret = storvsc_channel_init(device, is_fc);
+ if (ret)
+ vmbus_close(device->channel);
return ret;
}
@@ -1668,7 +1670,7 @@ static int storvsc_host_reset_handler(struct scsi_cmnd *scmnd)
if (ret != 0)
return FAILED;
- t = wait_for_completion_timeout(&request->wait_event, 5*HZ);
+ t = wait_for_completion_timeout(&request->wait_event, storvsc_timeout * HZ);
if (t == 0)
return TIMEOUT_ERROR;
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
index fe0f122f07b0..aa1932ba17cb 100644
--- a/drivers/spi/spi-cadence-quadspi.c
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -1958,10 +1958,10 @@ static int cqspi_probe(struct platform_device *pdev)
goto probe_setup_failed;
}
- ret = devm_pm_runtime_enable(dev);
- if (ret) {
- if (cqspi->rx_chan)
- dma_release_channel(cqspi->rx_chan);
+ pm_runtime_enable(dev);
+
+ if (cqspi->rx_chan) {
+ dma_release_channel(cqspi->rx_chan);
goto probe_setup_failed;
}
@@ -1981,6 +1981,7 @@ static int cqspi_probe(struct platform_device *pdev)
return 0;
probe_setup_failed:
cqspi_controller_enable(cqspi, 0);
+ pm_runtime_disable(dev);
probe_reset_failed:
if (cqspi->is_jh7110)
cqspi_jh7110_disable_clk(pdev, cqspi);
@@ -1999,7 +2000,8 @@ static void cqspi_remove(struct platform_device *pdev)
if (cqspi->rx_chan)
dma_release_channel(cqspi->rx_chan);
- clk_disable_unprepare(cqspi->clk);
+ if (pm_runtime_get_sync(&pdev->dev) >= 0)
+ clk_disable(cqspi->clk);
if (cqspi->is_jh7110)
cqspi_jh7110_disable_clk(pdev, cqspi);
diff --git a/drivers/spi/spi-loongson-core.c b/drivers/spi/spi-loongson-core.c
index 4fec226456d1..b46f072a0387 100644
--- a/drivers/spi/spi-loongson-core.c
+++ b/drivers/spi/spi-loongson-core.c
@@ -5,6 +5,7 @@
#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/interrupt.h>
#include <linux/io.h>
diff --git a/drivers/spi/spi-offload.c b/drivers/spi/spi-offload.c
index e674097bf3be..d336f4d228d5 100644
--- a/drivers/spi/spi-offload.c
+++ b/drivers/spi/spi-offload.c
@@ -297,7 +297,7 @@ int spi_offload_trigger_enable(struct spi_offload *offload,
if (trigger->ops->enable) {
ret = trigger->ops->enable(trigger, config);
if (ret) {
- if (offload->ops->trigger_disable)
+ if (offload->ops && offload->ops->trigger_disable)
offload->ops->trigger_disable(offload);
return ret;
}
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 29c616e2c408..70bb74b3bd9c 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -134,6 +134,7 @@ struct omap2_mcspi {
size_t max_xfer_len;
u32 ref_clk_hz;
bool use_multi_mode;
+ bool last_msg_kept_cs;
};
struct omap2_mcspi_cs {
@@ -1269,6 +1270,10 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
* multi-mode is applicable.
*/
mcspi->use_multi_mode = true;
+
+ if (mcspi->last_msg_kept_cs)
+ mcspi->use_multi_mode = false;
+
list_for_each_entry(tr, &msg->transfers, transfer_list) {
if (!tr->bits_per_word)
bits_per_word = msg->spi->bits_per_word;
@@ -1287,18 +1292,19 @@ static int omap2_mcspi_prepare_message(struct spi_controller *ctlr,
mcspi->use_multi_mode = false;
}
- /* Check if transfer asks to change the CS status after the transfer */
- if (!tr->cs_change)
- mcspi->use_multi_mode = false;
-
- /*
- * If at least one message is not compatible, switch back to single mode
- *
- * The bits_per_word of certain transfer can be different, but it will have no
- * impact on the signal itself.
- */
- if (!mcspi->use_multi_mode)
- break;
+ if (list_is_last(&tr->transfer_list, &msg->transfers)) {
+ /* Check if transfer asks to keep the CS status after the whole message */
+ if (tr->cs_change) {
+ mcspi->use_multi_mode = false;
+ mcspi->last_msg_kept_cs = true;
+ } else {
+ mcspi->last_msg_kept_cs = false;
+ }
+ } else {
+ /* Check if transfer asks to change the CS status after the transfer */
+ if (!tr->cs_change)
+ mcspi->use_multi_mode = false;
+ }
}
omap2_mcspi_set_mode(ctlr);
diff --git a/drivers/spi/spi-pci1xxxx.c b/drivers/spi/spi-pci1xxxx.c
index c6489e90b8b9..e27642c4dea4 100644
--- a/drivers/spi/spi-pci1xxxx.c
+++ b/drivers/spi/spi-pci1xxxx.c
@@ -762,10 +762,10 @@ static int pci1xxxx_spi_probe(struct pci_dev *pdev, const struct pci_device_id *
return -EINVAL;
num_vector = pci_alloc_irq_vectors(pdev, 1, hw_inst_cnt,
- PCI_IRQ_ALL_TYPES);
+ PCI_IRQ_INTX | PCI_IRQ_MSI);
if (num_vector < 0) {
dev_err(&pdev->dev, "Error allocating MSI vectors\n");
- return ret;
+ return num_vector;
}
init_completion(&spi_sub_ptr->spi_xfer_done);
diff --git a/drivers/spi/spi-stm32-ospi.c b/drivers/spi/spi-stm32-ospi.c
index 7c1fa55fbc47..4ab7e86f4bd5 100644
--- a/drivers/spi/spi-stm32-ospi.c
+++ b/drivers/spi/spi-stm32-ospi.c
@@ -804,7 +804,7 @@ static int stm32_ospi_get_resources(struct platform_device *pdev)
return ret;
}
- ospi->rstc = devm_reset_control_array_get_exclusive(dev);
+ ospi->rstc = devm_reset_control_array_get_exclusive_released(dev);
if (IS_ERR(ospi->rstc))
return dev_err_probe(dev, PTR_ERR(ospi->rstc),
"Can't get reset\n");
@@ -936,12 +936,16 @@ static int stm32_ospi_probe(struct platform_device *pdev)
if (ret < 0)
goto err_pm_enable;
- if (ospi->rstc) {
- reset_control_assert(ospi->rstc);
- udelay(2);
- reset_control_deassert(ospi->rstc);
+ ret = reset_control_acquire(ospi->rstc);
+ if (ret) {
+ dev_err_probe(dev, ret, "Can not acquire reset %d\n", ret);
+ goto err_pm_resume;
}
+ reset_control_assert(ospi->rstc);
+ udelay(2);
+ reset_control_deassert(ospi->rstc);
+
ret = spi_register_controller(ctrl);
if (ret) {
/* Disable ospi */
@@ -987,6 +991,8 @@ static void stm32_ospi_remove(struct platform_device *pdev)
if (ospi->dma_chrx)
dma_release_channel(ospi->dma_chrx);
+ reset_control_release(ospi->rstc);
+
pm_runtime_put_sync_suspend(ospi->dev);
pm_runtime_force_suspend(ospi->dev);
}
@@ -997,6 +1003,8 @@ static int __maybe_unused stm32_ospi_suspend(struct device *dev)
pinctrl_pm_select_sleep_state(dev);
+ reset_control_release(ospi->rstc);
+
return pm_runtime_force_suspend(ospi->dev);
}
@@ -1016,6 +1024,12 @@ static int __maybe_unused stm32_ospi_resume(struct device *dev)
if (ret < 0)
return ret;
+ ret = reset_control_acquire(ospi->rstc);
+ if (ret) {
+ dev_err(dev, "Can not acquire reset\n");
+ return ret;
+ }
+
writel_relaxed(ospi->cr_reg, regs_base + OSPI_CR);
writel_relaxed(ospi->dcr_reg, regs_base + OSPI_DCR1);
pm_runtime_mark_last_busy(ospi->dev);
diff --git a/drivers/spi/spi-tegra210-quad.c b/drivers/spi/spi-tegra210-quad.c
index 3581757a269b..3be7499db21e 100644
--- a/drivers/spi/spi-tegra210-quad.c
+++ b/drivers/spi/spi-tegra210-quad.c
@@ -407,9 +407,6 @@ tegra_qspi_read_rx_fifo_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_tra
static void
tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
- dma_sync_single_for_cpu(tqspi->dev, tqspi->tx_dma_phys,
- tqspi->dma_buf_size, DMA_TO_DEVICE);
-
/*
* In packed mode, each word in FIFO may contain multiple packets
* based on bits per word. So all bytes in each FIFO word are valid.
@@ -442,17 +439,11 @@ tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_
tqspi->cur_tx_pos += write_bytes;
}
-
- dma_sync_single_for_device(tqspi->dev, tqspi->tx_dma_phys,
- tqspi->dma_buf_size, DMA_TO_DEVICE);
}
static void
tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
- dma_sync_single_for_cpu(tqspi->dev, tqspi->rx_dma_phys,
- tqspi->dma_buf_size, DMA_FROM_DEVICE);
-
if (tqspi->is_packed) {
tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
} else {
@@ -478,9 +469,6 @@ tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_
tqspi->cur_rx_pos += read_bytes;
}
-
- dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
- tqspi->dma_buf_size, DMA_FROM_DEVICE);
}
static void tegra_qspi_dma_complete(void *args)
@@ -701,8 +689,6 @@ static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct
return ret;
}
- dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
- tqspi->dma_buf_size, DMA_FROM_DEVICE);
ret = tegra_qspi_start_rx_dma(tqspi, t, len);
if (ret < 0) {
dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 34cf2c399b39..70905805cb17 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1842,7 +1842,9 @@ out:
}
kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
- core_scsi3_lunacl_undepend_item(dest_se_deve);
+
+ if (dest_se_deve)
+ core_scsi3_lunacl_undepend_item(dest_se_deve);
if (is_local)
continue;
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 4410e7d93b7d..50adfb8b335b 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6623,9 +6623,14 @@ static void ufshcd_err_handler(struct work_struct *work)
up(&hba->host_sem);
return;
}
- ufshcd_set_eh_in_progress(hba);
spin_unlock_irqrestore(hba->host->host_lock, flags);
+
ufshcd_err_handling_prepare(hba);
+
+ spin_lock_irqsave(hba->host->host_lock, flags);
+ ufshcd_set_eh_in_progress(hba);
+ spin_unlock_irqrestore(hba->host->host_lock, flags);
+
/* Complete requests that have door-bell cleared by h/w */
ufshcd_complete_requests(hba, false);
spin_lock_irqsave(hba->host->host_lock, flags);
@@ -7802,7 +7807,8 @@ static int ufshcd_host_reset_and_restore(struct ufs_hba *hba)
hba->silence_err_logs = false;
/* scale up clocks to max frequency before full reinitialization */
- ufshcd_scale_clks(hba, ULONG_MAX, true);
+ if (ufshcd_is_clkscaling_supported(hba))
+ ufshcd_scale_clks(hba, ULONG_MAX, true);
err = ufshcd_hba_enable(hba);
diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 3651a296d506..5a1cede2febf 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -296,7 +296,6 @@ do { \
#define bch2_fmt(_c, fmt) bch2_log_msg(_c, fmt "\n")
void bch2_print_str(struct bch_fs *, const char *, const char *);
-void bch2_print_str_nonblocking(struct bch_fs *, const char *, const char *);
__printf(2, 3)
void bch2_print_opts(struct bch_opts *, const char *, ...);
diff --git a/fs/bcachefs/btree_gc.c b/fs/bcachefs/btree_gc.c
index 9ddcbe1bda78..e92cf3928c63 100644
--- a/fs/bcachefs/btree_gc.c
+++ b/fs/bcachefs/btree_gc.c
@@ -397,7 +397,11 @@ again:
continue;
}
- ret = btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan);
+ ret = lockrestart_do(trans,
+ btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan));
+ if (ret < 0)
+ goto err;
+
if (ret == DID_FILL_FROM_SCAN) {
new_pass = true;
ret = 0;
@@ -438,7 +442,8 @@ again:
if (!ret && !IS_ERR_OR_NULL(prev)) {
BUG_ON(cur);
- ret = btree_repair_node_end(trans, b, prev, pulled_from_scan);
+ ret = lockrestart_do(trans,
+ btree_repair_node_end(trans, b, prev, pulled_from_scan));
if (ret == DID_FILL_FROM_SCAN) {
new_pass = true;
ret = 0;
@@ -519,6 +524,46 @@ fsck_err:
bch2_bkey_buf_exit(&prev_k, c);
bch2_bkey_buf_exit(&cur_k, c);
printbuf_exit(&buf);
+ bch_err_fn(c, ret);
+ return ret;
+}
+
+static int bch2_check_root(struct btree_trans *trans, enum btree_id i,
+ bool *reconstructed_root)
+{
+ struct bch_fs *c = trans->c;
+ struct btree_root *r = bch2_btree_id_root(c, i);
+ struct printbuf buf = PRINTBUF;
+ int ret = 0;
+
+ bch2_btree_id_to_text(&buf, i);
+
+ if (r->error) {
+ bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
+
+ r->alive = false;
+ r->error = 0;
+
+ if (!bch2_btree_has_scanned_nodes(c, i)) {
+ __fsck_err(trans,
+ FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
+ btree_root_unreadable_and_scan_found_nothing,
+ "no nodes found for btree %s, continue?", buf.buf);
+ bch2_btree_root_alloc_fake_trans(trans, i, 0);
+ } else {
+ bch2_btree_root_alloc_fake_trans(trans, i, 1);
+ bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
+ ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
+ if (ret)
+ goto err;
+ }
+
+ *reconstructed_root = true;
+ }
+err:
+fsck_err:
+ printbuf_exit(&buf);
+ bch_err_fn(c, ret);
return ret;
}
@@ -526,42 +571,18 @@ int bch2_check_topology(struct bch_fs *c)
{
struct btree_trans *trans = bch2_trans_get(c);
struct bpos pulled_from_scan = POS_MIN;
- struct printbuf buf = PRINTBUF;
int ret = 0;
bch2_trans_srcu_unlock(trans);
for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) {
- struct btree_root *r = bch2_btree_id_root(c, i);
bool reconstructed_root = false;
+recover:
+ ret = lockrestart_do(trans, bch2_check_root(trans, i, &reconstructed_root));
+ if (ret)
+ break;
- printbuf_reset(&buf);
- bch2_btree_id_to_text(&buf, i);
-
- if (r->error) {
-reconstruct_root:
- bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf);
-
- r->alive = false;
- r->error = 0;
-
- if (!bch2_btree_has_scanned_nodes(c, i)) {
- __fsck_err(trans,
- FSCK_CAN_FIX|(!btree_id_important(i) ? FSCK_AUTOFIX : 0),
- btree_root_unreadable_and_scan_found_nothing,
- "no nodes found for btree %s, continue?", buf.buf);
- bch2_btree_root_alloc_fake_trans(trans, i, 0);
- } else {
- bch2_btree_root_alloc_fake_trans(trans, i, 1);
- bch2_shoot_down_journal_keys(c, i, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX);
- ret = bch2_get_scanned_nodes(c, i, 0, POS_MIN, SPOS_MAX);
- if (ret)
- break;
- }
-
- reconstructed_root = true;
- }
-
+ struct btree_root *r = bch2_btree_id_root(c, i);
struct btree *b = r->b;
btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read);
@@ -575,17 +596,21 @@ reconstruct_root:
r->b = NULL;
- if (!reconstructed_root)
- goto reconstruct_root;
+ if (!reconstructed_root) {
+ r->error = -EIO;
+ goto recover;
+ }
+ struct printbuf buf = PRINTBUF;
+ bch2_btree_id_to_text(&buf, i);
bch_err(c, "empty btree root %s", buf.buf);
+ printbuf_exit(&buf);
bch2_btree_root_alloc_fake_trans(trans, i, 0);
r->alive = false;
ret = 0;
}
}
-fsck_err:
- printbuf_exit(&buf);
+
bch2_trans_put(trans);
return ret;
}
diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index 57eff3012a7b..d8f3c4c65e90 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -741,16 +741,22 @@ static int validate_bset(struct bch_fs *c, struct bch_dev *ca,
BCH_VERSION_MAJOR(version),
BCH_VERSION_MINOR(version));
- if (btree_err_on(version < c->sb.version_min,
+ if (c->recovery.curr_pass != BCH_RECOVERY_PASS_scan_for_btree_nodes &&
+ btree_err_on(version < c->sb.version_min,
-BCH_ERR_btree_node_read_err_fixable,
c, NULL, b, i, NULL,
btree_node_bset_older_than_sb_min,
"bset version %u older than superblock version_min %u",
version, c->sb.version_min)) {
- mutex_lock(&c->sb_lock);
- c->disk_sb.sb->version_min = cpu_to_le16(version);
- bch2_write_super(c);
- mutex_unlock(&c->sb_lock);
+ if (bch2_version_compatible(version)) {
+ mutex_lock(&c->sb_lock);
+ c->disk_sb.sb->version_min = cpu_to_le16(version);
+ bch2_write_super(c);
+ mutex_unlock(&c->sb_lock);
+ } else {
+ /* We have no idea what's going on: */
+ i->version = cpu_to_le16(c->sb.version);
+ }
}
if (btree_err_on(BCH_VERSION_MAJOR(version) >
@@ -1045,6 +1051,7 @@ got_good_key:
le16_add_cpu(&i->u64s, -next_good_key);
memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k);
set_btree_node_need_rewrite(b);
+ set_btree_node_need_rewrite_error(b);
}
fsck_err:
printbuf_exit(&buf);
@@ -1305,6 +1312,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
(u64 *) vstruct_end(i) - (u64 *) k);
set_btree_bset_end(b, b->set);
set_btree_node_need_rewrite(b);
+ set_btree_node_need_rewrite_error(b);
continue;
}
if (ret)
@@ -1329,12 +1337,16 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
bkey_for_each_ptr(bch2_bkey_ptrs(bkey_i_to_s(&b->key)), ptr) {
struct bch_dev *ca2 = bch2_dev_rcu(c, ptr->dev);
- if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw)
+ if (!ca2 || ca2->mi.state != BCH_MEMBER_STATE_rw) {
set_btree_node_need_rewrite(b);
+ set_btree_node_need_rewrite_degraded(b);
+ }
}
- if (!ptr_written)
+ if (!ptr_written) {
set_btree_node_need_rewrite(b);
+ set_btree_node_need_rewrite_ptr_written_zero(b);
+ }
fsck_err:
mempool_free(iter, &c->fill_iter);
printbuf_exit(&buf);
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 47035aae232e..91a51aef82f1 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -213,7 +213,7 @@ static noinline __noreturn void break_cycle_fail(struct lock_graph *g)
prt_newline(&buf);
}
- bch2_print_str_nonblocking(g->g->trans->c, KERN_ERR, buf.buf);
+ bch2_print_str(g->g->trans->c, KERN_ERR, buf.buf);
printbuf_exit(&buf);
BUG();
}
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index 9adca77e2580..f2173a3316f4 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -417,8 +417,10 @@ static inline void btree_path_set_should_be_locked(struct btree_trans *trans, st
EBUG_ON(!btree_node_locked(path, path->level));
EBUG_ON(path->uptodate);
- path->should_be_locked = true;
- trace_btree_path_should_be_locked(trans, path);
+ if (!path->should_be_locked) {
+ path->should_be_locked = true;
+ trace_btree_path_should_be_locked(trans, path);
+ }
}
static inline void __btree_path_set_level_up(struct btree_trans *trans,
diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h
index c61c4171ae50..3aa4a602bd02 100644
--- a/fs/bcachefs/btree_types.h
+++ b/fs/bcachefs/btree_types.h
@@ -617,6 +617,9 @@ enum btree_write_type {
x(dying) \
x(fake) \
x(need_rewrite) \
+ x(need_rewrite_error) \
+ x(need_rewrite_degraded) \
+ x(need_rewrite_ptr_written_zero) \
x(never_write) \
x(pinned)
@@ -641,6 +644,32 @@ static inline void clear_btree_node_ ## flag(struct btree *b) \
BTREE_FLAGS()
#undef x
+#define BTREE_NODE_REWRITE_REASON() \
+ x(none) \
+ x(unknown) \
+ x(error) \
+ x(degraded) \
+ x(ptr_written_zero)
+
+enum btree_node_rewrite_reason {
+#define x(n) BTREE_NODE_REWRITE_##n,
+ BTREE_NODE_REWRITE_REASON()
+#undef x
+};
+
+static inline enum btree_node_rewrite_reason btree_node_rewrite_reason(struct btree *b)
+{
+ if (btree_node_need_rewrite_ptr_written_zero(b))
+ return BTREE_NODE_REWRITE_ptr_written_zero;
+ if (btree_node_need_rewrite_degraded(b))
+ return BTREE_NODE_REWRITE_degraded;
+ if (btree_node_need_rewrite_error(b))
+ return BTREE_NODE_REWRITE_error;
+ if (btree_node_need_rewrite(b))
+ return BTREE_NODE_REWRITE_unknown;
+ return BTREE_NODE_REWRITE_none;
+}
+
static inline struct btree_write *btree_current_write(struct btree *b)
{
return b->writes + btree_node_write_idx(b);
diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c
index d2ecb782919b..e77584607f0d 100644
--- a/fs/bcachefs/btree_update_interior.c
+++ b/fs/bcachefs/btree_update_interior.c
@@ -1138,6 +1138,13 @@ static void bch2_btree_update_done(struct btree_update *as, struct btree_trans *
start_time);
}
+static const char * const btree_node_reawrite_reason_strs[] = {
+#define x(n) #n,
+ BTREE_NODE_REWRITE_REASON()
+#undef x
+ NULL,
+};
+
static struct btree_update *
bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
unsigned level_start, bool split,
@@ -1232,6 +1239,15 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path,
list_add_tail(&as->list, &c->btree_interior_update_list);
mutex_unlock(&c->btree_interior_update_lock);
+ struct btree *b = btree_path_node(path, path->level);
+ as->node_start = b->data->min_key;
+ as->node_end = b->data->max_key;
+ as->node_needed_rewrite = btree_node_rewrite_reason(b);
+ as->node_written = b->written;
+ as->node_sectors = btree_buf_bytes(b) >> 9;
+ as->node_remaining = __bch2_btree_u64s_remaining(b,
+ btree_bkey_last(b, bset_tree_last(b)));
+
/*
* We don't want to allocate if we're in an error state, that can cause
* deadlock on emergency shutdown due to open buckets getting stuck in
@@ -2108,6 +2124,9 @@ int __bch2_foreground_maybe_merge(struct btree_trans *trans,
if (ret)
goto err;
+ as->node_start = prev->data->min_key;
+ as->node_end = next->data->max_key;
+
trace_and_count(c, btree_node_merge, trans, b);
n = bch2_btree_node_alloc(as, trans, b->c.level);
@@ -2681,9 +2700,19 @@ static void bch2_btree_update_to_text(struct printbuf *out, struct btree_update
prt_str(out, " ");
bch2_btree_id_to_text(out, as->btree_id);
- prt_printf(out, " l=%u-%u mode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
+ prt_printf(out, " l=%u-%u ",
as->update_level_start,
- as->update_level_end,
+ as->update_level_end);
+ bch2_bpos_to_text(out, as->node_start);
+ prt_char(out, ' ');
+ bch2_bpos_to_text(out, as->node_end);
+ prt_printf(out, "\nwritten %u/%u u64s_remaining %u need_rewrite %s",
+ as->node_written,
+ as->node_sectors,
+ as->node_remaining,
+ btree_node_reawrite_reason_strs[as->node_needed_rewrite]);
+
+ prt_printf(out, "\nmode=%s nodes_written=%u cl.remaining=%u journal_seq=%llu\n",
bch2_btree_update_modes[as->mode],
as->nodes_written,
closure_nr_remaining(&as->cl),
diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h
index 7fe793788a79..b649c36c3fbb 100644
--- a/fs/bcachefs/btree_update_interior.h
+++ b/fs/bcachefs/btree_update_interior.h
@@ -57,6 +57,13 @@ struct btree_update {
unsigned took_gc_lock:1;
enum btree_id btree_id;
+ struct bpos node_start;
+ struct bpos node_end;
+ enum btree_node_rewrite_reason node_needed_rewrite;
+ u16 node_written;
+ u16 node_sectors;
+ u16 node_remaining;
+
unsigned update_level_start;
unsigned update_level_end;
diff --git a/fs/bcachefs/chardev.c b/fs/bcachefs/chardev.c
index 2d38466eddfd..fde3c2380e28 100644
--- a/fs/bcachefs/chardev.c
+++ b/fs/bcachefs/chardev.c
@@ -399,7 +399,7 @@ static long bch2_ioctl_data(struct bch_fs *c,
return ret;
}
-static long bch2_ioctl_fs_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_fs_usage(struct bch_fs *c,
struct bch_ioctl_fs_usage __user *user_arg)
{
struct bch_ioctl_fs_usage arg = {};
@@ -469,7 +469,7 @@ err:
}
/* obsolete, didn't allow for new data types: */
-static long bch2_ioctl_dev_usage(struct bch_fs *c,
+static noinline_for_stack long bch2_ioctl_dev_usage(struct bch_fs *c,
struct bch_ioctl_dev_usage __user *user_arg)
{
struct bch_ioctl_dev_usage arg;
diff --git a/fs/bcachefs/disk_accounting.c b/fs/bcachefs/disk_accounting.c
index 3d59a57a5256..f7528cd69c73 100644
--- a/fs/bcachefs/disk_accounting.c
+++ b/fs/bcachefs/disk_accounting.c
@@ -618,7 +618,9 @@ int bch2_gc_accounting_done(struct bch_fs *c)
for (unsigned j = 0; j < nr; j++)
src_v[j] -= dst_v[j];
- if (fsck_err(trans, accounting_mismatch, "%s", buf.buf)) {
+ bch2_trans_unlock_long(trans);
+
+ if (fsck_err(c, accounting_mismatch, "%s", buf.buf)) {
percpu_up_write(&c->mark_lock);
ret = commit_do(trans, NULL, NULL, 0,
bch2_disk_accounting_mod(trans, &acc_k, src_v, nr, false));
diff --git a/fs/bcachefs/error.c b/fs/bcachefs/error.c
index 63951e293c47..a8ec6aae5738 100644
--- a/fs/bcachefs/error.c
+++ b/fs/bcachefs/error.c
@@ -69,7 +69,7 @@ static bool bch2_fs_trans_inconsistent(struct bch_fs *c, struct btree_trans *tra
if (trans)
bch2_trans_updates_to_text(&buf, trans);
bool ret = __bch2_inconsistent_error(c, &buf);
- bch2_print_str_nonblocking(c, KERN_ERR, buf.buf);
+ bch2_print_str(c, KERN_ERR, buf.buf);
printbuf_exit(&buf);
return ret;
@@ -620,6 +620,9 @@ print:
if (s)
s->ret = ret;
+
+ if (trans)
+ ret = bch2_trans_log_str(trans, bch2_sb_error_strs[err]) ?: ret;
err_unlock:
mutex_unlock(&c->fsck_error_msgs_lock);
err:
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 85d13f800165..3063a8ddc2df 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -2490,6 +2490,14 @@ static int bch2_fs_get_tree(struct fs_context *fc)
if (ret)
goto err_stop_fs;
+ /*
+ * We might be doing a RO mount because other options required it, or we
+ * have no alloc info and it's a small image with no room to regenerate
+ * it
+ */
+ if (c->opts.read_only)
+ fc->sb_flags |= SB_RDONLY;
+
sb = sget(fc->fs_type, NULL, bch2_set_super, fc->sb_flags|SB_NOSEC, c);
ret = PTR_ERR_OR_ZERO(sb);
if (ret)
diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index a77779afad01..04bbdcf58e40 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -343,6 +343,10 @@ static struct bch_read_bio *promote_alloc(struct btree_trans *trans,
*bounce = true;
*read_full = promote_full;
+
+ if (have_io_error(failed))
+ orig->self_healing = true;
+
return promote;
nopromote:
trace_io_read_nopromote(c, ret);
@@ -635,12 +639,15 @@ static void bch2_rbio_retry(struct work_struct *work)
prt_str(&buf, "(internal move) ");
prt_str(&buf, "data read error, ");
- if (!ret)
+ if (!ret) {
prt_str(&buf, "successful retry");
- else
+ if (rbio->self_healing)
+ prt_str(&buf, ", self healing");
+ } else
prt_str(&buf, bch2_err_str(ret));
prt_newline(&buf);
+
if (!bkey_deleted(&sk.k->k)) {
bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(sk.k));
prt_newline(&buf);
diff --git a/fs/bcachefs/io_read.h b/fs/bcachefs/io_read.h
index 45c959018919..9c5ddbf861b3 100644
--- a/fs/bcachefs/io_read.h
+++ b/fs/bcachefs/io_read.h
@@ -44,6 +44,7 @@ struct bch_read_bio {
have_ioref:1,
narrow_crcs:1,
saw_error:1,
+ self_healing:1,
context:2;
};
u16 _state;
diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 6d7b1d5f7697..27e68d470ad0 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -28,7 +28,7 @@
#include <linux/wait.h>
struct buckets_in_flight {
- struct rhashtable table;
+ struct rhashtable *table;
struct move_bucket *first;
struct move_bucket *last;
size_t nr;
@@ -98,7 +98,7 @@ out:
static void move_bucket_free(struct buckets_in_flight *list,
struct move_bucket *b)
{
- int ret = rhashtable_remove_fast(&list->table, &b->hash,
+ int ret = rhashtable_remove_fast(list->table, &b->hash,
bch_move_bucket_params);
BUG_ON(ret);
kfree(b);
@@ -133,7 +133,7 @@ static void move_buckets_wait(struct moving_context *ctxt,
static bool bucket_in_flight(struct buckets_in_flight *list,
struct move_bucket_key k)
{
- return rhashtable_lookup_fast(&list->table, &k, bch_move_bucket_params);
+ return rhashtable_lookup_fast(list->table, &k, bch_move_bucket_params);
}
static int bch2_copygc_get_buckets(struct moving_context *ctxt,
@@ -185,7 +185,7 @@ static int bch2_copygc_get_buckets(struct moving_context *ctxt,
goto err;
}
- ret2 = rhashtable_lookup_insert_fast(&buckets_in_flight->table, &b_i->hash,
+ ret2 = rhashtable_lookup_insert_fast(buckets_in_flight->table, &b_i->hash,
bch_move_bucket_params);
BUG_ON(ret2);
@@ -350,10 +350,13 @@ static int bch2_copygc_thread(void *arg)
struct buckets_in_flight buckets = {};
u64 last, wait;
- int ret = rhashtable_init(&buckets.table, &bch_move_bucket_params);
+ buckets.table = kzalloc(sizeof(*buckets.table), GFP_KERNEL);
+ int ret = !buckets.table
+ ? -ENOMEM
+ : rhashtable_init(buckets.table, &bch_move_bucket_params);
bch_err_msg(c, ret, "allocating copygc buckets in flight");
if (ret)
- return ret;
+ goto err;
set_freezable();
@@ -421,11 +424,12 @@ static int bch2_copygc_thread(void *arg)
}
move_buckets_wait(&ctxt, &buckets, true);
- rhashtable_destroy(&buckets.table);
+ rhashtable_destroy(buckets.table);
bch2_moving_ctxt_exit(&ctxt);
bch2_move_stats_exit(&move_stats, c);
-
- return 0;
+err:
+ kfree(buckets.table);
+ return ret;
}
void bch2_copygc_stop(struct bch_fs *c)
diff --git a/fs/bcachefs/namei.c b/fs/bcachefs/namei.c
index 24120037c031..779c22eb3979 100644
--- a/fs/bcachefs/namei.c
+++ b/fs/bcachefs/namei.c
@@ -175,6 +175,16 @@ int bch2_create_trans(struct btree_trans *trans,
new_inode->bi_dir_offset = dir_offset;
}
+ if (S_ISDIR(mode)) {
+ ret = bch2_maybe_propagate_has_case_insensitive(trans,
+ (subvol_inum) {
+ new_inode->bi_subvol ?: dir.subvol,
+ new_inode->bi_inum },
+ new_inode);
+ if (ret)
+ goto err;
+ }
+
if (S_ISDIR(mode) &&
!new_inode->bi_subvol)
new_inode->bi_depth = dir_u->bi_depth + 1;
diff --git a/fs/bcachefs/rcu_pending.c b/fs/bcachefs/rcu_pending.c
index bef2aa1b8bcd..b1438be9d690 100644
--- a/fs/bcachefs/rcu_pending.c
+++ b/fs/bcachefs/rcu_pending.c
@@ -182,11 +182,6 @@ static inline void kfree_bulk(size_t nr, void ** p)
while (nr--)
kfree(*p);
}
-
-#define local_irq_save(flags) \
-do { \
- flags = 0; \
-} while (0)
#endif
static noinline void __process_finished_items(struct rcu_pending *pending,
@@ -429,9 +424,15 @@ __rcu_pending_enqueue(struct rcu_pending *pending, struct rcu_head *head,
BUG_ON((ptr != NULL) != (pending->process == RCU_PENDING_KVFREE_FN));
- local_irq_save(flags);
- p = this_cpu_ptr(pending->p);
- spin_lock(&p->lock);
+ /* We could technically be scheduled before taking the lock and end up
+ * using a different cpu's rcu_pending_pcpu: that's ok, it needs a lock
+ * anyways
+ *
+ * And we have to do it this way to avoid breaking PREEMPT_RT, which
+ * redefines how spinlocks work:
+ */
+ p = raw_cpu_ptr(pending->p);
+ spin_lock_irqsave(&p->lock, flags);
rcu_gp_poll_state_t seq = __get_state_synchronize_rcu(pending->srcu);
restart:
if (may_sleep &&
@@ -520,9 +521,8 @@ check_expired:
goto free_node;
}
- local_irq_save(flags);
- p = this_cpu_ptr(pending->p);
- spin_lock(&p->lock);
+ p = raw_cpu_ptr(pending->p);
+ spin_lock_irqsave(&p->lock, flags);
goto restart;
}
diff --git a/fs/bcachefs/recovery.c b/fs/bcachefs/recovery.c
index 1e68e61f08e8..0b21fa6ff062 100644
--- a/fs/bcachefs/recovery.c
+++ b/fs/bcachefs/recovery.c
@@ -99,9 +99,11 @@ int bch2_btree_lost_data(struct bch_fs *c,
goto out;
case BTREE_ID_snapshots:
ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_reconstruct_snapshots, 0) ?: ret;
+ ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
goto out;
default:
+ ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_check_topology, 0) ?: ret;
ret = __bch2_run_explicit_recovery_pass(c, msg, BCH_RECOVERY_PASS_scan_for_btree_nodes, 0) ?: ret;
goto out;
}
@@ -271,13 +273,24 @@ static int bch2_journal_replay_key(struct btree_trans *trans,
goto out;
struct btree_path *path = btree_iter_path(trans, &iter);
- if (unlikely(!btree_path_node(path, k->level))) {
+ if (unlikely(!btree_path_node(path, k->level) &&
+ !k->allocated)) {
+ struct bch_fs *c = trans->c;
+
+ if (!(c->recovery.passes_complete & (BIT_ULL(BCH_RECOVERY_PASS_scan_for_btree_nodes)|
+ BIT_ULL(BCH_RECOVERY_PASS_check_topology)))) {
+ bch_err(c, "have key in journal replay for btree depth that does not exist, confused");
+ ret = -EINVAL;
+ }
+#if 0
bch2_trans_iter_exit(trans, &iter);
bch2_trans_node_iter_init(trans, &iter, k->btree_id, k->k->k.p,
BTREE_MAX_DEPTH, 0, iter_flags);
ret = bch2_btree_iter_traverse(trans, &iter) ?:
bch2_btree_increase_depth(trans, iter.path, 0) ?:
-BCH_ERR_transaction_restart_nested;
+#endif
+ k->overwritten = true;
goto out;
}
@@ -739,9 +752,11 @@ int bch2_fs_recovery(struct bch_fs *c)
? min(c->opts.recovery_pass_last, BCH_RECOVERY_PASS_snapshots_read)
: BCH_RECOVERY_PASS_snapshots_read;
c->opts.nochanges = true;
- c->opts.read_only = true;
}
+ if (c->opts.nochanges)
+ c->opts.read_only = true;
+
mutex_lock(&c->sb_lock);
struct bch_sb_field_ext *ext = bch2_sb_field_get(c->disk_sb.sb, ext);
bool write_sb = false;
@@ -1093,9 +1108,6 @@ use_clean:
out:
bch2_flush_fsck_errs(c);
- if (!IS_ERR(clean))
- kfree(clean);
-
if (!ret &&
test_bit(BCH_FS_need_delete_dead_snapshots, &c->flags) &&
!c->opts.nochanges) {
@@ -1104,6 +1116,9 @@ out:
}
bch_err_fn(c, ret);
+final_out:
+ if (!IS_ERR(clean))
+ kfree(clean);
return ret;
err:
fsck_err:
@@ -1117,7 +1132,7 @@ fsck_err:
bch2_print_str(c, KERN_ERR, buf.buf);
printbuf_exit(&buf);
}
- return ret;
+ goto final_out;
}
int bch2_fs_initialize(struct bch_fs *c)
diff --git a/fs/bcachefs/recovery_passes.c b/fs/bcachefs/recovery_passes.c
index 605588e33fb3..35ac0d64d73a 100644
--- a/fs/bcachefs/recovery_passes.c
+++ b/fs/bcachefs/recovery_passes.c
@@ -294,8 +294,13 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
enum bch_run_recovery_pass_flags *flags)
{
struct bch_fs_recovery *r = &c->recovery;
- bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
- bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
+
+ /*
+ * Never run scan_for_btree_nodes persistently: check_topology will run
+ * it if required
+ */
+ if (pass == BCH_RECOVERY_PASS_scan_for_btree_nodes)
+ *flags |= RUN_RECOVERY_PASS_nopersistent;
if ((*flags & RUN_RECOVERY_PASS_ratelimit) &&
!bch2_recovery_pass_want_ratelimit(c, pass))
@@ -310,6 +315,8 @@ static bool recovery_pass_needs_set(struct bch_fs *c,
* Otherwise, we run run_explicit_recovery_pass when we find damage, so
* it should run again even if it's already run:
*/
+ bool in_recovery = test_bit(BCH_FS_in_recovery, &c->flags);
+ bool persistent = !in_recovery || !(*flags & RUN_RECOVERY_PASS_nopersistent);
if (persistent
? !(c->sb.recovery_passes_required & BIT_ULL(pass))
@@ -334,6 +341,7 @@ int __bch2_run_explicit_recovery_pass(struct bch_fs *c,
struct bch_fs_recovery *r = &c->recovery;
int ret = 0;
+
lockdep_assert_held(&c->sb_lock);
bch2_printbuf_make_room(out, 1024);
@@ -446,7 +454,7 @@ int bch2_require_recovery_pass(struct bch_fs *c,
int bch2_run_print_explicit_recovery_pass(struct bch_fs *c, enum bch_recovery_pass pass)
{
- enum bch_run_recovery_pass_flags flags = RUN_RECOVERY_PASS_nopersistent;
+ enum bch_run_recovery_pass_flags flags = 0;
if (!recovery_pass_needs_set(c, pass, &flags))
return 0;
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index b61f88450a6d..1506d05e0665 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -253,6 +253,7 @@ DOWNGRADE_TABLE()
static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
{
+ unsigned dst_offset = table->nr;
struct bch_sb_field_downgrade_entry *dst = (void *) &darray_top(*table);
unsigned bytes = sizeof(*dst) + sizeof(dst->errors[0]) * le16_to_cpu(dst->nr_errors);
int ret = 0;
@@ -268,6 +269,9 @@ static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
if (ret)
return ret;
+ dst = (void *) &table->data[dst_offset];
+ dst->nr_errors = cpu_to_le16(nr_errors + 1);
+
/* open coded __set_bit_le64, as dst is packed and
* dst->recovery_passes is misaligned */
unsigned b = BCH_RECOVERY_PASS_STABLE_check_allocations;
@@ -278,7 +282,6 @@ static int downgrade_table_extra(struct bch_fs *c, darray_char *table)
break;
}
- dst->nr_errors = cpu_to_le16(nr_errors);
return ret;
}
diff --git a/fs/bcachefs/sb-errors_format.h b/fs/bcachefs/sb-errors_format.h
index 6fdbf265e4c0..d06e73884871 100644
--- a/fs/bcachefs/sb-errors_format.h
+++ b/fs/bcachefs/sb-errors_format.h
@@ -134,7 +134,7 @@ enum bch_fsck_flags {
x(bucket_gens_to_invalid_buckets, 121, FSCK_AUTOFIX) \
x(bucket_gens_nonzero_for_invalid_buckets, 122, FSCK_AUTOFIX) \
x(need_discard_freespace_key_to_invalid_dev_bucket, 123, 0) \
- x(need_discard_freespace_key_bad, 124, 0) \
+ x(need_discard_freespace_key_bad, 124, FSCK_AUTOFIX) \
x(discarding_bucket_not_in_need_discard_btree, 291, 0) \
x(backpointer_bucket_offset_wrong, 125, 0) \
x(backpointer_level_bad, 294, 0) \
@@ -165,7 +165,7 @@ enum bch_fsck_flags {
x(ptr_to_missing_replicas_entry, 149, FSCK_AUTOFIX) \
x(ptr_to_missing_stripe, 150, 0) \
x(ptr_to_incorrect_stripe, 151, 0) \
- x(ptr_gen_newer_than_bucket_gen, 152, 0) \
+ x(ptr_gen_newer_than_bucket_gen, 152, FSCK_AUTOFIX) \
x(ptr_too_stale, 153, 0) \
x(stale_dirty_ptr, 154, FSCK_AUTOFIX) \
x(ptr_bucket_data_type_mismatch, 155, 0) \
@@ -236,7 +236,7 @@ enum bch_fsck_flags {
x(inode_multiple_links_but_nlink_0, 207, FSCK_AUTOFIX) \
x(inode_wrong_backpointer, 208, FSCK_AUTOFIX) \
x(inode_wrong_nlink, 209, FSCK_AUTOFIX) \
- x(inode_has_child_snapshots_wrong, 287, 0) \
+ x(inode_has_child_snapshots_wrong, 287, FSCK_AUTOFIX) \
x(inode_unreachable, 210, FSCK_AUTOFIX) \
x(inode_journal_seq_in_future, 299, FSCK_AUTOFIX) \
x(inode_i_sectors_underflow, 312, FSCK_AUTOFIX) \
@@ -279,8 +279,8 @@ enum bch_fsck_flags {
x(root_dir_missing, 239, 0) \
x(root_inode_not_dir, 240, 0) \
x(dir_loop, 241, 0) \
- x(hash_table_key_duplicate, 242, 0) \
- x(hash_table_key_wrong_offset, 243, 0) \
+ x(hash_table_key_duplicate, 242, FSCK_AUTOFIX) \
+ x(hash_table_key_wrong_offset, 243, FSCK_AUTOFIX) \
x(unlinked_inode_not_on_deleted_list, 244, FSCK_AUTOFIX) \
x(reflink_p_front_pad_bad, 245, 0) \
x(journal_entry_dup_same_device, 246, 0) \
diff --git a/fs/bcachefs/sb-members.c b/fs/bcachefs/sb-members.c
index 363eb0c6eb7c..6245e342a8a8 100644
--- a/fs/bcachefs/sb-members.c
+++ b/fs/bcachefs/sb-members.c
@@ -325,9 +325,17 @@ static void bch2_sb_members_v1_to_text(struct printbuf *out, struct bch_sb *sb,
{
struct bch_sb_field_members_v1 *mi = field_to_type(f, members_v1);
struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
- unsigned i;
- for (i = 0; i < sb->nr_devices; i++)
+ if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+ prt_printf(out, "field ends before start of entries");
+ return;
+ }
+
+ unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / sizeof(mi->_members[0]);
+ if (nr != sb->nr_devices)
+ prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+ for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
member_to_text(out, members_v1_get(mi, i), gi, sb, i);
}
@@ -341,9 +349,27 @@ static void bch2_sb_members_v2_to_text(struct printbuf *out, struct bch_sb *sb,
{
struct bch_sb_field_members_v2 *mi = field_to_type(f, members_v2);
struct bch_sb_field_disk_groups *gi = bch2_sb_field_get(sb, disk_groups);
- unsigned i;
- for (i = 0; i < sb->nr_devices; i++)
+ if (vstruct_end(&mi->field) <= (void *) &mi->_members[0]) {
+ prt_printf(out, "field ends before start of entries");
+ return;
+ }
+
+ if (!le16_to_cpu(mi->member_bytes)) {
+ prt_printf(out, "member_bytes 0");
+ return;
+ }
+
+ unsigned nr = (vstruct_end(&mi->field) - (void *) &mi->_members[0]) / le16_to_cpu(mi->member_bytes);
+ if (nr != sb->nr_devices)
+ prt_printf(out, "nr_devices mismatch: have %i entries, should be %u", nr, sb->nr_devices);
+
+ /*
+ * We call to_text() on superblock sections that haven't passed
+ * validate, so we can't trust sb->nr_devices.
+ */
+
+ for (unsigned i = 0; i < min(sb->nr_devices, nr); i++)
member_to_text(out, members_v2_get(mi, i), gi, sb, i);
}
diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 397a69da5a75..a5b97c9c5163 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -104,7 +104,7 @@ const char * const bch2_dev_write_refs[] = {
#undef x
static void __bch2_print_str(struct bch_fs *c, const char *prefix,
- const char *str, bool nonblocking)
+ const char *str)
{
#ifdef __KERNEL__
struct stdio_redirect *stdio = bch2_fs_stdio_redirect(c);
@@ -114,17 +114,12 @@ static void __bch2_print_str(struct bch_fs *c, const char *prefix,
return;
}
#endif
- bch2_print_string_as_lines(KERN_ERR, str, nonblocking);
+ bch2_print_string_as_lines(KERN_ERR, str);
}
void bch2_print_str(struct bch_fs *c, const char *prefix, const char *str)
{
- __bch2_print_str(c, prefix, str, false);
-}
-
-void bch2_print_str_nonblocking(struct bch_fs *c, const char *prefix, const char *str)
-{
- __bch2_print_str(c, prefix, str, true);
+ __bch2_print_str(c, prefix, str);
}
__printf(2, 0)
@@ -1072,12 +1067,13 @@ noinline_for_stack
static void print_mount_opts(struct bch_fs *c)
{
enum bch_opt_id i;
- struct printbuf p = PRINTBUF;
- bool first = true;
+ CLASS(printbuf, p)();
+ bch2_log_msg_start(c, &p);
prt_str(&p, "starting version ");
bch2_version_to_text(&p, c->sb.version);
+ bool first = true;
for (i = 0; i < bch2_opts_nr; i++) {
const struct bch_option *opt = &bch2_opt_table[i];
u64 v = bch2_opt_get_by_id(&c->opts, i);
@@ -1094,17 +1090,24 @@ static void print_mount_opts(struct bch_fs *c)
}
if (c->sb.version_incompat_allowed != c->sb.version) {
- prt_printf(&p, "\n allowing incompatible features above ");
+ prt_printf(&p, "\nallowing incompatible features above ");
bch2_version_to_text(&p, c->sb.version_incompat_allowed);
}
if (c->opts.verbose) {
- prt_printf(&p, "\n features: ");
+ prt_printf(&p, "\nfeatures: ");
prt_bitflags(&p, bch2_sb_features, c->sb.features);
}
- bch_info(c, "%s", p.buf);
- printbuf_exit(&p);
+ if (c->sb.multi_device) {
+ prt_printf(&p, "\nwith devices");
+ for_each_online_member(c, ca, BCH_DEV_READ_REF_bch2_online_devs) {
+ prt_char(&p, ' ');
+ prt_str(&p, ca->name);
+ }
+ }
+
+ bch2_print_str(c, KERN_INFO, p.buf);
}
static bool bch2_fs_may_start(struct bch_fs *c)
@@ -1995,6 +1998,22 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
goto err_late;
}
+ /*
+ * We just changed the superblock UUID, invalidate cache and send a
+ * uevent to update /dev/disk/by-uuid
+ */
+ invalidate_bdev(ca->disk_sb.bdev);
+
+ char uuid_str[37];
+ snprintf(uuid_str, sizeof(uuid_str), "UUID=%pUb", &c->sb.uuid);
+
+ char *envp[] = {
+ "CHANGE=uuid",
+ uuid_str,
+ NULL,
+ };
+ kobject_uevent_env(&ca->disk_sb.bdev->bd_device.kobj, KOBJ_CHANGE, envp);
+
up_write(&c->state_lock);
out:
printbuf_exit(&label);
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index dc3817f545fa..df9a6071fe18 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -262,8 +262,7 @@ static bool string_is_spaces(const char *str)
return true;
}
-void bch2_print_string_as_lines(const char *prefix, const char *lines,
- bool nonblocking)
+void bch2_print_string_as_lines(const char *prefix, const char *lines)
{
bool locked = false;
const char *p;
@@ -273,12 +272,7 @@ void bch2_print_string_as_lines(const char *prefix, const char *lines,
return;
}
- if (!nonblocking) {
- console_lock();
- locked = true;
- } else {
- locked = console_trylock();
- }
+ locked = console_trylock();
while (*lines) {
p = strchrnul(lines, '\n');
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index 0a4b1d433621..6488f098d140 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -214,7 +214,7 @@ u64 bch2_read_flag_list(const char *, const char * const[]);
void bch2_prt_u64_base2_nbits(struct printbuf *, u64, unsigned);
void bch2_prt_u64_base2(struct printbuf *, u64);
-void bch2_print_string_as_lines(const char *, const char *, bool);
+void bch2_print_string_as_lines(const char *, const char *);
typedef DARRAY(unsigned long) bch_stacktrace;
int bch2_save_backtrace(bch_stacktrace *stack, struct task_struct *, unsigned, gfp_t);
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index c7cc24a5dd5e..8c597fa60523 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1377,7 +1377,10 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
void btrfs_assert_delayed_root_empty(struct btrfs_fs_info *fs_info)
{
- WARN_ON(btrfs_first_delayed_node(fs_info->delayed_root));
+ struct btrfs_delayed_node *node = btrfs_first_delayed_node(fs_info->delayed_root);
+
+ if (WARN_ON(node))
+ refcount_dec(&node->refs);
}
static bool could_end_wait(struct btrfs_delayed_root *delayed_root, int seq)
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 1beb9458f622..0d6ad7512f21 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1835,6 +1835,8 @@ void btrfs_put_root(struct btrfs_root *root)
if (refcount_dec_and_test(&root->refs)) {
if (WARN_ON(!xa_empty(&root->inodes)))
xa_destroy(&root->inodes);
+ if (WARN_ON(!xa_empty(&root->delayed_nodes)))
+ xa_destroy(&root->delayed_nodes);
WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
if (root->anon_dev)
free_anon_bdev(root->anon_dev);
@@ -2156,8 +2158,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
found = true;
root = read_tree_root_path(tree_root, path, &key);
if (IS_ERR(root)) {
- if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
- ret = PTR_ERR(root);
+ ret = PTR_ERR(root);
break;
}
set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
@@ -4310,8 +4311,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
*
* So wait for all ongoing ordered extents to complete and then run
* delayed iputs. This works because once we reach this point no one
- * can either create new ordered extents nor create delayed iputs
- * through some other means.
+ * can create new ordered extents, but delayed iputs can still be added
+ * by a reclaim worker (see comments further below).
*
* Also note that btrfs_wait_ordered_roots() is not safe here, because
* it waits for BTRFS_ORDERED_COMPLETE to be set on an ordered extent,
@@ -4322,15 +4323,29 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
btrfs_flush_workqueue(fs_info->endio_write_workers);
/* Ordered extents for free space inodes. */
btrfs_flush_workqueue(fs_info->endio_freespace_worker);
+ /*
+ * Run delayed iputs in case an async reclaim worker is waiting for them
+ * to be run as mentioned above.
+ */
btrfs_run_delayed_iputs(fs_info);
- /* There should be no more workload to generate new delayed iputs. */
- set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
cancel_work_sync(&fs_info->async_reclaim_work);
cancel_work_sync(&fs_info->async_data_reclaim_work);
cancel_work_sync(&fs_info->preempt_reclaim_work);
cancel_work_sync(&fs_info->em_shrinker_work);
+ /*
+ * Run delayed iputs again because an async reclaim worker may have
+ * added new ones if it was flushing delalloc:
+ *
+ * shrink_delalloc() -> btrfs_start_delalloc_roots() ->
+ * start_delalloc_inodes() -> btrfs_add_delayed_iput()
+ */
+ btrfs_run_delayed_iputs(fs_info);
+
+ /* There should be no more workload to generate new delayed iputs. */
+ set_bit(BTRFS_FS_STATE_NO_DELAYED_IPUT, &fs_info->fs_state);
+
/* Cancel or finish ongoing discard work */
btrfs_discard_cleanup(fs_info);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 849199768664..1dc931c4937f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4312,7 +4312,6 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
spin_unlock(&eb->refs_lock);
continue;
}
- xa_unlock_irq(&fs_info->buffer_tree);
/*
* If tree ref isn't set then we know the ref on this eb is a
@@ -4329,6 +4328,7 @@ static int try_release_subpage_extent_buffer(struct folio *folio)
* check the folio private at the end. And
* release_extent_buffer() will release the refs_lock.
*/
+ xa_unlock_irq(&fs_info->buffer_tree);
release_extent_buffer(eb);
xa_lock_irq(&fs_info->buffer_tree);
}
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index 0c573d46639a..a3e2a2a81461 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1115,11 +1115,21 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
ret = btrfs_search_slot_for_read(extent_root, &key, path, 1, 0);
if (ret < 0)
goto out_locked;
- ASSERT(ret == 0);
+ /*
+ * If ret is 1 (no key found), it means this is an empty block group,
+ * without any extents allocated from it and there's no block group
+ * item (key BTRFS_BLOCK_GROUP_ITEM_KEY) located in the extent tree
+ * because we are using the block group tree feature, so block group
+ * items are stored in the block group tree. It also means there are no
+ * extents allocated for block groups with a start offset beyond this
+ * block group's end offset (this is the last, highest, block group).
+ */
+ if (!btrfs_fs_compat_ro(trans->fs_info, BLOCK_GROUP_TREE))
+ ASSERT(ret == 0);
start = block_group->start;
end = block_group->start + block_group->length;
- while (1) {
+ while (ret == 0) {
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
if (key.type == BTRFS_EXTENT_ITEM_KEY ||
@@ -1149,8 +1159,6 @@ static int populate_free_space_tree(struct btrfs_trans_handle *trans,
ret = btrfs_next_item(extent_root, path);
if (ret < 0)
goto out_locked;
- if (ret)
- break;
}
if (start < end) {
ret = __add_to_free_space_tree(trans, block_group, path2,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index c0c778243bf1..26d6ed170a19 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4250,9 +4250,9 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index);
if (ret) {
- btrfs_info(fs_info,
- "failed to delete reference to %.*s, inode %llu parent %llu",
- name->len, name->name, ino, dir_ino);
+ btrfs_crit(fs_info,
+ "failed to delete reference to %.*s, root %llu inode %llu parent %llu",
+ name->len, name->name, btrfs_root_id(root), ino, dir_ino);
btrfs_abort_transaction(trans, ret);
goto err;
}
@@ -8059,6 +8059,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
int ret;
int ret2;
bool need_abort = false;
+ bool logs_pinned = false;
struct fscrypt_name old_fname, new_fname;
struct fscrypt_str *old_name, *new_name;
@@ -8182,6 +8183,31 @@ static int btrfs_rename_exchange(struct inode *old_dir,
inode_inc_iversion(new_inode);
simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID &&
+ new_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ /*
+ * If we are renaming in the same directory (and it's not for
+ * root entries) pin the log early to prevent any concurrent
+ * task from logging the directory after we removed the old
+ * entries and before we add the new entries, otherwise that
+ * task can sync a log without any entry for the inodes we are
+ * renaming and therefore replaying that log, if a power failure
+ * happens after syncing the log, would result in deleting the
+ * inodes.
+ *
+ * If the rename affects two different directories, we want to
+ * make sure the that there's no log commit that contains
+ * updates for only one of the directories but not for the
+ * other.
+ *
+ * If we are renaming an entry for a root, we don't care about
+ * log updates since we called btrfs_set_log_full_commit().
+ */
+ btrfs_pin_log_trans(root);
+ btrfs_pin_log_trans(dest);
+ logs_pinned = true;
+ }
+
if (old_dentry->d_parent != new_dentry->d_parent) {
btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
BTRFS_I(old_inode), true);
@@ -8253,30 +8279,23 @@ static int btrfs_rename_exchange(struct inode *old_dir,
BTRFS_I(new_inode)->dir_index = new_idx;
/*
- * Now pin the logs of the roots. We do it to ensure that no other task
- * can sync the logs while we are in progress with the rename, because
- * that could result in an inconsistency in case any of the inodes that
- * are part of this rename operation were logged before.
+ * Do the log updates for all inodes.
+ *
+ * If either entry is for a root we don't need to update the logs since
+ * we've called btrfs_set_log_full_commit() before.
*/
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
- btrfs_pin_log_trans(root);
- if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
- btrfs_pin_log_trans(dest);
-
- /* Do the log updates for all inodes. */
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+ if (logs_pinned) {
btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
old_rename_ctx.index, new_dentry->d_parent);
- if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
new_rename_ctx.index, old_dentry->d_parent);
+ }
- /* Now unpin the logs. */
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+out_fail:
+ if (logs_pinned) {
btrfs_end_log_trans(root);
- if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
btrfs_end_log_trans(dest);
-out_fail:
+ }
ret2 = btrfs_end_transaction(trans);
ret = ret ? ret : ret2;
out_notrans:
@@ -8326,6 +8345,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
int ret2;
u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
struct fscrypt_name old_fname, new_fname;
+ bool logs_pinned = false;
if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
@@ -8460,6 +8480,29 @@ static int btrfs_rename(struct mnt_idmap *idmap,
inode_inc_iversion(old_inode);
simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ /*
+ * If we are renaming in the same directory (and it's not a
+ * root entry) pin the log to prevent any concurrent task from
+ * logging the directory after we removed the old entry and
+ * before we add the new entry, otherwise that task can sync
+ * a log without any entry for the inode we are renaming and
+ * therefore replaying that log, if a power failure happens
+ * after syncing the log, would result in deleting the inode.
+ *
+ * If the rename affects two different directories, we want to
+ * make sure the that there's no log commit that contains
+ * updates for only one of the directories but not for the
+ * other.
+ *
+ * If we are renaming an entry for a root, we don't care about
+ * log updates since we called btrfs_set_log_full_commit().
+ */
+ btrfs_pin_log_trans(root);
+ btrfs_pin_log_trans(dest);
+ logs_pinned = true;
+ }
+
if (old_dentry->d_parent != new_dentry->d_parent)
btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
BTRFS_I(old_inode), true);
@@ -8524,7 +8567,7 @@ static int btrfs_rename(struct mnt_idmap *idmap,
if (old_inode->i_nlink == 1)
BTRFS_I(old_inode)->dir_index = index;
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
+ if (logs_pinned)
btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
rename_ctx.index, new_dentry->d_parent);
@@ -8540,6 +8583,10 @@ static int btrfs_rename(struct mnt_idmap *idmap,
}
}
out_fail:
+ if (logs_pinned) {
+ btrfs_end_log_trans(root);
+ btrfs_end_log_trans(dest);
+ }
ret2 = btrfs_end_transaction(trans);
ret = ret ? ret : ret2;
out_notrans:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 913acef3f0a9..4eda35bdba71 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3139,7 +3139,7 @@ static long btrfs_ioctl_scrub(struct file *file, void __user *arg)
return -EPERM;
if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
- btrfs_err(fs_info, "scrub is not supported on extent tree v2 yet");
+ btrfs_err(fs_info, "scrub: extent tree v2 not yet supported");
return -EINVAL;
}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index ce36fafc771e..7cd5e76a783c 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -557,7 +557,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
*/
for (i = 0; i < ipath->fspath->elem_cnt; ++i)
btrfs_warn_in_rcu(fs_info,
-"%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu, length %u, links %u (path: %s)",
+"scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu length %u links %u (path: %s)",
swarn->errstr, swarn->logical,
btrfs_dev_name(swarn->dev),
swarn->physical,
@@ -571,7 +571,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
err:
btrfs_warn_in_rcu(fs_info,
- "%s at logical %llu on dev %s, physical %llu, root %llu, inode %llu, offset %llu: path resolving failed with ret=%d",
+ "scrub: %s at logical %llu on dev %s, physical %llu root %llu inode %llu offset %llu: path resolving failed with ret=%d",
swarn->errstr, swarn->logical,
btrfs_dev_name(swarn->dev),
swarn->physical,
@@ -596,7 +596,7 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
/* Super block error, no need to search extent tree. */
if (is_super) {
- btrfs_warn_in_rcu(fs_info, "%s on device %s, physical %llu",
+ btrfs_warn_in_rcu(fs_info, "scrub: %s on device %s, physical %llu",
errstr, btrfs_dev_name(dev), physical);
return;
}
@@ -631,14 +631,14 @@ static void scrub_print_common_warning(const char *errstr, struct btrfs_device *
&ref_level);
if (ret < 0) {
btrfs_warn(fs_info,
- "failed to resolve tree backref for logical %llu: %d",
- swarn.logical, ret);
+ "scrub: failed to resolve tree backref for logical %llu: %d",
+ swarn.logical, ret);
break;
}
if (ret > 0)
break;
btrfs_warn_in_rcu(fs_info,
-"%s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu",
+"scrub: %s at logical %llu on dev %s, physical %llu: metadata %s (level %d) in tree %llu",
errstr, swarn.logical, btrfs_dev_name(dev),
swarn.physical, (ref_level ? "node" : "leaf"),
ref_level, ref_root);
@@ -718,7 +718,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
- "tree block %llu mirror %u has bad bytenr, has %llu want %llu",
+ "scrub: tree block %llu mirror %u has bad bytenr, has %llu want %llu",
logical, stripe->mirror_num,
btrfs_stack_header_bytenr(header), logical);
return;
@@ -728,7 +728,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
- "tree block %llu mirror %u has bad fsid, has %pU want %pU",
+ "scrub: tree block %llu mirror %u has bad fsid, has %pU want %pU",
logical, stripe->mirror_num,
header->fsid, fs_info->fs_devices->fsid);
return;
@@ -738,7 +738,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
- "tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU",
+ "scrub: tree block %llu mirror %u has bad chunk tree uuid, has %pU want %pU",
logical, stripe->mirror_num,
header->chunk_tree_uuid, fs_info->chunk_tree_uuid);
return;
@@ -760,7 +760,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
scrub_bitmap_set_meta_error(stripe, sector_nr, sectors_per_tree);
scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
- "tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT,
+"scrub: tree block %llu mirror %u has bad csum, has " CSUM_FMT " want " CSUM_FMT,
logical, stripe->mirror_num,
CSUM_FMT_VALUE(fs_info->csum_size, on_disk_csum),
CSUM_FMT_VALUE(fs_info->csum_size, calculated_csum));
@@ -771,7 +771,7 @@ static void scrub_verify_one_metadata(struct scrub_stripe *stripe, int sector_nr
scrub_bitmap_set_meta_gen_error(stripe, sector_nr, sectors_per_tree);
scrub_bitmap_set_error(stripe, sector_nr, sectors_per_tree);
btrfs_warn_rl(fs_info,
- "tree block %llu mirror %u has bad generation, has %llu want %llu",
+ "scrub: tree block %llu mirror %u has bad generation, has %llu want %llu",
logical, stripe->mirror_num,
btrfs_stack_header_generation(header),
stripe->sectors[sector_nr].generation);
@@ -814,7 +814,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
*/
if (unlikely(sector_nr + sectors_per_tree > stripe->nr_sectors)) {
btrfs_warn_rl(fs_info,
- "tree block at %llu crosses stripe boundary %llu",
+ "scrub: tree block at %llu crosses stripe boundary %llu",
stripe->logical +
(sector_nr << fs_info->sectorsize_bits),
stripe->logical);
@@ -1046,12 +1046,12 @@ skip:
if (repaired) {
if (dev) {
btrfs_err_rl_in_rcu(fs_info,
- "fixed up error at logical %llu on dev %s physical %llu",
+ "scrub: fixed up error at logical %llu on dev %s physical %llu",
stripe->logical, btrfs_dev_name(dev),
physical);
} else {
btrfs_err_rl_in_rcu(fs_info,
- "fixed up error at logical %llu on mirror %u",
+ "scrub: fixed up error at logical %llu on mirror %u",
stripe->logical, stripe->mirror_num);
}
continue;
@@ -1060,12 +1060,12 @@ skip:
/* The remaining are all for unrepaired. */
if (dev) {
btrfs_err_rl_in_rcu(fs_info,
- "unable to fixup (regular) error at logical %llu on dev %s physical %llu",
+"scrub: unable to fixup (regular) error at logical %llu on dev %s physical %llu",
stripe->logical, btrfs_dev_name(dev),
physical);
} else {
btrfs_err_rl_in_rcu(fs_info,
- "unable to fixup (regular) error at logical %llu on mirror %u",
+ "scrub: unable to fixup (regular) error at logical %llu on mirror %u",
stripe->logical, stripe->mirror_num);
}
@@ -1593,8 +1593,7 @@ static int sync_write_pointer_for_zoned(struct scrub_ctx *sctx, u64 logical,
physical,
sctx->write_pointer);
if (ret)
- btrfs_err(fs_info,
- "zoned: failed to recover write pointer");
+ btrfs_err(fs_info, "scrub: zoned: failed to recover write pointer");
}
mutex_unlock(&sctx->wr_lock);
btrfs_dev_clear_zone_empty(sctx->wr_tgtdev, physical);
@@ -1658,7 +1657,7 @@ static int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
int ret;
if (unlikely(!extent_root || !csum_root)) {
- btrfs_err(fs_info, "no valid extent or csum root for scrub");
+ btrfs_err(fs_info, "scrub: no valid extent or csum root found");
return -EUCLEAN;
}
memset(stripe->sectors, 0, sizeof(struct scrub_sector_verification) *
@@ -1907,7 +1906,7 @@ static bool stripe_has_metadata_error(struct scrub_stripe *stripe)
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
btrfs_err(fs_info,
- "stripe %llu has unrepaired metadata sector at %llu",
+ "scrub: stripe %llu has unrepaired metadata sector at logical %llu",
stripe->logical,
stripe->logical + (i << fs_info->sectorsize_bits));
return true;
@@ -2167,7 +2166,7 @@ static int scrub_raid56_parity_stripe(struct scrub_ctx *sctx,
bitmap_and(&error, &error, &has_extent, stripe->nr_sectors);
if (!bitmap_empty(&error, stripe->nr_sectors)) {
btrfs_err(fs_info,
-"unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl",
+"scrub: unrepaired sectors detected, full stripe %llu data stripe %u errors %*pbl",
full_stripe_start, i, stripe->nr_sectors,
&error);
ret = -EIO;
@@ -2789,14 +2788,14 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
ro_set = 0;
} else if (ret == -ETXTBSY) {
btrfs_warn(fs_info,
- "skipping scrub of block group %llu due to active swapfile",
+ "scrub: skipping scrub of block group %llu due to active swapfile",
cache->start);
scrub_pause_off(fs_info);
ret = 0;
goto skip_unfreeze;
} else {
- btrfs_warn(fs_info,
- "failed setting block group ro: %d", ret);
+ btrfs_warn(fs_info, "scrub: failed setting block group ro: %d",
+ ret);
btrfs_unfreeze_block_group(cache);
btrfs_put_block_group(cache);
scrub_pause_off(fs_info);
@@ -2892,13 +2891,13 @@ static int scrub_one_super(struct scrub_ctx *sctx, struct btrfs_device *dev,
ret = btrfs_check_super_csum(fs_info, sb);
if (ret != 0) {
btrfs_err_rl(fs_info,
- "super block at physical %llu devid %llu has bad csum",
+ "scrub: super block at physical %llu devid %llu has bad csum",
physical, dev->devid);
return -EIO;
}
if (btrfs_super_generation(sb) != generation) {
btrfs_err_rl(fs_info,
-"super block at physical %llu devid %llu has bad generation %llu expect %llu",
+"scrub: super block at physical %llu devid %llu has bad generation %llu expect %llu",
physical, dev->devid,
btrfs_super_generation(sb), generation);
return -EUCLEAN;
@@ -3059,7 +3058,7 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
!test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
mutex_unlock(&fs_info->fs_devices->device_list_mutex);
btrfs_err_in_rcu(fs_info,
- "scrub on devid %llu: filesystem on %s is not writable",
+ "scrub: devid %llu: filesystem on %s is not writable",
devid, btrfs_dev_name(dev));
ret = -EROFS;
goto out;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 97e933113b82..858b609e292c 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -668,15 +668,15 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
extent_end = ALIGN(start + size,
fs_info->sectorsize);
} else {
- ret = 0;
- goto out;
+ btrfs_err(fs_info,
+ "unexpected extent type=%d root=%llu inode=%llu offset=%llu",
+ found_type, btrfs_root_id(root), key->objectid, key->offset);
+ return -EUCLEAN;
}
inode = read_one_inode(root, key->objectid);
- if (!inode) {
- ret = -EIO;
- goto out;
- }
+ if (!inode)
+ return -EIO;
/*
* first check to see if we already have this extent in the
@@ -961,7 +961,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
ret = unlink_inode_for_log_replay(trans, dir, inode, &name);
out:
kfree(name.name);
- iput(&inode->vfs_inode);
+ if (inode)
+ iput(&inode->vfs_inode);
return ret;
}
@@ -1176,8 +1177,8 @@ again:
ret = unlink_inode_for_log_replay(trans,
victim_parent,
inode, &victim_name);
+ iput(&victim_parent->vfs_inode);
}
- iput(&victim_parent->vfs_inode);
kfree(victim_name.name);
if (ret)
return ret;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 89835071cfea..f475b4b7c457 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3282,6 +3282,12 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
device->bytes_used - dev_extent_len);
atomic64_add(dev_extent_len, &fs_info->free_chunk_space);
btrfs_clear_space_info_full(fs_info);
+
+ if (list_empty(&device->post_commit_list)) {
+ list_add_tail(&device->post_commit_list,
+ &trans->transaction->dev_update_list);
+ }
+
mutex_unlock(&fs_info->chunk_mutex);
}
}
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index b5b0156d5b95..9430b34d3cbb 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -1403,7 +1403,8 @@ static int btrfs_load_block_group_single(struct btrfs_block_group *bg,
static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
struct btrfs_chunk_map *map,
struct zone_info *zone_info,
- unsigned long *active)
+ unsigned long *active,
+ u64 last_alloc)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
@@ -1426,6 +1427,13 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
zone_info[1].physical);
return -EIO;
}
+
+ if (zone_info[0].alloc_offset == WP_CONVENTIONAL)
+ zone_info[0].alloc_offset = last_alloc;
+
+ if (zone_info[1].alloc_offset == WP_CONVENTIONAL)
+ zone_info[1].alloc_offset = last_alloc;
+
if (zone_info[0].alloc_offset != zone_info[1].alloc_offset) {
btrfs_err(bg->fs_info,
"zoned: write pointer offset mismatch of zones in DUP profile");
@@ -1446,7 +1454,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
struct btrfs_chunk_map *map,
struct zone_info *zone_info,
- unsigned long *active)
+ unsigned long *active,
+ u64 last_alloc)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
int i;
@@ -1461,10 +1470,12 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
for (i = 0; i < map->num_stripes; i++) {
- if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
- zone_info[i].alloc_offset == WP_CONVENTIONAL)
+ if (zone_info[i].alloc_offset == WP_MISSING_DEV)
continue;
+ if (zone_info[i].alloc_offset == WP_CONVENTIONAL)
+ zone_info[i].alloc_offset = last_alloc;
+
if ((zone_info[0].alloc_offset != zone_info[i].alloc_offset) &&
!btrfs_test_opt(fs_info, DEGRADED)) {
btrfs_err(fs_info,
@@ -1494,7 +1505,8 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
struct btrfs_chunk_map *map,
struct zone_info *zone_info,
- unsigned long *active)
+ unsigned long *active,
+ u64 last_alloc)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
@@ -1505,10 +1517,29 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
}
for (int i = 0; i < map->num_stripes; i++) {
- if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
- zone_info[i].alloc_offset == WP_CONVENTIONAL)
+ if (zone_info[i].alloc_offset == WP_MISSING_DEV)
continue;
+ if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
+ u64 stripe_nr, full_stripe_nr;
+ u64 stripe_offset;
+ int stripe_index;
+
+ stripe_nr = div64_u64(last_alloc, map->stripe_size);
+ stripe_offset = stripe_nr * map->stripe_size;
+ full_stripe_nr = div_u64(stripe_nr, map->num_stripes);
+ div_u64_rem(stripe_nr, map->num_stripes, &stripe_index);
+
+ zone_info[i].alloc_offset =
+ full_stripe_nr * map->stripe_size;
+
+ if (stripe_index > i)
+ zone_info[i].alloc_offset += map->stripe_size;
+ else if (stripe_index == i)
+ zone_info[i].alloc_offset +=
+ (last_alloc - stripe_offset);
+ }
+
if (test_bit(0, active) != test_bit(i, active)) {
if (!btrfs_zone_activate(bg))
return -EIO;
@@ -1526,7 +1557,8 @@ static int btrfs_load_block_group_raid0(struct btrfs_block_group *bg,
static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
struct btrfs_chunk_map *map,
struct zone_info *zone_info,
- unsigned long *active)
+ unsigned long *active,
+ u64 last_alloc)
{
struct btrfs_fs_info *fs_info = bg->fs_info;
@@ -1537,8 +1569,7 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
}
for (int i = 0; i < map->num_stripes; i++) {
- if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
- zone_info[i].alloc_offset == WP_CONVENTIONAL)
+ if (zone_info[i].alloc_offset == WP_MISSING_DEV)
continue;
if (test_bit(0, active) != test_bit(i, active)) {
@@ -1549,6 +1580,29 @@ static int btrfs_load_block_group_raid10(struct btrfs_block_group *bg,
set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
}
+ if (zone_info[i].alloc_offset == WP_CONVENTIONAL) {
+ u64 stripe_nr, full_stripe_nr;
+ u64 stripe_offset;
+ int stripe_index;
+
+ stripe_nr = div64_u64(last_alloc, map->stripe_size);
+ stripe_offset = stripe_nr * map->stripe_size;
+ full_stripe_nr = div_u64(stripe_nr,
+ map->num_stripes / map->sub_stripes);
+ div_u64_rem(stripe_nr,
+ (map->num_stripes / map->sub_stripes),
+ &stripe_index);
+
+ zone_info[i].alloc_offset =
+ full_stripe_nr * map->stripe_size;
+
+ if (stripe_index > (i / map->sub_stripes))
+ zone_info[i].alloc_offset += map->stripe_size;
+ else if (stripe_index == (i / map->sub_stripes))
+ zone_info[i].alloc_offset +=
+ (last_alloc - stripe_offset);
+ }
+
if ((i % map->sub_stripes) == 0) {
bg->zone_capacity += zone_info[i].capacity;
bg->alloc_offset += zone_info[i].alloc_offset;
@@ -1637,18 +1691,22 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
ret = btrfs_load_block_group_single(cache, &zone_info[0], active);
break;
case BTRFS_BLOCK_GROUP_DUP:
- ret = btrfs_load_block_group_dup(cache, map, zone_info, active);
+ ret = btrfs_load_block_group_dup(cache, map, zone_info, active,
+ last_alloc);
break;
case BTRFS_BLOCK_GROUP_RAID1:
case BTRFS_BLOCK_GROUP_RAID1C3:
case BTRFS_BLOCK_GROUP_RAID1C4:
- ret = btrfs_load_block_group_raid1(cache, map, zone_info, active);
+ ret = btrfs_load_block_group_raid1(cache, map, zone_info,
+ active, last_alloc);
break;
case BTRFS_BLOCK_GROUP_RAID0:
- ret = btrfs_load_block_group_raid0(cache, map, zone_info, active);
+ ret = btrfs_load_block_group_raid0(cache, map, zone_info,
+ active, last_alloc);
break;
case BTRFS_BLOCK_GROUP_RAID10:
- ret = btrfs_load_block_group_raid10(cache, map, zone_info, active);
+ ret = btrfs_load_block_group_raid10(cache, map, zone_info,
+ active, last_alloc);
break;
case BTRFS_BLOCK_GROUP_RAID5:
case BTRFS_BLOCK_GROUP_RAID6:
diff --git a/fs/erofs/fileio.c b/fs/erofs/fileio.c
index 7d81f504bff0..df5cc63f2c01 100644
--- a/fs/erofs/fileio.c
+++ b/fs/erofs/fileio.c
@@ -47,6 +47,7 @@ static void erofs_fileio_ki_complete(struct kiocb *iocb, long ret)
static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
{
+ const struct cred *old_cred;
struct iov_iter iter;
int ret;
@@ -60,7 +61,9 @@ static void erofs_fileio_rq_submit(struct erofs_fileio_rq *rq)
rq->iocb.ki_flags = IOCB_DIRECT;
iov_iter_bvec(&iter, ITER_DEST, rq->bvecs, rq->bio.bi_vcnt,
rq->bio.bi_iter.bi_size);
+ old_cred = override_creds(rq->iocb.ki_filp->f_cred);
ret = vfs_iocb_iter_read(rq->iocb.ki_filp, &rq->iocb, &iter);
+ revert_creds(old_cred);
if (ret != -EIOCBQUEUED)
erofs_fileio_ki_complete(&rq->iocb, ret);
}
diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c
index 14ea47f954f5..0bebc6e3a4d7 100644
--- a/fs/erofs/zmap.c
+++ b/fs/erofs/zmap.c
@@ -597,6 +597,10 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
if (la > map->m_la) {
r = mid;
+ if (la > lend) {
+ DBG_BUGON(1);
+ return -EFSCORRUPTED;
+ }
lend = la;
} else {
l = mid + 1;
@@ -635,12 +639,6 @@ static int z_erofs_map_blocks_ext(struct inode *inode,
}
}
map->m_llen = lend - map->m_la;
- if (!last && map->m_llen < sb->s_blocksize) {
- erofs_err(sb, "extent too small %llu @ offset %llu of nid %llu",
- map->m_llen, map->m_la, vi->nid);
- DBG_BUGON(1);
- return -EFSCORRUPTED;
- }
return 0;
}
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6bd3de64f2a8..696131e655ed 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -35,6 +35,17 @@
#include <trace/events/f2fs.h>
#include <uapi/linux/f2fs.h>
+static void f2fs_zero_post_eof_page(struct inode *inode, loff_t new_size)
+{
+ loff_t old_size = i_size_read(inode);
+
+ if (old_size >= new_size)
+ return;
+
+ /* zero or drop pages only in range of [old_size, new_size] */
+ truncate_pagecache(inode, old_size);
+}
+
static vm_fault_t f2fs_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
@@ -103,8 +114,13 @@ static vm_fault_t f2fs_vm_page_mkwrite(struct vm_fault *vmf)
f2fs_bug_on(sbi, f2fs_has_inline_data(inode));
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, (folio->index + 1) << PAGE_SHIFT);
+ filemap_invalidate_unlock(inode->i_mapping);
+
file_update_time(vmf->vma->vm_file);
filemap_invalidate_lock_shared(inode->i_mapping);
+
folio_lock(folio);
if (unlikely(folio->mapping != inode->i_mapping ||
folio_pos(folio) > i_size_read(inode) ||
@@ -1109,6 +1125,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
f2fs_down_write(&fi->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
+ if (attr->ia_size > old_size)
+ f2fs_zero_post_eof_page(inode, attr->ia_size);
truncate_setsize(inode, attr->ia_size);
if (attr->ia_size <= old_size)
@@ -1227,6 +1245,10 @@ static int f2fs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
if (ret)
return ret;
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(inode->i_mapping);
+
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
@@ -1510,6 +1532,8 @@ static int f2fs_do_collapse(struct inode *inode, loff_t offset, loff_t len)
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+
f2fs_lock_op(sbi);
f2fs_drop_extent_tree(inode);
truncate_pagecache(inode, offset);
@@ -1631,6 +1655,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
if (ret)
return ret;
+ filemap_invalidate_lock(mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(mapping);
+
pg_start = ((unsigned long long) offset) >> PAGE_SHIFT;
pg_end = ((unsigned long long) offset + len) >> PAGE_SHIFT;
@@ -1762,6 +1790,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
/* avoid gc operation during block exchange */
f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
filemap_invalidate_lock(mapping);
+
+ f2fs_zero_post_eof_page(inode, offset + len);
truncate_pagecache(inode, offset);
while (!ret && idx > pg_start) {
@@ -1819,6 +1849,10 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset,
if (err)
return err;
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, offset + len);
+ filemap_invalidate_unlock(inode->i_mapping);
+
f2fs_balance_fs(sbi, true);
pg_start = ((unsigned long long)offset) >> PAGE_SHIFT;
@@ -4860,6 +4894,10 @@ static ssize_t f2fs_write_checks(struct kiocb *iocb, struct iov_iter *from)
err = file_modified(file);
if (err)
return err;
+
+ filemap_invalidate_lock(inode->i_mapping);
+ f2fs_zero_post_eof_page(inode, iocb->ki_pos + iov_iter_count(from));
+ filemap_invalidate_unlock(inode->i_mapping);
return count;
}
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 1cb4cba7f961..bfe104db284e 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -2078,7 +2078,6 @@ write_node:
if (!__write_node_folio(folio, false, &submitted,
wbc, do_balance, io_type, NULL)) {
- folio_unlock(folio);
folio_batch_release(&fbatch);
ret = -EIO;
goto out;
diff --git a/fs/file.c b/fs/file.c
index 3a3146664cf3..b6db031545e6 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1198,8 +1198,12 @@ bool file_seek_cur_needs_f_lock(struct file *file)
if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared)
return false;
- VFS_WARN_ON_ONCE((file_count(file) > 1) &&
- !mutex_is_locked(&file->f_pos_lock));
+ /*
+ * Note that we are not guaranteed to be called after fdget_pos() on
+ * this file obj, in which case the caller is expected to provide the
+ * appropriate locking.
+ */
+
return true;
}
diff --git a/fs/namei.c b/fs/namei.c
index 4bb889fc980b..f761cafaeaad 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2917,7 +2917,8 @@ static int lookup_one_common(struct mnt_idmap *idmap,
* @base: base directory to lookup from
*
* Look up a dentry by name in the dcache, returning NULL if it does not
- * currently exist. The function does not try to create a dentry.
+ * currently exist. The function does not try to create a dentry and if one
+ * is found it doesn't try to revalidate it.
*
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code. It does no permission checking.
@@ -2933,7 +2934,7 @@ struct dentry *try_lookup_noperm(struct qstr *name, struct dentry *base)
if (err)
return ERR_PTR(err);
- return lookup_dcache(name, base, 0);
+ return d_lookup(base, name);
}
EXPORT_SYMBOL(try_lookup_noperm);
@@ -3057,14 +3058,22 @@ EXPORT_SYMBOL(lookup_one_positive_unlocked);
* Note that this routine is purely a helper for filesystem usage and should
* not be called by generic code. It does no permission checking.
*
- * Unlike lookup_noperm, it should be called without the parent
+ * Unlike lookup_noperm(), it should be called without the parent
* i_rwsem held, and will take the i_rwsem itself if necessary.
+ *
+ * Unlike try_lookup_noperm() it *does* revalidate the dentry if it already
+ * existed.
*/
struct dentry *lookup_noperm_unlocked(struct qstr *name, struct dentry *base)
{
struct dentry *ret;
+ int err;
- ret = try_lookup_noperm(name, base);
+ err = lookup_noperm_common(name, base);
+ if (err)
+ return ERR_PTR(err);
+
+ ret = lookup_dcache(name, base, 0);
if (!ret)
ret = lookup_slow(name, base, 0);
return ret;
diff --git a/fs/namespace.c b/fs/namespace.c
index e13d9ab4f564..54c59e091919 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2310,21 +2310,62 @@ out:
return dst_mnt;
}
-/* Caller should check returned pointer for errors */
+static inline bool extend_array(struct path **res, struct path **to_free,
+ unsigned n, unsigned *count, unsigned new_count)
+{
+ struct path *p;
-struct vfsmount *collect_mounts(const struct path *path)
+ if (likely(n < *count))
+ return true;
+ p = kmalloc_array(new_count, sizeof(struct path), GFP_KERNEL);
+ if (p && *count)
+ memcpy(p, *res, *count * sizeof(struct path));
+ *count = new_count;
+ kfree(*to_free);
+ *to_free = *res = p;
+ return p;
+}
+
+struct path *collect_paths(const struct path *path,
+ struct path *prealloc, unsigned count)
{
- struct mount *tree;
- namespace_lock();
- if (!check_mnt(real_mount(path->mnt)))
- tree = ERR_PTR(-EINVAL);
- else
- tree = copy_tree(real_mount(path->mnt), path->dentry,
- CL_COPY_ALL | CL_PRIVATE);
- namespace_unlock();
- if (IS_ERR(tree))
- return ERR_CAST(tree);
- return &tree->mnt;
+ struct mount *root = real_mount(path->mnt);
+ struct mount *child;
+ struct path *res = prealloc, *to_free = NULL;
+ unsigned n = 0;
+
+ guard(rwsem_read)(&namespace_sem);
+
+ if (!check_mnt(root))
+ return ERR_PTR(-EINVAL);
+ if (!extend_array(&res, &to_free, 0, &count, 32))
+ return ERR_PTR(-ENOMEM);
+ res[n++] = *path;
+ list_for_each_entry(child, &root->mnt_mounts, mnt_child) {
+ if (!is_subdir(child->mnt_mountpoint, path->dentry))
+ continue;
+ for (struct mount *m = child; m; m = next_mnt(m, child)) {
+ if (!extend_array(&res, &to_free, n, &count, 2 * count))
+ return ERR_PTR(-ENOMEM);
+ res[n].mnt = &m->mnt;
+ res[n].dentry = m->mnt.mnt_root;
+ n++;
+ }
+ }
+ if (!extend_array(&res, &to_free, n, &count, count + 1))
+ return ERR_PTR(-ENOMEM);
+ memset(res + n, 0, (count - n) * sizeof(struct path));
+ for (struct path *p = res; p->mnt; p++)
+ path_get(p);
+ return res;
+}
+
+void drop_collected_paths(struct path *paths, struct path *prealloc)
+{
+ for (struct path *p = paths; p->mnt; p++)
+ path_put(p);
+ if (paths != prealloc)
+ kfree(paths);
}
static void free_mnt_ns(struct mnt_namespace *);
@@ -2401,15 +2442,6 @@ void dissolve_on_fput(struct vfsmount *mnt)
free_mnt_ns(ns);
}
-void drop_collected_mounts(struct vfsmount *mnt)
-{
- namespace_lock();
- lock_mount_hash();
- umount_tree(real_mount(mnt), 0);
- unlock_mount_hash();
- namespace_unlock();
-}
-
static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
{
struct mount *child;
@@ -2511,21 +2543,6 @@ struct vfsmount *clone_private_mount(const struct path *path)
}
EXPORT_SYMBOL_GPL(clone_private_mount);
-int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
- struct vfsmount *root)
-{
- struct mount *mnt;
- int res = f(root, arg);
- if (res)
- return res;
- list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
- res = f(&mnt->mnt, arg);
- if (res)
- return res;
- }
- return 0;
-}
-
static void lock_mnt_tree(struct mount *mnt)
{
struct mount *p;
@@ -2751,14 +2768,14 @@ static int attach_recursive_mnt(struct mount *source_mnt,
hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
struct mount *q;
hlist_del_init(&child->mnt_hash);
- q = __lookup_mnt(&child->mnt_parent->mnt,
- child->mnt_mountpoint);
- if (q)
- mnt_change_mountpoint(child, smp, q);
/* Notice when we are propagating across user namespaces */
if (child->mnt_parent->mnt_ns->user_ns != user_ns)
lock_mnt_tree(child);
child->mnt.mnt_flags &= ~MNT_LOCKED;
+ q = __lookup_mnt(&child->mnt_parent->mnt,
+ child->mnt_mountpoint);
+ if (q)
+ mnt_change_mountpoint(child, smp, q);
commit_tree(child);
}
put_mountpoint(smp);
@@ -5290,16 +5307,12 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
kattr.kflags |= MOUNT_KATTR_RECURSE;
ret = wants_mount_setattr(uattr, usize, &kattr);
- if (ret < 0)
- return ret;
-
- if (ret) {
+ if (ret > 0) {
ret = do_mount_setattr(&file->f_path, &kattr);
- if (ret)
- return ret;
-
finish_mount_kattr(&kattr);
}
+ if (ret)
+ return ret;
}
fd = get_unused_fd_flags(flags & O_CLOEXEC);
@@ -6262,7 +6275,11 @@ void put_mnt_ns(struct mnt_namespace *ns)
{
if (!refcount_dec_and_test(&ns->ns.count))
return;
- drop_collected_mounts(&ns->root->mnt);
+ namespace_lock();
+ lock_mount_hash();
+ umount_tree(ns->root, 0);
+ unlock_mount_hash();
+ namespace_unlock();
free_mnt_ns(ns);
}
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ccb00aa93be0..e00b2aea8da2 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1409,6 +1409,7 @@ void nfsd41_cb_referring_call(struct nfsd4_callback *cb,
out:
if (!rcl->__nr_referring_calls) {
cb->cb_nr_referring_call_list--;
+ list_del(&rcl->__list);
kfree(rcl);
}
}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 3f3e9f6c4250..6a42cc7a845a 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -1611,7 +1611,7 @@ out_unlock:
*/
int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
{
- int *nthreads, count = 0, nrpools, i, ret = -EOPNOTSUPP, rem;
+ int *nthreads, nrpools = 0, i, ret = -EOPNOTSUPP, rem;
struct net *net = genl_info_net(info);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
const struct nlattr *attr;
@@ -1623,12 +1623,11 @@ int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
/* count number of SERVER_THREADS values */
nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
if (nla_type(attr) == NFSD_A_SERVER_THREADS)
- count++;
+ nrpools++;
}
mutex_lock(&nfsd_mutex);
- nrpools = max(count, nfsd_nrpools(net));
nthreads = kcalloc(nrpools, sizeof(int), GFP_KERNEL);
if (!nthreads) {
ret = -ENOMEM;
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 0b8b28392eb7..2043f0369059 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -1393,7 +1393,7 @@ out:
bool ovl_lower_positive(struct dentry *dentry)
{
struct ovl_entry *poe = OVL_E(dentry->d_parent);
- struct qstr *name = &dentry->d_name;
+ const struct qstr *name = &dentry->d_name;
const struct cred *old_cred;
unsigned int i;
bool positive = false;
@@ -1416,9 +1416,15 @@ bool ovl_lower_positive(struct dentry *dentry)
struct dentry *this;
struct ovl_path *parentpath = &ovl_lowerstack(poe)[i];
+ /*
+ * We need to make a non-const copy of dentry->d_name,
+ * because lookup_one_positive_unlocked() will hash name
+ * with parentpath base, which is on another (lower fs).
+ */
this = lookup_one_positive_unlocked(
mnt_idmap(parentpath->layer->mnt),
- name, parentpath->dentry);
+ &QSTR_LEN(name->name, name->len),
+ parentpath->dentry);
if (IS_ERR(this)) {
switch (PTR_ERR(this)) {
case -ENOENT:
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8baaba0a3fe5..497323128e5f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -246,9 +246,11 @@ static inline struct dentry *ovl_do_mkdir(struct ovl_fs *ofs,
struct dentry *dentry,
umode_t mode)
{
- dentry = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
- pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(dentry));
- return dentry;
+ struct dentry *ret;
+
+ ret = vfs_mkdir(ovl_upper_mnt_idmap(ofs), dir, dentry, mode);
+ pr_debug("mkdir(%pd2, 0%o) = %i\n", dentry, mode, PTR_ERR_OR_ZERO(ret));
+ return ret;
}
static inline int ovl_do_mknod(struct ovl_fs *ofs,
diff --git a/fs/pidfs.c b/fs/pidfs.c
index c1f0a067be40..69919be1c9d8 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -366,7 +366,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
kinfo.pid = task_pid_vnr(task);
kinfo.mask |= PIDFD_INFO_PID;
- if (kinfo.pid == 0 || kinfo.tgid == 0 || (kinfo.ppid == 0 && kinfo.pid != 1))
+ if (kinfo.pid == 0 || kinfo.tgid == 0)
return -ESRCH;
copy_out:
diff --git a/fs/pnode.h b/fs/pnode.h
index 34b6247af01d..2d026fb98b18 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -28,8 +28,6 @@
#define CL_SHARED_TO_SLAVE 0x20
#define CL_COPY_MNT_NS_FILE 0x40
-#define CL_COPY_ALL (CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
-
static inline void set_mnt_shared(struct mount *mnt)
{
mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 6ed2dfd4dbbd..d98e0d2de09f 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
struct rmid_read rr = {0};
struct rdt_mon_domain *d;
struct rdtgroup *rdtgrp;
+ int domid, cpu, ret = 0;
struct rdt_resource *r;
+ struct cacheinfo *ci;
struct mon_data *md;
- int domid, ret = 0;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
@@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
* one that matches this cache id.
*/
list_for_each_entry(d, &r->mon_domains, hdr.list) {
- if (d->ci->id == domid) {
- rr.ci = d->ci;
+ if (d->ci_id == domid) {
+ rr.ci_id = d->ci_id;
+ cpu = cpumask_any(&d->hdr.cpu_mask);
+ ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!ci)
+ continue;
mon_event_read(&rr, r, NULL, rdtgrp,
- &d->ci->shared_cpu_map, evtid, false);
+ &ci->shared_cpu_map, evtid, false);
goto checkresult;
}
}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151..0a1eedba2b03 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
* domains in @r sharing L3 @ci.id
* @evtid: Which monitor event to read.
