summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
Diffstat (limited to 'arch')
-rw-r--r--arch/alpha/include/asm/local.h33
-rw-r--r--arch/alpha/kernel/syscalls/syscall.tbl4
-rw-r--r--arch/arc/kernel/troubleshoot.c6
-rw-r--r--arch/arm/boot/dts/rockchip/rk3128.dtsi18
-rw-r--r--arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi5
-rw-r--r--arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi3
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi5
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4-l4-abe.dtsi6
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4-l4.dtsi2
-rw-r--r--arch/arm/boot/dts/ti/omap/omap443x.dtsi1
-rw-r--r--arch/arm/boot/dts/ti/omap/omap4460.dtsi1
-rw-r--r--arch/arm/boot/dts/ti/omap/omap5-l4-abe.dtsi6
-rw-r--r--arch/arm/configs/hardening.config7
-rw-r--r--arch/arm/include/asm/hardware/locomo.h2
-rw-r--r--arch/arm/mach-omap1/board-ams-delta.c60
-rw-r--r--arch/arm/mach-omap1/timer32k.c14
-rw-r--r--arch/arm/mach-omap2/omap_hwmod.c2
-rw-r--r--arch/arm/mach-omap2/pm44xx.c4
-rw-r--r--arch/arm/mach-sa1100/include/mach/collie.h2
-rw-r--r--arch/arm/mm/cache-uniphier.c4
-rw-r--r--arch/arm/net/bpf_jit_32.c280
-rw-r--r--arch/arm/net/bpf_jit_32.h4
-rw-r--r--arch/arm/tools/syscall.tbl3
-rw-r--r--arch/arm/xen/enlighten.c2
-rw-r--r--arch/arm64/Kconfig13
-rw-r--r--arch/arm64/boot/dts/freescale/Makefile1
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi32
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts5
-rw-r--r--arch/arm64/boot/dts/freescale/imx8mp.dtsi6
-rw-r--r--arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi2
-rw-r--r--arch/arm64/boot/dts/freescale/imx93.dtsi4
-rw-r--r--arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi2
-rw-r--r--arch/arm64/boot/dts/mediatek/mt7622.dtsi2
-rw-r--r--arch/arm64/boot/dts/mediatek/mt7986a.dtsi2
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8195-demo.dts39
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8195.dtsi11
-rw-r--r--arch/arm64/boot/dts/qcom/apq8096-db820c.dts32
-rw-r--r--arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi32
-rw-r--r--arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts18
-rw-r--r--arch/arm64/boot/dts/qcom/sa8775p-pmics.dtsi2
-rw-r--r--arch/arm64/boot/dts/qcom/sm8150.dtsi2
-rw-r--r--arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts10
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi1
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399.dtsi10
-rw-r--r--arch/arm64/configs/defconfig2
-rw-r--r--arch/arm64/configs/hardening.config22
-rw-r--r--arch/arm64/include/asm/acpi.h19
-rw-r--r--arch/arm64/include/asm/cpufeature.h2
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/hugetlb.h2
-rw-r--r--arch/arm64/include/asm/kvm_arm.h4
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h2
-rw-r--r--arch/arm64/include/asm/unistd.h2
-rw-r--r--arch/arm64/include/asm/unistd32.h6
-rw-r--r--arch/arm64/kernel/cpu_errata.c8
-rw-r--r--arch/arm64/kernel/cpufeature.c3
-rw-r--r--arch/arm64/kernel/entry.S4
-rw-r--r--arch/arm64/kernel/smp.c4
-rw-r--r--arch/arm64/kvm/arch_timer.c13
-rw-r--r--arch/arm64/kvm/emulate-nested.c2
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/ffa.h2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/ffa.c3
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-init.S1
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c8
-rw-r--r--arch/arm64/kvm/hyp/nvhe/psci-relay.c3