* @first: Initialize MBM counter when true.
- * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
* @err: Error encountered when reading counter.
* @val: Returned value of event counter. If @rgrp is a parent resource group,
* @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
struct rdt_mon_domain *d;
enum resctrl_event_id evtid;
bool first;
- struct cacheinfo *ci;
+ unsigned int ci_id;
int err;
u64 val;
void *arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index bde2801289d3..f5637855c3ac 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
{
int cpu = smp_processor_id();
struct rdt_mon_domain *d;
+ struct cacheinfo *ci;
struct mbm_state *m;
int err, ret;
u64 tval = 0;
@@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
}
/* Summing domains that share a cache, must be on a CPU for that cache. */
- if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+ ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!ci || ci->id != rr->ci_id)
return -EINVAL;
/*
@@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
*/
ret = -EINVAL;
list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
- if (d->ci->id != rr->ci->id)
+ if (d->ci_id != rr->ci_id)
continue;
err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 1beb124e25f6..77d08229d855 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
char name[32];
snc_mode = r->mon_scope == RESCTRL_L3_NODE;
- sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+ sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
if (snc_mode)
sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
return -EPERM;
list_for_each_entry(mevt, &r->evt_list, list) {
- domid = do_sum ? d->ci->id : d->hdr.id;
+ domid = do_sum ? d->ci_id : d->hdr.id;
priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
if (WARN_ON_ONCE(!priv))
return -EINVAL;
@@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
lockdep_assert_held(&rdtgroup_mutex);
snc_mode = r->mon_scope == RESCTRL_L3_NODE;
- sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+ sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
kn = kernfs_find_and_get(parent_kn, name);
if (kn) {
/*
diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c
index 5200a0f3cafc..368e870624da 100644
--- a/fs/smb/client/cached_dir.c
+++ b/fs/smb/client/cached_dir.c
@@ -509,8 +509,17 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb)
spin_lock(&cfids->cfid_list_lock);
list_for_each_entry(cfid, &cfids->entries, entry) {
tmp_list = kmalloc(sizeof(*tmp_list), GFP_ATOMIC);
- if (tmp_list == NULL)
- break;
+ if (tmp_list == NULL) {
+ /*
+ * If the malloc() fails, we won't drop all
+ * dentries, and unmounting is likely to trigger
+ * a 'Dentry still in use' error.
+ */
+ cifs_tcon_dbg(VFS, "Out of memory while dropping dentries\n");
+ spin_unlock(&cfids->cfid_list_lock);
+ spin_unlock(&cifs_sb->tlink_tree_lock);
+ goto done;
+ }
spin_lock(&cfid->fid_lock);
tmp_list->dentry = cfid->dentry;
cfid->dentry = NULL;
@@ -522,6 +531,7 @@ void close_all_cached_dirs(struct cifs_sb_info *cifs_sb)
}
spin_unlock(&cifs_sb->tlink_tree_lock);
+done:
list_for_each_entry_safe(tmp_list, q, &entry, entry) {
list_del(&tmp_list->entry);
dput(tmp_list->dentry);
diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h
index 1dfe79d947a6..a28f7cae3caa 100644
--- a/fs/smb/client/cached_dir.h
+++ b/fs/smb/client/cached_dir.h
@@ -21,12 +21,12 @@ struct cached_dirent {
struct cached_dirents {
bool is_valid:1;
bool is_failed:1;
- struct dir_context *ctx; /*
- * Only used to make sure we only take entries
- * from a single context. Never dereferenced.
- */
+ struct file *file; /*
+ * Used to associate the cache with a single
+ * open file instance.
+ */
struct mutex de_mutex;
- int pos; /* Expected ctx->pos */
+ loff_t pos; /* Expected ctx->pos */
struct list_head entries;
};
diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
index c0196be0e65f..3fdf75737d43 100644
--- a/fs/smb/client/cifs_debug.c
+++ b/fs/smb/client/cifs_debug.c
@@ -1105,7 +1105,7 @@ static ssize_t cifs_security_flags_proc_write(struct file *file,
if ((count < 1) || (count > 11))
return -EINVAL;
- memset(flags_string, 0, 12);
+ memset(flags_string, 0, sizeof(flags_string));
if (copy_from_user(flags_string, buffer, count))
return -EFAULT;
diff --git a/fs/smb/client/cifs_ioctl.h b/fs/smb/client/cifs_ioctl.h
index 26327442e383..b51ce64fcccf 100644
--- a/fs/smb/client/cifs_ioctl.h
+++ b/fs/smb/client/cifs_ioctl.h
@@ -61,7 +61,7 @@ struct smb_query_info {
struct smb3_key_debug_info {
__u64 Suid;
__u16 cipher_type;
- __u8 auth_key[16]; /* SMB2_NTLMV2_SESSKEY_SIZE */
+ __u8 auth_key[SMB2_NTLMV2_SESSKEY_SIZE];
__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
} __packed;
diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index 28bc33496623..c48869c29e15 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -3718,9 +3718,15 @@ int cifs_mount_get_tcon(struct cifs_mount_ctx *mnt_ctx)
goto out;
}
- /* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
- if (tcon->posix_extensions)
+ /*
+ * if new SMB3.11 POSIX extensions are supported, do not change anything in the
+ * path (i.e., do not remap / and \ and do not map any special characters)
+ */
+ if (tcon->posix_extensions) {
cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
+ cifs_sb->mnt_cifs_flags &= ~(CIFS_MOUNT_MAP_SFM_CHR |
+ CIFS_MOUNT_MAP_SPECIAL_CHR);
+ }
#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
/* tell server which Unix caps we support */
@@ -4193,6 +4199,7 @@ retry:
return 0;
}
+ server->lstrp = jiffies;
server->tcpStatus = CifsInNegotiate;
spin_unlock(&server->srv_lock);
diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
index d2df10b8e6fd..e9212da32f01 100644
--- a/fs/smb/client/file.c
+++ b/fs/smb/client/file.c
@@ -52,6 +52,7 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
struct netfs_io_stream *stream = &req->rreq.io_streams[subreq->stream_nr];
struct TCP_Server_Info *server;
struct cifsFileInfo *open_file = req->cfile;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(wdata->rreq->inode->i_sb);
size_t wsize = req->rreq.wsize;
int rc;
@@ -63,6 +64,10 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
server = cifs_pick_channel(tlink_tcon(open_file->tlink)->ses);
wdata->server = server;
+ if (cifs_sb->ctx->wsize == 0)
+ cifs_negotiate_wsize(server, cifs_sb->ctx,
+ tlink_tcon(req->cfile->tlink));
+
retry:
if (open_file->invalidHandle) {
rc = cifs_reopen_file(open_file, false);
@@ -160,10 +165,9 @@ static int cifs_prepare_read(struct netfs_io_subrequest *subreq)
server = cifs_pick_channel(tlink_tcon(req->cfile->tlink)->ses);
rdata->server = server;
- if (cifs_sb->ctx->rsize == 0) {
+ if (cifs_sb->ctx->rsize == 0)
cifs_negotiate_rsize(server, cifs_sb->ctx,
tlink_tcon(req->cfile->tlink));
- }
rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
&size, &rdata->credits);
@@ -999,15 +1003,18 @@ int cifs_open(struct inode *inode, struct file *file)
rc = cifs_get_readable_path(tcon, full_path, &cfile);
}
if (rc == 0) {
- if (file->f_flags == cfile->f_flags) {
+ unsigned int oflags = file->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+ unsigned int cflags = cfile->f_flags & ~(O_CREAT|O_EXCL|O_TRUNC);
+
+ if (cifs_convert_flags(oflags, 0) == cifs_convert_flags(cflags, 0) &&
+ (oflags & (O_SYNC|O_DIRECT)) == (cflags & (O_SYNC|O_DIRECT))) {
file->private_data = cfile;
spin_lock(&CIFS_I(inode)->deferred_lock);
cifs_del_deferred_close(cfile);
spin_unlock(&CIFS_I(inode)->deferred_lock);
goto use_cache;
- } else {
- _cifsFileInfo_put(cfile, true, false);
}
+ _cifsFileInfo_put(cfile, true, false);
} else {
/* hard link on the defeered close file */
rc = cifs_get_hardlink_path(tcon, inode, file);
diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c
index 56439da4f119..0a9935ce05a5 100644
--- a/fs/smb/client/ioctl.c
+++ b/fs/smb/client/ioctl.c
@@ -506,7 +506,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
le16_to_cpu(tcon->ses->server->cipher_type);
pkey_inf.Suid = tcon->ses->Suid;
memcpy(pkey_inf.auth_key, tcon->ses->auth_key.response,
- 16 /* SMB2_NTLMV2_SESSKEY_SIZE */);
+ SMB2_NTLMV2_SESSKEY_SIZE);
memcpy(pkey_inf.smb3decryptionkey,
tcon->ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
memcpy(pkey_inf.smb3encryptionkey,
diff --git a/fs/smb/client/readdir.c b/fs/smb/client/readdir.c
index f9f11cbf89be..ba0193cf9033 100644
--- a/fs/smb/client/readdir.c
+++ b/fs/smb/client/readdir.c
@@ -851,9 +851,9 @@ static bool emit_cached_dirents(struct cached_dirents *cde,
}
static void update_cached_dirents_count(struct cached_dirents *cde,
- struct dir_context *ctx)
+ struct file *file)
{
- if (cde->ctx != ctx)
+ if (cde->file != file)
return;
if (cde->is_valid || cde->is_failed)
return;
@@ -862,9 +862,9 @@ static void update_cached_dirents_count(struct cached_dirents *cde,
}
static void finished_cached_dirents_count(struct cached_dirents *cde,
- struct dir_context *ctx)
+ struct dir_context *ctx, struct file *file)
{
- if (cde->ctx != ctx)
+ if (cde->file != file)
return;
if (cde->is_valid || cde->is_failed)
return;
@@ -877,11 +877,12 @@ static void finished_cached_dirents_count(struct cached_dirents *cde,
static void add_cached_dirent(struct cached_dirents *cde,
struct dir_context *ctx,
const char *name, int namelen,
- struct cifs_fattr *fattr)
+ struct cifs_fattr *fattr,
+ struct file *file)
{
struct cached_dirent *de;
- if (cde->ctx != ctx)
+ if (cde->file != file)
return;
if (cde->is_valid || cde->is_failed)
return;
@@ -911,7 +912,8 @@ static void add_cached_dirent(struct cached_dirents *cde,
static bool cifs_dir_emit(struct dir_context *ctx,
const char *name, int namelen,
struct cifs_fattr *fattr,
- struct cached_fid *cfid)
+ struct cached_fid *cfid,
+ struct file *file)
{
bool rc;
ino_t ino = cifs_uniqueid_to_ino_t(fattr->cf_uniqueid);
@@ -923,7 +925,7 @@ static bool cifs_dir_emit(struct dir_context *ctx,
if (cfid) {
mutex_lock(&cfid->dirents.de_mutex);
add_cached_dirent(&cfid->dirents, ctx, name, namelen,
- fattr);
+ fattr, file);
mutex_unlock(&cfid->dirents.de_mutex);
}
@@ -1023,7 +1025,7 @@ static int cifs_filldir(char *find_entry, struct file *file,
cifs_prime_dcache(file_dentry(file), &name, &fattr);
return !cifs_dir_emit(ctx, name.name, name.len,
- &fattr, cfid);
+ &fattr, cfid, file);
}
@@ -1074,8 +1076,8 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
* we need to initialize scanning and storing the
* directory content.
*/
- if (ctx->pos == 0 && cfid->dirents.ctx == NULL) {
- cfid->dirents.ctx = ctx;
+ if (ctx->pos == 0 && cfid->dirents.file == NULL) {
+ cfid->dirents.file = file;
cfid->dirents.pos = 2;
}
/*
@@ -1143,7 +1145,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
} else {
if (cfid) {
mutex_lock(&cfid->dirents.de_mutex);
- finished_cached_dirents_count(&cfid->dirents, ctx);
+ finished_cached_dirents_count(&cfid->dirents, ctx, file);
mutex_unlock(&cfid->dirents.de_mutex);
}
cifs_dbg(FYI, "Could not find entry\n");
@@ -1184,7 +1186,7 @@ int cifs_readdir(struct file *file, struct dir_context *ctx)
ctx->pos++;
if (cfid) {
mutex_lock(&cfid->dirents.de_mutex);
- update_cached_dirents_count(&cfid->dirents, ctx);
+ update_cached_dirents_count(&cfid->dirents, file);
mutex_unlock(&cfid->dirents.de_mutex);
}
diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
index bb25e77c5540..511611206dab 100644
--- a/fs/smb/client/reparse.c
+++ b/fs/smb/client/reparse.c
@@ -1172,7 +1172,6 @@ out:
if (!have_xattr_dev && (tag == IO_REPARSE_TAG_LX_CHR || tag == IO_REPARSE_TAG_LX_BLK))
return false;
- fattr->cf_dtype = S_DT(fattr->cf_mode);
return true;
}
diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c
index ec0db32c7d98..330bc3d25bad 100644
--- a/fs/smb/client/sess.c
+++ b/fs/smb/client/sess.c
@@ -498,8 +498,7 @@ cifs_ses_add_channel(struct cifs_ses *ses,
ctx->domainauto = ses->domainAuto;
ctx->domainname = ses->domainName;
- /* no hostname for extra channels */
- ctx->server_hostname = "";
+ ctx->server_hostname = ses->server->hostname;
ctx->username = ses->user_name;
ctx->password = ses->password;
diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
index 5ae847919da5..cbc85bca006f 100644
--- a/fs/smb/client/smbdirect.c
+++ b/fs/smb/client/smbdirect.c
@@ -2589,13 +2589,14 @@ static ssize_t smb_extract_folioq_to_rdma(struct iov_iter *iter,
size_t fsize = folioq_folio_size(folioq, slot);
if (offset < fsize) {
- size_t part = umin(maxsize - ret, fsize - offset);
+ size_t part = umin(maxsize, fsize - offset);
if (!smb_set_sge(rdma, folio_page(folio, 0), offset, part))
return -EIO;
offset += part;
ret += part;
+ maxsize -= part;
}
if (offset >= fsize) {
@@ -2610,7 +2611,7 @@ static ssize_t smb_extract_folioq_to_rdma(struct iov_iter *iter,
slot = 0;
}
}
- } while (rdma->nr_sge < rdma->max_sge || maxsize > 0);
+ } while (rdma->nr_sge < rdma->max_sge && maxsize > 0);
iter->folioq = folioq;
iter->folioq_slot = slot;
diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index 83764c230e9d..3f04a2977ba8 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -40,7 +40,7 @@ void ksmbd_conn_free(struct ksmbd_conn *conn)
kvfree(conn->request_buf);
kfree(conn->preauth_info);
if (atomic_dec_and_test(&conn->refcnt)) {
- ksmbd_free_transport(conn->transport);
+ conn->transport->ops->free_transport(conn->transport);
kfree(conn);
}
}
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index 6efed923bd68..dd3e0e3f7bf0 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -133,6 +133,7 @@ struct ksmbd_transport_ops {
void *buf, unsigned int len,
struct smb2_buffer_desc_v1 *desc,
unsigned int desc_len);
+ void (*free_transport)(struct ksmbd_transport *kt);
};
struct ksmbd_transport {
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 1a308171b599..fafa86273f12 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -1607,17 +1607,18 @@ static int krb5_authenticate(struct ksmbd_work *work,
out_len = work->response_sz -
(le16_to_cpu(rsp->SecurityBufferOffset) + 4);
- /* Check previous session */
- prev_sess_id = le64_to_cpu(req->PreviousSessionId);
- if (prev_sess_id && prev_sess_id != sess->id)
- destroy_previous_session(conn, sess->user, prev_sess_id);
-
retval = ksmbd_krb5_authenticate(sess, in_blob, in_len,
out_blob, &out_len);
if (retval) {
ksmbd_debug(SMB, "krb5 authentication failed\n");
return -EINVAL;
}
+
+ /* Check previous session */
+ prev_sess_id = le64_to_cpu(req->PreviousSessionId);
+ if (prev_sess_id && prev_sess_id != sess->id)
+ destroy_previous_session(conn, sess->user, prev_sess_id);
+
rsp->SecurityBufferLength = cpu_to_le16(out_len);
if ((conn->sign || server_conf.enforced_signing) ||
@@ -4871,8 +4872,13 @@ static int get_file_standard_info(struct smb2_query_info_rsp *rsp,
sinfo = (struct smb2_file_standard_info *)rsp->Buffer;
delete_pending = ksmbd_inode_pending_delete(fp);
- sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
- sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ if (ksmbd_stream_fd(fp) == false) {
+ sinfo->AllocationSize = cpu_to_le64(stat.blocks << 9);
+ sinfo->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ } else {
+ sinfo->AllocationSize = cpu_to_le64(fp->stream.size);
+ sinfo->EndOfFile = cpu_to_le64(fp->stream.size);
+ }
sinfo->NumberOfLinks = cpu_to_le32(get_nlink(&stat) - delete_pending);
sinfo->DeletePending = delete_pending;
sinfo->Directory = S_ISDIR(stat.mode) ? 1 : 0;
@@ -4935,9 +4941,14 @@ static int get_file_all_info(struct ksmbd_work *work,
file_info->ChangeTime = cpu_to_le64(time);
file_info->Attributes = fp->f_ci->m_fattr;
file_info->Pad1 = 0;
- file_info->AllocationSize =
- cpu_to_le64(stat.blocks << 9);
- file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ if (ksmbd_stream_fd(fp) == false) {
+ file_info->AllocationSize =
+ cpu_to_le64(stat.blocks << 9);
+ file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ } else {
+ file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+ file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+ }
file_info->NumberOfLinks =
cpu_to_le32(get_nlink(&stat) - delete_pending);
file_info->DeletePending = delete_pending;
@@ -4946,7 +4957,10 @@ static int get_file_all_info(struct ksmbd_work *work,
file_info->IndexNumber = cpu_to_le64(stat.ino);
file_info->EASize = 0;
file_info->AccessFlags = fp->daccess;
- file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+ if (ksmbd_stream_fd(fp) == false)
+ file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+ else
+ file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
file_info->Mode = fp->coption;
file_info->AlignmentRequirement = 0;
conv_len = smbConvertToUTF16((__le16 *)file_info->FileName, filename,
@@ -5134,8 +5148,13 @@ static int get_file_network_open_info(struct smb2_query_info_rsp *rsp,
time = ksmbd_UnixTimeToNT(stat.ctime);
file_info->ChangeTime = cpu_to_le64(time);
file_info->Attributes = fp->f_ci->m_fattr;
- file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
- file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ if (ksmbd_stream_fd(fp) == false) {
+ file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+ file_info->EndOfFile = S_ISDIR(stat.mode) ? 0 : cpu_to_le64(stat.size);
+ } else {
+ file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+ file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+ }
file_info->Reserved = cpu_to_le32(0);
rsp->OutputBufferLength =
cpu_to_le32(sizeof(struct smb2_file_ntwrk_info));
@@ -5158,7 +5177,11 @@ static void get_file_position_info(struct smb2_query_info_rsp *rsp,
struct smb2_file_pos_info *file_info;
file_info = (struct smb2_file_pos_info *)rsp->Buffer;
- file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+ if (ksmbd_stream_fd(fp) == false)
+ file_info->CurrentByteOffset = cpu_to_le64(fp->filp->f_pos);
+ else
+ file_info->CurrentByteOffset = cpu_to_le64(fp->stream.pos);
+
rsp->OutputBufferLength =
cpu_to_le32(sizeof(struct smb2_file_pos_info));
}
@@ -5247,8 +5270,13 @@ static int find_file_posix_info(struct smb2_query_info_rsp *rsp,
file_info->ChangeTime = cpu_to_le64(time);
file_info->DosAttributes = fp->f_ci->m_fattr;
file_info->Inode = cpu_to_le64(stat.ino);
- file_info->EndOfFile = cpu_to_le64(stat.size);
- file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+ if (ksmbd_stream_fd(fp) == false) {
+ file_info->EndOfFile = cpu_to_le64(stat.size);
+ file_info->AllocationSize = cpu_to_le64(stat.blocks << 9);
+ } else {
+ file_info->EndOfFile = cpu_to_le64(fp->stream.size);
+ file_info->AllocationSize = cpu_to_le64(fp->stream.size);
+ }
file_info->HardLinks = cpu_to_le32(stat.nlink);
file_info->Mode = cpu_to_le32(stat.mode & 0777);
switch (stat.mode & S_IFMT) {
@@ -6190,6 +6218,9 @@ static int set_file_allocation_info(struct ksmbd_work *work,
if (!(fp->daccess & FILE_WRITE_DATA_LE))
return -EACCES;
+ if (ksmbd_stream_fd(fp) == true)
+ return 0;
+
rc = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS,
AT_STATX_SYNC_AS_STAT);
if (rc)
@@ -6248,7 +6279,8 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp,
* truncate of some filesystem like FAT32 fill zero data in
* truncated range.
*/
- if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) {
+ if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC &&
+ ksmbd_stream_fd(fp) == false) {
ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize);
rc = ksmbd_vfs_truncate(work, fp, newsize);
if (rc) {
@@ -6321,7 +6353,13 @@ static int set_file_position_info(struct ksmbd_file *fp,
return -EINVAL;
}
- fp->filp->f_pos = current_byte_offset;
+ if (ksmbd_stream_fd(fp) == false)
+ fp->filp->f_pos = current_byte_offset;
+ else {
+ if (current_byte_offset > XATTR_SIZE_MAX)
+ current_byte_offset = XATTR_SIZE_MAX;
+ fp->stream.pos = current_byte_offset;
+ }
return 0;
}
diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c
index 4998df04ab95..64a428a06ace 100644
--- a/fs/smb/server/transport_rdma.c
+++ b/fs/smb/server/transport_rdma.c
@@ -159,7 +159,8 @@ struct smb_direct_transport {
};
#define KSMBD_TRANS(t) ((struct ksmbd_transport *)&((t)->transport))
-
+#define SMBD_TRANS(t) ((struct smb_direct_transport *)container_of(t, \
+ struct smb_direct_transport, transport))
enum {
SMB_DIRECT_MSG_NEGOTIATE_REQ = 0,
SMB_DIRECT_MSG_DATA_TRANSFER
@@ -410,6 +411,11 @@ err:
return NULL;
}
+static void smb_direct_free_transport(struct ksmbd_transport *kt)
+{
+ kfree(SMBD_TRANS(kt));
+}
+
static void free_transport(struct smb_direct_transport *t)
{
struct smb_direct_recvmsg *recvmsg;
@@ -455,7 +461,6 @@ static void free_transport(struct smb_direct_transport *t)
smb_direct_destroy_pools(t);
ksmbd_conn_free(KSMBD_TRANS(t)->conn);
- kfree(t);
}
static struct smb_direct_sendmsg
@@ -2281,4 +2286,5 @@ static const struct ksmbd_transport_ops ksmbd_smb_direct_transport_ops = {
.read = smb_direct_read,
.rdma_read = smb_direct_rdma_read,
.rdma_write = smb_direct_rdma_write,
+ .free_transport = smb_direct_free_transport,
};
diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
index abedf510899a..4e9f98db9ff4 100644
--- a/fs/smb/server/transport_tcp.c
+++ b/fs/smb/server/transport_tcp.c
@@ -93,7 +93,7 @@ static struct tcp_transport *alloc_transport(struct socket *client_sk)
return t;
}
-void ksmbd_free_transport(struct ksmbd_transport *kt)
+static void ksmbd_tcp_free_transport(struct ksmbd_transport *kt)
{
struct tcp_transport *t = TCP_TRANS(kt);
@@ -656,4 +656,5 @@ static const struct ksmbd_transport_ops ksmbd_tcp_transport_ops = {
.read = ksmbd_tcp_read,
.writev = ksmbd_tcp_writev,
.disconnect = ksmbd_tcp_disconnect,
+ .free_transport = ksmbd_tcp_free_transport,
};
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index ba45e809555a..0f3aad12e495 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -293,6 +293,7 @@ static int ksmbd_vfs_stream_read(struct ksmbd_file *fp, char *buf, loff_t *pos,
if (v_len - *pos < count)
count = v_len - *pos;
+ fp->stream.pos = v_len;
memcpy(buf, &stream_buf[*pos], count);
@@ -456,8 +457,8 @@ static int ksmbd_vfs_stream_write(struct ksmbd_file *fp, char *buf, loff_t *pos,
true);
if (err < 0)
goto out;
-
- fp->filp->f_pos = *pos;
+ else
+ fp->stream.pos = size;
err = 0;
out:
kvfree(stream_buf);
diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h
index 5bbb179736c2..0708155b5caf 100644
--- a/fs/smb/server/vfs_cache.h
+++ b/fs/smb/server/vfs_cache.h
@@ -44,6 +44,7 @@ struct ksmbd_lock {
struct stream {
char *name;
ssize_t size;
+ loff_t pos;
};
struct ksmbd_inode {
diff --git a/fs/super.c b/fs/super.c
index 21799e213fd7..80418ca8e215 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -964,8 +964,10 @@ void iterate_supers_type(struct file_system_type *type,
spin_unlock(&sb_lock);
locked = super_lock_shared(sb);
- if (locked)
+ if (locked) {
f(sb, arg);
+ super_unlock_shared(sb);
+ }
spin_lock(&sb_lock);
if (p)
diff --git a/fs/xattr.c b/fs/xattr.c
index 8ec5b0204bfd..600ae97969cf 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -1479,6 +1479,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
buffer += err;
}
remaining_size -= err;
+ err = 0;
read_lock(&xattrs->lock);
for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) {
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index 6f6b9de12cd3..db294d452e8c 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -202,6 +202,8 @@ struct shash_desc {
#define HASH_REQUEST_CLONE(name, gfp) \
hash_request_clone(name, sizeof(__##name##_req), gfp)
+#define CRYPTO_HASH_STATESIZE(coresize, blocksize) (coresize + blocksize + 1)
+
/**
* struct shash_alg - synchronous message digest definition
* @init: see struct ahash_alg
diff --git a/include/crypto/internal/simd.h b/include/crypto/internal/simd.h
index 7e7f1ac3b7fd..9e338e7aafbd 100644
--- a/include/crypto/internal/simd.h
+++ b/include/crypto/internal/simd.h
@@ -44,9 +44,11 @@ void simd_unregister_aeads(struct aead_alg *algs, int count,
*
* This delegates to may_use_simd(), except that this also returns false if SIMD
* in crypto code has been temporarily disabled on this CPU by the crypto
- * self-tests, in order to test the no-SIMD fallback code.
+ * self-tests, in order to test the no-SIMD fallback code. This override is
+ * currently limited to configurations where the "full" self-tests are enabled,
+ * because it might be a bit too invasive to be part of the "fast" self-tests.
*/
-#ifdef CONFIG_CRYPTO_SELFTESTS
+#ifdef CONFIG_CRYPTO_SELFTESTS_FULL
DECLARE_PER_CPU(bool, crypto_simd_disabled_for_test);
#define crypto_simd_usable() \
(may_use_simd() && !this_cpu_read(crypto_simd_disabled_for_test))
diff --git a/include/crypto/md5.h b/include/crypto/md5.h
index 198b5d69b92f..28ee533a0507 100644
--- a/include/crypto/md5.h
+++ b/include/crypto/md5.h
@@ -2,6 +2,7 @@
#ifndef _CRYPTO_MD5_H
#define _CRYPTO_MD5_H
+#include <crypto/hash.h>
#include <linux/types.h>
#define MD5_DIGEST_SIZE 16
@@ -15,6 +16,9 @@
#define MD5_H2 0x98badcfeUL
#define MD5_H3 0x10325476UL
+#define CRYPTO_MD5_STATESIZE \
+ CRYPTO_HASH_STATESIZE(MD5_STATE_SIZE, MD5_HMAC_BLOCK_SIZE)
+
extern const u8 md5_zero_message_hash[MD5_DIGEST_SIZE];
struct md5_state {
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 9b02961d65ee..45f2f278b50a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -249,6 +249,12 @@ static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
ATM_SKB(skb)->atm_options = vcc->atm_options;
}
+static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+ WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize,
+ &sk_atm(vcc)->sk_wmem_alloc));
+}
+
static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
{
atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 9c37c66ef9ca..46ffac5caab7 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -291,7 +291,7 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
fi->folio = page_folio(bvec->bv_page);
fi->offset = bvec->bv_offset +
- PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
+ PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page);
fi->_seg_count = bvec->bv_len;
fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
fi->_next = folio_next(fi->folio);
diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
index 0985221d5478..c9e6b26abab6 100644
--- a/include/linux/bpf-cgroup-defs.h
+++ b/include/linux/bpf-cgroup-defs.h
@@ -63,6 +63,7 @@ struct cgroup_bpf {
*/
struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
+ u64 revisions[MAX_CGROUP_BPF_ATTACH_TYPE];
/* list of cgroup shared storages */
struct list_head storages;
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b25d278409b..5dd556e89cce 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2288,6 +2288,9 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
return ret;
}
+bool bpf_jit_bypass_spec_v1(void);
+bool bpf_jit_bypass_spec_v4(void);
+
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern struct mutex bpf_stats_enabled_mutex;
@@ -2475,12 +2478,16 @@ static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
{
- return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+ return bpf_jit_bypass_spec_v1() ||
+ cpu_mitigations_off() ||
+ bpf_token_capable(token, CAP_PERFMON);
}
static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
{
- return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+ return bpf_jit_bypass_spec_v4() ||
+ cpu_mitigations_off() ||
+ bpf_token_capable(token, CAP_PERFMON);
}
int bpf_map_new_fd(struct bpf_map *map, int flags);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 256274acb1d8..7e459e839f8b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -344,7 +344,7 @@ struct bpf_func_state {
#define MAX_CALL_FRAMES 8
-/* instruction history flags, used in bpf_insn_hist_entry.flags field */
+/* instruction history flags, used in bpf_jmp_history_entry.flags field */
enum {
/* instruction references stack slot through PTR_TO_STACK register;
* we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8)
@@ -366,7 +366,7 @@ enum {
static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES);
static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8);
-struct bpf_insn_hist_entry {
+struct bpf_jmp_history_entry {
u32 idx;
/* insn idx can't be bigger than 1 million */
u32 prev_idx : 20;
@@ -449,32 +449,20 @@ struct bpf_verifier_state {
/* first and last insn idx of this verifier state */
u32 first_insn_idx;
u32 last_insn_idx;
- /* If this state is a part of states loop this field points to some
- * parent of this state such that:
- * - it is also a member of the same states loop;
- * - DFS states traversal starting from initial state visits loop_entry
- * state before this state.
- * Used to compute topmost loop entry for state loops.
- * State loops might appear because of open coded iterators logic.
- * See get_loop_entry() for more information.
+ /* if this state is a backedge state then equal_state
+ * records cached state to which this state is equal.
*/
- struct bpf_verifier_state *loop_entry;
- /* Sub-range of env->insn_hist[] corresponding to this state's
- * instruction history.
- * Backtracking is using it to go from last to first.
- * For most states instruction history is short, 0-3 instructions.
+ struct bpf_verifier_state *equal_state;
+ /* jmp history recorded from first to last.
+ * backtracking is using it to go from last to first.
+ * For most states jmp_history_cnt is [0-3].
* For loops can go up to ~40.
*/
- u32 insn_hist_start;
- u32 insn_hist_end;
+ struct bpf_jmp_history_entry *jmp_history;
+ u32 jmp_history_cnt;
u32 dfs_depth;
u32 callback_unroll_depth;
u32 may_goto_depth;
- /* If this state was ever pointed-to by other state's loop_entry field
- * this flag would be set to true. Used to avoid freeing such states
- * while they are still in use.
- */
- u32 used_as_loop_entry;
};
#define bpf_get_spilled_reg(slot, frame, mask) \
@@ -580,7 +568,8 @@ struct bpf_insn_aux_data {
u64 map_key_state; /* constant (32 bit) key tracking for maps */
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
- bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
+ bool nospec; /* do not execute this instruction speculatively */
+ bool nospec_result; /* result is unsafe under speculation, nospec must follow */
bool zext_dst; /* this insn zero extends dst reg */
bool needs_zext; /* alu op needs to clear upper bits */
bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
@@ -609,6 +598,11 @@ struct bpf_insn_aux_data {
* accepts callback function as a parameter.
*/
bool calls_callback;
+ /*
+ * CFG strongly connected component this instruction belongs to,
+ * zero if it is a singleton SCC.
+ */
+ u32 scc;
/* registers alive before this instruction. */
u16 live_regs_before;
};
@@ -718,6 +712,38 @@ struct bpf_idset {
u32 ids[BPF_ID_MAP_SIZE];
};
+/* see verifier.c:compute_scc_callchain() */
+struct bpf_scc_callchain {
+ /* call sites from bpf_verifier_state->frame[*]->callsite leading to this SCC */
+ u32 callsites[MAX_CALL_FRAMES - 1];
+ /* last frame in a chain is identified by SCC id */
+ u32 scc;
+};
+
+/* verifier state waiting for propagate_backedges() */
+struct bpf_scc_backedge {
+ struct bpf_scc_backedge *next;
+ struct bpf_verifier_state state;
+};
+
+struct bpf_scc_visit {
+ struct bpf_scc_callchain callchain;
+ /* first state in current verification path that entered SCC
+ * identified by the callchain
+ */
+ struct bpf_verifier_state *entry_state;
+ struct bpf_scc_backedge *backedges; /* list of backedges */
+ u32 num_backedges;
+};
+
+/* An array of bpf_scc_visit structs sharing tht same bpf_scc_callchain->scc
+ * but having different bpf_scc_callchain->callsites.
+ */
+struct bpf_scc_info {
+ u32 num_visits;
+ struct bpf_scc_visit visits[];
+};
+
/* single container for all structs
* one verifier_env per bpf_check() call
*/
@@ -775,9 +801,7 @@ struct bpf_verifier_env {
int cur_postorder;
} cfg;
struct backtrack_state bt;
- struct bpf_insn_hist_entry *insn_hist;
- struct bpf_insn_hist_entry *cur_hist_ent;
- u32 insn_hist_cap;
+ struct bpf_jmp_history_entry *cur_hist_ent;
u32 pass_cnt; /* number of times do_check() was called */
u32 subprog_cnt;
/* number of instructions analyzed by the verifier */
@@ -799,6 +823,7 @@ struct bpf_verifier_env {
u32 longest_mark_read_walk;
u32 free_list_size;
u32 explored_states_size;
+ u32 num_backedges;
bpfptr_t fd_array;
/* bit mask to keep track of whether a register has been accessed
@@ -816,6 +841,9 @@ struct bpf_verifier_env {
char tmp_str_buf[TMP_STR_BUF_LEN];
struct bpf_insn insn_buf[INSN_BUF_SIZE];
struct bpf_insn epilogue_buf[INSN_BUF_SIZE];
+ /* array of pointers to bpf_scc_info indexed by SCC id */
+ struct bpf_scc_info **scc_info;
+ u32 scc_cnt;
};
static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog)
diff --git a/include/linux/btf.h b/include/linux/btf.h
index b2983706292f..a40beb9cf160 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -221,6 +221,8 @@ bool btf_is_vmlinux(const struct btf *btf);
struct module *btf_try_get_module(const struct btf *btf);
u32 btf_nr_types(const struct btf *btf);
struct btf *btf_base_btf(const struct btf *btf);
+bool btf_type_is_i32(const struct btf_type *t);
+bool btf_type_is_i64(const struct btf_type *t);
bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
const struct btf_member *m,
u32 expected_offset, u32 expected_size);
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 204b22a99c4b..0a80e1f9aa20 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -57,9 +57,12 @@ static inline void bvec_set_page(struct bio_vec *bv, struct page *page,
* @offset: offset into the folio
*/
static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio,
- unsigned int len, unsigned int offset)
+ size_t len, size_t offset)
{
- bvec_set_page(bv, &folio->page, len, offset);
+ unsigned long nr = offset / PAGE_SIZE;
+
+ WARN_ON_ONCE(len > UINT_MAX);
+ bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE);
}
/**
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index e6089abc28e2..96a3a0d6a60e 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -120,6 +120,7 @@ extern void cpu_maps_update_begin(void);
extern void cpu_maps_update_done(void);
int bringup_hibernate_cpu(unsigned int sleep_cpu);
void bringup_nonboot_cpus(unsigned int max_cpus);
+int arch_cpu_rescan_dead_smt_siblings(void);
#else /* CONFIG_SMP */
#define cpuhp_tasks_frozen 0
@@ -134,6 +135,8 @@ static inline void cpu_maps_update_done(void)
static inline int add_cpu(unsigned int cpu) { return 0;}
+static inline int arch_cpu_rescan_dead_smt_siblings(void) { return 0; }
+
#endif /* CONFIG_SMP */
extern const struct bus_type cpu_subsys;
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index ca42d5e46ccc..3be35680a54f 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -54,7 +54,7 @@ enum execmem_range_flags {
EXECMEM_ROX_CACHE = (1 << 1),
};
-#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
/**
* execmem_fill_trapping_insns - set memory to contain instructions that
* will trap
@@ -94,15 +94,9 @@ int execmem_make_temp_rw(void *ptr, size_t size);
* Return: 0 on success or negative error code on failure.
*/
int execmem_restore_rox(void *ptr, size_t size);
-
-/*
- * Called from mark_readonly(), where the system transitions to ROX.
- */
-void execmem_cache_make_ro(void);
#else
static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
-static inline void execmem_cache_make_ro(void) { }
#endif
/**
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f5cf4d35d83e..eca229752cbe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -82,7 +82,7 @@ struct ctl_table_header;
#define BPF_CALL_ARGS 0xe0
/* unused opcode to mark speculation barrier for mitigating
- * Speculative Store Bypass
+ * Spectre v1 and v4
*/
#define BPF_NOSPEC 0xc0
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..b085f161ed22 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -399,7 +399,9 @@ struct readahead_control;
{ IOCB_WAITQ, "WAITQ" }, \
{ IOCB_NOIO, "NOIO" }, \
{ IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \
- { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }
+ { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }, \
+ { IOCB_AIO_RW, "AIO_RW" }, \
+ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" }
struct kiocb {
struct file *ki_filp;
@@ -2274,10 +2276,12 @@ static inline bool file_has_valid_mmap_hooks(struct file *file)
return true;
}
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma);
+
static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
{
- if (WARN_ON_ONCE(file->f_op->mmap_prepare))
- return -EINVAL;
+ if (file->f_op->mmap_prepare)
+ return compat_vma_mmap_prepare(file, vma);
return file->f_op->mmap(file, vma);
}
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index ce377f7fb912..22f39e5e2ff1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1278,7 +1278,7 @@ struct ieee80211_ext {
u8 sa[ETH_ALEN];
__le32 timestamp;
u8 change_seq;
- u8 variable[0];
+ u8 variable[];
} __packed s1g_beacon;
} u;
} __packed __aligned(2);
@@ -1536,7 +1536,7 @@ struct ieee80211_mgmt {
u8 action_code;
u8 dialog_token;
__le16 capability;
- u8 variable[0];
+ u8 variable[];
} __packed tdls_discover_resp;
struct {
u8 action_code;
@@ -1721,35 +1721,35 @@ struct ieee80211_tdls_data {
struct {
u8 dialog_token;
__le16 capability;
- u8 variable[0];
+ u8 variable[];
} __packed setup_req;
struct {
__le16 status_code;
u8 dialog_token;
__le16 capability;
- u8 variable[0];
+ u8 variable[];
} __packed setup_resp;
struct {
__le16 status_code;
u8 dialog_token;
- u8 variable[0];
+ u8 variable[];
} __packed setup_cfm;
struct {
__le16 reason_code;
- u8 variable[0];
+ u8 variable[];
} __packed teardown;
struct {
u8 dialog_token;
- u8 variable[0];
+ u8 variable[];
} __packed discover_req;
struct {
u8 target_channel;
u8 oper_class;
- u8 variable[0];
+ u8 variable[];
} __packed chan_switch_req;
struct {
__le16 status_code;
- u8 variable[0];
+ u8 variable[];
} __packed chan_switch_resp;
} u;
} __packed;
diff --git a/include/linux/key.h b/include/linux/key.h
index ba05de8579ec..81b8f05c6898 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -236,7 +236,7 @@ struct key {
#define KEY_FLAG_ROOT_CAN_INVAL 7 /* set if key can be invalidated by root without permission */
#define KEY_FLAG_KEEP 8 /* set if key should not be removed */
#define KEY_FLAG_UID_KEYRING 9 /* set if key is a user or user session keyring */
-#define KEY_FLAG_FINAL_PUT 10 /* set if final put has happened on key */
+#define KEY_FLAG_USER_ALIVE 10 /* set if final put has not happened on key yet */
/* the key type and key description string
* - the desc is used to match a key against search criteria
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 31be45fd47a6..1e5aec839041 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1352,7 +1352,7 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm);
int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm);
unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
const struct ata_acpi_gtm *gtm);
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm);
+int ata_acpi_cbl_pata_type(struct ata_port *ap);
#else
static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap)
{
@@ -1377,10 +1377,9 @@ static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
return 0;
}
-static inline int ata_acpi_cbl_80wire(struct ata_port *ap,
- const struct ata_acpi_gtm *gtm)
+static inline int ata_acpi_cbl_pata_type(struct ata_port *ap)
{
- return 0;
+ return ATA_CBL_PATA40;
}
#endif
diff --git a/include/linux/module.h b/include/linux/module.h
index 92e1420fccdf..5faa1fb1f4b4 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -586,11 +586,6 @@ struct module {
atomic_t refcnt;
#endif
-#ifdef CONFIG_MITIGATION_ITS
- int its_num_pages;
- void **its_page_array;
-#endif
-
#ifdef CONFIG_CONSTRUCTORS
/* Constructor functions. */
ctor_fn_t *ctors;
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 4880f434c021..1a508beba446 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -116,10 +116,8 @@ extern int may_umount_tree(struct vfsmount *);
extern int may_umount(struct vfsmount *);
int do_mount(const char *, const char __user *,
const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
- struct vfsmount *);
+extern struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(struct path *, struct path *);
extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
extern int cifs_root_data(char **dev, char **opts);
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 5daf80df9e89..b74a539ec581 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -108,7 +108,7 @@ extern void deregister_mtd_parser(struct mtd_part_parser *parser);
deregister_mtd_parser)
int mtd_add_partition(struct mtd_info *master, const char *name,
- long long offset, long long length, struct mtd_info **part);
+ long long offset, long long length);
int mtd_del_partition(struct mtd_info *master, int partno);
uint64_t mtd_get_device_size(const struct mtd_info *mtd);
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 811a0f356315..15eaa09da998 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -113,11 +113,12 @@
SPI_MEM_DTR_OP_DATA_IN(len, buf, 2), \
SPI_MEM_OP_MAX_FREQ(freq))
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, ...) \
SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \
SPI_MEM_OP_ADDR(2, addr, 2), \
SPI_MEM_OP_DUMMY(ndummy, 2), \
- SPI_MEM_OP_DATA_IN(len, buf, 2))
+ SPI_MEM_OP_DATA_IN(len, buf, 2), \
+ SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len) \
SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1), \
@@ -151,11 +152,12 @@
SPI_MEM_DTR_OP_DATA_IN(len, buf, 4), \
SPI_MEM_OP_MAX_FREQ(freq))
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, ...) \
SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \
SPI_MEM_OP_ADDR(2, addr, 4), \
SPI_MEM_OP_DUMMY(ndummy, 4), \
- SPI_MEM_OP_DATA_IN(len, buf, 4))
+ SPI_MEM_OP_DATA_IN(len, buf, 4), \
+ SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len) \
SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1), \
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 52dc7cfab0e0..ec9d96025683 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -635,8 +635,46 @@ struct perf_addr_filter_range {
unsigned long size;
};
-/**
- * enum perf_event_state - the states of an event:
+/*
+ * The normal states are:
+ *
+ * ACTIVE --.
+ * ^ |
+ * | |
+ * sched_{in,out}() |
+ * | |
+ * v |
+ * ,---> INACTIVE --+ <-.
+ * | | |
+ * | {dis,en}able()
+ * sched_in() | |
+ * | OFF <--' --+
+ * | |
+ * `---> ERROR ------'
+ *
+ * That is:
+ *
+ * sched_in: INACTIVE -> {ACTIVE,ERROR}
+ * sched_out: ACTIVE -> INACTIVE
+ * disable: {ACTIVE,INACTIVE} -> OFF
+ * enable: {OFF,ERROR} -> INACTIVE
+ *
+ * Where {OFF,ERROR} are disabled states.
+ *
+ * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of
+ * defunct events:
+ *
+ * - EXIT means task that the even was assigned to died, but child events
+ * still live, and further children can still be created. But the event
+ * itself will never be active again. It can only transition to
+ * {REVOKED,DEAD};
+ *
+ * - REVOKED means the PMU the event was associated with is gone; all
+ * functionality is stopped but the event is still alive. Can only
+ * transition to DEAD;
+ *
+ * - DEAD event really is DYING tearing down state and freeing bits.
+ *
*/
enum perf_event_state {
PERF_EVENT_STATE_DEAD = -5,
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9ba771f2ddea..6fb4894b8cfd 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -159,7 +159,7 @@ struct rdt_ctrl_domain {
/**
* struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
* @hdr: common header for different domain types
- * @ci: cache info for this domain
+ * @ci_id: cache info id for this domain
* @rmid_busy_llc: bitmap of which limbo RMIDs are above threshold
* @mbm_total: saved state for MBM total bandwidth
* @mbm_local: saved state for MBM local bandwidth
@@ -170,7 +170,7 @@ struct rdt_ctrl_domain {
*/
struct rdt_mon_domain {
struct rdt_domain_hdr hdr;
- struct cacheinfo *ci;
+ unsigned int ci_id;
unsigned long *rmid_busy_llc;
struct mbm_state *mbm_total;
struct mbm_state *mbm_local;
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index 0cdbfc42f153..6f8a4965f9b9 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -99,7 +99,7 @@ static inline bool sg_is_last(struct scatterlist *sg)
* @sg: The current sg entry
*
* Description:
- * Usually the next entry will be @sg@ + 1, but if this sg element is part
+ * Usually the next entry will be @sg + 1, but if this sg element is part
* of a chained scatterlist, it could jump to the start of a new
* scatterlist array.
*
@@ -254,7 +254,7 @@ static inline void __sg_chain(struct scatterlist *chain_sg,
* @sgl: Second scatterlist
*
* Description:
- * Links @prv@ and @sgl@ together, to form a longer scatterlist.
+ * Links @prv and @sgl together, to form a longer scatterlist.
*
**/
static inline void sg_chain(struct scatterlist *prv, unsigned int prv_nents,
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index 3c13240077b8..57ed3035cc30 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -40,6 +40,8 @@ struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness);
struct tnum tnum_add(struct tnum a, struct tnum b);
/* Subtract two tnums, return @a - @b */
struct tnum tnum_sub(struct tnum a, struct tnum b);
+/* Neg of a tnum, return 0 - @a */
+struct tnum tnum_neg(struct tnum a);
/* Bitwise-AND, return @a & @b */
struct tnum tnum_and(struct tnum a, struct tnum b);
/* Bitwise-OR, return @a | @b */
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 7c06f4795670..1beb5b395d81 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -296,6 +296,8 @@ static inline bool pagefault_disabled(void)
*/
#define faulthandler_disabled() (pagefault_disabled() || in_atomic())
+DEFINE_LOCK_GUARD_0(pagefault, pagefault_disable(), pagefault_enable())
+
#ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
/**
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2b261e74e2c4..9fc8f544e20e 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -29,6 +29,7 @@
#include <linux/idr.h>
#include <linux/leds.h>
#include <linux/rculist.h>
+#include <linux/srcu.h>
#include <net/bluetooth/hci.h>
#include <net/bluetooth/hci_drv.h>
@@ -242,6 +243,7 @@ struct adv_info {
__u8 mesh;
__u8 instance;
__u8 handle;
+ __u8 sid;
__u32 flags;
__u16 timeout;
__u16 remaining_time;
@@ -346,6 +348,7 @@ struct adv_monitor {
struct hci_dev {
struct list_head list;
+ struct srcu_struct srcu;
struct mutex lock;
struct ida unset_handle_ida;
@@ -546,6 +549,7 @@ struct hci_dev {
struct hci_conn_hash conn_hash;
struct list_head mesh_pending;
+ struct mutex mgmt_pending_lock;
struct list_head mgmt_pending;
struct list_head reject_list;
struct list_head accept_list;
@@ -1550,13 +1554,14 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst,
u16 timeout);
struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, struct bt_iso_qos *qos);
-struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid,
struct bt_iso_qos *qos,
__u8 base_len, __u8 *base);
struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, struct bt_iso_qos *qos);
struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
- __u8 dst_type, struct bt_iso_qos *qos,
+ __u8 dst_type, __u8 sid,
+ struct bt_iso_qos *qos,
__u8 data_len, __u8 *data);
struct hci_conn *hci_pa_create_sync(struct hci_dev *hdev, bdaddr_t *dst,
__u8 dst_type, __u8 sid, struct bt_iso_qos *qos);
@@ -1831,6 +1836,7 @@ int hci_remove_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr,
void hci_adv_instances_clear(struct hci_dev *hdev);
struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance);
+struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid);
struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance);
struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
u32 flags, u16 adv_data_len, u8 *adv_data,
@@ -1838,7 +1844,7 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
u16 timeout, u16 duration, s8 tx_power,
u32 min_interval, u32 max_interval,
u8 mesh_handle);
-struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
+struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid,
u32 flags, u8 data_len, u8 *data,
u32 min_interval, u32 max_interval);
int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance,
@@ -2400,7 +2406,6 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev,
u8 instance);
void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev,
u8 instance);
-void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle);
int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip);
void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle,
bdaddr_t *bdaddr, u8 addr_type);
diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
index 72558c826aa1..5224f57f6af2 100644
--- a/include/net/bluetooth/hci_sync.h
+++ b/include/net/bluetooth/hci_sync.h
@@ -115,8 +115,8 @@ int hci_enable_ext_advertising_sync(struct hci_dev *hdev, u8 instance);
int hci_enable_advertising_sync(struct hci_dev *hdev);
int hci_enable_advertising(struct hci_dev *hdev);
-int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
- u8 *data, u32 flags, u16 min_interval,
+int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 sid,
+ u8 data_len, u8 *data, u32 flags, u16 min_interval,
u16 max_interval, u16 sync_interval);
int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 629368ab2787..638948be4c50 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -973,14 +973,6 @@ static inline void qdisc_qstats_qlen_backlog(struct Qdisc *sch, __u32 *qlen,
*backlog = qstats.backlog;
}
-static inline void qdisc_tree_flush_backlog(struct Qdisc *sch)
-{
- __u32 qlen, backlog;
-
- qdisc_qstats_qlen_backlog(sch, &qlen, &backlog);
- qdisc_tree_reduce_backlog(sch, qlen, backlog);
-}
-
static inline void qdisc_purge_queue(struct Qdisc *sch)
{
__u32 qlen, backlog;
diff --git a/include/net/sock.h b/include/net/sock.h
index 92e7c1aae3cc..4c37015b7cf7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -3010,8 +3010,11 @@ int sock_ioctl_inout(struct sock *sk, unsigned int cmd,
int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
static inline bool sk_is_readable(struct sock *sk)
{
- if (sk->sk_prot->sock_is_readable)
- return sk->sk_prot->sock_is_readable(sk);
+ const struct proto *prot = READ_ONCE(sk->sk_prot);
+
+ if (prot->sock_is_readable)
+ return prot->sock_is_readable(sk);
+
return false;
}
#endif /* _SOCK_H */
diff --git a/include/trace/events/erofs.h b/include/trace/events/erofs.h
index a5f4b9234f46..dad7360f42f9 100644
--- a/include/trace/events/erofs.h
+++ b/include/trace/events/erofs.h
@@ -211,24 +211,6 @@ TRACE_EVENT(erofs_map_blocks_exit,
show_mflags(__entry->mflags), __entry->ret)
);
-TRACE_EVENT(erofs_destroy_inode,
- TP_PROTO(struct inode *inode),
-
- TP_ARGS(inode),
-
- TP_STRUCT__entry(
- __field( dev_t, dev )
- __field( erofs_nid_t, nid )
- ),
-
- TP_fast_assign(
- __entry->dev = inode->i_sb->s_dev;
- __entry->nid = EROFS_I(inode)->nid;
- ),
-
- TP_printk("dev = (%d,%d), nid = %llu", show_dev_nid(__entry))
-);
-
#endif /* _TRACE_EROFS_H */
/* This part must be outside protection */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0b4a2f124d11..719ba230032f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1794,6 +1794,13 @@ union bpf_attr {
};
__u64 expected_revision;
} netkit;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } cgroup;
};
} link_create;
@@ -2403,7 +2410,7 @@ union bpf_attr {
* into it. An example is available in file
* *samples/bpf/trace_output_user.c* in the Linux kernel source
* tree (the eBPF program counterpart is in
- * *samples/bpf/trace_output_kern.c*).
+ * *samples/bpf/trace_output.bpf.c*).
*
* **bpf_perf_event_output**\ () achieves better performance
* than **bpf_trace_printk**\ () for sharing data with user
@@ -6653,11 +6660,15 @@ struct bpf_link_info {
struct {
__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
__u32 tp_name_len; /* in/out: tp_name buffer len */
+ __u32 :32;
+ __u64 cookie;
} raw_tracepoint;
struct {
__u32 attach_type;
__u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
__u32 target_btf_id; /* BTF type id inside the object */
+ __u32 :32;
+ __u64 cookie;
} tracing;
struct {
__u64 cgroup_id;
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index 9ff72cfb2e98..09a75bdb6560 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -208,10 +208,6 @@ enum {
ETHTOOL_A_STATS_PHY_MAX = (__ETHTOOL_A_STATS_PHY_CNT - 1)
};
-/* generic netlink info */
-#define ETHTOOL_GENL_NAME "ethtool"
-#define ETHTOOL_GENL_VERSION 1
-
#define ETHTOOL_MCGRP_MONITOR_NAME "monitor"
#endif /* _UAPI_LINUX_ETHTOOL_NETLINK_H_ */
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 9a02f579de22..aa8ab5227c1e 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -6,8 +6,8 @@
#ifndef _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
#define _UAPI_LINUX_ETHTOOL_NETLINK_GENERATED_H
-#define ETHTOOL_FAMILY_NAME "ethtool"
-#define ETHTOOL_FAMILY_VERSION 1
+#define ETHTOOL_GENL_NAME "ethtool"
+#define ETHTOOL_GENL_VERSION 1
enum {
ETHTOOL_UDP_TUNNEL_TYPE_VXLAN,
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index d00b85cb168c..37891580d05d 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -178,6 +178,7 @@ struct kvm_xen_exit {
#define KVM_EXIT_NOTIFY 37
#define KVM_EXIT_LOONGARCH_IOCSR 38
#define KVM_EXIT_MEMORY_FAULT 39
+#define KVM_EXIT_TDX 40
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -447,6 +448,27 @@ struct kvm_run {
__u64 gpa;
__u64 size;
} memory_fault;
+ /* KVM_EXIT_TDX */
+ struct {
+ __u64 flags;
+ __u64 nr;
+ union {
+ struct {
+ __u64 ret;
+ __u64 data[5];
+ } unknown;
+ struct {
+ __u64 ret;
+ __u64 gpa;
+ __u64 size;
+ } get_quote;
+ struct {
+ __u64 ret;
+ __u64 leaf;
+ __u64 r11, r12, r13, r14;
+ } get_tdvmcall_info;
+ };
+ } tdx;
/* Fix the size of the union. */
char padding[256];
};
diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h
index 84fa8a21dfd0..6ac84b2f636c 100644
--- a/include/uapi/linux/mptcp_pm.h
+++ b/include/uapi/linux/mptcp_pm.h
@@ -27,14 +27,14 @@
* token, rem_id.
* @MPTCP_EVENT_SUB_ESTABLISHED: A new subflow has been established. 'error'
* should not be set. Attributes: token, family, loc_id, rem_id, saddr4 |
- * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error].
+ * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error].
* @MPTCP_EVENT_SUB_CLOSED: A subflow has been closed. An error (copy of
* sk_err) could be set if an error has been detected for this subflow.
* Attributes: token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 |
- * daddr6, sport, dport, backup, if_idx [, error].
+ * daddr6, sport, dport, backup, if-idx [, error].
* @MPTCP_EVENT_SUB_PRIORITY: The priority of a subflow has changed. 'error'
* should not be set. Attributes: token, family, loc_id, rem_id, saddr4 |
- * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error].
+ * saddr6, daddr4 | daddr6, sport, dport, backup, if-idx [, error].
* @MPTCP_EVENT_LISTENER_CREATED: A new PM listener is created. Attributes:
* family, sport, saddr4 | saddr6.
* @MPTCP_EVENT_LISTENER_CLOSED: A PM listener is closed. Attributes: family,
diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h
index ed07181d4eff..e05280e41522 100644
--- a/include/uapi/linux/vm_sockets.h
+++ b/include/uapi/linux/vm_sockets.h
@@ -17,6 +17,10 @@
#ifndef _UAPI_VM_SOCKETS_H
#define _UAPI_VM_SOCKETS_H
+#ifndef __KERNEL__
+#include <sys/socket.h> /* for struct sockaddr and sa_family_t */
+#endif
+
#include <linux/socket.h>
#include <linux/types.h>
diff --git a/init/initramfs.c b/init/initramfs.c
index 72bad44a1d41..097673b97784 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/init.h>
#include <linux/async.h>
+#include <linux/export.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/types.h>
diff --git a/init/main.c b/init/main.c
index ed576c7f475d..225a58279acd 100644
--- a/init/main.c
+++ b/init/main.c
@@ -13,6 +13,7 @@
#define DEBUG /* Enable initcall_debug */
#include <linux/types.h>
+#include <linux/export.h>
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index e9355276ab5d..9798d6fb4ec7 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -141,18 +141,26 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
if (ctx->flags & IORING_SETUP_SQPOLL) {
struct io_sq_data *sq = ctx->sq_data;
+ struct task_struct *tsk;
+ rcu_read_lock();
+ tsk = rcu_dereference(sq->thread);
/*
* sq->thread might be NULL if we raced with the sqpoll
* thread termination.
*/
- if (sq->thread) {
+ if (tsk) {
+ get_task_struct(tsk);
+ rcu_read_unlock();
+ getrusage(tsk, RUSAGE_SELF, &sq_usage);
+ put_task_struct(tsk);
sq_pid = sq->task_pid;
sq_cpu = sq->sq_cpu;
- getrusage(sq->thread, RUSAGE_SELF, &sq_usage);
sq_total_time = (sq_usage.ru_stime.tv_sec * 1000000
+ sq_usage.ru_stime.tv_usec);
sq_work_time = sq->work_time;
+ } else {
+ rcu_read_unlock();
}
}
diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index cd1fcb115739..be91edf34f01 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -1259,8 +1259,10 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
atomic_set(&wq->worker_refs, 1);
init_completion(&wq->worker_done);
ret = cpuhp_state_add_instance_nocalls(io_wq_online, &wq->cpuhp_node);
- if (ret)
+ if (ret) {
+ put_task_struct(wq->task);
goto err;
+ }
return wq;
err:
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index cf759c172083..5111ec040c53 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1523,6 +1523,9 @@ static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx)
}
}
mutex_unlock(&ctx->uring_lock);
+
+ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+ io_move_task_work_from_local(ctx);
}
static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned int min_events)
@@ -2906,7 +2909,7 @@ static __cold void io_ring_exit_work(struct work_struct *work)
struct task_struct *tsk;
io_sq_thread_park(sqd);
- tsk = sqd->thread;
+ tsk = sqpoll_task_locked(sqd);
if (tsk && tsk->io_uring && tsk->io_uring->io_wq)
io_wq_cancel_cb(tsk->io_uring->io_wq,
io_cancel_ctx_cb, ctx, true);
@@ -3142,7 +3145,7 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
s64 inflight;
DEFINE_WAIT(wait);
- WARN_ON_ONCE(sqd && sqd->thread != current);
+ WARN_ON_ONCE(sqd && sqpoll_task_locked(sqd) != current);
if (!current->io_uring)
return;
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index d59c12277d58..66c1ca73f55e 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -98,8 +98,6 @@ struct llist_node *io_handle_tw_list(struct llist_node *node, unsigned int *coun
struct llist_node *tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
void tctx_task_work(struct callback_head *cb);
__cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd);
-int io_uring_alloc_task_context(struct task_struct *task,
- struct io_ring_ctx *ctx);
int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
int start, int end);
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 2ea65f3cef72..ce95e3af44a9 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -270,8 +270,11 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
/* truncate end piece, if needed, for non partial buffers */
if (len > arg->max_len) {
len = arg->max_len;
- if (!(bl->flags & IOBL_INC))
+ if (!(bl->flags & IOBL_INC)) {
+ if (iov != arg->iovs)
+ break;
buf->len = len;
+ }
}
iov->iov_base = u64_to_user_ptr(buf->addr);
diff --git a/io_uring/net.c b/io_uring/net.c
index e16633fd6630..9550d4c8f866 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -821,7 +821,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
if (sr->flags & IORING_RECVSEND_BUNDLE) {
size_t this_ret = *ret - sr->done_io;
- cflags |= io_put_kbufs(req, *ret, io_bundle_nbufs(kmsg, this_ret),
+ cflags |= io_put_kbufs(req, this_ret, io_bundle_nbufs(kmsg, this_ret),
issue_flags);
if (sr->retry)
cflags = req->cqe.flags | (cflags & CQE_F_MASK);
diff --git a/io_uring/register.c b/io_uring/register.c
index cc23a4c205cd..a59589249fce 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -273,6 +273,8 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
if (ctx->flags & IORING_SETUP_SQPOLL) {
sqd = ctx->sq_data;
if (sqd) {
+ struct task_struct *tsk;
+
/*
* Observe the correct sqd->lock -> ctx->uring_lock
* ordering. Fine to drop uring_lock here, we hold
@@ -282,8 +284,9 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
mutex_unlock(&ctx->uring_lock);
mutex_lock(&sqd->lock);
mutex_lock(&ctx->uring_lock);
- if (sqd->thread)
- tctx = sqd->thread->io_uring;
+ tsk = sqpoll_task_locked(sqd);
+ if (tsk)
+ tctx = tsk->io_uring;
}
} else {
tctx = current->io_uring;
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index c592ceace97d..d724602697e7 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -809,10 +809,8 @@ static struct io_rsrc_node *io_sqe_buffer_register(struct io_ring_ctx *ctx,
imu->nr_bvecs = nr_pages;
ret = io_buffer_account_pin(ctx, pages, nr_pages, imu, last_hpage);
- if (ret) {
- unpin_user_pages(pages, nr_pages);
+ if (ret)
goto done;
- }
size = iov->iov_len;
/* store original address for later verification */
@@ -842,6 +840,8 @@ done:
if (ret) {
if (imu)
io_free_imu(ctx, imu);
+ if (pages)
+ unpin_user_pages(pages, nr_pages);
io_cache_free(&ctx->node_cache, node);
node = ERR_PTR(ret);
}
@@ -1177,6 +1177,8 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
return -EINVAL;
if (check_add_overflow(arg->nr, arg->dst_off, &nbufs))
return -EOVERFLOW;
+ if (nbufs > IORING_MAX_REG_BUFFERS)
+ return -EINVAL;
ret = io_rsrc_data_alloc(&data, max(nbufs, ctx->buf_table.nr));
if (ret)
diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
index 03c699493b5a..a3f11349ce06 100644
--- a/io_uring/sqpoll.c
+++ b/io_uring/sqpoll.c
@@ -16,6 +16,7 @@
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
+#include "tctx.h"
#include "napi.h"
#include "sqpoll.h"
@@ -30,7 +31,7 @@ enum {
void io_sq_thread_unpark(struct io_sq_data *sqd)
__releases(&sqd->lock)
{
- WARN_ON_ONCE(sqd->thread == current);
+ WARN_ON_ONCE(sqpoll_task_locked(sqd) == current);
/*
* Do the dance but not conditional clear_bit() because it'd race with
@@ -46,24 +47,32 @@ void io_sq_thread_unpark(struct io_sq_data *sqd)
void io_sq_thread_park(struct io_sq_data *sqd)
__acquires(&sqd->lock)
{
- WARN_ON_ONCE(data_race(sqd->thread) == current);
+ struct task_struct *tsk;
atomic_inc(&sqd->park_pending);
set_bit(IO_SQ_THREAD_SHOULD_PARK, &sqd->state);
mutex_lock(&sqd->lock);
- if (sqd->thread)
- wake_up_process(sqd->thread);
+
+ tsk = sqpoll_task_locked(sqd);
+ if (tsk) {
+ WARN_ON_ONCE(tsk == current);
+ wake_up_process(tsk);
+ }
}
void io_sq_thread_stop(struct io_sq_data *sqd)
{
- WARN_ON_ONCE(sqd->thread == current);
+ struct task_struct *tsk;
+
WARN_ON_ONCE(test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state));
set_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state);
mutex_lock(&sqd->lock);
- if (sqd->thread)
- wake_up_process(sqd->thread);
+ tsk = sqpoll_task_locked(sqd);
+ if (tsk) {
+ WARN_ON_ONCE(tsk == current);
+ wake_up_process(tsk);
+ }
mutex_unlock(&sqd->lock);
wait_for_completion(&sqd->exited);
}
@@ -270,7 +279,8 @@ static int io_sq_thread(void *data)
/* offload context creation failed, just exit */
if (!current->io_uring) {
mutex_lock(&sqd->lock);
- sqd->thread = NULL;
+ rcu_assign_pointer(sqd->thread, NULL);
+ put_task_struct(current);
mutex_unlock(&sqd->lock);
goto err_out;
}
@@ -379,7 +389,8 @@ static int io_sq_thread(void *data)
io_sq_tw(&retry_list, UINT_MAX);
io_uring_cancel_generic(true, sqd);
- sqd->thread = NULL;
+ rcu_assign_pointer(sqd->thread, NULL);
+ put_task_struct(current);
list_for_each_entry(ctx, &sqd->ctx_list, sqd_list)
atomic_or(IORING_SQ_NEED_WAKEUP, &ctx->rings->sq_flags);
io_run_task_work();
@@ -409,7 +420,6 @@ void io_sqpoll_wait_sq(struct io_ring_ctx *ctx)
__cold int io_sq_offload_create(struct io_ring_ctx *ctx,
struct io_uring_params *p)
{
- struct task_struct *task_to_put = NULL;
int ret;
/* Retain compatibility with failing for an invalid attach attempt */
@@ -484,8 +494,11 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
goto err_sqpoll;
}
- sqd->thread = tsk;
- task_to_put = get_task_struct(tsk);
+ mutex_lock(&sqd->lock);
+ rcu_assign_pointer(sqd->thread, tsk);
+ mutex_unlock(&sqd->lock);
+
+ get_task_struct(tsk);
ret = io_uring_alloc_task_context(tsk, ctx);
wake_up_new_task(tsk);
if (ret)
@@ -495,16 +508,11 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
ret = -EINVAL;
goto err;
}
-
- if (task_to_put)
- put_task_struct(task_to_put);
return 0;
err_sqpoll:
complete(&ctx->sq_data->exited);
err:
io_sq_thread_finish(ctx);
- if (task_to_put)
- put_task_struct(task_to_put);
return ret;
}
@@ -515,10 +523,13 @@ __cold int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx,
int ret = -EINVAL;
if (sqd) {
+ struct task_struct *tsk;
+
io_sq_thread_park(sqd);
/* Don't set affinity for a dying thread */
- if (sqd->thread)
- ret = io_wq_cpu_affinity(sqd->thread->io_uring, mask);
+ tsk = sqpoll_task_locked(sqd);
+ if (tsk)
+ ret = io_wq_cpu_affinity(tsk->io_uring, mask);
io_sq_thread_unpark(sqd);
}
diff --git a/io_uring/sqpoll.h b/io_uring/sqpoll.h
index 4171666b1cf4..b83dcdec9765 100644
--- a/io_uring/sqpoll.h
+++ b/io_uring/sqpoll.h
@@ -8,7 +8,7 @@ struct io_sq_data {
/* ctx's that are using this sqd */
struct list_head ctx_list;
- struct task_struct *thread;
+ struct task_struct __rcu *thread;
struct wait_queue_head wait;
unsigned sq_thread_idle;
@@ -29,3 +29,9 @@ void io_sq_thread_unpark(struct io_sq_data *sqd);
void io_put_sq_data(struct io_sq_data *sqd);
void io_sqpoll_wait_sq(struct io_ring_ctx *ctx);
int io_sqpoll_wq_cpu_affinity(struct io_ring_ctx *ctx, cpumask_var_t mask);
+
+static inline struct task_struct *sqpoll_task_locked(struct io_sq_data *sqd)
+{
+ return rcu_dereference_protected(sqd->thread,
+ lockdep_is_held(&sqd->lock));
+}
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f2f38903b2fe..b0eae2a3c895 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule)
return 0;
}
-static int compare_root(struct vfsmount *mnt, void *arg)
-{
- return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
- (unsigned long)arg;
-}
-
void audit_trim_trees(void)
{
struct list_head cursor;
@@ -683,8 +677,9 @@ void audit_trim_trees(void)
while (cursor.next != &tree_list) {
struct audit_tree *tree;
struct path path;
- struct vfsmount *root_mnt;
struct audit_node *node;
+ struct path *paths;
+ struct path array[16];
int err;
tree = container_of(cursor.next, struct audit_tree, list);
@@ -696,9 +691,9 @@ void audit_trim_trees(void)
if (err)
goto skip_it;
- root_mnt = collect_mounts(&path);
+ paths = collect_paths(&path, array, 16);
path_put(&path);
- if (IS_ERR(root_mnt))
+ if (IS_ERR(paths))
goto skip_it;
spin_lock(&hash_lock);
@@ -706,14 +701,17 @@ void audit_trim_trees(void)
struct audit_chunk *chunk = find_chunk(node);
/* this could be NULL if the watch is dying else where... */
node->index |= 1U<<31;
- if (iterate_mounts(compare_root,
- (void *)(chunk->key),
- root_mnt))
- node->index &= ~(1U<<31);
+ for (struct path *p = paths; p->dentry; p++) {
+ struct inode *inode = p->dentry->d_inode;
+ if (inode_to_key(inode) == chunk->key) {
+ node->index &= ~(1U<<31);
+ break;
+ }
+ }
}
spin_unlock(&hash_lock);
trim_marked(tree);
- drop_collected_mounts(root_mnt);
+ drop_collected_paths(paths, array);
skip_it:
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree)
put_tree(tree);
}
-static int tag_mount(struct vfsmount *mnt, void *arg)
+static int tag_mounts(struct path *paths, struct audit_tree *tree)
{
- return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+ for (struct path *p = paths; p->dentry; p++) {
+ int err = tag_chunk(p->dentry->d_inode, tree);
+ if (err)
+ return err;
+ }
+ return 0;
}
/*
@@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
{
struct audit_tree *seed = rule->tree, *tree;
struct path path;
- struct vfsmount *mnt;
+ struct path array[16];
+ struct path *paths;
int err;
rule->tree = NULL;
@@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule)
err = kern_path(tree->pathname, 0, &path);
if (err)
goto Err;
- mnt = collect_mounts(&path);
+ paths = collect_paths(&path, array, 16);
path_put(&path);
- if (IS_ERR(mnt)) {
- err = PTR_ERR(mnt);
+ if (IS_ERR(paths)) {
+ err = PTR_ERR(paths);
goto Err;
}
get_tree(tree);
- err = iterate_mounts(tag_mount, tree, mnt);
- drop_collected_mounts(mnt);
+ err = tag_mounts(paths, tree);
+ drop_collected_paths(paths, array);
if (!err) {
struct audit_node *node;
@@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new)
struct list_head cursor, barrier;
int failed = 0;
struct path path1, path2;
- struct vfsmount *tagged;
+ struct path array[16];
+ struct path *paths;
int err;
err = kern_path(new, 0, &path2);
if (err)
return err;
- tagged = collect_mounts(&path2);
+ paths = collect_paths(&path2, array, 16);
path_put(&path2);
- if (IS_ERR(tagged))
- return PTR_ERR(tagged);
+ if (IS_ERR(paths))
+ return PTR_ERR(paths);
err = kern_path(old, 0, &path1);
if (err) {
- drop_collected_mounts(tagged);
+ drop_collected_paths(paths, array);
return err;
}
@@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new)
continue;
}
- failed = iterate_mounts(tag_mount, tree, tagged);
+ failed = tag_mounts(paths, tree);
if (failed) {
put_tree(tree);
mutex_lock(&audit_filter_mutex);
@@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new)
list_del(&cursor);
mutex_unlock(&audit_filter_mutex);
path_put(&path1);
- drop_collected_mounts(tagged);
+ drop_collected_paths(paths, array);
return failed;
}
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index eb28c0f219ee..3d080916faf9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -530,8 +530,6 @@ static int array_map_check_btf(const struct bpf_map *map,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
- u32 int_data;
-
/* One exception for keyless BTF: .bss/.data/.rodata map */
if (btf_type_is_void(key_type)) {
if (map->map_type != BPF_MAP_TYPE_ARRAY ||
@@ -544,14 +542,11 @@ static int array_map_check_btf(const struct bpf_map *map,
return 0;
}
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- /* bpf array can only take a u32 key. This check makes sure
+ /*
+ * Bpf array can only take a u32 key. This check makes sure
* that the btf matches the attr used during map_create.
*/
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i32(key_type))
return -EINVAL;
return 0;
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 380e9a7cac75..303ab1f42d3a 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -38,8 +38,7 @@ static DEFINE_MUTEX(link_mutex);
/* incremented on every opened seq_file */
static atomic64_t session_id;
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
- const struct bpf_iter_seq_info *seq_info);
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link);
static void bpf_iter_inc_seq_num(struct seq_file *seq)
{
@@ -257,7 +256,7 @@ static int iter_open(struct inode *inode, struct file *file)
{
struct bpf_iter_link *link = inode->i_private;
- return prepare_seq_file(file, link, __get_seq_info(link));
+ return prepare_seq_file(file, link);
}
static int iter_release(struct inode *inode, struct file *file)
@@ -586,9 +585,9 @@ static void init_seq_meta(struct bpf_iter_priv_data *priv_data,
priv_data->done_stop = false;
}
-static int prepare_seq_file(struct file *file, struct bpf_iter_link *link,
- const struct bpf_iter_seq_info *seq_info)
+static int prepare_seq_file(struct file *file, struct bpf_iter_link *link)
{
+ const struct bpf_iter_seq_info *seq_info = __get_seq_info(link);
struct bpf_iter_priv_data *priv_data;
struct bpf_iter_target_info *tinfo;
struct bpf_prog *prog;
@@ -653,7 +652,7 @@ int bpf_iter_new_fd(struct bpf_link *link)
}
iter_link = container_of(link, struct bpf_iter_link, link);
- err = prepare_seq_file(file, iter_link, __get_seq_info(iter_link));
+ err = prepare_seq_file(file, iter_link);
if (err)
goto free_file;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index fa56c30833ff..b931fbceb54d 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -722,13 +722,7 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
- u32 int_data;
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i32(key_type))
return -EINVAL;
return 0;
diff --git a/kernel/bpf/bpf_lru_list.c b/kernel/bpf/bpf_lru_list.c
index 3dabdd137d10..2d6e1c98d8ad 100644
--- a/kernel/bpf/bpf_lru_list.c
+++ b/kernel/bpf/bpf_lru_list.c
@@ -337,12 +337,12 @@ static void bpf_lru_list_pop_free_to_local(struct bpf_lru *lru,
list) {
__bpf_lru_node_move_to_free(l, node, local_free_list(loc_l),
BPF_LRU_LOCAL_LIST_T_FREE);
- if (++nfree == LOCAL_FREE_TARGET)
+ if (++nfree == lru->target_free)
break;
}
- if (nfree < LOCAL_FREE_TARGET)
- __bpf_lru_list_shrink(lru, l, LOCAL_FREE_TARGET - nfree,
+ if (nfree < lru->target_free)
+ __bpf_lru_list_shrink(lru, l, lru->target_free - nfree,
local_free_list(loc_l),
BPF_LRU_LOCAL_LIST_T_FREE);
@@ -577,6 +577,9 @@ static void bpf_common_lru_populate(struct bpf_lru *lru, void *buf,
list_add(&node->list, &l->lists[BPF_LRU_LIST_T_FREE]);
buf += elem_size;
}
+
+ lru->target_free = clamp((nr_elems / num_possible_cpus()) / 2,
+ 1, LOCAL_FREE_TARGET);
}
static void bpf_percpu_lru_populate(struct bpf_lru *lru, void *buf,
diff --git a/kernel/bpf/bpf_lru_list.h b/kernel/bpf/bpf_lru_list.h
index cbd8d3720c2b..fe2661a58ea9 100644
--- a/kernel/bpf/bpf_lru_list.h
+++ b/kernel/bpf/bpf_lru_list.h
@@ -58,6 +58,7 @@ struct bpf_lru {
del_from_htab_func del_from_htab;
void *del_arg;
unsigned int hash_offset;
+ unsigned int target_free;
unsigned int nr_scans;
bool percpu;
};
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 1d2cf898e21e..05fd64a371af 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -858,26 +858,37 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
EXPORT_SYMBOL_GPL(btf_type_by_id);
/*
- * Regular int is not a bit field and it must be either
- * u8/u16/u32/u64 or __int128.
+ * Check that the type @t is a regular int. This means that @t is not
+ * a bit field and it has the same size as either of u8/u16/u32/u64
+ * or __int128. If @expected_size is not zero, then size of @t should
+ * be the same. A caller should already have checked that the type @t
+ * is an integer.
*/
+static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size)
+{
+ u32 int_data = btf_type_int(t);
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+ return BITS_PER_BYTE_MASKED(nr_bits) == 0 &&
+ BTF_INT_OFFSET(int_data) == 0 &&
+ (nr_bytes <= 16 && is_power_of_2(nr_bytes)) &&
+ (expected_size == 0 || nr_bytes == expected_size);
+}
+
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u8 nr_bits, nr_bytes;
- u32 int_data;
+ return __btf_type_int_is_regular(t, 0);
+}
- int_data = btf_type_int(t);
- nr_bits = BTF_INT_BITS(int_data);
- nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
- if (BITS_PER_BYTE_MASKED(nr_bits) ||
- BTF_INT_OFFSET(int_data) ||
- (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
- nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
- nr_bytes != (2 * sizeof(u64)))) {
- return false;
- }
+bool btf_type_is_i32(const struct btf_type *t)
+{
+ return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4);
+}
- return true;
+bool btf_type_is_i64(const struct btf_type *t)
+{
+ return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8);
}
/*
@@ -3443,7 +3454,8 @@ btf_find_graph_root(const struct btf *btf, const struct btf_type *pt,
node_field_name = strstr(value_type, ":");
if (!node_field_name)
return -EINVAL;
- value_type = kstrndup(value_type, node_field_name - value_type, GFP_KERNEL | __GFP_NOWARN);
+ value_type = kstrndup(value_type, node_field_name - value_type,
+ GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!value_type)
return -ENOMEM;
id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT);
@@ -3958,7 +3970,7 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type
/* This needs to be kzalloc to zero out padding and unused fields, see
* comment in btf_record_equal.
*/
- rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL | __GFP_NOWARN);
+ rec = kzalloc(struct_size(rec, fields, cnt), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!rec)
return ERR_PTR(-ENOMEM);
@@ -9019,7 +9031,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
bpf_free_cands_from_cache(*cc);
*cc = NULL;
}
- new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL);
+ new_cands = kmemdup(cands, sizeof_cands(cands->cnt), GFP_KERNEL_ACCOUNT);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
@@ -9027,7 +9039,7 @@ static struct bpf_cand_cache *populate_cand_cache(struct bpf_cand_cache *cands,
/* strdup the name, since it will stay in cache.
* the cands->name points to strings in prog's BTF and the prog can be unloaded.
*/
- new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL);
+ new_cands->name = kmemdup_nul(cands->name, cands->name_len, GFP_KERNEL_ACCOUNT);
bpf_free_cands(cands);
if (!new_cands->name) {
kfree(new_cands);
@@ -9111,7 +9123,7 @@ bpf_core_add_cands(struct bpf_cand_cache *cands, const struct btf *targ_btf,
continue;
/* most of the time there is only one candidate for a given kind+name pair */
- new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL);
+ new_cands = kmalloc(sizeof_cands(cands->cnt + 1), GFP_KERNEL_ACCOUNT);
if (!new_cands) {
bpf_free_cands(cands);
return ERR_PTR(-ENOMEM);
@@ -9228,7 +9240,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
/* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
* into arrays of btf_ids of struct fields and array indices.
*/
- specs = kcalloc(3, sizeof(*specs), GFP_KERNEL);
+ specs = kcalloc(3, sizeof(*specs), GFP_KERNEL_ACCOUNT);
if (!specs)
return -ENOMEM;
@@ -9253,7 +9265,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
goto out;
}
if (cc->cnt) {
- cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL);
+ cands.cands = kcalloc(cc->cnt, sizeof(*cands.cands), GFP_KERNEL_ACCOUNT);
if (!cands.cands) {
err = -ENOMEM;
goto out;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 9122c39870bf..cd220e861d67 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -658,6 +658,116 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
return NULL;
}
+static struct bpf_link *bpf_get_anchor_link(u32 flags, u32 id_or_fd)
+{
+ struct bpf_link *link = ERR_PTR(-EINVAL);
+
+ if (flags & BPF_F_ID)
+ link = bpf_link_by_id(id_or_fd);
+ else if (id_or_fd)
+ link = bpf_link_get_from_fd(id_or_fd);
+ return link;
+}
+
+static struct bpf_prog *bpf_get_anchor_prog(u32 flags, u32 id_or_fd)
+{
+ struct bpf_prog *prog = ERR_PTR(-EINVAL);
+
+ if (flags & BPF_F_ID)
+ prog = bpf_prog_by_id(id_or_fd);
+ else if (id_or_fd)
+ prog = bpf_prog_get(id_or_fd);
+ return prog;
+}
+
+static struct bpf_prog_list *get_prog_list(struct hlist_head *progs, struct bpf_prog *prog,
+ struct bpf_cgroup_link *link, u32 flags, u32 id_or_fd)
+{
+ bool is_link = flags & BPF_F_LINK, is_id = flags & BPF_F_ID;
+ struct bpf_prog_list *pltmp, *pl = ERR_PTR(-EINVAL);
+ bool preorder = flags & BPF_F_PREORDER;
+ struct bpf_link *anchor_link = NULL;
+ struct bpf_prog *anchor_prog = NULL;
+ bool is_before, is_after;
+
+ is_before = flags & BPF_F_BEFORE;
+ is_after = flags & BPF_F_AFTER;
+ if (is_link || is_id || id_or_fd) {
+ /* flags must have either BPF_F_BEFORE or BPF_F_AFTER */
+ if (is_before == is_after)
+ return ERR_PTR(-EINVAL);
+ if ((is_link && !link) || (!is_link && !prog))
+ return ERR_PTR(-EINVAL);
+ } else if (!hlist_empty(progs)) {
+ /* flags cannot have both BPF_F_BEFORE and BPF_F_AFTER */
+ if (is_before && is_after)
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (is_link) {
+ anchor_link = bpf_get_anchor_link(flags, id_or_fd);
+ if (IS_ERR(anchor_link))
+ return ERR_PTR(PTR_ERR(anchor_link));
+ } else if (is_id || id_or_fd) {
+ anchor_prog = bpf_get_anchor_prog(flags, id_or_fd);
+ if (IS_ERR(anchor_prog))
+ return ERR_PTR(PTR_ERR(anchor_prog));
+ }
+
+ if (!anchor_prog && !anchor_link) {
+ /* if there is no anchor_prog/anchor_link, then BPF_F_PREORDER
+ * doesn't matter since either prepend or append to a combined
+ * list of progs will end up with correct result.
+ */
+ hlist_for_each_entry(pltmp, progs, node) {
+ if (is_before)
+ return pltmp;
+ if (pltmp->node.next)
+ continue;
+ return pltmp;
+ }
+ return NULL;
+ }
+
+ hlist_for_each_entry(pltmp, progs, node) {
+ if ((anchor_prog && anchor_prog == pltmp->prog) ||
+ (anchor_link && anchor_link == &pltmp->link->link)) {
+ if (!!(pltmp->flags & BPF_F_PREORDER) != preorder)
+ goto out;
+ pl = pltmp;
+ goto out;
+ }
+ }
+
+ pl = ERR_PTR(-ENOENT);
+out:
+ if (anchor_link)
+ bpf_link_put(anchor_link);
+ else
+ bpf_prog_put(anchor_prog);
+ return pl;
+}
+
+static int insert_pl_to_hlist(struct bpf_prog_list *pl, struct hlist_head *progs,
+ struct bpf_prog *prog, struct bpf_cgroup_link *link,
+ u32 flags, u32 id_or_fd)
+{
+ struct bpf_prog_list *pltmp;
+
+ pltmp = get_prog_list(progs, prog, link, flags, id_or_fd);
+ if (IS_ERR(pltmp))
+ return PTR_ERR(pltmp);
+
+ if (!pltmp)
+ hlist_add_head(&pl->node, progs);
+ else if (flags & BPF_F_BEFORE)
+ hlist_add_before(&pl->node, &pltmp->node);
+ else
+ hlist_add_behind(&pl->node, &pltmp->node);
+
+ return 0;
+}
+
/**
* __cgroup_bpf_attach() - Attach the program or the link to a cgroup, and
* propagate the change to descendants
@@ -667,6 +777,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
* @replace_prog: Previously attached program to replace if BPF_F_REPLACE is set
* @type: Type of attach operation
* @flags: Option flags
+ * @id_or_fd: Relative prog id or fd
+ * @revision: bpf_prog_list revision
*
* Exactly one of @prog or @link can be non-null.
* Must be called with cgroup_mutex held.
@@ -674,7 +786,8 @@ static struct bpf_prog_list *find_attach_entry(struct hlist_head *progs,
static int __cgroup_bpf_attach(struct cgroup *cgrp,
struct bpf_prog *prog, struct bpf_prog *replace_prog,
struct bpf_cgroup_link *link,
- enum bpf_attach_type type, u32 flags)
+ enum bpf_attach_type type, u32 flags, u32 id_or_fd,
+ u64 revision)
{
u32 saved_flags = (flags & (BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI));
struct bpf_prog *old_prog = NULL;
@@ -690,6 +803,9 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
((flags & BPF_F_REPLACE) && !(flags & BPF_F_ALLOW_MULTI)))
/* invalid combination */
return -EINVAL;
+ if ((flags & BPF_F_REPLACE) && (flags & (BPF_F_BEFORE | BPF_F_AFTER)))
+ /* only either replace or insertion with before/after */
+ return -EINVAL;
if (link && (prog || replace_prog))
/* only either link or prog/replace_prog can be specified */
return -EINVAL;
@@ -700,6 +816,8 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
atype = bpf_cgroup_atype_find(type, new_prog->aux->attach_btf_id);
if (atype < 0)
return -EINVAL;
+ if (revision && revision != cgrp->bpf.revisions[atype])
+ return -ESTALE;
progs = &cgrp->bpf.progs[atype];
@@ -728,22 +846,18 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
if (pl) {
old_prog = pl->prog;
} else {
- struct hlist_node *last = NULL;
-
pl = kmalloc(sizeof(*pl), GFP_KERNEL);
if (!pl) {
bpf_cgroup_storages_free(new_storage);
return -ENOMEM;
}
- if (hlist_empty(progs))
- hlist_add_head(&pl->node, progs);
- else
- hlist_for_each(last, progs) {
- if (last->next)
- continue;
- hlist_add_behind(&pl->node, last);
- break;
- }
+
+ err = insert_pl_to_hlist(pl, progs, prog, link, flags, id_or_fd);
+ if (err) {
+ kfree(pl);
+ bpf_cgroup_storages_free(new_storage);
+ return err;
+ }
}
pl->prog = prog;
@@ -762,6 +876,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
if (err)
goto cleanup_trampoline;
+ cgrp->bpf.revisions[atype] += 1;
if (old_prog) {
if (type == BPF_LSM_CGROUP)
bpf_trampoline_unlink_cgroup_shim(old_prog);
@@ -793,12 +908,13 @@ static int cgroup_bpf_attach(struct cgroup *cgrp,
struct bpf_prog *prog, struct bpf_prog *replace_prog,
struct bpf_cgroup_link *link,
enum bpf_attach_type type,
- u32 flags)
+ u32 flags, u32 id_or_fd, u64 revision)
{
int ret;
cgroup_lock();
- ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags);
+ ret = __cgroup_bpf_attach(cgrp, prog, replace_prog, link, type, flags,
+ id_or_fd, revision);
cgroup_unlock();
return ret;
}
@@ -886,6 +1002,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp,
if (!found)
return -ENOENT;
+ cgrp->bpf.revisions[atype] += 1;
old_prog = xchg(&link->link.prog, new_prog);
replace_effective_prog(cgrp, atype, link);
bpf_prog_put(old_prog);
@@ -1011,12 +1128,14 @@ found:
* @prog: A program to detach or NULL
* @link: A link to detach or NULL
* @type: Type of detach operation
+ * @revision: bpf_prog_list revision
*
* At most one of @prog or @link can be non-NULL.
* Must be called with cgroup_mutex held.
*/
static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
- struct bpf_cgroup_link *link, enum bpf_attach_type type)
+ struct bpf_cgroup_link *link, enum bpf_attach_type type,
+ u64 revision)
{
enum cgroup_bpf_attach_type atype;
struct bpf_prog *old_prog;
@@ -1034,6 +1153,9 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
if (atype < 0)
return -EINVAL;
+ if (revision && revision != cgrp->bpf.revisions[atype])
+ return -ESTALE;
+
progs = &cgrp->bpf.progs[atype];
flags = cgrp->bpf.flags[atype];
@@ -1059,6 +1181,7 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
/* now can actually delete it from this cgroup list */
hlist_del(&pl->node);
+ cgrp->bpf.revisions[atype] += 1;
kfree(pl);
if (hlist_empty(progs))
@@ -1074,12 +1197,12 @@ static int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
}
static int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
- enum bpf_attach_type type)
+ enum bpf_attach_type type, u64 revision)
{
int ret;
cgroup_lock();
- ret = __cgroup_bpf_detach(cgrp, prog, NULL, type);
+ ret = __cgroup_bpf_detach(cgrp, prog, NULL, type, revision);
cgroup_unlock();
return ret;
}
@@ -1097,6 +1220,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
struct bpf_prog_array *effective;
int cnt, ret = 0, i;
int total_cnt = 0;
+ u64 revision = 0;
u32 flags;
if (effective_query && prog_attach_flags)
@@ -1134,6 +1258,10 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return -EFAULT;
if (copy_to_user(&uattr->query.prog_cnt, &total_cnt, sizeof(total_cnt)))
return -EFAULT;
+ if (!effective_query && from_atype == to_atype)
+ revision = cgrp->bpf.revisions[from_atype];
+ if (copy_to_user(&uattr->query.revision, &revision, sizeof(revision)))
+ return -EFAULT;
if (attr->query.prog_cnt == 0 || !prog_ids || !total_cnt)
/* return early if user requested only program count + flags */
return 0;
@@ -1216,7 +1344,8 @@ int cgroup_bpf_prog_attach(const union bpf_attr *attr,
}
ret = cgroup_bpf_attach(cgrp, prog, replace_prog, NULL,
- attr->attach_type, attr->attach_flags);
+ attr->attach_type, attr->attach_flags,
+ attr->relative_fd, attr->expected_revision);
if (replace_prog)
bpf_prog_put(replace_prog);
@@ -1238,7 +1367,7 @@ int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
if (IS_ERR(prog))
prog = NULL;
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type);
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, attr->expected_revision);
if (prog)
bpf_prog_put(prog);
@@ -1267,7 +1396,7 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
}
WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
- cg_link->type));
+ cg_link->type, 0));
if (cg_link->type == BPF_LSM_CGROUP)
bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog);
@@ -1339,6 +1468,13 @@ static const struct bpf_link_ops bpf_cgroup_link_lops = {
.fill_link_info = bpf_cgroup_link_fill_link_info,
};
+#define BPF_F_LINK_ATTACH_MASK \
+ (BPF_F_ID | \
+ BPF_F_BEFORE | \
+ BPF_F_AFTER | \
+ BPF_F_PREORDER | \
+ BPF_F_LINK)
+
int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
{
struct bpf_link_primer link_primer;
@@ -1346,7 +1482,7 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
struct cgroup *cgrp;
int err;
- if (attr->link_create.flags)
+ if (attr->link_create.flags & (~BPF_F_LINK_ATTACH_MASK))
return -EINVAL;
cgrp = cgroup_get_from_fd(attr->link_create.target_fd);
@@ -1370,7 +1506,9 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
}
err = cgroup_bpf_attach(cgrp, NULL, NULL, link,
- link->type, BPF_F_ALLOW_MULTI);
+ link->type, BPF_F_ALLOW_MULTI | attr->link_create.flags,
+ attr->link_create.cgroup.relative_fd,
+ attr->link_create.cgroup.expected_revision);
if (err) {
bpf_link_cleanup(&link_primer);
goto out_put_cgroup;
@@ -2134,7 +2272,7 @@ static const struct bpf_func_proto bpf_sysctl_get_name_proto = {
.gpl_only = false,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_CTX,
- .arg2_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_PTR_TO_MEM | MEM_WRITE,
.arg3_type = ARG_CONST_SIZE,
.arg4_type = ARG_ANYTHING,
};
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c20babbf998f..e536a34a32c8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2102,14 +2102,15 @@ out:
#undef COND_JMP
/* ST, STX and LDX*/
ST_NOSPEC:
- /* Speculation barrier for mitigating Speculative Store Bypass.
- * In case of arm64, we rely on the firmware mitigation as
- * controlled via the ssbd kernel parameter. Whenever the
- * mitigation is enabled, it works for all of the kernel code
- * with no need to provide any additional instructions here.
- * In case of x86, we use 'lfence' insn for mitigation. We
- * reuse preexisting logic from Spectre v1 mitigation that
- * happens to produce the required code on x86 for v4 as well.
+ /* Speculation barrier for mitigating Speculative Store Bypass,
+ * Bounds-Check Bypass and Type Confusion. In case of arm64, we
+ * rely on the firmware mitigation as controlled via the ssbd
+ * kernel parameter. Whenever the mitigation is enabled, it
+ * works for all of the kernel code with no need to provide any
+ * additional instructions here. In case of x86, we use 'lfence'
+ * insn for mitigation. We reuse preexisting logic from Spectre
+ * v1 mitigation that happens to produce the required code on
+ * x86 for v4 as well.
*/
barrier_nospec();
CONT;
@@ -3034,6 +3035,21 @@ bool __weak bpf_jit_needs_zext(void)
return false;
}
+/* By default, enable the verifier's mitigations against Spectre v1 and v4 for
+ * all archs. The value returned must not change at runtime as there is
+ * currently no support for reloading programs that were loaded without
+ * mitigations.
+ */
+bool __weak bpf_jit_bypass_spec_v1(void)
+{
+ return false;
+}
+
+bool __weak bpf_jit_bypass_spec_v4(void)
+{
+ return false;
+}
+
/* Return true if the JIT inlines the call to the helper corresponding to
* the imm.
*
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 9ff1b4090289..6d051416c184 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -24,6 +24,7 @@
#include <linux/bpf_mem_alloc.h>
#include <linux/kasan.h>
#include <linux/bpf_verifier.h>
+#include <linux/uaccess.h>
#include "../../lib/kstrtox.h"
@@ -3278,6 +3279,376 @@ __bpf_kfunc void __bpf_trap(void)
{
}
+/*
+ * Kfuncs for string operations.
+ *
+ * Since strings are not necessarily %NUL-terminated, we cannot directly call
+ * in-kernel implementations. Instead, we open-code the implementations using
+ * __get_kernel_nofault instead of plain dereference to make them safe.
+ */
+
+/**
+ * bpf_strcmp - Compare two strings
+ * @s1__ign: One string
+ * @s2__ign: Another string
+ *
+ * Return:
+ * * %0 - Strings are equal
+ * * %-1 - @s1__ign is smaller
+ * * %1 - @s2__ign is smaller
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of strings is too large
+ * * %-ERANGE - One of strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcmp(const char *s1__ign, const char *s2__ign)
+{
+ char c1, c2;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s1__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(s2__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c1, s1__ign, char, err_out);
+ __get_kernel_nofault(&c2, s2__ign, char, err_out);
+ if (c1 != c2)
+ return c1 < c2 ? -1 : 1;
+ if (c1 == '\0')
+ return 0;
+ s1__ign++;
+ s2__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnchr - Find a character in a length limited string
+ * @s__ign: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in the first @count characters of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnchr(const char *s__ign, size_t count, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ return i;
+ if (sc == '\0')
+ return -ENOENT;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : -ENOENT;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strchr - Find the first occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Note that the %NUL-terminator is considered part of the string, and can
+ * be searched for.
+ *
+ * Return:
+ * * >=0 - The index of the first occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchr(const char *s__ign, char c)
+{
+ return bpf_strnchr(s__ign, XATTR_SIZE_MAX, c);
+}
+
+/**
+ * bpf_strchrnul - Find and return a character in a string, or end of string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the first occurrence of @c within @s__ign or index of
+ * the null byte at the end of @s__ign when @c is not found
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strchrnul(const char *s__ign, char c)
+{
+ char sc;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == '\0' || sc == c)
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strrchr - Find the last occurrence of a character in a string
+ * @s__ign: The string to be searched
+ * @c: The character to search for
+ *
+ * Return:
+ * * >=0 - Index of the last occurrence of @c within @s__ign
+ * * %-ENOENT - @c not found in @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strrchr(const char *s__ign, int c)
+{
+ char sc;
+ int i, last = -ENOENT;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&sc, s__ign, char, err_out);
+ if (sc == c)
+ last = i;
+ if (sc == '\0')
+ return last;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strlen - Calculate the length of a length-limited string
+ * @s__ign: The string
+ * @count: The maximum number of characters to count
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnlen(const char *s__ign, size_t count)
+{
+ char c;
+ int i;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1))
+ return -ERANGE;
+
+ guard(pagefault)();
+ for (i = 0; i < count && i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&c, s__ign, char, err_out);
+ if (c == '\0')
+ return i;
+ s__ign++;
+ }
+ return i == XATTR_SIZE_MAX ? -E2BIG : i;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strlen - Calculate the length of a string
+ * @s__ign: The string
+ *
+ * Return:
+ * * >=0 - The length of @s__ign
+ * * %-EFAULT - Cannot read @s__ign
+ * * %-E2BIG - @s__ign is too large
+ * * %-ERANGE - @s__ign is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strlen(const char *s__ign)
+{
+ return bpf_strnlen(s__ign, XATTR_SIZE_MAX);
+}
+
+/**
+ * bpf_strspn - Calculate the length of the initial substring of @s__ign which
+ * only contains letters in @accept__ign
+ * @s__ign: The string to be searched
+ * @accept__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which only
+ * contains letters from @accept__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strspn(const char *s__ign, const char *accept__ign)
+{
+ char cs, ca;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(accept__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&ca, accept__ign + j, char, err_out);
+ if (cs == ca || ca == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (ca == '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * strcspn - Calculate the length of the initial substring of @s__ign which
+ * does not contain letters in @reject__ign
+ * @s__ign: The string to be searched
+ * @reject__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - The length of the initial substring of @s__ign which does not
+ * contain letters from @reject__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strcspn(const char *s__ign, const char *reject__ign)
+{
+ char cs, cr;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(reject__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ __get_kernel_nofault(&cs, s__ign, char, err_out);
+ if (cs == '\0')
+ return i;
+ for (j = 0; j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&cr, reject__ign + j, char, err_out);
+ if (cs == cr || cr == '\0')
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (cr != '\0')
+ return i;
+ s__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strnstr - Find the first substring in a length-limited string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ * @len: the maximum number of characters to search
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within the first @len characters of @s1__ign
+ * * %-ENOENT - @s2__ign not found in the first @len characters of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strnstr(const char *s1__ign, const char *s2__ign, size_t len)
+{
+ char c1, c2;
+ int i, j;
+
+ if (!copy_from_kernel_nofault_allowed(s1__ign, 1) ||
+ !copy_from_kernel_nofault_allowed(s2__ign, 1)) {
+ return -ERANGE;
+ }
+
+ guard(pagefault)();
+ for (i = 0; i < XATTR_SIZE_MAX; i++) {
+ for (j = 0; i + j < len && j < XATTR_SIZE_MAX; j++) {
+ __get_kernel_nofault(&c2, s2__ign + j, char, err_out);
+ if (c2 == '\0')
+ return i;
+ __get_kernel_nofault(&c1, s1__ign + j, char, err_out);
+ if (c1 == '\0')
+ return -ENOENT;
+ if (c1 != c2)
+ break;
+ }
+ if (j == XATTR_SIZE_MAX)
+ return -E2BIG;
+ if (i + j == len)
+ return -ENOENT;
+ s1__ign++;
+ }
+ return -E2BIG;
+err_out:
+ return -EFAULT;
+}
+
+/**
+ * bpf_strstr - Find the first substring in a string
+ * @s1__ign: The string to be searched
+ * @s2__ign: The string to search for
+ *
+ * Return:
+ * * >=0 - Index of the first character of the first occurrence of @s2__ign
+ * within @s1__ign
+ * * %-ENOENT - @s2__ign is not a substring of @s1__ign
+ * * %-EFAULT - Cannot read one of the strings
+ * * %-E2BIG - One of the strings is too large
+ * * %-ERANGE - One of the strings is outside of kernel address space
+ */
+__bpf_kfunc int bpf_strstr(const char *s1__ign, const char *s2__ign)
+{
+ return bpf_strnstr(s1__ign, s2__ign, XATTR_SIZE_MAX);
+}
+
__bpf_kfunc_end_defs();
BTF_KFUNCS_START(generic_btf_ids)
@@ -3397,6 +3768,17 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPAB
BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)
#endif
BTF_ID_FLAGS(func, __bpf_trap)
+BTF_ID_FLAGS(func, bpf_strcmp);
+BTF_ID_FLAGS(func, bpf_strchr);
+BTF_ID_FLAGS(func, bpf_strchrnul);
+BTF_ID_FLAGS(func, bpf_strnchr);
+BTF_ID_FLAGS(func, bpf_strrchr);
+BTF_ID_FLAGS(func, bpf_strlen);
+BTF_ID_FLAGS(func, bpf_strnlen);
+BTF_ID_FLAGS(func, bpf_strspn);
+BTF_ID_FLAGS(func, bpf_strcspn);
+BTF_ID_FLAGS(func, bpf_strstr);
+BTF_ID_FLAGS(func, bpf_strnstr);
#ifdef CONFIG_CGROUPS
BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)
#endif
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 3969eb0382af..632d51b05fe9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -394,17 +394,10 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
return -EINVAL;
} else {
- u32 int_data;
-
/*
* Key is expected to be u64, which stores the cgroup_inode_id
*/
-
- if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
- return -EINVAL;
-
- int_data = *(u32 *)(key_type + 1);
- if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data))
+ if (!btf_type_is_i64(key_type))
return -EINVAL;
}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index dd5304c6ac3c..56500381c28a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3403,10 +3403,12 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
seq_printf(seq,
"attach_type:\t%d\n"
"target_obj_id:\t%u\n"
- "target_btf_id:\t%u\n",
+ "target_btf_id:\t%u\n"
+ "cookie:\t%llu\n",
tr_link->attach_type,
target_obj_id,
- target_btf_id);
+ target_btf_id,
+ tr_link->link.cookie);
}
static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
@@ -3416,6 +3418,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
container_of(link, struct bpf_tracing_link, link.link);
info->tracing.attach_type = tr_link->attach_type;
+ info->tracing.cookie = tr_link->link.cookie;
bpf_trampoline_unpack_key(tr_link->trampoline->key,
&info->tracing.target_obj_id,
&info->tracing.target_btf_id);
@@ -3651,8 +3654,10 @@ static void bpf_raw_tp_link_show_fdinfo(const struct bpf_link *link,
container_of(link, struct bpf_raw_tp_link, link);
seq_printf(seq,
- "tp_name:\t%s\n",
- raw_tp_link->btp->tp->name);
+ "tp_name:\t%s\n"
+ "cookie:\t%llu\n",
+ raw_tp_link->btp->tp->name,
+ raw_tp_link->cookie);
}
static int bpf_copy_to_user(char __user *ubuf, const char *buf, u32 ulen,
@@ -3688,6 +3693,7 @@ static int bpf_raw_tp_link_fill_link_info(const struct bpf_link *link,
return -EINVAL;
info->raw_tracepoint.tp_name_len = tp_len + 1;
+ info->raw_tracepoint.cookie = raw_tp_link->cookie;
if (!ubuf)
return 0;
@@ -3794,6 +3800,32 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event,
info->perf_event.kprobe.cookie = event->bpf_cookie;
return 0;
}
+
+static void bpf_perf_link_fdinfo_kprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, addr;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &addr, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "missed:\t%lu\n"
+ "addr:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, missed, addr,
+ type == BPF_FD_TYPE_KRETPROBE ? "kretprobe" : "kprobe",
+ event->bpf_cookie);
+}
#endif
#ifdef CONFIG_UPROBE_EVENTS
@@ -3822,6 +3854,31 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event,
info->perf_event.uprobe.ref_ctr_offset = ref_ctr_offset;
return 0;
}
+
+static void bpf_perf_link_fdinfo_uprobe(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ const char *name;
+ int err;
+ u32 prog_id, type;
+ u64 offset, ref_ctr_offset;
+ unsigned long missed;
+
+ err = bpf_get_perf_event_info(event, &prog_id, &type, &name,
+ &offset, &ref_ctr_offset, &missed);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "name:\t%s\n"
+ "offset:\t%#llx\n"
+ "ref_ctr_offset:\t%#llx\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, offset, ref_ctr_offset,
+ type == BPF_FD_TYPE_URETPROBE ? "uretprobe" : "uprobe",
+ event->bpf_cookie);
+}
#endif
static int bpf_perf_link_fill_probe(const struct perf_event *event,
@@ -3890,10 +3947,79 @@ static int bpf_perf_link_fill_link_info(const struct bpf_link *link,
}
}
+static void bpf_perf_event_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ seq_printf(seq,
+ "type:\t%u\n"
+ "config:\t%llu\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ event->attr.type, event->attr.config,
+ "event", event->bpf_cookie);
+}
+
+static void bpf_tracepoint_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+ int err;
+ const char *name;
+ u32 prog_id;
+
+ err = bpf_get_perf_event_info(event, &prog_id, NULL, &name, NULL,
+ NULL, NULL);
+ if (err)
+ return;
+
+ seq_printf(seq,
+ "tp_name:\t%s\n"
+ "event_type:\t%s\n"
+ "cookie:\t%llu\n",
+ name, "tracepoint", event->bpf_cookie);
+}
+
+static void bpf_probe_link_show_fdinfo(const struct perf_event *event,
+ struct seq_file *seq)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_KPROBE)
+ return bpf_perf_link_fdinfo_kprobe(event, seq);
+#endif
+
+#ifdef CONFIG_UPROBE_EVENTS
+ if (event->tp_event->flags & TRACE_EVENT_FL_UPROBE)
+ return bpf_perf_link_fdinfo_uprobe(event, seq);
+#endif
+}
+
+static void bpf_perf_link_show_fdinfo(const struct bpf_link *link,
+ struct seq_file *seq)
+{
+ struct bpf_perf_link *perf_link;
+ const struct perf_event *event;
+
+ perf_link = container_of(link, struct bpf_perf_link, link);
+ event = perf_get_event(perf_link->perf_file);
+ if (IS_ERR(event))
+ return;
+
+ switch (event->prog->type) {
+ case BPF_PROG_TYPE_PERF_EVENT:
+ return bpf_perf_event_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_TRACEPOINT:
+ return bpf_tracepoint_link_show_fdinfo(event, seq);
+ case BPF_PROG_TYPE_KPROBE:
+ return bpf_probe_link_show_fdinfo(event, seq);
+ default:
+ return;
+ }
+}
+
static const struct bpf_link_ops bpf_perf_link_lops = {
.release = bpf_perf_link_release,
.dealloc = bpf_perf_link_dealloc,
.fill_link_info = bpf_perf_link_fill_link_info,
+ .show_fdinfo = bpf_perf_link_show_fdinfo,
};
static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -4185,6 +4311,25 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
}
}
+static bool is_cgroup_prog_type(enum bpf_prog_type ptype, enum bpf_attach_type atype,
+ bool check_atype)
+{
+ switch (ptype) {
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ return true;
+ case BPF_PROG_TYPE_LSM:
+ return check_atype ? atype == BPF_LSM_CGROUP : true;
+ default:
+ return false;
+ }
+}
+
#define BPF_PROG_ATTACH_LAST_FIELD expected_revision
#define BPF_F_ATTACH_MASK_BASE \
@@ -4215,6 +4360,9 @@ static int bpf_prog_attach(const union bpf_attr *attr)
if (bpf_mprog_supported(ptype)) {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_MPROG)
return -EINVAL;
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags & ~(BPF_F_ATTACH_MASK_BASE | BPF_F_ATTACH_MASK_MPROG))
+ return -EINVAL;
} else {
if (attr->attach_flags & ~BPF_F_ATTACH_MASK_BASE)
return -EINVAL;
@@ -4232,6 +4380,11 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
+ if (is_cgroup_prog_type(ptype, prog->expected_attach_type, true)) {
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
+ goto out;
+ }
+
switch (ptype) {
case BPF_PROG_TYPE_SK_SKB:
case BPF_PROG_TYPE_SK_MSG:
@@ -4243,20 +4396,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
case BPF_PROG_TYPE_FLOW_DISSECTOR:
ret = netns_bpf_prog_attach(attr, prog);
break;
- case BPF_PROG_TYPE_CGROUP_DEVICE:
- case BPF_PROG_TYPE_CGROUP_SKB:
- case BPF_PROG_TYPE_CGROUP_SOCK:
- case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
- case BPF_PROG_TYPE_CGROUP_SOCKOPT:
- case BPF_PROG_TYPE_CGROUP_SYSCTL:
- case BPF_PROG_TYPE_SOCK_OPS:
- case BPF_PROG_TYPE_LSM:
- if (ptype == BPF_PROG_TYPE_LSM &&
- prog->expected_attach_type != BPF_LSM_CGROUP)
- ret = -EINVAL;
- else
- ret = cgroup_bpf_prog_attach(attr, ptype, prog);
- break;
case BPF_PROG_TYPE_SCHED_CLS:
if (attr->attach_type == BPF_TCX_INGRESS ||
attr->attach_type == BPF_TCX_EGRESS)
@@ -4267,7 +4406,7 @@ static int bpf_prog_attach(const union bpf_attr *attr)
default:
ret = -EINVAL;
}
-
+out:
if (ret)
bpf_prog_put(prog);
return ret;
@@ -4295,6 +4434,9 @@ static int bpf_prog_detach(const union bpf_attr *attr)
if (IS_ERR(prog))
return PTR_ERR(prog);
}
+ } else if (is_cgroup_prog_type(ptype, 0, false)) {
+ if (attr->attach_flags || attr->relative_fd)
+ return -EINVAL;
} else if (attr->attach_flags ||
attr->relative_fd ||
attr->expected_revision) {
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 9dbc31b25e3d..fa353c5d550f 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -83,6 +83,11 @@ struct tnum tnum_sub(struct tnum a, struct tnum b)
return TNUM(dv & ~mu, mu);
}
+struct tnum tnum_neg(struct tnum a)
+{
+ return tnum_sub(TNUM(0, 0), a);
+}
+
struct tnum tnum_and(struct tnum a, struct tnum b)
{
u64 alpha, beta, v;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index c4b1a98ff726..b1e358c16eeb 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -911,27 +911,32 @@ static u64 notrace __bpf_prog_enter_recur(struct bpf_prog *prog, struct bpf_tram
return bpf_prog_start_time();
}
-static void notrace update_prog_stats(struct bpf_prog *prog,
- u64 start)
+static void notrace __update_prog_stats(struct bpf_prog *prog, u64 start)
{
struct bpf_prog_stats *stats;
+ unsigned long flags;
+ u64 duration;
- if (static_branch_unlikely(&bpf_stats_enabled_key) &&
- /* static_key could be enabled in __bpf_prog_enter*
- * and disabled in __bpf_prog_exit*.
- * And vice versa.
- * Hence check that 'start' is valid.
- */
- start > NO_START_TIME) {
- u64 duration = sched_clock() - start;
- unsigned long flags;
-
- stats = this_cpu_ptr(prog->stats);
- flags = u64_stats_update_begin_irqsave(&stats->syncp);
- u64_stats_inc(&stats->cnt);
- u64_stats_add(&stats->nsecs, duration);
- u64_stats_update_end_irqrestore(&stats->syncp, flags);
- }
+ /*
+ * static_key could be enabled in __bpf_prog_enter* and disabled in
+ * __bpf_prog_exit*. And vice versa. Check that 'start' is valid.
+ */
+ if (start <= NO_START_TIME)
+ return;
+
+ duration = sched_clock() - start;
+ stats = this_cpu_ptr(prog->stats);
+ flags = u64_stats_update_begin_irqsave(&stats->syncp);
+ u64_stats_inc(&stats->cnt);
+ u64_stats_add(&stats->nsecs, duration);
+ u64_stats_update_end_irqrestore(&stats->syncp, flags);
+}
+
+static __always_inline void notrace update_prog_stats(struct bpf_prog *prog,
+ u64 start)
+{
+ if (static_branch_unlikely(&bpf_stats_enabled_key))
+ __update_prog_stats(prog, start);
}
static void notrace __bpf_prog_exit_recur(struct bpf_prog *prog, u64 start,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index db01bf51c792..90e688f81a48 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -44,6 +44,11 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#undef BPF_LINK_TYPE
};
+enum bpf_features {
+ BPF_FEAT_RDONLY_CAST_TO_VOID = 0,
+ __MAX_BPF_FEAT,
+};
+
struct bpf_mem_alloc bpf_global_percpu_ma;
static bool bpf_global_percpu_ma_set;
@@ -405,7 +410,8 @@ static bool reg_not_null(const struct bpf_reg_state *reg)
type == PTR_TO_MAP_KEY ||
type == PTR_TO_SOCK_COMMON ||
(type == PTR_TO_BTF_ID && is_trusted_reg(reg)) ||
- type == PTR_TO_MEM;
+ type == PTR_TO_MEM ||
+ type == CONST_PTR_TO_MAP;
}
static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
@@ -1403,7 +1409,7 @@ static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size)
goto out;
alloc_size = kmalloc_size_roundup(size_mul(new_n, size));
- new_arr = krealloc(arr, alloc_size, GFP_KERNEL);
+ new_arr = krealloc(arr, alloc_size, GFP_KERNEL_ACCOUNT);
if (!new_arr) {
kfree(arr);
return NULL;
@@ -1420,7 +1426,7 @@ out:
static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src)
{
dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs,
- sizeof(struct bpf_reference_state), GFP_KERNEL);
+ sizeof(struct bpf_reference_state), GFP_KERNEL_ACCOUNT);
if (!dst->refs)
return -ENOMEM;
@@ -1439,7 +1445,7 @@ static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_st
size_t n = src->allocated_stack / BPF_REG_SIZE;
dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!dst->stack)
return -ENOMEM;
@@ -1647,7 +1653,7 @@ static void update_peak_states(struct bpf_verifier_env *env)
{
u32 cur_states;
- cur_states = env->explored_states_size + env->free_list_size;
+ cur_states = env->explored_states_size + env->free_list_size + env->num_backedges;
env->peak_states = max(env->peak_states, cur_states);
}
@@ -1659,6 +1665,13 @@ static void free_func_state(struct bpf_func_state *state)
kfree(state);
}
+static void clear_jmp_history(struct bpf_verifier_state *state)
+{
+ kfree(state->jmp_history);
+ state->jmp_history = NULL;
+ state->jmp_history_cnt = 0;
+}
+
static void free_verifier_state(struct bpf_verifier_state *state,
bool free_self)
{
@@ -1669,11 +1682,12 @@ static void free_verifier_state(struct bpf_verifier_state *state,
state->frame[i] = NULL;
}
kfree(state->refs);
+ clear_jmp_history(state);
if (free_self)
kfree(state);
}
-/* struct bpf_verifier_state->{parent,loop_entry} refer to states
+/* struct bpf_verifier_state->parent refers to states
* that are in either of env->{expored_states,free_list}.
* In both cases the state is contained in struct bpf_verifier_state_list.
*/
@@ -1684,37 +1698,24 @@ static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_
return NULL;
}
-static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verifier_state *st)
-{
- if (st->loop_entry)
- return container_of(st->loop_entry, struct bpf_verifier_state_list, state);
- return NULL;
-}
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st);
/* A state can be freed if it is no longer referenced:
* - is in the env->free_list;
* - has no children states;
- * - is not used as loop_entry.
- *
- * Freeing a state can make it's loop_entry free-able.
*/
static void maybe_free_verifier_state(struct bpf_verifier_env *env,
struct bpf_verifier_state_list *sl)
{
- struct bpf_verifier_state_list *loop_entry_sl;
-
- while (sl && sl->in_free_list &&
- sl->state.branches == 0 &&
- sl->state.used_as_loop_entry == 0) {
- loop_entry_sl = state_loop_entry_as_list(&sl->state);
- if (loop_entry_sl)
- loop_entry_sl->state.used_as_loop_entry--;
- list_del(&sl->node);
- free_verifier_state(&sl->state, false);
- kfree(sl);
- env->free_list_size--;
- sl = loop_entry_sl;
- }
+ if (!sl->in_free_list
+ || sl->state.branches != 0
+ || incomplete_read_marks(env, &sl->state))
+ return;
+ list_del(&sl->node);
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ env->free_list_size--;
}
/* copy verifier state from src to dst growing dst stack space
@@ -1733,6 +1734,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
struct bpf_func_state *dst;
int i, err;
+ dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
+ src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+ GFP_KERNEL_ACCOUNT);
+ if (!dst_state->jmp_history)
+ return -ENOMEM;
+ dst_state->jmp_history_cnt = src->jmp_history_cnt;
+
/* if dst has more stack frames then src frame, free them, this is also
* necessary in case of exceptional exits using bpf_throw.
*/
@@ -1750,17 +1758,14 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
dst_state->parent = src->parent;
dst_state->first_insn_idx = src->first_insn_idx;
dst_state->last_insn_idx = src->last_insn_idx;
- dst_state->insn_hist_start = src->insn_hist_start;
- dst_state->insn_hist_end = src->insn_hist_end;
dst_state->dfs_depth = src->dfs_depth;
dst_state->callback_unroll_depth = src->callback_unroll_depth;
- dst_state->used_as_loop_entry = src->used_as_loop_entry;
dst_state->may_goto_depth = src->may_goto_depth;
- dst_state->loop_entry = src->loop_entry;
+ dst_state->equal_state = src->equal_state;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
- dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ dst = kzalloc(sizeof(*dst), GFP_KERNEL_ACCOUNT);
if (!dst)
return -ENOMEM;
dst_state->frame[i] = dst;
@@ -1799,173 +1804,232 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta
return true;
}
-/* Open coded iterators allow back-edges in the state graph in order to
- * check unbounded loops that iterators.
- *
- * In is_state_visited() it is necessary to know if explored states are
- * part of some loops in order to decide whether non-exact states
- * comparison could be used:
- * - non-exact states comparison establishes sub-state relation and uses
- * read and precision marks to do so, these marks are propagated from
- * children states and thus are not guaranteed to be final in a loop;
- * - exact states comparison just checks if current and explored states
- * are identical (and thus form a back-edge).
- *
- * Paper "A New Algorithm for Identifying Loops in Decompilation"
- * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient
- * algorithm for loop structure detection and gives an overview of
- * relevant terminology. It also has helpful illustrations.
- *
- * [1] https://api.semanticscholar.org/CorpusID:15784067
- *
- * We use a similar algorithm but because loop nested structure is
- * irrelevant for verifier ours is significantly simpler and resembles
- * strongly connected components algorithm from Sedgewick's textbook.
- *
- * Define topmost loop entry as a first node of the loop traversed in a
- * depth first search starting from initial state. The goal of the loop
- * tracking algorithm is to associate topmost loop entries with states
- * derived from these entries.
- *
- * For each step in the DFS states traversal algorithm needs to identify
- * the following situations:
- *
- * initial initial initial
- * | | |
- * V V V
- * ... ... .---------> hdr
- * | | | |
- * V V | V
- * cur .-> succ | .------...
- * | | | | | |
- * V | V | V V
- * succ '-- cur | ... ...
- * | | |
- * | V V
- * | succ <- cur
- * | |
- * | V
- * | ...
- * | |
- * '----'
- *
- * (A) successor state of cur (B) successor state of cur or it's entry
- * not yet traversed are in current DFS path, thus cur and succ
- * are members of the same outermost loop
- *
- * initial initial
- * | |
- * V V
- * ... ...
- * | |
- * V V
- * .------... .------...
- * | | | |
- * V V V V
- * .-> hdr ... ... ...
- * | | | | |
- * | V V V V
- * | succ <- cur succ <- cur
- * | | |
- * | V V
- * | ... ...
- * | | |
- * '----' exit
- *
- * (C) successor state of cur is a part of some loop but this loop
- * does not include cur or successor state is not in a loop at all.
- *
- * Algorithm could be described as the following python code:
- *
- * traversed = set() # Set of traversed nodes
- * entries = {} # Mapping from node to loop entry
- * depths = {} # Depth level assigned to graph node
- * path = set() # Current DFS path
- *
- * # Find outermost loop entry known for n
- * def get_loop_entry(n):
- * h = entries.get(n, None)
- * while h in entries:
- * h = entries[h]
- * return h
- *
- * # Update n's loop entry if h comes before n in current DFS path.
- * def update_loop_entry(n, h):
- * if h in path and depths[entries.get(n, n)] < depths[n]:
- * entries[n] = h1
+/* Return IP for a given frame in a call stack */
+static u32 frame_insn_idx(struct bpf_verifier_state *st, u32 frame)
+{
+ return frame == st->curframe
+ ? st->insn_idx
+ : st->frame[frame + 1]->callsite;
+}
+
+/* For state @st look for a topmost frame with frame_insn_idx() in some SCC,
+ * if such frame exists form a corresponding @callchain as an array of
+ * call sites leading to this frame and SCC id.
+ * E.g.:
*
- * def dfs(n, depth):
- * traversed.add(n)
- * path.add(n)
- * depths[n] = depth
- * for succ in G.successors(n):
- * if succ not in traversed:
- * # Case A: explore succ and update cur's loop entry
- * # only if succ's entry is in current DFS path.
- * dfs(succ, depth + 1)
- * h = entries.get(succ, None)
- * update_loop_entry(n, h)
- * else:
- * # Case B or C depending on `h1 in path` check in update_loop_entry().
- * update_loop_entry(n, succ)
- * path.remove(n)
+ * void foo() { A: loop {... SCC#1 ...}; }
+ * void bar() { B: loop { C: foo(); ... SCC#2 ... }
+ * D: loop { E: foo(); ... SCC#3 ... } }
+ * void main() { F: bar(); }
*
- * To adapt this algorithm for use with verifier:
- * - use st->branch == 0 as a signal that DFS of succ had been finished
- * and cur's loop entry has to be updated (case A), handle this in
- * update_branch_counts();
- * - use st->branch > 0 as a signal that st is in the current DFS path;
- * - handle cases B and C in is_state_visited().
+ * @callchain at (A) would be either (F,SCC#2) or (F,SCC#3) depending
+ * on @st frame call sites being (F,C,A) or (F,E,A).
*/
-static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_env *env,
- struct bpf_verifier_state *st)
+static bool compute_scc_callchain(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st,
+ struct bpf_scc_callchain *callchain)
{
- struct bpf_verifier_state *topmost = st->loop_entry;
- u32 steps = 0;
+ u32 i, scc, insn_idx;
- while (topmost && topmost->loop_entry) {
- if (verifier_bug_if(steps++ > st->dfs_depth, env, "infinite loop"))
- return ERR_PTR(-EFAULT);
- topmost = topmost->loop_entry;
+ memset(callchain, 0, sizeof(*callchain));
+ for (i = 0; i <= st->curframe; i++) {
+ insn_idx = frame_insn_idx(st, i);
+ scc = env->insn_aux_data[insn_idx].scc;
+ if (scc) {
+ callchain->scc = scc;
+ break;
+ } else if (i < st->curframe) {
+ callchain->callsites[i] = insn_idx;
+ } else {
+ return false;
+ }
}
- return topmost;
+ return true;
}
-static void update_loop_entry(struct bpf_verifier_env *env,
- struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr)
+/* Check if bpf_scc_visit instance for @callchain exists. */
+static struct bpf_scc_visit *scc_visit_lookup(struct bpf_verifier_env *env,
+ struct bpf_scc_callchain *callchain)
{
- /* The hdr->branches check decides between cases B and C in
- * comment for get_loop_entry(). If hdr->branches == 0 then
- * head's topmost loop entry is not in current DFS path,
- * hence 'cur' and 'hdr' are not in the same loop and there is
- * no need to update cur->loop_entry.
- */
- if (hdr->branches && hdr->dfs_depth < (cur->loop_entry ?: cur)->dfs_depth) {
- if (cur->loop_entry) {
- cur->loop_entry->used_as_loop_entry--;
- maybe_free_verifier_state(env, state_loop_entry_as_list(cur));
- }
- cur->loop_entry = hdr;
- hdr->used_as_loop_entry++;
+ struct bpf_scc_info *info = env->scc_info[callchain->scc];
+ struct bpf_scc_visit *visits = info->visits;
+ u32 i;
+
+ if (!info)
+ return NULL;
+ for (i = 0; i < info->num_visits; i++)
+ if (memcmp(callchain, &visits[i].callchain, sizeof(*callchain)) == 0)
+ return &visits[i];
+ return NULL;
+}
+
+/* Allocate a new bpf_scc_visit instance corresponding to @callchain.
+ * Allocated instances are alive for a duration of the do_check_common()
+ * call and are freed by free_states().
+ */
+static struct bpf_scc_visit *scc_visit_alloc(struct bpf_verifier_env *env,
+ struct bpf_scc_callchain *callchain)
+{
+ struct bpf_scc_visit *visit;
+ struct bpf_scc_info *info;
+ u32 scc, num_visits;
+ u64 new_sz;
+
+ scc = callchain->scc;
+ info = env->scc_info[scc];
+ num_visits = info ? info->num_visits : 0;
+ new_sz = sizeof(*info) + sizeof(struct bpf_scc_visit) * (num_visits + 1);
+ info = kvrealloc(env->scc_info[scc], new_sz, GFP_KERNEL_ACCOUNT);
+ if (!info)
+ return NULL;
+ env->scc_info[scc] = info;
+ info->num_visits = num_visits + 1;
+ visit = &info->visits[num_visits];
+ memset(visit, 0, sizeof(*visit));
+ memcpy(&visit->callchain, callchain, sizeof(*callchain));
+ return visit;
+}
+
+/* Form a string '(callsite#1,callsite#2,...,scc)' in env->tmp_str_buf */
+static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain)
+{
+ char *buf = env->tmp_str_buf;
+ int i, delta = 0;
+
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "(");
+ for (i = 0; i < ARRAY_SIZE(callchain->callsites); i++) {
+ if (!callchain->callsites[i])
+ break;
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u,",
+ callchain->callsites[i]);
+ }
+ delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u)", callchain->scc);
+ return env->tmp_str_buf;
+}
+
+/* If callchain for @st exists (@st is in some SCC), ensure that
+ * bpf_scc_visit instance for this callchain exists.
+ * If instance does not exist or is empty, assign visit->entry_state to @st.
+ */
+static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return 0;
+ visit = scc_visit_lookup(env, &callchain);
+ visit = visit ?: scc_visit_alloc(env, &callchain);
+ if (!visit)
+ return -ENOMEM;
+ if (!visit->entry_state) {
+ visit->entry_state = st;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC enter %s\n", format_callchain(env, &callchain));
+ }
+ return 0;
+}
+
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit);
+
+/* If callchain for @st exists (@st is in some SCC), make it empty:
+ * - set visit->entry_state to NULL;
+ * - flush accumulated backedges.
+ */
+static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return 0;
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit) {
+ verifier_bug(env, "scc exit: no visit info for call chain %s",
+ format_callchain(env, &callchain));
+ return -EFAULT;
+ }
+ if (visit->entry_state != st)
+ return 0;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC exit %s\n", format_callchain(env, &callchain));
+ visit->entry_state = NULL;
+ env->num_backedges -= visit->num_backedges;
+ visit->num_backedges = 0;
+ update_peak_states(env);
+ return propagate_backedges(env, visit);
+}
+
+/* Lookup an bpf_scc_visit instance corresponding to @st callchain
+ * and add @backedge to visit->backedges. @st callchain must exist.
+ */
+static int add_scc_backedge(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st,
+ struct bpf_scc_backedge *backedge)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain)) {
+ verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d",
+ st->insn_idx);
+ return -EFAULT;
+ }
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit) {
+ verifier_bug(env, "add backedge: no visit info for call chain %s",
+ format_callchain(env, &callchain));
+ return -EFAULT;
+ }
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "SCC backedge %s\n", format_callchain(env, &callchain));
+ backedge->next = visit->backedges;
+ visit->backedges = backedge;
+ visit->num_backedges++;
+ env->num_backedges++;
+ update_peak_states(env);
+ return 0;
+}
+
+/* bpf_reg_state->live marks for registers in a state @st are incomplete,
+ * if state @st is in some SCC and not all execution paths starting at this
+ * SCC are fully explored.
+ */
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st)
+{
+ struct bpf_scc_callchain callchain;
+ struct bpf_scc_visit *visit;
+
+ if (!compute_scc_callchain(env, st, &callchain))
+ return false;
+ visit = scc_visit_lookup(env, &callchain);
+ if (!visit)
+ return false;
+ return !!visit->backedges;
+}
+
+static void free_backedges(struct bpf_scc_visit *visit)
+{
+ struct bpf_scc_backedge *backedge, *next;
+
+ for (backedge = visit->backedges; backedge; backedge = next) {
+ free_verifier_state(&backedge->state, false);
+ next = backedge->next;
+ kvfree(backedge);
}
+ visit->backedges = NULL;
}
-static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+static int update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
{
struct bpf_verifier_state_list *sl = NULL, *parent_sl;
struct bpf_verifier_state *parent;
+ int err;
while (st) {
u32 br = --st->branches;
- /* br == 0 signals that DFS exploration for 'st' is finished,
- * thus it is necessary to update parent's loop entry if it
- * turned out that st is a part of some loop.
- * This is a part of 'case A' in get_loop_entry() comment.
- */
- if (br == 0 && st->parent && st->loop_entry)
- update_loop_entry(env, st->parent, st->loop_entry);
-
/* WARN_ON(br > 1) technically makes sense here,
* but see comment in push_stack(), hence:
*/
@@ -1974,6 +2038,9 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
br);
if (br)
break;
+ err = maybe_exit_scc(env, st);
+ if (err)
+ return err;
parent = st->parent;
parent_sl = state_parent_as_list(st);
if (sl)
@@ -1981,6 +2048,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
st = parent;
sl = parent_sl;
}
+ return 0;
}
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
@@ -2012,6 +2080,18 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
return 0;
}
+static bool error_recoverable_with_nospec(int err)
+{
+ /* Should only return true for non-fatal errors that are allowed to
+ * occur during speculative verification. For these we can insert a
+ * nospec and the program might still be accepted. Do not include
+ * something like ENOMEM because it is likely to re-occur for the next
+ * architectural path once it has been recovered-from in all speculative
+ * paths.
+ */
+ return err == -EPERM || err == -EACCES || err == -EINVAL;
+}
+
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx,
bool speculative)
@@ -2020,9 +2100,9 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
struct bpf_verifier_stack_elem *elem;
int err;
- elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT);
if (!elem)
- goto err;
+ return NULL;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
@@ -2032,12 +2112,12 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
env->stack_size++;
err = copy_verifier_state(&elem->st, cur);
if (err)
- goto err;
+ return NULL;
elem->st.speculative |= speculative;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
verbose(env, "The sequence of %d jumps is too complex.\n",
env->stack_size);
- goto err;
+ return NULL;
}
if (elem->st.parent) {
++elem->st.parent->branches;
@@ -2052,12 +2132,6 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
*/
}
return &elem->st;
-err:
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- /* pop all elements and return */
- while (!pop_stack(env, NULL, NULL, false));
- return NULL;
}
#define CALLER_SAVED_REGS 6
@@ -2787,9 +2861,9 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
struct bpf_verifier_stack_elem *elem;
struct bpf_func_state *frame;
- elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
+ elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL_ACCOUNT);
if (!elem)
- goto err;
+ return NULL;
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
@@ -2801,35 +2875,24 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
verbose(env,
"The sequence of %d jumps is too complex for async cb.\n",
env->stack_size);
- goto err;
+ return NULL;
}
/* Unlike push_stack() do not copy_verifier_state().
* The caller state doesn't matter.
* This is async callback. It starts in a fresh stack.
* Initialize it similar to do_check_common().
- * But we do need to make sure to not clobber insn_hist, so we keep
- * chaining insn_hist_start/insn_hist_end indices as for a normal
- * child state.
*/
elem->st.branches = 1;
elem->st.in_sleepable = is_sleepable;
- elem->st.insn_hist_start = env->cur_state->insn_hist_end;
- elem->st.insn_hist_end = elem->st.insn_hist_start;
- frame = kzalloc(sizeof(*frame), GFP_KERNEL);
+ frame = kzalloc(sizeof(*frame), GFP_KERNEL_ACCOUNT);
if (!frame)
- goto err;
+ return NULL;
init_func_state(env, frame,
BPF_MAIN_FUNC /* callsite */,
0 /* frameno within this callchain */,
subprog /* subprog number within this prog */);
elem->st.frame[0] = frame;
return &elem->st;
-err:
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- /* pop all elements and return */
- while (!pop_stack(env, NULL, NULL, false));
- return NULL;
}
@@ -3167,7 +3230,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
return -EINVAL;
}
- tab = kzalloc(sizeof(*tab), GFP_KERNEL);
+ tab = kzalloc(sizeof(*tab), GFP_KERNEL_ACCOUNT);
if (!tab)
return -ENOMEM;
prog_aux->kfunc_tab = tab;
@@ -3183,7 +3246,7 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
return 0;
if (!btf_tab && offset) {
- btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL);
+ btf_tab = kzalloc(sizeof(*btf_tab), GFP_KERNEL_ACCOUNT);
if (!btf_tab)
return -ENOMEM;
prog_aux->kfunc_btf_tab = btf_tab;
@@ -3843,10 +3906,11 @@ static void linked_regs_unpack(u64 val, struct linked_regs *s)
}
/* for any branch, call, exit record the history of jmps in the given state */
-static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
- int insn_flags, u64 linked_regs)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+ int insn_flags, u64 linked_regs)
{
- struct bpf_insn_hist_entry *p;
+ u32 cnt = cur->jmp_history_cnt;
+ struct bpf_jmp_history_entry *p;
size_t alloc_size;
/* combine instruction flags if we already recorded this instruction */
@@ -3866,32 +3930,29 @@ static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_s
return 0;
}
- if (cur->insn_hist_end + 1 > env->insn_hist_cap) {
- alloc_size = size_mul(cur->insn_hist_end + 1, sizeof(*p));
- p = kvrealloc(env->insn_hist, alloc_size, GFP_USER);
- if (!p)
- return -ENOMEM;
- env->insn_hist = p;
- env->insn_hist_cap = alloc_size / sizeof(*p);
- }
+ cnt++;
+ alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
+ p = krealloc(cur->jmp_history, alloc_size, GFP_KERNEL_ACCOUNT);
+ if (!p)
+ return -ENOMEM;
+ cur->jmp_history = p;
- p = &env->insn_hist[cur->insn_hist_end];
+ p = &cur->jmp_history[cnt - 1];
p->idx = env->insn_idx;
p->prev_idx = env->prev_insn_idx;
p->flags = insn_flags;
p->linked_regs = linked_regs;
-
- cur->insn_hist_end++;
+ cur->jmp_history_cnt = cnt;
env->cur_hist_ent = p;
return 0;
}
-static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *env,
- u32 hist_start, u32 hist_end, int insn_idx)
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+ u32 hist_end, int insn_idx)
{
- if (hist_end > hist_start && env->insn_hist[hist_end - 1].idx == insn_idx)
- return &env->insn_hist[hist_end - 1];
+ if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+ return &st->jmp_history[hist_end - 1];
return NULL;
}
@@ -3908,26 +3969,25 @@ static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *
* history entry recording a jump from last instruction of parent state and
* first instruction of given state.
*/
-static int get_prev_insn_idx(const struct bpf_verifier_env *env,
- struct bpf_verifier_state *st,
- int insn_idx, u32 hist_start, u32 *hist_endp)
+static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
+ u32 *history)
{
- u32 hist_end = *hist_endp;
- u32 cnt = hist_end - hist_start;
+ u32 cnt = *history;
- if (insn_idx == st->first_insn_idx) {
+ if (i == st->first_insn_idx) {
if (cnt == 0)
return -ENOENT;
- if (cnt == 1 && env->insn_hist[hist_start].idx == insn_idx)
+ if (cnt == 1 && st->jmp_history[0].idx == i)
return -ENOENT;
}
- if (cnt && env->insn_hist[hist_end - 1].idx == insn_idx) {
- (*hist_endp)--;
- return env->insn_hist[hist_end - 1].prev_idx;
+ if (cnt && st->jmp_history[cnt - 1].idx == i) {
+ i = st->jmp_history[cnt - 1].prev_idx;
+ (*history)--;
} else {
- return insn_idx - 1;
+ i--;
}
+ return i;
}
static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
@@ -4108,7 +4168,7 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
/* If any register R in hist->linked_regs is marked as precise in bt,
* do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs.
*/
-static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_insn_hist_entry *hist)
+static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist)
{
struct linked_regs linked_regs;
bool some_precise = false;
@@ -4153,7 +4213,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
* - *was* processed previously during backtracking.
*/
static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
- struct bpf_insn_hist_entry *hist, struct backtrack_state *bt)
+ struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
{
struct bpf_insn *insn = env->prog->insnsi + idx;
u8 class = BPF_CLASS(insn->code);
@@ -4571,7 +4631,7 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
* SCALARS, as well as any other registers and slots that contribute to
* a tracked state of given registers/stack slots, depending on specific BPF
* assembly instructions (see backtrack_insns() for exact instruction handling
- * logic). This backtracking relies on recorded insn_hist and is able to
+ * logic). This backtracking relies on recorded jmp_history and is able to
* traverse entire chain of parent states. This process ends only when all the
* necessary registers/slots and their transitive dependencies are marked as
* precise.
@@ -4651,23 +4711,27 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
* mark_all_scalars_imprecise() to hopefully get more permissive and generic
* finalized states which help in short circuiting more future states.
*/
-static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
+static int __mark_chain_precision(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *starting_state,
+ int regno,
+ bool *changed)
{
+ struct bpf_verifier_state *st = starting_state;
struct backtrack_state *bt = &env->bt;
- struct bpf_verifier_state *st = env->cur_state;
int first_idx = st->first_insn_idx;
- int last_idx = env->insn_idx;
+ int last_idx = starting_state->insn_idx;
int subseq_idx = -1;
struct bpf_func_state *func;
+ bool tmp, skip_first = true;
struct bpf_reg_state *reg;
- bool skip_first = true;
int i, fr, err;
if (!env->bpf_capable)
return 0;
+ changed = changed ?: &tmp;
/* set frame number from which we are starting to backtrack */
- bt_init(bt, env->cur_state->curframe);
+ bt_init(bt, starting_state->curframe);
/* Do sanity checks against current state of register and/or stack
* slot, but don't set precise flag in current state, as precision
@@ -4688,9 +4752,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
for (;;) {
DECLARE_BITMAP(mask, 64);
- u32 hist_start = st->insn_hist_start;
- u32 hist_end = st->insn_hist_end;
- struct bpf_insn_hist_entry *hist;
+ u32 history = st->jmp_history_cnt;
+ struct bpf_jmp_history_entry *hist;
if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4712,8 +4775,10 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
bt_clear_reg(bt, i);
- if (reg->type == SCALAR_VALUE)
+ if (reg->type == SCALAR_VALUE) {
reg->precise = true;
+ *changed = true;
+ }
}
return 0;
}
@@ -4728,11 +4793,11 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
err = 0;
skip_first = false;
} else {
- hist = get_insn_hist_entry(env, hist_start, hist_end, i);
+ hist = get_jmp_hist_entry(st, history, i);
err = backtrack_insn(env, i, subseq_idx, hist, bt);
}
if (err == -ENOTSUPP) {
- mark_all_scalars_precise(env, env->cur_state);
+ mark_all_scalars_precise(env, starting_state);
bt_reset(bt);
return 0;
} else if (err) {
@@ -4745,7 +4810,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
*/
return 0;
subseq_idx = i;
- i = get_prev_insn_idx(env, st, i, hist_start, &hist_end);
+ i = get_prev_insn_idx(st, i, &history);
if (i == -ENOENT)
break;
if (i >= env->prog->len) {
@@ -4772,10 +4837,12 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
bt_clear_frame_reg(bt, fr, i);
continue;
}
- if (reg->precise)
+ if (reg->precise) {
bt_clear_frame_reg(bt, fr, i);
- else
+ } else {
reg->precise = true;
+ *changed = true;
+ }
}
bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
@@ -4790,10 +4857,12 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
continue;
}
reg = &func->stack[i].spilled_ptr;
- if (reg->precise)
+ if (reg->precise) {
bt_clear_frame_slot(bt, fr, i);
- else
+ } else {
reg->precise = true;
+ *changed = true;
+ }
}
if (env->log.level & BPF_LOG_LEVEL2) {
fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
@@ -4820,7 +4889,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
* fallback to marking all precise
*/
if (!bt_empty(bt)) {
- mark_all_scalars_precise(env, env->cur_state);
+ mark_all_scalars_precise(env, starting_state);
bt_reset(bt);
}
@@ -4829,15 +4898,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
- return __mark_chain_precision(env, regno);
+ return __mark_chain_precision(env, env->cur_state, regno, NULL);
}
/* mark_chain_precision_batch() assumes that env->bt is set in the caller to
* desired reg and stack masks across all relevant frames
*/
-static int mark_chain_precision_batch(struct bpf_verifier_env *env)
+static int mark_chain_precision_batch(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *starting_state)
{
- return __mark_chain_precision(env, -1);
+ return __mark_chain_precision(env, starting_state, -1, NULL);
}
static bool is_spillable_regtype(enum bpf_reg_type type)
@@ -5026,7 +5096,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
}
if (sanitize)
- env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+ env->insn_aux_data[insn_idx].nospec_result = true;
}
err = destroy_if_dynptr_stack_slot(env, state, spi);
@@ -5109,7 +5179,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
}
if (insn_flags)
- return push_insn_history(env, env->cur_state, insn_flags, 0);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -5416,7 +5486,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
insn_flags = 0; /* we are not restoring spilled register */
}
if (insn_flags)
- return push_insn_history(env, env->cur_state, insn_flags, 0);
+ return push_jmp_history(env, env->cur_state, insn_flags, 0);
return 0;
}
@@ -7031,8 +7101,7 @@ BTF_TYPE_SAFE_TRUSTED(struct file) {
struct inode *f_inode;
};
-BTF_TYPE_SAFE_TRUSTED(struct dentry) {
- /* no negative dentry-s in places where bpf can see it */
+BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) {
struct inode *d_inode;
};
@@ -7071,7 +7140,6 @@ static bool type_is_trusted(struct bpf_verifier_env *env,
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm));
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file));
- BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct dentry));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted");
}
@@ -7081,6 +7149,7 @@ static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
const char *field_name, u32 btf_id)
{
BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
+ BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry));
return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
"__safe_trusted_or_null");
@@ -7475,6 +7544,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
}
} else if (base_type(reg->type) == PTR_TO_MEM) {
bool rdonly_mem = type_is_rdonly_mem(reg->type);
+ bool rdonly_untrusted = rdonly_mem && (reg->type & PTR_UNTRUSTED);
if (type_may_be_null(reg->type)) {
verbose(env, "R%d invalid mem access '%s'\n", regno,
@@ -7494,8 +7564,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
return -EACCES;
}
- err = check_mem_region_access(env, regno, off, size,
- reg->mem_size, false);
+ /*
+ * Accesses to untrusted PTR_TO_MEM are done through probe
+ * instructions, hence no need to check bounds in that case.
+ */
+ if (!rdonly_untrusted)
+ err = check_mem_region_access(env, regno, off, size,
+ reg->mem_size, false);
if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
mark_reg_unknown(env, regs, value_regno);
} else if (reg->type == PTR_TO_CTX) {
@@ -8959,7 +9034,7 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->type\n");
- return -EACCES;
+ return -EFAULT;
}
switch (meta->map_ptr->map_type) {
@@ -9495,7 +9570,7 @@ static int get_constant_map_key(struct bpf_verifier_env *env,
* to prevent pruning on it.
*/
bt_set_frame_slot(&env->bt, key->frameno, spi);
- err = mark_chain_precision_batch(env);
+ err = mark_chain_precision_batch(env, env->cur_state);
if (err < 0)
return err;
@@ -9647,7 +9722,7 @@ skip_type_check:
* that kernel subsystem misconfigured verifier
*/
verbose(env, "invalid map_ptr to access map->key\n");
- return -EACCES;
+ return -EFAULT;
}
key_size = meta->map_ptr->key_size;
err = check_helper_mem_access(env, regno, key_size, BPF_READ, false, NULL);
@@ -9674,7 +9749,7 @@ skip_type_check:
if (!meta->map_ptr) {
/* kernel subsystem misconfigured verifier */
verbose(env, "invalid map_ptr to access map->value\n");
- return -EACCES;
+ return -EFAULT;
}
meta->raw_mode = arg_type & MEM_UNINIT;
err = check_helper_mem_access(env, regno, meta->map_ptr->value_size,
@@ -10284,7 +10359,7 @@ static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int calls
}
caller = state->frame[state->curframe];
- callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ callee = kzalloc(sizeof(*callee), GFP_KERNEL_ACCOUNT);
if (!callee)
return -ENOMEM;
state->frame[state->curframe + 1] = callee;
@@ -10970,7 +11045,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
/* In case of read-only, some additional restrictions
@@ -11009,7 +11084,7 @@ record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
return 0;
if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) {
verbose(env, "kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
reg = &regs[BPF_REG_3];
@@ -11151,7 +11226,7 @@ static int check_get_func_ip(struct bpf_verifier_env *env)
return -ENOTSUPP;
}
-static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env)
{
return &env->insn_aux_data[env->insn_idx];
}
@@ -11263,7 +11338,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
func_id_name(func_id), func_id);
- return -EINVAL;
+ return -EFAULT;
}
memset(&meta, 0, sizeof(meta));
@@ -11565,7 +11640,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
if (meta.map_ptr == NULL) {
verbose(env,
"kernel subsystem misconfigured verifier\n");
- return -EINVAL;
+ return -EFAULT;
}
if (func_id == BPF_FUNC_map_lookup_elem &&
@@ -11658,7 +11733,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
verbose(env, "verifier internal error:");
verbose(env, "func %s has non-overwritten BPF_PTR_POISON return type\n",
func_id_name(func_id));
- return -EINVAL;
+ return -EFAULT;
}
ret_btf = btf_vmlinux;
ret_btf_id = *fn->ret_btf_id;
@@ -13542,16 +13617,24 @@ static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_ca
regs[BPF_REG_0].btf_id = meta->ret_btf_id;
} else if (meta->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value);
- if (!ret_t || !btf_type_is_struct(ret_t)) {
+ if (!ret_t) {
+ verbose(env, "Unknown type ID %lld passed to kfunc bpf_rdonly_cast\n",
+ meta->arg_constant.value);
+ return -EINVAL;
+ } else if (btf_type_is_struct(ret_t)) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
+ regs[BPF_REG_0].btf = desc_btf;
+ regs[BPF_REG_0].btf_id = meta->arg_constant.value;
+ } else if (btf_type_is_void(ret_t)) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED;
+ regs[BPF_REG_0].mem_size = 0;
+ } else {
verbose(env,
- "kfunc bpf_rdonly_cast type ID argument must be of a struct\n");
+ "kfunc bpf_rdonly_cast type ID argument must be of a struct or void\n");
return -EINVAL;
}
-
- mark_reg_known_zero(env, regs, BPF_REG_0);
- regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
- regs[BPF_REG_0].btf = desc_btf;
- regs[BPF_REG_0].btf_id = meta->arg_constant.value;
} else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice] ||
meta->func_id == special_kfunc_list[KF_bpf_dynptr_slice_rdwr]) {
enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->initialized_dynptr.type);
@@ -14019,7 +14102,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
- return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
+ return env->bypass_spec_v1 ||
+ BPF_SRC(insn->code) == BPF_K ||
+ cur_aux(env)->nospec;
}
static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -14219,7 +14304,7 @@ static int sanitize_err(struct bpf_verifier_env *env,
case REASON_STACK:
verbose(env, "R%d could not be pushed for speculative verification, %s\n",
dst, err);
- break;
+ return -ENOMEM;
default:
verbose(env, "verifier internal error: unknown reason (%d)\n",
reason);
@@ -14289,7 +14374,7 @@ static int sanitize_check_bounds(struct bpf_verifier_env *env,
}
break;
default:
- break;
+ return -EOPNOTSUPP;
}
return 0;
@@ -14316,7 +14401,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
struct bpf_sanitize_info info = {};
u8 opcode = BPF_OP(insn->code);
u32 dst = insn->dst_reg;
- int ret;
+ int ret, bounds_ret;
dst_reg = &regs[dst];
@@ -14348,6 +14433,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
return -EACCES;
}
+ /*
+ * Accesses to untrusted PTR_TO_MEM are done through probe
+ * instructions, hence no need to track offsets.
+ */
+ if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED))
+ return 0;
+
switch (base_type(ptr_reg->type)) {
case PTR_TO_CTX:
case PTR_TO_MAP_VALUE:
@@ -14516,11 +14608,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
return -EINVAL;
reg_bounds_sync(dst_reg);
- if (sanitize_check_bounds(env, insn, dst_reg) < 0)
- return -EACCES;
+ bounds_ret = sanitize_check_bounds(env, insn, dst_reg);
+ if (bounds_ret == -EACCES)
+ return bounds_ret;
if (sanitize_needed(opcode)) {
ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
&info, true);
+ if (verifier_bug_if(!can_skip_alu_sanitation(env, insn)
+ && !env->cur_state->speculative
+ && bounds_ret
+ && !ret,
+ env, "Pointer type unsupported by sanitize_check_bounds() not rejected by retrieve_ptr_limit() as required")) {
+ return -EFAULT;
+ }
if (ret < 0)
return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
@@ -14535,14 +14635,25 @@ static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
s32 *dst_smax = &dst_reg->s32_max_value;
u32 *dst_umin = &dst_reg->u32_min_value;
u32 *dst_umax = &dst_reg->u32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+ bool min_overflow, max_overflow;
if (check_add_overflow(*dst_smin, src_reg->s32_min_value, dst_smin) ||
check_add_overflow(*dst_smax, src_reg->s32_max_value, dst_smax)) {
*dst_smin = S32_MIN;
*dst_smax = S32_MAX;
}
- if (check_add_overflow(*dst_umin, src_reg->u32_min_value, dst_umin) ||
- check_add_overflow(*dst_umax, src_reg->u32_max_value, dst_umax)) {
+
+ /* If either all additions overflow or no additions overflow, then
+ * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax =
+ * dst_umax + src_umax. Otherwise (some additions overflow), set
+ * the output bounds to unbounded.
+ */
+ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin);
+ max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax);
+
+ if (!min_overflow && max_overflow) {
*dst_umin = 0;
*dst_umax = U32_MAX;
}
@@ -14555,14 +14666,25 @@ static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
s64 *dst_smax = &dst_reg->smax_value;
u64 *dst_umin = &dst_reg->umin_value;
u64 *dst_umax = &dst_reg->umax_value;
+ u64 umin_val = src_reg->umin_value;
+ u64 umax_val = src_reg->umax_value;
+ bool min_overflow, max_overflow;
if (check_add_overflow(*dst_smin, src_reg->smin_value, dst_smin) ||
check_add_overflow(*dst_smax, src_reg->smax_value, dst_smax)) {
*dst_smin = S64_MIN;
*dst_smax = S64_MAX;
}
- if (check_add_overflow(*dst_umin, src_reg->umin_value, dst_umin) ||
- check_add_overflow(*dst_umax, src_reg->umax_value, dst_umax)) {
+
+ /* If either all additions overflow or no additions overflow, then
+ * it is okay to set: dst_umin = dst_umin + src_umin, dst_umax =
+ * dst_umax + src_umax. Otherwise (some additions overflow), set
+ * the output bounds to unbounded.
+ */
+ min_overflow = check_add_overflow(*dst_umin, umin_val, dst_umin);
+ max_overflow = check_add_overflow(*dst_umax, umax_val, dst_umax);
+
+ if (!min_overflow && max_overflow) {
*dst_umin = 0;
*dst_umax = U64_MAX;
}
@@ -14573,8 +14695,11 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
{
s32 *dst_smin = &dst_reg->s32_min_value;
s32 *dst_smax = &dst_reg->s32_max_value;
+ u32 *dst_umin = &dst_reg->u32_min_value;
+ u32 *dst_umax = &dst_reg->u32_max_value;
u32 umin_val = src_reg->u32_min_value;
u32 umax_val = src_reg->u32_max_value;
+ bool min_underflow, max_underflow;
if (check_sub_overflow(*dst_smin, src_reg->s32_max_value, dst_smin) ||
check_sub_overflow(*dst_smax, src_reg->s32_min_value, dst_smax)) {
@@ -14582,14 +14707,18 @@ static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
*dst_smin = S32_MIN;
*dst_smax = S32_MAX;
}
- if (dst_reg->u32_min_value < umax_val) {
- /* Overflow possible, we know nothing */
- dst_reg->u32_min_value = 0;
- dst_reg->u32_max_value = U32_MAX;
- } else {
- /* Cannot overflow (as long as bounds are consistent) */
- dst_reg->u32_min_value -= umax_val;
- dst_reg->u32_max_value -= umin_val;
+
+ /* If either all subtractions underflow or no subtractions
+ * underflow, it is okay to set: dst_umin = dst_umin - src_umax,
+ * dst_umax = dst_umax - src_umin. Otherwise (some subtractions
+ * underflow), set the output bounds to unbounded.
+ */
+ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin);
+ max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax);
+
+ if (min_underflow && !max_underflow) {
+ *dst_umin = 0;
+ *dst_umax = U32_MAX;
}
}
@@ -14598,8 +14727,11 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
{
s64 *dst_smin = &dst_reg->smin_value;
s64 *dst_smax = &dst_reg->smax_value;
+ u64 *dst_umin = &dst_reg->umin_value;
+ u64 *dst_umax = &dst_reg->umax_value;
u64 umin_val = src_reg->umin_value;
u64 umax_val = src_reg->umax_value;
+ bool min_underflow, max_underflow;
if (check_sub_overflow(*dst_smin, src_reg->smax_value, dst_smin) ||
check_sub_overflow(*dst_smax, src_reg->smin_value, dst_smax)) {
@@ -14607,14 +14739,18 @@ static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
*dst_smin = S64_MIN;
*dst_smax = S64_MAX;
}
- if (dst_reg->umin_value < umax_val) {
- /* Overflow possible, we know nothing */
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- } else {
- /* Cannot overflow (as long as bounds are consistent) */
- dst_reg->umin_value -= umax_val;
- dst_reg->umax_value -= umin_val;
+
+ /* If either all subtractions underflow or no subtractions
+ * underflow, it is okay to set: dst_umin = dst_umin - src_umax,
+ * dst_umax = dst_umax - src_umin. Otherwise (some subtractions
+ * underflow), set the output bounds to unbounded.
+ */
+ min_underflow = check_sub_overflow(*dst_umin, umax_val, dst_umin);
+ max_underflow = check_sub_overflow(*dst_umax, umin_val, dst_umax);
+
+ if (min_underflow && !max_underflow) {
+ *dst_umin = 0;
+ *dst_umax = U64_MAX;
}
}
@@ -15076,6 +15212,7 @@ static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn,
switch (BPF_OP(insn->code)) {
case BPF_ADD:
case BPF_SUB:
+ case BPF_NEG:
case BPF_AND:
case BPF_XOR:
case BPF_OR:
@@ -15144,6 +15281,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
break;
+ case BPF_NEG:
+ env->fake_reg[0] = *dst_reg;
+ __mark_reg_known(dst_reg, 0);
+ scalar32_min_max_sub(dst_reg, &env->fake_reg[0]);
+ scalar_min_max_sub(dst_reg, &env->fake_reg[0]);
+ dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off);
+ break;
case BPF_MUL:
dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
scalar32_min_max_mul(dst_reg, &src_reg);
@@ -15283,12 +15427,12 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
if (WARN_ON_ONCE(ptr_reg)) {
print_verifier_state(env, vstate, vstate->curframe, true);
verbose(env, "verifier internal error: unexpected ptr_reg\n");
- return -EINVAL;
+ return -EFAULT;
}
if (WARN_ON(!src_reg)) {
print_verifier_state(env, vstate, vstate->curframe, true);
verbose(env, "verifier internal error: no src_reg\n");
- return -EINVAL;
+ return -EFAULT;
}
err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
if (err)
@@ -15367,7 +15511,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
}
/* check dest operand */
- err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ if (opcode == BPF_NEG) {
+ err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+ err = err ?: adjust_scalar_min_max_vals(env, insn,
+ &regs[insn->dst_reg],
+ regs[insn->dst_reg]);
+ } else {
+ err = check_reg_arg(env, insn->dst_reg, DST_OP);
+ }
if (err)
return err;
@@ -16478,7 +16629,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
if (insn_flags) {
- err = push_insn_history(env, this_branch, insn_flags, 0);
+ err = push_jmp_history(env, this_branch, insn_flags, 0);
if (err)
return err;
}
@@ -16536,7 +16687,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
if (linked_regs.cnt > 1) {
- err = push_insn_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
+ err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
if (err)
return err;
}
@@ -16734,7 +16885,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
dst_reg->type = CONST_PTR_TO_MAP;
} else {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
return 0;
@@ -16781,7 +16932,7 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (!env->ops->gen_ld_abs) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
@@ -17611,17 +17762,18 @@ static int check_cfg(struct bpf_verifier_env *env)
int *insn_stack, *insn_state, *insn_postorder;
int ex_insn_beg, i, ret = 0;
- insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_state)
return -ENOMEM;
- insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_stack) {
kvfree(insn_state);
return -ENOMEM;
}
- insn_postorder = env->cfg.insn_postorder = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_postorder = env->cfg.insn_postorder =
+ kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
if (!insn_postorder) {
kvfree(insn_state);
kvfree(insn_stack);
@@ -17755,7 +17907,7 @@ static int check_btf_func_early(struct bpf_verifier_env *env,
urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
min_size = min_t(u32, krec_size, urec_size);
- krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
+ krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!krecord)
return -ENOMEM;
@@ -17855,7 +18007,7 @@ static int check_btf_func(struct bpf_verifier_env *env,
urecord = make_bpfptr(attr->func_info, uattr.is_kernel);
krecord = prog->aux->func_info;
- info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!info_aux)
return -ENOMEM;
@@ -17941,7 +18093,7 @@ static int check_btf_line(struct bpf_verifier_env *env,
* pass in a smaller bpf_line_info object.
*/
linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info),
- GFP_KERNEL | __GFP_NOWARN);
+ GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
if (!linfo)
return -ENOMEM;
@@ -18264,10 +18416,6 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
{
int i;
- if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
- /* all regs in this state in all frames were already marked */
- return;
-
for (i = 0; i <= st->curframe; i++)
clean_func_state(env, st->frame[i]);
}
@@ -18307,7 +18455,6 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
static void clean_live_states(struct bpf_verifier_env *env, int insn,
struct bpf_verifier_state *cur)
{
- struct bpf_verifier_state *loop_entry;
struct bpf_verifier_state_list *sl;
struct list_head *pos, *head;
@@ -18316,12 +18463,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn,
sl = container_of(pos, struct bpf_verifier_state_list, node);
if (sl->state.branches)
continue;
- loop_entry = get_loop_entry(env, &sl->state);
- if (!IS_ERR_OR_NULL(loop_entry) && loop_entry->branches)
- continue;
if (sl->state.insn_idx != insn ||
!same_callsites(&sl->state, cur))
continue;
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE)
+ /* all regs in this state in all frames were already marked */
+ continue;
+ if (incomplete_read_marks(env, &sl->state))
+ continue;
clean_verifier_state(env, &sl->state);
}
}
@@ -18768,9 +18917,7 @@ static bool states_equal(struct bpf_verifier_env *env,
* and all frame states need to be equivalent
*/
for (i = 0; i <= old->curframe; i++) {
- insn_idx = i == old->curframe
- ? env->insn_idx
- : old->frame[i + 1]->callsite;
+ insn_idx = frame_insn_idx(old, i);
if (old->frame[i]->callsite != cur->frame[i]->callsite)
return false;
if (!func_states_equal(env, old->frame[i], cur->frame[i], insn_idx, exact))
@@ -18817,12 +18964,15 @@ static int propagate_liveness_reg(struct bpf_verifier_env *env,
*/
static int propagate_liveness(struct bpf_verifier_env *env,
const struct bpf_verifier_state *vstate,
- struct bpf_verifier_state *vparent)
+ struct bpf_verifier_state *vparent,
+ bool *changed)
{
struct bpf_reg_state *state_reg, *parent_reg;
struct bpf_func_state *state, *parent;
int i, frame, err = 0;
+ bool tmp = false;
+ changed = changed ?: &tmp;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
vparent->curframe, vstate->curframe);
@@ -18841,6 +18991,7 @@ static int propagate_liveness(struct bpf_verifier_env *env,
&parent_reg[i]);
if (err < 0)
return err;
+ *changed |= err > 0;
if (err == REG_LIVE_READ64)
mark_insn_zext(env, &parent_reg[i]);
}
@@ -18852,6 +19003,7 @@ static int propagate_liveness(struct bpf_verifier_env *env,
state_reg = &state->stack[i].spilled_ptr;
err = propagate_liveness_reg(env, state_reg,
parent_reg);
+ *changed |= err > 0;
if (err < 0)
return err;
}
@@ -18863,7 +19015,9 @@ static int propagate_liveness(struct bpf_verifier_env *env,
* propagate them into the current state
*/
static int propagate_precision(struct bpf_verifier_env *env,
- const struct bpf_verifier_state *old)
+ const struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur,
+ bool *changed)
{
struct bpf_reg_state *state_reg;
struct bpf_func_state *state;
@@ -18911,13 +19065,53 @@ static int propagate_precision(struct bpf_verifier_env *env,
verbose(env, "\n");
}
- err = mark_chain_precision_batch(env);
+ err = __mark_chain_precision(env, cur, -1, changed);
if (err < 0)
return err;
return 0;
}
+#define MAX_BACKEDGE_ITERS 64
+
+/* Propagate read and precision marks from visit->backedges[*].state->equal_state
+ * to corresponding parent states of visit->backedges[*].state until fixed point is reached,
+ * then free visit->backedges.
+ * After execution of this function incomplete_read_marks() will return false
+ * for all states corresponding to @visit->callchain.
+ */
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit)
+{
+ struct bpf_scc_backedge *backedge;
+ struct bpf_verifier_state *st;
+ bool changed;
+ int i, err;
+
+ i = 0;
+ do {
+ if (i++ > MAX_BACKEDGE_ITERS) {
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "%s: too many iterations\n", __func__);
+ for (backedge = visit->backedges; backedge; backedge = backedge->next)
+ mark_all_scalars_precise(env, &backedge->state);
+ break;
+ }
+ changed = false;
+ for (backedge = visit->backedges; backedge; backedge = backedge->next) {
+ st = &backedge->state;
+ err = propagate_liveness(env, st->equal_state, st, &changed);
+ if (err)
+ return err;
+ err = propagate_precision(env, st->equal_state, st, &changed);
+ if (err)
+ return err;
+ }
+ } while (changed);
+
+ free_backedges(visit);
+ return 0;
+}
+
static bool states_maybe_looping(struct bpf_verifier_state *old,
struct bpf_verifier_state *cur)
{
@@ -19027,14 +19221,14 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
struct bpf_verifier_state_list *sl;
- struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
+ struct bpf_verifier_state *cur = env->cur_state, *new;
+ bool force_new_state, add_new_state, loop;
int i, j, n, err, states_cnt = 0;
- bool force_new_state, add_new_state, force_exact;
struct list_head *pos, *tmp, *head;
force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) ||
/* Avoid accumulating infinitely long jmp history */
- cur->insn_hist_end - cur->insn_hist_start > 40;
+ cur->jmp_history_cnt > 40;
/* bpf progs typically have pruning point every 4 instructions
* http://vger.kernel.org/bpfconf2019.html#session-1
@@ -19051,6 +19245,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
clean_live_states(env, insn_idx, cur);
+ loop = false;
head = explored_state(env, insn_idx);
list_for_each_safe(pos, tmp, head) {
sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -19130,7 +19325,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
spi = __get_spi(iter_reg->off + iter_reg->var_off.value);
iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr;
if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) {
- update_loop_entry(env, cur, &sl->state);
+ loop = true;
goto hit;
}
}
@@ -19139,7 +19334,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
if (is_may_goto_insn_at(env, insn_idx)) {
if (sl->state.may_goto_depth != cur->may_goto_depth &&
states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
- update_loop_entry(env, cur, &sl->state);
+ loop = true;
goto hit;
}
}
@@ -19181,38 +19376,9 @@ skip_inf_loop_check:
add_new_state = false;
goto miss;
}
- /* If sl->state is a part of a loop and this loop's entry is a part of
- * current verification path then states have to be compared exactly.
- * 'force_exact' is needed to catch the following case:
- *
- * initial Here state 'succ' was processed first,
- * | it was eventually tracked to produce a
- * V state identical to 'hdr'.
- * .---------> hdr All branches from 'succ' had been explored
- * | | and thus 'succ' has its .branches == 0.
- * | V
- * | .------... Suppose states 'cur' and 'succ' correspond
- * | | | to the same instruction + callsites.
- * | V V In such case it is necessary to check
- * | ... ... if 'succ' and 'cur' are states_equal().
- * | | | If 'succ' and 'cur' are a part of the
- * | V V same loop exact flag has to be set.
- * | succ <- cur To check if that is the case, verify
- * | | if loop entry of 'succ' is in current
- * | V DFS path.
- * | ...
- * | |
- * '----'
- *
- * Additional details are in the comment before get_loop_entry().
- */
- loop_entry = get_loop_entry(env, &sl->state);
- if (IS_ERR(loop_entry))
- return PTR_ERR(loop_entry);
- force_exact = loop_entry && loop_entry->branches > 0;
- if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) {
- if (force_exact)
- update_loop_entry(env, cur, loop_entry);
+ /* See comments for mark_all_regs_read_and_precise() */
+ loop = incomplete_read_marks(env, &sl->state);
+ if (states_equal(env, &sl->state, cur, loop ? RANGE_WITHIN : NOT_EXACT)) {
hit:
sl->hit_cnt++;
/* reached equivalent register/stack state,
@@ -19225,7 +19391,7 @@ hit:
* they'll be immediately forgotten as we're pruning
* this state and will pop a new one.
*/
- err = propagate_liveness(env, &sl->state, cur);
+ err = propagate_liveness(env, &sl->state, cur, NULL);
/* if previous state reached the exit with precision and
* current state is equivalent to it (except precision marks)
@@ -19233,10 +19399,98 @@ hit:
* the current state.
*/
if (is_jmp_point(env, env->insn_idx))
- err = err ? : push_insn_history(env, cur, 0, 0);
- err = err ? : propagate_precision(env, &sl->state);
+ err = err ? : push_jmp_history(env, cur, 0, 0);
+ err = err ? : propagate_precision(env, &sl->state, cur, NULL);
if (err)
return err;
+ /* When processing iterator based loops above propagate_liveness and
+ * propagate_precision calls are not sufficient to transfer all relevant
+ * read and precision marks. E.g. consider the following case:
+ *
+ * .-> A --. Assume the states are visited in the order A, B, C.
+ * | | | Assume that state B reaches a state equivalent to state A.
+ * | v v At this point, state C is not processed yet, so state A
+ * '-- B C has not received any read or precision marks from C.
+ * Thus, marks propagated from A to B are incomplete.
+ *
+ * The verifier mitigates this by performing the following steps:
+ *
+ * - Prior to the main verification pass, strongly connected components
+ * (SCCs) are computed over the program's control flow graph,
+ * intraprocedurally.
+ *
+ * - During the main verification pass, `maybe_enter_scc()` checks
+ * whether the current verifier state is entering an SCC. If so, an
+ * instance of a `bpf_scc_visit` object is created, and the state
+ * entering the SCC is recorded as the entry state.
+ *
+ * - This instance is associated not with the SCC itself, but with a
+ * `bpf_scc_callchain`: a tuple consisting of the call sites leading to
+ * the SCC and the SCC id. See `compute_scc_callchain()`.
+ *
+ * - When a verification path encounters a `states_equal(...,
+ * RANGE_WITHIN)` condition, there exists a call chain describing the
+ * current state and a corresponding `bpf_scc_visit` instance. A copy
+ * of the current state is created and added to
+ * `bpf_scc_visit->backedges`.
+ *
+ * - When a verification path terminates, `maybe_exit_scc()` is called
+ * from `update_branch_counts()`. For states with `branches == 0`, it
+ * checks whether the state is the entry state of any `bpf_scc_visit`
+ * instance. If it is, this indicates that all paths originating from
+ * this SCC visit have been explored. `propagate_backedges()` is then
+ * called, which propagates read and precision marks through the
+ * backedges until a fixed point is reached.
+ * (In the earlier example, this would propagate marks from A to B,
+ * from C to A, and then again from A to B.)
+ *
+ * A note on callchains
+ * --------------------
+ *
+ * Consider the following example:
+ *
+ * void foo() { loop { ... SCC#1 ... } }
+ * void main() {
+ * A: foo();
+ * B: ...
+ * C: foo();
+ * }
+ *
+ * Here, there are two distinct callchains leading to SCC#1:
+ * - (A, SCC#1)
+ * - (C, SCC#1)
+ *
+ * Each callchain identifies a separate `bpf_scc_visit` instance that
+ * accumulates backedge states. The `propagate_{liveness,precision}()`
+ * functions traverse the parent state of each backedge state, which
+ * means these parent states must remain valid (i.e., not freed) while
+ * the corresponding `bpf_scc_visit` instance exists.
+ *
+ * Associating `bpf_scc_visit` instances directly with SCCs instead of
+ * callchains would break this invariant:
+ * - States explored during `C: foo()` would contribute backedges to
+ * SCC#1, but SCC#1 would only be exited once the exploration of
+ * `A: foo()` completes.
+ * - By that time, the states explored between `A: foo()` and `C: foo()`
+ * (i.e., `B: ...`) may have already been freed, causing the parent
+ * links for states from `C: foo()` to become invalid.
+ */
+ if (loop) {
+ struct bpf_scc_backedge *backedge;
+
+ backedge = kzalloc(sizeof(*backedge), GFP_KERNEL_ACCOUNT);
+ if (!backedge)
+ return -ENOMEM;
+ err = copy_verifier_state(&backedge->state, cur);
+ backedge->state.equal_state = &sl->state;
+ backedge->state.insn_idx = insn_idx;
+ err = err ?: add_scc_backedge(env, &sl->state, backedge);
+ if (err) {
+ free_verifier_state(&backedge->state, false);
+ kvfree(backedge);
+ return err;
+ }
+ }
return 1;
}
miss:
@@ -19288,7 +19542,7 @@ miss:
* When looping the sl->state.branches will be > 0 and this state
* will not be considered for equivalence until branches == 0.
*/
- new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
+ new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL_ACCOUNT);
if (!new_sl)
return -ENOMEM;
env->total_states++;
@@ -19312,11 +19566,17 @@ miss:
new->insn_idx = insn_idx;
WARN_ONCE(new->branches != 1,
"BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx);
+ err = maybe_enter_scc(env, new);
+ if (err) {
+ free_verifier_state(new, false);
+ kvfree(new_sl);
+ return err;
+ }
cur->parent = new;
cur->first_insn_idx = insn_idx;
- cur->insn_hist_start = cur->insn_hist_end;
cur->dfs_depth = new->dfs_depth + 1;
+ clear_jmp_history(cur);
list_add(&new_sl->node, head);
/* connect new state to parentage chain. Current frame needs all
@@ -19388,10 +19648,27 @@ static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
!reg_type_mismatch_ok(prev));
}
+static bool is_ptr_to_mem_or_btf_id(enum bpf_reg_type type)
+{
+ switch (base_type(type)) {
+ case PTR_TO_MEM:
+ case PTR_TO_BTF_ID:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool is_ptr_to_mem(enum bpf_reg_type type)
+{
+ return base_type(type) == PTR_TO_MEM;
+}
+
static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type,
bool allow_trust_mismatch)
{
enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type;
+ enum bpf_reg_type merged_type;
if (*prev_type == NOT_INIT) {
/* Saw a valid insn
@@ -19408,15 +19685,24 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Reject it.
*/
if (allow_trust_mismatch &&
- base_type(type) == PTR_TO_BTF_ID &&
- base_type(*prev_type) == PTR_TO_BTF_ID) {
+ is_ptr_to_mem_or_btf_id(type) &&
+ is_ptr_to_mem_or_btf_id(*prev_type)) {
/*
* Have to support a use case when one path through
* the program yields TRUSTED pointer while another
* is UNTRUSTED. Fallback to UNTRUSTED to generate
* BPF_PROBE_MEM/BPF_PROBE_MEMSX.
+ * Same behavior of MEM_RDONLY flag.
*/
- *prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
+ if (is_ptr_to_mem(type) || is_ptr_to_mem(*prev_type))
+ merged_type = PTR_TO_MEM;
+ else
+ merged_type = PTR_TO_BTF_ID;
+ if ((type & PTR_UNTRUSTED) || (*prev_type & PTR_UNTRUSTED))
+ merged_type |= PTR_UNTRUSTED;
+ if ((type & MEM_RDONLY) || (*prev_type & MEM_RDONLY))
+ merged_type |= MEM_RDONLY;
+ *prev_type = merged_type;
} else {
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
@@ -19426,20 +19712,223 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
return 0;
}
+enum {
+ PROCESS_BPF_EXIT = 1
+};
+
+static int process_bpf_exit_full(struct bpf_verifier_env *env,
+ bool *do_print_state,
+ bool exception_exit)
+{
+ /* We must do check_reference_leak here before
+ * prepare_func_exit to handle the case when
+ * state->curframe > 0, it may be a callback function,
+ * for which reference_state must match caller reference
+ * state when it exits.
+ */
+ int err = check_resource_leak(env, exception_exit,
+ !env->cur_state->curframe,
+ "BPF_EXIT instruction in main prog");
+ if (err)
+ return err;
+
+ /* The side effect of the prepare_func_exit which is
+ * being skipped is that it frees bpf_func_state.
+ * Typically, process_bpf_exit will only be hit with
+ * outermost exit. copy_verifier_state in pop_stack will
+ * handle freeing of any extra bpf_func_state left over
+ * from not processing all nested function exits. We
+ * also skip return code checks as they are not needed
+ * for exceptional exits.
+ */
+ if (exception_exit)
+ return PROCESS_BPF_EXIT;
+
+ if (env->cur_state->curframe) {
+ /* exit from nested function */
+ err = prepare_func_exit(env, &env->insn_idx);
+ if (err)
+ return err;
+ *do_print_state = true;
+ return 0;
+ }
+
+ err = check_return_code(env, BPF_REG_0, "R0");
+ if (err)
+ return err;
+ return PROCESS_BPF_EXIT;
+}
+
+static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state)
+{
+ int err;
+ struct bpf_insn *insn = &env->prog->insnsi[env->insn_idx];
+ u8 class = BPF_CLASS(insn->code);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ err = check_alu_op(env, insn);
+ if (err)
+ return err;
+
+ } else if (class == BPF_LDX) {
+ bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX;
+
+ /* Check for reserved fields is already done in
+ * resolve_pseudo_ldimm64().
+ */
+ err = check_load_mem(env, insn, false, is_ldsx, true, "ldx");
+ if (err)
+ return err;
+ } else if (class == BPF_STX) {
+ if (BPF_MODE(insn->code) == BPF_ATOMIC) {
+ err = check_atomic(env, insn);
+ if (err)
+ return err;
+ env->insn_idx++;
+ return 0;
+ }
+
+ if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
+ verbose(env, "BPF_STX uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ err = check_store_reg(env, insn, false);
+ if (err)
+ return err;
+ } else if (class == BPF_ST) {
+ enum bpf_reg_type dst_reg_type;
+
+ if (BPF_MODE(insn->code) != BPF_MEM ||
+ insn->src_reg != BPF_REG_0) {
+ verbose(env, "BPF_ST uses reserved fields\n");
+ return -EINVAL;
+ }
+ /* check src operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg_type = cur_regs(env)[insn->dst_reg].type;
+
+ /* check that memory (dst_reg + off) is writeable */
+ err = check_mem_access(env, env->insn_idx, insn->dst_reg,
+ insn->off, BPF_SIZE(insn->code),
+ BPF_WRITE, -1, false, false);
+ if (err)
+ return err;
+
+ err = save_aux_ptr_type(env, dst_reg_type, false);
+ if (err)
+ return err;
+ } else if (class == BPF_JMP || class == BPF_JMP32) {
+ u8 opcode = BPF_OP(insn->code);
+
+ env->jmps_processed++;
+ if (opcode == BPF_CALL) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ (insn->src_reg != BPF_PSEUDO_KFUNC_CALL &&
+ insn->off != 0) ||
+ (insn->src_reg != BPF_REG_0 &&
+ insn->src_reg != BPF_PSEUDO_CALL &&
+ insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
+ insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) {
+ verbose(env, "BPF_CALL uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (env->cur_state->active_locks) {
+ if ((insn->src_reg == BPF_REG_0 &&
+ insn->imm != BPF_FUNC_spin_unlock) ||
+ (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
+ (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) {
+ verbose(env,
+ "function calls are not allowed while holding a lock\n");
+ return -EINVAL;
+ }
+ }
+ if (insn->src_reg == BPF_PSEUDO_CALL) {
+ err = check_func_call(env, insn, &env->insn_idx);
+ } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
+ err = check_kfunc_call(env, insn, &env->insn_idx);
+ if (!err && is_bpf_throw_kfunc(insn))
+ return process_bpf_exit_full(env, do_print_state, true);
+ } else {
+ err = check_helper_call(env, insn, &env->insn_idx);
+ }
+ if (err)
+ return err;
+
+ mark_reg_scratched(env, BPF_REG_0);
+ } else if (opcode == BPF_JA) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ insn->src_reg != BPF_REG_0 ||
+ insn->dst_reg != BPF_REG_0 ||
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
+ verbose(env, "BPF_JA uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
+ return 0;
+ } else if (opcode == BPF_EXIT) {
+ if (BPF_SRC(insn->code) != BPF_K ||
+ insn->imm != 0 ||
+ insn->src_reg != BPF_REG_0 ||
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
+ verbose(env, "BPF_EXIT uses reserved fields\n");
+ return -EINVAL;
+ }
+ return process_bpf_exit_full(env, do_print_state, false);
+ } else {
+ err = check_cond_jmp_op(env, insn, &env->insn_idx);
+ if (err)
+ return err;
+ }
+ } else if (class == BPF_LD) {
+ u8 mode = BPF_MODE(insn->code);
+
+ if (mode == BPF_ABS || mode == BPF_IND) {
+ err = check_ld_abs(env, insn);
+ if (err)
+ return err;
+
+ } else if (mode == BPF_IMM) {
+ err = check_ld_imm(env, insn);
+ if (err)
+ return err;
+
+ env->insn_idx++;
+ sanitize_mark_insn_seen(env);
+ } else {
+ verbose(env, "invalid BPF_LD mode\n");
+ return -EINVAL;
+ }
+ } else {
+ verbose(env, "unknown insn class %d\n", class);
+ return -EINVAL;
+ }
+
+ env->insn_idx++;
+ return 0;
+}
+
static int do_check(struct bpf_verifier_env *env)
{
bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
- struct bpf_reg_state *regs;
int insn_cnt = env->prog->len;
bool do_print_state = false;
int prev_insn_idx = -1;
for (;;) {
- bool exception_exit = false;
struct bpf_insn *insn;
- u8 class;
int err;
/* reset current history entry on each new instruction */
@@ -19453,7 +19942,6 @@ static int do_check(struct bpf_verifier_env *env)
}
insn = &insns[env->insn_idx];
- class = BPF_CLASS(insn->code);
if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
@@ -19463,6 +19951,7 @@ static int do_check(struct bpf_verifier_env *env)
}
state->last_insn_idx = env->prev_insn_idx;
+ state->insn_idx = env->insn_idx;
if (is_prune_point(env, env->insn_idx)) {
err = is_state_visited(env, env->insn_idx);
@@ -19484,7 +19973,7 @@ static int do_check(struct bpf_verifier_env *env)
}
if (is_jmp_point(env, env->insn_idx)) {
- err = push_insn_history(env, state, 0, 0);
+ err = push_jmp_history(env, state, 0, 0);
if (err)
return err;
}
@@ -19523,215 +20012,60 @@ static int do_check(struct bpf_verifier_env *env)
return err;
}
- regs = cur_regs(env);
sanitize_mark_insn_seen(env);
prev_insn_idx = env->insn_idx;
- if (class == BPF_ALU || class == BPF_ALU64) {
- err = check_alu_op(env, insn);
- if (err)
- return err;
-
- } else if (class == BPF_LDX) {
- bool is_ldsx = BPF_MODE(insn->code) == BPF_MEMSX;
+ /* Reduce verification complexity by stopping speculative path
+ * verification when a nospec is encountered.
+ */
+ if (state->speculative && cur_aux(env)->nospec)
+ goto process_bpf_exit;
- /* Check for reserved fields is already done in
- * resolve_pseudo_ldimm64().
+ err = do_check_insn(env, &do_print_state);
+ if (error_recoverable_with_nospec(err) && state->speculative) {
+ /* Prevent this speculative path from ever reaching the
+ * insn that would have been unsafe to execute.
*/
- err = check_load_mem(env, insn, false, is_ldsx, true,
- "ldx");
- if (err)
- return err;
- } else if (class == BPF_STX) {
- if (BPF_MODE(insn->code) == BPF_ATOMIC) {
- err = check_atomic(env, insn);
- if (err)
- return err;
- env->insn_idx++;
- continue;
- }
-
- if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
- verbose(env, "BPF_STX uses reserved fields\n");
- return -EINVAL;
- }
-
- err = check_store_reg(env, insn, false);
- if (err)
- return err;
- } else if (class == BPF_ST) {
- enum bpf_reg_type dst_reg_type;
-
- if (BPF_MODE(insn->code) != BPF_MEM ||
- insn->src_reg != BPF_REG_0) {
- verbose(env, "BPF_ST uses reserved fields\n");
- return -EINVAL;
- }
- /* check src operand */
- err = check_reg_arg(env, insn->dst_reg, SRC_OP);
- if (err)
- return err;
-
- dst_reg_type = regs[insn->dst_reg].type;
-
- /* check that memory (dst_reg + off) is writeable */
- err = check_mem_access(env, env->insn_idx, insn->dst_reg,
- insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, -1, false, false);
- if (err)
- return err;
-
- err = save_aux_ptr_type(env, dst_reg_type, false);
+ cur_aux(env)->nospec = true;
+ /* If it was an ADD/SUB insn, potentially remove any
+ * markings for alu sanitization.
+ */
+ cur_aux(env)->alu_state = 0;
+ goto process_bpf_exit;
+ } else if (err < 0) {
+ return err;
+ } else if (err == PROCESS_BPF_EXIT) {
+ goto process_bpf_exit;
+ }
+ WARN_ON_ONCE(err);
+
+ if (state->speculative && cur_aux(env)->nospec_result) {
+ /* If we are on a path that performed a jump-op, this
+ * may skip a nospec patched-in after the jump. This can
+ * currently never happen because nospec_result is only
+ * used for the write-ops
+ * `*(size*)(dst_reg+off)=src_reg|imm32` which must
+ * never skip the following insn. Still, add a warning
+ * to document this in case nospec_result is used
+ * elsewhere in the future.
+ */
+ WARN_ON_ONCE(env->insn_idx != prev_insn_idx + 1);
+process_bpf_exit:
+ mark_verifier_state_scratched(env);
+ err = update_branch_counts(env, env->cur_state);
if (err)
return err;
- } else if (class == BPF_JMP || class == BPF_JMP32) {
- u8 opcode = BPF_OP(insn->code);
-
- env->jmps_processed++;
- if (opcode == BPF_CALL) {
- if (BPF_SRC(insn->code) != BPF_K ||
- (insn->src_reg != BPF_PSEUDO_KFUNC_CALL
- && insn->off != 0) ||
- (insn->src_reg != BPF_REG_0 &&
- insn->src_reg != BPF_PSEUDO_CALL &&
- insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
- insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
- verbose(env, "BPF_CALL uses reserved fields\n");
- return -EINVAL;
- }
-
- if (env->cur_state->active_locks) {
- if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) ||
- (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
- (insn->off != 0 || !kfunc_spin_allowed(insn->imm)))) {
- verbose(env, "function calls are not allowed while holding a lock\n");
- return -EINVAL;
- }
- }
- if (insn->src_reg == BPF_PSEUDO_CALL) {
- err = check_func_call(env, insn, &env->insn_idx);
- } else if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) {
- err = check_kfunc_call(env, insn, &env->insn_idx);
- if (!err && is_bpf_throw_kfunc(insn)) {
- exception_exit = true;
- goto process_bpf_exit_full;
- }
- } else {
- err = check_helper_call(env, insn, &env->insn_idx);
- }
- if (err)
- return err;
-
- mark_reg_scratched(env, BPF_REG_0);
- } else if (opcode == BPF_JA) {
- if (BPF_SRC(insn->code) != BPF_K ||
- insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0 ||
- (class == BPF_JMP && insn->imm != 0) ||
- (class == BPF_JMP32 && insn->off != 0)) {
- verbose(env, "BPF_JA uses reserved fields\n");
- return -EINVAL;
- }
-
- if (class == BPF_JMP)
- env->insn_idx += insn->off + 1;
- else
- env->insn_idx += insn->imm + 1;
- continue;
-
- } else if (opcode == BPF_EXIT) {
- if (BPF_SRC(insn->code) != BPF_K ||
- insn->imm != 0 ||
- insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
- verbose(env, "BPF_EXIT uses reserved fields\n");
- return -EINVAL;
- }
-process_bpf_exit_full:
- /* We must do check_reference_leak here before
- * prepare_func_exit to handle the case when
- * state->curframe > 0, it may be a callback
- * function, for which reference_state must
- * match caller reference state when it exits.
- */
- err = check_resource_leak(env, exception_exit, !env->cur_state->curframe,
- "BPF_EXIT instruction in main prog");
- if (err)
- return err;
-
- /* The side effect of the prepare_func_exit
- * which is being skipped is that it frees
- * bpf_func_state. Typically, process_bpf_exit
- * will only be hit with outermost exit.
- * copy_verifier_state in pop_stack will handle
- * freeing of any extra bpf_func_state left over
- * from not processing all nested function
- * exits. We also skip return code checks as
- * they are not needed for exceptional exits.
- */
- if (exception_exit)
- goto process_bpf_exit;
-
- if (state->curframe) {
- /* exit from nested function */
- err = prepare_func_exit(env, &env->insn_idx);
- if (err)
- return err;
- do_print_state = true;
- continue;
- }
-
- err = check_return_code(env, BPF_REG_0, "R0");
- if (err)
- return err;
-process_bpf_exit:
- mark_verifier_state_scratched(env);
- update_branch_counts(env, env->cur_state);
- err = pop_stack(env, &prev_insn_idx,
- &env->insn_idx, pop_log);
- if (err < 0) {
- if (err != -ENOENT)
- return err;
- break;
- } else {
- if (verifier_bug_if(env->cur_state->loop_entry, env,
- "broken loop detection"))
- return -EFAULT;
- do_print_state = true;
- continue;
- }
- } else {
- err = check_cond_jmp_op(env, insn, &env->insn_idx);
- if (err)
- return err;
- }
- } else if (class == BPF_LD) {
- u8 mode = BPF_MODE(insn->code);
-
- if (mode == BPF_ABS || mode == BPF_IND) {
- err = check_ld_abs(env, insn);
- if (err)
- return err;
-
- } else if (mode == BPF_IMM) {
- err = check_ld_imm(env, insn);
- if (err)
+ err = pop_stack(env, &prev_insn_idx, &env->insn_idx,
+ pop_log);
+ if (err < 0) {
+ if (err != -ENOENT)
return err;
-
- env->insn_idx++;
- sanitize_mark_insn_seen(env);
+ break;
} else {
- verbose(env, "invalid BPF_LD mode\n");
- return -EINVAL;
+ do_print_state = true;
+ continue;
}
- } else {
- verbose(env, "unknown insn class %d\n", class);
- return -EINVAL;
}
-
- env->insn_idx++;
}
return 0;
@@ -20803,7 +21137,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
-(subprogs[0].stack_depth + 8));
if (epilogue_cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
} else if (epilogue_cnt) {
/* Save the ARG_PTR_TO_CTX for the epilogue to use */
cnt = 0;
@@ -20826,13 +21160,13 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (ops->gen_prologue || env->seen_direct_write) {
if (!ops->gen_prologue) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
} else if (cnt) {
new_prog = bpf_patch_insn_data(env, 0, insn_buf, cnt);
if (!new_prog)
@@ -20859,6 +21193,29 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
bpf_convert_ctx_access_t convert_ctx_access;
u8 mode;
+ if (env->insn_aux_data[i + delta].nospec) {
+ WARN_ON_ONCE(env->insn_aux_data[i + delta].alu_state);
+ struct bpf_insn patch[] = {
+ BPF_ST_NOSPEC(),
+ *insn,
+ };
+
+ cnt = ARRAY_SIZE(patch);
+ new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ /* This can not be easily merged with the
+ * nospec_result-case, because an insn may require a
+ * nospec before and after itself. Therefore also do not
+ * 'continue' here but potentially apply further
+ * patching to insn. *insn should equal patch[1] now.
+ */
+ }
+
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
@@ -20908,7 +21265,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
}
if (type == BPF_WRITE &&
- env->insn_aux_data[i + delta].sanitize_stack_spill) {
+ env->insn_aux_data[i + delta].nospec_result) {
+ /* nospec_result is only used to mitigate Spectre v4 and
+ * to limit verification-time for Spectre v1.
+ */
struct bpf_insn patch[] = {
*insn,
BPF_ST_NOSPEC(),
@@ -20950,6 +21310,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
* for this case.
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
+ case PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED:
if (type == BPF_READ) {
if (BPF_MODE(insn->code) == BPF_MEM)
insn->code = BPF_LDX | BPF_PROBE_MEM |
@@ -20989,7 +21350,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (type == BPF_WRITE) {
verbose(env, "bpf verifier narrow ctx access misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
size_code = BPF_H;
@@ -21008,7 +21369,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
if (cnt == 0 || cnt >= INSN_BUF_SIZE ||
(ctx_field_size && !target_size)) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (is_narrower_load && size < target_size) {
@@ -21016,7 +21377,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
off, size, size_default) * 8;
if (shift && cnt + 1 >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier narrow ctx load misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
if (ctx_field_size <= 4) {
if (shift)
@@ -21781,7 +22142,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
cnt = env->ops->gen_ld_abs(insn, insn_buf);
if (cnt == 0 || cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
@@ -22117,7 +22478,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_map_ops_generic;
if (cnt <= 0 || cnt >= INSN_BUF_SIZE) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
new_prog = bpf_patch_insn_data(env, i + delta,
@@ -22477,7 +22838,7 @@ next_insn:
!map_ptr->ops->map_poke_untrack ||
!map_ptr->ops->map_poke_run) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
+ return -EFAULT;
}
ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux);
@@ -22667,7 +23028,12 @@ static void free_states(struct bpf_verifier_env *env)
{
struct bpf_verifier_state_list *sl;
struct list_head *head, *pos, *tmp;
- int i;
+ struct bpf_scc_info *info;
+ int i, j;
+
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ while (!pop_stack(env, NULL, NULL, false));
list_for_each_safe(pos, tmp, &env->free_list) {
sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -22676,6 +23042,14 @@ static void free_states(struct bpf_verifier_env *env)
}
INIT_LIST_HEAD(&env->free_list);
+ for (i = 0; i < env->scc_cnt; ++i) {
+ info = env->scc_info[i];
+ for (j = 0; j < info->num_visits; j++)
+ free_backedges(&info->visits[j]);
+ kvfree(info);
+ env->scc_info[i] = NULL;
+ }
+
if (!env->explored_states)
return;
@@ -22703,13 +23077,13 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
env->prev_linfo = NULL;
env->pass_cnt++;
- state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL_ACCOUNT);
if (!state)
return -ENOMEM;
state->curframe = 0;
state->speculative = false;
state->branches = 1;
- state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL_ACCOUNT);
if (!state->frame[0]) {
kfree(state);
return -ENOMEM;
@@ -22812,14 +23186,6 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
ret = do_check(env);
out:
- /* check for NULL is necessary, since cur_state can be freed inside
- * do_check() under memory pressure.
- */
- if (env->cur_state) {
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- }
- while (!pop_stack(env, NULL, NULL, false));
if (!ret && pop_log)
bpf_vlog_reset(&env->log, 0);
free_states(env);
@@ -22935,7 +23301,7 @@ static void print_verification_stats(struct bpf_verifier_env *env)
int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
const struct bpf_ctx_arg_aux *info, u32 cnt)
{
- prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL);
+ prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL_ACCOUNT);
prog->aux->ctx_arg_info_size = cnt;
return prog->aux->ctx_arg_info ? 0 : -ENOMEM;
@@ -23677,6 +24043,7 @@ static bool can_jump(struct bpf_insn *insn)
case BPF_JSLT:
case BPF_JSLE:
case BPF_JCOND:
+ case BPF_JSET:
return true;
}
@@ -23879,7 +24246,7 @@ static int compute_live_registers(struct bpf_verifier_env *env)
* - repeat the computation while {in,out} fields changes for
* any instruction.
*/
- state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL);
+ state = kvcalloc(insn_cnt, sizeof(*state), GFP_KERNEL_ACCOUNT);
if (!state) {
err = -ENOMEM;
goto out;
@@ -23917,6 +24284,10 @@ static int compute_live_registers(struct bpf_verifier_env *env)
if (env->log.level & BPF_LOG_LEVEL2) {
verbose(env, "Live regs before insn:\n");
for (i = 0; i < insn_cnt; ++i) {
+ if (env->insn_aux_data[i].scc)
+ verbose(env, "%3d ", env->insn_aux_data[i].scc);
+ else
+ verbose(env, " ");
verbose(env, "%3d: ", i);
for (j = BPF_REG_0; j < BPF_REG_10; ++j)
if (insn_aux[i].live_regs_before & BIT(j))
@@ -23938,6 +24309,185 @@ out:
return err;
}
+/*
+ * Compute strongly connected components (SCCs) on the CFG.
+ * Assign an SCC number to each instruction, recorded in env->insn_aux[*].scc.
+ * If instruction is a sole member of its SCC and there are no self edges,
+ * assign it SCC number of zero.
+ * Uses a non-recursive adaptation of Tarjan's algorithm for SCC computation.
+ */
+static int compute_scc(struct bpf_verifier_env *env)
+{
+ const u32 NOT_ON_STACK = U32_MAX;
+
+ struct bpf_insn_aux_data *aux = env->insn_aux_data;
+ const u32 insn_cnt = env->prog->len;
+ int stack_sz, dfs_sz, err = 0;
+ u32 *stack, *pre, *low, *dfs;
+ u32 succ_cnt, i, j, t, w;
+ u32 next_preorder_num;
+ u32 next_scc_id;
+ bool assign_scc;
+ u32 succ[2];
+
+ next_preorder_num = 1;
+ next_scc_id = 1;
+ /*
+ * - 'stack' accumulates vertices in DFS order, see invariant comment below;
+ * - 'pre[t] == p' => preorder number of vertex 't' is 'p';
+ * - 'low[t] == n' => smallest preorder number of the vertex reachable from 't' is 'n';
+ * - 'dfs' DFS traversal stack, used to emulate explicit recursion.
+ */
+ stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ pre = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ low = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL_ACCOUNT);
+ dfs = kvcalloc(insn_cnt, sizeof(*dfs), GFP_KERNEL_ACCOUNT);
+ if (!stack || !pre || !low || !dfs) {
+ err = -ENOMEM;
+ goto exit;
+ }
+ /*
+ * References:
+ * [1] R. Tarjan "Depth-First Search and Linear Graph Algorithms"
+ * [2] D. J. Pearce "A Space-Efficient Algorithm for Finding Strongly Connected Components"
+ *
+ * The algorithm maintains the following invariant:
+ * - suppose there is a path 'u' ~> 'v', such that 'pre[v] < pre[u]';
+ * - then, vertex 'u' remains on stack while vertex 'v' is on stack.
+ *
+ * Consequently:
+ * - If 'low[v] < pre[v]', there is a path from 'v' to some vertex 'u',
+ * such that 'pre[u] == low[v]'; vertex 'u' is currently on the stack,
+ * and thus there is an SCC (loop) containing both 'u' and 'v'.
+ * - If 'low[v] == pre[v]', loops containing 'v' have been explored,
+ * and 'v' can be considered the root of some SCC.
+ *
+ * Here is a pseudo-code for an explicitly recursive version of the algorithm:
+ *
+ * NOT_ON_STACK = insn_cnt + 1
+ * pre = [0] * insn_cnt
+ * low = [0] * insn_cnt
+ * scc = [0] * insn_cnt
+ * stack = []
+ *
+ * next_preorder_num = 1
+ * next_scc_id = 1
+ *
+ * def recur(w):
+ * nonlocal next_preorder_num
+ * nonlocal next_scc_id
+ *
+ * pre[w] = next_preorder_num
+ * low[w] = next_preorder_num
+ * next_preorder_num += 1
+ * stack.append(w)
+ * for s in successors(w):
+ * # Note: for classic algorithm the block below should look as:
+ * #
+ * # if pre[s] == 0:
+ * # recur(s)
+ * # low[w] = min(low[w], low[s])
+ * # elif low[s] != NOT_ON_STACK:
+ * # low[w] = min(low[w], pre[s])
+ * #
+ * # But replacing both 'min' instructions with 'low[w] = min(low[w], low[s])'
+ * # does not break the invariant and makes itartive version of the algorithm
+ * # simpler. See 'Algorithm #3' from [2].
+ *
+ * # 's' not yet visited
+ * if pre[s] == 0:
+ * recur(s)
+ * # if 's' is on stack, pick lowest reachable preorder number from it;
+ * # if 's' is not on stack 'low[s] == NOT_ON_STACK > low[w]',
+ * # so 'min' would be a noop.
+ * low[w] = min(low[w], low[s])
+ *
+ * if low[w] == pre[w]:
+ * # 'w' is the root of an SCC, pop all vertices
+ * # below 'w' on stack and assign same SCC to them.
+ * while True:
+ * t = stack.pop()
+ * low[t] = NOT_ON_STACK
+ * scc[t] = next_scc_id
+ * if t == w:
+ * break
+ * next_scc_id += 1
+ *
+ * for i in range(0, insn_cnt):
+ * if pre[i] == 0:
+ * recur(i)
+ *
+ * Below implementation replaces explicit recusion with array 'dfs'.
+ */
+ for (i = 0; i < insn_cnt; i++) {
+ if (pre[i])
+ continue;
+ stack_sz = 0;
+ dfs_sz = 1;
+ dfs[0] = i;
+dfs_continue:
+ while (dfs_sz) {
+ w = dfs[dfs_sz - 1];
+ if (pre[w] == 0) {
+ low[w] = next_preorder_num;
+ pre[w] = next_preorder_num;
+ next_preorder_num++;
+ stack[stack_sz++] = w;
+ }
+ /* Visit 'w' successors */
+ succ_cnt = insn_successors(env->prog, w, succ);
+ for (j = 0; j < succ_cnt; ++j) {
+ if (pre[succ[j]]) {
+ low[w] = min(low[w], low[succ[j]]);
+ } else {
+ dfs[dfs_sz++] = succ[j];
+ goto dfs_continue;
+ }
+ }
+ /*
+ * Preserve the invariant: if some vertex above in the stack
+ * is reachable from 'w', keep 'w' on the stack.
+ */
+ if (low[w] < pre[w]) {
+ dfs_sz--;
+ goto dfs_continue;
+ }
+ /*
+ * Assign SCC number only if component has two or more elements,
+ * or if component has a self reference.
+ */
+ assign_scc = stack[stack_sz - 1] != w;
+ for (j = 0; j < succ_cnt; ++j) {
+ if (succ[j] == w) {
+ assign_scc = true;
+ break;
+ }
+ }
+ /* Pop component elements from stack */
+ do {
+ t = stack[--stack_sz];
+ low[t] = NOT_ON_STACK;
+ if (assign_scc)
+ aux[t].scc = next_scc_id;
+ } while (t != w);
+ if (assign_scc)
+ next_scc_id++;
+ dfs_sz--;
+ }
+ }
+ env->scc_info = kvcalloc(next_scc_id, sizeof(*env->scc_info), GFP_KERNEL_ACCOUNT);
+ if (!env->scc_info) {
+ err = -ENOMEM;
+ goto exit;
+ }
+exit:
+ kvfree(stack);
+ kvfree(pre);
+ kvfree(low);
+ kvfree(dfs);
+ return err;
+}
+
int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
{
u64 start_time = ktime_get_ns();
@@ -23946,6 +24496,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
u32 log_true_size;
bool is_priv;
+ BTF_TYPE_EMIT(enum bpf_features);
+
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
return -EINVAL;
@@ -23953,7 +24505,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
/* 'struct bpf_verifier_env' can be global, but since it's not small,
* allocate/free it every time bpf_check() is called
*/
- env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL);
+ env = kvzalloc(sizeof(struct bpf_verifier_env), GFP_KERNEL_ACCOUNT);
if (!env)
return -ENOMEM;
@@ -24016,7 +24568,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
env->explored_states = kvcalloc(state_htab_size(env),
sizeof(struct list_head),
- GFP_USER);
+ GFP_KERNEL_ACCOUNT);
ret = -ENOMEM;
if (!env->explored_states)
goto skip_full_check;
@@ -24059,6 +24611,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (ret)
goto skip_full_check;
+ ret = compute_scc(env);
+ if (ret < 0)
+ goto skip_full_check;
+
ret = compute_live_registers(env);
if (ret < 0)
goto skip_full_check;
@@ -24143,7 +24699,7 @@ skip_full_check:
/* if program passed verifier, update used_maps in bpf_prog_info */
env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt,
sizeof(env->used_maps[0]),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!env->prog->aux->used_maps) {
ret = -ENOMEM;
@@ -24158,7 +24714,7 @@ skip_full_check:
/* if program passed verifier, update used_btfs in bpf_prog_aux */
env->prog->aux->used_btfs = kmalloc_array(env->used_btf_cnt,
sizeof(env->used_btfs[0]),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!env->prog->aux->used_btfs) {
ret = -ENOMEM;
goto err_release_maps;
@@ -24199,9 +24755,9 @@ err_unlock:
if (!is_priv)
mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
- kvfree(env->insn_hist);
err_free_env:
kvfree(env->cfg.insn_postorder);
+ kvfree(env->scc_info);
kvfree(env);
return ret;
}
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a723b7dc6e4e..312c6a8b55bb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2074,6 +2074,11 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
for_each_subsys(ss, ssid)
INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
+#ifdef CONFIG_CGROUP_BPF
+ for (int i = 0; i < ARRAY_SIZE(cgrp->bpf.revisions); i++)
+ cgrp->bpf.revisions[i] = 1;
+#endif
+
init_waitqueue_head(&cgrp->offline_waitq);
INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
}
diff --git a/kernel/cgroup/legacy_freezer.c b/kernel/cgroup/legacy_freezer.c
index 039d1eb2f215..507b8f19a262 100644
--- a/kernel/cgroup/legacy_freezer.c
+++ b/kernel/cgroup/legacy_freezer.c
@@ -188,13 +188,12 @@ static void freezer_attach(struct cgroup_taskset *tset)
if (!(freezer->state & CGROUP_FREEZING)) {
__thaw_task(task);
} else {
- freeze_task(task);
-
/* clear FROZEN and propagate upwards */
while (freezer && (freezer->state & CGROUP_FROZEN)) {
freezer->state &= ~CGROUP_FROZEN;
freezer = parent_freezer(freezer);
}
+ freeze_task(task);
}
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f34c99f8ce8f..1f746469fda5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -207,6 +207,19 @@ static void perf_ctx_unlock(struct perf_cpu_context *cpuctx,
__perf_ctx_unlock(&cpuctx->ctx);
}
+typedef struct {
+ struct perf_cpu_context *cpuctx;
+ struct perf_event_context *ctx;
+} class_perf_ctx_lock_t;
+
+static inline void class_perf_ctx_lock_destructor(class_perf_ctx_lock_t *_T)
+{ perf_ctx_unlock(_T->cpuctx, _T->ctx); }
+
+static inline class_perf_ctx_lock_t
+class_perf_ctx_lock_constructor(struct perf_cpu_context *cpuctx,
+ struct perf_event_context *ctx)
+{ perf_ctx_lock(cpuctx, ctx); return (class_perf_ctx_lock_t){ cpuctx, ctx }; }
+
#define TASK_TOMBSTONE ((void *)-1L)
static bool is_kernel_event(struct perf_event *event)
@@ -944,7 +957,13 @@ static void perf_cgroup_switch(struct task_struct *task)
if (READ_ONCE(cpuctx->cgrp) == cgrp)
return;
- perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+ guard(perf_ctx_lock)(cpuctx, cpuctx->task_ctx);
+ /*
+ * Re-check, could've raced vs perf_remove_from_context().
+ */
+ if (READ_ONCE(cpuctx->cgrp) == NULL)
+ return;
+
perf_ctx_disable(&cpuctx->ctx, true);
ctx_sched_out(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
@@ -962,7 +981,6 @@ static void perf_cgroup_switch(struct task_struct *task)
ctx_sched_in(&cpuctx->ctx, NULL, EVENT_ALL|EVENT_CGROUP);
perf_ctx_enable(&cpuctx->ctx, true);
- perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
static int perf_cgroup_ensure_storage(struct perf_event *event,
@@ -2120,18 +2138,6 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
if (event->group_leader == event)
del_event_from_groups(event, ctx);
- /*
- * If event was in error state, then keep it
- * that way, otherwise bogus counts will be
- * returned on read(). The only way to get out
- * of error state is by explicit re-enabling
- * of the event
- */
- if (event->state > PERF_EVENT_STATE_OFF) {
- perf_cgroup_event_disable(event, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_OFF);
- }
-
ctx->generation++;
event->pmu_ctx->nr_events--;
}
@@ -2149,8 +2155,9 @@ perf_aux_output_match(struct perf_event *event, struct perf_event *aux_event)
}
static void put_event(struct perf_event *event);
-static void event_sched_out(struct perf_event *event,
- struct perf_event_context *ctx);
+static void __event_disable(struct perf_event *event,
+ struct perf_event_context *ctx,
+ enum perf_event_state state);
static void perf_put_aux_event(struct perf_event *event)
{
@@ -2183,8 +2190,7 @@ static void perf_put_aux_event(struct perf_event *event)
* state so that we don't try to schedule it again. Note
* that perf_event_enable() will clear the ERROR status.
*/
- event_sched_out(iter, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
+ __event_disable(iter, ctx, PERF_EVENT_STATE_ERROR);
}
}
@@ -2242,18 +2248,6 @@ static inline struct list_head *get_event_list(struct perf_event *event)
&event->pmu_ctx->flexible_active;
}
-/*
- * Events that have PERF_EV_CAP_SIBLING require being part of a group and
- * cannot exist on their own, schedule them out and move them into the ERROR
- * state. Also see _perf_event_enable(), it will not be able to recover
- * this ERROR state.
- */
-static inline void perf_remove_sibling_event(struct perf_event *event)
-{
- event_sched_out(event, event->ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_ERROR);
-}
-
static void perf_group_detach(struct perf_event *event)
{
struct perf_event *leader = event->group_leader;
@@ -2289,8 +2283,15 @@ static void perf_group_detach(struct perf_event *event)
*/
list_for_each_entry_safe(sibling, tmp, &event->sibling_list, sibling_list) {
+ /*
+ * Events that have PERF_EV_CAP_SIBLING require being part of
+ * a group and cannot exist on their own, schedule them out
+ * and move them into the ERROR state. Also see
+ * _perf_event_enable(), it will not be able to recover this
+ * ERROR state.
+ */
if (sibling->event_caps & PERF_EV_CAP_SIBLING)
- perf_remove_sibling_event(sibling);
+ __event_disable(sibling, ctx, PERF_EVENT_STATE_ERROR);
sibling->group_leader = sibling;
list_del_init(&sibling->sibling_list);
@@ -2493,11 +2494,14 @@ __perf_remove_from_context(struct perf_event *event,
state = PERF_EVENT_STATE_EXIT;
if (flags & DETACH_REVOKE)
state = PERF_EVENT_STATE_REVOKED;
- if (flags & DETACH_DEAD) {
- event->pending_disable = 1;
+ if (flags & DETACH_DEAD)
state = PERF_EVENT_STATE_DEAD;
- }
+
event_sched_out(event, ctx);
+
+ if (event->state > PERF_EVENT_STATE_OFF)
+ perf_cgroup_event_disable(event, ctx);
+
perf_event_set_state(event, min(event->state, state));
if (flags & DETACH_GROUP)
@@ -2562,6 +2566,15 @@ static void perf_remove_from_context(struct perf_event *event, unsigned long fla
event_function_call(event, __perf_remove_from_context, (void *)flags);
}
+static void __event_disable(struct perf_event *event,
+ struct perf_event_context *ctx,
+ enum perf_event_state state)
+{
+ event_sched_out(event, ctx);
+ perf_cgroup_event_disable(event, ctx);
+ perf_event_set_state(event, state);
+}
+
/*
* Cross CPU call to disable a performance event
*/
@@ -2576,13 +2589,18 @@ static void __perf_event_disable(struct perf_event *event,
perf_pmu_disable(event->pmu_ctx->pmu);
ctx_time_update_event(ctx, event);
+ /*
+ * When disabling a group leader, the whole group becomes ineligible
+ * to run, so schedule out the full group.
+ */
if (event == event->group_leader)
group_sched_out(event, ctx);
- else
- event_sched_out(event, ctx);
- perf_event_set_state(event, PERF_EVENT_STATE_OFF);
- perf_cgroup_event_disable(event, ctx);
+ /*
+ * But only mark the leader OFF; the siblings will remain
+ * INACTIVE.
+ */
+ __event_disable(event, ctx, PERF_EVENT_STATE_OFF);
perf_pmu_enable(event->pmu_ctx->pmu);
}
@@ -2656,8 +2674,8 @@ static void perf_event_unthrottle(struct perf_event *event, bool start)
static void perf_event_throttle(struct perf_event *event)
{
- event->pmu->stop(event, 0);
event->hw.interrupts = MAX_INTERRUPTS;
+ event->pmu->stop(event, 0);
if (event == event->group_leader)
perf_log_throttle(event, 0);
}
@@ -7439,6 +7457,10 @@ perf_sample_ustack_size(u16 stack_size, u16 header_size,
if (!regs)
return 0;
+ /* No mm, no stack, no dump. */
+ if (!current->mm)
+ return 0;
+
/*
* Check if we fit in with the requested stack size into the:
* - TASK_SIZE
@@ -8150,6 +8172,9 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
const u32 max_stack = event->attr.sample_max_stack;
struct perf_callchain_entry *callchain;
+ if (!current->mm)
+ user = false;
+
if (!kernel && !user)
return &__empty_callchain;
@@ -11749,7 +11774,12 @@ static void perf_swevent_cancel_hrtimer(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
- if (is_sampling_event(event)) {
+ /*
+ * The throttle can be triggered in the hrtimer handler.
+ * The HRTIMER_NORESTART should be used to stop the timer,
+ * rather than hrtimer_cancel(). See perf_swevent_hrtimer()
+ */
+ if (is_sampling_event(event) && (hwc->interrupts != MAX_INTERRUPTS)) {
ktime_t remaining = hrtimer_get_remaining(&hwc->hrtimer);
local64_set(&hwc->period_left, ktime_to_ns(remaining));
@@ -11804,7 +11834,8 @@ static void cpu_clock_event_start(struct perf_event *event, int flags)
static void cpu_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
- cpu_clock_event_update(event);
+ if (flags & PERF_EF_UPDATE)
+ cpu_clock_event_update(event);
}
static int cpu_clock_event_add(struct perf_event *event, int flags)
@@ -11882,7 +11913,8 @@ static void task_clock_event_start(struct perf_event *event, int flags)
static void task_clock_event_stop(struct perf_event *event, int flags)
{
perf_swevent_cancel_hrtimer(event);
- task_clock_event_update(event, event->ctx->time);
+ if (flags & PERF_EF_UPDATE)
+ task_clock_event_update(event, event->ctx->time);
}
static int task_clock_event_add(struct perf_event *event, int flags)
diff --git a/kernel/exit.c b/kernel/exit.c
index bd743900354c..bb184a67ac73 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -940,6 +940,15 @@ void __noreturn do_exit(long code)
taskstats_exit(tsk, group_dead);
trace_sched_process_exit(tsk, group_dead);
+ /*
+ * Since sampling can touch ->mm, make sure to stop everything before we
+ * tear it down.
+ *
+ * Also flushes inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ */
+ perf_event_exit_task(tsk);
+
exit_mm();
if (group_dead)
@@ -955,14 +964,6 @@ void __noreturn do_exit(long code)
exit_task_work(tsk);
exit_thread(tsk);
- /*
- * Flush inherited counters to the parent - before the parent
- * gets woken up by child-exit notifications.
- *
- * because of cgroup mode, must be called before cgroup_exit()
- */
- perf_event_exit_task(tsk);
-
sched_autogroup_exit_task(tsk);
cgroup_exit(tsk);
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 565f9717c6ca..90d53fb0ee9e 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -583,8 +583,8 @@ int get_futex_key(u32 __user *uaddr, unsigned int flags, union futex_key *key,
if (futex_get_value(&node, naddr))
return -EFAULT;
- if (node != FUTEX_NO_NODE &&
- (node >= MAX_NUMNODES || !node_possible(node)))
+ if ((node != FUTEX_NO_NODE) &&
+ ((unsigned int)node >= MAX_NUMNODES || !node_possible(node)))
return -EINVAL;
}
@@ -1629,6 +1629,16 @@ again:
mm->futex_phash_new = NULL;
if (fph) {
+ if (cur && (!cur->hash_mask || cur->immutable)) {
+ /*
+ * If two threads simultaneously request the global
+ * hash then the first one performs the switch,
+ * the second one returns here.
+ */
+ free = fph;
+ mm->futex_phash_new = new;
+ return -EBUSY;
+ }
if (cur && !new) {
/*
* If we have an existing hash, but do not yet have
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b0e0a7332993..2b274007e8ba 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -205,6 +205,14 @@ __irq_startup_managed(struct irq_desc *desc, const struct cpumask *aff,
void irq_startup_managed(struct irq_desc *desc)
{
+ struct irq_data *d = irq_desc_get_irq_data(desc);
+
+ /*
+ * Clear managed-shutdown flag, so we don't repeat managed-startup for
+ * multiple hotplugs, and cause imbalanced disable depth.
+ */
+ irqd_clr_managed_shutdown(d);
+
/*
* Only start it up when the disable depth is 1, so that a disable,
* hotunplug, hotplug sequence does not end up enabling it during
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index f07529ae4895..755346ea9819 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -210,13 +210,6 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
!irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
return;
- /*
- * Don't restore suspended interrupts here when a system comes back
- * from S3. They are reenabled via resume_device_irqs().
- */
- if (desc->istate & IRQS_SUSPENDED)
- return;
-
if (irqd_is_managed_and_shutdown(data))
irq_startup_managed(desc);
diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c
index 1a3d483548e2..ae4c9cbd1b4b 100644
--- a/kernel/irq/irq_sim.c
+++ b/kernel/irq/irq_sim.c
@@ -202,7 +202,7 @@ struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode,
void *data)
{
struct irq_sim_work_ctx *work_ctx __free(kfree) =
- kmalloc(sizeof(*work_ctx), GFP_KERNEL);
+ kzalloc(sizeof(*work_ctx), GFP_KERNEL);
if (!work_ctx)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 69b953551677..5a21dbe17950 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -164,11 +164,21 @@ static int __kho_preserve_order(struct kho_mem_track *track, unsigned long pfn,
}
/* almost as free_reserved_page(), just don't free the page */
-static void kho_restore_page(struct page *page)
+static void kho_restore_page(struct page *page, unsigned int order)
{
- ClearPageReserved(page);
- init_page_count(page);
- adjust_managed_page_count(page, 1);
+ unsigned int nr_pages = (1 << order);
+
+ /* Head page gets refcount of 1. */
+ set_page_count(page, 1);
+
+ /* For higher order folios, tail pages get a page count of zero. */
+ for (unsigned int i = 1; i < nr_pages; i++)
+ set_page_count(page + i, 0);
+
+ if (order > 0)
+ prep_compound_page(page, order);
+
+ adjust_managed_page_count(page, nr_pages);
}
/**
@@ -186,15 +196,10 @@ struct folio *kho_restore_folio(phys_addr_t phys)
return NULL;
order = page->private;
- if (order) {
- if (order > MAX_PAGE_ORDER)
- return NULL;
-
- prep_compound_page(page, order);
- } else {
- kho_restore_page(page);
- }
+ if (order > MAX_PAGE_ORDER)
+ return NULL;
+ kho_restore_page(page, order);
return page_folio(page);
}
EXPORT_SYMBOL_GPL(kho_restore_folio);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index e8a4b720d7d2..14d4499c6fc3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3072,6 +3072,10 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in)
/* Misaligned rcu_head! */
WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1));
+ /* Avoid NULL dereference if callback is NULL. */
+ if (WARN_ON_ONCE(!func))
+ return;
+
if (debug_rcu_head_queue(head)) {
/*
* Probable double call_rcu(), so leak the callback.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dce50fa57471..8988d38d46a3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8545,7 +8545,7 @@ void __init sched_init(void)
init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_EXT_GROUP_SCHED
- root_task_group.scx_weight = CGROUP_WEIGHT_DFL;
+ scx_tg_init(&root_task_group);
#endif /* CONFIG_EXT_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -8985,7 +8985,7 @@ struct task_group *sched_create_group(struct task_group *parent)
if (!alloc_rt_sched_group(tg, parent))
goto err;
- scx_group_set_weight(tg, CGROUP_WEIGHT_DFL);
+ scx_tg_init(tg);
alloc_uclamp_sched_group(tg, parent);
return tg;
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 2c41c78be61e..b498d867ba21 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4092,6 +4092,11 @@ bool scx_can_stop_tick(struct rq *rq)
DEFINE_STATIC_PERCPU_RWSEM(scx_cgroup_rwsem);
static bool scx_cgroup_enabled;
+void scx_tg_init(struct task_group *tg)
+{
+ tg->scx_weight = CGROUP_WEIGHT_DFL;
+}
+
int scx_tg_online(struct task_group *tg)
{
struct scx_sched *sch = scx_root;
@@ -4241,12 +4246,12 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
percpu_down_read(&scx_cgroup_rwsem);
- if (scx_cgroup_enabled && tg->scx_weight != weight) {
- if (SCX_HAS_OP(sch, cgroup_set_weight))
- SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
- tg_cgrp(tg), weight);
- tg->scx_weight = weight;
- }
+ if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
+ tg->scx_weight != weight)
+ SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
+ tg_cgrp(tg), weight);
+
+ tg->scx_weight = weight;
percpu_up_read(&scx_cgroup_rwsem);
}
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 6e5072f57771..a75835c23f15 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -79,6 +79,7 @@ static inline void scx_update_idle(struct rq *rq, bool idle, bool do_notify) {}
#ifdef CONFIG_CGROUP_SCHED
#ifdef CONFIG_EXT_GROUP_SCHED
+void scx_tg_init(struct task_group *tg);
int scx_tg_online(struct task_group *tg);
void scx_tg_offline(struct task_group *tg);
int scx_cgroup_can_attach(struct cgroup_taskset *tset);
@@ -88,6 +89,7 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
void scx_group_set_idle(struct task_group *tg, bool idle);
#else /* CONFIG_EXT_GROUP_SCHED */
+static inline void scx_tg_init(struct task_group *tg) {}
static inline int scx_tg_online(struct task_group *tg) { return 0; }
static inline void scx_tg_offline(struct task_group *tg) {}
static inline int scx_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; }
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 50e8d04ab661..2e5b89d7d866 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -1406,6 +1406,15 @@ void run_posix_cpu_timers(void)
lockdep_assert_irqs_disabled();
/*
+ * Ensure that release_task(tsk) can't happen while
+ * handle_posix_cpu_timers() is running. Otherwise, a concurrent
+ * posix_cpu_timer_del() may fail to lock_task_sighand(tsk) and
+ * miss timer->it.cpu.firing != 0.
+ */
+ if (tsk->exit_state)
+ return;
+
+ /*
* If the actual expiry is deferred to task work context and the
* work is already scheduled there is no point to do anything here.
*/
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 132c8be6f635..0a06ea6638fe 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1270,7 +1270,7 @@ __bpf_kfunc_start_defs();
* Return: a bpf_key pointer with a valid key pointer if the key is found, a
* NULL pointer otherwise.
*/
-__bpf_kfunc struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+__bpf_kfunc struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags)
{
key_ref_t key_ref;
struct bpf_key *bkey;
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index ea8b364b6818..08141f105c95 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1437,10 +1437,8 @@ static void filter_free_subsystem_filters(struct trace_subsystem_dir *dir,
INIT_LIST_HEAD(&head->list);
item = kmalloc(sizeof(*item), GFP_KERNEL);
- if (!item) {
- kfree(head);
+ if (!item)
goto free_now;
- }
item->filter = filter;
list_add_tail(&item->list, &head->list);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 9234e2c39abf..14d74a7491b8 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -455,10 +455,16 @@ static int graph_trace_init(struct trace_array *tr)
return 0;
}
+static struct tracer graph_trace;
+
static int ftrace_graph_trace_args(struct trace_array *tr, int set)
{
trace_func_graph_ent_t entry;
+ /* Do nothing if the current tracer is not this tracer */
+ if (tr->current_trace != &graph_trace)
+ return 0;
+
if (set)
entry = trace_graph_entry_args;
else
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 97f37b5bae66..9f9148075828 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -7767,7 +7767,8 @@ void __init workqueue_init_early(void)
restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask);
cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask);
-
+ cpumask_andnot(wq_isolated_cpumask, cpu_possible_mask,
+ housekeeping_cpumask(HK_TYPE_DOMAIN));
pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC);
unbound_wq_update_pwq_attrs_buf = alloc_workqueue_attrs();
diff --git a/lib/Kconfig b/lib/Kconfig
index 6c1b8f184267..37db228f70a9 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -716,6 +716,7 @@ config GENERIC_LIB_DEVMEM_IS_ALLOWED
config PLDMFW
bool
+ select CRC32
default n
config ASN1_ENCODER
diff --git a/lib/crypto/Makefile b/lib/crypto/Makefile
index 3e79283b617d..b0c0f8aea269 100644
--- a/lib/crypto/Makefile
+++ b/lib/crypto/Makefile
@@ -35,6 +35,10 @@ obj-$(CONFIG_CRYPTO_LIB_CURVE25519_GENERIC) += libcurve25519-generic.o
libcurve25519-generic-y := curve25519-fiat32.o
libcurve25519-generic-$(CONFIG_ARCH_SUPPORTS_INT128) := curve25519-hacl64.o
libcurve25519-generic-y += curve25519-generic.o
+# clang versions prior to 18 may blow out the stack with KASAN
+ifeq ($(call clang-min-version, 180000),)
+KASAN_SANITIZE_curve25519-hacl64.o := n
+endif
obj-$(CONFIG_CRYPTO_LIB_CURVE25519) += libcurve25519.o
libcurve25519-y += curve25519.o
@@ -62,7 +66,7 @@ libsha256-generic-y := sha256-generic.o
obj-$(CONFIG_MPILIB) += mpi/
-obj-$(CONFIG_CRYPTO_SELFTESTS) += simd.o
+obj-$(CONFIG_CRYPTO_SELFTESTS_FULL) += simd.o
obj-$(CONFIG_CRYPTO_LIB_SM3) += libsm3.o
libsm3-y := sm3.o
diff --git a/lib/crypto/aescfb.c b/lib/crypto/aescfb.c
index 437613265e14..2f09ae92ffa0 100644
--- a/lib/crypto/aescfb.c
+++ b/lib/crypto/aescfb.c
@@ -106,11 +106,11 @@ MODULE_LICENSE("GPL");
*/
static struct {
- u8 ptext[64];
- u8 ctext[64];
+ u8 ptext[64] __nonstring;
+ u8 ctext[64] __nonstring;
- u8 key[AES_MAX_KEY_SIZE];
- u8 iv[AES_BLOCK_SIZE];
+ u8 key[AES_MAX_KEY_SIZE] __nonstring;
+ u8 iv[AES_BLOCK_SIZE] __nonstring;
int klen;
int len;
diff --git a/lib/crypto/aesgcm.c b/lib/crypto/aesgcm.c
index 277824d6b4af..faa4dee9bb1b 100644
--- a/lib/crypto/aesgcm.c
+++ b/lib/crypto/aesgcm.c
@@ -205,19 +205,19 @@ MODULE_LICENSE("GPL");
* Test code below. Vectors taken from crypto/testmgr.h
*/
-static const u8 __initconst ctext0[16] =
+static const u8 __initconst ctext0[16] __nonstring =
"\x58\xe2\xfc\xce\xfa\x7e\x30\x61"
"\x36\x7f\x1d\x57\xa4\xe7\x45\x5a";
static const u8 __initconst ptext1[16];
-static const u8 __initconst ctext1[32] =
+static const u8 __initconst ctext1[32] __nonstring =
"\x03\x88\xda\xce\x60\xb6\xa3\x92"
"\xf3\x28\xc2\xb9\x71\xb2\xfe\x78"
"\xab\x6e\x47\xd4\x2c\xec\x13\xbd"
"\xf5\x3a\x67\xb2\x12\x57\xbd\xdf";
-static const u8 __initconst ptext2[64] =
+static const u8 __initconst ptext2[64] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -227,7 +227,7 @@ static const u8 __initconst ptext2[64] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
-static const u8 __initconst ctext2[80] =
+static const u8 __initconst ctext2[80] __nonstring =
"\x42\x83\x1e\xc2\x21\x77\x74\x24"
"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
@@ -239,7 +239,7 @@ static const u8 __initconst ctext2[80] =
"\x4d\x5c\x2a\xf3\x27\xcd\x64\xa6"
"\x2c\xf3\x5a\xbd\x2b\xa6\xfa\xb4";
-static const u8 __initconst ptext3[60] =
+static const u8 __initconst ptext3[60] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -249,7 +249,7 @@ static const u8 __initconst ptext3[60] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39";
-static const u8 __initconst ctext3[76] =
+static const u8 __initconst ctext3[76] __nonstring =
"\x42\x83\x1e\xc2\x21\x77\x74\x24"
"\x4b\x72\x21\xb7\x84\xd0\xd4\x9c"
"\xe3\xaa\x21\x2f\x2c\x02\xa4\xe0"
@@ -261,17 +261,17 @@ static const u8 __initconst ctext3[76] =
"\x5b\xc9\x4f\xbc\x32\x21\xa5\xdb"
"\x94\xfa\xe9\x5a\xe7\x12\x1a\x47";
-static const u8 __initconst ctext4[16] =
+static const u8 __initconst ctext4[16] __nonstring =
"\xcd\x33\xb2\x8a\xc7\x73\xf7\x4b"
"\xa0\x0e\xd1\xf3\x12\x57\x24\x35";
-static const u8 __initconst ctext5[32] =
+static const u8 __initconst ctext5[32] __nonstring =
"\x98\xe7\x24\x7c\x07\xf0\xfe\x41"
"\x1c\x26\x7e\x43\x84\xb0\xf6\x00"
"\x2f\xf5\x8d\x80\x03\x39\x27\xab"
"\x8e\xf4\xd4\x58\x75\x14\xf0\xfb";
-static const u8 __initconst ptext6[64] =
+static const u8 __initconst ptext6[64] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -281,7 +281,7 @@ static const u8 __initconst ptext6[64] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
-static const u8 __initconst ctext6[80] =
+static const u8 __initconst ctext6[80] __nonstring =
"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
@@ -293,17 +293,17 @@ static const u8 __initconst ctext6[80] =
"\x99\x24\xa7\xc8\x58\x73\x36\xbf"
"\xb1\x18\x02\x4d\xb8\x67\x4a\x14";
-static const u8 __initconst ctext7[16] =
+static const u8 __initconst ctext7[16] __nonstring =
"\x53\x0f\x8a\xfb\xc7\x45\x36\xb9"
"\xa9\x63\xb4\xf1\xc4\xcb\x73\x8b";
-static const u8 __initconst ctext8[32] =
+static const u8 __initconst ctext8[32] __nonstring =
"\xce\xa7\x40\x3d\x4d\x60\x6b\x6e"
"\x07\x4e\xc5\xd3\xba\xf3\x9d\x18"
"\xd0\xd1\xc8\xa7\x99\x99\x6b\xf0"
"\x26\x5b\x98\xb5\xd4\x8a\xb9\x19";
-static const u8 __initconst ptext9[64] =
+static const u8 __initconst ptext9[64] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -313,7 +313,7 @@ static const u8 __initconst ptext9[64] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39\x1a\xaf\xd2\x55";
-static const u8 __initconst ctext9[80] =
+static const u8 __initconst ctext9[80] __nonstring =
"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
@@ -325,7 +325,7 @@ static const u8 __initconst ctext9[80] =
"\xb0\x94\xda\xc5\xd9\x34\x71\xbd"
"\xec\x1a\x50\x22\x70\xe3\xcc\x6c";
-static const u8 __initconst ptext10[60] =
+static const u8 __initconst ptext10[60] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -335,7 +335,7 @@ static const u8 __initconst ptext10[60] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39";
-static const u8 __initconst ctext10[76] =
+static const u8 __initconst ctext10[76] __nonstring =
"\x52\x2d\xc1\xf0\x99\x56\x7d\x07"
"\xf4\x7f\x37\xa3\x2a\x84\x42\x7d"
"\x64\x3a\x8c\xdc\xbf\xe5\xc0\xc9"
@@ -347,7 +347,7 @@ static const u8 __initconst ctext10[76] =
"\x76\xfc\x6e\xce\x0f\x4e\x17\x68"
"\xcd\xdf\x88\x53\xbb\x2d\x55\x1b";
-static const u8 __initconst ptext11[60] =
+static const u8 __initconst ptext11[60] __nonstring =
"\xd9\x31\x32\x25\xf8\x84\x06\xe5"
"\xa5\x59\x09\xc5\xaf\xf5\x26\x9a"
"\x86\xa7\xa9\x53\x15\x34\xf7\xda"
@@ -357,7 +357,7 @@ static const u8 __initconst ptext11[60] =
"\xb1\x6a\xed\xf5\xaa\x0d\xe6\x57"
"\xba\x63\x7b\x39";
-static const u8 __initconst ctext11[76] =
+static const u8 __initconst ctext11[76] __nonstring =
"\x39\x80\xca\x0b\x3c\x00\xe8\x41"
"\xeb\x06\xfa\xc4\x87\x2a\x27\x57"
"\x85\x9e\x1c\xea\xa6\xef\xd9\x84"
@@ -369,7 +369,7 @@ static const u8 __initconst ctext11[76] =
"\x25\x19\x49\x8e\x80\xf1\x47\x8f"
"\x37\xba\x55\xbd\x6d\x27\x61\x8c";
-static const u8 __initconst ptext12[719] =
+static const u8 __initconst ptext12[719] __nonstring =
"\x42\xc1\xcc\x08\x48\x6f\x41\x3f"
"\x2f\x11\x66\x8b\x2a\x16\xf0\xe0"
"\x58\x83\xf0\xc3\x70\x14\xc0\x5b"
@@ -461,7 +461,7 @@ static const u8 __initconst ptext12[719] =
"\x59\xfa\xfa\xaa\x44\x04\x01\xa7"
"\xa4\x78\xdb\x74\x3d\x8b\xb5";
-static const u8 __initconst ctext12[735] =
+static const u8 __initconst ctext12[735] __nonstring =
"\x84\x0b\xdb\xd5\xb7\xa8\xfe\x20"
"\xbb\xb1\x12\x7f\x41\xea\xb3\xc0"
"\xa2\xb4\x37\x19\x11\x58\xb6\x0b"
@@ -559,9 +559,9 @@ static struct {
const u8 *ptext;
const u8 *ctext;
- u8 key[AES_MAX_KEY_SIZE];
- u8 iv[GCM_AES_IV_SIZE];
- u8 assoc[20];
+ u8 key[AES_MAX_KEY_SIZE] __nonstring;
+ u8 iv[GCM_AES_IV_SIZE] __nonstring;
+ u8 assoc[20] __nonstring;
int klen;
int clen;
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index affe979bd14d..00524e55a21e 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5527,8 +5527,9 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
mas->store_type = mas_wr_store_type(&wr_mas);
request = mas_prealloc_calc(&wr_mas, entry);
if (!request)
- return ret;
+ goto set_flag;
+ mas->mas_flags &= ~MA_STATE_PREALLOC;
mas_node_count_gfp(mas, request, gfp);
if (mas_is_err(mas)) {
mas_set_alloc_req(mas, 0);
@@ -5538,6 +5539,7 @@ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
return ret;
}
+set_flag:
mas->mas_flags |= MA_STATE_PREALLOC;
return ret;
}
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 7582dfab7fe3..4af1c8b0775a 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -73,9 +73,9 @@ EXPORT_SYMBOL(sg_nents_for_len);
* Should only be used casually, it (currently) scans the entire list
* to get the last entry.
*
- * Note that the @sgl@ pointer passed in need not be the first one,
- * the important bit is that @nents@ denotes the number of entries that
- * exist from @sgl@.
+ * Note that the @sgl pointer passed in need not be the first one,
+ * the important bit is that @nents denotes the number of entries that
+ * exist from @sgl.
*
**/
struct scatterlist *sg_last(struct scatterlist *sgl, unsigned int nents)
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(__sg_alloc_table);
* @gfp_mask: GFP allocation mask
*
* Description:
- * Allocate and initialize an sg table. If @nents@ is larger than
+ * Allocate and initialize an sg table. If @nents is larger than
* SG_MAX_SINGLE_ALLOC a chained sg table will be setup.
*
**/
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index 551745df011b..c93d0c56b963 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -4,7 +4,6 @@ menu "Data Access Monitoring"
config DAMON
bool "DAMON: Data Access Monitoring Framework"
- default y
help
This builds a framework that allows kernel subsystems to monitor
access frequency of each memory region. The information can be useful
diff --git a/mm/execmem.c b/mm/execmem.c
index 9720ac2dfa41..2b683e7d864d 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,34 +254,6 @@ out_unlock:
return ptr;
}
-static bool execmem_cache_rox = false;
-
-void execmem_cache_make_ro(void)
-{
- struct maple_tree *free_areas = &execmem_cache.free_areas;
- struct maple_tree *busy_areas = &execmem_cache.busy_areas;
- MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
- MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
- struct mutex *mutex = &execmem_cache.mutex;
- void *area;
-
- execmem_cache_rox = true;
-
- mutex_lock(mutex);
-
- mas_for_each(&mas_free, area, ULONG_MAX) {
- unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
- set_memory_ro(mas_free.index, pages);
- }
-
- mas_for_each(&mas_busy, area, ULONG_MAX) {
- unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
- set_memory_ro(mas_busy.index, pages);
- }
-
- mutex_unlock(mutex);
-}
-
static int execmem_cache_populate(struct execmem_range *range, size_t size)
{
unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -302,15 +274,9 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
/* fill memory with instructions that will trap */
execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
- if (execmem_cache_rox) {
- err = set_memory_rox((unsigned long)p, vm->nr_pages);
- if (err)
- goto err_free_mem;
- } else {
- err = set_memory_x((unsigned long)p, vm->nr_pages);
- if (err)
- goto err_free_mem;
- }
+ err = set_memory_rox((unsigned long)p, vm->nr_pages);
+ if (err)
+ goto err_free_mem;
err = execmem_cache_add(p, alloc_size);
if (err)
diff --git a/mm/gup.c b/mm/gup.c
index e065a49842a8..3c39cbbeebef 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2303,13 +2303,13 @@ static void pofs_unpin(struct pages_or_folios *pofs)
/*
* Returns the number of collected folios. Return value is always >= 0.
*/
-static void collect_longterm_unpinnable_folios(
+static unsigned long collect_longterm_unpinnable_folios(
struct list_head *movable_folio_list,
struct pages_or_folios *pofs)
{
+ unsigned long i, collected = 0;
struct folio *prev_folio = NULL;
bool drain_allow = true;
- unsigned long i;
for (i = 0; i < pofs->nr_entries; i++) {
struct folio *folio = pofs_get_folio(pofs, i);
@@ -2321,6 +2321,8 @@ static void collect_longterm_unpinnable_folios(
if (folio_is_longterm_pinnable(folio))
continue;
+ collected++;
+
if (folio_is_device_coherent(folio))
continue;
@@ -2342,6 +2344,8 @@ static void collect_longterm_unpinnable_folios(
NR_ISOLATED_ANON + folio_is_file_lru(folio),
folio_nr_pages(folio));
}
+
+ return collected;
}
/*
@@ -2418,9 +2422,11 @@ static long
check_and_migrate_movable_pages_or_folios(struct pages_or_folios *pofs)
{
LIST_HEAD(movable_folio_list);
+ unsigned long collected;
- collect_longterm_unpinnable_folios(&movable_folio_list, pofs);
- if (list_empty(&movable_folio_list))
+ collected = collect_longterm_unpinnable_folios(&movable_folio_list,
+ pofs);
+ if (!collected)
return 0;
return migrate_longterm_unpinnable_folios(&movable_folio_list, pofs);
diff --git a/mm/madvise.c b/mm/madvise.c
index 5f7a66a1617e..1d44a35ae85c 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -508,6 +508,7 @@ restart:
pte_offset_map_lock(mm, pmd, addr, &ptl);
if (!start_pte)
break;
+ flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
if (!err)
nr = 0;
@@ -741,6 +742,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
start_pte = pte;
if (!start_pte)
break;
+ flush_tlb_batched_pending(mm);
arch_enter_lazy_mmu_mode();
if (!err)
nr = 0;
diff --git a/mm/memory.c b/mm/memory.c
index 8eba595056fe..b0cda5aab398 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4315,26 +4315,6 @@ static struct folio *__alloc_swap_folio(struct vm_fault *vmf)
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
-{
- struct swap_info_struct *si = swp_swap_info(entry);
- pgoff_t offset = swp_offset(entry);
- int i;
-
- /*
- * While allocating a large folio and doing swap_read_folio, which is
- * the case the being faulted pte doesn't have swapcache. We need to
- * ensure all PTEs have no cache as well, otherwise, we might go to
- * swap devices while the content is in swapcache.
- */
- for (i = 0; i < max_nr; i++) {
- if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
- return i;
- }
-
- return i;
-}
-
/*
* Check if the PTEs within a range are contiguous swap entries
* and have consistent swapcache, zeromap.
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..3a5a65b1f41a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2259,6 +2259,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
folio = swap_cache_get_folio(swap, NULL, 0);
order = xa_get_order(&mapping->i_pages, index);
if (!folio) {
+ int nr_pages = 1 << order;
bool fallback_order0 = false;
/* Or update major stats only when swapin succeeds?? */
@@ -2272,9 +2273,12 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
* If uffd is active for the vma, we need per-page fault
* fidelity to maintain the uffd semantics, then fallback
* to swapin order-0 folio, as well as for zswap case.
+ * Any existing sub folio in the swap cache also blocks
+ * mTHP swapin.
*/
if (order > 0 && ((vma && unlikely(userfaultfd_armed(vma))) ||
- !zswap_never_enabled()))
+ !zswap_never_enabled() ||
+ non_swapcache_batch(swap, nr_pages) != nr_pages))
fallback_order0 = true;
/* Skip swapcache for synchronous device. */
diff --git a/mm/swap.h b/mm/swap.h
index 2269eb9df0af..9096082a915e 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -106,6 +106,25 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
return find_next_bit(sis->zeromap, end, start) - start;
}
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+ struct swap_info_struct *si = swp_swap_info(entry);
+ pgoff_t offset = swp_offset(entry);
+ int i;
+
+ /*
+ * While allocating a large folio and doing mTHP swapin, we need to
+ * ensure all entries are not cached, otherwise, the mTHP folio will
+ * be in conflict with the folio in swap cache.
+ */
+ for (i = 0; i < max_nr; i++) {
+ if ((si->swap_map[offset + i] & SWAP_HAS_CACHE))
+ return i;
+ }
+
+ return i;
+}
+
#else /* CONFIG_SWAP */
struct swap_iocb;
static inline void swap_read_folio(struct folio *folio, struct swap_iocb **plug)
@@ -199,6 +218,10 @@ static inline int swap_zeromap_batch(swp_entry_t entry, int max_nr,
return 0;
}
+static inline int non_swapcache_batch(swp_entry_t entry, int max_nr)
+{
+ return 0;
+}
#endif /* CONFIG_SWAP */
/**
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index bc473ad21202..8253978ee0fb 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1084,8 +1084,18 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
pte_t orig_dst_pte, pte_t orig_src_pte,
pmd_t *dst_pmd, pmd_t dst_pmdval,
spinlock_t *dst_ptl, spinlock_t *src_ptl,
- struct folio *src_folio)
+ struct folio *src_folio,
+ struct swap_info_struct *si, swp_entry_t entry)
{
+ /*
+ * Check if the folio still belongs to the target swap entry after
+ * acquiring the lock. Folio can be freed in the swap cache while
+ * not locked.
+ */
+ if (src_folio && unlikely(!folio_test_swapcache(src_folio) ||
+ entry.val != src_folio->swap.val))
+ return -EAGAIN;
+
double_pt_lock(dst_ptl, src_ptl);
if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
@@ -1102,6 +1112,25 @@ static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
if (src_folio) {
folio_move_anon_rmap(src_folio, dst_vma);
src_folio->index = linear_page_index(dst_vma, dst_addr);
+ } else {
+ /*
+ * Check if the swap entry is cached after acquiring the src_pte
+ * lock. Otherwise, we might miss a newly loaded swap cache folio.
+ *
+ * Check swap_map directly to minimize overhead, READ_ONCE is sufficient.
+ * We are trying to catch newly added swap cache, the only possible case is
+ * when a folio is swapped in and out again staying in swap cache, using the
+ * same entry before the PTE check above. The PTL is acquired and released
+ * twice, each time after updating the swap_map's flag. So holding
+ * the PTL here ensures we see the updated value. False positive is possible,
+ * e.g. SWP_SYNCHRONOUS_IO swapin may set the flag without touching the
+ * cache, or during the tiny synchronization window between swap cache and
+ * swap_map, but it will be gone very quickly, worst result is retry jitters.
+ */
+ if (READ_ONCE(si->swap_map[swp_offset(entry)]) & SWAP_HAS_CACHE) {
+ double_pt_unlock(dst_ptl, src_ptl);
+ return -EAGAIN;
+ }
}
orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
@@ -1412,7 +1441,7 @@ retry:
}
err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval,
- dst_ptl, src_ptl, src_folio);
+ dst_ptl, src_ptl, src_folio, si, entry);
}
out:
diff --git a/mm/util.c b/mm/util.c
index 448117da071f..0b270c43d7d1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1131,3 +1131,43 @@ void flush_dcache_folio(struct folio *folio)
}
EXPORT_SYMBOL(flush_dcache_folio);
#endif
+
+/**
+ * compat_vma_mmap_prepare() - Apply the file's .mmap_prepare() hook to an
+ * existing VMA
+ * @file: The file which possesss an f_op->mmap_prepare() hook
+ * @vma: The VMA to apply the .mmap_prepare() hook to.
+ *
+ * Ordinarily, .mmap_prepare() is invoked directly upon mmap(). However, certain
+ * 'wrapper' file systems invoke a nested mmap hook of an underlying file.
+ *
+ * Until all filesystems are converted to use .mmap_prepare(), we must be
+ * conservative and continue to invoke these 'wrapper' filesystems using the
+ * deprecated .mmap() hook.
+ *
+ * However we have a problem if the underlying file system possesses an
+ * .mmap_prepare() hook, as we are in a different context when we invoke the
+ * .mmap() hook, already having a VMA to deal with.
+ *
+ * compat_vma_mmap_prepare() is a compatibility function that takes VMA state,
+ * establishes a struct vm_area_desc descriptor, passes to the underlying
+ * .mmap_prepare() hook and applies any changes performed by it.
+ *
+ * Once the conversion of filesystems is complete this function will no longer
+ * be required and will be removed.
+ *
+ * Returns: 0 on success or error.
+ */
+int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma)
+{
+ struct vm_area_desc desc;
+ int err;
+
+ err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc));
+ if (err)
+ return err;
+ set_vma_from_desc(vma, &desc);
+
+ return 0;
+}
+EXPORT_SYMBOL(compat_vma_mmap_prepare);
diff --git a/mm/vma.c b/mm/vma.c
index 726b2a31ce59..fef67a66a095 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -967,26 +967,9 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
err = dup_anon_vma(next, middle, &anon_dup);
}
- if (err)
+ if (err || commit_merge(vmg))
goto abort;
- err = commit_merge(vmg);
- if (err) {
- VM_WARN_ON(err != -ENOMEM);
-
- if (anon_dup)
- unlink_anon_vmas(anon_dup);
-
- /*
- * We've cleaned up any cloned anon_vma's, no VMAs have been
- * modified, no harm no foul if the user requests that we not
- * report this and just give up, leaving the VMAs unmerged.
- */
- if (!vmg->give_up_on_oom)
- vmg->state = VMA_MERGE_ERROR_NOMEM;
- return NULL;
- }
-
khugepaged_enter_vma(vmg->target, vmg->flags);
vmg->state = VMA_MERGE_SUCCESS;
return vmg->target;
@@ -995,6 +978,9 @@ abort:
vma_iter_set(vmg->vmi, start);
vma_iter_load(vmg->vmi);
+ if (anon_dup)
+ unlink_anon_vmas(anon_dup);
+
/*
* This means we have failed to clone anon_vma's correctly, but no
* actual changes to VMAs have occurred, so no harm no foul - if the
@@ -3127,7 +3113,6 @@ int __vm_munmap(unsigned long start, size_t len, bool unlock)
return ret;
}
-
/* Insert vm structure into process list sorted by address
* and into the inode's i_mmap tree. If vm_file is non-NULL
* then i_mmap_rwsem is taken here.
diff --git a/mm/vma.h b/mm/vma.h
index 0db066e7a45d..f47112a352db 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -222,6 +222,53 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
return 0;
}
+
+/*
+ * Temporary helper functions for file systems which wrap an invocation of
+ * f_op->mmap() but which might have an underlying file system which implements
+ * f_op->mmap_prepare().
+ */
+
+static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma,
+ struct vm_area_desc *desc)
+{
+ desc->mm = vma->vm_mm;
+ desc->start = vma->vm_start;
+ desc->end = vma->vm_end;
+
+ desc->pgoff = vma->vm_pgoff;
+ desc->file = vma->vm_file;
+ desc->vm_flags = vma->vm_flags;
+ desc->page_prot = vma->vm_page_prot;
+
+ desc->vm_ops = NULL;
+ desc->private_data = NULL;
+
+ return desc;
+}
+
+static inline void set_vma_from_desc(struct vm_area_struct *vma,
+ struct vm_area_desc *desc)
+{
+ /*
+ * Since we're invoking .mmap_prepare() despite having a partially
+ * established VMA, we must take care to handle setting fields
+ * correctly.
+ */
+
+ /* Mutable fields. Populated with initial state. */
+ vma->vm_pgoff = desc->pgoff;
+ if (vma->vm_file != desc->file)
+ vma_set_file(vma, desc->file);
+ if (vma->vm_flags != desc->vm_flags)
+ vm_flags_set(vma, desc->vm_flags);
+ vma->vm_page_prot = desc->page_prot;
+
+ /* User-defined fields. */
+ vma->vm_ops = desc->vm_ops;
+ vma->vm_private_data = desc->private_data;
+}
+
int
do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct mm_struct *mm, unsigned long start,
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 61b5b700817d..b234dc3bcb0d 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -193,12 +193,6 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
pr_debug("\n");
- if (!clip_devs) {
- atm_return(vcc, skb->truesize);
- kfree_skb(skb);
- return;
- }
-
if (!skb) {
pr_debug("removing VCC %p\n", clip_vcc);
if (clip_vcc->entry)
@@ -208,6 +202,11 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
return;
}
atm_return(vcc, skb->truesize);
+ if (!clip_devs) {
+ kfree_skb(skb);
+ return;
+ }
+
skb->dev = clip_vcc->entry ? clip_vcc->entry->neigh->dev : clip_devs;
/* clip_vcc->entry == NULL if we don't have an IP address yet */
if (!skb->dev) {
diff --git a/net/atm/common.c b/net/atm/common.c
index 9b75699992ff..d7f7976ea13a 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -635,6 +635,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
skb->dev = NULL; /* for paths shared with net_device interfaces */
if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
+ atm_return_tx(vcc, skb);
kfree_skb(skb);
error = -EFAULT;
goto out;
diff --git a/net/atm/lec.c b/net/atm/lec.c
index acef984f3367..afb8d3eb2185 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -124,6 +124,7 @@ static unsigned char bus_mac[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
/* Device structures */
static struct net_device *dev_lec[MAX_LEC_ITF];
+static DEFINE_MUTEX(lec_mutex);
#if IS_ENABLED(CONFIG_BRIDGE)
static void lec_handle_bridge(struct sk_buff *skb, struct net_device *dev)
@@ -685,6 +686,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
int bytes_left;
struct atmlec_ioc ioc_data;
+ lockdep_assert_held(&lec_mutex);
/* Lecd must be up in this case */
bytes_left = copy_from_user(&ioc_data, arg, sizeof(struct atmlec_ioc));
if (bytes_left != 0)
@@ -710,6 +712,7 @@ static int lec_vcc_attach(struct atm_vcc *vcc, void __user *arg)
static int lec_mcast_attach(struct atm_vcc *vcc, int arg)
{
+ lockdep_assert_held(&lec_mutex);
if (arg < 0 || arg >= MAX_LEC_ITF)
return -EINVAL;
arg = array_index_nospec(arg, MAX_LEC_ITF);
@@ -725,6 +728,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
int i;
struct lec_priv *priv;
+ lockdep_assert_held(&lec_mutex);
if (arg < 0)
arg = 0;
if (arg >= MAX_LEC_ITF)
@@ -742,6 +746,7 @@ static int lecd_attach(struct atm_vcc *vcc, int arg)
snprintf(dev_lec[i]->name, IFNAMSIZ, "lec%d", i);
if (register_netdev(dev_lec[i])) {
free_netdev(dev_lec[i]);
+ dev_lec[i] = NULL;
return -EINVAL;
}
@@ -904,7 +909,6 @@ static void *lec_itf_walk(struct lec_state *state, loff_t *l)
v = (dev && netdev_priv(dev)) ?
lec_priv_walk(state, l, netdev_priv(dev)) : NULL;
if (!v && dev) {
- dev_put(dev);
/* Partial state reset for the next time we get called */
dev = NULL;
}
@@ -928,6 +932,7 @@ static void *lec_seq_start(struct seq_file *seq, loff_t *pos)
{
struct lec_state *state = seq->private;
+ mutex_lock(&lec_mutex);
state->itf = 0;
state->dev = NULL;
state->locked = NULL;
@@ -945,8 +950,9 @@ static void lec_seq_stop(struct seq_file *seq, void *v)
if (state->dev) {
spin_unlock_irqrestore(&state->locked->lec_arp_lock,
state->flags);
- dev_put(state->dev);
+ state->dev = NULL;
}
+ mutex_unlock(&lec_mutex);
}
static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos)
@@ -1003,6 +1009,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return -ENOIOCTLCMD;
}
+ mutex_lock(&lec_mutex);
switch (cmd) {
case ATMLEC_CTRL:
err = lecd_attach(vcc, (int)arg);
@@ -1017,6 +1024,7 @@ static int lane_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
}
+ mutex_unlock(&lec_mutex);
return err;
}
diff --git a/net/atm/raw.c b/net/atm/raw.c
index 2b5f78a7ec3e..1e6511ec842c 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -36,7 +36,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
pr_debug("(%d) %d -= %d\n",
vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
- WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
+ atm_return_tx(vcc, skb);
dev_kfree_skb_any(skb);
sk->sk_write_space(sk);
}
diff --git a/net/atm/resources.c b/net/atm/resources.c
index 995d29e7fb13..b19d851e1f44 100644
--- a/net/atm/resources.c
+++ b/net/atm/resources.c
@@ -146,11 +146,10 @@ void atm_dev_deregister(struct atm_dev *dev)
*/
mutex_lock(&atm_dev_mutex);
list_del(&dev->dev_list);
- mutex_unlock(&atm_dev_mutex);
-
atm_dev_release_vccs(dev);
atm_unregister_sysfs(dev);
atm_proc_dev_deregister(dev);
+ mutex_unlock(&atm_dev_mutex);
atm_dev_put(dev);
}
diff --git a/net/bluetooth/eir.c b/net/bluetooth/eir.c
index 1bc51e2b05a3..3f72111ba651 100644
--- a/net/bluetooth/eir.c
+++ b/net/bluetooth/eir.c
@@ -242,7 +242,7 @@ u8 eir_create_per_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
return ad_len;
}
-u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
+u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr, u8 size)
{
struct adv_info *adv = NULL;
u8 ad_len = 0, flags = 0;
@@ -286,7 +286,7 @@ u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
/* If flags would still be empty, then there is no need to
* include the "Flags" AD field".
*/
- if (flags) {
+ if (flags && (ad_len + eir_precalc_len(1) <= size)) {
ptr[0] = 0x02;
ptr[1] = EIR_FLAGS;
ptr[2] = flags;
@@ -316,7 +316,8 @@ skip_flags:
}
/* Provide Tx Power only if we can provide a valid value for it */
- if (adv_tx_power != HCI_TX_POWER_INVALID) {
+ if (adv_tx_power != HCI_TX_POWER_INVALID &&
+ (ad_len + eir_precalc_len(1) <= size)) {
ptr[0] = 0x02;
ptr[1] = EIR_TX_POWER;
ptr[2] = (u8)adv_tx_power;
@@ -366,17 +367,19 @@ u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr)
void *eir_get_service_data(u8 *eir, size_t eir_len, u16 uuid, size_t *len)
{
- while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, len))) {
+ size_t dlen;
+
+ while ((eir = eir_get_data(eir, eir_len, EIR_SERVICE_DATA, &dlen))) {
u16 value = get_unaligned_le16(eir);
if (uuid == value) {
if (len)
- *len -= 2;
+ *len = dlen - 2;
return &eir[2];
}
- eir += *len;
- eir_len -= *len;
+ eir += dlen;
+ eir_len -= dlen;
}
return NULL;
diff --git a/net/bluetooth/eir.h b/net/bluetooth/eir.h
index 5c89a05e8b29..9372db83f912 100644
--- a/net/bluetooth/eir.h
+++ b/net/bluetooth/eir.h
@@ -9,7 +9,7 @@
void eir_create(struct hci_dev *hdev, u8 *data);
-u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr);
+u8 eir_create_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr, u8 size);
u8 eir_create_scan_rsp(struct hci_dev *hdev, u8 instance, u8 *ptr);
u8 eir_create_per_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 99efeed6a766..4f379184df5b 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1501,8 +1501,8 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos)
/* This function requires the caller holds hdev->lock */
static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
- struct bt_iso_qos *qos, __u8 base_len,
- __u8 *base)
+ __u8 sid, struct bt_iso_qos *qos,
+ __u8 base_len, __u8 *base)
{
struct hci_conn *conn;
int err;
@@ -1543,6 +1543,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst,
return conn;
conn->state = BT_CONNECT;
+ conn->sid = sid;
hci_conn_hold(conn);
return conn;
@@ -2062,7 +2063,8 @@ static int create_big_sync(struct hci_dev *hdev, void *data)
if (qos->bcast.bis)
sync_interval = interval * 4;
- err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->le_per_adv_data_len,
+ err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->sid,
+ conn->le_per_adv_data_len,
conn->le_per_adv_data, flags, interval,
interval, sync_interval);
if (err)
@@ -2134,7 +2136,7 @@ static void create_big_complete(struct hci_dev *hdev, void *data, int err)
}
}
-struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
+struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst, __u8 sid,
struct bt_iso_qos *qos,
__u8 base_len, __u8 *base)
{
@@ -2156,7 +2158,7 @@ struct hci_conn *hci_bind_bis(struct hci_dev *hdev, bdaddr_t *dst,
base, base_len);
/* We need hci_conn object using the BDADDR_ANY as dst */
- conn = hci_add_bis(hdev, dst, qos, base_len, eir);
+ conn = hci_add_bis(hdev, dst, sid, qos, base_len, eir);
if (IS_ERR(conn))
return conn;
@@ -2207,20 +2209,35 @@ static void bis_mark_per_adv(struct hci_conn *conn, void *data)
}
struct hci_conn *hci_connect_bis(struct hci_dev *hdev, bdaddr_t *dst,
- __u8 dst_type, struct bt_iso_qos *qos,
+ __u8 dst_type, __u8 sid,
+ struct bt_iso_qos *qos,
__u8 base_len, __u8 *base)
{
struct hci_conn *conn;
int err;
struct iso_list_data data;
- conn = hci_bind_bis(hdev, dst, qos, base_len, base);
+ conn = hci_bind_bis(hdev, dst, sid, qos, base_len, base);
if (IS_ERR(conn))
return conn;
if (conn->state == BT_CONNECTED)
return conn;
+ /* Check if SID needs to be allocated then search for the first
+ * available.
+ */
+ if (conn->sid == HCI_SID_INVALID) {
+ u8 sid;
+
+ for (sid = 0; sid <= 0x0f; sid++) {
+ if (!hci_find_adv_sid(hdev, sid)) {
+ conn->sid = sid;
+ break;
+ }
+ }
+ }
+
data.big = qos->bcast.big;
data.bis = qos->bcast.bis;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 3b49828160b7..14d7221b8ac0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -64,7 +64,7 @@ static DEFINE_IDA(hci_index_ida);
/* Get HCI device by index.
* Device is held on return. */
-struct hci_dev *hci_dev_get(int index)
+static struct hci_dev *__hci_dev_get(int index, int *srcu_index)
{
struct hci_dev *hdev = NULL, *d;
@@ -77,6 +77,8 @@ struct hci_dev *hci_dev_get(int index)
list_for_each_entry(d, &hci_dev_list, list) {
if (d->id == index) {
hdev = hci_dev_hold(d);
+ if (srcu_index)
+ *srcu_index = srcu_read_lock(&d->srcu);
break;
}
}
@@ -84,6 +86,22 @@ struct hci_dev *hci_dev_get(int index)
return hdev;
}
+struct hci_dev *hci_dev_get(int index)
+{
+ return __hci_dev_get(index, NULL);
+}
+
+static struct hci_dev *hci_dev_get_srcu(int index, int *srcu_index)
+{
+ return __hci_dev_get(index, srcu_index);
+}
+
+static void hci_dev_put_srcu(struct hci_dev *hdev, int srcu_index)
+{
+ srcu_read_unlock(&hdev->srcu, srcu_index);
+ hci_dev_put(hdev);
+}
+
/* ---- Inquiry support ---- */
bool hci_discovery_active(struct hci_dev *hdev)
@@ -568,9 +586,9 @@ static int hci_dev_do_reset(struct hci_dev *hdev)
int hci_dev_reset(__u16 dev)
{
struct hci_dev *hdev;
- int err;
+ int err, srcu_index;
- hdev = hci_dev_get(dev);
+ hdev = hci_dev_get_srcu(dev, &srcu_index);
if (!hdev)
return -ENODEV;
@@ -592,7 +610,7 @@ int hci_dev_reset(__u16 dev)
err = hci_dev_do_reset(hdev);
done:
- hci_dev_put(hdev);
+ hci_dev_put_srcu(hdev, srcu_index);
return err;
}
@@ -1585,6 +1603,19 @@ struct adv_info *hci_find_adv_instance(struct hci_dev *hdev, u8 instance)
}
/* This function requires the caller holds hdev->lock */
+struct adv_info *hci_find_adv_sid(struct hci_dev *hdev, u8 sid)
+{
+ struct adv_info *adv;
+
+ list_for_each_entry(adv, &hdev->adv_instances, list) {
+ if (adv->sid == sid)
+ return adv;
+ }
+
+ return NULL;
+}
+
+/* This function requires the caller holds hdev->lock */
struct adv_info *hci_get_next_instance(struct hci_dev *hdev, u8 instance)
{
struct adv_info *cur_instance;
@@ -1736,7 +1767,7 @@ struct adv_info *hci_add_adv_instance(struct hci_dev *hdev, u8 instance,
}
/* This function requires the caller holds hdev->lock */
-struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
+struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance, u8 sid,
u32 flags, u8 data_len, u8 *data,
u32 min_interval, u32 max_interval)
{
@@ -1748,6 +1779,7 @@ struct adv_info *hci_add_per_instance(struct hci_dev *hdev, u8 instance,
if (IS_ERR(adv))
return adv;
+ adv->sid = sid;
adv->periodic = true;
adv->per_adv_data_len = data_len;
@@ -1877,10 +1909,8 @@ void hci_free_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor)
if (monitor->handle)
idr_remove(&hdev->adv_monitors_idr, monitor->handle);
- if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED) {
+ if (monitor->state != ADV_MONITOR_STATE_NOT_REGISTERED)
hdev->adv_monitors_cnt--;
- mgmt_adv_monitor_removed(hdev, monitor->handle);
- }
kfree(monitor);
}
@@ -2421,6 +2451,11 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv)
if (!hdev)
return NULL;
+ if (init_srcu_struct(&hdev->srcu)) {
+ kfree(hdev);
+ return NULL;
+ }
+
hdev->pkt_type = (HCI_DM1 | HCI_DH1 | HCI_HV1);
hdev->esco_type = (ESCO_HV1);
hdev->link_mode = (HCI_LM_ACCEPT);
@@ -2487,6 +2522,7 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv)
mutex_init(&hdev->lock);
mutex_init(&hdev->req_lock);
+ mutex_init(&hdev->mgmt_pending_lock);
ida_init(&hdev->unset_handle_ida);
@@ -2665,6 +2701,9 @@ void hci_unregister_dev(struct hci_dev *hdev)
list_del(&hdev->list);
write_unlock(&hci_dev_list_lock);
+ synchronize_srcu(&hdev->srcu);
+ cleanup_srcu_struct(&hdev->srcu);
+
disable_work_sync(&hdev->rx_work);
disable_work_sync(&hdev->cmd_work);
disable_work_sync(&hdev->tx_work);
@@ -3417,23 +3456,18 @@ static void hci_link_tx_to(struct hci_dev *hdev, __u8 type)
bt_dev_err(hdev, "link tx timeout");
- rcu_read_lock();
+ hci_dev_lock(hdev);
/* Kill stalled connections */
- list_for_each_entry_rcu(c, &h->list, list) {
+ list_for_each_entry(c, &h->list, list) {
if (c->type == type && c->sent) {
bt_dev_err(hdev, "killing stalled connection %pMR",
&c->dst);
- /* hci_disconnect might sleep, so, we have to release
- * the RCU read lock before calling it.
- */
- rcu_read_unlock();
hci_disconnect(c, HCI_ERROR_REMOTE_USER_TERM);
- rcu_read_lock();
}
}
- rcu_read_unlock();
+ hci_dev_unlock(hdev);
}
static struct hci_chan *hci_chan_sent(struct hci_dev *hdev, __u8 type,
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index 62d1ff951ebe..6687f2a4d1eb 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1261,10 +1261,12 @@ int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance)
hci_cpu_to_le24(adv->min_interval, cp.min_interval);
hci_cpu_to_le24(adv->max_interval, cp.max_interval);
cp.tx_power = adv->tx_power;
+ cp.sid = adv->sid;
} else {
hci_cpu_to_le24(hdev->le_adv_min_interval, cp.min_interval);
hci_cpu_to_le24(hdev->le_adv_max_interval, cp.max_interval);
cp.tx_power = HCI_ADV_TX_POWER_NO_PREFERENCE;
+ cp.sid = 0x00;
}
secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK);
@@ -1559,7 +1561,8 @@ static int hci_enable_per_advertising_sync(struct hci_dev *hdev, u8 instance)
static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv)
{
u8 bid[3];
- u8 ad[4 + 3];
+ u8 ad[HCI_MAX_EXT_AD_LENGTH];
+ u8 len;
/* Skip if NULL adv as instance 0x00 is used for general purpose
* advertising so it cannot used for the likes of Broadcast Announcement
@@ -1585,14 +1588,16 @@ static int hci_adv_bcast_annoucement(struct hci_dev *hdev, struct adv_info *adv)
/* Generate Broadcast ID */
get_random_bytes(bid, sizeof(bid));
- eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid));
- hci_set_adv_instance_data(hdev, adv->instance, sizeof(ad), ad, 0, NULL);
+ len = eir_append_service_data(ad, 0, 0x1852, bid, sizeof(bid));
+ memcpy(ad + len, adv->adv_data, adv->adv_data_len);
+ hci_set_adv_instance_data(hdev, adv->instance, len + adv->adv_data_len,
+ ad, 0, NULL);
return hci_update_adv_data_sync(hdev, adv->instance);
}
-int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
- u8 *data, u32 flags, u16 min_interval,
+int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 sid,
+ u8 data_len, u8 *data, u32 flags, u16 min_interval,
u16 max_interval, u16 sync_interval)
{
struct adv_info *adv = NULL;
@@ -1603,9 +1608,28 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len,
if (instance) {
adv = hci_find_adv_instance(hdev, instance);
- /* Create an instance if that could not be found */
- if (!adv) {
- adv = hci_add_per_instance(hdev, instance, flags,
+ if (adv) {
+ if (sid != HCI_SID_INVALID && adv->sid != sid) {
+ /* If the SID don't match attempt to find by
+ * SID.
+ */
+ adv = hci_find_adv_sid(hdev, sid);
+ if (!adv) {
+ bt_dev_err(hdev,
+ "Unable to find adv_info");
+ return -EINVAL;
+ }
+ }
+
+ /* Turn it into periodic advertising */
+ adv->periodic = true;
+ adv->per_adv_data_len = data_len;
+ if (data)
+ memcpy(adv->per_adv_data, data, data_len);
+ adv->flags = flags;
+ } else if (!adv) {
+ /* Create an instance if that could not be found */
+ adv = hci_add_per_instance(hdev, instance, sid, flags,
data_len, data,
sync_interval,
sync_interval);
@@ -1812,7 +1836,8 @@ static int hci_set_ext_adv_data_sync(struct hci_dev *hdev, u8 instance)
return 0;
}
- len = eir_create_adv_data(hdev, instance, pdu->data);
+ len = eir_create_adv_data(hdev, instance, pdu->data,
+ HCI_MAX_EXT_AD_LENGTH);
pdu->length = len;
pdu->handle = adv ? adv->handle : instance;
@@ -1843,7 +1868,7 @@ static int hci_set_adv_data_sync(struct hci_dev *hdev, u8 instance)
memset(&cp, 0, sizeof(cp));
- len = eir_create_adv_data(hdev, instance, cp.data);
+ len = eir_create_adv_data(hdev, instance, cp.data, sizeof(cp.data));
/* There's nothing to do if the data hasn't changed */
if (hdev->adv_data_len == len &&
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 6e2c752aaa8f..3c2c98eecc62 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -336,7 +336,7 @@ static int iso_connect_bis(struct sock *sk)
struct hci_dev *hdev;
int err;
- BT_DBG("%pMR", &iso_pi(sk)->src);
+ BT_DBG("%pMR (SID 0x%2.2x)", &iso_pi(sk)->src, iso_pi(sk)->bc_sid);
hdev = hci_get_route(&iso_pi(sk)->dst, &iso_pi(sk)->src,
iso_pi(sk)->src_type);
@@ -365,7 +365,7 @@ static int iso_connect_bis(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_bis(hdev, &iso_pi(sk)->dst,
+ hcon = hci_bind_bis(hdev, &iso_pi(sk)->dst, iso_pi(sk)->bc_sid,
&iso_pi(sk)->qos, iso_pi(sk)->base_len,
iso_pi(sk)->base);
if (IS_ERR(hcon)) {
@@ -375,12 +375,16 @@ static int iso_connect_bis(struct sock *sk)
} else {
hcon = hci_connect_bis(hdev, &iso_pi(sk)->dst,
le_addr_type(iso_pi(sk)->dst_type),
- &iso_pi(sk)->qos, iso_pi(sk)->base_len,
- iso_pi(sk)->base);
+ iso_pi(sk)->bc_sid, &iso_pi(sk)->qos,
+ iso_pi(sk)->base_len, iso_pi(sk)->base);
if (IS_ERR(hcon)) {
err = PTR_ERR(hcon);
goto unlock;
}
+
+ /* Update SID if it was not set */
+ if (iso_pi(sk)->bc_sid == HCI_SID_INVALID)
+ iso_pi(sk)->bc_sid = hcon->sid;
}
conn = iso_conn_add(hcon);
@@ -1337,10 +1341,13 @@ static int iso_sock_getname(struct socket *sock, struct sockaddr *addr,
addr->sa_family = AF_BLUETOOTH;
if (peer) {
+ struct hci_conn *hcon = iso_pi(sk)->conn ?
+ iso_pi(sk)->conn->hcon : NULL;
+
bacpy(&sa->iso_bdaddr, &iso_pi(sk)->dst);
sa->iso_bdaddr_type = iso_pi(sk)->dst_type;
- if (test_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags)) {
+ if (hcon && hcon->type == BIS_LINK) {
sa->iso_bc->bc_sid = iso_pi(sk)->bc_sid;
sa->iso_bc->bc_num_bis = iso_pi(sk)->bc_num_bis;
memcpy(sa->iso_bc->bc_bis, iso_pi(sk)->bc_bis,
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a5bde5db58ef..40daa38276f3 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -3415,7 +3415,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data
struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC };
struct l2cap_conf_efs efs;
u8 remote_efs = 0;
- u16 mtu = L2CAP_DEFAULT_MTU;
+ u16 mtu = 0;
u16 result = L2CAP_CONF_SUCCESS;
u16 size;
@@ -3520,6 +3520,13 @@ done:
/* Configure output options and let the other side know
* which ones we don't like. */
+ /* If MTU is not provided in configure request, use the most recently
+ * explicitly or implicitly accepted value for the other direction,
+ * or the default value.
+ */
+ if (mtu == 0)
+ mtu = chan->imtu ? chan->imtu : L2CAP_DEFAULT_MTU;
+
if (mtu < L2CAP_DEFAULT_MIN_MTU)
result = L2CAP_CONF_UNACCEPT;
else {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 14a9462fced5..d540f7b4f75f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1447,22 +1447,17 @@ static void settings_rsp(struct mgmt_pending_cmd *cmd, void *data)
send_settings_rsp(cmd->sk, cmd->opcode, match->hdev);
- list_del(&cmd->list);
-
if (match->sk == NULL) {
match->sk = cmd->sk;
sock_hold(match->sk);
}
-
- mgmt_pending_free(cmd);
}
static void cmd_status_rsp(struct mgmt_pending_cmd *cmd, void *data)
{
u8 *status = data;
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, *status);
- mgmt_pending_remove(cmd);
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, *status);
}
static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
@@ -1476,8 +1471,6 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
if (cmd->cmd_complete) {
cmd->cmd_complete(cmd, match->mgmt_status);
- mgmt_pending_remove(cmd);
-
return;
}
@@ -1486,13 +1479,13 @@ static void cmd_complete_rsp(struct mgmt_pending_cmd *cmd, void *data)
static int generic_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
{
- return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+ return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status,
cmd->param, cmd->param_len);
}
static int addr_cmd_complete(struct mgmt_pending_cmd *cmd, u8 status)
{
- return mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status,
+ return mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status,
cmd->param, sizeof(struct mgmt_addr_info));
}
@@ -1532,7 +1525,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data,
if (err) {
u8 mgmt_err = mgmt_status(err);
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
hci_dev_clear_flag(hdev, HCI_LIMITED_DISCOVERABLE);
goto done;
}
@@ -1707,7 +1700,7 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data,
if (err) {
u8 mgmt_err = mgmt_status(err);
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
goto done;
}
@@ -1943,8 +1936,8 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err)
new_settings(hdev, NULL);
}
- mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, cmd_status_rsp,
- &mgmt_err);
+ mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true,
+ cmd_status_rsp, &mgmt_err);
return;
}
@@ -1954,7 +1947,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err)
changed = hci_dev_test_and_clear_flag(hdev, HCI_SSP_ENABLED);
}
- mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, settings_rsp, &match);
+ mgmt_pending_foreach(MGMT_OP_SET_SSP, hdev, true, settings_rsp, &match);
if (changed)
new_settings(hdev, match.sk);
@@ -2074,12 +2067,12 @@ static void set_le_complete(struct hci_dev *hdev, void *data, int err)
bt_dev_dbg(hdev, "err %d", err);
if (status) {
- mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, cmd_status_rsp,
- &status);
+ mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, cmd_status_rsp,
+ &status);
return;
}
- mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, settings_rsp, &match);
+ mgmt_pending_foreach(MGMT_OP_SET_LE, hdev, true, settings_rsp, &match);
new_settings(hdev, match.sk);
@@ -2138,7 +2131,7 @@ static void set_mesh_complete(struct hci_dev *hdev, void *data, int err)
struct sock *sk = cmd->sk;
if (status) {
- mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev,
+ mgmt_pending_foreach(MGMT_OP_SET_MESH_RECEIVER, hdev, true,
cmd_status_rsp, &status);
return;
}
@@ -2638,7 +2631,7 @@ static void mgmt_class_complete(struct hci_dev *hdev, void *data, int err)
bt_dev_dbg(hdev, "err %d", err);
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err), hdev->dev_class, 3);
mgmt_pending_free(cmd);
@@ -3427,7 +3420,7 @@ static int pairing_complete(struct mgmt_pending_cmd *cmd, u8 status)
bacpy(&rp.addr.bdaddr, &conn->dst);
rp.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
- err = mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_PAIR_DEVICE,
+ err = mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_PAIR_DEVICE,
status, &rp, sizeof(rp));
/* So we don't get further callbacks for this connection */
@@ -5108,24 +5101,14 @@ static void mgmt_adv_monitor_added(struct sock *sk, struct hci_dev *hdev,
mgmt_event(MGMT_EV_ADV_MONITOR_ADDED, hdev, &ev, sizeof(ev), sk);
}
-void mgmt_adv_monitor_removed(struct hci_dev *hdev, u16 handle)
+static void mgmt_adv_monitor_removed(struct sock *sk, struct hci_dev *hdev,
+ __le16 handle)
{
struct mgmt_ev_adv_monitor_removed ev;
- struct mgmt_pending_cmd *cmd;
- struct sock *sk_skip = NULL;
- struct mgmt_cp_remove_adv_monitor *cp;
-
- cmd = pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev);
- if (cmd) {
- cp = cmd->param;
-
- if (cp->monitor_handle)
- sk_skip = cmd->sk;
- }
- ev.monitor_handle = cpu_to_le16(handle);
+ ev.monitor_handle = handle;
- mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk_skip);
+ mgmt_event(MGMT_EV_ADV_MONITOR_REMOVED, hdev, &ev, sizeof(ev), sk);
}
static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
@@ -5196,7 +5179,7 @@ static void mgmt_add_adv_patterns_monitor_complete(struct hci_dev *hdev,
hci_update_passive_scan(hdev);
}
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(status), &rp, sizeof(rp));
mgmt_pending_remove(cmd);
@@ -5227,8 +5210,7 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
if (pending_find(MGMT_OP_SET_LE, hdev) ||
pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) ||
- pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev) ||
- pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev)) {
+ pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) {
status = MGMT_STATUS_BUSY;
goto unlock;
}
@@ -5398,8 +5380,7 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
struct mgmt_pending_cmd *cmd = data;
struct mgmt_cp_remove_adv_monitor *cp;
- if (status == -ECANCELED ||
- cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev))
+ if (status == -ECANCELED)
return;
hci_dev_lock(hdev);
@@ -5408,12 +5389,14 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
rp.monitor_handle = cp->monitor_handle;
- if (!status)
+ if (!status) {
+ mgmt_adv_monitor_removed(cmd->sk, hdev, cp->monitor_handle);
hci_update_passive_scan(hdev);
+ }
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(status), &rp, sizeof(rp));
- mgmt_pending_remove(cmd);
+ mgmt_pending_free(cmd);
hci_dev_unlock(hdev);
bt_dev_dbg(hdev, "remove monitor %d complete, status %d",
@@ -5423,10 +5406,6 @@ static void mgmt_remove_adv_monitor_complete(struct hci_dev *hdev,
static int mgmt_remove_adv_monitor_sync(struct hci_dev *hdev, void *data)
{
struct mgmt_pending_cmd *cmd = data;
-
- if (cmd != pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev))
- return -ECANCELED;
-
struct mgmt_cp_remove_adv_monitor *cp = cmd->param;
u16 handle = __le16_to_cpu(cp->monitor_handle);
@@ -5445,14 +5424,13 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
hci_dev_lock(hdev);
if (pending_find(MGMT_OP_SET_LE, hdev) ||
- pending_find(MGMT_OP_REMOVE_ADV_MONITOR, hdev) ||
pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR, hdev) ||
pending_find(MGMT_OP_ADD_ADV_PATTERNS_MONITOR_RSSI, hdev)) {
status = MGMT_STATUS_BUSY;
goto unlock;
}
- cmd = mgmt_pending_add(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len);
+ cmd = mgmt_pending_new(sk, MGMT_OP_REMOVE_ADV_MONITOR, hdev, data, len);
if (!cmd) {
status = MGMT_STATUS_NO_RESOURCES;
goto unlock;
@@ -5462,7 +5440,7 @@ static int remove_adv_monitor(struct sock *sk, struct hci_dev *hdev,
mgmt_remove_adv_monitor_complete);
if (err) {
- mgmt_pending_remove(cmd);
+ mgmt_pending_free(cmd);
if (err == -ENOMEM)
status = MGMT_STATUS_NO_RESOURCES;
@@ -5792,7 +5770,7 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err)
cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev))
return;
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err),
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err),
cmd->param, 1);
mgmt_pending_remove(cmd);
@@ -6013,7 +5991,7 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err)
bt_dev_dbg(hdev, "err %d", err);
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err),
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_status(err),
cmd->param, 1);
mgmt_pending_remove(cmd);
@@ -6238,7 +6216,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err)
u8 status = mgmt_status(err);
if (status) {
- mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev,
+ mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true,
cmd_status_rsp, &status);
return;
}
@@ -6248,7 +6226,7 @@ static void set_advertising_complete(struct hci_dev *hdev, void *data, int err)
else
hci_dev_clear_flag(hdev, HCI_ADVERTISING);
- mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, settings_rsp,
+ mgmt_pending_foreach(MGMT_OP_SET_ADVERTISING, hdev, true, settings_rsp,
&match);
new_settings(hdev, match.sk);
@@ -6592,7 +6570,7 @@ static void set_bredr_complete(struct hci_dev *hdev, void *data, int err)
*/
hci_dev_clear_flag(hdev, HCI_BREDR_ENABLED);
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
} else {
send_settings_rsp(cmd->sk, MGMT_OP_SET_BREDR, hdev);
new_settings(hdev, cmd->sk);
@@ -6729,7 +6707,7 @@ static void set_secure_conn_complete(struct hci_dev *hdev, void *data, int err)
if (err) {
u8 mgmt_err = mgmt_status(err);
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode, mgmt_err);
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode, mgmt_err);
goto done;
}
@@ -7176,7 +7154,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err)
rp.max_tx_power = HCI_TX_POWER_INVALID;
}
- mgmt_cmd_complete(cmd->sk, cmd->index, MGMT_OP_GET_CONN_INFO, status,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, MGMT_OP_GET_CONN_INFO, status,
&rp, sizeof(rp));
mgmt_pending_free(cmd);
@@ -7336,7 +7314,7 @@ static void get_clock_info_complete(struct hci_dev *hdev, void *data, int err)
}
complete:
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, status, &rp,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode, status, &rp,
sizeof(rp));
mgmt_pending_free(cmd);
@@ -8586,10 +8564,10 @@ static void add_advertising_complete(struct hci_dev *hdev, void *data, int err)
rp.instance = cp->instance;
if (err)
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err));
else
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err), &rp, sizeof(rp));
add_adv_complete(hdev, cmd->sk, cp->instance, err);
@@ -8777,10 +8755,10 @@ static void add_ext_adv_params_complete(struct hci_dev *hdev, void *data,
hci_remove_adv_instance(hdev, cp->instance);
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err));
} else {
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err), &rp, sizeof(rp));
}
@@ -8927,10 +8905,10 @@ static void add_ext_adv_data_complete(struct hci_dev *hdev, void *data, int err)
rp.instance = cp->instance;
if (err)
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err));
else
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err), &rp, sizeof(rp));
mgmt_pending_free(cmd);
@@ -9089,10 +9067,10 @@ static void remove_advertising_complete(struct hci_dev *hdev, void *data,
rp.instance = cp->instance;
if (err)
- mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_status(cmd->sk, cmd->hdev->id, cmd->opcode,
mgmt_status(err));
else
- mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+ mgmt_cmd_complete(cmd->sk, cmd->hdev->id, cmd->opcode,
MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
mgmt_pending_free(cmd);
@@ -9364,7 +9342,7 @@ void mgmt_index_removed(struct hci_dev *hdev)
if (test_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks))
return;
- mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match);
+ mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match);
if (hci_dev_test_flag(hdev, HCI_UNCONFIGURED)) {
mgmt_index_event(MGMT_EV_UNCONF_INDEX_REMOVED, hdev, NULL, 0,
@@ -9402,7 +9380,8 @@ void mgmt_power_on(struct hci_dev *hdev, int err)
hci_update_passive_scan(hdev);
}
- mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
+ mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp,
+ &match);
new_settings(hdev, match.sk);
@@ -9417,7 +9396,8 @@ void __mgmt_power_off(struct hci_dev *hdev)
struct cmd_lookup match = { NULL, hdev };
u8 zero_cod[] = { 0, 0, 0 };
- mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, settings_rsp, &match);
+ mgmt_pending_foreach(MGMT_OP_SET_POWERED, hdev, true, settings_rsp,
+ &match);
/* If the power off is because of hdev unregistration let
* use the appropriate INVALID_INDEX status. Otherwise use
@@ -9431,7 +9411,7 @@ void __mgmt_power_off(struct hci_dev *hdev)
else
match.mgmt_status = MGMT_STATUS_NOT_POWERED;
- mgmt_pending_foreach(0, hdev, cmd_complete_rsp, &match);
+ mgmt_pending_foreach(0, hdev, true, cmd_complete_rsp, &match);
if (memcmp(hdev->dev_class, zero_cod, sizeof(zero_cod)) != 0) {
mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev,
@@ -9672,7 +9652,6 @@ static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data)
device_unpaired(hdev, &cp->addr.bdaddr, cp->addr.type, cmd->sk);
cmd->cmd_complete(cmd, 0);
- mgmt_pending_remove(cmd);
}
bool mgmt_powering_down(struct hci_dev *hdev)
@@ -9728,8 +9707,8 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
struct mgmt_cp_disconnect *cp;
struct mgmt_pending_cmd *cmd;
- mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
- hdev);
+ mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, true,
+ unpair_device_rsp, hdev);
cmd = pending_find(MGMT_OP_DISCONNECT, hdev);
if (!cmd)
@@ -9922,7 +9901,7 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
if (status) {
u8 mgmt_err = mgmt_status(status);
- mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev,
+ mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true,
cmd_status_rsp, &mgmt_err);
return;
}
@@ -9932,8 +9911,8 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status)
else
changed = hci_dev_test_and_clear_flag(hdev, HCI_LINK_SECURITY);
- mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, settings_rsp,
- &match);
+ mgmt_pending_foreach(MGMT_OP_SET_LINK_SECURITY, hdev, true,
+ settings_rsp, &match);
if (changed)
new_settings(hdev, match.sk);
@@ -9957,9 +9936,12 @@ void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
{
struct cmd_lookup match = { NULL, hdev, mgmt_status(status) };
- mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, sk_lookup, &match);
- mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, sk_lookup, &match);
- mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, sk_lookup, &match);
+ mgmt_pending_foreach(MGMT_OP_SET_DEV_CLASS, hdev, false, sk_lookup,
+ &match);
+ mgmt_pending_foreach(MGMT_OP_ADD_UUID, hdev, false, sk_lookup,
+ &match);
+ mgmt_pending_foreach(MGMT_OP_REMOVE_UUID, hdev, false, sk_lookup,
+ &match);
if (!status) {
mgmt_limited_event(MGMT_EV_CLASS_OF_DEV_CHANGED, hdev, dev_class,
diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c
index 3713ff490c65..a88a07da3947 100644
--- a/net/bluetooth/mgmt_util.c
+++ b/net/bluetooth/mgmt_util.c
@@ -217,30 +217,47 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
struct hci_dev *hdev)
{
- struct mgmt_pending_cmd *cmd;
+ struct mgmt_pending_cmd *cmd, *tmp;
+
+ mutex_lock(&hdev->mgmt_pending_lock);
- list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
+ list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
if (hci_sock_get_channel(cmd->sk) != channel)
continue;
- if (cmd->opcode == opcode)
+
+ if (cmd->opcode == opcode) {
+ mutex_unlock(&hdev->mgmt_pending_lock);
return cmd;
+ }
}
+ mutex_unlock(&hdev->mgmt_pending_lock);
+
return NULL;
}
-void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove,
void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
void *data)
{
struct mgmt_pending_cmd *cmd, *tmp;
+ mutex_lock(&hdev->mgmt_pending_lock);
+
list_for_each_entry_safe(cmd, tmp, &hdev->mgmt_pending, list) {
if (opcode > 0 && cmd->opcode != opcode)
continue;
+ if (remove)
+ list_del(&cmd->list);
+
cb(cmd, data);
+
+ if (remove)
+ mgmt_pending_free(cmd);
}
+
+ mutex_unlock(&hdev->mgmt_pending_lock);
}
struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode,
@@ -254,7 +271,7 @@ struct mgmt_pending_cmd *mgmt_pending_new(struct sock *sk, u16 opcode,
return NULL;
cmd->opcode = opcode;
- cmd->index = hdev->id;
+ cmd->hdev = hdev;
cmd->param = kmemdup(data, len, GFP_KERNEL);
if (!cmd->param) {
@@ -280,7 +297,9 @@ struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
if (!cmd)
return NULL;
+ mutex_lock(&hdev->mgmt_pending_lock);
list_add_tail(&cmd->list, &hdev->mgmt_pending);
+ mutex_unlock(&hdev->mgmt_pending_lock);
return cmd;
}
@@ -294,7 +313,10 @@ void mgmt_pending_free(struct mgmt_pending_cmd *cmd)
void mgmt_pending_remove(struct mgmt_pending_cmd *cmd)
{
+ mutex_lock(&cmd->hdev->mgmt_pending_lock);
list_del(&cmd->list);
+ mutex_unlock(&cmd->hdev->mgmt_pending_lock);
+
mgmt_pending_free(cmd);
}
diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h
index f2ba994ab1d8..024e51dd6937 100644
--- a/net/bluetooth/mgmt_util.h
+++ b/net/bluetooth/mgmt_util.h
@@ -33,7 +33,7 @@ struct mgmt_mesh_tx {
struct mgmt_pending_cmd {
struct list_head list;
u16 opcode;
- int index;
+ struct hci_dev *hdev;
void *param;
size_t param_len;
struct sock *sk;
@@ -54,7 +54,7 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
struct hci_dev *hdev);
-void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
+void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev, bool remove,
void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
void *data);
struct mgmt_pending_cmd *mgmt_pending_add(struct sock *sk, u16 opcode,
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index aaf13a7d58ed..9728dbd4c66c 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -1255,7 +1255,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
headroom -= ctx->data;
}
- max_data_sz = 4096 - headroom - tailroom;
+ max_data_sz = PAGE_SIZE - headroom - tailroom;
if (size > max_data_sz) {
/* disallow live data mode for jumbo frames */
if (do_live)
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 0224ef3dfec0..1377f31b719c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -2015,10 +2015,19 @@ void br_multicast_port_ctx_init(struct net_bridge_port *port,
void br_multicast_port_ctx_deinit(struct net_bridge_mcast_port *pmctx)
{
+ struct net_bridge *br = pmctx->port->br;
+ bool del = false;
+
#if IS_ENABLED(CONFIG_IPV6)
timer_delete_sync(&pmctx->ip6_mc_router_timer);
#endif
timer_delete_sync(&pmctx->ip4_mc_router_timer);
+
+ spin_lock_bh(&br->multicast_lock);
+ del |= br_ip6_multicast_rport_del(pmctx);
+ del |= br_ip4_multicast_rport_del(pmctx);
+ br_multicast_rport_del_notify(pmctx, del);
+ spin_unlock_bh(&br->multicast_lock);
}
int br_multicast_add_port(struct net_bridge_port *port)
diff --git a/net/core/filter.c b/net/core/filter.c
index 327ca73f9cd7..7a72f766aacf 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3233,6 +3233,13 @@ static const struct bpf_func_proto bpf_skb_vlan_pop_proto = {
.arg1_type = ARG_PTR_TO_CTX,
};
+static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto)
+{
+ skb->protocol = htons(proto);
+ if (skb_valid_dst(skb))
+ skb_dst_drop(skb);
+}
+
static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len)
{
/* Caller already did skb_cow() with len as headroom,
@@ -3329,7 +3336,7 @@ static int bpf_skb_proto_4_to_6(struct sk_buff *skb)
}
}
- skb->protocol = htons(ETH_P_IPV6);
+ bpf_skb_change_protocol(skb, ETH_P_IPV6);
skb_clear_hash(skb);
return 0;
@@ -3359,7 +3366,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb)
}
}
- skb->protocol = htons(ETH_P_IP);
+ bpf_skb_change_protocol(skb, ETH_P_IP);
skb_clear_hash(skb);
return 0;
@@ -3550,10 +3557,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
/* Match skb->protocol to new outer l3 protocol */
if (skb->protocol == htons(ETH_P_IP) &&
flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
- skb->protocol = htons(ETH_P_IPV6);
+ bpf_skb_change_protocol(skb, ETH_P_IPV6);
else if (skb->protocol == htons(ETH_P_IPV6) &&
flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
- skb->protocol = htons(ETH_P_IP);
+ bpf_skb_change_protocol(skb, ETH_P_IP);
}
if (skb_is_gso(skb)) {
@@ -3606,10 +3613,10 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
/* Match skb->protocol to new outer l3 protocol */
if (skb->protocol == htons(ETH_P_IP) &&
flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
- skb->protocol = htons(ETH_P_IPV6);
+ bpf_skb_change_protocol(skb, ETH_P_IPV6);
else if (skb->protocol == htons(ETH_P_IPV6) &&
flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
- skb->protocol = htons(ETH_P_IP);
+ bpf_skb_change_protocol(skb, ETH_P_IP);
if (skb_is_gso(skb)) {
struct skb_shared_info *shinfo = skb_shinfo(skb);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 4ddb7490df4b..6ad84d4a2b46 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -432,6 +432,7 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
udph->dest = htons(np->remote_port);
udph->len = htons(udp_len);
+ udph->check = 0;
if (np->ipv6) {
udph->check = csum_ipv6_magic(&np->local_ip.in6,
&np->remote_ip.in6,
@@ -460,7 +461,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
skb_reset_mac_header(skb);
skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
} else {
- udph->check = 0;
udph->check = csum_tcpudp_magic(np->local_ip.ip,
np->remote_ip.ip,
udp_len, IPPROTO_UDP,
diff --git a/net/core/selftests.c b/net/core/selftests.c
index 35f807ea9952..406faf8e5f3f 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -160,8 +160,9 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
skb->csum = 0;
skb->ip_summed = CHECKSUM_PARTIAL;
if (attr->tcp) {
- thdr->check = ~tcp_v4_check(skb->len, ihdr->saddr,
- ihdr->daddr, 0);
+ int l4len = skb->len - skb_transport_offset(skb);
+
+ thdr->check = ~tcp_v4_check(l4len, ihdr->saddr, ihdr->daddr, 0);
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct tcphdr, check);
} else {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 85fc82f72d26..d6420b74ea9c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6261,9 +6261,6 @@ int skb_ensure_writable(struct sk_buff *skb, unsigned int write_len)
if (!pskb_may_pull(skb, write_len))
return -ENOMEM;
- if (!skb_frags_readable(skb))
- return -EFAULT;
-
if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
return 0;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 39ec920f5de7..71c828d0bf31 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1083,7 +1083,8 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
ethtool_get_flow_spec_ring(info.fs.ring_cookie))
return -EINVAL;
- if (!xa_load(&dev->ethtool->rss_ctx, info.rss_context))
+ if (info.rss_context &&
+ !xa_load(&dev->ethtool->rss_ctx, info.rss_context))
return -EINVAL;
}
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 9b83d639b5ac..5107121c5e37 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -3,6 +3,7 @@
#include <linux/tcp.h>
#include <linux/rcupdate.h>
#include <net/tcp.h>
+#include <net/busy_poll.h>
void tcp_fastopen_init_key_once(struct net *net)
{
@@ -279,6 +280,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
refcount_set(&req->rsk_refcnt, 2);
+ sk_mark_napi_id_set(child, skb);
+
/* Now finish processing the fastopen child socket. */
tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 8ec92dec321a..12c2e6fc85c6 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2479,20 +2479,33 @@ static inline bool tcp_packet_delayed(const struct tcp_sock *tp)
{
const struct sock *sk = (const struct sock *)tp;
- if (tp->retrans_stamp &&
- tcp_tsopt_ecr_before(tp, tp->retrans_stamp))
- return true; /* got echoed TS before first retransmission */
-
- /* Check if nothing was retransmitted (retrans_stamp==0), which may
- * happen in fast recovery due to TSQ. But we ignore zero retrans_stamp
- * in TCP_SYN_SENT, since when we set FLAG_SYN_ACKED we also clear
- * retrans_stamp even if we had retransmitted the SYN.
+ /* Received an echoed timestamp before the first retransmission? */
+ if (tp->retrans_stamp)
+ return tcp_tsopt_ecr_before(tp, tp->retrans_stamp);
+
+ /* We set tp->retrans_stamp upon the first retransmission of a loss
+ * recovery episode, so normally if tp->retrans_stamp is 0 then no
+ * retransmission has happened yet (likely due to TSQ, which can cause
+ * fast retransmits to be delayed). So if snd_una advanced while
+ * (tp->retrans_stamp is 0 then apparently a packet was merely delayed,
+ * not lost. But there are exceptions where we retransmit but then
+ * clear tp->retrans_stamp, so we check for those exceptions.
*/
- if (!tp->retrans_stamp && /* no record of a retransmit/SYN? */
- sk->sk_state != TCP_SYN_SENT) /* not the FLAG_SYN_ACKED case? */
- return true; /* nothing was retransmitted */
- return false;
+ /* (1) For non-SACK connections, tcp_is_non_sack_preventing_reopen()
+ * clears tp->retrans_stamp when snd_una == high_seq.
+ */
+ if (!tcp_is_sack(tp) && !before(tp->snd_una, tp->high_seq))
+ return false;
+
+ /* (2) In TCP_SYN_SENT tcp_clean_rtx_queue() clears tp->retrans_stamp
+ * when setting FLAG_SYN_ACKED is set, even if the SYN was
+ * retransmitted.
+ */
+ if (sk->sk_state == TCP_SYN_SENT)
+ return false;
+
+ return true; /* tp->retrans_stamp is zero; no retransmit yet */
}
/* Undo procedures. */
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 62618a058b8f..a247bb93908b 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -1207,6 +1207,10 @@ static int calipso_req_setattr(struct request_sock *req,
struct ipv6_opt_hdr *old, *new;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return -ENOMEM;
+
if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt)
old = req_inet->ipv6_opt->hopopt;
else
@@ -1247,6 +1251,10 @@ static void calipso_req_delattr(struct request_sock *req)
struct ipv6_txoptions *txopts;
struct sock *sk = sk_to_full_sk(req_to_sk(req));
+ /* sk is NULL for SYN+ACK w/ SYN Cookie */
+ if (!sk)
+ return;
+
if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt)
return;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0143262094b0..79c8f1acf8a3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3737,6 +3737,53 @@ void fib6_nh_release_dsts(struct fib6_nh *fib6_nh)
}
}
+static int fib6_config_validate(struct fib6_config *cfg,
+ struct netlink_ext_ack *extack)
+{
+ /* RTF_PCPU is an internal flag; can not be set by userspace */
+ if (cfg->fc_flags & RTF_PCPU) {
+ NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
+ goto errout;
+ }
+
+ /* RTF_CACHE is an internal flag; can not be set by userspace */
+ if (cfg->fc_flags & RTF_CACHE) {
+ NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
+ goto errout;
+ }
+
+ if (cfg->fc_type > RTN_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid route type");
+ goto errout;
+ }
+
+ if (cfg->fc_dst_len > 128) {
+ NL_SET_ERR_MSG(extack, "Invalid prefix length");
+ goto errout;
+ }
+
+#ifdef CONFIG_IPV6_SUBTREES
+ if (cfg->fc_src_len > 128) {
+ NL_SET_ERR_MSG(extack, "Invalid source address length");
+ goto errout;
+ }
+
+ if (cfg->fc_nh_id && cfg->fc_src_len) {
+ NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+ goto errout;
+ }
+#else
+ if (cfg->fc_src_len) {
+ NL_SET_ERR_MSG(extack,
+ "Specifying source address requires IPV6_SUBTREES to be enabled");
+ goto errout;
+ }
+#endif
+ return 0;
+errout:
+ return -EINVAL;
+}
+
static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
gfp_t gfp_flags,
struct netlink_ext_ack *extack)
@@ -3886,6 +3933,10 @@ int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct fib6_info *rt;
int err;
+ err = fib6_config_validate(cfg, extack);
+ if (err)
+ return err;
+
rt = ip6_route_info_create(cfg, gfp_flags, extack);
if (IS_ERR(rt))
return PTR_ERR(rt);
@@ -4479,53 +4530,6 @@ void rt6_purge_dflt_routers(struct net *net)
rcu_read_unlock();
}
-static int fib6_config_validate(struct fib6_config *cfg,
- struct netlink_ext_ack *extack)
-{
- /* RTF_PCPU is an internal flag; can not be set by userspace */
- if (cfg->fc_flags & RTF_PCPU) {
- NL_SET_ERR_MSG(extack, "Userspace can not set RTF_PCPU");
- goto errout;
- }
-
- /* RTF_CACHE is an internal flag; can not be set by userspace */
- if (cfg->fc_flags & RTF_CACHE) {
- NL_SET_ERR_MSG(extack, "Userspace can not set RTF_CACHE");
- goto errout;
- }
-
- if (cfg->fc_type > RTN_MAX) {
- NL_SET_ERR_MSG(extack, "Invalid route type");
- goto errout;
- }
-
- if (cfg->fc_dst_len > 128) {
- NL_SET_ERR_MSG(extack, "Invalid prefix length");
- goto errout;
- }
-
-#ifdef CONFIG_IPV6_SUBTREES
- if (cfg->fc_src_len > 128) {
- NL_SET_ERR_MSG(extack, "Invalid source address length");
- goto errout;
- }
-
- if (cfg->fc_nh_id && cfg->fc_src_len) {
- NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
- goto errout;
- }
-#else
- if (cfg->fc_src_len) {
- NL_SET_ERR_MSG(extack,
- "Specifying source address requires IPV6_SUBTREES to be enabled");
- goto errout;
- }
-#endif
- return 0;
-errout:
- return -EINVAL;
-}
-
static void rtmsg_to_fib6_config(struct net *net,
struct in6_rtmsg *rtmsg,
struct fib6_config *cfg)
@@ -4563,10 +4567,6 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, struct in6_rtmsg *rtmsg)
switch (cmd) {
case SIOCADDRT:
- err = fib6_config_validate(&cfg, NULL);
- if (err)
- break;
-
/* Only do the default setting of fc_metric in route adding */
if (cfg.fc_metric == 0)
cfg.fc_metric = IP6_RT_PRIO_USER;
@@ -5402,6 +5402,10 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
int nhn = 0;
int err;
+ err = fib6_config_validate(cfg, extack);
+ if (err)
+ return err;
+
replace = (cfg->fc_nlinfo.nlh &&
(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_REPLACE));
@@ -5636,10 +5640,6 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (err < 0)
return err;
- err = fib6_config_validate(&cfg, extack);
- if (err)
- return err;
-
if (cfg.fc_metric == 0)
cfg.fc_metric = IP6_RT_PRIO_USER;
diff --git a/net/mac80211/debug.h b/net/mac80211/debug.h
index 5b81998cb0c9..ef7c1a68d88d 100644
--- a/net/mac80211/debug.h
+++ b/net/mac80211/debug.h
@@ -1,10 +1,11 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* Portions
- * Copyright (C) 2022 - 2024 Intel Corporation
+ * Copyright (C) 2022 - 2025 Intel Corporation
*/
#ifndef __MAC80211_DEBUG_H
#define __MAC80211_DEBUG_H
+#include <linux/once_lite.h>
#include <net/cfg80211.h>
#ifdef CONFIG_MAC80211_OCB_DEBUG
@@ -152,6 +153,8 @@ do { \
else \
_sdata_err((link)->sdata, fmt, ##__VA_ARGS__); \
} while (0)
+#define link_err_once(link, fmt, ...) \
+ DO_ONCE_LITE(link_err, link, fmt, ##__VA_ARGS__)
#define link_id_info(sdata, link_id, fmt, ...) \
do { \
if (ieee80211_vif_is_mld(&sdata->vif)) \
diff --git a/net/mac80211/link.c b/net/mac80211/link.c
index d40c2bd3b50b..4f7b7d0f64f2 100644
--- a/net/mac80211/link.c
+++ b/net/mac80211/link.c
@@ -93,9 +93,6 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
if (link_id < 0)
link_id = 0;
- rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf);
- rcu_assign_pointer(sdata->link[link_id], link);
-
if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
struct ieee80211_sub_if_data *ap_bss;
struct ieee80211_bss_conf *ap_bss_conf;
@@ -145,6 +142,9 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata,
ieee80211_link_debugfs_add(link);
}
+
+ rcu_assign_pointer(sdata->vif.link_conf[link_id], link_conf);
+ rcu_assign_pointer(sdata->link[link_id], link);
}
void ieee80211_link_stop(struct ieee80211_link_data *link)
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 09beb65d6108..e73431549ce7 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -4432,6 +4432,10 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
if (!multicast &&
!ether_addr_equal(sdata->dev->dev_addr, hdr->addr1))
return false;
+ /* reject invalid/our STA address */
+ if (!is_valid_ether_addr(hdr->addr2) ||
+ ether_addr_equal(sdata->dev->dev_addr, hdr->addr2))
+ return false;
if (!rx->sta) {
int rate_idx;
if (status->encoding != RX_ENC_LEGACY)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index d8d4f3d7d7f2..d58b80813bdd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5,7 +5,7 @@
* Copyright 2006-2007 Jiri Benc <jbenc@suse.cz>
* Copyright 2007 Johannes Berg <johannes@sipsolutions.net>
* Copyright 2013-2014 Intel Mobile Communications GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
*
* Transmit and frame generation functions.
*/
@@ -5016,12 +5016,25 @@ static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata,
}
}
-static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
+static u8 __ieee80211_beacon_update_cntdwn(struct ieee80211_link_data *link,
+ struct beacon_data *beacon)
{
- beacon->cntdwn_current_counter--;
+ if (beacon->cntdwn_current_counter == 1) {
+ /*
+ * Channel switch handling is done by a worker thread while
+ * beacons get pulled from hardware timers. It's therefore
+ * possible that software threads are slow enough to not be
+ * able to complete CSA handling in a single beacon interval,
+ * in which case we get here. There isn't much to do about
+ * it, other than letting the user know that the AP isn't
+ * behaving correctly.
+ */
+ link_err_once(link,
+ "beacon TX faster than countdown (channel/color switch) completion\n");
+ return 0;
+ }
- /* the counter should never reach 0 */
- WARN_ON_ONCE(!beacon->cntdwn_current_counter);
+ beacon->cntdwn_current_counter--;
return beacon->cntdwn_current_counter;
}
@@ -5052,7 +5065,7 @@ u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif, unsigned int link_i
if (!beacon)
goto unlock;
- count = __ieee80211_beacon_update_cntdwn(beacon);
+ count = __ieee80211_beacon_update_cntdwn(link, beacon);
unlock:
rcu_read_unlock();
@@ -5450,7 +5463,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
if (beacon->cntdwn_counter_offsets[0]) {
if (!is_template)
- __ieee80211_beacon_update_cntdwn(beacon);
+ __ieee80211_beacon_update_cntdwn(link, beacon);
ieee80211_set_beacon_cntdwn(sdata, beacon, link);
}
@@ -5482,7 +5495,7 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
* for now we leave it consistent with overall
* mac80211's behavior.
*/
- __ieee80211_beacon_update_cntdwn(beacon);
+ __ieee80211_beacon_update_cntdwn(link, beacon);
ieee80211_set_beacon_cntdwn(sdata, beacon, link);
}
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 27d414efa3fd..a125995ed252 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -3884,7 +3884,7 @@ void ieee80211_recalc_dtim(struct ieee80211_local *local,
{
u64 tsf = drv_get_tsf(local, sdata);
u64 dtim_count = 0;
- u16 beacon_int = sdata->vif.bss_conf.beacon_int * 1024;
+ u32 beacon_int = sdata->vif.bss_conf.beacon_int * 1024;
u8 dtim_period = sdata->vif.bss_conf.dtim_period;
struct ps_data *ps;
u8 bcns_from_dtim;
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index d536c97144e9..47d7dfd9ad09 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -81,8 +81,8 @@ static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
if (index < net->mpls.platform_labels) {
struct mpls_route __rcu **platform_label =
- rcu_dereference(net->mpls.platform_label);
- rt = rcu_dereference(platform_label[index]);
+ rcu_dereference_rtnl(net->mpls.platform_label);
+ rt = rcu_dereference_rtnl(platform_label[index]);
}
return rt;
}
diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c
index ed1508a9e093..aab107727f18 100644
--- a/net/nfc/nci/uart.c
+++ b/net/nfc/nci/uart.c
@@ -119,22 +119,22 @@ static int nci_uart_set_driver(struct tty_struct *tty, unsigned int driver)
memcpy(nu, nci_uart_drivers[driver], sizeof(struct nci_uart));
nu->tty = tty;
- tty->disc_data = nu;
skb_queue_head_init(&nu->tx_q);
INIT_WORK(&nu->write_work, nci_uart_write_work);
spin_lock_init(&nu->rx_lock);
ret = nu->ops.open(nu);
if (ret) {
- tty->disc_data = NULL;
kfree(nu);
+ return ret;
} else if (!try_module_get(nu->owner)) {
nu->ops.close(nu);
- tty->disc_data = NULL;
kfree(nu);
return -ENOENT;
}
- return ret;
+ tty->disc_data = nu;
+
+ return 0;
}
/* ------ LDISC part ------ */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index e7269a3eec79..3add108340bf 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -39,16 +39,14 @@
#include "flow_netlink.h"
#include "openvswitch_trace.h"
-DEFINE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage) = {
- .bh_lock = INIT_LOCAL_LOCK(bh_lock),
-};
+struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
/* Make a clone of the 'key', using the pre-allocated percpu 'flow_keys'
* space. Return NULL if out of key spaces.
*/
static struct sw_flow_key *clone_key(const struct sw_flow_key *key_)
{
- struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+ struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
struct action_flow_keys *keys = &ovs_pcpu->flow_keys;
int level = ovs_pcpu->exec_level;
struct sw_flow_key *key = NULL;
@@ -94,7 +92,7 @@ static struct deferred_action *add_deferred_actions(struct sk_buff *skb,
const struct nlattr *actions,
const int actions_len)
{
- struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+ struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
struct deferred_action *da;
da = action_fifo_put(fifo);
@@ -755,7 +753,7 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
static int ovs_vport_output(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
- struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+ struct ovs_frag_data *data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
struct vport *vport = data->vport;
if (skb_cow_head(skb, data->l2_len) < 0) {
@@ -807,7 +805,7 @@ static void prepare_frag(struct vport *vport, struct sk_buff *skb,
unsigned int hlen = skb_network_offset(skb);
struct ovs_frag_data *data;
- data = this_cpu_ptr(&ovs_pcpu_storage.frag_data);
+ data = this_cpu_ptr(&ovs_pcpu_storage->frag_data);
data->dst = skb->_skb_refdst;
data->vport = vport;
data->cb = *OVS_CB(skb);
@@ -1566,16 +1564,15 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
clone = clone_flow_key ? clone_key(key) : key;
if (clone) {
int err = 0;
-
if (actions) { /* Sample action */
if (clone_flow_key)
- __this_cpu_inc(ovs_pcpu_storage.exec_level);
+ __this_cpu_inc(ovs_pcpu_storage->exec_level);
err = do_execute_actions(dp, skb, clone,
actions, len);
if (clone_flow_key)
- __this_cpu_dec(ovs_pcpu_storage.exec_level);
+ __this_cpu_dec(ovs_pcpu_storage->exec_level);
} else { /* Recirc action */
clone->recirc_id = recirc_id;
ovs_dp_process_packet(skb, clone);
@@ -1611,7 +1608,7 @@ static int clone_execute(struct datapath *dp, struct sk_buff *skb,
static void process_deferred_actions(struct datapath *dp)
{
- struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage.action_fifos);
+ struct action_fifo *fifo = this_cpu_ptr(&ovs_pcpu_storage->action_fifos);
/* Do not touch the FIFO in case there is no deferred actions. */
if (action_fifo_is_empty(fifo))
@@ -1642,7 +1639,7 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
{
int err, level;
- level = __this_cpu_inc_return(ovs_pcpu_storage.exec_level);
+ level = __this_cpu_inc_return(ovs_pcpu_storage->exec_level);
if (unlikely(level > OVS_RECURSION_LIMIT)) {
net_crit_ratelimited("ovs: recursion limit reached on datapath %s, probable configuration error\n",
ovs_dp_name(dp));
@@ -1659,6 +1656,6 @@ int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb,
process_deferred_actions(dp);
out:
- __this_cpu_dec(ovs_pcpu_storage.exec_level);
+ __this_cpu_dec(ovs_pcpu_storage->exec_level);
return err;
}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6a304ae2d959..b990dc83504f 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -244,7 +244,7 @@ void ovs_dp_detach_port(struct vport *p)
/* Must be called with rcu_read_lock. */
void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
{
- struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(&ovs_pcpu_storage);
+ struct ovs_pcpu_storage *ovs_pcpu = this_cpu_ptr(ovs_pcpu_storage);
const struct vport *p = OVS_CB(skb)->input_vport;
struct datapath *dp = p->dp;
struct sw_flow *flow;
@@ -299,7 +299,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
* avoided.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT) && ovs_pcpu->owner != current) {
- local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+ local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
ovs_pcpu->owner = current;
ovs_pcpu_locked = true;
}
@@ -310,7 +310,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
ovs_dp_name(dp), error);
if (ovs_pcpu_locked) {
ovs_pcpu->owner = NULL;
- local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+ local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
}
stats_counter = &stats->n_hit;
@@ -689,13 +689,13 @@ static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
sf_acts = rcu_dereference(flow->sf_acts);
local_bh_disable();
- local_lock_nested_bh(&ovs_pcpu_storage.bh_lock);
+ local_lock_nested_bh(&ovs_pcpu_storage->bh_lock);
if (IS_ENABLED(CONFIG_PREEMPT_RT))
- this_cpu_write(ovs_pcpu_storage.owner, current);
+ this_cpu_write(ovs_pcpu_storage->owner, current);
err = ovs_execute_actions(dp, packet, sf_acts, &flow->key);
if (IS_ENABLED(CONFIG_PREEMPT_RT))
- this_cpu_write(ovs_pcpu_storage.owner, NULL);
- local_unlock_nested_bh(&ovs_pcpu_storage.bh_lock);
+ this_cpu_write(ovs_pcpu_storage->owner, NULL);
+ local_unlock_nested_bh(&ovs_pcpu_storage->bh_lock);
local_bh_enable();
rcu_read_unlock();
@@ -2744,6 +2744,28 @@ static struct drop_reason_list drop_reason_list_ovs = {
.n_reasons = ARRAY_SIZE(ovs_drop_reasons),
};
+static int __init ovs_alloc_percpu_storage(void)
+{
+ unsigned int cpu;
+
+ ovs_pcpu_storage = alloc_percpu(*ovs_pcpu_storage);
+ if (!ovs_pcpu_storage)
+ return -ENOMEM;
+
+ for_each_possible_cpu(cpu) {
+ struct ovs_pcpu_storage *ovs_pcpu;
+
+ ovs_pcpu = per_cpu_ptr(ovs_pcpu_storage, cpu);
+ local_lock_init(&ovs_pcpu->bh_lock);
+ }
+ return 0;
+}
+
+static void ovs_free_percpu_storage(void)
+{
+ free_percpu(ovs_pcpu_storage);
+}
+
static int __init dp_init(void)
{
int err;
@@ -2753,6 +2775,10 @@ static int __init dp_init(void)
pr_info("Open vSwitch switching datapath\n");
+ err = ovs_alloc_percpu_storage();
+ if (err)
+ goto error;
+
err = ovs_internal_dev_rtnl_link_register();
if (err)
goto error;
@@ -2799,6 +2825,7 @@ error_flow_exit:
error_unreg_rtnl_link:
ovs_internal_dev_rtnl_link_unregister();
error:
+ ovs_free_percpu_storage();
return err;
}
@@ -2813,6 +2840,7 @@ static void dp_cleanup(void)
ovs_vport_exit();
ovs_flow_exit();
ovs_internal_dev_rtnl_link_unregister();
+ ovs_free_percpu_storage();
}
module_init(dp_init);
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 1b5348b0f559..cfeb817a1889 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -220,7 +220,8 @@ struct ovs_pcpu_storage {
struct task_struct *owner;
local_lock_t bh_lock;
};
-DECLARE_PER_CPU(struct ovs_pcpu_storage, ovs_pcpu_storage);
+
+extern struct ovs_pcpu_storage __percpu *ovs_pcpu_storage;
/**
* enum ovs_pkt_hash_types - hash info to include with a packet
diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 2c069f0181c6..037f764822b9 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -661,7 +661,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
for (i = q->nbands; i < oldbands; i++) {
if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
list_del_init(&q->classes[i].alist);
- qdisc_tree_flush_backlog(q->classes[i].qdisc);
+ qdisc_purge_queue(q->classes[i].qdisc);
}
WRITE_ONCE(q->nstrict, nstrict);
memcpy(q->prio2band, priomap, sizeof(priomap));
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index cc30f7a32f1a..9e2b9a490db2 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -211,7 +211,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt,
memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1);
for (i = q->bands; i < oldbands; i++)
- qdisc_tree_flush_backlog(q->queues[i]);
+ qdisc_purge_queue(q->queues[i]);
for (i = oldbands; i < q->bands; i++) {
q->queues[i] = queues[i];
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 339d70b4a4c5..479c42d11083 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -285,7 +285,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
q->userbits = userbits;
q->limit = ctl->limit;
if (child) {
- qdisc_tree_flush_backlog(q->qdisc);
+ qdisc_purge_queue(q->qdisc);
old_child = q->qdisc;
q->qdisc = child;
}
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index a8081492d671..96eb2f122973 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -310,7 +310,10 @@ drop:
/* It is difficult to believe, but ALL THE SLOTS HAVE LENGTH 1. */
x = q->tail->next;
slot = &q->slots[x];
- q->tail->next = slot->next;
+ if (slot->next == x)
+ q->tail = NULL; /* no more active slots */
+ else
+ q->tail->next = slot->next;
q->ht[slot->hash] = SFQ_EMPTY_SLOT;
goto drop;
}
@@ -653,6 +656,14 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
NL_SET_ERR_MSG_MOD(extack, "invalid quantum");
return -EINVAL;
}
+
+ if (ctl->perturb_period < 0 ||
+ ctl->perturb_period > INT_MAX / HZ) {
+ NL_SET_ERR_MSG_MOD(extack, "invalid perturb period");
+ return -EINVAL;
+ }
+ perturb_period = ctl->perturb_period * HZ;
+
if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
ctl_v1->Wlog, ctl_v1->Scell_log, NULL))
return -EINVAL;
@@ -669,14 +680,12 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt,
headdrop = q->headdrop;
maxdepth = q->maxdepth;
maxflows = q->maxflows;
- perturb_period = q->perturb_period;
quantum = q->quantum;
flags = q->flags;
/* update and validate configuration */
if (ctl->quantum)
quantum = ctl->quantum;
- perturb_period = ctl->perturb_period * HZ;
if (ctl->flows)
maxflows = min_t(u32, ctl->flows, SFQ_MAX_FLOWS);
if (ctl->divisor) {
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 14021b812329..2b14c81a87e5 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1328,13 +1328,15 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event,
stab = rtnl_dereference(q->root->stab);
- oper = rtnl_dereference(q->oper_sched);
+ rcu_read_lock();
+ oper = rcu_dereference(q->oper_sched);
if (oper)
taprio_update_queue_max_sdu(q, oper, stab);
- admin = rtnl_dereference(q->admin_sched);
+ admin = rcu_dereference(q->admin_sched);
if (admin)
taprio_update_queue_max_sdu(q, admin, stab);
+ rcu_read_unlock();
break;
}
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index dc26b22d53c7..4c977f049670 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -452,7 +452,7 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt,
sch_tree_lock(sch);
if (child) {
- qdisc_tree_flush_backlog(q->qdisc);
+ qdisc_purge_queue(q->qdisc);
old = q->qdisc;
q->qdisc = child;
}
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 939b6239df8a..9c93b854e809 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -638,8 +638,6 @@ EXPORT_SYMBOL_GPL(svc_destroy);
static bool
svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
{
- unsigned long ret;
-
rqstp->rq_maxpages = svc_serv_maxpages(serv);
/* rq_pages' last entry is NULL for historical reasons. */
@@ -649,9 +647,7 @@ svc_init_buffer(struct svc_rqst *rqstp, const struct svc_serv *serv, int node)
if (!rqstp->rq_pages)
return false;
- ret = alloc_pages_bulk_node(GFP_KERNEL, node, rqstp->rq_maxpages,
- rqstp->rq_pages);
- return ret == rqstp->rq_maxpages;
+ return true;
}
/*
@@ -1375,7 +1371,8 @@ svc_process_common(struct svc_rqst *rqstp)
case SVC_OK:
break;
case SVC_GARBAGE:
- goto err_garbage_args;
+ rqstp->rq_auth_stat = rpc_autherr_badcred;
+ goto err_bad_auth;
case SVC_SYSERR:
goto err_system_err;
case SVC_DENIED:
@@ -1516,14 +1513,6 @@ err_bad_proc:
*rqstp->rq_accept_statp = rpc_proc_unavail;
goto sendit;
-err_garbage_args:
- svc_printk(rqstp, "failed to decode RPC header\n");
-
- if (serv->sv_stats)
- serv->sv_stats->rpcbadfmt++;
- *rqstp->rq_accept_statp = rpc_garbage_args;
- goto sendit;
-
err_system_err:
if (serv->sv_stats)
serv->sv_stats->rpcbadfmt++;
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 108a4cc2e001..258d6aa4f21a 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -489,7 +489,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
rtnl_lock();
b = tipc_bearer_find(net, bname);
- if (!b) {
+ if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
rtnl_unlock();
return -EINVAL;
}
@@ -500,7 +500,7 @@ int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb)
rtnl_lock();
b = rtnl_dereference(tn->bearer_list[bid]);
- if (!b) {
+ if (!b || b->bcast_addr.media_id != TIPC_MEDIA_TYPE_UDP) {
rtnl_unlock();
return -EINVAL;
}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2e2e9997a68e..52b155123985 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -660,6 +660,11 @@ static void unix_sock_destructor(struct sock *sk)
#endif
}
+static unsigned int unix_skb_len(const struct sk_buff *skb)
+{
+ return skb->len - UNIXCB(skb).consumed;
+}
+
static void unix_release_sock(struct sock *sk, int embrion)
{
struct unix_sock *u = unix_sk(sk);
@@ -694,10 +699,16 @@ static void unix_release_sock(struct sock *sk, int embrion)
if (skpair != NULL) {
if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) {
+ struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
+
+#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
+ if (skb && !unix_skb_len(skb))
+ skb = skb_peek_next(skb, &sk->sk_receive_queue);
+#endif
unix_state_lock(skpair);
/* No more writes */
WRITE_ONCE(skpair->sk_shutdown, SHUTDOWN_MASK);
- if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || embrion)
+ if (skb || embrion)
WRITE_ONCE(skpair->sk_err, ECONNRESET);
unix_state_unlock(skpair);
skpair->sk_state_change(skpair);
@@ -1971,7 +1982,8 @@ static void unix_maybe_add_creds(struct sk_buff *skb, const struct sock *sk,
if (UNIXCB(skb).pid)
return;
- if (unix_may_passcred(sk) || unix_may_passcred(other)) {
+ if (unix_may_passcred(sk) || unix_may_passcred(other) ||
+ !other->sk_socket) {
UNIXCB(skb).pid = get_pid(task_tgid(current));
current_uid_gid(&UNIXCB(skb).uid, &UNIXCB(skb).gid);
}
@@ -2660,11 +2672,6 @@ static long unix_stream_data_wait(struct sock *sk, long timeo,
return timeo;
}
-static unsigned int unix_skb_len(const struct sk_buff *skb)
-{
- return skb->len - UNIXCB(skb).consumed;
-}
-
struct unix_stream_read_state {
int (*recv_actor)(struct sk_buff *, int, int,
struct unix_stream_read_state *);
@@ -2679,11 +2686,11 @@ struct unix_stream_read_state {
#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
static int unix_stream_recv_urg(struct unix_stream_read_state *state)
{
+ struct sk_buff *oob_skb, *read_skb = NULL;
struct socket *sock = state->socket;
struct sock *sk = sock->sk;
struct unix_sock *u = unix_sk(sk);
int chunk = 1;
- struct sk_buff *oob_skb;
mutex_lock(&u->iolock);
unix_state_lock(sk);
@@ -2698,9 +2705,16 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
oob_skb = u->oob_skb;
- if (!(state->flags & MSG_PEEK))
+ if (!(state->flags & MSG_PEEK)) {
WRITE_ONCE(u->oob_skb, NULL);
+ if (oob_skb->prev != (struct sk_buff *)&sk->sk_receive_queue &&
+ !unix_skb_len(oob_skb->prev)) {
+ read_skb = oob_skb->prev;
+ __skb_unlink(read_skb, &sk->sk_receive_queue);
+ }
+ }
+
spin_unlock(&sk->sk_receive_queue.lock);
unix_state_unlock(sk);
@@ -2711,6 +2725,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
mutex_unlock(&u->iolock);
+ consume_skb(read_skb);
+
if (chunk < 0)
return -EFAULT;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fd5f79266471..85f139016da2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1583,7 +1583,7 @@ nl80211_parse_connkeys(struct cfg80211_registered_device *rdev,
return result;
error:
- kfree(result);
+ kfree_sensitive(result);
return ERR_PTR(err);
}
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index bc494745f67b..8cbb660e2ec2 100644
--- a/rust/bindings/bindings_helper.h
+++ b/rust/bindings/bindings_helper.h
@@ -39,6 +39,7 @@
#include <linux/blk_types.h>
#include <linux/blkdev.h>
#include <linux/clk.h>
+#include <linux/completion.h>
#include <linux/configfs.h>
#include <linux/cpu.h>
#include <linux/cpufreq.h>
diff --git a/rust/helpers/completion.c b/rust/helpers/completion.c
new file mode 100644
index 000000000000..b2443262a2ae
--- /dev/null
+++ b/rust/helpers/completion.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/completion.h>
+
+void rust_helper_init_completion(struct completion *x)
+{
+ init_completion(x);
+}
diff --git a/rust/helpers/cpu.c b/rust/helpers/cpu.c
new file mode 100644
index 000000000000..824e0adb19d4
--- /dev/null
+++ b/rust/helpers/cpu.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/smp.h>
+
+unsigned int rust_helper_raw_smp_processor_id(void)
+{
+ return raw_smp_processor_id();
+}
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index 0f1b5d115985..b15b3cddad4e 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -13,6 +13,8 @@
#include "build_assert.c"
#include "build_bug.c"
#include "clk.c"
+#include "completion.c"
+#include "cpu.c"
#include "cpufreq.c"
#include "cpumask.c"
#include "cred.c"
diff --git a/rust/kernel/cpu.rs b/rust/kernel/cpu.rs
index 10c5c3b25873..b75403b0eb56 100644
--- a/rust/kernel/cpu.rs
+++ b/rust/kernel/cpu.rs
@@ -6,6 +6,127 @@
use crate::{bindings, device::Device, error::Result, prelude::ENODEV};
+/// Returns the maximum number of possible CPUs in the current system configuration.
+#[inline]
+pub fn nr_cpu_ids() -> u32 {
+ #[cfg(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS))]
+ {
+ bindings::NR_CPUS
+ }
+
+ #[cfg(not(any(NR_CPUS_1, CONFIG_FORCE_NR_CPUS)))]
+ // SAFETY: `nr_cpu_ids` is a valid global provided by the kernel.
+ unsafe {
+ bindings::nr_cpu_ids
+ }
+}
+
+/// The CPU ID.
+///
+/// Represents a CPU identifier as a wrapper around an [`u32`].
+///
+/// # Invariants
+///
+/// The CPU ID lies within the range `[0, nr_cpu_ids())`.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::cpu::CpuId;
+///
+/// let cpu = 0;
+///
+/// // SAFETY: 0 is always a valid CPU number.
+/// let id = unsafe { CpuId::from_u32_unchecked(cpu) };
+///
+/// assert_eq!(id.as_u32(), cpu);
+/// assert!(CpuId::from_i32(0).is_some());
+/// assert!(CpuId::from_i32(-1).is_none());
+/// ```
+#[derive(Copy, Clone, PartialEq, Eq, Debug)]
+pub struct CpuId(u32);
+
+impl CpuId {
+ /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+ ///
+ /// # Safety
+ ///
+ /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+ #[inline]
+ pub unsafe fn from_i32_unchecked(id: i32) -> Self {
+ debug_assert!(id >= 0);
+ debug_assert!((id as u32) < nr_cpu_ids());
+
+ // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+ Self(id as u32)
+ }
+
+ /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+ pub fn from_i32(id: i32) -> Option<Self> {
+ if id < 0 || id as u32 >= nr_cpu_ids() {
+ None
+ } else {
+ // INVARIANT: `id` has just been checked as a valid CPU ID.
+ Some(Self(id as u32))
+ }
+ }
+
+ /// Creates a new [`CpuId`] from the given `id` without checking bounds.
+ ///
+ /// # Safety
+ ///
+ /// The caller must ensure that `id` is a valid CPU ID (i.e., `0 <= id < nr_cpu_ids()`).
+ #[inline]
+ pub unsafe fn from_u32_unchecked(id: u32) -> Self {
+ debug_assert!(id < nr_cpu_ids());
+
+ // Ensure the `id` fits in an [`i32`] as it's also representable that way.
+ debug_assert!(id <= i32::MAX as u32);
+
+ // INVARIANT: The function safety guarantees `id` is a valid CPU id.
+ Self(id)
+ }
+
+ /// Creates a new [`CpuId`] from the given `id`, checking that it is valid.
+ pub fn from_u32(id: u32) -> Option<Self> {
+ if id >= nr_cpu_ids() {
+ None
+ } else {
+ // INVARIANT: `id` has just been checked as a valid CPU ID.
+ Some(Self(id))
+ }
+ }
+
+ /// Returns CPU number.
+ #[inline]
+ pub fn as_u32(&self) -> u32 {
+ self.0
+ }
+
+ /// Returns the ID of the CPU the code is currently running on.
+ ///
+ /// The returned value is considered unstable because it may change
+ /// unexpectedly due to preemption or CPU migration. It should only be
+ /// used when the context ensures that the task remains on the same CPU
+ /// or the users could use a stale (yet valid) CPU ID.
+ pub fn current() -> Self {
+ // SAFETY: raw_smp_processor_id() always returns a valid CPU ID.
+ unsafe { Self::from_u32_unchecked(bindings::raw_smp_processor_id()) }
+ }
+}
+
+impl From<CpuId> for u32 {
+ fn from(id: CpuId) -> Self {
+ id.as_u32()
+ }
+}
+
+impl From<CpuId> for i32 {
+ fn from(id: CpuId) -> Self {
+ id.as_u32() as i32
+ }
+}
+
/// Creates a new instance of CPU's device.
///
/// # Safety
@@ -17,9 +138,9 @@ use crate::{bindings, device::Device, error::Result, prelude::ENODEV};
/// Callers must ensure that the CPU device is not used after it has been unregistered.
/// This can be achieved, for example, by registering a CPU hotplug notifier and removing
/// any references to the CPU device within the notifier's callback.
-pub unsafe fn from_cpu(cpu: u32) -> Result<&'static Device> {
+pub unsafe fn from_cpu(cpu: CpuId) -> Result<&'static Device> {
// SAFETY: It is safe to call `get_cpu_device()` for any CPU.
- let ptr = unsafe { bindings::get_cpu_device(cpu) };
+ let ptr = unsafe { bindings::get_cpu_device(u32::from(cpu)) };
if ptr.is_null() {
return Err(ENODEV);
}
diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index b0a9c6182aec..11b03e9d7e89 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -10,6 +10,7 @@
use crate::{
clk::Hertz,
+ cpu::CpuId,
cpumask,
device::{Bound, Device},
devres::Devres,
@@ -465,8 +466,9 @@ impl Policy {
/// Returns the primary CPU for the [`Policy`].
#[inline]
- pub fn cpu(&self) -> u32 {
- self.as_ref().cpu
+ pub fn cpu(&self) -> CpuId {
+ // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+ unsafe { CpuId::from_u32_unchecked(self.as_ref().cpu) }
}
/// Returns the minimum frequency for the [`Policy`].
@@ -525,7 +527,7 @@ impl Policy {
#[inline]
pub fn generic_get(&self) -> Result<u32> {
// SAFETY: By the type invariant, the pointer stored in `self` is valid.
- Ok(unsafe { bindings::cpufreq_generic_get(self.cpu()) })
+ Ok(unsafe { bindings::cpufreq_generic_get(u32::from(self.cpu())) })
}
/// Provides a wrapper to the register with energy model using the OPP core.
@@ -678,9 +680,9 @@ impl Policy {
struct PolicyCpu<'a>(&'a mut Policy);
impl<'a> PolicyCpu<'a> {
- fn from_cpu(cpu: u32) -> Result<Self> {
+ fn from_cpu(cpu: CpuId) -> Result<Self> {
// SAFETY: It is safe to call `cpufreq_cpu_get` for any valid CPU.
- let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(cpu) })?;
+ let ptr = from_err_ptr(unsafe { bindings::cpufreq_cpu_get(u32::from(cpu)) })?;
Ok(Self(
// SAFETY: The `ptr` is guaranteed to be valid and remains valid for the lifetime of
@@ -1055,8 +1057,11 @@ impl<T: Driver> Registration<T> {
impl<T: Driver> Registration<T> {
/// Driver's `init` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn init_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1070,8 +1075,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `exit` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn exit_callback(ptr: *mut bindings::cpufreq_policy) {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1082,8 +1090,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `online` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn online_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1094,8 +1105,13 @@ impl<T: Driver> Registration<T> {
/// Driver's `offline` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn offline_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn offline_callback(
+ ptr: *mut bindings::cpufreq_policy,
+ ) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1106,8 +1122,13 @@ impl<T: Driver> Registration<T> {
/// Driver's `suspend` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn suspend_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn suspend_callback(
+ ptr: *mut bindings::cpufreq_policy,
+ ) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1118,8 +1139,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `resume` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn resume_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1130,8 +1154,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `ready` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn ready_callback(ptr: *mut bindings::cpufreq_policy) {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1140,8 +1167,13 @@ impl<T: Driver> Registration<T> {
/// Driver's `verify` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn verify_callback(ptr: *mut bindings::cpufreq_policy_data) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn verify_callback(
+ ptr: *mut bindings::cpufreq_policy_data,
+ ) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1152,8 +1184,13 @@ impl<T: Driver> Registration<T> {
/// Driver's `setpolicy` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn setpolicy_callback(ptr: *mut bindings::cpufreq_policy) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn setpolicy_callback(
+ ptr: *mut bindings::cpufreq_policy,
+ ) -> kernel::ffi::c_int {
from_result(|| {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
@@ -1164,8 +1201,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `target` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn target_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn target_callback(
ptr: *mut bindings::cpufreq_policy,
target_freq: u32,
relation: u32,
@@ -1180,8 +1220,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `target_index` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn target_index_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn target_index_callback(
ptr: *mut bindings::cpufreq_policy,
index: u32,
) -> kernel::ffi::c_int {
@@ -1200,8 +1243,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `fast_switch` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn fast_switch_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn fast_switch_callback(
ptr: *mut bindings::cpufreq_policy,
target_freq: u32,
) -> kernel::ffi::c_uint {
@@ -1212,21 +1258,31 @@ impl<T: Driver> Registration<T> {
}
/// Driver's `adjust_perf` callback.
- extern "C" fn adjust_perf_callback(
+ ///
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ unsafe extern "C" fn adjust_perf_callback(
cpu: u32,
min_perf: usize,
target_perf: usize,
capacity: usize,
) {
- if let Ok(mut policy) = PolicyCpu::from_cpu(cpu) {
+ // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+ let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+ if let Ok(mut policy) = PolicyCpu::from_cpu(cpu_id) {
T::adjust_perf(&mut policy, min_perf, target_perf, capacity);
}
}
/// Driver's `get_intermediate` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn get_intermediate_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn get_intermediate_callback(
ptr: *mut bindings::cpufreq_policy,
index: u32,
) -> kernel::ffi::c_uint {
@@ -1243,8 +1299,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `target_intermediate` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn target_intermediate_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn target_intermediate_callback(
ptr: *mut bindings::cpufreq_policy,
index: u32,
) -> kernel::ffi::c_int {
@@ -1262,12 +1321,24 @@ impl<T: Driver> Registration<T> {
}
/// Driver's `get` callback.
- extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
- PolicyCpu::from_cpu(cpu).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
+ ///
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ unsafe extern "C" fn get_callback(cpu: u32) -> kernel::ffi::c_uint {
+ // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+ let cpu_id = unsafe { CpuId::from_u32_unchecked(cpu) };
+
+ PolicyCpu::from_cpu(cpu_id).map_or(0, |mut policy| T::get(&mut policy).map_or(0, |f| f))
}
/// Driver's `update_limit` callback.
- extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
+ ///
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn update_limits_callback(ptr: *mut bindings::cpufreq_policy) {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
let policy = unsafe { Policy::from_raw_mut(ptr) };
@@ -1276,10 +1347,16 @@ impl<T: Driver> Registration<T> {
/// Driver's `bios_limit` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn bios_limit_callback(cpu: i32, limit: *mut u32) -> kernel::ffi::c_int {
+ // SAFETY: The C API guarantees that `cpu` refers to a valid CPU number.
+ let cpu_id = unsafe { CpuId::from_i32_unchecked(cpu) };
+
from_result(|| {
- let mut policy = PolicyCpu::from_cpu(cpu as u32)?;
+ let mut policy = PolicyCpu::from_cpu(cpu_id)?;
// SAFETY: `limit` is guaranteed by the C code to be valid.
T::bios_limit(&mut policy, &mut (unsafe { *limit })).map(|()| 0)
@@ -1288,8 +1365,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `set_boost` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn set_boost_callback(
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn set_boost_callback(
ptr: *mut bindings::cpufreq_policy,
state: i32,
) -> kernel::ffi::c_int {
@@ -1303,8 +1383,11 @@ impl<T: Driver> Registration<T> {
/// Driver's `register_em` callback.
///
- /// SAFETY: Called from C. Inputs must be valid pointers.
- extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
+ /// # Safety
+ ///
+ /// - This function may only be called from the cpufreq C infrastructure.
+ /// - The pointer arguments must be valid pointers.
+ unsafe extern "C" fn register_em_callback(ptr: *mut bindings::cpufreq_policy) {
// SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
// lifetime of `policy`.
let policy = unsafe { Policy::from_raw_mut(ptr) };
diff --git a/rust/kernel/cpumask.rs b/rust/kernel/cpumask.rs
index c90bfac9346a..19c607709b5f 100644
--- a/rust/kernel/cpumask.rs
+++ b/rust/kernel/cpumask.rs
@@ -6,6 +6,7 @@
use crate::{
alloc::{AllocError, Flags},
+ cpu::CpuId,
prelude::*,
types::Opaque,
};
@@ -35,9 +36,10 @@ use core::ops::{Deref, DerefMut};
///
/// ```
/// use kernel::bindings;
+/// use kernel::cpu::CpuId;
/// use kernel::cpumask::Cpumask;
///
-/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: u32, clear_cpu: i32) {
+/// fn set_clear_cpu(ptr: *mut bindings::cpumask, set_cpu: CpuId, clear_cpu: CpuId) {
/// // SAFETY: The `ptr` is valid for writing and remains valid for the lifetime of the
/// // returned reference.
/// let mask = unsafe { Cpumask::as_mut_ref(ptr) };
@@ -90,9 +92,9 @@ impl Cpumask {
/// This mismatches kernel naming convention and corresponds to the C
/// function `__cpumask_set_cpu()`.
#[inline]
- pub fn set(&mut self, cpu: u32) {
+ pub fn set(&mut self, cpu: CpuId) {
// SAFETY: By the type invariant, `self.as_raw` is a valid argument to `__cpumask_set_cpu`.
- unsafe { bindings::__cpumask_set_cpu(cpu, self.as_raw()) };
+ unsafe { bindings::__cpumask_set_cpu(u32::from(cpu), self.as_raw()) };
}
/// Clear `cpu` in the cpumask.
@@ -101,19 +103,19 @@ impl Cpumask {
/// This mismatches kernel naming convention and corresponds to the C
/// function `__cpumask_clear_cpu()`.
#[inline]
- pub fn clear(&mut self, cpu: i32) {
+ pub fn clear(&mut self, cpu: CpuId) {
// SAFETY: By the type invariant, `self.as_raw` is a valid argument to
// `__cpumask_clear_cpu`.
- unsafe { bindings::__cpumask_clear_cpu(cpu, self.as_raw()) };
+ unsafe { bindings::__cpumask_clear_cpu(i32::from(cpu), self.as_raw()) };
}
/// Test `cpu` in the cpumask.
///
/// Equivalent to the kernel's `cpumask_test_cpu` API.
#[inline]
- pub fn test(&self, cpu: i32) -> bool {
+ pub fn test(&self, cpu: CpuId) -> bool {
// SAFETY: By the type invariant, `self.as_raw` is a valid argument to `cpumask_test_cpu`.
- unsafe { bindings::cpumask_test_cpu(cpu, self.as_raw()) }
+ unsafe { bindings::cpumask_test_cpu(i32::from(cpu), self.as_raw()) }
}
/// Set all CPUs in the cpumask.
@@ -178,21 +180,40 @@ impl Cpumask {
/// The following example demonstrates how to create and update a [`CpumaskVar`].
///
/// ```
+/// use kernel::cpu::CpuId;
/// use kernel::cpumask::CpumaskVar;
///
/// let mut mask = CpumaskVar::new_zero(GFP_KERNEL).unwrap();
///
/// assert!(mask.empty());
-/// mask.set(2);
-/// assert!(mask.test(2));
-/// mask.set(3);
-/// assert!(mask.test(3));
-/// assert_eq!(mask.weight(), 2);
+/// let mut count = 0;
+///
+/// let cpu2 = CpuId::from_u32(2);
+/// if let Some(cpu) = cpu2 {
+/// mask.set(cpu);
+/// assert!(mask.test(cpu));
+/// count += 1;
+/// }
+///
+/// let cpu3 = CpuId::from_u32(3);
+/// if let Some(cpu) = cpu3 {
+/// mask.set(cpu);
+/// assert!(mask.test(cpu));
+/// count += 1;
+/// }
+///
+/// assert_eq!(mask.weight(), count);
///
/// let mask2 = CpumaskVar::try_clone(&mask).unwrap();
-/// assert!(mask2.test(2));
-/// assert!(mask2.test(3));
-/// assert_eq!(mask2.weight(), 2);
+///
+/// if let Some(cpu) = cpu2 {
+/// assert!(mask2.test(cpu));
+/// }
+///
+/// if let Some(cpu) = cpu3 {
+/// assert!(mask2.test(cpu));
+/// }
+/// assert_eq!(mask2.weight(), count);
/// ```
pub struct CpumaskVar {
#[cfg(CONFIG_CPUMASK_OFFSTACK)]
diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs
index 0f79a2ec9474..57502534d985 100644
--- a/rust/kernel/devres.rs
+++ b/rust/kernel/devres.rs
@@ -12,26 +12,28 @@ use crate::{
error::{Error, Result},
ffi::c_void,
prelude::*,
- revocable::Revocable,
- sync::Arc,
+ revocable::{Revocable, RevocableGuard},
+ sync::{rcu, Arc, Completion},
types::ARef,
};
-use core::ops::Deref;
-
#[pin_data]
struct DevresInner<T> {
dev: ARef<Device>,
callback: unsafe extern "C" fn(*mut c_void),
#[pin]
data: Revocable<T>,
+ #[pin]
+ revoke: Completion,
}
/// This abstraction is meant to be used by subsystems to containerize [`Device`] bound resources to
/// manage their lifetime.
///
/// [`Device`] bound resources should be freed when either the resource goes out of scope or the
-/// [`Device`] is unbound respectively, depending on what happens first.
+/// [`Device`] is unbound respectively, depending on what happens first. In any case, it is always
+/// guaranteed that revoking the device resource is completed before the corresponding [`Device`]
+/// is unbound.
///
/// To achieve that [`Devres`] registers a devres callback on creation, which is called once the
/// [`Device`] is unbound, revoking access to the encapsulated resource (see also [`Revocable`]).
@@ -102,6 +104,7 @@ impl<T> DevresInner<T> {
dev: dev.into(),
callback: Self::devres_callback,
data <- Revocable::new(data),
+ revoke <- Completion::new(),
}),
flags,
)?;
@@ -130,26 +133,28 @@ impl<T> DevresInner<T> {
self as _
}
- fn remove_action(this: &Arc<Self>) {
+ fn remove_action(this: &Arc<Self>) -> bool {
// SAFETY:
// - `self.inner.dev` is a valid `Device`,
// - the `action` and `data` pointers are the exact same ones as given to devm_add_action()
// previously,
// - `self` is always valid, even if the action has been released already.
- let ret = unsafe {
+ let success = unsafe {
bindings::devm_remove_action_nowarn(
this.dev.as_raw(),
Some(this.callback),
this.as_ptr() as _,
)
- };
+ } == 0;
- if ret == 0 {
+ if success {
// SAFETY: We leaked an `Arc` reference to devm_add_action() in `DevresInner::new`; if
// devm_remove_action_nowarn() was successful we can (and have to) claim back ownership
// of this reference.
let _ = unsafe { Arc::from_raw(this.as_ptr()) };
}
+
+ success
}
#[allow(clippy::missing_safety_doc)]
@@ -161,7 +166,12 @@ impl<T> DevresInner<T> {
// `DevresInner::new`.
let inner = unsafe { Arc::from_raw(ptr) };
- inner.data.revoke();
+ if !inner.data.revoke() {
+ // If `revoke()` returns false, it means that `Devres::drop` already started revoking
+ // `inner.data` for us. Hence we have to wait until `Devres::drop()` signals that it
+ // completed revoking `inner.data`.
+ inner.revoke.wait_for_completion();
+ }
}
}
@@ -218,20 +228,36 @@ impl<T> Devres<T> {
// SAFETY: `dev` being the same device as the device this `Devres` has been created for
// proves that `self.0.data` hasn't been revoked and is guaranteed to not be revoked as
// long as `dev` lives; `dev` lives at least as long as `self`.
- Ok(unsafe { self.deref().access() })
+ Ok(unsafe { self.0.data.access() })
}
-}
-impl<T> Deref for Devres<T> {
- type Target = Revocable<T>;
+ /// [`Devres`] accessor for [`Revocable::try_access`].
+ pub fn try_access(&self) -> Option<RevocableGuard<'_, T>> {
+ self.0.data.try_access()
+ }
+
+ /// [`Devres`] accessor for [`Revocable::try_access_with`].
+ pub fn try_access_with<R, F: FnOnce(&T) -> R>(&self, f: F) -> Option<R> {
+ self.0.data.try_access_with(f)
+ }
- fn deref(&self) -> &Self::Target {
- &self.0.data
+ /// [`Devres`] accessor for [`Revocable::try_access_with_guard`].
+ pub fn try_access_with_guard<'a>(&'a self, guard: &'a rcu::Guard) -> Option<&'a T> {
+ self.0.data.try_access_with_guard(guard)
}
}
impl<T> Drop for Devres<T> {
fn drop(&mut self) {
- DevresInner::remove_action(&self.0);
+ // SAFETY: When `drop` runs, it is guaranteed that nobody is accessing the revocable data
+ // anymore, hence it is safe not to wait for the grace period to finish.
+ if unsafe { self.0.data.revoke_nosync() } {
+ // We revoked `self.0.data` before the devres action did, hence try to remove it.
+ if !DevresInner::remove_action(&self.0) {
+ // We could not remove the devres action, which means that it now runs concurrently,
+ // hence signal that `self.0.data` has been revoked successfully.
+ self.0.revoke.complete_all();
+ }
+ }
}
}
diff --git a/rust/kernel/revocable.rs b/rust/kernel/revocable.rs
index db4aa46bb121..06a3cdfce344 100644
--- a/rust/kernel/revocable.rs
+++ b/rust/kernel/revocable.rs
@@ -154,8 +154,10 @@ impl<T> Revocable<T> {
/// # Safety
///
/// Callers must ensure that there are no more concurrent users of the revocable object.
- unsafe fn revoke_internal<const SYNC: bool>(&self) {
- if self.is_available.swap(false, Ordering::Relaxed) {
+ unsafe fn revoke_internal<const SYNC: bool>(&self) -> bool {
+ let revoke = self.is_available.swap(false, Ordering::Relaxed);
+
+ if revoke {
if SYNC {
// SAFETY: Just an FFI call, there are no further requirements.
unsafe { bindings::synchronize_rcu() };
@@ -165,6 +167,8 @@ impl<T> Revocable<T> {
// `compare_exchange` above that takes `is_available` from `true` to `false`.
unsafe { drop_in_place(self.data.get()) };
}
+
+ revoke
}
/// Revokes access to and drops the wrapped object.
@@ -172,10 +176,13 @@ impl<T> Revocable<T> {
/// Access to the object is revoked immediately to new callers of [`Revocable::try_access`],
/// expecting that there are no concurrent users of the object.
///
+ /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+ /// already.
+ ///
/// # Safety
///
/// Callers must ensure that there are no more concurrent users of the revocable object.
- pub unsafe fn revoke_nosync(&self) {
+ pub unsafe fn revoke_nosync(&self) -> bool {
// SAFETY: By the safety requirement of this function, the caller ensures that nobody is
// accessing the data anymore and hence we don't have to wait for the grace period to
// finish.
@@ -189,7 +196,10 @@ impl<T> Revocable<T> {
/// If there are concurrent users of the object (i.e., ones that called
/// [`Revocable::try_access`] beforehand and still haven't dropped the returned guard), this
/// function waits for the concurrent access to complete before dropping the wrapped object.
- pub fn revoke(&self) {
+ ///
+ /// Returns `true` if `&self` has been revoked with this call, `false` if it was revoked
+ /// already.
+ pub fn revoke(&self) -> bool {
// SAFETY: By passing `true` we ask `revoke_internal` to wait for the grace period to
// finish.
unsafe { self.revoke_internal::<true>() }
diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 36a719015583..c23a12639924 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -10,6 +10,7 @@ use crate::types::Opaque;
use pin_init;
mod arc;
+pub mod completion;
mod condvar;
pub mod lock;
mod locked_by;
@@ -17,6 +18,7 @@ pub mod poll;
pub mod rcu;
pub use arc::{Arc, ArcBorrow, UniqueArc};
+pub use completion::Completion;
pub use condvar::{new_condvar, CondVar, CondVarTimeoutResult};
pub use lock::global::{global_lock, GlobalGuard, GlobalLock, GlobalLockBackend, GlobalLockedBy};
pub use lock::mutex::{new_mutex, Mutex, MutexGuard};
diff --git a/rust/kernel/sync/completion.rs b/rust/kernel/sync/completion.rs
new file mode 100644
index 000000000000..c50012a940a3
--- /dev/null
+++ b/rust/kernel/sync/completion.rs
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Completion support.
+//!
+//! Reference: <https://docs.kernel.org/scheduler/completion.html>
+//!
+//! C header: [`include/linux/completion.h`](srctree/include/linux/completion.h)
+
+use crate::{bindings, prelude::*, types::Opaque};
+
+/// Synchronization primitive to signal when a certain task has been completed.
+///
+/// The [`Completion`] synchronization primitive signals when a certain task has been completed by
+/// waking up other tasks that have been queued up to wait for the [`Completion`] to be completed.
+///
+/// # Examples
+///
+/// ```
+/// use kernel::sync::{Arc, Completion};
+/// use kernel::workqueue::{self, impl_has_work, new_work, Work, WorkItem};
+///
+/// #[pin_data]
+/// struct MyTask {
+/// #[pin]
+/// work: Work<MyTask>,
+/// #[pin]
+/// done: Completion,
+/// }
+///
+/// impl_has_work! {
+/// impl HasWork<Self> for MyTask { self.work }
+/// }
+///
+/// impl MyTask {
+/// fn new() -> Result<Arc<Self>> {
+/// let this = Arc::pin_init(pin_init!(MyTask {
+/// work <- new_work!("MyTask::work"),
+/// done <- Completion::new(),
+/// }), GFP_KERNEL)?;
+///
+/// let _ = workqueue::system().enqueue(this.clone());
+///
+/// Ok(this)
+/// }
+///
+/// fn wait_for_completion(&self) {
+/// self.done.wait_for_completion();
+///
+/// pr_info!("Completion: task complete\n");
+/// }
+/// }
+///
+/// impl WorkItem for MyTask {
+/// type Pointer = Arc<MyTask>;
+///
+/// fn run(this: Arc<MyTask>) {
+/// // process this task
+/// this.done.complete_all();
+/// }
+/// }
+///
+/// let task = MyTask::new()?;
+/// task.wait_for_completion();
+/// # Ok::<(), Error>(())
+/// ```
+#[pin_data]
+pub struct Completion {
+ #[pin]
+ inner: Opaque<bindings::completion>,
+}
+
+// SAFETY: `Completion` is safe to be send to any task.
+unsafe impl Send for Completion {}
+
+// SAFETY: `Completion` is safe to be accessed concurrently.
+unsafe impl Sync for Completion {}
+
+impl Completion {
+ /// Create an initializer for a new [`Completion`].
+ pub fn new() -> impl PinInit<Self> {
+ pin_init!(Self {
+ inner <- Opaque::ffi_init(|slot: *mut bindings::completion| {
+ // SAFETY: `slot` is a valid pointer to an uninitialized `struct completion`.
+ unsafe { bindings::init_completion(slot) };
+ }),
+ })
+ }
+
+ fn as_raw(&self) -> *mut bindings::completion {
+ self.inner.get()
+ }
+
+ /// Signal all tasks waiting on this completion.
+ ///
+ /// This method wakes up all tasks waiting on this completion; after this operation the
+ /// completion is permanently done, i.e. signals all current and future waiters.
+ pub fn complete_all(&self) {
+ // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+ unsafe { bindings::complete_all(self.as_raw()) };
+ }
+
+ /// Wait for completion of a task.
+ ///
+ /// This method waits for the completion of a task; it is not interruptible and there is no
+ /// timeout.
+ ///
+ /// See also [`Completion::complete_all`].
+ pub fn wait_for_completion(&self) {
+ // SAFETY: `self.as_raw()` is a pointer to a valid `struct completion`.
+ unsafe { bindings::wait_for_completion(self.as_raw()) };
+ }
+}
diff --git a/rust/kernel/time/hrtimer.rs b/rust/kernel/time/hrtimer.rs
index 9df3dcd2fa39..36e1290cd079 100644
--- a/rust/kernel/time/hrtimer.rs
+++ b/rust/kernel/time/hrtimer.rs
@@ -517,7 +517,7 @@ macro_rules! impl_has_hr_timer {
) -> *mut Self {
// SAFETY: As per the safety requirement of this function, `ptr`
// is pointing inside a `$timer_type`.
- unsafe { ::kernel::container_of!(ptr, $timer_type, $field).cast_mut() }
+ unsafe { ::kernel::container_of!(ptr, $timer_type, $field) }
}
}
}
diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h
index 7dd03ffe0c5c..d9c06d2cb1df 100644
--- a/scripts/gendwarfksyms/gendwarfksyms.h
+++ b/scripts/gendwarfksyms/gendwarfksyms.h
@@ -216,24 +216,14 @@ int cache_get(struct cache *cache, unsigned long key);
void cache_init(struct cache *cache);
void cache_free(struct cache *cache);
-static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr)
-{
- cache_set(cache, addr, 1);
-}
-
-static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr)
-{
- return cache_get(cache, addr) == 1;
-}
-
static inline void cache_mark_expanded(struct cache *cache, void *addr)
{
- __cache_mark_expanded(cache, (uintptr_t)addr);
+ cache_set(cache, (unsigned long)addr, 1);
}
static inline bool cache_was_expanded(struct cache *cache, void *addr)
{
- return __cache_was_expanded(cache, (uintptr_t)addr);
+ return cache_get(cache, (unsigned long)addr) == 1;
}
/*
diff --git a/scripts/gendwarfksyms/types.c b/scripts/gendwarfksyms/types.c
index 39ce1770e463..7bd459ea6c59 100644
--- a/scripts/gendwarfksyms/types.c
+++ b/scripts/gendwarfksyms/types.c
@@ -333,37 +333,11 @@ static void calculate_version(struct version *version,
cache_free(&expansion_cache);
}
-static void __type_expand(struct die *cache, struct type_expansion *type,
- bool recursive);
-
-static void type_expand_child(struct die *cache, struct type_expansion *type,
- bool recursive)
-{
- struct type_expansion child;
- char *name;
-
- name = get_type_name(cache);
- if (!name) {
- __type_expand(cache, type, recursive);
- return;
- }
-
- if (recursive && !__cache_was_expanded(&expansion_cache, cache->addr)) {
- __cache_mark_expanded(&expansion_cache, cache->addr);
- type_expansion_init(&child);
- __type_expand(cache, &child, true);
- type_map_add(name, &child);
- type_expansion_free(&child);
- }
-
- type_expansion_append(type, name, name);
-}
-
-static void __type_expand(struct die *cache, struct type_expansion *type,
- bool recursive)
+static void __type_expand(struct die *cache, struct type_expansion *type)
{
struct die_fragment *df;
struct die *child;
+ char *name;
list_for_each_entry(df, &cache->fragments, list) {
switch (df->type) {
@@ -379,7 +353,12 @@ static void __type_expand(struct die *cache, struct type_expansion *type,
error("unknown child: %" PRIxPTR,
df->data.addr);
- type_expand_child(child, type, recursive);
+ name = get_type_name(child);
+ if (name)
+ type_expansion_append(type, name, name);
+ else
+ __type_expand(child, type);
+
break;
case FRAGMENT_LINEBREAK:
/*
@@ -397,12 +376,17 @@ static void __type_expand(struct die *cache, struct type_expansion *type,
}
}
-static void type_expand(struct die *cache, struct type_expansion *type,
- bool recursive)
+static void type_expand(const char *name, struct die *cache,
+ struct type_expansion *type)
{
+ const char *override;
+
type_expansion_init(type);
- __type_expand(cache, type, recursive);
- cache_free(&expansion_cache);
+
+ if (stable && kabi_get_type_string(name, &override))
+ type_parse(name, override, type);
+ else
+ __type_expand(cache, type);
}
static void type_parse(const char *name, const char *str,
@@ -416,8 +400,6 @@ static void type_parse(const char *name, const char *str,
if (!*str)
error("empty type string override for '%s'", name);
- type_expansion_init(type);
-
for (pos = 0; str[pos]; ++pos) {
bool empty;
char marker = ' ';
@@ -478,7 +460,6 @@ static void type_parse(const char *name, const char *str,
static void expand_type(struct die *cache, void *arg)
{
struct type_expansion type;
- const char *override;
char *name;
if (cache->mapped)
@@ -504,11 +485,7 @@ static void expand_type(struct die *cache, void *arg)
debug("%s", name);
- if (stable && kabi_get_type_string(name, &override))
- type_parse(name, override, &type);
- else
- type_expand(cache, &type, true);
-
+ type_expand(name, cache, &type);
type_map_add(name, &type);
type_expansion_free(&type);
free(name);
@@ -518,7 +495,6 @@ static void expand_symbol(struct symbol *sym, void *arg)
{
struct type_expansion type;
struct version version;
- const char *override;
struct die *cache;
/*
@@ -532,10 +508,7 @@ static void expand_symbol(struct symbol *sym, void *arg)
if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache))
return; /* We'll warn about missing CRCs later. */
- if (stable && kabi_get_type_string(sym->name, &override))
- type_parse(sym->name, override, &type);
- else
- type_expand(cache, &type, false);
+ type_expand(sym->name, cache, &type);
/* If the symbol already has a version, don't calculate it again. */
if (sym->state != SYMBOL_PROCESSED) {
diff --git a/scripts/misc-check b/scripts/misc-check
index a74450e799d1..84f08da17b2c 100755
--- a/scripts/misc-check
+++ b/scripts/misc-check
@@ -62,6 +62,15 @@ check_unnecessary_include_linux_export_h () {
xargs -r printf "%s: warning: EXPORT_SYMBOL() is not used, but #include <linux/export.h> is present\n" >&2
}
-check_tracked_ignored_files
-check_missing_include_linux_export_h
-check_unnecessary_include_linux_export_h
+case "${KBUILD_EXTRA_WARN}" in
+*1*)
+ check_tracked_ignored_files
+ ;;
+esac
+
+case "${KBUILD_EXTRA_WARN}" in
+*2*)
+ check_missing_include_linux_export_h
+ check_unnecessary_include_linux_export_h
+ ;;
+esac
diff --git a/security/keys/gc.c b/security/keys/gc.c
index f27223ea4578..748e83818a76 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -218,8 +218,8 @@ continue_scanning:
key = rb_entry(cursor, struct key, serial_node);
cursor = rb_next(cursor);
- if (test_bit(KEY_FLAG_FINAL_PUT, &key->flags)) {
- smp_mb(); /* Clobber key->user after FINAL_PUT seen. */
+ if (!test_bit_acquire(KEY_FLAG_USER_ALIVE, &key->flags)) {
+ /* Clobber key->user after final put seen. */
goto found_unreferenced_key;
}
diff --git a/security/keys/key.c b/security/keys/key.c
index 7198cd2ac3a3..3bbdde778631 100644
--- a/security/keys/key.c
+++ b/security/keys/key.c
@@ -298,6 +298,7 @@ struct key *key_alloc(struct key_type *type, const char *desc,
key->restrict_link = restrict_link;
key->last_used_at = ktime_get_real_seconds();
+ key->flags |= 1 << KEY_FLAG_USER_ALIVE;
if (!(flags & KEY_ALLOC_NOT_IN_QUOTA))
key->flags |= 1 << KEY_FLAG_IN_QUOTA;
if (flags & KEY_ALLOC_BUILT_IN)
@@ -658,8 +659,8 @@ void key_put(struct key *key)
key->user->qnbytes -= key->quotalen;
spin_unlock_irqrestore(&key->user->lock, flags);
}
- smp_mb(); /* key->user before FINAL_PUT set. */
- set_bit(KEY_FLAG_FINAL_PUT, &key->flags);
+ /* Mark key as safe for GC after key->user done. */
+ clear_bit_unlock(KEY_FLAG_USER_ALIVE, &key->flags);
schedule_work(&key_gc_work);
}
}
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 7becf3808818..d185754c2786 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1909,11 +1909,17 @@ retry:
goto out_unlock;
}
/* Obtain the sid for the context. */
- rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
- if (rc == -ESTALE) {
- rcu_read_unlock();
- context_destroy(&newcontext);
- goto retry;
+ if (context_equal(scontext, &newcontext))
+ *out_sid = ssid;
+ else if (context_equal(tcontext, &newcontext))
+ *out_sid = tsid;
+ else {
+ rc = sidtab_context_to_sid(sidtab, &newcontext, out_sid);
+ if (rc == -ESTALE) {
+ rcu_read_unlock();
+ context_destroy(&newcontext);
+ goto retry;
+ }
}
out_unlock:
rcu_read_unlock();
diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c
index 90ec4ef1b082..61d56b0c2be1 100644
--- a/security/selinux/xfrm.c
+++ b/security/selinux/xfrm.c
@@ -94,7 +94,7 @@ static int selinux_xfrm_alloc_user(struct xfrm_sec_ctx **ctxp,
ctx->ctx_doi = XFRM_SC_DOI_LSM;
ctx->ctx_alg = XFRM_SC_ALG_SELINUX;
- ctx->ctx_len = str_len;
+ ctx->ctx_len = str_len + 1;
memcpy(ctx->ctx_str, &uctx[1], str_len);
ctx->ctx_str[str_len] = '\0';
rc = security_context_to_sid(ctx->ctx_str, str_len,
diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 74db11525003..5a083eecaa6b 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -703,6 +703,9 @@ static int snd_sb16_dma_control_put(struct snd_kcontrol *kcontrol, struct snd_ct
unsigned char nval, oval;
int change;
+ if (chip->mode & (SB_MODE_PLAYBACK | SB_MODE_CAPTURE))
+ return -EBUSY;
+
nval = ucontrol->value.enumerated.item[0];
if (nval > 2)
return -EINVAL;
@@ -711,6 +714,10 @@ static int snd_sb16_dma_control_put(struct snd_kcontrol *kcontrol, struct snd_ct
change = nval != oval;
snd_sb16_set_dma_mode(chip, nval);
spin_unlock_irqrestore(&chip->reg_lock, flags);
+ if (change) {
+ snd_dma_disable(chip->dma8);
+ snd_dma_disable(chip->dma16);
+ }
return change;
}
diff --git a/sound/pci/ctxfi/xfi.c b/sound/pci/ctxfi/xfi.c
index 713d36ea40cb..d8dd84d41c87 100644
--- a/sound/pci/ctxfi/xfi.c
+++ b/sound/pci/ctxfi/xfi.c
@@ -98,8 +98,8 @@ ct_card_probe(struct pci_dev *pci, const struct pci_device_id *pci_id)
if (err < 0)
goto error;
- strcpy(card->driver, "SB-XFi");
- strcpy(card->shortname, "Creative X-Fi");
+ strscpy(card->driver, "SB-XFi");
+ strscpy(card->shortname, "Creative X-Fi");
snprintf(card->longname, sizeof(card->longname), "%s %s %s",
card->shortname, atc->chip_name, atc->model_name);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index e5210ed48ddf..439cf1bda6e6 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2283,6 +2283,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
/* Dell ALC3271 */
SND_PCI_QUIRK(0x1028, 0x0962, "Dell ALC3271", 0),
+ /* https://bugzilla.kernel.org/show_bug.cgi?id=220210 */
+ SND_PCI_QUIRK(0x17aa, 0x5079, "Lenovo Thinkpad E15", 0),
{}
};
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index cd0d7ba7320e..2e1618494c20 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8030,6 +8030,9 @@ enum {
ALC294_FIXUP_ASUS_CS35L41_SPI_2,
ALC274_FIXUP_HP_AIO_BIND_DACS,
ALC287_FIXUP_PREDATOR_SPK_CS35L41_I2C_2,
+ ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC,
+ ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1,
+ ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC,
};
/* A special fixup for Lenovo C940 and Yoga Duet 7;
@@ -10414,6 +10417,26 @@ static const struct hda_fixup alc269_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = alc274_fixup_hp_aio_bind_dacs,
},
+ [ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x19, 0x03a11050 },
+ { 0x1b, 0x03a11c30 },
+ { }
+ },
+ .chained = true,
+ .chain_id = ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1
+ },
+ [ALC285_FIXUP_ASUS_GA605K_I2C_SPEAKER2_TO_DAC1] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc285_fixup_speaker2_to_dac1,
+ },
+ [ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc269_fixup_limit_int_mic_boost,
+ .chained = true,
+ .chain_id = ALC269VC_FIXUP_ACER_MIC_NO_PRESENCE,
+ },
};
static const struct hda_quirk alc269_fixup_tbl[] = {
@@ -10509,6 +10532,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC),
SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB),
+ SND_PCI_QUIRK(0x1028, 0x0879, "Dell Latitude 5420 Rugged", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),
@@ -10787,6 +10811,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8b97, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8bb3, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8bb4, "HP Slim OMEN", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8bc8, "HP Victus 15-fa1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
SND_PCI_QUIRK(0x103c, 0x8bcd, "HP Omen 16-xd0xxx", ALC245_FIXUP_HP_MUTE_LED_V1_COEFBIT),
SND_PCI_QUIRK(0x103c, 0x8bdd, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8bde, "HP Envy 17", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10840,6 +10865,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8c91, "HP EliteBook 660", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8c96, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
SND_PCI_QUIRK(0x103c, 0x8c97, "HP ZBook", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+ SND_PCI_QUIRK(0x103c, 0x8c9c, "HP Victus 16-s1xxx (MB 8C9C)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
SND_PCI_QUIRK(0x103c, 0x8ca1, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
@@ -10904,6 +10930,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x103c, 0x8e60, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e61, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
SND_PCI_QUIRK(0x103c, 0x8e62, "HP Trekker ", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x1043, 0x1032, "ASUS VivoBook X513EA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x1034, "ASUS GU605C", ALC285_FIXUP_ASUS_GU605_SPI_SPEAKER2_TO_DAC1),
SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
@@ -10932,6 +10960,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1043, 0x1314, "ASUS GA605K", ALC285_FIXUP_ASUS_GA605K_HEADSET_MIC),
SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
@@ -11384,6 +11413,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x2782, 0x0214, "VAIO VJFE-CL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
SND_PCI_QUIRK(0x2782, 0x0228, "Infinix ZERO BOOK 13", ALC269VB_FIXUP_INFINIX_ZERO_BOOK_13),
SND_PCI_QUIRK(0x2782, 0x0232, "CHUWI CoreBook XPro", ALC269VB_FIXUP_CHUWI_COREBOOK_XPRO),
+ SND_PCI_QUIRK(0x2782, 0x1407, "Positivo P15X", ALC269_FIXUP_POSITIVO_P15X_HEADSET_MIC),
SND_PCI_QUIRK(0x2782, 0x1701, "Infinix Y4 Max", ALC269VC_FIXUP_INFINIX_Y4_MAX),
SND_PCI_QUIRK(0x2782, 0x1705, "MEDION E15433", ALC269VC_FIXUP_INFINIX_Y4_MAX),
SND_PCI_QUIRK(0x2782, 0x1707, "Vaio VJFE-ADL", ALC298_FIXUP_SPK_VOLUME),
diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index 7e62445e02c1..98022e5fd428 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -454,6 +454,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
{
.driver_data = &acp6x_card,
.matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 17 D7VF"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "Alienware"),
DMI_MATCH(DMI_PRODUCT_NAME, "Alienware m17 R5 AMD"),
}
@@ -518,6 +525,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
.driver_data = &acp6x_card,
.matches = {
DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
+ DMI_MATCH(DMI_PRODUCT_NAME, "Victus by HP Gaming Laptop 15-fb2xxx"),
+ }
+ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
DMI_MATCH(DMI_BOARD_NAME, "8A42"),
}
},
diff --git a/sound/soc/apple/Kconfig b/sound/soc/apple/Kconfig
index 793f7782e0d7..e9c777cdb6e3 100644
--- a/sound/soc/apple/Kconfig
+++ b/sound/soc/apple/Kconfig
@@ -2,7 +2,6 @@ config SND_SOC_APPLE_MCA
tristate "Apple Silicon MCA driver"
depends on ARCH_APPLE || COMPILE_TEST
select SND_DMAENGINE_PCM
- default ARCH_APPLE
help
This option enables an ASoC platform driver for MCA peripherals found
on Apple Silicon SoCs.
diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
index 13f602f51bf3..fa9693af3722 100644
--- a/sound/soc/codecs/cs35l56-sdw.c
+++ b/sound/soc/codecs/cs35l56-sdw.c
@@ -238,16 +238,15 @@ static const struct regmap_bus cs35l56_regmap_bus_sdw = {
.val_format_endian_default = REGMAP_ENDIAN_BIG,
};
-static int cs35l56_sdw_set_cal_index(struct cs35l56_private *cs35l56)
+static int cs35l56_sdw_get_unique_id(struct cs35l56_private *cs35l56)
{
int ret;
- /* SoundWire UniqueId is used to index the calibration array */
ret = sdw_read_no_pm(cs35l56->sdw_peripheral, SDW_SCP_DEVID_0);
if (ret < 0)
return ret;
- cs35l56->base.cal_index = ret & 0xf;
+ cs35l56->sdw_unique_id = ret & 0xf;
return 0;
}
@@ -259,11 +258,13 @@ static void cs35l56_sdw_init(struct sdw_slave *peripheral)
pm_runtime_get_noresume(cs35l56->base.dev);
- if (cs35l56->base.cal_index < 0) {
- ret = cs35l56_sdw_set_cal_index(cs35l56);
- if (ret < 0)
- goto out;
- }
+ ret = cs35l56_sdw_get_unique_id(cs35l56);
+ if (ret)
+ goto out;
+
+ /* SoundWire UniqueId is used to index the calibration array */
+ if (cs35l56->base.cal_index < 0)
+ cs35l56->base.cal_index = cs35l56->sdw_unique_id;
ret = cs35l56_init(cs35l56);
if (ret < 0) {
@@ -587,6 +588,7 @@ static int cs35l56_sdw_probe(struct sdw_slave *peripheral, const struct sdw_devi
cs35l56->base.dev = dev;
cs35l56->sdw_peripheral = peripheral;
+ cs35l56->sdw_link_num = peripheral->bus->link_id;
INIT_WORK(&cs35l56->sdw_irq_work, cs35l56_sdw_irq_work);
dev_set_drvdata(dev, cs35l56);
diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
index c78e4746e428..1b42586794ad 100644
--- a/sound/soc/codecs/cs35l56.c
+++ b/sound/soc/codecs/cs35l56.c
@@ -706,17 +706,41 @@ static int cs35l56_write_cal(struct cs35l56_private *cs35l56)
return ret;
}
-static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
+static int cs35l56_dsp_download_and_power_up(struct cs35l56_private *cs35l56,
+ bool load_firmware)
{
int ret;
- /* Use wm_adsp to load and apply the firmware patch and coefficient files */
- ret = wm_adsp_power_up(&cs35l56->dsp, true);
+ /*
+ * Abort the first load if it didn't find the suffixed bins and
+ * we have an alternate fallback suffix.
+ */
+ cs35l56->dsp.bin_mandatory = (load_firmware && cs35l56->fallback_fw_suffix);
+
+ ret = wm_adsp_power_up(&cs35l56->dsp, load_firmware);
+ if ((ret == -ENOENT) && cs35l56->dsp.bin_mandatory) {
+ cs35l56->dsp.fwf_suffix = cs35l56->fallback_fw_suffix;
+ cs35l56->fallback_fw_suffix = NULL;
+ cs35l56->dsp.bin_mandatory = false;
+ ret = wm_adsp_power_up(&cs35l56->dsp, load_firmware);
+ }
+
if (ret) {
- dev_dbg(cs35l56->base.dev, "%s: wm_adsp_power_up ret %d\n", __func__, ret);
- return;
+ dev_dbg(cs35l56->base.dev, "wm_adsp_power_up ret %d\n", ret);
+ return ret;
}
+ return 0;
+}
+
+static void cs35l56_reinit_patch(struct cs35l56_private *cs35l56)
+{
+ int ret;
+
+ ret = cs35l56_dsp_download_and_power_up(cs35l56, true);
+ if (ret)
+ return;
+
cs35l56_write_cal(cs35l56);
/* Always REINIT after applying patch or coefficients */
@@ -750,11 +774,9 @@ static void cs35l56_patch(struct cs35l56_private *cs35l56, bool firmware_missing
* but only if firmware is missing. If firmware is already patched just
* power-up wm_adsp without downloading firmware.
*/
- ret = wm_adsp_power_up(&cs35l56->dsp, !!firmware_missing);
- if (ret) {
- dev_dbg(cs35l56->base.dev, "%s: wm_adsp_power_up ret %d\n", __func__, ret);
+ ret = cs35l56_dsp_download_and_power_up(cs35l56, firmware_missing);
+ if (ret)
goto err;
- }
mutex_lock(&cs35l56->base.irq_lock);
@@ -853,6 +875,34 @@ err:
pm_runtime_put_autosuspend(cs35l56->base.dev);
}
+static int cs35l56_set_fw_suffix(struct cs35l56_private *cs35l56)
+{
+ if (cs35l56->dsp.fwf_suffix)
+ return 0;
+
+ if (!cs35l56->sdw_peripheral)
+ return 0;
+
+ cs35l56->dsp.fwf_suffix = devm_kasprintf(cs35l56->base.dev, GFP_KERNEL,
+ "l%uu%u",
+ cs35l56->sdw_link_num,
+ cs35l56->sdw_unique_id);
+ if (!cs35l56->dsp.fwf_suffix)
+ return -ENOMEM;
+
+ /*
+ * There are published firmware files for L56 B0 silicon using
+ * the ALSA prefix as the filename suffix. Default to trying these
+ * first, with the new name as an alternate.
+ */
+ if ((cs35l56->base.type == 0x56) && (cs35l56->base.rev == 0xb0)) {
+ cs35l56->fallback_fw_suffix = cs35l56->dsp.fwf_suffix;
+ cs35l56->dsp.fwf_suffix = cs35l56->component->name_prefix;
+ }
+
+ return 0;
+}
+
static int cs35l56_component_probe(struct snd_soc_component *component)
{
struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
@@ -892,6 +942,10 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
return -ENOMEM;
cs35l56->component = component;
+ ret = cs35l56_set_fw_suffix(cs35l56);
+ if (ret)
+ return ret;
+
wm_adsp2_component_probe(&cs35l56->dsp, component);
debugfs_create_bool("init_done", 0444, debugfs_root, &cs35l56->base.init_done);
diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
index 200f695efca3..bd77a57249d7 100644
--- a/sound/soc/codecs/cs35l56.h
+++ b/sound/soc/codecs/cs35l56.h
@@ -38,6 +38,7 @@ struct cs35l56_private {
struct snd_soc_component *component;
struct regulator_bulk_data supplies[CS35L56_NUM_BULK_SUPPLIES];
struct sdw_slave *sdw_peripheral;
+ const char *fallback_fw_suffix;
struct work_struct sdw_irq_work;
bool sdw_irq_no_unmask;
bool soft_resetting;
@@ -52,6 +53,8 @@ struct cs35l56_private {
bool tdm_mode;
bool sysclk_set;
u8 old_sdw_clock_scale;
+ u8 sdw_link_num;
+ u8 sdw_unique_id;
};
extern const struct dev_pm_ops cs35l56_pm_ops_i2c_spi;
diff --git a/sound/soc/codecs/cs48l32.c b/sound/soc/codecs/cs48l32.c
index 90a795230d27..9bdd48aab42a 100644
--- a/sound/soc/codecs/cs48l32.c
+++ b/sound/soc/codecs/cs48l32.c
@@ -2162,6 +2162,10 @@ static int cs48l32_hw_params(struct snd_pcm_substream *substream,
n_slots_multiple = 1;
sclk_target = snd_soc_tdm_params_to_bclk(params, slotw, n_slots, n_slots_multiple);
+ if (sclk_target < 0) {
+ cs48l32_asp_err(dai, "Invalid parameters\n");
+ return sclk_target;
+ }
for (i = 0; i < ARRAY_SIZE(cs48l32_sclk_rates); i++) {
if ((cs48l32_sclk_rates[i].freq >= sclk_target) &&
diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
index 066d92b54312..78c4e68f6002 100644
--- a/sound/soc/codecs/es8326.c
+++ b/sound/soc/codecs/es8326.c
@@ -1079,8 +1079,7 @@ static void es8326_init(struct snd_soc_component *component)
regmap_update_bits(es8326->regmap, ES8326_HPDET_TYPE, 0x03, 0x00);
regmap_write(es8326->regmap, ES8326_INTOUT_IO,
es8326->interrupt_clk);
- regmap_write(es8326->regmap, ES8326_SDINOUT1_IO,
- (ES8326_IO_DMIC_CLK << ES8326_SDINOUT1_SHIFT));
+ regmap_write(es8326->regmap, ES8326_SDINOUT1_IO, ES8326_IO_INPUT);
regmap_write(es8326->regmap, ES8326_SDINOUT23_IO, ES8326_IO_INPUT);
regmap_write(es8326->regmap, ES8326_ANA_PDN, 0x00);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 3c580faab3b7..8a1d5cc75d6c 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -783,16 +783,19 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
char **coeff_filename)
{
const char *system_name = dsp->system_name;
- const char *asoc_component_prefix = dsp->component->name_prefix;
+ const char *suffix = dsp->component->name_prefix;
int ret = 0;
- if (system_name && asoc_component_prefix) {
+ if (dsp->fwf_suffix)
+ suffix = dsp->fwf_suffix;
+
+ if (system_name && suffix) {
if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
cirrus_dir, system_name,
- asoc_component_prefix, "wmfw")) {
+ suffix, "wmfw")) {
wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
cirrus_dir, system_name,
- asoc_component_prefix, "bin");
+ suffix, "bin");
return 0;
}
}
@@ -801,10 +804,10 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
if (!wm_adsp_request_firmware_file(dsp, wmfw_firmware, wmfw_filename,
cirrus_dir, system_name,
NULL, "wmfw")) {
- if (asoc_component_prefix)
+ if (suffix)
wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
cirrus_dir, system_name,
- asoc_component_prefix, "bin");
+ suffix, "bin");
if (!*coeff_firmware)
wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -816,10 +819,10 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
/* Check system-specific bin without wmfw before falling back to generic */
if (dsp->wmfw_optional && system_name) {
- if (asoc_component_prefix)
+ if (suffix)
wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
cirrus_dir, system_name,
- asoc_component_prefix, "bin");
+ suffix, "bin");
if (!*coeff_firmware)
wm_adsp_request_firmware_file(dsp, coeff_firmware, coeff_filename,
@@ -850,7 +853,7 @@ static int wm_adsp_request_firmware_files(struct wm_adsp *dsp,
adsp_err(dsp, "Failed to request firmware <%s>%s-%s-%s<-%s<%s>>.wmfw\n",
cirrus_dir, dsp->part,
dsp->fwf_name ? dsp->fwf_name : dsp->cs_dsp.name,
- wm_adsp_fw[dsp->fw].file, system_name, asoc_component_prefix);
+ wm_adsp_fw[dsp->fw].file, system_name, suffix);
return -ENOENT;
}
@@ -997,11 +1000,17 @@ int wm_adsp_power_up(struct wm_adsp *dsp, bool load_firmware)
return ret;
}
+ if (dsp->bin_mandatory && !coeff_firmware) {
+ ret = -ENOENT;
+ goto err;
+ }
+
ret = cs_dsp_power_up(&dsp->cs_dsp,
wmfw_firmware, wmfw_filename,
coeff_firmware, coeff_filename,
wm_adsp_fw_text[dsp->fw]);
+err:
wm_adsp_release_firmware_files(dsp,
wmfw_firmware, wmfw_filename,
coeff_firmware, coeff_filename);
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index edc5b02ae765..25210d404bf1 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -29,12 +29,14 @@ struct wm_adsp {
const char *part;
const char *fwf_name;
const char *system_name;
+ const char *fwf_suffix;
struct snd_soc_component *component;
unsigned int sys_config_size;
int fw;
bool wmfw_optional;
+ bool bin_mandatory;
struct work_struct boot_work;
int (*control_add)(struct wm_adsp *dsp, struct cs_dsp_coeff_ctl *cs_ctl);
diff --git a/sound/soc/intel/common/sof-function-topology-lib.c b/sound/soc/intel/common/sof-function-topology-lib.c
index 90fe7aa3df1c..3cc81dcf047e 100644
--- a/sound/soc/intel/common/sof-function-topology-lib.c
+++ b/sound/soc/intel/common/sof-function-topology-lib.c
@@ -73,7 +73,8 @@ int sof_sdw_get_tplg_files(struct snd_soc_card *card, const struct snd_soc_acpi_
break;
default:
dev_warn(card->dev,
- "only -2ch and -4ch are supported for dmic\n");
+ "unsupported number of dmics: %d\n",
+ mach_params.dmic_num);
continue;
}
tplg_dev = TPLG_DEVICE_INTEL_PCH_DMIC;
diff --git a/sound/soc/loongson/loongson_i2s.c b/sound/soc/loongson/loongson_i2s.c
index e8852a30f213..e336656e13eb 100644
--- a/sound/soc/loongson/loongson_i2s.c
+++ b/sound/soc/loongson/loongson_i2s.c
@@ -9,6 +9,7 @@
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
+#include <linux/export.h>
#include <linux/pm_runtime.h>
#include <linux/dma-mapping.h>
#include <sound/soc.h>
diff --git a/sound/soc/sdw_utils/soc_sdw_utils.c b/sound/soc/sdw_utils/soc_sdw_utils.c
index b7060b746356..d75e7292240b 100644
--- a/sound/soc/sdw_utils/soc_sdw_utils.c
+++ b/sound/soc/sdw_utils/soc_sdw_utils.c
@@ -1205,6 +1205,8 @@ static int is_sdca_endpoint_present(struct device *dev,
int i;
dlc = kzalloc(sizeof(*dlc), GFP_KERNEL);
+ if (!dlc)
+ return -ENOMEM;
adr_end = &adr_dev->endpoints[end_index];
dai_info = &codec_info->dais[adr_end->num];
diff --git a/sound/soc/sof/imx/imx8.c b/sound/soc/sof/imx/imx8.c
index a40a8047873e..b73dd91bd529 100644
--- a/sound/soc/sof/imx/imx8.c
+++ b/sound/soc/sof/imx/imx8.c
@@ -40,6 +40,19 @@ struct imx8m_chip_data {
struct reset_control *run_stall;
};
+static int imx8_shutdown(struct snd_sof_dev *sdev)
+{
+ /*
+ * Force the DSP to stall. After the firmware image is loaded,
+ * the stall will be removed during run() by a matching
+ * imx_sc_pm_cpu_start() call.
+ */
+ imx_sc_pm_cpu_start(get_chip_pdata(sdev), IMX_SC_R_DSP, false,
+ RESET_VECTOR_VADDR);
+
+ return 0;
+}
+
/*
* DSP control.
*/
@@ -281,11 +294,13 @@ static int imx8_ops_init(struct snd_sof_dev *sdev)
static const struct imx_chip_ops imx8_chip_ops = {
.probe = imx8_probe,
.core_kick = imx8_run,
+ .core_shutdown = imx8_shutdown,
};
static const struct imx_chip_ops imx8x_chip_ops = {
.probe = imx8_probe,
.core_kick = imx8x_run,
+ .core_shutdown = imx8_shutdown,
};
static const struct imx_chip_ops imx8m_chip_ops = {
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index 0e9b5431a47f..faac7df1fbcf 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -383,6 +383,13 @@ static const struct usbmix_name_map ms_usb_link_map[] = {
{ 0 } /* terminator */
};
+/* KTMicro USB */
+static struct usbmix_name_map s31b2_0022_map[] = {
+ { 23, "Speaker Playback" },
+ { 18, "Headphone Playback" },
+ { 0 }
+};
+
/* ASUS ROG Zenith II with Realtek ALC1220-VB */
static const struct usbmix_name_map asus_zenith_ii_map[] = {
{ 19, NULL, 12 }, /* FU, Input Gain Pad - broken response, disabled */
@@ -692,6 +699,11 @@ static const struct usbmix_ctl_map usbmix_ctl_maps[] = {
.id = USB_ID(0x045e, 0x083c),
.map = ms_usb_link_map,
},
+ {
+ /* KTMicro USB */
+ .id = USB_ID(0X31b2, 0x0022),
+ .map = s31b2_0022_map,
+ },
{ 0 } /* terminator */
};
diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h
index af9d9acaf997..ed5f3892674c 100644
--- a/tools/arch/arm64/include/uapi/asm/kvm.h
+++ b/tools/arch/arm64/include/uapi/asm/kvm.h
@@ -431,10 +431,11 @@ enum {
/* Device Control API on vcpu fd */
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
-#define KVM_ARM_VCPU_PMU_V3_IRQ 0
-#define KVM_ARM_VCPU_PMU_V3_INIT 1
-#define KVM_ARM_VCPU_PMU_V3_FILTER 2
-#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3
+#define KVM_ARM_VCPU_PMU_V3_IRQ 0
+#define KVM_ARM_VCPU_PMU_V3_INIT 1
+#define KVM_ARM_VCPU_PMU_V3_FILTER 2
+#define KVM_ARM_VCPU_PMU_V3_SET_PMU 3
+#define KVM_ARM_VCPU_PMU_V3_SET_NR_COUNTERS 4
#define KVM_ARM_VCPU_TIMER_CTRL 1
#define KVM_ARM_VCPU_TIMER_IRQ_VTIMER 0
#define KVM_ARM_VCPU_TIMER_IRQ_PTIMER 1
diff --git a/tools/arch/x86/include/asm/amd/ibs.h b/tools/arch/x86/include/asm/amd/ibs.h
index 300b6e0765b2..cbce54fec7b9 100644
--- a/tools/arch/x86/include/asm/amd/ibs.h
+++ b/tools/arch/x86/include/asm/amd/ibs.h
@@ -1,4 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_IBS_H
+#define _ASM_X86_AMD_IBS_H
+
/*
* From PPR Vol 1 for AMD Family 19h Model 01h B1
* 55898 Rev 0.35 - Feb 5, 2021
@@ -151,3 +154,5 @@ struct perf_ibs_data {
};
u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX];
};
+
+#endif /* _ASM_X86_AMD_IBS_H */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index e02be2962a01..ee176236c2be 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -336,7 +336,7 @@
#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
-#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
+#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
@@ -379,6 +379,7 @@
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
+#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */
#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -447,6 +448,7 @@
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */
#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */
+#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */
@@ -458,6 +460,7 @@
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
+#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */
#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
@@ -482,7 +485,8 @@
#define X86_FEATURE_AMD_HTR_CORES (21*32+ 6) /* Heterogeneous Core Topology */
#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32+ 7) /* Workload Classification */
#define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */
-#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+ 9) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */
+#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
/*
* BUG word(s)
@@ -535,6 +539,8 @@
#define X86_BUG_BHI X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
#define X86_BUG_IBPB_NO_RET X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
#define X86_BUG_SPECTRE_V2_USER X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
-#define X86_BUG_ITS X86_BUG( 1*32+ 6) /* "its" CPU is affected by Indirect Target Selection */
-#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
+#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index e7d2f460fcc6..b7dded3c8113 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -533,7 +533,7 @@
#define MSR_HWP_CAPABILITIES 0x00000771
#define MSR_HWP_REQUEST_PKG 0x00000772
#define MSR_HWP_INTERRUPT 0x00000773
-#define MSR_HWP_REQUEST 0x00000774
+#define MSR_HWP_REQUEST 0x00000774
#define MSR_HWP_STATUS 0x00000777
/* CPUID.6.EAX */
@@ -550,16 +550,16 @@
#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff)
/* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) (x & 0xff)
-#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
+#define HWP_MIN_PERF(x) (x & 0xff)
+#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24)
+#define HWP_ENERGY_PERF_PREFERENCE(x) (((u64)x & 0xff) << 24)
#define HWP_EPP_PERFORMANCE 0x00
#define HWP_EPP_BALANCE_PERFORMANCE 0x80
#define HWP_EPP_BALANCE_POWERSAVE 0xC0
#define HWP_EPP_POWERSAVE 0xFF
-#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42)
+#define HWP_ACTIVITY_WINDOW(x) ((u64)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x) ((u64)(x & 0x1) << 42)
/* IA32_HWP_STATUS */
#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
@@ -602,7 +602,11 @@
/* V6 PMON MSR range */
#define MSR_IA32_PMC_V6_GP0_CTR 0x1900
#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B 0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C 0x1903
#define MSR_IA32_PMC_V6_FX0_CTR 0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B 0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C 0x1983
#define MSR_IA32_PMC_V6_STEP 4
/* KeyID partitioning between MKTME and TDX */
diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index b663d916f162..6f3499507c5e 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -441,6 +441,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7)
#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8)
+#define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
@@ -931,4 +932,74 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_SNP_VM 4
#define KVM_X86_TDX_VM 5
+/* Trust Domain eXtension sub-ioctl() commands. */
+enum kvm_tdx_cmd_id {
+ KVM_TDX_CAPABILITIES = 0,
+ KVM_TDX_INIT_VM,
+ KVM_TDX_INIT_VCPU,
+ KVM_TDX_INIT_MEM_REGION,
+ KVM_TDX_FINALIZE_VM,
+ KVM_TDX_GET_CPUID,
+
+ KVM_TDX_CMD_NR_MAX,
+};
+
+struct kvm_tdx_cmd {
+ /* enum kvm_tdx_cmd_id */
+ __u32 id;
+ /* flags for sub-commend. If sub-command doesn't use this, set zero. */
+ __u32 flags;
+ /*
+ * data for each sub-command. An immediate or a pointer to the actual
+ * data in process virtual address. If sub-command doesn't use it,
+ * set zero.
+ */
+ __u64 data;
+ /*
+ * Auxiliary error code. The sub-command may return TDX SEAMCALL
+ * status code in addition to -Exxx.
+ */
+ __u64 hw_error;
+};
+
+struct kvm_tdx_capabilities {
+ __u64 supported_attrs;
+ __u64 supported_xfam;
+ __u64 reserved[254];
+
+ /* Configurable CPUID bits for userspace */
+ struct kvm_cpuid2 cpuid;
+};
+
+struct kvm_tdx_init_vm {
+ __u64 attributes;
+ __u64 xfam;
+ __u64 mrconfigid[6]; /* sha384 digest */
+ __u64 mrowner[6]; /* sha384 digest */
+ __u64 mrownerconfig[6]; /* sha384 digest */
+
+ /* The total space for TD_PARAMS before the CPUIDs is 256 bytes */
+ __u64 reserved[12];
+
+ /*
+ * Call KVM_TDX_INIT_VM before vcpu creation, thus before
+ * KVM_SET_CPUID2.
+ * This configuration supersedes KVM_SET_CPUID2s for VCPUs because the
+ * TDX module directly virtualizes those CPUIDs without VMM. The user
+ * space VMM, e.g. qemu, should make KVM_SET_CPUID2 consistent with
+ * those values. If it doesn't, KVM may have wrong idea of vCPUIDs of
+ * the guest, and KVM may wrongly emulate CPUIDs or MSRs that the TDX
+ * module doesn't virtualize.
+ */
+ struct kvm_cpuid2 cpuid;
+};
+
+#define KVM_TDX_MEASURE_MEMORY_REGION _BITULL(0)
+
+struct kvm_tdx_init_mem_region {
+ __u64 source_addr;
+ __u64 gpa;
+ __u64 nr_pages;
+};
+
#endif /* _ASM_X86_KVM_H */
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index ec1321248dac..9c640a521a67 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
#define SVM_EXIT_CR14_WRITE_TRAP 0x09e
#define SVM_EXIT_CR15_WRITE_TRAP 0x09f
#define SVM_EXIT_INVPCID 0x0a2
+#define SVM_EXIT_BUS_LOCK 0x0a5
#define SVM_EXIT_IDLE_HLT 0x0a6
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
@@ -225,6 +226,7 @@
{ SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \
{ SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \
{ SVM_EXIT_INVPCID, "invpcid" }, \
+ { SVM_EXIT_BUS_LOCK, "buslock" }, \
{ SVM_EXIT_IDLE_HLT, "idle-halt" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index a5faf6d88f1b..f0f4a4cf84a7 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -34,6 +34,7 @@
#define EXIT_REASON_TRIPLE_FAULT 2
#define EXIT_REASON_INIT_SIGNAL 3
#define EXIT_REASON_SIPI_SIGNAL 4
+#define EXIT_REASON_OTHER_SMI 6
#define EXIT_REASON_INTERRUPT_WINDOW 7
#define EXIT_REASON_NMI_WINDOW 8
@@ -92,6 +93,7 @@
#define EXIT_REASON_TPAUSE 68
#define EXIT_REASON_BUS_LOCK 74
#define EXIT_REASON_NOTIFY 75
+#define EXIT_REASON_TDCALL 77
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -155,7 +157,8 @@
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }, \
{ EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \
- { EXIT_REASON_NOTIFY, "NOTIFY" }
+ { EXIT_REASON_NOTIFY, "NOTIFY" }, \
+ { EXIT_REASON_TDCALL, "TDCALL" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 59cf6f9065aa..ccc3d923fc1e 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -40,6 +40,7 @@ SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
EXPORT_SYMBOL(memcpy)
SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index d66b710d628f..fb5a03cf5ab7 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -42,6 +42,7 @@ SYM_FUNC_END(__memset)
EXPORT_SYMBOL(__memset)
SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
EXPORT_SYMBOL(memset)
SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/tools/bpf/bpf_jit_disasm.c b/tools/bpf/bpf_jit_disasm.c
index 1baee9e2aba9..5ab8f80e2834 100644
--- a/tools/bpf/bpf_jit_disasm.c
+++ b/tools/bpf/bpf_jit_disasm.c
@@ -45,6 +45,8 @@ static void get_exec_path(char *tpath, size_t size)
assert(path);
len = readlink(path, tpath, size);
+ if (len < 0)
+ len = 0;
tpath[len] = 0;
free(path);
diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 6b14cbfa58aa..946612029dee 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -905,7 +905,8 @@ static int do_dump(int argc, char **argv)
return -1;
}
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len,
+ BPF_F_RDONLY);
if (fd < 0)
return -1;
@@ -1118,10 +1119,13 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type,
[BPF_OBJ_PROG] = "prog",
[BPF_OBJ_MAP] = "map",
};
+ LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts_ro);
__u32 btf_id, id = 0;
int err;
int fd;
+ opts_ro.open_flags = BPF_F_RDONLY;
+
while (true) {
switch (type) {
case BPF_OBJ_PROG:
@@ -1151,7 +1155,7 @@ build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type,
fd = bpf_prog_get_fd_by_id(id);
break;
case BPF_OBJ_MAP:
- fd = bpf_map_get_fd_by_id(id);
+ fd = bpf_map_get_fd_by_id_opts(id, &opts_ro);
break;
default:
err = -1;
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index ecfa790adc13..b07317d2842f 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -4,6 +4,7 @@
#ifndef _GNU_SOURCE
#define _GNU_SOURCE
#endif
+#include <assert.h>
#include <ctype.h>
#include <errno.h>
#include <fcntl.h>
@@ -193,7 +194,8 @@ int mount_tracefs(const char *target)
return err;
}
-int open_obj_pinned(const char *path, bool quiet)
+int open_obj_pinned(const char *path, bool quiet,
+ const struct bpf_obj_get_opts *opts)
{
char *pname;
int fd = -1;
@@ -205,7 +207,7 @@ int open_obj_pinned(const char *path, bool quiet)
goto out_ret;
}
- fd = bpf_obj_get(pname);
+ fd = bpf_obj_get_opts(pname, opts);
if (fd < 0) {
if (!quiet)
p_err("bpf obj get (%s): %s", pname,
@@ -221,12 +223,13 @@ out_ret:
return fd;
}
-int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type)
+int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type,
+ const struct bpf_obj_get_opts *opts)
{
enum bpf_obj_type type;
int fd;
- fd = open_obj_pinned(path, false);
+ fd = open_obj_pinned(path, false, opts);
if (fd < 0)
return -1;
@@ -555,7 +558,7 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
if (typeflag != FTW_F)
goto out_ret;
- fd = open_obj_pinned(fpath, true);
+ fd = open_obj_pinned(fpath, true, NULL);
if (fd < 0)
goto out_ret;
@@ -928,7 +931,7 @@ int prog_parse_fds(int *argc, char ***argv, int **fds)
path = **argv;
NEXT_ARGP();
- (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG);
+ (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_PROG, NULL);
if ((*fds)[0] < 0)
return -1;
return 1;
@@ -965,7 +968,8 @@ exit_free:
return fd;
}
-static int map_fd_by_name(char *name, int **fds)
+static int map_fd_by_name(char *name, int **fds,
+ const struct bpf_get_fd_by_id_opts *opts)
{
unsigned int id = 0;
int fd, nb_fds = 0;
@@ -973,6 +977,7 @@ static int map_fd_by_name(char *name, int **fds)
int err;
while (true) {
+ LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts_ro);
struct bpf_map_info info = {};
__u32 len = sizeof(info);
@@ -985,7 +990,9 @@ static int map_fd_by_name(char *name, int **fds)
return nb_fds;
}
- fd = bpf_map_get_fd_by_id(id);
+ /* Request a read-only fd to query the map info */
+ opts_ro.open_flags = BPF_F_RDONLY;
+ fd = bpf_map_get_fd_by_id_opts(id, &opts_ro);
if (fd < 0) {
p_err("can't get map by id (%u): %s",
id, strerror(errno));
@@ -1004,6 +1011,19 @@ static int map_fd_by_name(char *name, int **fds)
continue;
}
+ /* Get an fd with the requested options, if they differ
+ * from the read-only options used to get the fd above.
+ */
+ if (memcmp(opts, &opts_ro, sizeof(opts_ro))) {
+ close(fd);
+ fd = bpf_map_get_fd_by_id_opts(id, opts);
+ if (fd < 0) {
+ p_err("can't get map by id (%u): %s", id,
+ strerror(errno));
+ goto err_close_fds;
+ }
+ }
+
if (nb_fds > 0) {
tmp = realloc(*fds, (nb_fds + 1) * sizeof(int));
if (!tmp) {
@@ -1023,8 +1043,13 @@ err_close_fds:
return -1;
}
-int map_parse_fds(int *argc, char ***argv, int **fds)
+int map_parse_fds(int *argc, char ***argv, int **fds, __u32 open_flags)
{
+ LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts);
+
+ assert((open_flags & ~BPF_F_RDONLY) == 0);
+ opts.open_flags = open_flags;
+
if (is_prefix(**argv, "id")) {
unsigned int id;
char *endptr;
@@ -1038,7 +1063,7 @@ int map_parse_fds(int *argc, char ***argv, int **fds)
}
NEXT_ARGP();
- (*fds)[0] = bpf_map_get_fd_by_id(id);
+ (*fds)[0] = bpf_map_get_fd_by_id_opts(id, &opts);
if ((*fds)[0] < 0) {
p_err("get map by id (%u): %s", id, strerror(errno));
return -1;
@@ -1056,16 +1081,18 @@ int map_parse_fds(int *argc, char ***argv, int **fds)
}
NEXT_ARGP();
- return map_fd_by_name(name, fds);
+ return map_fd_by_name(name, fds, &opts);
} else if (is_prefix(**argv, "pinned")) {
char *path;
+ LIBBPF_OPTS(bpf_obj_get_opts, get_opts);
+ get_opts.file_flags = open_flags;
NEXT_ARGP();
path = **argv;
NEXT_ARGP();
- (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP);
+ (*fds)[0] = open_obj_pinned_any(path, BPF_OBJ_MAP, &get_opts);
if ((*fds)[0] < 0)
return -1;
return 1;
@@ -1075,7 +1102,7 @@ int map_parse_fds(int *argc, char ***argv, int **fds)
return -1;
}
-int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv, __u32 open_flags)
{
int *fds = NULL;
int nb_fds, fd;
@@ -1085,7 +1112,7 @@ int map_parse_fd(int *argc, char ***argv)
p_err("mem alloc failed");
return -1;
}
- nb_fds = map_parse_fds(argc, argv, &fds);
+ nb_fds = map_parse_fds(argc, argv, &fds, open_flags);
if (nb_fds != 1) {
if (nb_fds > 1) {
p_err("several maps match this handle");
@@ -1103,12 +1130,12 @@ exit_free:
}
int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info,
- __u32 *info_len)
+ __u32 *info_len, __u32 open_flags)
{
int err;
int fd;
- fd = map_parse_fd(argc, argv);
+ fd = map_parse_fd(argc, argv, open_flags);
if (fd < 0)
return -1;
diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c
index 5c39c2ed36a2..df5f0d1e07e8 100644
--- a/tools/bpf/bpftool/iter.c
+++ b/tools/bpf/bpftool/iter.c
@@ -37,7 +37,7 @@ static int do_pin(int argc, char **argv)
return -1;
}
- map_fd = map_parse_fd(&argc, &argv);
+ map_fd = map_parse_fd(&argc, &argv, BPF_F_RDONLY);
if (map_fd < 0)
return -1;
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 3535afc80a49..a773e05d5ade 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -117,7 +117,7 @@ static int link_parse_fd(int *argc, char ***argv)
path = **argv;
NEXT_ARGP();
- return open_obj_pinned_any(path, BPF_OBJ_LINK);
+ return open_obj_pinned_any(path, BPF_OBJ_LINK, NULL);
}
p_err("expected 'id' or 'pinned', got: '%s'?", **argv);
@@ -485,6 +485,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
case BPF_LINK_TYPE_RAW_TRACEPOINT:
jsonw_string_field(json_wtr, "tp_name",
u64_to_ptr(info->raw_tracepoint.tp_name));
+ jsonw_uint_field(json_wtr, "cookie", info->raw_tracepoint.cookie);
break;
case BPF_LINK_TYPE_TRACING:
err = get_prog_info(info->prog_id, &prog_info);
@@ -502,6 +503,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
json_wtr);
jsonw_uint_field(json_wtr, "target_obj_id", info->tracing.target_obj_id);
jsonw_uint_field(json_wtr, "target_btf_id", info->tracing.target_btf_id);
+ jsonw_uint_field(json_wtr, "cookie", info->tracing.cookie);
break;
case BPF_LINK_TYPE_CGROUP:
jsonw_lluint_field(json_wtr, "cgroup_id",
@@ -879,6 +881,8 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
case BPF_LINK_TYPE_RAW_TRACEPOINT:
printf("\n\ttp '%s' ",
(const char *)u64_to_ptr(info->raw_tracepoint.tp_name));
+ if (info->raw_tracepoint.cookie)
+ printf("cookie %llu ", info->raw_tracepoint.cookie);
break;
case BPF_LINK_TYPE_TRACING:
err = get_prog_info(info->prog_id, &prog_info);
@@ -897,6 +901,8 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
printf("\n\ttarget_obj_id %u target_btf_id %u ",
info->tracing.target_obj_id,
info->tracing.target_btf_id);
+ if (info->tracing.cookie)
+ printf("\n\tcookie %llu ", info->tracing.cookie);
break;
case BPF_LINK_TYPE_CGROUP:
printf("\n\tcgroup_id %zu ", (size_t)info->cgroup.cgroup_id);
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index cd5963cb6058..2b7f2bd3a7db 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -534,9 +534,9 @@ int main(int argc, char **argv)
usage();
if (version_requested)
- return do_version(argc, argv);
-
- ret = cmd_select(commands, argc, argv, do_help);
+ ret = do_version(argc, argv);
+ else
+ ret = cmd_select(commands, argc, argv, do_help);
if (json_output)
jsonw_destroy(&json_wtr);
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 9eb764fe4cc8..6db704fda5c0 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -15,6 +15,7 @@
#include <bpf/hashmap.h>
#include <bpf/libbpf.h>
+#include <bpf/bpf.h>
#include "json_writer.h"
@@ -140,8 +141,10 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
int get_fd_type(int fd);
const char *get_fd_type_name(enum bpf_obj_type type);
char *get_fdinfo(int fd, const char *key);
-int open_obj_pinned(const char *path, bool quiet);
-int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type);
+int open_obj_pinned(const char *path, bool quiet,
+ const struct bpf_obj_get_opts *opts);
+int open_obj_pinned_any(const char *path, enum bpf_obj_type exp_type,
+ const struct bpf_obj_get_opts *opts);
int mount_bpffs_for_file(const char *file_name);
int create_and_mount_bpffs_dir(const char *dir_name);
int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(int *, char ***));
@@ -167,10 +170,10 @@ int do_iter(int argc, char **argv) __weak;
int parse_u32_arg(int *argc, char ***argv, __u32 *val, const char *what);
int prog_parse_fd(int *argc, char ***argv);
int prog_parse_fds(int *argc, char ***argv, int **fds);
-int map_parse_fd(int *argc, char ***argv);
-int map_parse_fds(int *argc, char ***argv, int **fds);
+int map_parse_fd(int *argc, char ***argv, __u32 open_flags);
+int map_parse_fds(int *argc, char ***argv, int **fds, __u32 open_flags);
int map_parse_fd_and_info(int *argc, char ***argv, struct bpf_map_info *info,
- __u32 *info_len);
+ __u32 *info_len, __u32 open_flags);
struct bpf_prog_linfo;
#if defined(HAVE_LLVM_SUPPORT) || defined(HAVE_LIBBFD_SUPPORT)
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 81cc668b4b05..c9de44a45778 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -337,9 +337,9 @@ static void fill_per_cpu_value(struct bpf_map_info *info, void *value)
memcpy(value + i * step, value, info->value_size);
}
-static int parse_elem(char **argv, struct bpf_map_info *info,
- void *key, void *value, __u32 key_size, __u32 value_size,
- __u32 *flags, __u32 **value_fd)
+static int parse_elem(char **argv, struct bpf_map_info *info, void *key,
+ void *value, __u32 key_size, __u32 value_size,
+ __u32 *flags, __u32 **value_fd, __u32 open_flags)
{
if (!*argv) {
if (!key && !value)
@@ -362,7 +362,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
return -1;
return parse_elem(argv, info, NULL, value, key_size, value_size,
- flags, value_fd);
+ flags, value_fd, open_flags);
} else if (is_prefix(*argv, "value")) {
int fd;
@@ -388,7 +388,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
return -1;
}
- fd = map_parse_fd(&argc, &argv);
+ fd = map_parse_fd(&argc, &argv, open_flags);
if (fd < 0)
return -1;
@@ -424,7 +424,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
}
return parse_elem(argv, info, key, NULL, key_size, value_size,
- flags, NULL);
+ flags, NULL, open_flags);
} else if (is_prefix(*argv, "any") || is_prefix(*argv, "noexist") ||
is_prefix(*argv, "exist")) {
if (!flags) {
@@ -440,7 +440,7 @@ static int parse_elem(char **argv, struct bpf_map_info *info,
*flags = BPF_EXIST;
return parse_elem(argv + 1, info, key, value, key_size,
- value_size, NULL, value_fd);
+ value_size, NULL, value_fd, open_flags);
}
p_err("expected key or value, got: %s", *argv);
@@ -639,7 +639,7 @@ static int do_show_subset(int argc, char **argv)
p_err("mem alloc failed");
return -1;
}
- nb_fds = map_parse_fds(&argc, &argv, &fds);
+ nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY);
if (nb_fds < 1)
goto exit_free;
@@ -672,12 +672,15 @@ exit_free:
static int do_show(int argc, char **argv)
{
+ LIBBPF_OPTS(bpf_get_fd_by_id_opts, opts);
struct bpf_map_info info = {};
__u32 len = sizeof(info);
__u32 id = 0;
int err;
int fd;
+ opts.open_flags = BPF_F_RDONLY;
+
if (show_pinned) {
map_table = hashmap__new(hash_fn_for_key_as_id,
equal_fn_for_key_as_id, NULL);
@@ -707,7 +710,7 @@ static int do_show(int argc, char **argv)
break;
}
- fd = bpf_map_get_fd_by_id(id);
+ fd = bpf_map_get_fd_by_id_opts(id, &opts);
if (fd < 0) {
if (errno == ENOENT)
continue;
@@ -909,7 +912,7 @@ static int do_dump(int argc, char **argv)
p_err("mem alloc failed");
return -1;
}
- nb_fds = map_parse_fds(&argc, &argv, &fds);
+ nb_fds = map_parse_fds(&argc, &argv, &fds, BPF_F_RDONLY);
if (nb_fds < 1)
goto exit_free;
@@ -997,7 +1000,7 @@ static int do_update(int argc, char **argv)
if (argc < 2)
usage();
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0);
if (fd < 0)
return -1;
@@ -1006,7 +1009,7 @@ static int do_update(int argc, char **argv)
goto exit_free;
err = parse_elem(argv, &info, key, value, info.key_size,
- info.value_size, &flags, &value_fd);
+ info.value_size, &flags, &value_fd, 0);
if (err)
goto exit_free;
@@ -1076,7 +1079,7 @@ static int do_lookup(int argc, char **argv)
if (argc < 2)
usage();
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY);
if (fd < 0)
return -1;
@@ -1084,7 +1087,8 @@ static int do_lookup(int argc, char **argv)
if (err)
goto exit_free;
- err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+ err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL,
+ BPF_F_RDONLY);
if (err)
goto exit_free;
@@ -1127,7 +1131,7 @@ static int do_getnext(int argc, char **argv)
if (argc < 2)
usage();
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len, BPF_F_RDONLY);
if (fd < 0)
return -1;
@@ -1140,8 +1144,8 @@ static int do_getnext(int argc, char **argv)
}
if (argc) {
- err = parse_elem(argv, &info, key, NULL, info.key_size, 0,
- NULL, NULL);
+ err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL,
+ NULL, BPF_F_RDONLY);
if (err)
goto exit_free;
} else {
@@ -1198,7 +1202,7 @@ static int do_delete(int argc, char **argv)
if (argc < 2)
usage();
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0);
if (fd < 0)
return -1;
@@ -1209,7 +1213,8 @@ static int do_delete(int argc, char **argv)
goto exit_free;
}
- err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL);
+ err = parse_elem(argv, &info, key, NULL, info.key_size, 0, NULL, NULL,
+ 0);
if (err)
goto exit_free;
@@ -1226,11 +1231,16 @@ exit_free:
return err;
}
+static int map_parse_read_only_fd(int *argc, char ***argv)
+{
+ return map_parse_fd(argc, argv, BPF_F_RDONLY);
+}
+
static int do_pin(int argc, char **argv)
{
int err;
- err = do_pin_any(argc, argv, map_parse_fd);
+ err = do_pin_any(argc, argv, map_parse_read_only_fd);
if (!err && json_output)
jsonw_null(json_wtr);
return err;
@@ -1319,7 +1329,7 @@ offload_dev:
if (!REQ_ARGS(2))
usage();
inner_map_fd = map_parse_fd_and_info(&argc, &argv,
- &info, &len);
+ &info, &len, BPF_F_RDONLY);
if (inner_map_fd < 0)
return -1;
attr.inner_map_fd = inner_map_fd;
@@ -1368,7 +1378,7 @@ static int do_pop_dequeue(int argc, char **argv)
if (argc < 2)
usage();
- fd = map_parse_fd_and_info(&argc, &argv, &info, &len);
+ fd = map_parse_fd_and_info(&argc, &argv, &info, &len, 0);
if (fd < 0)
return -1;
@@ -1407,7 +1417,7 @@ static int do_freeze(int argc, char **argv)
if (!REQ_ARGS(2))
return -1;
- fd = map_parse_fd(&argc, &argv);
+ fd = map_parse_fd(&argc, &argv, 0);
if (fd < 0)
return -1;
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 552b4ca40c27..bcb767e2d673 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -128,7 +128,8 @@ int do_event_pipe(int argc, char **argv)
int err, map_fd;
map_info_len = sizeof(map_info);
- map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len);
+ map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len,
+ 0);
if (map_fd < 0)
return -1;
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 64f958f437b0..cfc6f944f7c3 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -366,17 +366,18 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
{
struct bpf_netdev_t *netinfo = cookie;
struct ifinfomsg *ifinfo = msg;
+ struct ip_devname_ifindex *tmp;
if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index)
return 0;
if (netinfo->used_len == netinfo->array_len) {
- netinfo->devices = realloc(netinfo->devices,
- (netinfo->array_len + 16) *
- sizeof(struct ip_devname_ifindex));
- if (!netinfo->devices)
+ tmp = realloc(netinfo->devices,
+ (netinfo->array_len + 16) * sizeof(struct ip_devname_ifindex));
+ if (!tmp)
return -ENOMEM;
+ netinfo->devices = tmp;
netinfo->array_len += 16;
}
netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index;
@@ -395,6 +396,7 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
{
struct bpf_tcinfo_t *tcinfo = cookie;
struct tcmsg *info = msg;
+ struct tc_kind_handle *tmp;
if (tcinfo->is_qdisc) {
/* skip clsact qdisc */
@@ -406,11 +408,12 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
}
if (tcinfo->used_len == tcinfo->array_len) {
- tcinfo->handle_array = realloc(tcinfo->handle_array,
+ tmp = realloc(tcinfo->handle_array,
(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
- if (!tcinfo->handle_array)
+ if (!tmp)
return -ENOMEM;
+ tcinfo->handle_array = tmp;
tcinfo->array_len += 16;
}
tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 96eea8a67225..deeaa5c1ed7d 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1062,7 +1062,7 @@ static int parse_attach_detach_args(int argc, char **argv, int *progfd,
if (!REQ_ARGS(2))
return -EINVAL;
- *mapfd = map_parse_fd(&argc, &argv);
+ *mapfd = map_parse_fd(&argc, &argv, 0);
if (*mapfd < 0)
return *mapfd;
@@ -1608,7 +1608,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
}
NEXT_ARG();
- fd = map_parse_fd(&argc, &argv);
+ fd = map_parse_fd(&argc, &argv, 0);
if (fd < 0)
goto err_free_reuse_maps;
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index afbddea3a39c..ce1b556dfa90 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -17,7 +17,7 @@ endif
# Overrides for the prepare step libraries.
HOST_OVERRIDES := AR="$(HOSTAR)" CC="$(HOSTCC)" LD="$(HOSTLD)" ARCH="$(HOSTARCH)" \
- CROSS_COMPILE="" EXTRA_CFLAGS="$(HOSTCFLAGS)"
+ CROSS_COMPILE="" CLANG_CROSS_FLAGS="" EXTRA_CFLAGS="$(HOSTCFLAGS)"
RM ?= rm
HOSTCC ?= gcc
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 14fd0ca9a6cd..7ad056219115 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -12,6 +12,7 @@
#define BIT_ULL_MASK(nr) (ULL(1) << ((nr) % BITS_PER_LONG_LONG))
#define BIT_ULL_WORD(nr) ((nr) / BITS_PER_LONG_LONG)
#define BITS_PER_BYTE 8
+#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
/*
* Create a contiguous bitmask starting at bit position @l and ending at
@@ -19,16 +20,68 @@
* GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
*/
#if !defined(__ASSEMBLY__)
+
+/*
+ * Missing asm support
+ *
+ * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(),
+ * something not available in asm. Nevertheless, fixed width integers is a C
+ * concept. Assembly code can rely on the long and long long versions instead.
+ */
+
#include <linux/build_bug.h>
#include <linux/compiler.h>
+#include <linux/overflow.h>
+
#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
-#else
+
+/*
+ * Generate a mask for the specified type @t. Additional checks are made to
+ * guarantee the value returned fits in that type, relying on
+ * -Wshift-count-overflow compiler check to detect incompatible arguments.
+ * For example, all these create build errors or warnings:
+ *
+ * - GENMASK(15, 20): wrong argument order
+ * - GENMASK(72, 15): doesn't fit unsigned long
+ * - GENMASK_U32(33, 15): doesn't fit in a u32
+ */
+#define GENMASK_TYPE(t, h, l) \
+ ((t)(GENMASK_INPUT_CHECK(h, l) + \
+ (type_max(t) << (l) & \
+ type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
+
+#define GENMASK_U8(h, l) GENMASK_TYPE(u8, h, l)
+#define GENMASK_U16(h, l) GENMASK_TYPE(u16, h, l)
+#define GENMASK_U32(h, l) GENMASK_TYPE(u32, h, l)
+#define GENMASK_U64(h, l) GENMASK_TYPE(u64, h, l)
+
+/*
+ * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
+ * following examples generate compiler warnings due to -Wshift-count-overflow:
+ *
+ * - BIT_U8(8)
+ * - BIT_U32(-1)
+ * - BIT_U32(40)
+ */
+#define BIT_INPUT_CHECK(type, nr) \
+ BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type)))
+
+#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr)))
+
+#define BIT_U8(nr) BIT_TYPE(u8, nr)
+#define BIT_U16(nr) BIT_TYPE(u16, nr)
+#define BIT_U32(nr) BIT_TYPE(u32, nr)
+#define BIT_U64(nr) BIT_TYPE(u64, nr)
+
+#else /* defined(__ASSEMBLY__) */
+
/*
* BUILD_BUG_ON_ZERO is not available in h files included from asm files,
* disable the input check if that is the case.
*/
#define GENMASK_INPUT_CHECK(h, l) 0
-#endif
+
+#endif /* !defined(__ASSEMBLY__) */
#define GENMASK(h, l) \
(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index b4898ff085de..ab2aa97bd8ce 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -4,17 +4,17 @@
#include <linux/compiler.h>
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_ZERO(e) (0)
-#else /* __CHECKER__ */
/*
* Force a compilation error if condition is true, but also produce a
* result (of value 0 and type int), so the expression can be used
* e.g. in a structure initializer (or where-ever else comma expressions
* aren't permitted).
+ *
+ * Take an error message as an optional second argument. If omitted,
+ * default to the stringification of the tested expression.
*/
-#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
-#endif /* __CHECKER__ */
+#define BUILD_BUG_ON_ZERO(e, ...) \
+ __BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
/* Force a compilation error if a constant expression is not a power of 2 */
#define __BUILD_BUG_ON_NOT_POWER_OF_2(n) \
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index d627e66a04a6..33411ca0cc90 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -244,6 +244,14 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
__asm__ ("" : "=r" (var) : "0" (var))
#endif
+#ifndef __BUILD_BUG_ON_ZERO_MSG
+#if defined(__clang__)
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)(sizeof(struct { int:(-!!(e)); })))
+#else
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#endif
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 7fba37b94401..e63a71d3c607 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -905,13 +905,17 @@ struct drm_syncobj_destroy {
};
#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE (1 << 1)
#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE (1 << 1)
struct drm_syncobj_handle {
__u32 handle;
__u32 flags;
__s32 fd;
__u32 pad;
+
+ __u64 point;
};
struct drm_syncobj_transfer {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0b4a2f124d11..719ba230032f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1794,6 +1794,13 @@ union bpf_attr {
};
__u64 expected_revision;
} netkit;
+ struct {
+ union {
+ __u32 relative_fd;
+ __u32 relative_id;
+ };
+ __u64 expected_revision;
+ } cgroup;
};
} link_create;
@@ -2403,7 +2410,7 @@ union bpf_attr {
* into it. An example is available in file
* *samples/bpf/trace_output_user.c* in the Linux kernel source
* tree (the eBPF program counterpart is in
- * *samples/bpf/trace_output_kern.c*).
+ * *samples/bpf/trace_output.bpf.c*).
*
* **bpf_perf_event_output**\ () achieves better performance
* than **bpf_trace_printk**\ () for sharing data with user
@@ -6653,11 +6660,15 @@ struct bpf_link_info {
struct {
__aligned_u64 tp_name; /* in/out: tp_name buffer ptr */
__u32 tp_name_len; /* in/out: tp_name buffer len */
+ __u32 :32;
+ __u64 cookie;
} raw_tracepoint;
struct {
__u32 attach_type;
__u32 target_obj_id; /* prog_id for PROG_EXT, otherwise btf object id */
__u32 target_btf_id; /* BTF type id inside the object */
+ __u32 :32;
+ __u64 cookie;
} tracing;
struct {
__u64 cgroup_id;
diff --git a/tools/include/uapi/linux/fscrypt.h b/tools/include/uapi/linux/fscrypt.h
index 7a8f4c290187..3aff99f2696a 100644
--- a/tools/include/uapi/linux/fscrypt.h
+++ b/tools/include/uapi/linux/fscrypt.h
@@ -119,7 +119,7 @@ struct fscrypt_key_specifier {
*/
struct fscrypt_provisioning_key_payload {
__u32 type;
- __u32 __reserved;
+ __u32 flags;
__u8 raw[];
};
@@ -128,7 +128,9 @@ struct fscrypt_add_key_arg {
struct fscrypt_key_specifier key_spec;
__u32 raw_size;
__u32 key_id;
- __u32 __reserved[8];
+#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001
+ __u32 flags;
+ __u32 __reserved[7];
__u8 raw[];
};
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index b6ae8ad8934b..d00b85cb168c 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -375,6 +375,7 @@ struct kvm_run {
#define KVM_SYSTEM_EVENT_WAKEUP 4
#define KVM_SYSTEM_EVENT_SUSPEND 5
#define KVM_SYSTEM_EVENT_SEV_TERM 6
+#define KVM_SYSTEM_EVENT_TDX_FATAL 7
__u32 type;
__u32 ndata;
union {
@@ -930,6 +931,9 @@ struct kvm_enable_cap {
#define KVM_CAP_X86_APIC_BUS_CYCLES_NS 237
#define KVM_CAP_X86_GUEST_MODE 238
#define KVM_CAP_ARM_WRITABLE_IMP_ID_REGS 239
+#define KVM_CAP_ARM_EL2 240
+#define KVM_CAP_ARM_EL2_E2H0 241
+#define KVM_CAP_RISCV_MP_STATE_RESET 242
struct kvm_irq_routing_irqchip {
__u32 irqchip;
diff --git a/tools/include/uapi/linux/stat.h b/tools/include/uapi/linux/stat.h
index f78ee3670dd5..1686861aae20 100644
--- a/tools/include/uapi/linux/stat.h
+++ b/tools/include/uapi/linux/stat.h
@@ -182,8 +182,12 @@ struct statx {
/* File offset alignment for direct I/O reads */
__u32 stx_dio_read_offset_align;
- /* 0xb8 */
- __u64 __spare3[9]; /* Spare space for future expansion */
+ /* Optimised max atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max_opt;
+ __u32 __spare2[1];
+
+ /* 0xc0 */
+ __u64 __spare3[8]; /* Spare space for future expansion */
/* 0x100 */
};
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a9c3e33d0f8a..6eb421ccf91b 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -837,6 +837,50 @@ int bpf_link_create(int prog_fd, int target_fd,
if (!OPTS_ZEROED(opts, netkit))
return libbpf_err(-EINVAL);
break;
+ case BPF_CGROUP_INET_INGRESS:
+ case BPF_CGROUP_INET_EGRESS:
+ case BPF_CGROUP_INET_SOCK_CREATE:
+ case BPF_CGROUP_INET_SOCK_RELEASE:
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ case BPF_CGROUP_INET4_POST_BIND:
+ case BPF_CGROUP_INET6_POST_BIND:
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ case BPF_CGROUP_UNIX_CONNECT:
+ case BPF_CGROUP_INET4_GETPEERNAME:
+ case BPF_CGROUP_INET6_GETPEERNAME:
+ case BPF_CGROUP_UNIX_GETPEERNAME:
+ case BPF_CGROUP_INET4_GETSOCKNAME:
+ case BPF_CGROUP_INET6_GETSOCKNAME:
+ case BPF_CGROUP_UNIX_GETSOCKNAME:
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ case BPF_CGROUP_UNIX_SENDMSG:
+ case BPF_CGROUP_UDP4_RECVMSG:
+ case BPF_CGROUP_UDP6_RECVMSG:
+ case BPF_CGROUP_UNIX_RECVMSG:
+ case BPF_CGROUP_SOCK_OPS:
+ case BPF_CGROUP_DEVICE:
+ case BPF_CGROUP_SYSCTL:
+ case BPF_CGROUP_GETSOCKOPT:
+ case BPF_CGROUP_SETSOCKOPT:
+ case BPF_LSM_CGROUP:
+ relative_fd = OPTS_GET(opts, cgroup.relative_fd, 0);
+ relative_id = OPTS_GET(opts, cgroup.relative_id, 0);
+ if (relative_fd && relative_id)
+ return libbpf_err(-EINVAL);
+ if (relative_id) {
+ attr.link_create.cgroup.relative_id = relative_id;
+ attr.link_create.flags |= BPF_F_ID;
+ } else {
+ attr.link_create.cgroup.relative_fd = relative_fd;
+ }
+ attr.link_create.cgroup.expected_revision =
+ OPTS_GET(opts, cgroup.expected_revision, 0);
+ if (!OPTS_ZEROED(opts, cgroup))
+ return libbpf_err(-EINVAL);
+ break;
default:
if (!OPTS_ZEROED(opts, flags))
return libbpf_err(-EINVAL);
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 777627d33d25..1342564214c8 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -438,6 +438,11 @@ struct bpf_link_create_opts {
__u32 relative_id;
__u64 expected_revision;
} netkit;
+ struct {
+ __u32 relative_fd;
+ __u32 relative_id;
+ __u64 expected_revision;
+ } cgroup;
};
size_t :0;
};
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index f1d495dc66bb..37682908cb0f 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1384,12 +1384,12 @@ static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf)
fd = open(path, O_RDONLY);
if (fd < 0)
- return libbpf_err_ptr(-errno);
+ return ERR_PTR(-errno);
if (fstat(fd, &st) < 0) {
err = -errno;
close(fd);
- return libbpf_err_ptr(err);
+ return ERR_PTR(err);
}
data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
@@ -1397,7 +1397,7 @@ static struct btf *btf_parse_raw_mmap(const char *path, struct btf *base_btf)
close(fd);
if (data == MAP_FAILED)
- return libbpf_err_ptr(err);
+ return ERR_PTR(err);
btf = btf_new(data, st.st_size, base_btf, true);
if (IS_ERR(btf))
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4392451d634b..ccfd905f03df 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -326,9 +326,10 @@ struct btf_dump_type_data_opts {
bool compact; /* no newlines/indentation */
bool skip_names; /* skip member/type names */
bool emit_zeroes; /* show 0-valued fields */
+ bool emit_strings; /* print char arrays as strings */
size_t :0;
};
-#define btf_dump_type_data_opts__last_field emit_zeroes
+#define btf_dump_type_data_opts__last_field emit_strings
LIBBPF_API int
btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 460c3e57fadb..f09f25eccf3c 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -68,6 +68,7 @@ struct btf_dump_data {
bool compact;
bool skip_names;
bool emit_zeroes;
+ bool emit_strings;
__u8 indent_lvl; /* base indent level */
char indent_str[BTF_DATA_INDENT_STR_LEN];
/* below are used during iteration */
@@ -226,6 +227,9 @@ static void btf_dump_free_names(struct hashmap *map)
size_t bkt;
struct hashmap_entry *cur;
+ if (!map)
+ return;
+
hashmap__for_each_entry(map, cur, bkt)
free((void *)cur->pkey);
@@ -2028,6 +2032,52 @@ static int btf_dump_var_data(struct btf_dump *d,
return btf_dump_dump_type_data(d, NULL, t, type_id, data, 0, 0);
}
+static int btf_dump_string_data(struct btf_dump *d,
+ const struct btf_type *t,
+ __u32 id,
+ const void *data)
+{
+ const struct btf_array *array = btf_array(t);
+ const char *chars = data;
+ __u32 i;
+
+ /* Make sure it is a NUL-terminated string. */
+ for (i = 0; i < array->nelems; i++) {
+ if ((void *)(chars + i) >= d->typed_dump->data_end)
+ return -E2BIG;
+ if (chars[i] == '\0')
+ break;
+ }
+ if (i == array->nelems) {
+ /* The caller will print this as a regular array. */
+ return -EINVAL;
+ }
+
+ btf_dump_data_pfx(d);
+ btf_dump_printf(d, "\"");
+
+ for (i = 0; i < array->nelems; i++) {
+ char c = chars[i];
+
+ if (c == '\0') {
+ /*
+ * When printing character arrays as strings, NUL bytes
+ * are always treated as string terminators; they are
+ * never printed.
+ */
+ break;
+ }
+ if (isprint(c))
+ btf_dump_printf(d, "%c", c);
+ else
+ btf_dump_printf(d, "\\x%02x", (__u8)c);
+ }
+
+ btf_dump_printf(d, "\"");
+
+ return 0;
+}
+
static int btf_dump_array_data(struct btf_dump *d,
const struct btf_type *t,
__u32 id,
@@ -2055,8 +2105,13 @@ static int btf_dump_array_data(struct btf_dump *d,
* char arrays, so if size is 1 and element is
* printable as a char, we'll do that.
*/
- if (elem_size == 1)
+ if (elem_size == 1) {
+ if (d->typed_dump->emit_strings &&
+ btf_dump_string_data(d, t, id, data) == 0) {
+ return 0;
+ }
d->typed_dump->is_array_char = true;
+ }
}
/* note that we increment depth before calling btf_dump_print() below;
@@ -2544,6 +2599,7 @@ int btf_dump__dump_type_data(struct btf_dump *d, __u32 id,
d->typed_dump->compact = OPTS_GET(opts, compact, false);
d->typed_dump->skip_names = OPTS_GET(opts, skip_names, false);
d->typed_dump->emit_zeroes = OPTS_GET(opts, emit_zeroes, false);
+ d->typed_dump->emit_strings = OPTS_GET(opts, emit_strings, false);
ret = btf_dump_dump_type_data(d, NULL, t, id, data, 0, 0);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e9c641a2fb20..aee36402f0a3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -597,7 +597,7 @@ struct extern_desc {
int sym_idx;
int btf_id;
int sec_btf_id;
- const char *name;
+ char *name;
char *essent_name;
bool is_set;
bool is_weak;
@@ -4259,7 +4259,9 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
return ext->btf_id;
}
t = btf__type_by_id(obj->btf, ext->btf_id);
- ext->name = btf__name_by_offset(obj->btf, t->name_off);
+ ext->name = strdup(btf__name_by_offset(obj->btf, t->name_off));
+ if (!ext->name)
+ return -ENOMEM;
ext->sym_idx = i;
ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
@@ -9138,8 +9140,10 @@ void bpf_object__close(struct bpf_object *obj)
zfree(&obj->btf_custom_path);
zfree(&obj->kconfig);
- for (i = 0; i < obj->nr_extern; i++)
+ for (i = 0; i < obj->nr_extern; i++) {
+ zfree(&obj->externs[i].name);
zfree(&obj->externs[i].essent_name);
+ }
zfree(&obj->externs);
obj->nr_extern = 0;
@@ -12838,6 +12842,34 @@ struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifi
}
struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+ const struct bpf_cgroup_opts *opts)
+{
+ LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
+ __u32 relative_id;
+ int relative_fd;
+
+ if (!OPTS_VALID(opts, bpf_cgroup_opts))
+ return libbpf_err_ptr(-EINVAL);
+
+ relative_id = OPTS_GET(opts, relative_id, 0);
+ relative_fd = OPTS_GET(opts, relative_fd, 0);
+
+ if (relative_fd && relative_id) {
+ pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n",
+ prog->name);
+ return libbpf_err_ptr(-EINVAL);
+ }
+
+ link_create_opts.cgroup.expected_revision = OPTS_GET(opts, expected_revision, 0);
+ link_create_opts.cgroup.relative_fd = relative_fd;
+ link_create_opts.cgroup.relative_id = relative_id;
+ link_create_opts.flags = OPTS_GET(opts, flags, 0);
+
+ return bpf_program_attach_fd(prog, cgroup_fd, "cgroup", &link_create_opts);
+}
+
+struct bpf_link *
bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex,
const struct bpf_tcx_opts *opts)
{
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1137e7d2e1b5..d1cf813a057b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -877,6 +877,21 @@ LIBBPF_API struct bpf_link *
bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex,
const struct bpf_netkit_opts *opts);
+struct bpf_cgroup_opts {
+ /* size of this struct, for forward/backward compatibility */
+ size_t sz;
+ __u32 flags;
+ __u32 relative_fd;
+ __u32 relative_id;
+ __u64 expected_revision;
+ size_t :0;
+};
+#define bpf_cgroup_opts__last_field expected_revision
+
+LIBBPF_API struct bpf_link *
+bpf_program__attach_cgroup_opts(const struct bpf_program *prog, int cgroup_fd,
+ const struct bpf_cgroup_opts *opts);
+
struct bpf_map;
LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 1205f9a4fe04..c7fc0bde5648 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -437,6 +437,7 @@ LIBBPF_1.6.0 {
bpf_linker__add_fd;
bpf_linker__new_fd;
bpf_object__prepare;
+ bpf_program__attach_cgroup_opts;
bpf_program__func_info;
bpf_program__func_info_cnt;
bpf_program__line_info;
diff --git a/tools/lib/bpf/usdt.c b/tools/lib/bpf/usdt.c
index 4e4a52742b01..3373b9d45ac4 100644
--- a/tools/lib/bpf/usdt.c
+++ b/tools/lib/bpf/usdt.c
@@ -59,7 +59,7 @@
*
* STAP_PROBE3(my_usdt_provider, my_usdt_probe_name, 123, x, &y);
*
- * USDT is identified by it's <provider-name>:<probe-name> pair of names. Each
+ * USDT is identified by its <provider-name>:<probe-name> pair of names. Each
* individual USDT has a fixed number of arguments (3 in the above example)
* and specifies values of each argument as if it was a function call.
*
@@ -81,7 +81,7 @@
* NOP instruction that kernel can replace with an interrupt instruction to
* trigger instrumentation code (BPF program for all that we care about).
*
- * Semaphore above is and optional feature. It records an address of a 2-byte
+ * Semaphore above is an optional feature. It records an address of a 2-byte
* refcount variable (normally in '.probes' ELF section) used for signaling if
* there is anything that is attached to USDT. This is useful for user
* applications if, for example, they need to prepare some arguments that are
@@ -121,7 +121,7 @@
* a uprobe BPF program (which for kernel, at least currently, is just a kprobe
* program, so BPF_PROG_TYPE_KPROBE program type). With the only difference
* that uprobe is usually attached at the function entry, while USDT will
- * normally will be somewhere inside the function. But it should always be
+ * normally be somewhere inside the function. But it should always be
* pointing to NOP instruction, which makes such uprobes the fastest uprobe
* kind.
*
@@ -151,7 +151,7 @@
* libbpf sets to spec ID during attach time, or, if kernel is too old to
* support BPF cookie, through IP-to-spec-ID map that libbpf maintains in such
* case. The latter means that some modes of operation can't be supported
- * without BPF cookie. Such mode is attaching to shared library "generically",
+ * without BPF cookie. Such a mode is attaching to shared library "generically",
* without specifying target process. In such case, it's impossible to
* calculate absolute IP addresses for IP-to-spec-ID map, and thus such mode
* is not supported without BPF cookie support.
@@ -185,7 +185,7 @@
* as even if USDT spec string is the same, USDT cookie value can be
* different. It was deemed excessive to try to deduplicate across independent
* USDT attachments by taking into account USDT spec string *and* USDT cookie
- * value, which would complicated spec ID accounting significantly for little
+ * value, which would complicate spec ID accounting significantly for little
* gain.
*/
diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index 55b59f6c79b8..61deb5923067 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -231,14 +231,7 @@ class NlMsg:
self.extack['unknown'].append(extack)
if attr_space:
- # We don't have the ability to parse nests yet, so only do global
- if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
- miss_type = self.extack['miss-type']
- if miss_type in attr_space.attrs_by_val:
- spec = attr_space.attrs_by_val[miss_type]
- self.extack['miss-type'] = spec['name']
- if 'doc' in spec:
- self.extack['miss-type-doc'] = spec['doc']
+ self.annotate_extack(attr_space)
def _decode_policy(self, raw):
policy = {}
@@ -264,6 +257,18 @@ class NlMsg:
policy['mask'] = attr.as_scalar('u64')
return policy
+ def annotate_extack(self, attr_space):
+ """ Make extack more human friendly with attribute information """
+
+ # We don't have the ability to parse nests yet, so only do global
+ if 'miss-type' in self.extack and 'miss-nest' not in self.extack:
+ miss_type = self.extack['miss-type']
+ if miss_type in attr_space.attrs_by_val:
+ spec = attr_space.attrs_by_val[miss_type]
+ self.extack['miss-type'] = spec['name']
+ if 'doc' in spec:
+ self.extack['miss-type-doc'] = spec['doc']
+
def cmd(self):
return self.nl_type
@@ -277,12 +282,12 @@ class NlMsg:
class NlMsgs:
- def __init__(self, data, attr_space=None):
+ def __init__(self, data):
self.msgs = []
offset = 0
while offset < len(data):
- msg = NlMsg(data, offset, attr_space=attr_space)
+ msg = NlMsg(data, offset)
offset += msg.nl_len
self.msgs.append(msg)
@@ -1034,12 +1039,13 @@ class YnlFamily(SpecFamily):
op_rsp = []
while not done:
reply = self.sock.recv(self._recv_size)
- nms = NlMsgs(reply, attr_space=op.attr_set)
+ nms = NlMsgs(reply)
self._recv_dbg_print(reply, nms)
for nl_msg in nms:
if nl_msg.nl_seq in reqs_by_seq:
(op, vals, req_msg, req_flags) = reqs_by_seq[nl_msg.nl_seq]
if nl_msg.extack:
+ nl_msg.annotate_extack(op.attr_set)
self._decode_extack(req_msg, op, nl_msg.extack, vals)
else:
op = None
diff --git a/tools/perf/Documentation/perf-amd-ibs.txt b/tools/perf/Documentation/perf-amd-ibs.txt
index 55f80beae037..548549935760 100644
--- a/tools/perf/Documentation/perf-amd-ibs.txt
+++ b/tools/perf/Documentation/perf-amd-ibs.txt
@@ -171,23 +171,48 @@ Below is a simple example of the perf mem tool.
# perf mem report
A normal perf mem report output will provide detailed memory access profile.
-However, it can also be aggregated based on output fields. For example:
-
- # perf mem report -F mem,sample,snoop
- Samples: 3M of event 'ibs_op//', Event count (approx.): 23524876
- Memory access Samples Snoop
- N/A 1903343 N/A
- L1 hit 1056754 N/A
- L2 hit 75231 N/A
- L3 hit 9496 HitM
- L3 hit 2270 N/A
- RAM hit 8710 N/A
- Remote node, same socket RAM hit 3241 N/A
- Remote core, same node Any cache hit 1572 HitM
- Remote core, same node Any cache hit 514 N/A
- Remote node, same socket Any cache hit 1216 HitM
- Remote node, same socket Any cache hit 350 N/A
- Uncached hit 18 N/A
+New output fields will show related access info together. For example:
+
+ # perf mem report -F overhead,cache,snoop,comm
+ ...
+ # Samples: 92K of event 'ibs_op//'
+ # Total weight : 531104
+ #
+ # ---------- Cache ----------- --- Snoop ----
+ # Overhead L1 L2 L1-buf Other HitM Other Command
+ # ........ ............................ .............. ..........
+ #
+ 76.07% 5.8% 35.7% 0.0% 34.6% 23.3% 52.8% cc1
+ 5.79% 0.2% 0.0% 0.0% 5.6% 0.1% 5.7% make
+ 5.78% 0.1% 4.4% 0.0% 1.2% 0.5% 5.3% gcc
+ 5.33% 0.3% 3.9% 0.0% 1.1% 0.2% 5.2% as
+ 5.00% 0.1% 3.8% 0.0% 1.0% 0.3% 4.7% sh
+ 1.56% 0.1% 0.1% 0.0% 1.4% 0.6% 0.9% ld
+ 0.28% 0.1% 0.0% 0.0% 0.2% 0.1% 0.2% pkg-config
+ 0.09% 0.0% 0.0% 0.0% 0.1% 0.0% 0.1% git
+ 0.03% 0.0% 0.0% 0.0% 0.0% 0.0% 0.0% rm
+ ...
+
+Also, it can be aggregated based on various memory access info using the
+sort keys. For example:
+
+ # perf mem report -s mem,snoop
+ ...
+ # Samples: 92K of event 'ibs_op//'
+ # Total weight : 531104
+ # Sort order : mem,snoop
+ #
+ # Overhead Samples Memory access Snoop
+ # ........ ............ ....................................... ............
+ #
+ 47.99% 1509 L2 hit N/A
+ 25.08% 338 core, same node Any cache hit HitM
+ 10.24% 54374 N/A N/A
+ 6.77% 35938 L1 hit N/A
+ 6.39% 101 core, same node Any cache hit N/A
+ 3.50% 69 RAM hit N/A
+ 0.03% 158 LFB/MAB hit N/A
+ 0.00% 2 Uncached hit N/A
Please refer to their man page for more detail.
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 965e73d37772..4d164836d094 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -119,6 +119,22 @@ REPORT OPTIONS
And the default sort keys are changed to local_weight, mem, sym, dso,
symbol_daddr, dso_daddr, snoop, tlb, locked, blocked, local_ins_lat.
+-F::
+--fields=::
+ Specify output field - multiple keys can be specified in CSV format.
+ Please see linkperf:perf-report[1] for details.
+
+ In addition to the default fields, 'perf mem report' will provide the
+ following fields to break down sample periods.
+
+ - op: operation in the sample instruction (load, store, prefetch, ...)
+ - cache: location in CPU cache (L1, L2, ...) where the sample hit
+ - mem: location in memory or other places the sample hit
+ - dtlb: location in Data TLB (L1, L2) where the sample hit
+ - snoop: snoop result for the sampled data access
+
+ Please take a look at the OUTPUT FIELD SELECTION section for caveats.
+
-T::
--type-profile::
Show data-type profile result instead of code symbols. This requires
@@ -156,6 +172,40 @@ but one sample with weight 180 and the other with weight 20:
90% [k] memcpy
10% [.] strcmp
+OUTPUT FIELD SELECTION
+----------------------
+"perf mem report" adds a number of new output fields specific to data source
+information in the sample. Some of them have the same name with the existing
+sort keys ("mem" and "snoop"). So unlike other fields and sort keys, they'll
+behave differently when it's used by -F/--fields or -s/--sort.
+
+Using those two as output fields will aggregate samples altogether and show
+breakdown.
+
+ $ perf mem report -F mem,snoop
+ ...
+ # ------ Memory ------- --- Snoop ----
+ # RAM Uncach Other HitM Other
+ # ..................... ..............
+ #
+ 3.5% 0.0% 96.5% 25.1% 74.9%
+
+But using the same name for sort keys will aggregate samples for each type
+separately.
+
+ $ perf mem report -s mem,snoop
+ # Overhead Samples Memory access Snoop
+ # ........ ............ ....................................... ............
+ #
+ 47.99% 1509 L2 hit N/A
+ 25.08% 338 core, same node Any cache hit HitM
+ 10.24% 54374 N/A N/A
+ 6.77% 35938 L1 hit N/A
+ 6.39% 101 core, same node Any cache hit N/A
+ 3.50% 69 RAM hit N/A
+ 0.03% 158 LFB/MAB hit N/A
+ 0.00% 2 Uncached hit N/A
+
SEE ALSO
--------
linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-arm-spe[1]
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fdf133c9520f..d2d6d7f3ea33 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -18,7 +18,6 @@
#include <stdlib.h>
#include <linux/compiler.h>
#include <linux/kernel.h>
-#include <linux/prctl.h>
#include <linux/zalloc.h>
#include <sys/time.h>
#include <sys/mman.h>
diff --git a/tools/perf/bench/futex.c b/tools/perf/bench/futex.c
index 26382e4d8d4c..4c4fee107e59 100644
--- a/tools/perf/bench/futex.c
+++ b/tools/perf/bench/futex.c
@@ -2,11 +2,18 @@
#include <err.h>
#include <stdio.h>
#include <stdlib.h>
-#include <linux/prctl.h>
#include <sys/prctl.h>
#include "futex.h"
+#ifndef PR_FUTEX_HASH
+#define PR_FUTEX_HASH 78
+# define PR_FUTEX_HASH_SET_SLOTS 1
+# define FH_FLAG_IMMUTABLE (1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS 2
+# define PR_FUTEX_HASH_GET_IMMUTABLE 3
+#endif // PR_FUTEX_HASH
+
void futex_set_nbuckets_param(struct bench_futex_parameters *params)
{
unsigned long flags;
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index e9fab20e9330..8085e4d1d8af 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -186,7 +186,7 @@ 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_\(erms\|orig\))" -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/x86/include/asm/amd/ibs.h '-I "^#include .*/msr-index.h"'
check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"'
check include/linux/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"'
check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"'
diff --git a/tools/perf/tests/shell/stat+event_uniquifying.sh b/tools/perf/tests/shell/stat+event_uniquifying.sh
index 5ec35c52b7d9..bf54bd6c3e2e 100755
--- a/tools/perf/tests/shell/stat+event_uniquifying.sh
+++ b/tools/perf/tests/shell/stat+event_uniquifying.sh
@@ -9,7 +9,8 @@ perf_tool=perf
err=0
test_event_uniquifying() {
- # We use `clockticks` to verify the uniquify behavior.
+ # We use `clockticks` in `uncore_imc` to verify the uniquify behavior.
+ pmu="uncore_imc"
event="clockticks"
# If the `-A` option is added, the event should be uniquified.
@@ -43,11 +44,18 @@ test_event_uniquifying() {
echo "stat event uniquifying test"
uniquified_event_array=()
+ # Skip if the machine does not have `uncore_imc` device.
+ if ! ${perf_tool} list pmu | grep -q ${pmu}; then
+ echo "Target does not support PMU ${pmu} [Skipped]"
+ err=2
+ return
+ fi
+
# Check how many uniquified events.
while IFS= read -r line; do
uniquified_event=$(echo "$line" | awk '{print $1}')
uniquified_event_array+=("${uniquified_event}")
- done < <(${perf_tool} list -v ${event} | grep "\[Kernel PMU event\]")
+ done < <(${perf_tool} list -v ${event} | grep ${pmu})
perf_command="${perf_tool} stat -e $event -A -o ${stat_output} -- true"
$perf_command
diff --git a/tools/perf/tests/tests-scripts.c b/tools/perf/tests/tests-scripts.c
index 1d5759d08141..3a2a8438f9af 100644
--- a/tools/perf/tests/tests-scripts.c
+++ b/tools/perf/tests/tests-scripts.c
@@ -260,6 +260,7 @@ static void append_scripts_in_dir(int dir_fd,
continue; /* Skip scripts that have a separate driver. */
fd = openat(dir_fd, ent->d_name, O_PATH);
append_scripts_in_dir(fd, result, result_sz);
+ close(fd);
}
for (i = 0; i < n_dirs; i++) /* Clean up */
zfree(&entlist[i]);
diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h
index c3322eb3d686..3b262487ec06 100644
--- a/tools/perf/trace/beauty/include/linux/socket.h
+++ b/tools/perf/trace/beauty/include/linux/socket.h
@@ -168,7 +168,7 @@ static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr
return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
}
-static inline size_t msg_data_left(struct msghdr *msg)
+static inline size_t msg_data_left(const struct msghdr *msg)
{
return iov_iter_count(&msg->msg_iter);
}
diff --git a/tools/perf/trace/beauty/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index e762e1af650c..0098b0ce8ccb 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
@@ -361,6 +361,7 @@ typedef int __bitwise __kernel_rwf_t;
#define PAGE_IS_PFNZERO (1 << 5)
#define PAGE_IS_HUGE (1 << 6)
#define PAGE_IS_SOFT_DIRTY (1 << 7)
+#define PAGE_IS_GUARD (1 << 8)
/*
* struct page_region - Page region with flags
diff --git a/tools/perf/trace/beauty/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 15c18ef4eb11..43dec6eed559 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
@@ -364,4 +364,11 @@ struct prctl_mm_map {
# define PR_TIMER_CREATE_RESTORE_IDS_ON 1
# define PR_TIMER_CREATE_RESTORE_IDS_GET 2
+/* FUTEX hash management */
+#define PR_FUTEX_HASH 78
+# define PR_FUTEX_HASH_SET_SLOTS 1
+# define FH_FLAG_IMMUTABLE (1ULL << 0)
+# define PR_FUTEX_HASH_GET_SLOTS 2
+# define PR_FUTEX_HASH_GET_IMMUTABLE 3
+
#endif /* _LINUX_PRCTL_H */
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
index f78ee3670dd5..1686861aae20 100644
--- a/tools/perf/trace/beauty/include/uapi/linux/stat.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -182,8 +182,12 @@ struct statx {
/* File offset alignment for direct I/O reads */
__u32 stx_dio_read_offset_align;
- /* 0xb8 */
- __u64 __spare3[9]; /* Spare space for future expansion */
+ /* Optimised max atomic write unit in bytes */
+ __u32 stx_atomic_write_unit_max_opt;
+ __u32 __spare2[1];
+
+ /* 0xc0 */
+ __u64 __spare3[8]; /* Spare space for future expansion */
/* 0x100 */
};
diff --git a/tools/perf/util/include/linux/linkage.h b/tools/perf/util/include/linux/linkage.h
index 178b00205fe6..89979ca23c3f 100644
--- a/tools/perf/util/include/linux/linkage.h
+++ b/tools/perf/util/include/linux/linkage.h
@@ -132,4 +132,8 @@
SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
#endif
+#ifndef SYM_PIC_ALIAS
+#define SYM_PIC_ALIAS(sym) SYM_ALIAS(__pi_ ## sym, sym, SYM_T_FUNC, SYM_L_GLOBAL)
+#endif
+
#endif /* PERF_LINUX_LINKAGE_H_ */
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index a786cbfb0ff5..83aaf7cda635 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -268,6 +268,7 @@ bool is_event_supported(u8 type, u64 config)
ret = evsel__open(evsel, NULL, tmap) >= 0;
}
+ evsel__close(evsel);
evsel__delete(evsel);
}
diff --git a/tools/power/cpupower/Makefile b/tools/power/cpupower/Makefile
index be8dfac14076..c43db1c41205 100644
--- a/tools/power/cpupower/Makefile
+++ b/tools/power/cpupower/Makefile
@@ -73,6 +73,7 @@ sbindir ?= /usr/sbin
mandir ?= /usr/man
libdir ?= /usr/lib
libexecdir ?= /usr/libexec
+unitdir ?= /usr/lib/systemd/system
includedir ?= /usr/include
localedir ?= /usr/share/locale
docdir ?= /usr/share/doc/packages/cpupower
@@ -309,9 +310,9 @@ install-tools: $(OUTPUT)cpupower
$(INSTALL_DATA) cpupower-service.conf '$(DESTDIR)${confdir}'
$(INSTALL) -d $(DESTDIR)${libexecdir}
$(INSTALL_PROGRAM) cpupower.sh '$(DESTDIR)${libexecdir}/cpupower'
- $(INSTALL) -d $(DESTDIR)${libdir}/systemd/system
- sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
- $(SETPERM_DATA) '$(DESTDIR)${libdir}/systemd/system/cpupower.service'
+ $(INSTALL) -d $(DESTDIR)${unitdir}
+ sed 's|___CDIR___|${confdir}|; s|___LDIR___|${libexecdir}|' cpupower.service.in > '$(DESTDIR)${unitdir}/cpupower.service'
+ $(SETPERM_DATA) '$(DESTDIR)${unitdir}/cpupower.service'
install-man:
$(INSTALL_DATA) -D man/cpupower.1 $(DESTDIR)${mandir}/man1/cpupower.1
@@ -348,7 +349,7 @@ uninstall:
- rm -f $(DESTDIR)${bindir}/utils/cpupower
- rm -f $(DESTDIR)${confdir}cpupower-service.conf
- rm -f $(DESTDIR)${libexecdir}/cpupower
- - rm -f $(DESTDIR)${libdir}/systemd/system/cpupower.service
+ - rm -f $(DESTDIR)${unitdir}/cpupower.service
- rm -f $(DESTDIR)${mandir}/man1/cpupower.1
- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-set.1
- rm -f $(DESTDIR)${mandir}/man1/cpupower-frequency-info.1
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index e2a2c46c008b..3d8378972d26 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -21,7 +21,6 @@ test_lirc_mode2_user
flow_dissector_load
test_tcpnotify_user
test_libbpf
-test_sysctl
xdping
test_cpp
*.d
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index cf5ed3bee573..4863106034df 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -73,7 +73,7 @@ endif
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_progs \
test_sockmap \
- test_tcpnotify_user test_sysctl \
+ test_tcpnotify_user \
test_progs-no_alu32
TEST_INST_SUBDIRS := no_alu32
@@ -109,6 +109,7 @@ TEST_PROGS := test_kmod.sh \
test_xdping.sh \
test_bpftool_build.sh \
test_bpftool.sh \
+ test_bpftool_map.sh \
test_bpftool_metadata.sh \
test_doc_build.sh \
test_xsk.sh \
@@ -220,7 +221,7 @@ ifeq ($(VMLINUX_BTF),)
$(error Cannot find a vmlinux for VMLINUX_BTF at any of "$(VMLINUX_BTF_PATHS)")
endif
-# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
+# Define simple and short `make test_progs`, `make test_maps`, etc targets
# to build individual tests.
# NOTE: Semicolon at the end is critical to override lib.mk's default static
# rule for binaries.
@@ -329,7 +330,6 @@ NETWORK_HELPERS := $(OUTPUT)/network_helpers.o
$(OUTPUT)/test_sockmap: $(CGROUP_HELPERS) $(TESTING_HELPERS)
$(OUTPUT)/test_tcpnotify_user: $(CGROUP_HELPERS) $(TESTING_HELPERS) $(TRACE_HELPERS)
$(OUTPUT)/test_sock_fields: $(CGROUP_HELPERS) $(TESTING_HELPERS)
-$(OUTPUT)/test_sysctl: $(CGROUP_HELPERS) $(TESTING_HELPERS)
$(OUTPUT)/test_tag: $(TESTING_HELPERS)
$(OUTPUT)/test_lirc_mode2_user: $(TESTING_HELPERS)
$(OUTPUT)/xdping: $(TESTING_HELPERS)
@@ -841,6 +841,11 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
$(call msg,BINARY,,$@)
$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
+# This works around GCC warning about snprintf truncating strings like:
+#
+# char a[PATH_MAX], b[PATH_MAX];
+# snprintf(a, "%s/foo", b); // triggers -Wformat-truncation
+$(OUTPUT)/veristat.o: CFLAGS += -Wno-format-truncation
$(OUTPUT)/veristat.o: $(BPFOBJ)
$(OUTPUT)/veristat: $(OUTPUT)/veristat.o
$(call msg,BINARY,,$@)
diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
index 8215c9b3115e..9386dfe8b884 100644
--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
+++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
@@ -69,7 +69,7 @@ extern int bpf_get_file_xattr(struct file *file, const char *name,
struct bpf_dynptr *value_ptr) __ksym;
extern int bpf_get_fsverity_digest(struct file *file, struct bpf_dynptr *digest_ptr) __ksym;
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
extern void bpf_key_put(struct bpf_key *key) __ksym;
extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
diff --git a/tools/testing/selftests/bpf/config.ppc64el b/tools/testing/selftests/bpf/config.ppc64el
new file mode 100644
index 000000000000..9acf389dc4ce
--- /dev/null
+++ b/tools/testing/selftests/bpf/config.ppc64el
@@ -0,0 +1,93 @@
+CONFIG_ALTIVEC=y
+CONFIG_AUDIT=y
+CONFIG_BLK_CGROUP=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BONDING=y
+CONFIG_BPF_JIT_ALWAYS_ON=y
+CONFIG_BPF_PRELOAD_UMD=y
+CONFIG_BPF_PRELOAD=y
+CONFIG_CGROUP_CPUACCT=y
+CONFIG_CGROUP_DEVICE=y
+CONFIG_CGROUP_FREEZER=y
+CONFIG_CGROUP_HUGETLB=y
+CONFIG_CGROUP_NET_CLASSID=y
+CONFIG_CGROUP_PERF=y
+CONFIG_CGROUP_PIDS=y
+CONFIG_CGROUP_SCHED=y
+CONFIG_CGROUPS=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1"
+CONFIG_CPU_LITTLE_ENDIAN=y
+CONFIG_CPUSETS=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_FS=y
+CONFIG_DETECT_HUNG_TASK=y
+CONFIG_DEVTMPFS_MOUNT=y
+CONFIG_DEVTMPFS=y
+CONFIG_EXPERT=y
+CONFIG_EXT4_FS_POSIX_ACL=y
+CONFIG_EXT4_FS_SECURITY=y
+CONFIG_EXT4_FS=y
+CONFIG_FRAME_POINTER=y
+CONFIG_FRAME_WARN=1280
+CONFIG_HARDLOCKUP_DETECTOR=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_HUGETLBFS=y
+CONFIG_HVC_CONSOLE=y
+CONFIG_INET=y
+CONFIG_IP_ADVANCED_ROUTER=y
+CONFIG_IP_MULTICAST=y
+CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IPV6_SEG6_LWTUNNEL=y
+CONFIG_JUMP_LABEL=y
+CONFIG_KALLSYMS_ALL=y
+CONFIG_KPROBES=y
+CONFIG_MEMCG=y
+CONFIG_NAMESPACES=y
+CONFIG_NET_ACT_BPF=y
+CONFIG_NETDEVICES=y
+CONFIG_NETFILTER_XT_MATCH_BPF=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_NET=y
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NONPORTABLE=y
+CONFIG_NR_CPUS=256
+CONFIG_PACKET=y
+CONFIG_PANIC_ON_OOPS=y
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCI=y
+CONFIG_POSIX_MQUEUE=y
+CONFIG_PPC64=y
+CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
+CONFIG_PPC_PSERIES=y
+CONFIG_PPC_RADIX_MMU=y
+CONFIG_PRINTK_TIME=y
+CONFIG_PROC_KCORE=y
+CONFIG_PROFILING=y
+CONFIG_RCU_CPU_STALL_TIMEOUT=60
+CONFIG_RT_GROUP_SCHED=y
+CONFIG_SECTION_MISMATCH_WARN_ONLY=y
+CONFIG_SECURITY_NETWORK=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_SMP=y
+CONFIG_SOC_VIRT=y
+CONFIG_SYSVIPC=y
+CONFIG_TCP_CONG_ADVANCED=y
+CONFIG_THREAD_SHIFT=14
+CONFIG_TLS=y
+CONFIG_TMPFS_POSIX_ACL=y
+CONFIG_TMPFS=y
+CONFIG_TUN=y
+CONFIG_UNIX=y
+CONFIG_UPROBES=y
+CONFIG_USER_NS=y
+CONFIG_VETH=y
+CONFIG_VLAN_8021Q=y
+CONFIG_VSOCKETS_LOOPBACK=y
+CONFIG_VSX=y
+CONFIG_XFRM_USER=y
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
index 6befa870434b..4a0670c056ba 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_cookie.c
@@ -489,10 +489,28 @@ cleanup:
bpf_link__destroy(link);
}
+static int verify_tracing_link_info(int fd, u64 cookie)
+{
+ struct bpf_link_info info;
+ int err;
+ u32 len = sizeof(info);
+
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_TRACING, "link_type"))
+ return -1;
+
+ ASSERT_EQ(info.tracing.cookie, cookie, "tracing_cookie");
+
+ return 0;
+}
+
static void tracing_subtest(struct test_bpf_cookie *skel)
{
__u64 cookie;
- int prog_fd;
+ int prog_fd, err;
int fentry_fd = -1, fexit_fd = -1, fmod_ret_fd = -1;
LIBBPF_OPTS(bpf_test_run_opts, opts);
LIBBPF_OPTS(bpf_link_create_opts, link_opts);
@@ -507,6 +525,10 @@ static void tracing_subtest(struct test_bpf_cookie *skel)
if (!ASSERT_GE(fentry_fd, 0, "fentry.link_create"))
goto cleanup;
+ err = verify_tracing_link_info(fentry_fd, cookie);
+ if (!ASSERT_OK(err, "verify_tracing_link_info"))
+ goto cleanup;
+
cookie = 0x20000000000000L;
prog_fd = bpf_program__fd(skel->progs.fexit_test1);
link_opts.tracing.cookie = cookie;
@@ -635,10 +657,29 @@ cleanup:
bpf_link__destroy(link);
}
+static int verify_raw_tp_link_info(int fd, u64 cookie)
+{
+ struct bpf_link_info info;
+ int err;
+ u32 len = sizeof(info);
+
+ memset(&info, 0, sizeof(info));
+ err = bpf_link_get_info_by_fd(fd, &info, &len);
+ if (!ASSERT_OK(err, "get_link_info"))
+ return -1;
+
+ if (!ASSERT_EQ(info.type, BPF_LINK_TYPE_RAW_TRACEPOINT, "link_type"))
+ return -1;
+
+ ASSERT_EQ(info.raw_tracepoint.cookie, cookie, "raw_tp_cookie");
+
+ return 0;
+}
+
static void raw_tp_subtest(struct test_bpf_cookie *skel)
{
__u64 cookie;
- int prog_fd, link_fd = -1;
+ int err, prog_fd, link_fd = -1;
struct bpf_link *link = NULL;
LIBBPF_OPTS(bpf_raw_tp_opts, raw_tp_opts);
LIBBPF_OPTS(bpf_raw_tracepoint_opts, opts);
@@ -656,6 +697,11 @@ static void raw_tp_subtest(struct test_bpf_cookie *skel)
goto cleanup;
usleep(1); /* trigger */
+
+ err = verify_raw_tp_link_info(link_fd, cookie);
+ if (!ASSERT_OK(err, "verify_raw_tp_link_info"))
+ goto cleanup;
+
close(link_fd); /* detach */
link_fd = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
index fe2c502e5089..ecc3d47919ad 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_mod_race.c
@@ -78,7 +78,7 @@ static int test_setup_uffd(void *fault_addr)
}
uffd_register.range.start = (unsigned long)fault_addr;
- uffd_register.range.len = 4096;
+ uffd_register.range.len = getpagesize();
uffd_register.mode = UFFDIO_REGISTER_MODE_MISSING;
if (ioctl(uffd, UFFDIO_REGISTER, &uffd_register)) {
close(uffd);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index c0a776feec23..82903585c870 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -879,6 +879,122 @@ static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
"static int bpf_cgrp_storage_busy = (int)2", 2);
}
+struct btf_dump_string_ctx {
+ struct btf *btf;
+ struct btf_dump *d;
+ char *str;
+ struct btf_dump_type_data_opts *opts;
+ int array_id;
+};
+
+static int btf_dump_one_string(struct btf_dump_string_ctx *ctx,
+ char *ptr, size_t ptr_sz,
+ const char *expected_val)
+{
+ size_t type_sz;
+ int ret;
+
+ ctx->str[0] = '\0';
+ type_sz = btf__resolve_size(ctx->btf, ctx->array_id);
+ ret = btf_dump__dump_type_data(ctx->d, ctx->array_id, ptr, ptr_sz, ctx->opts);
+ if (type_sz <= ptr_sz) {
+ if (!ASSERT_EQ(ret, type_sz, "failed/unexpected type_sz"))
+ return -EINVAL;
+ }
+ if (!ASSERT_STREQ(ctx->str, expected_val, "ensure expected/actual match"))
+ return -EFAULT;
+ return 0;
+}
+
+static void btf_dump_strings(struct btf_dump_string_ctx *ctx)
+{
+ struct btf_dump_type_data_opts *opts = ctx->opts;
+
+ opts->emit_strings = true;
+
+ opts->compact = true;
+ opts->emit_zeroes = false;
+
+ opts->skip_names = false;
+ btf_dump_one_string(ctx, "foo", 4, "(char[4])\"foo\"");
+
+ opts->skip_names = true;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* This should have no effect. */
+ opts->emit_zeroes = false;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* This should have no effect. */
+ opts->compact = false;
+ btf_dump_one_string(ctx, "foo", 4, "\"foo\"");
+
+ /* Non-printable characters come out as hex. */
+ btf_dump_one_string(ctx, "fo\xff", 4, "\"fo\\xff\"");
+ btf_dump_one_string(ctx, "fo\x7", 4, "\"fo\\x07\"");
+
+ /*
+ * Strings that are too long for the specified type ("char[4]")
+ * should fall back to the current behavior.
+ */
+ opts->compact = true;
+ btf_dump_one_string(ctx, "abcde", 6, "['a','b','c','d',]");
+
+ /*
+ * Strings that are too short for the specified type ("char[4]")
+ * should work normally.
+ */
+ btf_dump_one_string(ctx, "ab", 3, "\"ab\"");
+
+ /* Non-NUL-terminated arrays don't get printed as strings. */
+ char food[4] = { 'f', 'o', 'o', 'd' };
+ char bye[3] = { 'b', 'y', 'e' };
+
+ btf_dump_one_string(ctx, food, 4, "['f','o','o','d',]");
+ btf_dump_one_string(ctx, bye, 3, "['b','y','e',]");
+
+ /* The embedded NUL should terminate the string. */
+ char embed[4] = { 'f', 'o', '\0', 'd' };
+
+ btf_dump_one_string(ctx, embed, 4, "\"fo\"");
+}
+
+static void test_btf_dump_string_data(void)
+{
+ struct test_ctx t = {};
+ char str[STRSIZE];
+ struct btf_dump *d;
+ DECLARE_LIBBPF_OPTS(btf_dump_type_data_opts, opts);
+ struct btf_dump_string_ctx ctx;
+ int char_id, int_id, array_id;
+
+ if (test_ctx__init(&t))
+ return;
+
+ d = btf_dump__new(t.btf, btf_dump_snprintf, str, NULL);
+ if (!ASSERT_OK_PTR(d, "could not create BTF dump"))
+ return;
+
+ /* Generate BTF for a four-element char array. */
+ char_id = btf__add_int(t.btf, "char", 1, BTF_INT_CHAR);
+ ASSERT_EQ(char_id, 1, "char_id");
+ int_id = btf__add_int(t.btf, "int", 4, BTF_INT_SIGNED);
+ ASSERT_EQ(int_id, 2, "int_id");
+ array_id = btf__add_array(t.btf, int_id, char_id, 4);
+ ASSERT_EQ(array_id, 3, "array_id");
+
+ ctx.btf = t.btf;
+ ctx.d = d;
+ ctx.str = str;
+ ctx.opts = &opts;
+ ctx.array_id = array_id;
+
+ btf_dump_strings(&ctx);
+
+ btf_dump__free(d);
+ test_ctx__free(&t);
+}
+
static void test_btf_datasec(struct btf *btf, struct btf_dump *d, char *str,
const char *name, const char *expected_val,
void *data, size_t data_sz)
@@ -970,6 +1086,8 @@ void test_btf_dump() {
test_btf_dump_struct_data(btf, d, str);
if (test__start_subtest("btf_dump: var_data"))
test_btf_dump_var_data(btf, d, str);
+ if (test__start_subtest("btf_dump: string_data"))
+ test_btf_dump_string_data();
btf_dump__free(d);
btf__free(btf);
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
new file mode 100644
index 000000000000..bb60704a3ef9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_opts.c
@@ -0,0 +1,617 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_mprog.skel.h"
+
+static void assert_mprog_count(int cg, int atype, int expected)
+{
+ __u32 count = 0, attach_flags = 0;
+ int err;
+
+ err = bpf_prog_query(cg, atype, 0, &attach_flags,
+ NULL, &count);
+ ASSERT_EQ(count, expected, "count");
+ ASSERT_EQ(err, 0, "prog_query");
+}
+
+static void test_prog_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+ LIBBPF_OPTS(bpf_prog_query_opts, optq);
+ __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+ struct cgroup_mprog *skel;
+ __u32 prog_ids[10];
+ int cg, err;
+
+ cg = test__join_cgroup("/prog_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /prog_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ id1 = id_from_prog_fd(fd1);
+ id2 = id_from_prog_fd(fd2);
+ id3 = id_from_prog_fd(fd3);
+ id4 = id_from_prog_fd(fd4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd2, fd1] */
+ err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd2, fd3, fd1] */
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ /* retrieve optq.prog_cnt */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ /* optq.prog_cnt will be used in below query */
+ memset(prog_ids, 0, sizeof(prog_ids));
+ optq.prog_ids = prog_ids;
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ ASSERT_EQ(optq.count, 4, "count");
+ ASSERT_EQ(optq.revision, 5, "revision");
+ ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+ ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+ ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+ ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+ ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+ ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+ optd.expected_revision = 5;
+ err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ LIBBPF_OPTS_RESET(optd);
+ err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 2);
+
+ /* Check revision after two detach operations */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ ASSERT_OK(err, "prog_query");
+ ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+ err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_link_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_cgroup_opts, opta);
+ LIBBPF_OPTS(bpf_cgroup_opts, optd);
+ LIBBPF_OPTS(bpf_prog_query_opts, optq);
+ struct bpf_link *link1, *link2, *link3, *link4;
+ __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4;
+ struct cgroup_mprog *skel;
+ __u32 prog_ids[10];
+ int cg, err;
+
+ cg = test__join_cgroup("/link_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /link_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ id1 = id_from_prog_fd(fd1);
+ id2 = id_from_prog_fd(fd2);
+ id3 = id_from_prog_fd(fd3);
+ id4 = id_from_prog_fd(fd4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+ if (!ASSERT_OK_PTR(link1, "link_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_BEFORE | BPF_F_LINK,
+ .relative_id = id_from_link_fd(bpf_link__fd(link1)),
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd2, fd1] */
+ link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+ if (!ASSERT_OK_PTR(link2, "link_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER | BPF_F_LINK,
+ .relative_fd = bpf_link__fd(link2),
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd2, fd3, fd1] */
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_OK_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+ if (!ASSERT_OK_PTR(link4, "link_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ /* retrieve optq.prog_cnt */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ /* optq.prog_cnt will be used in below query */
+ memset(prog_ids, 0, sizeof(prog_ids));
+ optq.prog_ids = prog_ids;
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ if (!ASSERT_OK(err, "prog_query"))
+ goto cleanup4;
+
+ ASSERT_EQ(optq.count, 4, "count");
+ ASSERT_EQ(optq.revision, 5, "revision");
+ ASSERT_EQ(optq.prog_ids[0], id2, "prog_ids[0]");
+ ASSERT_EQ(optq.prog_ids[1], id3, "prog_ids[1]");
+ ASSERT_EQ(optq.prog_ids[2], id1, "prog_ids[2]");
+ ASSERT_EQ(optq.prog_ids[3], id4, "prog_ids[3]");
+ ASSERT_EQ(optq.prog_ids[4], 0, "prog_ids[4]");
+ ASSERT_EQ(optq.link_ids, NULL, "link_ids");
+
+cleanup4:
+ bpf_link__destroy(link4);
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ bpf_link__destroy(link3);
+ assert_mprog_count(cg, atype, 2);
+
+ /* Check revision after two detach operations */
+ err = bpf_prog_query_opts(cg, atype, &optq);
+ ASSERT_OK(err, "prog_query");
+ ASSERT_EQ(optq.revision, 7, "revision");
+
+cleanup2:
+ bpf_link__destroy(link2);
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ bpf_link__destroy(link1);
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_preorder_prog_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ LIBBPF_OPTS(bpf_prog_detach_opts, optd);
+ __u32 fd1, fd2, fd3, fd4;
+ struct cgroup_mprog *skel;
+ int cg, err;
+
+ cg = test__join_cgroup("/preorder_prog_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_prog_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+ fd3 = bpf_program__fd(skel->progs.getsockopt_3);
+ fd4 = bpf_program__fd(skel->progs.getsockopt_4);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_PREORDER,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd1, fd2] */
+ err = bpf_prog_attach_opts(fd2, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, -EINVAL, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_PREORDER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd1, fd2, fd3] */
+ err = bpf_prog_attach_opts(fd3, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ err = bpf_prog_attach_opts(fd4, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ err = bpf_prog_detach_opts(fd4, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ err = bpf_prog_detach_opts(fd3, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+ err = bpf_prog_detach_opts(fd2, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ err = bpf_prog_detach_opts(fd1, cg, atype, &optd);
+ ASSERT_OK(err, "prog_detach");
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_preorder_link_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_cgroup_opts, opta);
+ struct bpf_link *link1, *link2, *link3, *link4;
+ struct cgroup_mprog *skel;
+ __u32 fd2;
+ int cg;
+
+ cg = test__join_cgroup("/preorder_link_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /preorder_link_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 1,
+ );
+
+ /* ordering: [fd1] */
+ link1 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_1, cg, &opta);
+ if (!ASSERT_OK_PTR(link1, "link_attach"))
+ goto cleanup;
+
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_PREORDER,
+ .expected_revision = 2,
+ );
+
+ /* ordering: [fd1, fd2] */
+ link2 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_2, cg, &opta);
+ if (!ASSERT_OK_PTR(link2, "link_attach"))
+ goto cleanup1;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER,
+ .relative_fd = fd2,
+ .expected_revision = 3,
+ );
+
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_ERR_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 2);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_AFTER | BPF_F_PREORDER | BPF_F_LINK,
+ .relative_fd = bpf_link__fd(link2),
+ .expected_revision = 3,
+ );
+
+ /* ordering: [fd1, fd2, fd3] */
+ link3 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_3, cg, &opta);
+ if (!ASSERT_OK_PTR(link3, "link_attach"))
+ goto cleanup2;
+
+ assert_mprog_count(cg, atype, 3);
+
+ LIBBPF_OPTS_RESET(opta,
+ .expected_revision = 4,
+ );
+
+ /* ordering: [fd2, fd3, fd1, fd4] */
+ link4 = bpf_program__attach_cgroup_opts(skel->progs.getsockopt_4, cg, &opta);
+ if (!ASSERT_OK_PTR(link4, "prog_attach"))
+ goto cleanup3;
+
+ assert_mprog_count(cg, atype, 4);
+
+ bpf_link__destroy(link4);
+ assert_mprog_count(cg, atype, 3);
+
+cleanup3:
+ bpf_link__destroy(link3);
+ assert_mprog_count(cg, atype, 2);
+
+cleanup2:
+ bpf_link__destroy(link2);
+ assert_mprog_count(cg, atype, 1);
+
+cleanup1:
+ bpf_link__destroy(link1);
+ assert_mprog_count(cg, atype, 0);
+
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+static void test_invalid_attach_detach(int atype)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opta);
+ __u32 fd1, fd2, id2;
+ struct cgroup_mprog *skel;
+ int cg, err;
+
+ cg = test__join_cgroup("/invalid_attach_detach");
+ if (!ASSERT_GE(cg, 0, "join_cgroup /invalid_attach_detach"))
+ return;
+
+ skel = cgroup_mprog__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "skel_load"))
+ goto cleanup;
+
+ fd1 = bpf_program__fd(skel->progs.getsockopt_1);
+ fd2 = bpf_program__fd(skel->progs.getsockopt_2);
+
+ id2 = id_from_prog_fd(fd2);
+
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_ID,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER | BPF_F_ID,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE | BPF_F_AFTER,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_LINK,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ .relative_id = id2,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE,
+ .relative_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ .relative_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -ENOENT, "prog_attach");
+ assert_mprog_count(cg, atype, 0);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ if (!ASSERT_EQ(err, 0, "prog_attach"))
+ goto cleanup;
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_AFTER,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 1);
+
+ LIBBPF_OPTS_RESET(opta,
+ .flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE | BPF_F_AFTER,
+ .replace_prog_fd = fd1,
+ );
+
+ err = bpf_prog_attach_opts(fd1, cg, atype, &opta);
+ ASSERT_EQ(err, -EINVAL, "prog_attach");
+ assert_mprog_count(cg, atype, 1);
+cleanup:
+ cgroup_mprog__destroy(skel);
+ close(cg);
+}
+
+void test_cgroup_mprog_opts(void)
+{
+ if (test__start_subtest("prog_attach_detach"))
+ test_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("link_attach_detach"))
+ test_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("preorder_prog_attach_detach"))
+ test_preorder_prog_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("preorder_link_attach_detach"))
+ test_preorder_link_attach_detach(BPF_CGROUP_GETSOCKOPT);
+ if (test__start_subtest("invalid_attach_detach"))
+ test_invalid_attach_detach(BPF_CGROUP_GETSOCKOPT);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
new file mode 100644
index 000000000000..a36d2e968bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_mprog_ordering.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "cgroup_helpers.h"
+#include "cgroup_preorder.skel.h"
+
+static int run_getsockopt_test(int cg_parent, int sock_fd, bool has_relative_fd)
+{
+ LIBBPF_OPTS(bpf_prog_attach_opts, opts);
+ enum bpf_attach_type prog_p_atype, prog_p2_atype;
+ int prog_p_fd, prog_p2_fd;
+ struct cgroup_preorder *skel = NULL;
+ struct bpf_program *prog;
+ __u8 *result, buf;
+ socklen_t optlen = 1;
+ int err = 0;
+
+ skel = cgroup_preorder__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "cgroup_preorder__open_and_load"))
+ return 0;
+
+ LIBBPF_OPTS_RESET(opts);
+ opts.flags = BPF_F_ALLOW_MULTI;
+ prog = skel->progs.parent;
+ prog_p_fd = bpf_program__fd(prog);
+ prog_p_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p_fd, cg_parent, prog_p_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent"))
+ goto close_skel;
+
+ opts.flags = BPF_F_ALLOW_MULTI | BPF_F_BEFORE;
+ if (has_relative_fd)
+ opts.relative_fd = prog_p_fd;
+ prog = skel->progs.parent_2;
+ prog_p2_fd = bpf_program__fd(prog);
+ prog_p2_atype = bpf_program__expected_attach_type(prog);
+ err = bpf_prog_attach_opts(prog_p2_fd, cg_parent, prog_p2_atype, &opts);
+ if (!ASSERT_OK(err, "bpf_prog_attach_opts-parent_2"))
+ goto detach_parent;
+
+ err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen);
+ if (!ASSERT_OK(err, "getsockopt"))
+ goto detach_parent_2;
+
+ result = skel->bss->result;
+ ASSERT_TRUE(result[0] == 4 && result[1] == 3, "result values");
+
+detach_parent_2:
+ ASSERT_OK(bpf_prog_detach2(prog_p2_fd, cg_parent, prog_p2_atype),
+ "bpf_prog_detach2-parent_2");
+detach_parent:
+ ASSERT_OK(bpf_prog_detach2(prog_p_fd, cg_parent, prog_p_atype),
+ "bpf_prog_detach2-parent");
+close_skel:
+ cgroup_preorder__destroy(skel);
+ return err;
+}
+
+void test_cgroup_mprog_ordering(void)
+{
+ int cg_parent = -1, sock_fd = -1;
+
+ cg_parent = test__join_cgroup("/parent");
+ if (!ASSERT_GE(cg_parent, 0, "join_cgroup /parent"))
+ goto out;
+
+ sock_fd = socket(AF_INET, SOCK_STREAM, 0);
+ if (!ASSERT_GE(sock_fd, 0, "socket"))
+ goto out;
+
+ ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, false), "getsockopt_test_1");
+ ASSERT_OK(run_getsockopt_test(cg_parent, sock_fd, true), "getsockopt_test_2");
+
+out:
+ close(sock_fd);
+ close(cg_parent);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c
index 9add890c2d37..241b2c8c6e0f 100644
--- a/tools/testing/selftests/bpf/prog_tests/fd_array.c
+++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c
@@ -312,7 +312,7 @@ static void check_fd_array_cnt__referenced_btfs(void)
/* btf should still exist when original file descriptor is closed */
err = get_btf_id_by_fd(extra_fds[0], &btf_id);
- if (!ASSERT_GE(err, 0, "get_btf_id_by_fd"))
+ if (!ASSERT_EQ(err, 0, "get_btf_id_by_fd"))
goto cleanup;
Close(extra_fds[0]);
diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c
index 169ce689b97c..d6f14a232002 100644
--- a/tools/testing/selftests/bpf/prog_tests/log_buf.c
+++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c
@@ -7,6 +7,10 @@
#include "test_log_buf.skel.h"
#include "bpf_util.h"
+#if !defined(__clang__)
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+#endif
+
static size_t libbpf_log_pos;
static char libbpf_log_buf[1024 * 1024];
static bool libbpf_log_error;
diff --git a/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
new file mode 100644
index 000000000000..40d4f687bd9c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/mem_rdonly_untrusted.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <test_progs.h>
+#include "mem_rdonly_untrusted.skel.h"
+
+void test_mem_rdonly_untrusted(void)
+{
+ RUN_TESTS(mem_rdonly_untrusted);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index da430df45aa4..d1e4cb28a72c 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -97,7 +97,7 @@ static void ringbuf_write_subtest(void)
if (!ASSERT_OK_PTR(skel, "skel_open"))
return;
- skel->maps.ringbuf.max_entries = 0x4000;
+ skel->maps.ringbuf.max_entries = 0x40000;
err = test_ringbuf_write_lskel__load(skel);
if (!ASSERT_OK(err, "skel_load"))
@@ -108,7 +108,7 @@ static void ringbuf_write_subtest(void)
mmap_ptr = mmap(NULL, page_size, PROT_READ | PROT_WRITE, MAP_SHARED, rb_fd, 0);
if (!ASSERT_OK_PTR(mmap_ptr, "rw_cons_pos"))
goto cleanup;
- *mmap_ptr = 0x3000;
+ *mmap_ptr = 0x30000;
ASSERT_OK(munmap(mmap_ptr, page_size), "unmap_rw");
skel->bss->pid = getpid();
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 1d98eee7a2c3..f1bdccc7e4e7 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -924,6 +924,8 @@ static void redir_partial(int family, int sotype, int sock_map, int parser_map)
goto close;
n = xsend(c1, buf, sizeof(buf), 0);
+ if (n == -1)
+ goto close;
if (n < sizeof(buf))
FAIL("incomplete write");
diff --git a/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
new file mode 100644
index 000000000000..35af8044d059
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/string_kfuncs.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include <test_progs.h>
+#include "string_kfuncs_success.skel.h"
+#include "string_kfuncs_failure1.skel.h"
+#include "string_kfuncs_failure2.skel.h"
+#include <sys/mman.h>
+
+static const char * const test_cases[] = {
+ "strcmp",
+ "strchr",
+ "strchrnul",
+ "strnchr",
+ "strrchr",
+ "strlen",
+ "strnlen",
+ "strspn_str",
+ "strspn_accept",
+ "strcspn_str",
+ "strcspn_reject",
+ "strstr",
+ "strnstr",
+};
+
+void run_too_long_tests(void)
+{
+ struct string_kfuncs_failure2 *skel;
+ struct bpf_program *prog;
+ char test_name[256];
+ int err, i;
+
+ skel = string_kfuncs_failure2__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "string_kfuncs_failure2__open_and_load"))
+ return;
+
+ memset(skel->bss->long_str, 'a', sizeof(skel->bss->long_str));
+
+ for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+ sprintf(test_name, "test_%s_too_long", test_cases[i]);
+ if (!test__start_subtest(test_name))
+ continue;
+
+ prog = bpf_object__find_program_by_name(skel->obj, test_name);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto cleanup;
+
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+ err = bpf_prog_test_run_opts(bpf_program__fd(prog), &topts);
+ if (!ASSERT_OK(err, "bpf_prog_test_run"))
+ goto cleanup;
+
+ ASSERT_EQ(topts.retval, -E2BIG, "reading too long string fails with -E2BIG");
+ }
+
+cleanup:
+ string_kfuncs_failure2__destroy(skel);
+}
+
+void test_string_kfuncs(void)
+{
+ RUN_TESTS(string_kfuncs_success);
+ RUN_TESTS(string_kfuncs_failure1);
+
+ run_too_long_tests();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 66a900327f91..0ab36503c3b2 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -1195,7 +1195,7 @@ static void test_tailcall_hierarchy_count(const char *which, bool test_fentry,
bool test_fexit,
bool test_fentry_entry)
{
- int err, map_fd, prog_fd, main_data_fd, fentry_data_fd, fexit_data_fd, i, val;
+ int err, map_fd, prog_fd, main_data_fd, fentry_data_fd = 0, fexit_data_fd = 0, i, val;
struct bpf_object *obj = NULL, *fentry_obj = NULL, *fexit_obj = NULL;
struct bpf_link *fentry_link = NULL, *fexit_link = NULL;
struct bpf_program *prog, *fentry_prog;
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
index 924d0e25320c..d52a62af77bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h
@@ -8,34 +8,6 @@
# define loopback 1
#endif
-static inline __u32 id_from_prog_fd(int fd)
-{
- struct bpf_prog_info prog_info = {};
- __u32 prog_info_len = sizeof(prog_info);
- int err;
-
- err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len);
- if (!ASSERT_OK(err, "id_from_prog_fd"))
- return 0;
-
- ASSERT_NEQ(prog_info.id, 0, "prog_info.id");
- return prog_info.id;
-}
-
-static inline __u32 id_from_link_fd(int fd)
-{
- struct bpf_link_info link_info = {};
- __u32 link_info_len = sizeof(link_info);
- int err;
-
- err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
- if (!ASSERT_OK(err, "id_from_link_fd"))
- return 0;
-
- ASSERT_NEQ(link_info.id, 0, "link_info.id");
- return link_info.id;
-}
-
static inline __u32 ifindex_from_link_fd(int fd)
{
struct bpf_link_info link_info = {};
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
index bcdbd27f22f0..273dd41ca09e 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_sysctl.c
@@ -1,22 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2019 Facebook
-#include <fcntl.h>
-#include <stdint.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <linux/filter.h>
-
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include <bpf/bpf_endian.h>
-#include "bpf_util.h"
+#include "test_progs.h"
#include "cgroup_helpers.h"
-#include "testing_helpers.h"
#define CG_PATH "/foo"
#define MAX_INSNS 512
@@ -1608,26 +1594,19 @@ static int run_tests(int cgfd)
return fails ? -1 : 0;
}
-int main(int argc, char **argv)
+void test_sysctl(void)
{
- int cgfd = -1;
- int err = 0;
+ int cgfd;
cgfd = cgroup_setup_and_join(CG_PATH);
- if (cgfd < 0)
- goto err;
+ if (!ASSERT_OK_FD(cgfd < 0, "create_cgroup"))
+ goto out;
- /* Use libbpf 1.0 API mode */
- libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+ if (!ASSERT_OK(run_tests(cgfd), "run_tests"))
+ goto out;
- if (run_tests(cgfd))
- goto err;
-
- goto out;
-err:
- err = -1;
out:
close(cgfd);
cleanup_cgroup_environment();
- return err;
+ return;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_veristat.c b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
index 47b56c258f3f..367f47e4a936 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_veristat.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_veristat.c
@@ -60,13 +60,19 @@ static void test_set_global_vars_succeeds(void)
" -G \"var_s8 = -128\" "\
" -G \"var_u8 = 255\" "\
" -G \"var_ea = EA2\" "\
- " -G \"var_eb = EB2\" "\
- " -G \"var_ec = EC2\" "\
+ " -G \"var_eb = EB2\" "\
+ " -G \"var_ec=EC2\" "\
" -G \"var_b = 1\" "\
- " -G \"struct1.struct2.u.var_u8 = 170\" "\
+ " -G \"struct1[2].struct2[1][2].u.var_u8[2]=170\" "\
" -G \"union1.struct3.var_u8_l = 0xaa\" "\
" -G \"union1.struct3.var_u8_h = 0xaa\" "\
- "-vl2 > %s", fix->veristat, fix->tmpfile);
+ " -G \"arr[3]= 171\" " \
+ " -G \"arr[EA2] =172\" " \
+ " -G \"enum_arr[EC2]=EA3\" " \
+ " -G \"three_d[31][7][EA2]=173\"" \
+ " -G \"struct1[2].struct2[1][2].u.mat[5][3]=174\" " \
+ " -G \"struct11 [ 7 ] [ 5 ] .struct2[0][1].u.mat[3][0] = 175\" " \
+ " -vl2 > %s", fix->veristat, fix->tmpfile);
read(fix->fd, fix->output, fix->sz);
__CHECK_STR("_w=0xf000000000000001 ", "var_s64 = 0xf000000000000001");
@@ -81,8 +87,14 @@ static void test_set_global_vars_succeeds(void)
__CHECK_STR("_w=12 ", "var_eb = EB2");
__CHECK_STR("_w=13 ", "var_ec = EC2");
__CHECK_STR("_w=1 ", "var_b = 1");
- __CHECK_STR("_w=170 ", "struct1.struct2.u.var_u8 = 170");
+ __CHECK_STR("_w=170 ", "struct1[2].struct2[1][2].u.var_u8[2]=170");
__CHECK_STR("_w=0xaaaa ", "union1.var_u16 = 0xaaaa");
+ __CHECK_STR("_w=171 ", "arr[3]= 171");
+ __CHECK_STR("_w=172 ", "arr[EA2] =172");
+ __CHECK_STR("_w=10 ", "enum_arr[EC2]=EA3");
+ __CHECK_STR("_w=173 ", "matrix[31][7][11]=173");
+ __CHECK_STR("_w=174 ", "struct1[2].struct2[1][2].u.mat[5][3]=174");
+ __CHECK_STR("_w=175 ", "struct11[7][5].struct2[0][1].u.mat[3][0]=175");
out:
teardown_fixture(fix);
@@ -129,6 +141,95 @@ out:
teardown_fixture(fix);
}
+static void test_unsupported_ptr_array_type(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"ptr_arr[0] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Can't set ptr_arr[0]. Only ints and enums are supported", "ptr_arr");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_out_of_bounds(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr[99] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Array index 99 is out of bounds", "arr[99]");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_index_not_found(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr[EG2] = 0\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ read(fix->fd, fix->output, fix->sz);
+ __CHECK_STR("Can't resolve enum value EG2", "arr[EG2]");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_array_index_for_non_array(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"var_b[0] = 1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Array index is not expected for var_b", "var_b[0] = 1");
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"union1.struct3[0].var_u8_l=1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Array index is not expected for struct3", "union1.struct3[0].var_u8_l=1");
+
+out:
+ teardown_fixture(fix);
+}
+
+static void test_no_array_index_for_array(void)
+{
+ struct fixture *fix = init_fixture();
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"arr = 1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Can't set arr. Only ints and enums are supported", "arr = 1");
+
+ SYS_FAIL(out,
+ "%s set_global_vars.bpf.o -G \"struct1[0].struct2.u.var_u8[2]=1\" -vl2 2> %s",
+ fix->veristat, fix->tmpfile);
+
+ pread(fix->fd, fix->output, fix->sz, 0);
+ __CHECK_STR("Can't resolve field u for non-composite type", "struct1[0].struct2.u.var_u8[2]=1");
+
+out:
+ teardown_fixture(fix);
+}
+
void test_veristat(void)
{
if (test__start_subtest("set_global_vars_succeeds"))
@@ -139,6 +240,22 @@ void test_veristat(void)
if (test__start_subtest("set_global_vars_from_file_succeeds"))
test_set_global_vars_from_file_succeeds();
+
+ if (test__start_subtest("test_unsupported_ptr_array_type"))
+ test_unsupported_ptr_array_type();
+
+ if (test__start_subtest("test_array_out_of_bounds"))
+ test_array_out_of_bounds();
+
+ if (test__start_subtest("test_array_index_not_found"))
+ test_array_index_not_found();
+
+ if (test__start_subtest("test_array_index_for_non_array"))
+ test_array_index_for_non_array();
+
+ if (test__start_subtest("test_no_array_index_for_array"))
+ test_no_array_index_for_array();
+
}
#undef __CHECK_STR
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
index 495d66414b57..9057e983cc54 100644
--- a/tools/testing/selftests/bpf/prog_tests/usdt.c
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -270,8 +270,16 @@ static void subtest_multispec_usdt(void)
*/
trigger_300_usdts();
- /* we'll reuse usdt_100 BPF program for usdt_300 test */
bpf_link__destroy(skel->links.usdt_100);
+
+ bss->usdt_100_called = 0;
+ bss->usdt_100_sum = 0;
+
+ /* If built with arm64/clang, there will be much less number of specs
+ * for usdt_300 call sites.
+ */
+#if !defined(__aarch64__) || !defined(__clang__)
+ /* we'll reuse usdt_100 BPF program for usdt_300 test */
skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1, "/proc/self/exe",
"test", "usdt_300", NULL);
err = -errno;
@@ -282,13 +290,11 @@ static void subtest_multispec_usdt(void)
/* let's check that there are no "dangling" BPF programs attached due
* to partial success of the above test:usdt_300 attachment
*/
- bss->usdt_100_called = 0;
- bss->usdt_100_sum = 0;
-
f300(777); /* this is 301st instance of usdt_300 */
ASSERT_EQ(bss->usdt_100_called, 0, "usdt_301_called");
ASSERT_EQ(bss->usdt_100_sum, 0, "usdt_301_sum");
+#endif
/* This time we have USDT with 400 inlined invocations, but arg specs
* should be the same across all sites, so libbpf will only need to
diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
index d424e7ecbd12..9fd3ae987321 100644
--- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
@@ -21,8 +21,7 @@
#include "../progs/test_user_ringbuf.h"
static const long c_sample_size = sizeof(struct sample) + BPF_RINGBUF_HDR_SZ;
-static const long c_ringbuf_size = 1 << 12; /* 1 small page */
-static const long c_max_entries = c_ringbuf_size / c_sample_size;
+static long c_ringbuf_size, c_max_entries;
static void drain_current_samples(void)
{
@@ -424,7 +423,9 @@ static void test_user_ringbuf_loop(void)
uint32_t remaining_samples = total_samples;
int err;
- BUILD_BUG_ON(total_samples <= c_max_entries);
+ if (!ASSERT_LT(c_max_entries, total_samples, "compare_c_max_entries"))
+ return;
+
err = load_skel_create_user_ringbuf(&skel, &ringbuf);
if (err)
return;
@@ -686,6 +687,9 @@ void test_user_ringbuf(void)
{
int i;
+ c_ringbuf_size = getpagesize(); /* 1 page */
+ c_max_entries = c_ringbuf_size / c_sample_size;
+
for (i = 0; i < ARRAY_SIZE(success_tests); i++) {
if (!test__start_subtest(success_tests[i].test_name))
continue;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index b2b2d85dbb1b..43264347e7d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -37,21 +37,26 @@ static void test_xdp_adjust_tail_shrink(void)
bpf_object__close(obj);
}
-static void test_xdp_adjust_tail_grow(void)
+static void test_xdp_adjust_tail_grow(bool is_64k_pagesize)
{
const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
struct bpf_object *obj;
- char buf[4096]; /* avoid segfault: large buf to hold grow results */
+ char buf[8192]; /* avoid segfault: large buf to hold grow results */
__u32 expect_sz;
int err, prog_fd;
LIBBPF_OPTS(bpf_test_run_opts, topts,
.data_in = &pkt_v4,
- .data_size_in = sizeof(pkt_v4),
.data_out = buf,
.data_size_out = sizeof(buf),
.repeat = 1,
);
+ /* topts.data_size_in as a special signal to bpf prog */
+ if (is_64k_pagesize)
+ topts.data_size_in = sizeof(pkt_v4) - 1;
+ else
+ topts.data_size_in = sizeof(pkt_v4);
+
err = bpf_prog_test_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
if (!ASSERT_OK(err, "test_xdp_adjust_tail_grow"))
return;
@@ -208,7 +213,7 @@ out:
bpf_object__close(obj);
}
-static void test_xdp_adjust_frags_tail_grow(void)
+static void test_xdp_adjust_frags_tail_grow_4k(void)
{
const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
__u32 exp_size;
@@ -246,14 +251,20 @@ static void test_xdp_adjust_frags_tail_grow(void)
ASSERT_EQ(topts.retval, XDP_TX, "9Kb+10b retval");
ASSERT_EQ(topts.data_size_out, exp_size, "9Kb+10b size");
- for (i = 0; i < 9000; i++)
- ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+ for (i = 0; i < 9000; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-old");
+ }
- for (i = 9000; i < 9010; i++)
- ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+ for (i = 9000; i < 9010; i++) {
+ if (buf[i] != 0)
+ ASSERT_EQ(buf[i], 0, "9Kb+10b-new");
+ }
- for (i = 9010; i < 16384; i++)
- ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+ for (i = 9010; i < 16384; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "9Kb+10b-untouched");
+ }
/* Test a too large grow */
memset(buf, 1, 16384);
@@ -273,16 +284,93 @@ out:
bpf_object__close(obj);
}
+static void test_xdp_adjust_frags_tail_grow_64k(void)
+{
+ const char *file = "./test_xdp_adjust_tail_grow.bpf.o";
+ __u32 exp_size;
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int err, i, prog_fd;
+ __u8 *buf;
+ LIBBPF_OPTS(bpf_test_run_opts, topts);
+
+ obj = bpf_object__open(file);
+ if (libbpf_get_error(obj))
+ return;
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+ goto out;
+
+ prog_fd = bpf_program__fd(prog);
+
+ buf = malloc(262144);
+ if (!ASSERT_OK_PTR(buf, "alloc buf 256Kb"))
+ goto out;
+
+ /* Test case add 10 bytes to last frag */
+ memset(buf, 1, 262144);
+ exp_size = 90000 + 10;
+
+ topts.data_in = buf;
+ topts.data_out = buf;
+ topts.data_size_in = 90000;
+ topts.data_size_out = 262144;
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+ ASSERT_OK(err, "90Kb+10b");
+ ASSERT_EQ(topts.retval, XDP_TX, "90Kb+10b retval");
+ ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+ for (i = 0; i < 90000; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "90Kb+10b-old");
+ }
+
+ for (i = 90000; i < 90010; i++) {
+ if (buf[i] != 0)
+ ASSERT_EQ(buf[i], 0, "90Kb+10b-new");
+ }
+
+ for (i = 90010; i < 262144; i++) {
+ if (buf[i] != 1)
+ ASSERT_EQ(buf[i], 1, "90Kb+10b-untouched");
+ }
+
+ /* Test a too large grow */
+ memset(buf, 1, 262144);
+ exp_size = 90001;
+
+ topts.data_in = topts.data_out = buf;
+ topts.data_size_in = 90001;
+ topts.data_size_out = 262144;
+ err = bpf_prog_test_run_opts(prog_fd, &topts);
+
+ ASSERT_OK(err, "90Kb+10b");
+ ASSERT_EQ(topts.retval, XDP_DROP, "90Kb+10b retval");
+ ASSERT_EQ(topts.data_size_out, exp_size, "90Kb+10b size");
+
+ free(buf);
+out:
+ bpf_object__close(obj);
+}
+
void test_xdp_adjust_tail(void)
{
+ int page_size = getpagesize();
+
if (test__start_subtest("xdp_adjust_tail_shrink"))
test_xdp_adjust_tail_shrink();
if (test__start_subtest("xdp_adjust_tail_grow"))
- test_xdp_adjust_tail_grow();
+ test_xdp_adjust_tail_grow(page_size == 65536);
if (test__start_subtest("xdp_adjust_tail_grow2"))
test_xdp_adjust_tail_grow2();
if (test__start_subtest("xdp_adjust_frags_tail_shrink"))
test_xdp_adjust_frags_tail_shrink();
- if (test__start_subtest("xdp_adjust_frags_tail_grow"))
- test_xdp_adjust_frags_tail_grow();
+ if (test__start_subtest("xdp_adjust_frags_tail_grow")) {
+ if (page_size == 65536)
+ test_xdp_adjust_frags_tail_grow_64k();
+ else
+ test_xdp_adjust_frags_tail_grow_4k();
+ }
}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
index 7dac044664ac..dd34b0cc4b4e 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c
@@ -66,16 +66,25 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int fd)
#else
#define MAX_PKT_SIZE 3408
#endif
+
+#define PAGE_SIZE_4K 4096
+#define PAGE_SIZE_64K 65536
+
static void test_max_pkt_size(int fd)
{
- char data[MAX_PKT_SIZE + 1] = {};
+ char data[PAGE_SIZE_64K + 1] = {};
int err;
DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts,
.data_in = &data,
- .data_size_in = MAX_PKT_SIZE,
.flags = BPF_F_TEST_XDP_LIVE_FRAMES,
.repeat = 1,
);
+
+ if (getpagesize() == PAGE_SIZE_64K)
+ opts.data_size_in = MAX_PKT_SIZE + PAGE_SIZE_64K - PAGE_SIZE_4K;
+ else
+ opts.data_size_in = MAX_PKT_SIZE;
+
err = bpf_prog_test_run_opts(fd, &opts);
ASSERT_OK(err, "prog_run_max_size");
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c
new file mode 100644
index 000000000000..2f20485e0de3
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_map_elem.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u32 value_sum = 0;
+
+SEC("iter/bpf_map_elem")
+int dump_bpf_map_values(struct bpf_iter__bpf_map_elem *ctx)
+{
+ __u32 value = 0;
+
+ if (ctx->value == (void *)0)
+ return 0;
+
+ bpf_probe_read_kernel(&value, sizeof(value), ctx->value);
+ value_sum += value;
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 6e208e24ba3b..20dce508d8e0 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -83,9 +83,11 @@
* expect return value to match passed parameter:
* - a decimal number
* - a hexadecimal number, when starts from 0x
- * - literal INT_MIN
- * - literal POINTER_VALUE (see definition below)
- * - literal TEST_DATA_LEN (see definition below)
+ * - a macro which expands to one of the above
+ * - literal _INT_MIN (expands to INT_MIN)
+ * In addition, two special macros are defined below:
+ * - POINTER_VALUE
+ * - TEST_DATA_LEN
* __retval_unpriv Same, but load program in unprivileged mode.
*
* __description Text to be used instead of a program name for display
@@ -125,8 +127,8 @@
#define __success_unpriv __attribute__((btf_decl_tag("comment:test_expect_success_unpriv")))
#define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
#define __flag(flag) __attribute__((btf_decl_tag("comment:test_prog_flags="#flag)))
-#define __retval(val) __attribute__((btf_decl_tag("comment:test_retval="#val)))
-#define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="#val)))
+#define __retval(val) __attribute__((btf_decl_tag("comment:test_retval="XSTR(val))))
+#define __retval_unpriv(val) __attribute__((btf_decl_tag("comment:test_retval_unpriv="XSTR(val))))
#define __auxiliary __attribute__((btf_decl_tag("comment:test_auxiliary")))
#define __auxiliary_unpriv __attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
#define __btf_path(path) __attribute__((btf_decl_tag("comment:test_btf_path=" path)))
@@ -155,7 +157,7 @@
#define __imm_insn(name, expr) [name]"i"(*(long *)&(expr))
/* Magic constants used with __retval() */
-#define POINTER_VALUE 0xcafe4all
+#define POINTER_VALUE 0xbadcafe
#define TEST_DATA_LEN 64
#ifndef __used
@@ -231,4 +233,8 @@
#define CAN_USE_LOAD_ACQ_STORE_REL
#endif
+#if defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)
+#define SPEC_V1
+#endif
+
#endif
diff --git a/tools/testing/selftests/bpf/progs/cgroup_mprog.c b/tools/testing/selftests/bpf/progs/cgroup_mprog.c
new file mode 100644
index 000000000000..6a0ea02c4de2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/cgroup_mprog.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+SEC("cgroup/getsockopt")
+int getsockopt_1(struct bpf_sockopt *ctx)
+{
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_2(struct bpf_sockopt *ctx)
+{
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_3(struct bpf_sockopt *ctx)
+{
+ return 1;
+}
+
+SEC("cgroup/getsockopt")
+int getsockopt_4(struct bpf_sockopt *ctx)
+{
+ return 1;
+}
diff --git a/tools/testing/selftests/bpf/progs/compute_live_registers.c b/tools/testing/selftests/bpf/progs/compute_live_registers.c
index f3d79aecbf93..6884ab99a421 100644
--- a/tools/testing/selftests/bpf/progs/compute_live_registers.c
+++ b/tools/testing/selftests/bpf/progs/compute_live_registers.c
@@ -240,6 +240,22 @@ __naked void if2(void)
::: __clobber_all);
}
+/* Verifier misses that r2 is alive if jset is not handled properly */
+SEC("socket")
+__log_level(2)
+__msg("2: 012....... (45) if r1 & 0x7 goto pc+1")
+__naked void if3_jset_bug(void)
+{
+ asm volatile (
+ "r0 = 1;"
+ "r2 = 2;"
+ "if r1 & 0x7 goto +1;"
+ "exit;"
+ "r0 = r2;"
+ "exit;"
+ ::: __clobber_all);
+}
+
SEC("socket")
__log_level(2)
__msg("0: .......... (b7) r1 = 0")
diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
index 76adf4a8f2da..7dd92a303bf6 100644
--- a/tools/testing/selftests/bpf/progs/iters.c
+++ b/tools/testing/selftests/bpf/progs/iters.c
@@ -1649,4 +1649,281 @@ int clean_live_states(const void *ctx)
return 0;
}
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state(void)
+{
+ /* This is equivalent to C program below.
+ *
+ * r8 = bpf_get_prandom_u32();
+ * r6 = -32;
+ * bpf_iter_num_new(&fp[-8], 0, 10);
+ * if (unlikely(bpf_get_prandom_u32()))
+ * r6 = -31;
+ * while (bpf_iter_num_next(&fp[-8])) {
+ * if (unlikely(bpf_get_prandom_u32()))
+ * *(fp + r6) = 7;
+ * }
+ * bpf_iter_num_destroy(&fp[-8])
+ * return 0
+ */
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r8 = r0;"
+ "r7 = 0;"
+ "r6 = -32;"
+ "r0 = 0;"
+ "*(u64 *)(r10 - 16) = r0;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 10;"
+ "call %[bpf_iter_num_new];"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto change_r6_%=;"
+ "loop_%=:"
+ "call noop;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_next];"
+ "if r0 == 0 goto loop_end_%=;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto use_r6_%=;"
+ "goto loop_%=;"
+ "loop_end_%=:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ "r0 = 0;"
+ "exit;"
+ "use_r6_%=:"
+ "r0 = r10;"
+ "r0 += r6;"
+ "r1 = 7;"
+ "*(u64 *)(r0 + 0) = r1;"
+ "goto loop_%=;"
+ "change_r6_%=:"
+ "r6 = -31;"
+ "goto loop_%=;"
+ :
+ : __imm(bpf_iter_num_new),
+ __imm(bpf_iter_num_next),
+ __imm(bpf_iter_num_destroy),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all
+ );
+}
+
+__used __naked
+static int noop(void)
+{
+ asm volatile (
+ "r0 = 0;"
+ "exit;"
+ );
+}
+
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state2(void)
+{
+ /* This is equivalent to C program below.
+ *
+ * r8 = bpf_get_prandom_u32();
+ * r6 = -32;
+ * bpf_iter_num_new(&fp[-8], 0, 10);
+ * if (unlikely(bpf_get_prandom_u32())) {
+ * r6 = -31;
+ * jump_into_loop:
+ * goto +0;
+ * goto loop;
+ * }
+ * if (unlikely(bpf_get_prandom_u32()))
+ * goto jump_into_loop;
+ * loop:
+ * while (bpf_iter_num_next(&fp[-8])) {
+ * if (unlikely(bpf_get_prandom_u32()))
+ * *(fp + r6) = 7;
+ * }
+ * bpf_iter_num_destroy(&fp[-8])
+ * return 0
+ */
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r8 = r0;"
+ "r7 = 0;"
+ "r6 = -32;"
+ "r0 = 0;"
+ "*(u64 *)(r10 - 16) = r0;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 10;"
+ "call %[bpf_iter_num_new];"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto change_r6_%=;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto jump_into_loop_%=;"
+ "loop_%=:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_next];"
+ "if r0 == 0 goto loop_end_%=;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto use_r6_%=;"
+ "goto loop_%=;"
+ "loop_end_%=:"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ "r0 = 0;"
+ "exit;"
+ "use_r6_%=:"
+ "r0 = r10;"
+ "r0 += r6;"
+ "r1 = 7;"
+ "*(u64 *)(r0 + 0) = r1;"
+ "goto loop_%=;"
+ "change_r6_%=:"
+ "r6 = -31;"
+ "jump_into_loop_%=: "
+ "goto +0;"
+ "goto loop_%=;"
+ :
+ : __imm(bpf_iter_num_new),
+ __imm(bpf_iter_num_next),
+ __imm(bpf_iter_num_destroy),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all
+ );
+}
+
+SEC("?raw_tp")
+__flag(BPF_F_TEST_STATE_FREQ)
+__failure __msg("misaligned stack access off 0+-31+0 size 8")
+__naked int absent_mark_in_the_middle_state3(void)
+{
+ /*
+ * bpf_iter_num_new(&fp[-8], 0, 10)
+ * loop1(-32, &fp[-8])
+ * loop1_wrapper(&fp[-8])
+ * bpf_iter_num_destroy(&fp[-8])
+ */
+ asm volatile (
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 10;"
+ "call %[bpf_iter_num_new];"
+ /* call #1 */
+ "r1 = -32;"
+ "r2 = r10;"
+ "r2 += -8;"
+ "call loop1;"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ /* call #2 */
+ "r1 = r10;"
+ "r1 += -8;"
+ "r2 = 0;"
+ "r3 = 10;"
+ "call %[bpf_iter_num_new];"
+ "r1 = r10;"
+ "r1 += -8;"
+ "call loop1_wrapper;"
+ /* return */
+ "r1 = r10;"
+ "r1 += -8;"
+ "call %[bpf_iter_num_destroy];"
+ "r0 = 0;"
+ "exit;"
+ :
+ : __imm(bpf_iter_num_new),
+ __imm(bpf_iter_num_destroy),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all
+ );
+}
+
+__used __naked
+static int loop1(void)
+{
+ /*
+ * int loop1(num, iter) {
+ * r6 = num;
+ * r7 = iter;
+ * while (bpf_iter_num_next(r7)) {
+ * if (unlikely(bpf_get_prandom_u32()))
+ * *(fp + r6) = 7;
+ * }
+ * return 0
+ * }
+ */
+ asm volatile (
+ "r6 = r1;"
+ "r7 = r2;"
+ "call %[bpf_get_prandom_u32];"
+ "r8 = r0;"
+ "loop_%=:"
+ "r1 = r7;"
+ "call %[bpf_iter_num_next];"
+ "if r0 == 0 goto loop_end_%=;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto use_r6_%=;"
+ "goto loop_%=;"
+ "loop_end_%=:"
+ "r0 = 0;"
+ "exit;"
+ "use_r6_%=:"
+ "r0 = r10;"
+ "r0 += r6;"
+ "r1 = 7;"
+ "*(u64 *)(r0 + 0) = r1;"
+ "goto loop_%=;"
+ :
+ : __imm(bpf_iter_num_next),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all
+ );
+}
+
+__used __naked
+static int loop1_wrapper(void)
+{
+ /*
+ * int loop1_wrapper(iter) {
+ * r6 = -32;
+ * r7 = iter;
+ * if (unlikely(bpf_get_prandom_u32()))
+ * r6 = -31;
+ * loop1(r6, r7);
+ * return 0;
+ * }
+ */
+ asm volatile (
+ "r6 = -32;"
+ "r7 = r1;"
+ "call %[bpf_get_prandom_u32];"
+ "r8 = r0;"
+ "call %[bpf_get_prandom_u32];"
+ "if r0 == r8 goto change_r6_%=;"
+ "loop_%=:"
+ "r1 = r6;"
+ "r2 = r7;"
+ "call loop1;"
+ "r0 = 0;"
+ "exit;"
+ "change_r6_%=:"
+ "r6 = -31;"
+ "goto loop_%=;"
+ :
+ : __imm(bpf_iter_num_next),
+ __imm(bpf_get_prandom_u32)
+ : __clobber_all
+ );
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
new file mode 100644
index 000000000000..00604755e698
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mem_rdonly_untrusted.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include "bpf_misc.h"
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+SEC("socket")
+__success
+__retval(0)
+int ldx_is_ok_bad_addr(void *ctx)
+{
+ char *p;
+
+ if (!bpf_core_enum_value_exists(enum bpf_features, BPF_FEAT_RDONLY_CAST_TO_VOID))
+ return 42;
+
+ p = bpf_rdonly_cast(0, 0);
+ return p[0x7fff];
+}
+
+SEC("socket")
+__success
+__retval(1)
+int ldx_is_ok_good_addr(void *ctx)
+{
+ int v, *p;
+
+ v = 1;
+ p = bpf_rdonly_cast(&v, 0);
+ return *p;
+}
+
+SEC("socket")
+__success
+int offset_not_tracked(void *ctx)
+{
+ int *p, i, s;
+
+ p = bpf_rdonly_cast(0, 0);
+ s = 0;
+ bpf_for(i, 0, 1000 * 1000 * 1000) {
+ p++;
+ s += *p;
+ }
+ return s;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int stx_not_ok(void *ctx)
+{
+ int v, *p;
+
+ v = 1;
+ p = bpf_rdonly_cast(&v, 0);
+ *p = 1;
+ return 0;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int atomic_not_ok(void *ctx)
+{
+ int v, *p;
+
+ v = 1;
+ p = bpf_rdonly_cast(&v, 0);
+ __sync_fetch_and_add(p, 1);
+ return 0;
+}
+
+SEC("socket")
+__failure
+__msg("cannot write into rdonly_untrusted_mem")
+int atomic_rmw_not_ok(void *ctx)
+{
+ long v, *p;
+
+ v = 1;
+ p = bpf_rdonly_cast(&v, 0);
+ return __sync_val_compare_and_swap(p, 0, 42);
+}
+
+SEC("socket")
+__failure
+__msg("invalid access to memory, mem_size=0 off=0 size=4")
+__msg("R1 min value is outside of the allowed memory range")
+int kfunc_param_not_ok(void *ctx)
+{
+ int *p;
+
+ p = bpf_rdonly_cast(0, 0);
+ bpf_kfunc_trusted_num_test(p);
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+__failure
+__msg("R1 type=rdonly_untrusted_mem expected=")
+int helper_param_not_ok(void *ctx)
+{
+ char *p;
+
+ p = bpf_rdonly_cast(0, 0);
+ /*
+ * Any helper with ARG_CONST_SIZE_OR_ZERO constraint will do,
+ * the most permissive constraint
+ */
+ bpf_copy_from_user(p, 0, (void *)42);
+ return 0;
+}
+
+static __noinline u64 *get_some_addr(void)
+{
+ if (bpf_get_prandom_u32())
+ return bpf_rdonly_cast(0, bpf_core_type_id_kernel(struct sock));
+ else
+ return bpf_rdonly_cast(0, 0);
+}
+
+SEC("socket")
+__success
+__retval(0)
+int mixed_mem_type(void *ctx)
+{
+ u64 *p;
+
+ /* Try to avoid compiler hoisting load to if branches by using __noinline func. */
+ p = get_some_addr();
+ return *p;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/rbtree.c b/tools/testing/selftests/bpf/progs/rbtree.c
index a3620c15c136..49fe93d7e059 100644
--- a/tools/testing/selftests/bpf/progs/rbtree.c
+++ b/tools/testing/selftests/bpf/progs/rbtree.c
@@ -61,19 +61,19 @@ static long __add_three(struct bpf_rb_root *root, struct bpf_spin_lock *lock)
}
m->key = 1;
- bpf_spin_lock(&glock);
- bpf_rbtree_add(&groot, &n->node, less);
- bpf_rbtree_add(&groot, &m->node, less);
- bpf_spin_unlock(&glock);
+ bpf_spin_lock(lock);
+ bpf_rbtree_add(root, &n->node, less);
+ bpf_rbtree_add(root, &m->node, less);
+ bpf_spin_unlock(lock);
n = bpf_obj_new(typeof(*n));
if (!n)
return 3;
n->key = 3;
- bpf_spin_lock(&glock);
- bpf_rbtree_add(&groot, &n->node, less);
- bpf_spin_unlock(&glock);
+ bpf_spin_lock(lock);
+ bpf_rbtree_add(root, &n->node, less);
+ bpf_spin_unlock(lock);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
index 43637ee2cdcd..3a868a199349 100644
--- a/tools/testing/selftests/bpf/progs/rcu_read_lock.c
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -16,10 +16,11 @@ struct {
__type(value, long);
} map_a SEC(".maps");
-__u32 user_data, key_serial, target_pid;
+__u32 user_data, target_pid;
+__s32 key_serial;
__u64 flags, task_storage_val, cgroup_id;
-struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
void bpf_key_put(struct bpf_key *key) __ksym;
void bpf_rcu_read_lock(void) __ksym;
void bpf_rcu_read_unlock(void) __ksym;
diff --git a/tools/testing/selftests/bpf/progs/security_bpf_map.c b/tools/testing/selftests/bpf/progs/security_bpf_map.c
new file mode 100644
index 000000000000..7216b3450e96
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/security_bpf_map.c
@@ -0,0 +1,69 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "vmlinux.h"
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+#define EPERM 1 /* Operation not permitted */
+
+/* From include/linux/mm.h. */
+#define FMODE_WRITE 0x2
+
+struct map;
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 1);
+} prot_status_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 3);
+} prot_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __type(key, __u32);
+ __type(value, __u32);
+ __uint(max_entries, 3);
+} not_prot_map SEC(".maps");
+
+SEC("fmod_ret/security_bpf_map")
+int BPF_PROG(fmod_bpf_map, struct bpf_map *map, int fmode)
+{
+ __u32 key = 0;
+ __u32 *status_ptr = bpf_map_lookup_elem(&prot_status_map, &key);
+
+ if (!status_ptr || !*status_ptr)
+ return 0;
+
+ if (map == &prot_map) {
+ /* Allow read-only access */
+ if (fmode & FMODE_WRITE)
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+/*
+ * This program keeps references to maps. This is needed to prevent
+ * optimizing them out.
+ */
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(fentry_dummy1, int a)
+{
+ __u32 key = 0;
+ __u32 val1 = a;
+ __u32 val2 = a + 1;
+
+ bpf_map_update_elem(&prot_map, &key, &val1, BPF_ANY);
+ bpf_map_update_elem(&not_prot_map, &key, &val2, BPF_ANY);
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/set_global_vars.c b/tools/testing/selftests/bpf/progs/set_global_vars.c
index 90f5656c3991..ebaef28b2cb3 100644
--- a/tools/testing/selftests/bpf/progs/set_global_vars.c
+++ b/tools/testing/selftests/bpf/progs/set_global_vars.c
@@ -7,22 +7,30 @@
char _license[] SEC("license") = "GPL";
-enum Enum { EA1 = 0, EA2 = 11 };
+typedef __s32 s32;
+typedef s32 i32;
+typedef __u8 u8;
+
+enum Enum { EA1 = 0, EA2 = 11, EA3 = 10 };
enum Enumu64 {EB1 = 0llu, EB2 = 12llu };
enum Enums64 { EC1 = 0ll, EC2 = 13ll };
const volatile __s64 var_s64 = -1;
const volatile __u64 var_u64 = 0;
-const volatile __s32 var_s32 = -1;
+const volatile i32 var_s32 = -1;
const volatile __u32 var_u32 = 0;
const volatile __s16 var_s16 = -1;
const volatile __u16 var_u16 = 0;
const volatile __s8 var_s8 = -1;
-const volatile __u8 var_u8 = 0;
+const volatile u8 var_u8 = 0;
const volatile enum Enum var_ea = EA1;
const volatile enum Enumu64 var_eb = EB1;
const volatile enum Enums64 var_ec = EC1;
const volatile bool var_b = false;
+const volatile i32 arr[32];
+const volatile enum Enum enum_arr[32];
+const volatile i32 three_d[47][19][17];
+const volatile i32 *ptr_arr[32];
struct Struct {
int:16;
@@ -35,34 +43,38 @@ struct Struct {
volatile struct {
const int:1;
union {
- const volatile __u8 var_u8;
+ const volatile u8 var_u8[3];
const volatile __s16 filler3;
const int:1;
+ s32 mat[7][5];
} u;
};
- } struct2;
+ } struct2[2][4];
};
const volatile __u32 stru = 0; /* same prefix as below */
-const volatile struct Struct struct1 = {.struct2 = {.u = {.var_u8 = 1}}};
+const volatile struct Struct struct1[3];
+const volatile struct Struct struct11[11][7];
-union Union {
- __u16 var_u16;
- struct Struct3 {
- struct {
- __u8 var_u8_l;
- };
+struct Struct3 {
+ struct {
+ u8 var_u8_l;
+ };
+ struct {
struct {
- struct {
- __u8 var_u8_h;
- };
+ u8 var_u8_h;
};
- } struct3;
+ };
};
-const volatile union Union union1 = {.var_u16 = -1};
+typedef struct Struct3 Struct3_t;
-char arr[4] = {0};
+union Union {
+ __u16 var_u16;
+ Struct3_t struct3;
+};
+
+const volatile union Union union1 = {.var_u16 = -1};
SEC("socket")
int test_set_globals(void *ctx)
@@ -81,8 +93,14 @@ int test_set_globals(void *ctx)
a = var_eb;
a = var_ec;
a = var_b;
- a = struct1.struct2.u.var_u8;
+ a = struct1[2].struct2[1][2].u.var_u8[2];
a = union1.var_u16;
+ a = arr[3];
+ a = arr[EA2];
+ a = enum_arr[EC2];
+ a = three_d[31][7][EA2];
+ a = struct1[2].struct2[1][2].u.mat[5][3];
+ a = struct11[7][5].struct2[0][1].u.mat[3][0];
return a;
}
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
new file mode 100644
index 000000000000..53af438bd998
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure1.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <linux/limits.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char *user_ptr = (char *)1;
+char *invalid_kern_ptr = (char *)-1;
+
+/*
+ * When passing userspace pointers, the error code differs based on arch:
+ * -ERANGE on arches with non-overlapping address spaces
+ * -EFAULT on other arches
+ */
+#if defined(__TARGET_ARCH_arm) || defined(__TARGET_ARCH_loongarch) || \
+ defined(__TARGET_ARCH_powerpc) || defined(__TARGET_ARCH_x86)
+#define USER_PTR_ERR -ERANGE
+#else
+#define USER_PTR_ERR -EFAULT
+#endif
+
+/*
+ * On s390, __get_kernel_nofault (used in string kfuncs) returns 0 for NULL and
+ * user_ptr (instead of causing an exception) so the below two groups of tests
+ * are not applicable.
+ */
+#ifndef __TARGET_ARCH_s390
+
+/* Passing NULL to string kfuncs (treated as a userspace ptr) */
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_null1(void *ctx) { return bpf_strcmp(NULL, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strcmp_null2(void *ctx) { return bpf_strcmp("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strchr_null(void *ctx) { return bpf_strchr(NULL, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strchrnul_null(void *ctx) { return bpf_strchrnul(NULL, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strnchr_null(void *ctx) { return bpf_strnchr(NULL, 1, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strrchr_null(void *ctx) { return bpf_strrchr(NULL, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strlen_null(void *ctx) { return bpf_strlen(NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strnlen_null(void *ctx) { return bpf_strnlen(NULL, 1); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strspn_null1(void *ctx) { return bpf_strspn(NULL, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strspn_null2(void *ctx) { return bpf_strspn("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null1(void *ctx) { return bpf_strcspn(NULL, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strcspn_null2(void *ctx) { return bpf_strcspn("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null1(void *ctx) { return bpf_strstr(NULL, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strstr_null2(void *ctx) { return bpf_strstr("hello", NULL); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null1(void *ctx) { return bpf_strnstr(NULL, "hello", 1); }
+SEC("syscall") __retval(USER_PTR_ERR)int test_strnstr_null2(void *ctx) { return bpf_strnstr("hello", NULL, 1); }
+
+/* Passing userspace ptr to string kfuncs */
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr1(void *ctx) { return bpf_strcmp(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcmp_user_ptr2(void *ctx) { return bpf_strcmp("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strchr_user_ptr(void *ctx) { return bpf_strchr(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strchrnul_user_ptr(void *ctx) { return bpf_strchrnul(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnchr_user_ptr(void *ctx) { return bpf_strnchr(user_ptr, 1, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strrchr_user_ptr(void *ctx) { return bpf_strrchr(user_ptr, 'a'); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strlen_user_ptr(void *ctx) { return bpf_strlen(user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnlen_user_ptr(void *ctx) { return bpf_strnlen(user_ptr, 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr1(void *ctx) { return bpf_strspn(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strspn_user_ptr2(void *ctx) { return bpf_strspn("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr1(void *ctx) { return bpf_strcspn(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strcspn_user_ptr2(void *ctx) { return bpf_strcspn("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr1(void *ctx) { return bpf_strstr(user_ptr, "hello"); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strstr_user_ptr2(void *ctx) { return bpf_strstr("hello", user_ptr); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr1(void *ctx) { return bpf_strnstr(user_ptr, "hello", 1); }
+SEC("syscall") __retval(USER_PTR_ERR) int test_strnstr_user_ptr2(void *ctx) { return bpf_strnstr("hello", user_ptr, 1); }
+
+#endif /* __TARGET_ARCH_s390 */
+
+/* Passing invalid kernel ptr to string kfuncs should always return -EFAULT */
+SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault1(void *ctx) { return bpf_strcmp(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strcmp_pagefault2(void *ctx) { return bpf_strcmp("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strchr_pagefault(void *ctx) { return bpf_strchr(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strchrnul_pagefault(void *ctx) { return bpf_strchrnul(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strnchr_pagefault(void *ctx) { return bpf_strnchr(invalid_kern_ptr, 1, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strrchr_pagefault(void *ctx) { return bpf_strrchr(invalid_kern_ptr, 'a'); }
+SEC("syscall") __retval(-EFAULT) int test_strlen_pagefault(void *ctx) { return bpf_strlen(invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strnlen_pagefault(void *ctx) { return bpf_strnlen(invalid_kern_ptr, 1); }
+SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault1(void *ctx) { return bpf_strspn(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strspn_pagefault2(void *ctx) { return bpf_strspn("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault1(void *ctx) { return bpf_strcspn(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strcspn_pagefault2(void *ctx) { return bpf_strcspn("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault1(void *ctx) { return bpf_strstr(invalid_kern_ptr, "hello"); }
+SEC("syscall") __retval(-EFAULT) int test_strstr_pagefault2(void *ctx) { return bpf_strstr("hello", invalid_kern_ptr); }
+SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault1(void *ctx) { return bpf_strnstr(invalid_kern_ptr, "hello", 1); }
+SEC("syscall") __retval(-EFAULT) int test_strnstr_pagefault2(void *ctx) { return bpf_strnstr("hello", invalid_kern_ptr, 1); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
new file mode 100644
index 000000000000..89fb4669b0e9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_failure2.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <linux/limits.h>
+
+char long_str[XATTR_SIZE_MAX + 1];
+
+SEC("syscall") int test_strcmp_too_long(void *ctx) { return bpf_strcmp(long_str, long_str); }
+SEC("syscall") int test_strchr_too_long(void *ctx) { return bpf_strchr(long_str, 'b'); }
+SEC("syscall") int test_strchrnul_too_long(void *ctx) { return bpf_strchrnul(long_str, 'b'); }
+SEC("syscall") int test_strnchr_too_long(void *ctx) { return bpf_strnchr(long_str, sizeof(long_str), 'b'); }
+SEC("syscall") int test_strrchr_too_long(void *ctx) { return bpf_strrchr(long_str, 'b'); }
+SEC("syscall") int test_strlen_too_long(void *ctx) { return bpf_strlen(long_str); }
+SEC("syscall") int test_strnlen_too_long(void *ctx) { return bpf_strnlen(long_str, sizeof(long_str)); }
+SEC("syscall") int test_strspn_str_too_long(void *ctx) { return bpf_strspn(long_str, "a"); }
+SEC("syscall") int test_strspn_accept_too_long(void *ctx) { return bpf_strspn("b", long_str); }
+SEC("syscall") int test_strcspn_str_too_long(void *ctx) { return bpf_strcspn(long_str, "b"); }
+SEC("syscall") int test_strcspn_reject_too_long(void *ctx) { return bpf_strcspn("b", long_str); }
+SEC("syscall") int test_strstr_too_long(void *ctx) { return bpf_strstr(long_str, "hello"); }
+SEC("syscall") int test_strnstr_too_long(void *ctx) { return bpf_strnstr(long_str, "hello", sizeof(long_str)); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/string_kfuncs_success.c b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
new file mode 100644
index 000000000000..46697f381878
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/string_kfuncs_success.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2025 Red Hat, Inc.*/
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include "bpf_misc.h"
+#include "errno.h"
+
+char str[] = "hello world";
+
+#define __test(retval) SEC("syscall") __success __retval(retval)
+
+/* Functional tests */
+__test(0) int test_strcmp_eq(void *ctx) { return bpf_strcmp(str, "hello world"); }
+__test(1) int test_strcmp_neq(void *ctx) { return bpf_strcmp(str, "hello"); }
+__test(1) int test_strchr_found(void *ctx) { return bpf_strchr(str, 'e'); }
+__test(11) int test_strchr_null(void *ctx) { return bpf_strchr(str, '\0'); }
+__test(-ENOENT) int test_strchr_notfound(void *ctx) { return bpf_strchr(str, 'x'); }
+__test(1) int test_strchrnul_found(void *ctx) { return bpf_strchrnul(str, 'e'); }
+__test(11) int test_strchrnul_notfound(void *ctx) { return bpf_strchrnul(str, 'x'); }
+__test(1) int test_strnchr_found(void *ctx) { return bpf_strnchr(str, 5, 'e'); }
+__test(11) int test_strnchr_null(void *ctx) { return bpf_strnchr(str, 12, '\0'); }
+__test(-ENOENT) int test_strnchr_notfound(void *ctx) { return bpf_strnchr(str, 5, 'w'); }
+__test(9) int test_strrchr_found(void *ctx) { return bpf_strrchr(str, 'l'); }
+__test(11) int test_strrchr_null(void *ctx) { return bpf_strrchr(str, '\0'); }
+__test(-ENOENT) int test_strrchr_notfound(void *ctx) { return bpf_strrchr(str, 'x'); }
+__test(11) int test_strlen(void *ctx) { return bpf_strlen(str); }
+__test(11) int test_strnlen(void *ctx) { return bpf_strnlen(str, 12); }
+__test(5) int test_strspn(void *ctx) { return bpf_strspn(str, "ehlo"); }
+__test(2) int test_strcspn(void *ctx) { return bpf_strcspn(str, "lo"); }
+__test(6) int test_strstr_found(void *ctx) { return bpf_strstr(str, "world"); }
+__test(-ENOENT) int test_strstr_notfound(void *ctx) { return bpf_strstr(str, "hi"); }
+__test(0) int test_strstr_empty(void *ctx) { return bpf_strstr(str, ""); }
+__test(0) int test_strnstr_found(void *ctx) { return bpf_strnstr(str, "hello", 6); }
+__test(-ENOENT) int test_strnstr_notfound(void *ctx) { return bpf_strnstr(str, "hi", 10); }
+__test(0) int test_strnstr_empty(void *ctx) { return bpf_strnstr(str, "", 1); }
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_global_map_resize.c b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
index a3f220ba7025..ee65bad0436d 100644
--- a/tools/testing/selftests/bpf/progs/test_global_map_resize.c
+++ b/tools/testing/selftests/bpf/progs/test_global_map_resize.c
@@ -32,6 +32,16 @@ int my_int_last SEC(".data.array_not_last");
int percpu_arr[1] SEC(".data.percpu_arr");
+/* at least one extern is included, to ensure that a specific
+ * regression is tested whereby resizing resulted in a free-after-use
+ * bug after type information is invalidated by the resize operation.
+ *
+ * There isn't a particularly good API to test for this specific condition,
+ * but by having externs for the resizing tests it will cover this path.
+ */
+extern int LINUX_KERNEL_VERSION __kconfig;
+long version_sink;
+
SEC("tp/syscalls/sys_enter_getpid")
int bss_array_sum(void *ctx)
{
@@ -44,6 +54,9 @@ int bss_array_sum(void *ctx)
for (size_t i = 0; i < bss_array_len; ++i)
sum += array[i];
+ /* see above; ensure this is not optimized out */
+ version_sink = LINUX_KERNEL_VERSION;
+
return 0;
}
@@ -59,6 +72,9 @@ int data_array_sum(void *ctx)
for (size_t i = 0; i < data_array_len; ++i)
sum += my_array[i];
+ /* see above; ensure this is not optimized out */
+ version_sink = LINUX_KERNEL_VERSION;
+
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/test_lookup_key.c b/tools/testing/selftests/bpf/progs/test_lookup_key.c
index cdbbb12f1491..1f7e1e59b073 100644
--- a/tools/testing/selftests/bpf/progs/test_lookup_key.c
+++ b/tools/testing/selftests/bpf/progs/test_lookup_key.c
@@ -14,11 +14,11 @@
char _license[] SEC("license") = "GPL";
__u32 monitored_pid;
-__u32 key_serial;
+__s32 key_serial;
__u32 key_id;
__u64 flags;
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
extern void bpf_key_put(struct bpf_key *key) __ksym;
diff --git a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
index 350513c0e4c9..f063a0013f85 100644
--- a/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
+++ b/tools/testing/selftests/bpf/progs/test_ringbuf_write.c
@@ -26,11 +26,11 @@ int test_ringbuf_write(void *ctx)
if (cur_pid != pid)
return 0;
- sample1 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+ sample1 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0);
if (!sample1)
return 0;
/* first one can pass */
- sample2 = bpf_ringbuf_reserve(&ringbuf, 0x3000, 0);
+ sample2 = bpf_ringbuf_reserve(&ringbuf, 0x30000, 0);
if (!sample2) {
bpf_ringbuf_discard(sample1, 0);
__sync_fetch_and_add(&discarded, 1);
diff --git a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
index 8ef6b39335b6..34b30e2603f0 100644
--- a/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
+++ b/tools/testing/selftests/bpf/progs/test_sig_in_xattr.c
@@ -40,7 +40,7 @@ char digest[MAGIC_SIZE + SIZEOF_STRUCT_FSVERITY_DIGEST + SHA256_DIGEST_SIZE];
__u32 monitored_pid;
char sig[MAX_SIG_SIZE];
__u32 sig_size;
-__u32 user_keyring_serial;
+__s32 user_keyring_serial;
SEC("lsm.s/file_open")
int BPF_PROG(test_file_open, struct file *f)
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
index 2796dd8545eb..1c7941a4ad00 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_change_tail.c
@@ -1,8 +1,13 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2024 ByteDance */
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+#endif
+#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2)
+
struct {
__uint(type, BPF_MAP_TYPE_SOCKMAP);
__uint(max_entries, 1);
@@ -31,7 +36,7 @@ int prog_skb_verdict(struct __sk_buff *skb)
change_tail_ret = bpf_skb_change_tail(skb, skb->len + 1, 0);
return SK_PASS;
} else if (data[0] == 'E') { /* Error */
- change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+ change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0);
return SK_PASS;
}
return SK_PASS;
diff --git a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
index 28edafe803f0..fcba8299f0bc 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_change_tail.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/bpf.h>
+#include "vmlinux.h"
#include <bpf/bpf_helpers.h>
-#include <linux/if_ether.h>
-#include <linux/in.h>
-#include <linux/ip.h>
-#include <linux/udp.h>
-#include <linux/pkt_cls.h>
+
+#ifndef PAGE_SIZE
+#define PAGE_SIZE __PAGE_SIZE
+#endif
+#define BPF_SKB_MAX_LEN (PAGE_SIZE << 2)
long change_tail_ret = 1;
@@ -94,7 +94,7 @@ int change_tail(struct __sk_buff *skb)
bpf_skb_change_tail(skb, len, 0);
return TCX_PASS;
} else if (payload[0] == 'E') { /* Error */
- change_tail_ret = bpf_skb_change_tail(skb, 65535, 0);
+ change_tail_ret = bpf_skb_change_tail(skb, BPF_SKB_MAX_LEN, 0);
return TCX_PASS;
} else if (payload[0] == 'Z') { /* Zero */
change_tail_ret = bpf_skb_change_tail(skb, 0, 0);
diff --git a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
index e96d09e11115..ff8d755548b9 100644
--- a/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
+++ b/tools/testing/selftests/bpf/progs/test_verify_pkcs7_sig.c
@@ -17,7 +17,7 @@
#define MAX_SIG_SIZE 1024
__u32 monitored_pid;
-__u32 user_keyring_serial;
+__s32 user_keyring_serial;
__u64 system_keyring_id;
struct data {
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
index dc74d8cf9e3f..5904f45cfbc4 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
@@ -19,7 +19,9 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp)
/* Data length determine test case */
if (data_len == 54) { /* sizeof(pkt_v4) */
- offset = 4096; /* test too large offset */
+ offset = 4096; /* test too large offset, 4k page size */
+ } else if (data_len == 53) { /* sizeof(pkt_v4) - 1 */
+ offset = 65536; /* test too large offset, 64k page size */
} else if (data_len == 74) { /* sizeof(pkt_v6) */
offset = 40;
} else if (data_len == 64) {
@@ -31,6 +33,10 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp)
offset = 10;
} else if (data_len == 9001) {
offset = 4096;
+ } else if (data_len == 90000) {
+ offset = 10; /* test a small offset, 64k page size */
+ } else if (data_len == 90001) {
+ offset = 65536; /* test too large offset, 64k page size */
} else {
return XDP_ABORTED; /* No matching test */
}
diff --git a/tools/testing/selftests/bpf/progs/verifier_and.c b/tools/testing/selftests/bpf/progs/verifier_and.c
index e97e518516b6..2b4fdca162be 100644
--- a/tools/testing/selftests/bpf/progs/verifier_and.c
+++ b/tools/testing/selftests/bpf/progs/verifier_and.c
@@ -85,8 +85,14 @@ l0_%=: r0 = r0; \
SEC("socket")
__description("check known subreg with unknown reg")
-__success __failure_unpriv __msg_unpriv("R1 !read_ok")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w0 < 0x1 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R1 !read_ok'` */
+__xlated_unpriv("goto pc-1") /* `r1 = *(u32*)(r1 + 512)`, sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void known_subreg_with_unknown_reg(void)
{
asm volatile (" \
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 0eb33bb801b5..e52a24e15b34 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -620,8 +620,14 @@ l1_%=: exit; \
SEC("socket")
__description("bounds check mixed 32bit and 64bit arithmetic. test1")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
__naked void _32bit_and_64bit_arithmetic_test1(void)
{
asm volatile (" \
@@ -643,8 +649,14 @@ l1_%=: exit; \
SEC("socket")
__description("bounds check mixed 32bit and 64bit arithmetic. test2")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
__naked void _32bit_and_64bit_arithmetic_test2(void)
{
asm volatile (" \
@@ -691,9 +703,14 @@ l0_%=: r0 = 0; \
SEC("socket")
__description("bounds check for reg = 0, reg xor 1")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void reg_0_reg_xor_1(void)
{
asm volatile (" \
@@ -719,9 +736,14 @@ l1_%=: r0 = 0; \
SEC("socket")
__description("bounds check for reg32 = 0, reg32 xor 1")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void reg32_0_reg32_xor_1(void)
{
asm volatile (" \
@@ -747,9 +769,14 @@ l1_%=: r0 = 0; \
SEC("socket")
__description("bounds check for reg = 2, reg xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 > 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void reg_2_reg_xor_3(void)
{
asm volatile (" \
@@ -829,9 +856,14 @@ l1_%=: r0 = 0; \
SEC("socket")
__description("bounds check for reg > 0, reg xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void reg_0_reg_xor_3(void)
{
asm volatile (" \
@@ -858,9 +890,14 @@ l1_%=: r0 = 0; \
SEC("socket")
__description("bounds check for reg32 > 0, reg32 xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
__naked void reg32_0_reg32_xor_3(void)
{
asm volatile (" \
@@ -1334,4 +1371,165 @@ __naked void mult_sign_ovf(void)
__imm(bpf_skb_store_bytes)
: __clobber_all);
}
+
+SEC("socket")
+__description("64-bit addition, all outcomes overflow")
+__success __log_level(2)
+__msg("5: (0f) r3 += r3 {{.*}} R3_w=scalar(umin=0x4000000000000000,umax=0xfffffffffffffffe)")
+__retval(0)
+__naked void add64_full_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r4 = r0;"
+ "r3 = 0xa000000000000000 ll;"
+ "r3 |= r4;"
+ "r3 += r3;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit addition, partial overflow, result in unbounded reg")
+__success __log_level(2)
+__msg("4: (0f) r3 += r3 {{.*}} R3_w=scalar()")
+__retval(0)
+__naked void add64_partial_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r4 = r0;"
+ "r3 = 2;"
+ "r3 |= r4;"
+ "r3 += r3;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit addition overflow, all outcomes overflow")
+__success __log_level(2)
+__msg("4: (0c) w3 += w3 {{.*}} R3_w=scalar(smin=umin=umin32=0x40000000,smax=umax=umax32=0xfffffffe,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void add32_full_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "w4 = w0;"
+ "w3 = 0xa0000000;"
+ "w3 |= w4;"
+ "w3 += w3;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit addition, partial overflow, result in unbounded u32 bounds")
+__success __log_level(2)
+__msg("4: (0c) w3 += w3 {{.*}} R3_w=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void add32_partial_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "w4 = w0;"
+ "w3 = 2;"
+ "w3 |= w4;"
+ "w3 += w3;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit subtraction, all outcomes underflow")
+__success __log_level(2)
+__msg("6: (1f) r3 -= r1 {{.*}} R3_w=scalar(umin=1,umax=0x8000000000000000)")
+__retval(0)
+__naked void sub64_full_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r1 = r0;"
+ "r2 = 0x8000000000000000 ll;"
+ "r1 |= r2;"
+ "r3 = 0;"
+ "r3 -= r1;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("64-bit subtration, partial overflow, result in unbounded reg")
+__success __log_level(2)
+__msg("3: (1f) r3 -= r2 {{.*}} R3_w=scalar()")
+__retval(0)
+__naked void sub64_partial_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "r3 = r0;"
+ "r2 = 1;"
+ "r3 -= r2;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit subtraction overflow, all outcomes underflow")
+__success __log_level(2)
+__msg("5: (1c) w3 -= w1 {{.*}} R3_w=scalar(smin=umin=umin32=1,smax=umax=umax32=0x80000000,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void sub32_full_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "w1 = w0;"
+ "w2 = 0x80000000;"
+ "w1 |= w2;"
+ "w3 = 0;"
+ "w3 -= w1;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("32-bit subtration, partial overflow, result in unbounded u32 bounds")
+__success __log_level(2)
+__msg("3: (1c) w3 -= w2 {{.*}} R3_w=scalar(smin=0,smax=umax=0xffffffff,var_off=(0x0; 0xffffffff))")
+__retval(0)
+__naked void sub32_partial_overflow(void)
+{
+ asm volatile (
+ "call %[bpf_get_prandom_u32];"
+ "w3 = w0;"
+ "w2 = 1;"
+ "w3 -= w2;"
+ "r0 = 0;"
+ "exit"
+ :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
index c506afbdd936..260a6df264e3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
@@ -159,13 +159,16 @@ __failure_unpriv
__naked void deducing_bounds_from_const_10(void)
{
asm volatile (" \
+ r6 = r1; \
r0 = 0; \
if r0 s<= 0 goto l0_%=; \
-l0_%=: /* Marks reg as unknown. */ \
- r0 = -r0; \
- r0 -= r1; \
+l0_%=: /* Marks r0 as unknown. */ \
+ call %[bpf_get_prandom_u32]; \
+ r0 -= r6; \
exit; \
-" ::: __clobber_all);
+" :
+ : __imm(bpf_get_prandom_u32)
+ : __clobber_all);
}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c
index 458984da804c..34e0c012ee76 100644
--- a/tools/testing/selftests/bpf/progs/verifier_div_overflow.c
+++ b/tools/testing/selftests/bpf/progs/verifier_div_overflow.c
@@ -77,7 +77,7 @@ l0_%=: exit; \
SEC("tc")
__description("MOD32 overflow, check 1")
-__success __retval(INT_MIN)
+__success __retval(_INT_MIN)
__naked void mod32_overflow_check_1(void)
{
asm volatile (" \
@@ -92,7 +92,7 @@ __naked void mod32_overflow_check_1(void)
SEC("tc")
__description("MOD32 overflow, check 2")
-__success __retval(INT_MIN)
+__success __retval(_INT_MIN)
__naked void mod32_overflow_check_2(void)
{
asm volatile (" \
diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c
index 7d088ba99ea5..16b761e510f0 100644
--- a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c
@@ -139,4 +139,122 @@ __naked void on_the_inner_map_pointer(void)
: __clobber_all);
}
+SEC("socket")
+__description("map_ptr is never null")
+__success
+__naked void map_ptr_is_never_null(void)
+{
+ asm volatile (" \
+ r0 = 0; \
+ r1 = %[map_in_map] ll; \
+ if r1 != 0 goto l0_%=; \
+ r10 = 42; \
+l0_%=: exit; \
+" :
+ : __imm(bpf_map_lookup_elem),
+ __imm_addr(map_in_map)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr is never null inner")
+__success
+__naked void map_ptr_is_never_null_inner(void)
+{
+ asm volatile (" \
+ r1 = 0; \
+ *(u32*)(r10 - 4) = r1; \
+ r2 = r10; \
+ r2 += -4; \
+ r1 = %[map_in_map] ll; \
+ call %[bpf_map_lookup_elem]; \
+ if r0 == 0 goto l0_%=; \
+ if r0 != 0 goto l0_%=; \
+ r10 = 42; \
+l0_%=: exit; \
+" :
+ : __imm(bpf_map_lookup_elem),
+ __imm_addr(map_in_map)
+ : __clobber_all);
+}
+
+SEC("socket")
+__description("map_ptr is never null inner spill fill")
+__success
+__naked void map_ptr_is_never_null_inner_spill_fill(void)
+{
+ asm volatile (" \
+ r1 = 0; \
+ *(u32*)(r10 - 4) = r1; \
+ r2 = r10; \
+ r2 += -4; \
+ r1 = %[map_in_map] ll; \
+ call %[bpf_map_lookup_elem]; \
+ if r0 != 0 goto l0_%=; \
+ exit; \
+l0_%=: *(u64 *)(r10 -16) = r0; \
+ r1 = *(u64 *)(r10 -16); \
+ if r1 == 0 goto l1_%=; \
+ exit; \
+l1_%=: r10 = 42; \
+ exit; \
+" :
+ : __imm(bpf_map_lookup_elem),
+ __imm_addr(map_in_map)
+ : __clobber_all);
+}
+
+struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+ __uint(max_entries, 1);
+ __type(key, int);
+ __type(value, int);
+ __array(values, struct {
+ __uint(type, BPF_MAP_TYPE_RINGBUF);
+ __uint(max_entries, 64 * 1024);
+ });
+} rb_in_map SEC(".maps");
+
+struct rb_ctx {
+ void *rb;
+ struct bpf_dynptr dptr;
+};
+
+static __always_inline struct rb_ctx __rb_event_reserve(__u32 sz)
+{
+ struct rb_ctx rb_ctx = {};
+ void *rb;
+ __u32 cpu = bpf_get_smp_processor_id();
+ __u32 rb_slot = cpu & 1;
+
+ rb = bpf_map_lookup_elem(&rb_in_map, &rb_slot);
+ if (!rb)
+ return rb_ctx;
+
+ rb_ctx.rb = rb;
+ bpf_ringbuf_reserve_dynptr(rb, sz, 0, &rb_ctx.dptr);
+
+ return rb_ctx;
+}
+
+static __noinline void __rb_event_submit(struct rb_ctx *ctx)
+{
+ if (!ctx->rb)
+ return;
+
+ /* If the verifier (incorrectly) concludes that ctx->rb can be
+ * NULL at this point, we'll get "BPF_EXIT instruction in main
+ * prog would lead to reference leak" error
+ */
+ bpf_ringbuf_submit_dynptr(&ctx->dptr, 0);
+}
+
+SEC("socket")
+int map_ptr_is_never_null_rb(void *ctx)
+{
+ struct rb_ctx event_ctx = __rb_event_reserve(256);
+ __rb_event_submit(&event_ctx);
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index 994bbc346d25..a4d8814eb5ed 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -245,7 +245,13 @@ l0_%=: \
SEC("socket")
__description("MOV32SX, S8, var_off not u32_max, positive after s8 extension")
__success __retval(0)
-__failure_unpriv __msg_unpriv("frame pointer is read only")
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
__naked void mov64sx_s32_varoff_2(void)
{
asm volatile (" \
@@ -267,7 +273,13 @@ l0_%=: \
SEC("socket")
__description("MOV32SX, S8, var_off not u32_max, negative after s8 extension")
__success __retval(0)
-__failure_unpriv __msg_unpriv("frame pointer is read only")
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
__naked void mov64sx_s32_varoff_3(void)
{
asm volatile (" \
diff --git a/tools/testing/selftests/bpf/progs/verifier_precision.c b/tools/testing/selftests/bpf/progs/verifier_precision.c
index 9fe5d255ee37..73fee2aec698 100644
--- a/tools/testing/selftests/bpf/progs/verifier_precision.c
+++ b/tools/testing/selftests/bpf/progs/verifier_precision.c
@@ -231,4 +231,74 @@ __naked void bpf_cond_op_not_r10(void)
::: __clobber_all);
}
+SEC("lsm.s/socket_connect")
+__success __log_level(2)
+__msg("0: (b7) r0 = 1 ; R0_w=1")
+__msg("1: (84) w0 = -w0 ; R0_w=0xffffffff")
+__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (84) w0 = -w0")
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
+__naked int bpf_neg_2(void)
+{
+ /*
+ * lsm.s/socket_connect requires a return value within [-4095, 0].
+ * Returning -1 is allowed
+ */
+ asm volatile (
+ "r0 = 1;"
+ "w0 = -w0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__failure __msg("At program exit the register R0 has")
+__naked int bpf_neg_3(void)
+{
+ /*
+ * lsm.s/socket_connect requires a return value within [-4095, 0].
+ * Returning -10000 is not allowed.
+ */
+ asm volatile (
+ "r0 = 10000;"
+ "w0 = -w0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__success __log_level(2)
+__msg("0: (b7) r0 = 1 ; R0_w=1")
+__msg("1: (87) r0 = -r0 ; R0_w=-1")
+__msg("mark_precise: frame0: last_idx 2 first_idx 0 subseq_idx -1")
+__msg("mark_precise: frame0: regs=r0 stack= before 1: (87) r0 = -r0")
+__msg("mark_precise: frame0: regs=r0 stack= before 0: (b7) r0 = 1")
+__naked int bpf_neg_4(void)
+{
+ /*
+ * lsm.s/socket_connect requires a return value within [-4095, 0].
+ * Returning -1 is allowed
+ */
+ asm volatile (
+ "r0 = 1;"
+ "r0 = -r0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
+SEC("lsm.s/socket_connect")
+__failure __msg("At program exit the register R0 has")
+__naked int bpf_neg_5(void)
+{
+ /*
+ * lsm.s/socket_connect requires a return value within [-4095, 0].
+ * Returning -10000 is not allowed.
+ */
+ asm volatile (
+ "r0 = 10000;"
+ "r0 = -r0;"
+ "exit;"
+ ::: __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c
index 683a882b3e6d..910365201f68 100644
--- a/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c
+++ b/tools/testing/selftests/bpf/progs/verifier_ref_tracking.c
@@ -27,7 +27,7 @@ struct bpf_key {} __attribute__((preserve_access_index));
extern void bpf_key_put(struct bpf_key *key) __ksym;
extern struct bpf_key *bpf_lookup_system_key(__u64 id) __ksym;
-extern struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+extern struct bpf_key *bpf_lookup_user_key(__s32 serial, __u64 flags) __ksym;
/* BTF FUNC records are not generated for kfuncs referenced
* from inline assembly. These records are necessary for
diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
index a4a5e2071604..4470541b5e71 100644
--- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
@@ -572,8 +572,14 @@ l0_%=: exit; \
SEC("socket")
__description("alu32: mov u32 const")
-__success __failure_unpriv __msg_unpriv("R7 invalid mem access 'scalar'")
+__success __success_unpriv
__retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r0 == 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R7 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
__naked void alu32_mov_u32_const(void)
{
asm volatile (" \
@@ -619,12 +625,11 @@ __naked void pass_pointer_to_tail_call(void)
SEC("socket")
__description("unpriv: cmp map pointer with zero")
-__success __failure_unpriv __msg_unpriv("R1 pointer comparison")
+__success __success_unpriv
__retval(0)
__naked void cmp_map_pointer_with_zero(void)
{
asm volatile (" \
- r1 = 0; \
r1 = %[map_hash_8b] ll; \
if r1 == 0 goto l0_%=; \
l0_%=: r0 = 0; \
@@ -635,6 +640,22 @@ l0_%=: r0 = 0; \
}
SEC("socket")
+__description("unpriv: cmp map pointer with const")
+__success __failure_unpriv __msg_unpriv("R1 pointer comparison prohibited")
+__retval(0)
+__naked void cmp_map_pointer_with_const(void)
+{
+ asm volatile (" \
+ r1 = %[map_hash_8b] ll; \
+ if r1 == 0x0000beef goto l0_%=; \
+l0_%=: r0 = 0; \
+ exit; \
+" :
+ : __imm_addr(map_hash_8b)
+ : __clobber_all);
+}
+
+SEC("socket")
__description("unpriv: write into frame pointer")
__failure __msg("frame pointer is read only")
__failure_unpriv
@@ -723,4 +744,61 @@ l0_%=: r0 = 0; \
" ::: __clobber_all);
}
+SEC("socket")
+__description("unpriv: Spectre v1 path-based type confusion of scalar as stack-ptr")
+__success __success_unpriv __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r0 != 0x1 goto pc+2")
+/* This nospec prevents the exploit because it forces the mispredicted (not
+ * taken) `if r0 != 0x0 goto l0_%=` to resolve before using r6 as a pointer.
+ * This causes the CPU to realize that `r6 = r9` should have never executed. It
+ * ensures that r6 always contains a readable stack slot ptr when the insn after
+ * the nospec executes.
+ */
+__xlated_unpriv("nospec")
+__xlated_unpriv("r9 = *(u8 *)(r6 +0)")
+#endif
+__naked void unpriv_spec_v1_type_confusion(void)
+{
+ asm volatile (" \
+ r1 = 0; \
+ *(u64*)(r10 - 8) = r1; \
+ r2 = r10; \
+ r2 += -8; \
+ r1 = %[map_hash_8b] ll; \
+ call %[bpf_map_lookup_elem]; \
+ if r0 == 0 goto l2_%=; \
+ /* r0: pointer to a map array entry */ \
+ r2 = r10; \
+ r2 += -8; \
+ r1 = %[map_hash_8b] ll; \
+ /* r1, r2: prepared call args */ \
+ r6 = r10; \
+ r6 += -8; \
+ /* r6: pointer to readable stack slot */ \
+ r9 = 0xffffc900; \
+ r9 <<= 32; \
+ /* r9: scalar controlled by attacker */ \
+ r0 = *(u64 *)(r0 + 0); /* cache miss */ \
+ if r0 != 0x0 goto l0_%=; \
+ r6 = r9; \
+l0_%=: if r0 != 0x1 goto l1_%=; \
+ r9 = *(u8 *)(r6 + 0); \
+l1_%=: /* leak r9 */ \
+ r9 &= 1; \
+ r9 <<= 9; \
+ *(u64*)(r10 - 8) = r9; \
+ call %[bpf_map_lookup_elem]; \
+ if r0 == 0 goto l2_%=; \
+ /* leak secret into is_cached(map[0|512]): */ \
+ r0 = *(u64 *)(r0 + 0); \
+l2_%=: \
+ r0 = 0; \
+ exit; \
+" :
+ : __imm(bpf_map_lookup_elem),
+ __imm_addr(map_hash_8b)
+ : __clobber_all);
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
index 5ba6e53571c8..af7938ce56cb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
@@ -231,6 +231,10 @@ __retval(1)
__naked void ptr_unknown_vs_unknown_lt(void)
{
asm volatile (" \
+ r8 = r1; \
+ call %[bpf_get_prandom_u32]; \
+ r9 = r0; \
+ r1 = r8; \
r0 = *(u32*)(r1 + %[__sk_buff_len]); \
r1 = 0; \
*(u64*)(r10 - 8) = r1; \
@@ -245,11 +249,11 @@ l1_%=: call %[bpf_map_lookup_elem]; \
r4 = *(u8*)(r0 + 0); \
if r4 == 1 goto l3_%=; \
r1 = 6; \
- r1 = -r1; \
+ r1 = r9; \
r1 &= 0x3; \
goto l4_%=; \
l3_%=: r1 = 6; \
- r1 = -r1; \
+ r1 = r9; \
r1 &= 0x7; \
l4_%=: r1 += r0; \
r0 = *(u8*)(r1 + 0); \
@@ -259,7 +263,8 @@ l2_%=: r0 = 1; \
: __imm(bpf_map_lookup_elem),
__imm_addr(map_array_48b),
__imm_addr(map_hash_16b),
- __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+ __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+ __imm(bpf_get_prandom_u32)
: __clobber_all);
}
@@ -271,6 +276,10 @@ __retval(1)
__naked void ptr_unknown_vs_unknown_gt(void)
{
asm volatile (" \
+ r8 = r1; \
+ call %[bpf_get_prandom_u32]; \
+ r9 = r0; \
+ r1 = r8; \
r0 = *(u32*)(r1 + %[__sk_buff_len]); \
r1 = 0; \
*(u64*)(r10 - 8) = r1; \
@@ -285,11 +294,11 @@ l1_%=: call %[bpf_map_lookup_elem]; \
r4 = *(u8*)(r0 + 0); \
if r4 == 1 goto l3_%=; \
r1 = 6; \
- r1 = -r1; \
+ r1 = r9; \
r1 &= 0x7; \
goto l4_%=; \
l3_%=: r1 = 6; \
- r1 = -r1; \
+ r1 = r9; \
r1 &= 0x3; \
l4_%=: r1 += r0; \
r0 = *(u8*)(r1 + 0); \
@@ -299,7 +308,8 @@ l2_%=: r0 = 1; \
: __imm(bpf_map_lookup_elem),
__imm_addr(map_array_48b),
__imm_addr(map_hash_16b),
- __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+ __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+ __imm(bpf_get_prandom_u32)
: __clobber_all);
}
@@ -398,7 +408,8 @@ l2_%=: r0 = 1; \
SEC("socket")
__description("map access: mixing value pointer and scalar, 1")
-__success __failure_unpriv __msg_unpriv("R2 pointer comparison prohibited")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
__retval(0)
__naked void value_pointer_and_scalar_1(void)
{
@@ -433,6 +444,7 @@ l2_%=: /* common instruction */ \
l3_%=: /* branch B */ \
r0 = 0x13371337; \
/* verifier follows fall-through */ \
+ /* unpriv: nospec (inserted to prevent `R2 pointer comparison prohibited`) */\
if r2 != 0x100000 goto l4_%=; \
r0 = 0; \
exit; \
@@ -450,7 +462,8 @@ l4_%=: /* fake-dead code; targeted from branch A to \
SEC("socket")
__description("map access: mixing value pointer and scalar, 2")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
__retval(0)
__naked void value_pointer_and_scalar_2(void)
{
@@ -492,6 +505,7 @@ l4_%=: /* fake-dead code; targeted from branch A to \
* prevent dead code sanitization, rejected \
* via branch B however \
*/ \
+ /* unpriv: nospec (inserted to prevent `R0 invalid mem access 'scalar'`) */\
r0 = *(u8*)(r0 + 0); \
r0 = 0; \
exit; \
@@ -1296,9 +1310,13 @@ l0_%=: r0 = 1; \
SEC("socket")
__description("map access: value_ptr -= unknown scalar, 2")
-__success __failure_unpriv
-__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__success __success_unpriv
__retval(1)
+#ifdef SPEC_V1
+__xlated_unpriv("r1 &= 7")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 pointer arithmetic of map value goes out of range` */
+__xlated_unpriv("r0 -= r1")
+#endif
__naked void value_ptr_unknown_scalar_2_2(void)
{
asm volatile (" \
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
index a7c0a553aa50..3e2d76ee8050 100644
--- a/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_accept.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2024 Google LLC. */
#include <vmlinux.h>
+#include <errno.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
@@ -82,4 +83,21 @@ int BPF_PROG(path_d_path_from_file_argument, struct file *file)
return 0;
}
+SEC("lsm.s/inode_rename")
+__success
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
+{
+ struct inode *inode = new_dentry->d_inode;
+ ino_t ino;
+
+ if (!inode)
+ return 0;
+ ino = inode->i_ino;
+ if (ino == 0)
+ return -EACCES;
+ return 0;
+}
+
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
index d6d3f4fcb24c..4b392c6c8fc4 100644
--- a/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
+++ b/tools/testing/selftests/bpf/progs/verifier_vfs_reject.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2024 Google LLC. */
#include <vmlinux.h>
+#include <errno.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include <linux/limits.h>
@@ -158,4 +159,18 @@ int BPF_PROG(path_d_path_kfunc_non_lsm, struct path *path, struct file *f)
return 0;
}
+SEC("lsm.s/inode_rename")
+__failure __msg("invalid mem access 'trusted_ptr_or_null_'")
+int BPF_PROG(inode_rename, struct inode *old_dir, struct dentry *old_dentry,
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
+{
+ struct inode *inode = new_dentry->d_inode;
+ ino_t ino;
+
+ ino = inode->i_ino;
+ if (ino == 0)
+ return -EACCES;
+ return 0;
+}
char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_bpftool_map.sh b/tools/testing/selftests/bpf/test_bpftool_map.sh
new file mode 100755
index 000000000000..515b1df0501e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_bpftool_map.sh
@@ -0,0 +1,398 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+TESTNAME="bpftool_map"
+BPF_FILE="security_bpf_map.bpf.o"
+BPF_ITER_FILE="bpf_iter_map_elem.bpf.o"
+PROTECTED_MAP_NAME="prot_map"
+NOT_PROTECTED_MAP_NAME="not_prot_map"
+BPF_FS_TMP_PARENT="/tmp"
+BPF_FS_PARENT=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts)
+BPF_FS_PARENT=${BPF_FS_PARENT:-$BPF_FS_TMP_PARENT}
+# bpftool will mount bpf file system under BPF_DIR if it is not mounted
+# under BPF_FS_PARENT.
+BPF_DIR="$BPF_FS_PARENT/test_$TESTNAME"
+SCRIPT_DIR=$(dirname $(realpath "$0"))
+BPF_FILE_PATH="$SCRIPT_DIR/$BPF_FILE"
+BPF_ITER_FILE_PATH="$SCRIPT_DIR/$BPF_ITER_FILE"
+BPFTOOL_PATH="bpftool"
+# Assume the script is located under tools/testing/selftests/bpf/
+KDIR_ROOT_DIR=$(realpath "$SCRIPT_DIR"/../../../../)
+
+_cleanup()
+{
+ set +eu
+
+ # If BPF_DIR is a mount point this will not remove the mount point itself.
+ [ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2> /dev/null
+
+ # Unmount if BPF filesystem was temporarily created.
+ if [ "$BPF_FS_PARENT" = "$BPF_FS_TMP_PARENT" ]; then
+ # A loop and recursive unmount are required as bpftool might
+ # create multiple mounts. For example, a bind mount of the directory
+ # to itself. The bind mount is created to change mount propagation
+ # flags on an actual mount point.
+ max_attempts=3
+ attempt=0
+ while mountpoint -q "$BPF_DIR" && [ $attempt -lt $max_attempts ]; do
+ umount -R "$BPF_DIR" 2>/dev/null
+ attempt=$((attempt+1))
+ done
+
+ # The directory still exists. Remove it now.
+ [ -d "$BPF_DIR" ] && rm -rf "$BPF_DIR" 2>/dev/null
+ fi
+}
+
+cleanup_skip()
+{
+ echo "selftests: $TESTNAME [SKIP]"
+ _cleanup
+
+ exit $ksft_skip
+}
+
+cleanup()
+{
+ if [ "$?" = 0 ]; then
+ echo "selftests: $TESTNAME [PASS]"
+ else
+ echo "selftests: $TESTNAME [FAILED]"
+ fi
+ _cleanup
+}
+
+check_root_privileges() {
+ if [ $(id -u) -ne 0 ]; then
+ echo "Need root privileges"
+ exit $ksft_skip
+ fi
+}
+
+# Function to verify bpftool path.
+# Parameters:
+# $1: bpftool path
+verify_bpftool_path() {
+ local bpftool_path="$1"
+ if ! "$bpftool_path" version > /dev/null 2>&1; then
+ echo "Could not run test without bpftool"
+ exit $ksft_skip
+ fi
+}
+
+# Function to verify BTF support.
+# The test requires BTF support for fmod_ret programs.
+verify_btf_support() {
+ if [ ! -f /sys/kernel/btf/vmlinux ]; then
+ echo "Could not run test without BTF support"
+ exit $ksft_skip
+ fi
+}
+
+# Function to initialize map entries with keys [0..2] and values set to 0.
+# Parameters:
+# $1: Map name
+# $2: bpftool path
+initialize_map_entries() {
+ local map_name="$1"
+ local bpftool_path="$2"
+
+ for key in 0 1 2; do
+ "$bpftool_path" map update name "$map_name" key $key 0 0 0 value 0 0 0 $key
+ done
+}
+
+# Test read access to the map.
+# Parameters:
+# $1: Name command (name/pinned)
+# $2: Map name
+# $3: bpftool path
+# $4: key
+access_for_read() {
+ local name_cmd="$1"
+ local map_name="$2"
+ local bpftool_path="$3"
+ local key="$4"
+
+ # Test read access to the map.
+ if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+ echo " Read access to $key in $map_name failed"
+ exit 1
+ fi
+
+ # Test read access to map's BTF data.
+ if ! "$bpftool_path" btf dump map "$name_cmd" "$map_name" 1>/dev/null; then
+ echo " Read access to $map_name for BTF data failed"
+ exit 1
+ fi
+}
+
+# Test write access to the map.
+# Parameters:
+# $1: Name command (name/pinned)
+# $2: Map name
+# $3: bpftool path
+# $4: key
+# $5: Whether write should succeed (true/false)
+access_for_write() {
+ local name_cmd="$1"
+ local map_name="$2"
+ local bpftool_path="$3"
+ local key="$4"
+ local write_should_succeed="$5"
+ local value="1 1 1 1"
+
+ if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
+ $value 2>/dev/null; then
+ if [ "$write_should_succeed" = "false" ]; then
+ echo " Write access to $key in $map_name succeeded but should have failed"
+ exit 1
+ fi
+ else
+ if [ "$write_should_succeed" = "true" ]; then
+ echo " Write access to $key in $map_name failed but should have succeeded"
+ exit 1
+ fi
+ fi
+}
+
+# Test entry deletion for the map.
+# Parameters:
+# $1: Name command (name/pinned)
+# $2: Map name
+# $3: bpftool path
+# $4: key
+# $5: Whether write should succeed (true/false)
+access_for_deletion() {
+ local name_cmd="$1"
+ local map_name="$2"
+ local bpftool_path="$3"
+ local key="$4"
+ local write_should_succeed="$5"
+ local value="1 1 1 1"
+
+ # Test deletion by key for the map.
+ # Before deleting, check the key exists.
+ if ! "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+ echo " Key $key does not exist in $map_name"
+ exit 1
+ fi
+
+ # Delete by key.
+ if "$bpftool_path" map delete "$name_cmd" "$map_name" key $key 2>/dev/null; then
+ if [ "$write_should_succeed" = "false" ]; then
+ echo " Deletion for $key in $map_name succeeded but should have failed"
+ exit 1
+ fi
+ else
+ if [ "$write_should_succeed" = "true" ]; then
+ echo " Deletion for $key in $map_name failed but should have succeeded"
+ exit 1
+ fi
+ fi
+
+ # After deleting, check the entry existence according to the expected status.
+ if "$bpftool_path" map lookup "$name_cmd" "$map_name" key $key 1>/dev/null; then
+ if [ "$write_should_succeed" = "true" ]; then
+ echo " Key $key for $map_name was not deleted but should have been deleted"
+ exit 1
+ fi
+ else
+ if [ "$write_should_succeed" = "false" ]; then
+ echo "Key $key for $map_name was deleted but should have not been deleted"
+ exit 1
+ fi
+ fi
+
+ # Test creation of map's deleted entry, if deletion was successful.
+ # Otherwise, the entry exists.
+ if "$bpftool_path" map update "$name_cmd" "$map_name" key $key value \
+ $value 2>/dev/null; then
+ if [ "$write_should_succeed" = "false" ]; then
+ echo " Write access to $key in $map_name succeeded after deletion attempt but should have failed"
+ exit 1
+ fi
+ else
+ if [ "$write_should_succeed" = "true" ]; then
+ echo " Write access to $key in $map_name failed after deletion attempt but should have succeeded"
+ exit 1
+ fi
+ fi
+}
+
+# Test map elements iterator.
+# Parameters:
+# $1: Name command (name/pinned)
+# $2: Map name
+# $3: bpftool path
+# $4: BPF_DIR
+# $5: bpf iterator object file path
+iterate_map_elem() {
+ local name_cmd="$1"
+ local map_name="$2"
+ local bpftool_path="$3"
+ local bpf_dir="$4"
+ local bpf_file="$5"
+ local pin_path="$bpf_dir/map_iterator"
+
+ "$bpftool_path" iter pin "$bpf_file" "$pin_path" map "$name_cmd" "$map_name"
+ if [ ! -f "$pin_path" ]; then
+ echo " Failed to pin iterator to $pin_path"
+ exit 1
+ fi
+
+ cat "$pin_path" 1>/dev/null
+ rm "$pin_path" 2>/dev/null
+}
+
+# Function to test map access with configurable write expectations
+# Parameters:
+# $1: Name command (name/pinned)
+# $2: Map name
+# $3: bpftool path
+# $4: key for rw
+# $5: key to delete
+# $6: Whether write should succeed (true/false)
+# $7: BPF_DIR
+# $8: bpf iterator object file path
+access_map() {
+ local name_cmd="$1"
+ local map_name="$2"
+ local bpftool_path="$3"
+ local key_for_rw="$4"
+ local key_to_del="$5"
+ local write_should_succeed="$6"
+ local bpf_dir="$7"
+ local bpf_iter_file_path="$8"
+
+ access_for_read "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw"
+ access_for_write "$name_cmd" "$map_name" "$bpftool_path" "$key_for_rw" \
+ "$write_should_succeed"
+ access_for_deletion "$name_cmd" "$map_name" "$bpftool_path" "$key_to_del" \
+ "$write_should_succeed"
+ iterate_map_elem "$name_cmd" "$map_name" "$bpftool_path" "$bpf_dir" \
+ "$bpf_iter_file_path"
+}
+
+# Function to test map access with configurable write expectations
+# Parameters:
+# $1: Map name
+# $2: bpftool path
+# $3: BPF_DIR
+# $4: Whether write should succeed (true/false)
+# $5: bpf iterator object file path
+test_map_access() {
+ local map_name="$1"
+ local bpftool_path="$2"
+ local bpf_dir="$3"
+ local pin_path="$bpf_dir/${map_name}_pinned"
+ local write_should_succeed="$4"
+ local bpf_iter_file_path="$5"
+
+ # Test access to the map by name.
+ access_map "name" "$map_name" "$bpftool_path" "0 0 0 0" "1 0 0 0" \
+ "$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
+
+ # Pin the map to the BPF filesystem
+ "$bpftool_path" map pin name "$map_name" "$pin_path"
+ if [ ! -e "$pin_path" ]; then
+ echo " Failed to pin $map_name"
+ exit 1
+ fi
+
+ # Test access to the pinned map.
+ access_map "pinned" "$pin_path" "$bpftool_path" "0 0 0 0" "2 0 0 0" \
+ "$write_should_succeed" "$bpf_dir" "$bpf_iter_file_path"
+}
+
+# Function to test map creation and map-of-maps
+# Parameters:
+# $1: bpftool path
+# $2: BPF_DIR
+test_map_creation_and_map_of_maps() {
+ local bpftool_path="$1"
+ local bpf_dir="$2"
+ local outer_map_name="outer_map_tt"
+ local inner_map_name="inner_map_tt"
+
+ "$bpftool_path" map create "$bpf_dir/$inner_map_name" type array key 4 \
+ value 4 entries 4 name "$inner_map_name"
+ if [ ! -f "$bpf_dir/$inner_map_name" ]; then
+ echo " Failed to create inner map file at $bpf_dir/$outer_map_name"
+ return 1
+ fi
+
+ "$bpftool_path" map create "$bpf_dir/$outer_map_name" type hash_of_maps \
+ key 4 value 4 entries 2 name "$outer_map_name" inner_map name "$inner_map_name"
+ if [ ! -f "$bpf_dir/$outer_map_name" ]; then
+ echo " Failed to create outer map file at $bpf_dir/$outer_map_name"
+ return 1
+ fi
+
+ # Add entries to the outer map by name and by pinned path.
+ "$bpftool_path" map update pinned "$bpf_dir/$outer_map_name" key 0 0 0 0 \
+ value pinned "$bpf_dir/$inner_map_name"
+ "$bpftool_path" map update name "$outer_map_name" key 1 0 0 0 value \
+ name "$inner_map_name"
+
+ # The outer map should be full by now.
+ # The following map update command is expected to fail.
+ if "$bpftool_path" map update name "$outer_map_name" key 2 0 0 0 value name \
+ "$inner_map_name" 2>/dev/null; then
+ echo " Update for $outer_map_name succeeded but should have failed"
+ exit 1
+ fi
+}
+
+# Function to test map access with the btf list command
+# Parameters:
+# $1: bpftool path
+test_map_access_with_btf_list() {
+ local bpftool_path="$1"
+
+ # The btf list command iterates over maps for
+ # loaded BPF programs.
+ if ! "$bpftool_path" btf list 1>/dev/null; then
+ echo " Failed to access btf data"
+ exit 1
+ fi
+}
+
+set -eu
+
+trap cleanup_skip EXIT
+
+check_root_privileges
+
+verify_bpftool_path "$BPFTOOL_PATH"
+
+verify_btf_support
+
+trap cleanup EXIT
+
+# Load and attach the BPF programs to control maps access.
+"$BPFTOOL_PATH" prog loadall "$BPF_FILE_PATH" "$BPF_DIR" autoattach
+
+initialize_map_entries "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
+initialize_map_entries "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH"
+
+# Activate the map protection mechanism. Protection status is controlled
+# by a value stored in the prot_status_map at index 0.
+"$BPFTOOL_PATH" map update name prot_status_map key 0 0 0 0 value 1 0 0 0
+
+# Test protected map (write should fail).
+test_map_access "$PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "false" \
+ "$BPF_ITER_FILE_PATH"
+
+# Test not protected map (write should succeed).
+test_map_access "$NOT_PROTECTED_MAP_NAME" "$BPFTOOL_PATH" "$BPF_DIR" "true" \
+ "$BPF_ITER_FILE_PATH"
+
+test_map_creation_and_map_of_maps "$BPFTOOL_PATH" "$BPF_DIR"
+
+test_map_access_with_btf_list "$BPFTOOL_PATH"
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
index 9551d8d5f8f9..78423cf89e01 100644
--- a/tools/testing/selftests/bpf/test_loader.c
+++ b/tools/testing/selftests/bpf/test_loader.c
@@ -40,7 +40,7 @@
#define TEST_TAG_LOAD_MODE_PFX "comment:load_mode="
/* Warning: duplicated in bpf_misc.h */
-#define POINTER_VALUE 0xcafe4all
+#define POINTER_VALUE 0xbadcafe
#define TEST_DATA_LEN 64
#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -318,20 +318,14 @@ static int parse_caps(const char *str, __u64 *val, const char *name)
static int parse_retval(const char *str, int *val, const char *name)
{
- struct {
- char *name;
- int val;
- } named_values[] = {
- { "INT_MIN" , INT_MIN },
- { "POINTER_VALUE", POINTER_VALUE },
- { "TEST_DATA_LEN", TEST_DATA_LEN },
- };
- int i;
-
- for (i = 0; i < ARRAY_SIZE(named_values); ++i) {
- if (strcmp(str, named_values[i].name) != 0)
- continue;
- *val = named_values[i].val;
+ /*
+ * INT_MIN is defined as (-INT_MAX -1), i.e. it doesn't expand to a
+ * single int and cannot be parsed with strtol, so we handle it
+ * separately here. In addition, it expands to different expressions in
+ * different compilers so we use a prefixed _INT_MIN instead.
+ */
+ if (strcmp(str, "_INT_MIN") == 0) {
+ *val = INT_MIN;
return 0;
}
@@ -1103,9 +1097,9 @@ void run_subtest(struct test_loader *tester,
}
}
- do_prog_test_run(bpf_program__fd(tprog), &retval,
- bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false);
- if (retval != subspec->retval && subspec->retval != POINTER_VALUE) {
+ err = do_prog_test_run(bpf_program__fd(tprog), &retval,
+ bpf_program__type(tprog) == BPF_PROG_TYPE_SYSCALL ? true : false);
+ if (!err && retval != subspec->retval && subspec->retval != POINTER_VALUE) {
PRINT_FAIL("Unexpected retval: %d != %d\n", retval, subspec->retval);
goto tobj_cleanup;
}
diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
index fda7589c5023..0921939532c6 100644
--- a/tools/testing/selftests/bpf/test_lru_map.c
+++ b/tools/testing/selftests/bpf/test_lru_map.c
@@ -138,6 +138,18 @@ static int sched_next_online(int pid, int *next_to_try)
return ret;
}
+/* Derive target_free from map_size, same as bpf_common_lru_populate */
+static unsigned int __tgt_size(unsigned int map_size)
+{
+ return (map_size / nr_cpus) / 2;
+}
+
+/* Inverse of how bpf_common_lru_populate derives target_free from map_size. */
+static unsigned int __map_size(unsigned int tgt_free)
+{
+ return tgt_free * nr_cpus * 2;
+}
+
/* Size of the LRU map is 2
* Add key=1 (+1 key)
* Add key=2 (+1 key)
@@ -231,11 +243,11 @@ static void test_lru_sanity0(int map_type, int map_flags)
printf("Pass\n");
}
-/* Size of the LRU map is 1.5*tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Lookup 1 to tgt_free/2
- * Insert 1+tgt_free to 2*tgt_free (+tgt_free keys)
- * => 1+tgt_free/2 to LOCALFREE_TARGET will be removed by LRU
+/* Verify that unreferenced elements are recycled before referenced ones.
+ * Insert elements.
+ * Reference a subset of these.
+ * Insert more, enough to trigger recycling.
+ * Verify that unreferenced are recycled.
*/
static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
{
@@ -257,7 +269,7 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
- map_size = tgt_free + batch_size;
+ map_size = __map_size(tgt_free) + batch_size;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
@@ -266,13 +278,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
value[0] = 1234;
- /* Insert 1 to tgt_free (+tgt_free keys) */
- end_key = 1 + tgt_free;
+ /* Insert map_size - batch_size keys */
+ end_key = 1 + __map_size(tgt_free);
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
- /* Lookup 1 to tgt_free/2 */
+ /* Lookup 1 to batch_size */
end_key = 1 + batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
@@ -280,12 +292,13 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
BPF_NOEXIST));
}
- /* Insert 1+tgt_free to 2*tgt_free
- * => 1+tgt_free/2 to LOCALFREE_TARGET will be
+ /* Insert another map_size - batch_size keys
+ * Map will contain 1 to batch_size plus these latest, i.e.,
+ * => previous 1+batch_size to map_size - batch_size will have been
* removed by LRU
*/
- key = 1 + tgt_free;
- end_key = key + tgt_free;
+ key = 1 + __map_size(tgt_free);
+ end_key = key + __map_size(tgt_free);
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
@@ -301,17 +314,8 @@ static void test_lru_sanity1(int map_type, int map_flags, unsigned int tgt_free)
printf("Pass\n");
}
-/* Size of the LRU map 1.5 * tgt_free
- * Insert 1 to tgt_free (+tgt_free keys)
- * Update 1 to tgt_free/2
- * => The original 1 to tgt_free/2 will be removed due to
- * the LRU shrink process
- * Re-insert 1 to tgt_free/2 again and do a lookup immeidately
- * Insert 1+tgt_free to tgt_free*3/2
- * Insert 1+tgt_free*3/2 to tgt_free*5/2
- * => Key 1+tgt_free to tgt_free*3/2
- * will be removed from LRU because it has never
- * been lookup and ref bit is not set
+/* Verify that insertions exceeding map size will recycle the oldest.
+ * Verify that unreferenced elements are recycled before referenced.
*/
static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
{
@@ -334,7 +338,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
batch_size = tgt_free / 2;
assert(batch_size * 2 == tgt_free);
- map_size = tgt_free + batch_size;
+ map_size = __map_size(tgt_free) + batch_size;
lru_map_fd = create_map(map_type, map_flags, map_size);
assert(lru_map_fd != -1);
@@ -343,8 +347,8 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
value[0] = 1234;
- /* Insert 1 to tgt_free (+tgt_free keys) */
- end_key = 1 + tgt_free;
+ /* Insert map_size - batch_size keys */
+ end_key = 1 + __map_size(tgt_free);
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
@@ -357,8 +361,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
* shrink the inactive list to get tgt_free
* number of free nodes.
*
- * Hence, the oldest key 1 to tgt_free/2
- * are removed from the LRU list.
+ * Hence, the oldest key is removed from the LRU list.
*/
key = 1;
if (map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) {
@@ -370,8 +373,7 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
BPF_EXIST));
}
- /* Re-insert 1 to tgt_free/2 again and do a lookup
- * immeidately.
+ /* Re-insert 1 to batch_size again and do a lookup immediately.
*/
end_key = 1 + batch_size;
value[0] = 4321;
@@ -387,17 +389,18 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
value[0] = 1234;
- /* Insert 1+tgt_free to tgt_free*3/2 */
- end_key = 1 + tgt_free + batch_size;
- for (key = 1 + tgt_free; key < end_key; key++)
+ /* Insert batch_size new elements */
+ key = 1 + __map_size(tgt_free);
+ end_key = key + batch_size;
+ for (; key < end_key; key++)
/* These newly added but not referenced keys will be
* gone during the next LRU shrink.
*/
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
- /* Insert 1+tgt_free*3/2 to tgt_free*5/2 */
- end_key = key + tgt_free;
+ /* Insert map_size - batch_size elements */
+ end_key += __map_size(tgt_free);
for (; key < end_key; key++) {
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
@@ -413,12 +416,12 @@ static void test_lru_sanity2(int map_type, int map_flags, unsigned int tgt_free)
printf("Pass\n");
}
-/* Size of the LRU map is 2*tgt_free
- * It is to test the active/inactive list rotation
- * Insert 1 to 2*tgt_free (+2*tgt_free keys)
- * Lookup key 1 to tgt_free*3/2
- * Add 1+2*tgt_free to tgt_free*5/2 (+tgt_free/2 keys)
- * => key 1+tgt_free*3/2 to 2*tgt_free are removed from LRU
+/* Test the active/inactive list rotation
+ *
+ * Fill the whole map, deplete the free list.
+ * Reference all except the last lru->target_free elements.
+ * Insert lru->target_free new elements. This triggers one shrink.
+ * Verify that the non-referenced elements are replaced.
*/
static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
{
@@ -437,8 +440,7 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
assert(sched_next_online(0, &next_cpu) != -1);
- batch_size = tgt_free / 2;
- assert(batch_size * 2 == tgt_free);
+ batch_size = __tgt_size(tgt_free);
map_size = tgt_free * 2;
lru_map_fd = create_map(map_type, map_flags, map_size);
@@ -449,23 +451,21 @@ static void test_lru_sanity3(int map_type, int map_flags, unsigned int tgt_free)
value[0] = 1234;
- /* Insert 1 to 2*tgt_free (+2*tgt_free keys) */
- end_key = 1 + (2 * tgt_free);
+ /* Fill the map */
+ end_key = 1 + map_size;
for (key = 1; key < end_key; key++)
assert(!bpf_map_update_elem(lru_map_fd, &key, value,
BPF_NOEXIST));
- /* Lookup key 1 to tgt_free*3/2 */
- end_key = tgt_free + batch_size;
+ /* Reference all but the last batch_size */
+ end_key = 1 + map_size - batch_size;
for (key = 1; key < end_key; key++) {
assert(!bpf_map_lookup_elem_with_ref_bit(lru_map_fd, key, value));
assert(!bpf_map_update_elem(expected_map_fd, &key, value,
BPF_NOEXIST));
}
- /* Add 1+2*tgt_free to tgt_free*5/2
- * (+tgt_free/2 keys)
- */
+ /* Insert new batch_size: replaces the non-referenced elements */
key = 2 * tgt_free + 1;
end_key = key + batch_size;
for (; key < end_key; key++) {
@@ -500,7 +500,8 @@ static void test_lru_sanity4(int map_type, int map_flags, unsigned int tgt_free)
lru_map_fd = create_map(map_type, map_flags,
3 * tgt_free * nr_cpus);
else
- lru_map_fd = create_map(map_type, map_flags, 3 * tgt_free);
+ lru_map_fd = create_map(map_type, map_flags,
+ 3 * __map_size(tgt_free));
assert(lru_map_fd != -1);
expected_map_fd = create_map(BPF_MAP_TYPE_HASH, 0,
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 870694f2a359..df2222a1806f 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -460,6 +460,34 @@ static inline void *u64_to_ptr(__u64 ptr)
return (void *) (unsigned long) ptr;
}
+static inline __u32 id_from_prog_fd(int fd)
+{
+ struct bpf_prog_info prog_info = {};
+ __u32 prog_info_len = sizeof(prog_info);
+ int err;
+
+ err = bpf_obj_get_info_by_fd(fd, &prog_info, &prog_info_len);
+ if (!ASSERT_OK(err, "id_from_prog_fd"))
+ return 0;
+
+ ASSERT_NEQ(prog_info.id, 0, "prog_info.id");
+ return prog_info.id;
+}
+
+static inline __u32 id_from_link_fd(int fd)
+{
+ struct bpf_link_info link_info = {};
+ __u32 link_info_len = sizeof(link_info);
+ int err;
+
+ err = bpf_link_get_info_by_fd(fd, &link_info, &link_info_len);
+ if (!ASSERT_OK(err, "id_from_link_fd"))
+ return 0;
+
+ ASSERT_NEQ(link_info.id, 0, "link_info.id");
+ return link_info.id;
+}
+
int bpf_find_map(const char *test, struct bpf_object *obj, const char *name);
int compare_map_keys(int map1_fd, int map2_fd);
int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c
index 220f6a963813..f997d7ec8fd0 100644
--- a/tools/testing/selftests/bpf/unpriv_helpers.c
+++ b/tools/testing/selftests/bpf/unpriv_helpers.c
@@ -1,15 +1,76 @@
// SPDX-License-Identifier: GPL-2.0-only
+#include <errno.h>
+#include <limits.h>
#include <stdbool.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
+#include <sys/utsname.h>
#include <unistd.h>
#include <fcntl.h>
+#include <zlib.h>
#include "unpriv_helpers.h"
-static bool get_mitigations_off(void)
+static gzFile open_config(void)
+{
+ struct utsname uts;
+ char buf[PATH_MAX];
+ gzFile config;
+
+ if (uname(&uts)) {
+ perror("uname");
+ goto config_gz;
+ }
+
+ snprintf(buf, sizeof(buf), "/boot/config-%s", uts.release);
+ config = gzopen(buf, "rb");
+ if (config)
+ return config;
+ fprintf(stderr, "gzopen %s: %s\n", buf, strerror(errno));
+
+config_gz:
+ config = gzopen("/proc/config.gz", "rb");
+ if (!config)
+ perror("gzopen /proc/config.gz");
+ return config;
+}
+
+static int config_contains(const char *pat)
+{
+ const char *msg;
+ char buf[1024];
+ gzFile config;
+ int n, err;
+
+ config = open_config();
+ if (!config)
+ return -1;
+
+ for (;;) {
+ if (!gzgets(config, buf, sizeof(buf))) {
+ msg = gzerror(config, &err);
+ if (err == Z_ERRNO)
+ perror("gzgets /proc/config.gz");
+ else if (err != Z_OK)
+ fprintf(stderr, "gzgets /proc/config.gz: %s", msg);
+ gzclose(config);
+ return -1;
+ }
+ n = strlen(buf);
+ if (buf[n - 1] == '\n')
+ buf[n - 1] = 0;
+ if (strcmp(buf, pat) == 0) {
+ gzclose(config);
+ return 1;
+ }
+ }
+ gzclose(config);
+ return 0;
+}
+
+static bool cmdline_contains(const char *pat)
{
char cmdline[4096], *c;
int fd, ret = false;
@@ -27,7 +88,7 @@ static bool get_mitigations_off(void)
cmdline[sizeof(cmdline) - 1] = '\0';
for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) {
- if (strncmp(c, "mitigations=off", strlen(c)))
+ if (strncmp(c, pat, strlen(c)))
continue;
ret = true;
break;
@@ -37,8 +98,21 @@ out:
return ret;
}
+static int get_mitigations_off(void)
+{
+ int enabled_in_config;
+
+ if (cmdline_contains("mitigations=off"))
+ return 1;
+ enabled_in_config = config_contains("CONFIG_CPU_MITIGATIONS=y");
+ if (enabled_in_config < 0)
+ return -1;
+ return !enabled_in_config;
+}
+
bool get_unpriv_disabled(void)
{
+ int mitigations_off;
bool disabled;
char buf[2];
FILE *fd;
@@ -52,5 +126,19 @@ bool get_unpriv_disabled(void)
disabled = true;
}
- return disabled ? true : get_mitigations_off();
+ if (disabled)
+ return true;
+
+ /*
+ * Some unpriv tests rely on spectre mitigations being on.
+ * If mitigations are off or status can't be determined
+ * assume that unpriv tests are disabled.
+ */
+ mitigations_off = get_mitigations_off();
+ if (mitigations_off < 0) {
+ fprintf(stderr,
+ "Can't determine if mitigations are enabled, disabling unpriv tests.");
+ return true;
+ }
+ return mitigations_off;
}
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index ee454327e5c6..77207b498c6f 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -2,14 +2,13 @@
"dead code: start",
.insns = {
BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_JMP_IMM(BPF_JA, 0, 0, 2),
BPF_MOV64_IMM(BPF_REG_0, 7),
BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 7,
},
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index 43776f6f92f4..91d83e9cb148 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -84,11 +84,10 @@
BPF_JMP32_IMM(BPF_JSET, BPF_REG_7, 0x10, 1),
BPF_EXIT_INSN(),
BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x10, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -149,11 +148,10 @@
BPF_JMP32_IMM(BPF_JEQ, BPF_REG_7, 0x10, 1),
BPF_EXIT_INSN(),
BPF_JMP32_IMM(BPF_JSGE, BPF_REG_7, 0xf, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -214,11 +212,10 @@
BPF_JMP32_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
BPF_EXIT_INSN(),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -283,11 +280,10 @@
BPF_JMP32_REG(BPF_JGE, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -354,11 +350,10 @@
BPF_JMP32_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -425,11 +420,10 @@
BPF_JMP32_REG(BPF_JLE, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP32_IMM(BPF_JLE, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -496,11 +490,10 @@
BPF_JMP32_REG(BPF_JLT, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -567,11 +560,10 @@
BPF_JMP32_REG(BPF_JSGE, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -638,11 +630,10 @@
BPF_JMP32_REG(BPF_JSGT, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, -2, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -709,11 +700,10 @@
BPF_JMP32_REG(BPF_JSLE, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSLE, BPF_REG_7, 0x7ffffff0, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -780,11 +770,10 @@
BPF_JMP32_REG(BPF_JSLT, BPF_REG_7, BPF_REG_8, 1),
BPF_EXIT_INSN(),
BPF_JMP32_IMM(BPF_JSLT, BPF_REG_7, -1, 1),
+ /* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .errstr_unpriv = "R0 invalid mem access 'scalar'",
- .result_unpriv = REJECT,
.result = ACCEPT,
.retval = 2,
.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 11fc68da735e..e901eefd774a 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -78,12 +78,11 @@
.insns = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.retval = 1,
.result = ACCEPT,
},
@@ -136,13 +135,12 @@
BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
},
{
@@ -154,16 +152,16 @@
BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
BPF_EXIT_INSN(),
BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+ /* unpriv: nospec (inserted to prevent "R9 !read_ok") */
BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
BPF_EXIT_INSN(),
},
.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
- .errstr_unpriv = "R9 !read_ok",
- .result_unpriv = REJECT,
.result = ACCEPT,
},
diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
index b2bb20b00952..1e9f61f9fd0a 100644
--- a/tools/testing/selftests/bpf/veristat.c
+++ b/tools/testing/selftests/bpf/veristat.c
@@ -49,6 +49,7 @@ enum stat_id {
STACK,
PROG_TYPE,
ATTACH_TYPE,
+ MEMORY_PEAK,
FILE_NAME,
PROG_NAME,
@@ -155,13 +156,27 @@ struct filter {
bool abs;
};
-struct var_preset {
- char *name;
+struct rvalue {
enum { INTEGRAL, ENUMERATOR } type;
union {
long long ivalue;
char *svalue;
};
+};
+
+struct field_access {
+ enum { FIELD_NAME, ARRAY_INDEX } type;
+ union {
+ char *name;
+ struct rvalue index;
+ };
+};
+
+struct var_preset {
+ struct field_access *atoms;
+ int atom_count;
+ char *full_name;
+ struct rvalue value;
bool applied;
};
@@ -208,6 +223,9 @@ static struct env {
int top_src_lines;
struct var_preset *presets;
int npresets;
+ char orig_cgroup[PATH_MAX];
+ char stat_cgroup[PATH_MAX];
+ int memory_peak_fd;
} env;
static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va_list args)
@@ -219,6 +237,22 @@ static int libbpf_print_fn(enum libbpf_print_level level, const char *format, va
return vfprintf(stderr, format, args);
}
+#define log_errno(fmt, ...) log_errno_aux(__FILE__, __LINE__, fmt, ##__VA_ARGS__)
+
+__printf(3, 4)
+static int log_errno_aux(const char *file, int line, const char *fmt, ...)
+{
+ int err = -errno;
+ va_list ap;
+
+ va_start(ap, fmt);
+ fprintf(stderr, "%s:%d: ", file, line);
+ vfprintf(stderr, fmt, ap);
+ fprintf(stderr, " failed with error '%s'.\n", strerror(errno));
+ va_end(ap);
+ return err;
+}
+
#ifndef VERISTAT_VERSION
#define VERISTAT_VERSION "<kernel>"
#endif
@@ -344,6 +378,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
fprintf(stderr, "invalid top N specifier: %s\n", arg);
argp_usage(state);
}
+ break;
case 'C':
env.comparison_mode = true;
break;
@@ -734,13 +769,13 @@ cleanup:
}
static const struct stat_specs default_csv_output_spec = {
- .spec_cnt = 14,
+ .spec_cnt = 15,
.ids = {
FILE_NAME, PROG_NAME, VERDICT, DURATION,
TOTAL_INSNS, TOTAL_STATES, PEAK_STATES,
MAX_STATES_PER_INSN, MARK_READ_MAX_LEN,
SIZE, JITED_SIZE, PROG_TYPE, ATTACH_TYPE,
- STACK,
+ STACK, MEMORY_PEAK,
},
};
@@ -781,6 +816,7 @@ static struct stat_def {
[STACK] = {"Stack depth", {"stack_depth", "stack"}, },
[PROG_TYPE] = { "Program type", {"prog_type"}, },
[ATTACH_TYPE] = { "Attach type", {"attach_type", }, },
+ [MEMORY_PEAK] = { "Peak memory (MiB)", {"mem_peak", }, },
};
static bool parse_stat_id_var(const char *name, size_t len, int *id,
@@ -1182,6 +1218,7 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch
case BPF_MAP_TYPE_TASK_STORAGE:
case BPF_MAP_TYPE_INODE_STORAGE:
case BPF_MAP_TYPE_CGROUP_STORAGE:
+ case BPF_MAP_TYPE_CGRP_STORAGE:
break;
case BPF_MAP_TYPE_STRUCT_OPS:
mask_unrelated_struct_ops_progs(obj, map, prog);
@@ -1278,16 +1315,243 @@ static int max_verifier_log_size(void)
return log_size;
}
+static bool output_stat_enabled(int id)
+{
+ int i;
+
+ for (i = 0; i < env.output_spec.spec_cnt; i++)
+ if (env.output_spec.ids[i] == id)
+ return true;
+ return false;
+}
+
+__printf(2, 3)
+static int write_one_line(const char *file, const char *fmt, ...)
+{
+ int err, saved_errno;
+ va_list ap;
+ FILE *f;
+
+ f = fopen(file, "w");
+ if (!f)
+ return -1;
+
+ va_start(ap, fmt);
+ errno = 0;
+ err = vfprintf(f, fmt, ap);
+ saved_errno = errno;
+ va_end(ap);
+ fclose(f);
+ errno = saved_errno;
+ return err < 0 ? -1 : 0;
+}
+
+__scanf(3, 4)
+static int scanf_one_line(const char *file, int fields_expected, const char *fmt, ...)
+{
+ int res = 0, saved_errno = 0;
+ char *line = NULL;
+ size_t line_len;
+ va_list ap;
+ FILE *f;
+
+ f = fopen(file, "r");
+ if (!f)
+ return -1;
+
+ va_start(ap, fmt);
+ while (getline(&line, &line_len, f) > 0) {
+ res = vsscanf(line, fmt, ap);
+ if (res == fields_expected)
+ goto out;
+ }
+ if (ferror(f)) {
+ saved_errno = errno;
+ res = -1;
+ }
+
+out:
+ va_end(ap);
+ free(line);
+ fclose(f);
+ errno = saved_errno;
+ return res;
+}
+
+static void destroy_stat_cgroup(void)
+{
+ char buf[PATH_MAX];
+ int err;
+
+ close(env.memory_peak_fd);
+
+ if (env.orig_cgroup[0]) {
+ snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.orig_cgroup);
+ err = write_one_line(buf, "%d\n", getpid());
+ if (err < 0)
+ log_errno("moving self to original cgroup %s\n", env.orig_cgroup);
+ }
+
+ if (env.stat_cgroup[0]) {
+ err = rmdir(env.stat_cgroup);
+ if (err < 0)
+ log_errno("deletion of cgroup %s", env.stat_cgroup);
+ }
+
+ env.memory_peak_fd = -1;
+ env.orig_cgroup[0] = 0;
+ env.stat_cgroup[0] = 0;
+}
+
+/*
+ * Creates a cgroup at /sys/fs/cgroup/veristat-accounting-<pid>,
+ * moves current process to this cgroup.
+ */
+static void create_stat_cgroup(void)
+{
+ char cgroup_fs_mount[4096];
+ char buf[4096];
+ int err;
+
+ env.memory_peak_fd = -1;
+
+ if (!output_stat_enabled(MEMORY_PEAK))
+ return;
+
+ err = scanf_one_line("/proc/self/mounts", 2, "%*s %4095s cgroup2 %s",
+ cgroup_fs_mount, buf);
+ if (err != 2) {
+ if (err < 0)
+ log_errno("reading /proc/self/mounts");
+ else if (!env.quiet)
+ fprintf(stderr, "Can't find cgroupfs v2 mount point.\n");
+ goto err_out;
+ }
+
+ /* cgroup-v2.rst promises the line "0::<group>" for cgroups v2 */
+ err = scanf_one_line("/proc/self/cgroup", 1, "0::%4095s", buf);
+ if (err != 1) {
+ if (err < 0)
+ log_errno("reading /proc/self/cgroup");
+ else if (!env.quiet)
+ fprintf(stderr, "Can't infer veristat process cgroup.");
+ goto err_out;
+ }
+
+ snprintf(env.orig_cgroup, sizeof(env.orig_cgroup), "%s/%s", cgroup_fs_mount, buf);
+
+ snprintf(buf, sizeof(buf), "%s/veristat-accounting-%d", cgroup_fs_mount, getpid());
+ err = mkdir(buf, 0777);
+ if (err < 0) {
+ log_errno("creation of cgroup %s", buf);
+ goto err_out;
+ }
+ strcpy(env.stat_cgroup, buf);
+
+ snprintf(buf, sizeof(buf), "%s/cgroup.procs", env.stat_cgroup);
+ err = write_one_line(buf, "%d\n", getpid());
+ if (err < 0) {
+ log_errno("entering cgroup %s", buf);
+ goto err_out;
+ }
+
+ snprintf(buf, sizeof(buf), "%s/memory.peak", env.stat_cgroup);
+ env.memory_peak_fd = open(buf, O_RDWR | O_APPEND);
+ if (env.memory_peak_fd < 0) {
+ log_errno("opening %s", buf);
+ goto err_out;
+ }
+
+ return;
+
+err_out:
+ if (!env.quiet)
+ fprintf(stderr, "Memory usage metric unavailable.\n");
+ destroy_stat_cgroup();
+}
+
+/* Current value of /sys/fs/cgroup/veristat-accounting-<pid>/memory.peak */
+static long cgroup_memory_peak(void)
+{
+ long err, memory_peak;
+ char buf[32];
+
+ if (env.memory_peak_fd < 0)
+ return -1;
+
+ err = pread(env.memory_peak_fd, buf, sizeof(buf) - 1, 0);
+ if (err <= 0) {
+ log_errno("pread(%s/memory.peak)", env.stat_cgroup);
+ return -1;
+ }
+
+ buf[err] = 0;
+ errno = 0;
+ memory_peak = strtoll(buf, NULL, 10);
+ if (errno) {
+ log_errno("%s/memory.peak:strtoll(%s)", env.stat_cgroup, buf);
+ return -1;
+ }
+
+ return memory_peak;
+}
+
+static int reset_stat_cgroup(void)
+{
+ char buf[] = "r\n";
+ int err;
+
+ if (env.memory_peak_fd < 0)
+ return -1;
+
+ err = pwrite(env.memory_peak_fd, buf, sizeof(buf), 0);
+ if (err <= 0) {
+ log_errno("pwrite(%s/memory.peak)", env.stat_cgroup);
+ return -1;
+ }
+ return 0;
+}
+
+static int parse_rvalue(const char *val, struct rvalue *rvalue)
+{
+ long long value;
+ char *val_end;
+
+ if (val[0] == '-' || isdigit(val[0])) {
+ /* must be a number */
+ errno = 0;
+ value = strtoll(val, &val_end, 0);
+ if (errno == ERANGE) {
+ errno = 0;
+ value = strtoull(val, &val_end, 0);
+ }
+ if (errno || *val_end != '\0') {
+ fprintf(stderr, "Failed to parse value '%s'\n", val);
+ return -EINVAL;
+ }
+ rvalue->ivalue = value;
+ rvalue->type = INTEGRAL;
+ } else {
+ /* if not a number, consider it enum value */
+ rvalue->svalue = strdup(val);
+ if (!rvalue->svalue)
+ return -ENOMEM;
+ rvalue->type = ENUMERATOR;
+ }
+ return 0;
+}
+
static int process_prog(const char *filename, struct bpf_object *obj, struct bpf_program *prog)
{
const char *base_filename = basename(strdupa(filename));
const char *prog_name = bpf_program__name(prog);
+ long mem_peak_a, mem_peak_b, mem_peak = -1;
char *buf;
int buf_sz, log_level;
struct verif_stats *stats;
struct bpf_prog_info info;
__u32 info_len = sizeof(info);
- int err = 0;
+ int err = 0, cgroup_err;
void *tmp;
int fd;
@@ -1332,7 +1596,15 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
if (env.force_reg_invariants)
bpf_program__set_flags(prog, bpf_program__flags(prog) | BPF_F_TEST_REG_INVARIANTS);
- err = bpf_object__load(obj);
+ err = bpf_object__prepare(obj);
+ if (!err) {
+ cgroup_err = reset_stat_cgroup();
+ mem_peak_a = cgroup_memory_peak();
+ err = bpf_object__load(obj);
+ mem_peak_b = cgroup_memory_peak();
+ if (!cgroup_err && mem_peak_a >= 0 && mem_peak_b >= 0)
+ mem_peak = mem_peak_b - mem_peak_a;
+ }
env.progs_processed++;
stats->file_name = strdup(base_filename);
@@ -1341,6 +1613,7 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
stats->stats[SIZE] = bpf_program__insn_cnt(prog);
stats->stats[PROG_TYPE] = bpf_program__type(prog);
stats->stats[ATTACH_TYPE] = bpf_program__expected_attach_type(prog);
+ stats->stats[MEMORY_PEAK] = mem_peak < 0 ? -1 : mem_peak / (1024 * 1024);
memset(&info, 0, info_len);
fd = bpf_program__fd(prog);
@@ -1361,15 +1634,70 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf
free(buf);
return 0;
-};
+}
+
+static int append_preset_atom(struct var_preset *preset, char *value, bool is_index)
+{
+ struct field_access *tmp;
+ int i = preset->atom_count;
+ int err;
+
+ tmp = reallocarray(preset->atoms, i + 1, sizeof(*preset->atoms));
+ if (!tmp)
+ return -ENOMEM;
+
+ preset->atoms = tmp;
+ preset->atom_count++;
+
+ if (is_index) {
+ preset->atoms[i].type = ARRAY_INDEX;
+ err = parse_rvalue(value, &preset->atoms[i].index);
+ if (err)
+ return err;
+ } else {
+ preset->atoms[i].type = FIELD_NAME;
+ preset->atoms[i].name = strdup(value);
+ if (!preset->atoms[i].name)
+ return -ENOMEM;
+ }
+ return 0;
+}
+
+static int parse_var_atoms(const char *full_var, struct var_preset *preset)
+{
+ char expr[256], var[256], *name, *saveptr;
+ int n, len, off;
+
+ snprintf(expr, sizeof(expr), "%s", full_var);
+ preset->atom_count = 0;
+ while ((name = strtok_r(preset->atom_count ? NULL : expr, ".", &saveptr))) {
+ len = strlen(name);
+ /* parse variable name */
+ if (sscanf(name, "%[a-zA-Z0-9_] %n", var, &off) != 1) {
+ fprintf(stderr, "Can't parse %s\n", name);
+ return -EINVAL;
+ }
+ append_preset_atom(preset, var, false);
+
+ /* parse optional array indexes */
+ while (off < len) {
+ if (sscanf(name + off, " [ %[a-zA-Z0-9_] ] %n", var, &n) != 1) {
+ fprintf(stderr, "Can't parse %s as index\n", name + off);
+ return -EINVAL;
+ }
+ append_preset_atom(preset, var, true);
+ off += n;
+ }
+ }
+ return 0;
+}
static int append_var_preset(struct var_preset **presets, int *cnt, const char *expr)
{
void *tmp;
struct var_preset *cur;
- char var[256], val[256], *val_end;
- long long value;
- int n;
+ char var[256], val[256];
+ int n, err, i;
tmp = realloc(*presets, (*cnt + 1) * sizeof(**presets));
if (!tmp)
@@ -1379,37 +1707,29 @@ static int append_var_preset(struct var_preset **presets, int *cnt, const char *
memset(cur, 0, sizeof(*cur));
(*cnt)++;
- if (sscanf(expr, "%s = %s %n", var, val, &n) != 2 || n != strlen(expr)) {
+ if (sscanf(expr, " %[][a-zA-Z0-9_. ] = %s %n", var, val, &n) != 2 || n != strlen(expr)) {
fprintf(stderr, "Failed to parse expression '%s'\n", expr);
return -EINVAL;
}
-
- if (val[0] == '-' || isdigit(val[0])) {
- /* must be a number */
- errno = 0;
- value = strtoll(val, &val_end, 0);
- if (errno == ERANGE) {
- errno = 0;
- value = strtoull(val, &val_end, 0);
- }
- if (errno || *val_end != '\0') {
- fprintf(stderr, "Failed to parse value '%s'\n", val);
- return -EINVAL;
- }
- cur->ivalue = value;
- cur->type = INTEGRAL;
- } else {
- /* if not a number, consider it enum value */
- cur->svalue = strdup(val);
- if (!cur->svalue)
- return -ENOMEM;
- cur->type = ENUMERATOR;
+ /* Remove trailing spaces from var, as scanf may add those */
+ for (i = strlen(var) - 1; i > 0; --i) {
+ if (!isspace(var[i]))
+ break;
+ var[i] = '\0';
}
- cur->name = strdup(var);
- if (!cur->name)
+ err = parse_rvalue(val, &cur->value);
+ if (err)
+ return err;
+
+ cur->full_name = strdup(var);
+ if (!cur->full_name)
return -ENOMEM;
+ err = parse_var_atoms(var, cur);
+ if (err)
+ return err;
+
return 0;
}
@@ -1486,22 +1806,96 @@ static bool is_preset_supported(const struct btf_type *t)
return btf_is_int(t) || btf_is_enum(t) || btf_is_enum64(t);
}
-const int btf_find_member(const struct btf *btf,
- const struct btf_type *parent_type,
- __u32 parent_offset,
- const char *member_name,
- int *member_tid,
- __u32 *member_offset)
+static int find_enum_value(const struct btf *btf, const char *name, long long *value)
+{
+ const struct btf_type *t;
+ int cnt, i;
+ long long lvalue;
+
+ cnt = btf__type_cnt(btf);
+ for (i = 1; i != cnt; ++i) {
+ t = btf__type_by_id(btf, i);
+
+ if (!btf_is_any_enum(t))
+ continue;
+
+ if (enum_value_from_name(btf, t, name, &lvalue) == 0) {
+ *value = lvalue;
+ return 0;
+ }
+ }
+ return -ESRCH;
+}
+
+static int resolve_rvalue(struct btf *btf, const struct rvalue *rvalue, long long *result)
+{
+ int err = 0;
+
+ switch (rvalue->type) {
+ case INTEGRAL:
+ *result = rvalue->ivalue;
+ return 0;
+ case ENUMERATOR:
+ err = find_enum_value(btf, rvalue->svalue, result);
+ if (err) {
+ fprintf(stderr, "Can't resolve enum value %s\n", rvalue->svalue);
+ return err;
+ }
+ return 0;
+ default:
+ fprintf(stderr, "Unknown rvalue type\n");
+ return -EOPNOTSUPP;
+ }
+ return 0;
+}
+
+static int adjust_var_secinfo_array(struct btf *btf, int tid, struct field_access *atom,
+ const char *array_name, struct btf_var_secinfo *sinfo)
+{
+ const struct btf_type *t;
+ struct btf_array *barr;
+ long long idx;
+ int err;
+
+ tid = btf__resolve_type(btf, tid);
+ t = btf__type_by_id(btf, tid);
+ if (!btf_is_array(t)) {
+ fprintf(stderr, "Array index is not expected for %s\n",
+ array_name);
+ return -EINVAL;
+ }
+ barr = btf_array(t);
+ err = resolve_rvalue(btf, &atom->index, &idx);
+ if (err)
+ return err;
+ if (idx < 0 || idx >= barr->nelems) {
+ fprintf(stderr, "Array index %lld is out of bounds [0, %u]: %s\n",
+ idx, barr->nelems, array_name);
+ return -EINVAL;
+ }
+ sinfo->size = btf__resolve_size(btf, barr->type);
+ sinfo->offset += sinfo->size * idx;
+ sinfo->type = btf__resolve_type(btf, barr->type);
+ return 0;
+}
+
+static int adjust_var_secinfo_member(const struct btf *btf,
+ const struct btf_type *parent_type,
+ __u32 parent_offset,
+ const char *member_name,
+ struct btf_var_secinfo *sinfo)
{
int i;
- if (!btf_is_composite(parent_type))
+ if (!btf_is_composite(parent_type)) {
+ fprintf(stderr, "Can't resolve field %s for non-composite type\n", member_name);
return -EINVAL;
+ }
for (i = 0; i < btf_vlen(parent_type); ++i) {
const struct btf_member *member;
const struct btf_type *member_type;
- int tid;
+ int tid, off;
member = btf_members(parent_type) + i;
tid = btf__resolve_type(btf, member->type);
@@ -1509,6 +1903,7 @@ const int btf_find_member(const struct btf *btf,
return -EINVAL;
member_type = btf__type_by_id(btf, tid);
+ off = parent_offset + member->offset;
if (member->name_off) {
const char *name = btf__name_by_offset(btf, member->name_off);
@@ -1518,15 +1913,16 @@ const int btf_find_member(const struct btf *btf,
name);
return -EINVAL;
}
- *member_offset = parent_offset + member->offset;
- *member_tid = tid;
+ sinfo->offset += off / 8;
+ sinfo->type = tid;
+ sinfo->size = member_type->size;
return 0;
}
} else if (btf_is_composite(member_type)) {
int err;
- err = btf_find_member(btf, member_type, parent_offset + member->offset,
- member_name, member_tid, member_offset);
+ err = adjust_var_secinfo_member(btf, member_type, off,
+ member_name, sinfo);
if (!err)
return 0;
}
@@ -1536,30 +1932,41 @@ const int btf_find_member(const struct btf *btf,
}
static int adjust_var_secinfo(struct btf *btf, const struct btf_type *t,
- struct btf_var_secinfo *sinfo, const char *var)
+ struct btf_var_secinfo *sinfo, struct var_preset *preset)
{
- char expr[256], *saveptr;
- const struct btf_type *base_type, *member_type;
- int err, member_tid;
- char *name;
- __u32 member_offset = 0;
+ const struct btf_type *base_type;
+ const char *prev_name;
+ int err, i;
+ int tid;
- base_type = btf__type_by_id(btf, btf__resolve_type(btf, t->type));
- snprintf(expr, sizeof(expr), "%s", var);
- strtok_r(expr, ".", &saveptr);
+ assert(preset->atom_count > 0);
+ assert(preset->atoms[0].type == FIELD_NAME);
- while ((name = strtok_r(NULL, ".", &saveptr))) {
- err = btf_find_member(btf, base_type, 0, name, &member_tid, &member_offset);
- if (err) {
- fprintf(stderr, "Could not find member %s for variable %s\n", name, var);
- return err;
+ tid = btf__resolve_type(btf, t->type);
+ base_type = btf__type_by_id(btf, tid);
+ prev_name = preset->atoms[0].name;
+
+ for (i = 1; i < preset->atom_count; ++i) {
+ struct field_access *atom = preset->atoms + i;
+
+ switch (atom->type) {
+ case ARRAY_INDEX:
+ err = adjust_var_secinfo_array(btf, tid, atom, prev_name, sinfo);
+ break;
+ case FIELD_NAME:
+ err = adjust_var_secinfo_member(btf, base_type, 0, atom->name, sinfo);
+ prev_name = atom->name;
+ break;
+ default:
+ fprintf(stderr, "Unknown field_access type\n");
+ return -EOPNOTSUPP;
}
- member_type = btf__type_by_id(btf, member_tid);
- sinfo->offset += member_offset / 8;
- sinfo->size = member_type->size;
- sinfo->type = member_tid;
- base_type = member_type;
+ if (err)
+ return err;
+ base_type = btf__type_by_id(btf, sinfo->type);
+ tid = sinfo->type;
}
+
return 0;
}
@@ -1569,7 +1976,7 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf,
{
const struct btf_type *base_type;
void *ptr;
- long long value = preset->ivalue;
+ long long value = preset->value.ivalue;
size_t size;
base_type = btf__type_by_id(btf, btf__resolve_type(btf, sinfo->type));
@@ -1578,22 +1985,23 @@ static int set_global_var(struct bpf_object *obj, struct btf *btf,
return -EINVAL;
}
if (!is_preset_supported(base_type)) {
- fprintf(stderr, "Setting value for type %s is not supported\n",
- btf__name_by_offset(btf, base_type->name_off));
+ fprintf(stderr, "Can't set %s. Only ints and enums are supported\n",
+ preset->full_name);
return -EINVAL;
}
- if (preset->type == ENUMERATOR) {
+ if (preset->value.type == ENUMERATOR) {
if (btf_is_any_enum(base_type)) {
- if (enum_value_from_name(btf, base_type, preset->svalue, &value)) {
+ if (enum_value_from_name(btf, base_type, preset->value.svalue, &value)) {
fprintf(stderr,
"Failed to find integer value for enum element %s\n",
- preset->svalue);
+ preset->value.svalue);
return -EINVAL;
}
} else {
fprintf(stderr, "Value %s is not supported for type %s\n",
- preset->svalue, btf__name_by_offset(btf, base_type->name_off));
+ preset->value.svalue,
+ btf__name_by_offset(btf, base_type->name_off));
return -EINVAL;
}
}
@@ -1660,20 +2068,16 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i
for (j = 0; j < n; ++j, ++sinfo) {
const struct btf_type *var_type = btf__type_by_id(btf, sinfo->type);
const char *var_name;
- int var_len;
if (!btf_is_var(var_type))
continue;
var_name = btf__name_by_offset(btf, var_type->name_off);
- var_len = strlen(var_name);
for (k = 0; k < npresets; ++k) {
struct btf_var_secinfo tmp_sinfo;
- if (strncmp(var_name, presets[k].name, var_len) != 0 ||
- (presets[k].name[var_len] != '\0' &&
- presets[k].name[var_len] != '.'))
+ if (strcmp(var_name, presets[k].atoms[0].name) != 0)
continue;
if (presets[k].applied) {
@@ -1683,7 +2087,7 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i
}
tmp_sinfo = *sinfo;
err = adjust_var_secinfo(btf, var_type,
- &tmp_sinfo, presets[k].name);
+ &tmp_sinfo, presets + k);
if (err)
return err;
@@ -1698,7 +2102,8 @@ static int set_global_vars(struct bpf_object *obj, struct var_preset *presets, i
for (i = 0; i < npresets; ++i) {
if (!presets[i].applied) {
fprintf(stderr, "Global variable preset %s has not been applied\n",
- presets[i].name);
+ presets[i].full_name);
+ err = -EINVAL;
}
presets[i].applied = false;
}
@@ -1824,6 +2229,7 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2,
case TOTAL_STATES:
case PEAK_STATES:
case MAX_STATES_PER_INSN:
+ case MEMORY_PEAK:
case MARK_READ_MAX_LEN: {
long v1 = s1->stats[id];
long v2 = s2->stats[id];
@@ -2053,6 +2459,7 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id,
case STACK:
case SIZE:
case JITED_SIZE:
+ case MEMORY_PEAK:
*val = s ? s->stats[id] : 0;
break;
default:
@@ -2139,6 +2546,7 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats
case MARK_READ_MAX_LEN:
case SIZE:
case JITED_SIZE:
+ case MEMORY_PEAK:
case STACK: {
long val;
int err, n;
@@ -2776,7 +3184,7 @@ static void output_prog_stats(void)
static int handle_verif_mode(void)
{
- int i, err;
+ int i, err = 0;
if (env.filename_cnt == 0) {
fprintf(stderr, "Please provide path to BPF object file!\n\n");
@@ -2784,11 +3192,12 @@ static int handle_verif_mode(void)
return -EINVAL;
}
+ create_stat_cgroup();
for (i = 0; i < env.filename_cnt; i++) {
err = process_obj(env.filenames[i]);
if (err) {
fprintf(stderr, "Failed to process '%s': %d\n", env.filenames[i], err);
- return err;
+ goto out;
}
}
@@ -2796,7 +3205,9 @@ static int handle_verif_mode(void)
output_prog_stats();
- return 0;
+out:
+ destroy_stat_cgroup();
+ return err;
}
static int handle_replay_mode(void)
@@ -2826,7 +3237,7 @@ static int handle_replay_mode(void)
int main(int argc, char **argv)
{
- int err = 0, i;
+ int err = 0, i, j;
if (argp_parse(&argp, argc, argv, 0, NULL, NULL))
return 1;
@@ -2885,9 +3296,19 @@ int main(int argc, char **argv)
}
free(env.deny_filters);
for (i = 0; i < env.npresets; ++i) {
- free(env.presets[i].name);
- if (env.presets[i].type == ENUMERATOR)
- free(env.presets[i].svalue);
+ free(env.presets[i].full_name);
+ for (j = 0; j < env.presets[i].atom_count; ++j) {
+ switch (env.presets[i].atoms[j].type) {
+ case FIELD_NAME:
+ free(env.presets[i].atoms[j].name);
+ break;
+ case ARRAY_INDEX:
+ if (env.presets[i].atoms[j].index.type == ENUMERATOR)
+ free(env.presets[i].atoms[j].index.svalue);
+ break;
+ }
+ }
+ free(env.presets[i].atoms);
}
free(env.presets);
return -err;
diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 79505d294c44..2f869daf8a06 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -43,6 +43,15 @@ riscv64)
BZIMAGE="arch/riscv/boot/Image"
ARCH="riscv"
;;
+ppc64el)
+ QEMU_BINARY=qemu-system-ppc64
+ QEMU_CONSOLE="hvc0"
+ # KVM could not be tested for powerpc, therefore not enabled for now.
+ HOST_FLAGS=(-machine pseries -cpu POWER9)
+ CROSS_FLAGS=(-machine pseries -cpu POWER9)
+ BZIMAGE="vmlinux"
+ ARCH="powerpc"
+ ;;
*)
echo "Unsupported architecture"
exit 1
diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index ca60ae325c22..7bb552f8b182 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -747,6 +747,62 @@ def test_rss_ntuple_addition(cfg):
'noise' : (0,) })
+def test_rss_default_context_rule(cfg):
+ """
+ Allocate a port, direct this port to context 0, then create a new RSS
+ context and steer all TCP traffic to it (context 1). Verify that:
+ * Traffic to the specific port continues to use queues of the main
+ context (0/1).
+ * Traffic to any other TCP port is redirected to the new context
+ (queues 2/3).
+ """
+
+ require_ntuple(cfg)
+
+ queue_cnt = len(_get_rx_cnts(cfg))
+ if queue_cnt < 4:
+ try:
+ ksft_pr(f"Increasing queue count {queue_cnt} -> 4")
+ ethtool(f"-L {cfg.ifname} combined 4")
+ defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}")
+ except Exception as exc:
+ raise KsftSkipEx("Not enough queues for the test") from exc
+
+ # Use queues 0 and 1 for the main context
+ ethtool(f"-X {cfg.ifname} equal 2")
+ defer(ethtool, f"-X {cfg.ifname} default")
+
+ # Create a new RSS context that uses queues 2 and 3
+ ctx_id = ethtool_create(cfg, "-X", "context new start 2 equal 2")
+ defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+ # Generic low-priority rule: redirect all TCP traffic to the new context.
+ # Give it an explicit higher location number (lower priority).
+ flow_generic = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} context {ctx_id} loc 1"
+ ethtool(f"-N {cfg.ifname} {flow_generic}")
+ defer(ethtool, f"-N {cfg.ifname} delete 1")
+
+ # Specific high-priority rule for a random port that should stay on context 0.
+ # Assign loc 0 so it is evaluated before the generic rule.
+ port_main = rand_port()
+ flow_main = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port {port_main} context 0 loc 0"
+ ethtool(f"-N {cfg.ifname} {flow_main}")
+ defer(ethtool, f"-N {cfg.ifname} delete 0")
+
+ _ntuple_rule_check(cfg, 1, ctx_id)
+
+ # Verify that traffic matching the specific rule still goes to queues 0/1
+ _send_traffic_check(cfg, port_main, "context 0",
+ { 'target': (0, 1),
+ 'empty' : (2, 3) })
+
+ # And that traffic for any other port is steered to the new context
+ port_other = rand_port()
+ _send_traffic_check(cfg, port_other, f"context {ctx_id}",
+ { 'target': (2, 3),
+ 'noise' : (0, 1) })
+
+
def main() -> None:
with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
cfg.context_cnt = None
@@ -760,7 +816,8 @@ def main() -> None:
test_rss_context_overlap, test_rss_context_overlap2,
test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
test_flow_add_context_missing,
- test_delete_rss_context_busy, test_rss_ntuple_addition],
+ test_delete_rss_context_busy, test_rss_ntuple_addition,
+ test_rss_default_context_rule],
args=(cfg, ))
ksft_exit()
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
index f439c434ba36..648ff50bc1c3 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -38,7 +38,7 @@ def test_rss_input_xfrm(cfg, ipver):
raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
input_xfrm = cfg.ethnl.rss_get(
- {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
+ {'header': {'dev-name': cfg.ifname}}).get('input-xfrm')
# Check for symmetric xor/or-xor
if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2):
diff --git a/tools/testing/selftests/drivers/net/netdevsim/peer.sh b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
index 1bb46ec435d4..7f32b5600925 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/peer.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/peer.sh
@@ -1,7 +1,8 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0-only
-source ../../../net/lib.sh
+lib_dir=$(dirname $0)/../../../net
+source $lib_dir/lib.sh
NSIM_DEV_1_ID=$((256 + RANDOM % 256))
NSIM_DEV_1_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_DEV_1_ID
diff --git a/tools/testing/selftests/futex/functional/futex_numa_mpol.c b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
index 20a9d3ecf743..a9ecfb2d3932 100644
--- a/tools/testing/selftests/futex/functional/futex_numa_mpol.c
+++ b/tools/testing/selftests/futex/functional/futex_numa_mpol.c
@@ -144,7 +144,7 @@ int main(int argc, char *argv[])
struct futex32_numa *futex_numa;
int mem_size, i;
void *futex_ptr;
- char c;
+ int c;
while ((c = getopt(argc, argv, "chv:")) != -1) {
switch (c) {
@@ -210,6 +210,10 @@ int main(int argc, char *argv[])
ret = mbind(futex_ptr, mem_size, MPOL_BIND, &nodemask,
sizeof(nodemask) * 8, 0);
if (ret == 0) {
+ ret = numa_set_mempolicy_home_node(futex_ptr, mem_size, i, 0);
+ if (ret != 0)
+ ksft_exit_fail_msg("Failed to set home node: %m, %d\n", errno);
+
ksft_print_msg("Node %d test\n", i);
futex_numa->futex = 0;
futex_numa->numa = FUTEX_NO_NODE;
@@ -220,8 +224,8 @@ int main(int argc, char *argv[])
if (0)
test_futex_mpol(futex_numa, 0);
if (futex_numa->numa != i) {
- ksft_test_result_fail("Returned NUMA node is %d expected %d\n",
- futex_numa->numa, i);
+ ksft_exit_fail_msg("Returned NUMA node is %d expected %d\n",
+ futex_numa->numa, i);
}
}
}
diff --git a/tools/testing/selftests/futex/functional/futex_priv_hash.c b/tools/testing/selftests/futex/functional/futex_priv_hash.c
index 2dca18fefedc..24a92dc94eb8 100644
--- a/tools/testing/selftests/futex/functional/futex_priv_hash.c
+++ b/tools/testing/selftests/futex/functional/futex_priv_hash.c
@@ -130,7 +130,7 @@ int main(int argc, char *argv[])
pthread_mutexattr_t mutex_attr_pi;
int use_global_hash = 0;
int ret;
- char c;
+ int c;
while ((c = getopt(argc, argv, "cghv:")) != -1) {
switch (c) {
diff --git a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
index a36a7e2db434..4e71740a098b 100644
--- a/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
+++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c
@@ -22,7 +22,8 @@
#include "gic.h"
#include "vgic.h"
-static const uint64_t CVAL_MAX = ~0ULL;
+/* Depends on counter width. */
+static uint64_t CVAL_MAX;
/* tval is a signed 32-bit int. */
static const int32_t TVAL_MAX = INT32_MAX;
static const int32_t TVAL_MIN = INT32_MIN;
@@ -30,8 +31,8 @@ static const int32_t TVAL_MIN = INT32_MIN;
/* After how much time we say there is no IRQ. */
static const uint32_t TIMEOUT_NO_IRQ_US = 50000;
-/* A nice counter value to use as the starting one for most tests. */
-static const uint64_t DEF_CNT = (CVAL_MAX / 2);
+/* Counter value to use as the starting one for most tests. Set to CVAL_MAX/2 */
+static uint64_t DEF_CNT;
/* Number of runs. */
static const uint32_t NR_TEST_ITERS_DEF = 5;
@@ -191,8 +192,8 @@ static void set_tval_irq(enum arch_timer timer, uint64_t tval_cycles,
{
atomic_set(&shared_data.handled, 0);
atomic_set(&shared_data.spurious, 0);
- timer_set_ctl(timer, ctl);
timer_set_tval(timer, tval_cycles);
+ timer_set_ctl(timer, ctl);
}
static void set_xval_irq(enum arch_timer timer, uint64_t xval, uint32_t ctl,
@@ -732,12 +733,6 @@ static void test_move_counters_ahead_of_timers(enum arch_timer timer)
test_set_cnt_after_tval(timer, 0, tval, (uint64_t) tval + 1,
wm);
}
-
- for (i = 0; i < ARRAY_SIZE(sleep_method); i++) {
- sleep_method_t sm = sleep_method[i];
-
- test_set_cnt_after_cval_no_irq(timer, 0, DEF_CNT, CVAL_MAX, sm);
- }
}
/*
@@ -849,17 +844,17 @@ static void guest_code(enum arch_timer timer)
GUEST_DONE();
}
+static cpu_set_t default_cpuset;
+
static uint32_t next_pcpu(void)
{
uint32_t max = get_nprocs();
uint32_t cur = sched_getcpu();
uint32_t next = cur;
- cpu_set_t cpuset;
+ cpu_set_t cpuset = default_cpuset;
TEST_ASSERT(max > 1, "Need at least two physical cpus");
- sched_getaffinity(0, sizeof(cpuset), &cpuset);
-
do {
next = (next + 1) % CPU_SETSIZE;
} while (!CPU_ISSET(next, &cpuset));
@@ -959,6 +954,8 @@ static void test_init_timer_irq(struct kvm_vm *vm, struct kvm_vcpu *vcpu)
pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
}
+static int gic_fd;
+
static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu,
enum arch_timer timer)
{
@@ -973,8 +970,18 @@ static void test_vm_create(struct kvm_vm **vm, struct kvm_vcpu **vcpu,
vcpu_args_set(*vcpu, 1, timer);
test_init_timer_irq(*vm, *vcpu);
- vgic_v3_setup(*vm, 1, 64);
+ gic_fd = vgic_v3_setup(*vm, 1, 64);
+ __TEST_REQUIRE(gic_fd >= 0, "Failed to create vgic-v3");
+
sync_global_to_guest(*vm, test_args);
+ sync_global_to_guest(*vm, CVAL_MAX);
+ sync_global_to_guest(*vm, DEF_CNT);
+}
+
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+ close(gic_fd);
+ kvm_vm_free(vm);
}
static void test_print_help(char *name)
@@ -986,7 +993,7 @@ static void test_print_help(char *name)
pr_info("\t-b: Test both physical and virtual timers (default: true)\n");
pr_info("\t-l: Delta (in ms) used for long wait time test (default: %u)\n",
LONG_WAIT_TEST_MS);
- pr_info("\t-l: Delta (in ms) used for wait times (default: %u)\n",
+ pr_info("\t-w: Delta (in ms) used for wait times (default: %u)\n",
WAIT_TEST_MS);
pr_info("\t-p: Test physical timer (default: true)\n");
pr_info("\t-v: Test virtual timer (default: true)\n");
@@ -1035,6 +1042,17 @@ static bool parse_args(int argc, char *argv[])
return false;
}
+static void set_counter_defaults(void)
+{
+ const uint64_t MIN_ROLLOVER_SECS = 40ULL * 365 * 24 * 3600;
+ uint64_t freq = read_sysreg(CNTFRQ_EL0);
+ uint64_t width = ilog2(MIN_ROLLOVER_SECS * freq);
+
+ width = clamp(width, 56, 64);
+ CVAL_MAX = GENMASK_ULL(width - 1, 0);
+ DEF_CNT = CVAL_MAX / 2;
+}
+
int main(int argc, char *argv[])
{
struct kvm_vcpu *vcpu;
@@ -1046,16 +1064,19 @@ int main(int argc, char *argv[])
if (!parse_args(argc, argv))
exit(KSFT_SKIP);
+ sched_getaffinity(0, sizeof(default_cpuset), &default_cpuset);
+ set_counter_defaults();
+
if (test_args.test_virtual) {
test_vm_create(&vm, &vcpu, VIRTUAL);
test_run(vm, vcpu);
- kvm_vm_free(vm);
+ test_vm_cleanup(vm);
}
if (test_args.test_physical) {
test_vm_create(&vm, &vcpu, PHYSICAL);
test_run(vm, vcpu);
- kvm_vm_free(vm);
+ test_vm_cleanup(vm);
}
return 0;
diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config
index a28baa536332..deba93379c80 100644
--- a/tools/testing/selftests/mm/config
+++ b/tools/testing/selftests/mm/config
@@ -8,3 +8,6 @@ CONFIG_GUP_TEST=y
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_MEM_SOFT_DIRTY=y
CONFIG_ANON_VMA_NAME=y
+CONFIG_FTRACE=y
+CONFIG_PROFILING=y
+CONFIG_UPROBES=y
diff --git a/tools/testing/selftests/mm/gup_longterm.c b/tools/testing/selftests/mm/gup_longterm.c
index 8a97ac5176a4..29047d2e0c49 100644
--- a/tools/testing/selftests/mm/gup_longterm.c
+++ b/tools/testing/selftests/mm/gup_longterm.c
@@ -298,8 +298,11 @@ static void run_with_memfd(test_fn fn, const char *desc)
log_test_start("%s ... with memfd", desc);
fd = memfd_create("test", 0);
- if (fd < 0)
+ if (fd < 0) {
ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+ log_test_result(KSFT_SKIP);
+ return;
+ }
fn(fd, pagesize);
close(fd);
@@ -366,6 +369,8 @@ static void run_with_memfd_hugetlb(test_fn fn, const char *desc,
fd = memfd_create("test", flags);
if (fd < 0) {
ksft_print_msg("memfd_create() failed (%s)\n", strerror(errno));
+ log_test_result(KSFT_SKIP);
+ return;
}
fn(fd, hugetlbsize);
diff --git a/tools/testing/selftests/mm/merge.c b/tools/testing/selftests/mm/merge.c
index bbae66fc5038..cc26480098ae 100644
--- a/tools/testing/selftests/mm/merge.c
+++ b/tools/testing/selftests/mm/merge.c
@@ -470,7 +470,9 @@ TEST_F(merge, handle_uprobe_upon_merged_vma)
ASSERT_GE(fd, 0);
ASSERT_EQ(ftruncate(fd, page_size), 0);
- ASSERT_EQ(read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type), 0);
+ if (read_sysfs("/sys/bus/event_source/devices/uprobe/type", &type) != 0) {
+ SKIP(goto out, "Failed to read uprobe sysfs file, skipping");
+ }
memset(&attr, 0, attr_sz);
attr.size = attr_sz;
@@ -491,6 +493,7 @@ TEST_F(merge, handle_uprobe_upon_merged_vma)
ASSERT_NE(mremap(ptr2, page_size, page_size,
MREMAP_MAYMOVE | MREMAP_FIXED, ptr1), MAP_FAILED);
+out:
close(fd);
remove(probe_file);
}
diff --git a/tools/testing/selftests/mm/settings b/tools/testing/selftests/mm/settings
index a953c96aa16e..e2206265f67c 100644
--- a/tools/testing/selftests/mm/settings
+++ b/tools/testing/selftests/mm/settings
@@ -1 +1 @@
-timeout=180
+timeout=900
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 532bb732bc6d..c6dd2a335cf4 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -50,6 +50,7 @@ tap
tcp_fastopen_backup_key
tcp_inq
tcp_mmap
+tfo
timestamping
tls
toeplitz
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ea84b88bcb30..332f387615d7 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -27,6 +27,7 @@ TEST_PROGS += amt.sh
TEST_PROGS += unicast_extensions.sh
TEST_PROGS += udpgro_fwd.sh
TEST_PROGS += udpgro_frglist.sh
+TEST_PROGS += nat6to4.sh
TEST_PROGS += veth.sh
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
@@ -109,6 +110,8 @@ TEST_GEN_PROGS += proc_net_pktgen
TEST_PROGS += lwt_dst_cache_ref_loop.sh
TEST_PROGS += skf_net_off.sh
TEST_GEN_FILES += skf_net_off
+TEST_GEN_FILES += tfo
+TEST_PROGS += tfo_passive.sh
# YNL files, must be before "include ..lib.mk"
YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
index 3ed3882a93b8..b5f474969917 100644
--- a/tools/testing/selftests/net/af_unix/msg_oob.c
+++ b/tools/testing/selftests/net/af_unix/msg_oob.c
@@ -210,7 +210,7 @@ static void __sendpair(struct __test_metadata *_metadata,
static void __recvpair(struct __test_metadata *_metadata,
FIXTURE_DATA(msg_oob) *self,
const char *expected_buf, int expected_len,
- int buf_len, int flags)
+ int buf_len, int flags, bool is_sender)
{
int i, ret[2], recv_errno[2], expected_errno = 0;
char recv_buf[2][BUF_SZ] = {};
@@ -221,7 +221,9 @@ static void __recvpair(struct __test_metadata *_metadata,
errno = 0;
for (i = 0; i < 2; i++) {
- ret[i] = recv(self->fd[i * 2 + 1], recv_buf[i], buf_len, flags);
+ int index = is_sender ? i * 2 : i * 2 + 1;
+
+ ret[i] = recv(self->fd[index], recv_buf[i], buf_len, flags);
recv_errno[i] = errno;
}
@@ -308,6 +310,20 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
ASSERT_EQ(answ[0], answ[1]);
}
+static void __resetpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+ const FIXTURE_VARIANT(msg_oob) *variant,
+ bool reset)
+{
+ int i;
+
+ for (i = 0; i < 2; i++)
+ close(self->fd[i * 2 + 1]);
+
+ __recvpair(_metadata, self, "", reset ? -ECONNRESET : 0, 1,
+ variant->peek ? MSG_PEEK : 0, true);
+}
+
#define sendpair(buf, len, flags) \
__sendpair(_metadata, self, buf, len, flags)
@@ -316,9 +332,10 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
if (variant->peek) \
__recvpair(_metadata, self, \
expected_buf, expected_len, \
- buf_len, (flags) | MSG_PEEK); \
+ buf_len, (flags) | MSG_PEEK, false); \
__recvpair(_metadata, self, \
- expected_buf, expected_len, buf_len, flags); \
+ expected_buf, expected_len, \
+ buf_len, flags, false); \
} while (0)
#define epollpair(oob_remaining) \
@@ -330,6 +347,9 @@ static void __siocatmarkpair(struct __test_metadata *_metadata,
#define setinlinepair() \
__setinlinepair(_metadata, self)
+#define resetpair(reset) \
+ __resetpair(_metadata, self, variant, reset)
+
#define tcp_incompliant \
for (self->tcp_compliant = false; \
self->tcp_compliant == false; \
@@ -344,6 +364,21 @@ TEST_F(msg_oob, non_oob)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(true);
+}
+
+TEST_F(msg_oob, non_oob_no_reset)
+{
+ sendpair("x", 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ recvpair("x", 1, 1, 0);
+ epollpair(false);
+ siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob)
@@ -355,6 +390,19 @@ TEST_F(msg_oob, oob)
recvpair("x", 1, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
+}
+
+TEST_F(msg_oob, oob_reset)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ resetpair(true);
}
TEST_F(msg_oob, oob_drop)
@@ -370,6 +418,8 @@ TEST_F(msg_oob, oob_drop)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_ahead)
@@ -385,6 +435,10 @@ TEST_F(msg_oob, oob_ahead)
recvpair("hell", 4, 4, 0);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
}
TEST_F(msg_oob, oob_break)
@@ -403,6 +457,8 @@ TEST_F(msg_oob, oob_break)
recvpair("", -EAGAIN, 1, 0);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_ahead_break)
@@ -426,6 +482,8 @@ TEST_F(msg_oob, oob_ahead_break)
recvpair("world", 5, 5, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, oob_break_drop)
@@ -449,6 +507,8 @@ TEST_F(msg_oob, oob_break_drop)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_break)
@@ -476,6 +536,8 @@ TEST_F(msg_oob, ex_oob_break)
recvpair("ld", 2, 2, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_drop)
@@ -498,6 +560,8 @@ TEST_F(msg_oob, ex_oob_drop)
epollpair(false);
siocatmarkpair(true);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_drop_2)
@@ -523,6 +587,8 @@ TEST_F(msg_oob, ex_oob_drop_2)
epollpair(false);
siocatmarkpair(true);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, ex_oob_oob)
@@ -546,6 +612,54 @@ TEST_F(msg_oob, ex_oob_oob)
recvpair("", -EINVAL, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
+}
+
+TEST_F(msg_oob, ex_oob_ex_oob_oob)
+{
+ sendpair("x", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("x", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("y", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
+
+ recvpair("y", 1, 1, MSG_OOB);
+ epollpair(false);
+ siocatmarkpair(true);
+
+ sendpair("z", 1, MSG_OOB);
+ epollpair(true);
+ siocatmarkpair(true);
}
TEST_F(msg_oob, ex_oob_ahead_break)
@@ -576,6 +690,10 @@ TEST_F(msg_oob, ex_oob_ahead_break)
recvpair("d", 1, 1, MSG_OOB);
epollpair(false);
siocatmarkpair(true);
+
+ tcp_incompliant {
+ resetpair(false); /* TCP sets -ECONNRESET for ex-OOB. */
+ }
}
TEST_F(msg_oob, ex_oob_siocatmark)
@@ -595,6 +713,8 @@ TEST_F(msg_oob, ex_oob_siocatmark)
recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
epollpair(true);
siocatmarkpair(false);
+
+ resetpair(true);
}
TEST_F(msg_oob, inline_oob)
@@ -612,6 +732,8 @@ TEST_F(msg_oob, inline_oob)
recvpair("x", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_oob_break)
@@ -633,6 +755,8 @@ TEST_F(msg_oob, inline_oob_break)
recvpair("o", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_oob_ahead_break)
@@ -661,6 +785,8 @@ TEST_F(msg_oob, inline_oob_ahead_break)
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_break)
@@ -686,6 +812,8 @@ TEST_F(msg_oob, inline_ex_oob_break)
recvpair("rld", 3, 3, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_no_drop)
@@ -707,6 +835,8 @@ TEST_F(msg_oob, inline_ex_oob_no_drop)
recvpair("y", 1, 1, 0);
epollpair(false);
siocatmarkpair(false);
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_drop)
@@ -731,6 +861,8 @@ TEST_F(msg_oob, inline_ex_oob_drop)
epollpair(false);
siocatmarkpair(false);
}
+
+ resetpair(false);
}
TEST_F(msg_oob, inline_ex_oob_siocatmark)
@@ -752,6 +884,8 @@ TEST_F(msg_oob, inline_ex_oob_siocatmark)
recvpair("hell", 4, 4, 0); /* Intentionally stop at ex-OOB. */
epollpair(true);
siocatmarkpair(false);
+
+ resetpair(true);
}
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/net/nat6to4.sh b/tools/testing/selftests/net/nat6to4.sh
new file mode 100755
index 000000000000..0ee859b622a4
--- /dev/null
+++ b/tools/testing/selftests/net/nat6to4.sh
@@ -0,0 +1,15 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS="ns-peer-$(mktemp -u XXXXXX)"
+
+ip netns add "${NS}"
+ip -netns "${NS}" link set lo up
+ip -netns "${NS}" route add default via 127.0.0.2 dev lo
+
+tc -n "${NS}" qdisc add dev lo ingress
+tc -n "${NS}" filter add dev lo ingress prio 4 protocol ip \
+ bpf object-file nat6to4.bpf.o section schedcls/egress4/snat4 direct-action
+
+ip netns exec "${NS}" \
+ bash -c 'echo 012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789abc | socat - UDP4-DATAGRAM:224.1.0.1:6666,ip-multicast-loop=1'
diff --git a/tools/testing/selftests/net/tfo.c b/tools/testing/selftests/net/tfo.c
new file mode 100644
index 000000000000..eb3cac5e583c
--- /dev/null
+++ b/tools/testing/selftests/net/tfo.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <errno.h>
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static struct sockaddr_in6 cfg_addr;
+static char *cfg_outfile;
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+ int ret;
+
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = htons(port);
+
+ ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+ if (ret != 1) {
+ /* fallback to plain IPv4 */
+ ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+ if (ret != 1)
+ return -1;
+
+ /* add ::ffff prefix */
+ sin6->sin6_addr.s6_addr32[0] = 0;
+ sin6->sin6_addr.s6_addr32[1] = 0;
+ sin6->sin6_addr.s6_addr16[4] = 0;
+ sin6->sin6_addr.s6_addr16[5] = 0xffff;
+ }
+
+ return 0;
+}
+
+static void run_server(void)
+{
+ unsigned long qlen = 32;
+ int fd, opt, connfd;
+ socklen_t len;
+ char buf[64];
+ FILE *outfile;
+
+ outfile = fopen(cfg_outfile, "w");
+ if (!outfile)
+ error(1, errno, "fopen() outfile");
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket()");
+
+ opt = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt)) < 0)
+ error(1, errno, "setsockopt(SO_REUSEADDR)");
+
+ if (setsockopt(fd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)) < 0)
+ error(1, errno, "setsockopt(TCP_FASTOPEN)");
+
+ if (bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)) < 0)
+ error(1, errno, "bind()");
+
+ if (listen(fd, 5) < 0)
+ error(1, errno, "listen()");
+
+ len = sizeof(cfg_addr);
+ connfd = accept(fd, (struct sockaddr *)&cfg_addr, &len);
+ if (connfd < 0)
+ error(1, errno, "accept()");
+
+ len = sizeof(opt);
+ if (getsockopt(connfd, SOL_SOCKET, SO_INCOMING_NAPI_ID, &opt, &len) < 0)
+ error(1, errno, "getsockopt(SO_INCOMING_NAPI_ID)");
+
+ read(connfd, buf, 64);
+ fprintf(outfile, "%d\n", opt);
+
+ fclose(outfile);
+ close(connfd);
+ close(fd);
+}
+
+static void run_client(void)
+{
+ int fd;
+ char *msg = "Hello, world!";
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket()");
+
+ sendto(fd, msg, strlen(msg), MSG_FASTOPEN, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+
+ close(fd);
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s (-s|-c) -h<server_ip> -p<port> -o<outfile> ", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+ char *addr = NULL;
+ int ret;
+ int c;
+
+ if (argc <= 1)
+ usage(argv[0]);
+
+ while ((c = getopt(argc, argv, "sch:p:o:")) != -1) {
+ switch (c) {
+ case 's':
+ if (cfg_client)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_server = 1;
+ break;
+ case 'c':
+ if (cfg_server)
+ error(1, 0, "Pass one of -s or -c");
+ cfg_client = 1;
+ break;
+ case 'h':
+ addr = optarg;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 'o':
+ cfg_outfile = strdup(optarg);
+ if (!cfg_outfile)
+ error(1, 0, "outfile invalid");
+ break;
+ }
+ }
+
+ if (cfg_server && addr)
+ error(1, 0, "Server cannot have -h specified");
+
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ addr6->sin6_addr = in6addr_any;
+ if (addr) {
+ ret = parse_address(addr, cfg_port, addr6);
+ if (ret)
+ error(1, 0, "Client address parse error: %s", addr);
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (cfg_server)
+ run_server();
+ else if (cfg_client)
+ run_client();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/net/tfo_passive.sh b/tools/testing/selftests/net/tfo_passive.sh
new file mode 100755
index 000000000000..80bf11fdc046
--- /dev/null
+++ b/tools/testing/selftests/net/tfo_passive.sh
@@ -0,0 +1,112 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+source lib.sh
+
+NSIM_SV_ID=$((256 + RANDOM % 256))
+NSIM_SV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_SV_ID
+NSIM_CL_ID=$((512 + RANDOM % 256))
+NSIM_CL_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_CL_ID
+
+NSIM_DEV_SYS_NEW=/sys/bus/netdevsim/new_device
+NSIM_DEV_SYS_DEL=/sys/bus/netdevsim/del_device
+NSIM_DEV_SYS_LINK=/sys/bus/netdevsim/link_device
+NSIM_DEV_SYS_UNLINK=/sys/bus/netdevsim/unlink_device
+
+SERVER_IP=192.168.1.1
+CLIENT_IP=192.168.1.2
+SERVER_PORT=48675
+
+setup_ns()
+{
+ set -e
+ ip netns add nssv
+ ip netns add nscl
+
+ NSIM_SV_NAME=$(find $NSIM_SV_SYS/net -maxdepth 1 -type d ! \
+ -path $NSIM_SV_SYS/net -exec basename {} \;)
+ NSIM_CL_NAME=$(find $NSIM_CL_SYS/net -maxdepth 1 -type d ! \
+ -path $NSIM_CL_SYS/net -exec basename {} \;)
+
+ ip link set $NSIM_SV_NAME netns nssv
+ ip link set $NSIM_CL_NAME netns nscl
+
+ ip netns exec nssv ip addr add "${SERVER_IP}/24" dev $NSIM_SV_NAME
+ ip netns exec nscl ip addr add "${CLIENT_IP}/24" dev $NSIM_CL_NAME
+
+ ip netns exec nssv ip link set dev $NSIM_SV_NAME up
+ ip netns exec nscl ip link set dev $NSIM_CL_NAME up
+
+ # Enable passive TFO
+ ip netns exec nssv sysctl -w net.ipv4.tcp_fastopen=519 > /dev/null
+
+ set +e
+}
+
+cleanup_ns()
+{
+ ip netns del nscl
+ ip netns del nssv
+}
+
+###
+### Code start
+###
+
+modprobe netdevsim
+
+# linking
+
+echo $NSIM_SV_ID > $NSIM_DEV_SYS_NEW
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_NEW
+udevadm settle
+
+setup_ns
+
+NSIM_SV_FD=$((256 + RANDOM % 256))
+exec {NSIM_SV_FD}</var/run/netns/nssv
+NSIM_SV_IFIDX=$(ip netns exec nssv cat /sys/class/net/$NSIM_SV_NAME/ifindex)
+
+NSIM_CL_FD=$((256 + RANDOM % 256))
+exec {NSIM_CL_FD}</var/run/netns/nscl
+NSIM_CL_IFIDX=$(ip netns exec nscl cat /sys/class/net/$NSIM_CL_NAME/ifindex)
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX $NSIM_CL_FD:$NSIM_CL_IFIDX" > \
+ $NSIM_DEV_SYS_LINK
+
+if [ $? -ne 0 ]; then
+ echo "linking netdevsim1 with netdevsim2 should succeed"
+ cleanup_ns
+ exit 1
+fi
+
+out_file=$(mktemp)
+
+timeout -k 1s 30s ip netns exec nssv ./tfo \
+ -s \
+ -p ${SERVER_PORT} \
+ -o ${out_file}&
+
+wait_local_port_listen nssv ${SERVER_PORT} tcp
+
+ip netns exec nscl ./tfo -c -h ${SERVER_IP} -p ${SERVER_PORT}
+
+wait
+
+res=$(cat $out_file)
+rm $out_file
+
+if [ $res -eq 0 ]; then
+ echo "got invalid NAPI ID from passive TFO socket"
+ cleanup_ns
+ exit 1
+fi
+
+echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
+
+echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
+
+cleanup_ns
+
+modprobe -r netdevsim
+
+exit 0
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index f703fcfe9f7c..83148875a12c 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -12,7 +12,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh "$(CC)" trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
- test_vsyscall mov_ss_trap \
+ test_vsyscall mov_ss_trap sigtrap_loop \
syscall_arg_fault fsgsbase_restore sigaltstack
TARGETS_C_BOTHBITS += nx_stack
TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
diff --git a/tools/testing/selftests/x86/sigtrap_loop.c b/tools/testing/selftests/x86/sigtrap_loop.c
new file mode 100644
index 000000000000..9d065479e89f
--- /dev/null
+++ b/tools/testing/selftests/x86/sigtrap_loop.c
@@ -0,0 +1,101 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#define _GNU_SOURCE
+
+#include <err.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ucontext.h>
+
+#ifdef __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *), int flags)
+{
+ struct sigaction sa;
+
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+
+ return;
+}
+
+static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
+{
+ ucontext_t *ctx = (ucontext_t *)ctx_void;
+ static unsigned int loop_count_on_same_ip;
+ static unsigned long last_trap_ip;
+
+ if (last_trap_ip == ctx->uc_mcontext.gregs[REG_IP]) {
+ printf("\tTrapped at %016lx\n", last_trap_ip);
+
+ /*
+ * If the same IP is hit more than 10 times in a row, it is
+ * _considered_ an infinite loop.
+ */
+ if (++loop_count_on_same_ip > 10) {
+ printf("[FAIL]\tDetected SIGTRAP infinite loop\n");
+ exit(1);
+ }
+
+ return;
+ }
+
+ loop_count_on_same_ip = 0;
+ last_trap_ip = ctx->uc_mcontext.gregs[REG_IP];
+ printf("\tTrapped at %016lx\n", last_trap_ip);
+}
+
+int main(int argc, char *argv[])
+{
+ sethandler(SIGTRAP, sigtrap, 0);
+
+ /*
+ * Set the Trap Flag (TF) to single-step the test code, therefore to
+ * trigger a SIGTRAP signal after each instruction until the TF is
+ * cleared.
+ *
+ * Because the arithmetic flags are not significant here, the TF is
+ * set by pushing 0x302 onto the stack and then popping it into the
+ * flags register.
+ *
+ * Four instructions in the following asm code are executed with the
+ * TF set, thus the SIGTRAP handler is expected to run four times.
+ */
+ printf("[RUN]\tSIGTRAP infinite loop detection\n");
+ asm volatile(
+#ifdef __x86_64__
+ /*
+ * Avoid clobbering the redzone
+ *
+ * Equivalent to "sub $128, %rsp", however -128 can be encoded
+ * in a single byte immediate while 128 uses 4 bytes.
+ */
+ "add $-128, %rsp\n\t"
+#endif
+ "push $0x302\n\t"
+ "popf\n\t"
+ "nop\n\t"
+ "nop\n\t"
+ "push $0x202\n\t"
+ "popf\n\t"
+#ifdef __x86_64__
+ "sub $-128, %rsp\n\t"
+#endif
+ );
+
+ printf("[OK]\tNo SIGTRAP infinite loop detected\n");
+ return 0;
+}
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 4505b1c31be1..14718ca23a05 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -159,6 +159,14 @@ typedef __bitwise unsigned int vm_fault_t;
#define ASSERT_EXCLUSIVE_WRITER(x)
+/**
+ * swap - swap values of @a and @b
+ * @a: first value
+ * @b: second value
+ */
+#define swap(a, b) \
+ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
+
struct kref {
refcount_t refcount;
};
@@ -1468,4 +1476,12 @@ static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
(void)vma;
}
+static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
+{
+ /* Changing an anonymous vma with this is illegal */
+ get_file(file);
+ swap(vma->vm_file, file);
+ fput(file);
+}
+
#endif /* __MM_VMA_INTERNAL_H */