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c44
-rw-r--r--arch/arm64/kvm/mmu.c3
-rw-r--r--arch/arm64/kvm/pmu.c4
-rw-r--r--arch/arm64/kvm/sys_regs.c4
-rw-r--r--arch/arm64/mm/hugetlbpage.c23
-rw-r--r--arch/arm64/net/bpf_jit_comp.c2
-rw-r--r--arch/arm64/tools/cpucaps1
-rw-r--r--arch/arm64/tools/sysreg6
-rw-r--r--arch/ia64/include/asm/cpu.h5
-rw-r--r--arch/ia64/kernel/acpi.c4
-rw-r--r--arch/ia64/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/ia64/kernel/topology.c2
-rw-r--r--arch/loongarch/include/asm/addrspace.h12
-rw-r--r--arch/loongarch/include/asm/elf.h9
-rw-r--r--arch/loongarch/include/asm/exception.h45
-rw-r--r--arch/loongarch/include/asm/io.h5
-rw-r--r--arch/loongarch/include/asm/kasan.h59
-rw-r--r--arch/loongarch/include/asm/linkage.h8
-rw-r--r--arch/loongarch/include/asm/local.h27
-rw-r--r--arch/loongarch/include/asm/pgtable-bits.h4
-rw-r--r--arch/loongarch/include/asm/smp.h1
-rw-r--r--arch/loongarch/kernel/Makefile4
-rw-r--r--arch/loongarch/kernel/acpi.c1
-rw-r--r--arch/loongarch/kernel/entry.S4
-rw-r--r--arch/loongarch/kernel/genex.S16
-rw-r--r--arch/loongarch/kernel/mem.c4
-rw-r--r--arch/loongarch/kernel/module-sections.c1
-rw-r--r--arch/loongarch/kernel/module.c22
-rw-r--r--arch/loongarch/kernel/numa.c2
-rw-r--r--arch/loongarch/kernel/process.c1
-rw-r--r--arch/loongarch/kernel/relocate_kernel.S1
-rw-r--r--arch/loongarch/kernel/setup.c10
-rw-r--r--arch/loongarch/kernel/signal.c7
-rw-r--r--arch/loongarch/kernel/smp.c3
-rw-r--r--arch/loongarch/kernel/syscall.c1
-rw-r--r--arch/loongarch/kernel/time.c2
-rw-r--r--arch/loongarch/kernel/topology.c3
-rw-r--r--arch/loongarch/kernel/traps.c25
-rw-r--r--arch/loongarch/kernel/vmlinux.lds.S55
-rw-r--r--arch/loongarch/mm/fault.c2
-rw-r--r--arch/loongarch/mm/hugetlbpage.c12
-rw-r--r--arch/loongarch/mm/init.c9
-rw-r--r--arch/loongarch/mm/ioremap.c1
-rw-r--r--arch/loongarch/mm/kasan_init.c51
-rw-r--r--arch/loongarch/mm/tlb.c2
-rw-r--r--arch/loongarch/mm/tlbex.S36
-rw-r--r--arch/m68k/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/microblaze/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/mips/alchemy/devboards/db1000.c4
-rw-r--r--arch/mips/alchemy/devboards/db1200.c6
-rw-r--r--arch/mips/alchemy/devboards/db1300.c4
-rw-r--r--arch/mips/include/asm/local.h27
-rw-r--r--arch/mips/kernel/syscalls/syscall_n32.tbl3
-rw-r--r--arch/mips/kernel/syscalls/syscall_n64.tbl3
-rw-r--r--arch/mips/kernel/syscalls/syscall_o32.tbl3
-rw-r--r--arch/mips/kvm/mmu.c3
-rw-r--r--arch/parisc/include/asm/cache.h1
-rw-r--r--arch/parisc/include/asm/hugetlb.h2
-rw-r--r--arch/parisc/include/asm/ldcw.h37
-rw-r--r--arch/parisc/include/asm/mckinley.h8
-rw-r--r--arch/parisc/include/asm/pdc.h5
-rw-r--r--arch/parisc/include/asm/processor.h1
-rw-r--r--arch/parisc/include/asm/ropes.h7
-rw-r--r--arch/parisc/include/asm/shmparam.h15
-rw-r--r--arch/parisc/include/asm/spinlock_types.h5
-rw-r--r--arch/parisc/kernel/asm-offsets.c2
-rw-r--r--arch/parisc/kernel/cache.c8
-rw-r--r--arch/parisc/kernel/drivers.c2
-rw-r--r--arch/parisc/kernel/firmware.c56
-rw-r--r--arch/parisc/kernel/head.S16
-rw-r--r--arch/parisc/kernel/irq.c2
-rw-r--r--arch/parisc/kernel/processor.c2
-rw-r--r--arch/parisc/kernel/smp.c4
-rw-r--r--arch/parisc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/parisc/kernel/vmlinux.lds.S1
-rw-r--r--arch/parisc/mm/hugetlbpage.c2
-rw-r--r--arch/parisc/mm/init.c72
-rw-r--r--arch/powerpc/Kconfig4
-rw-r--r--arch/powerpc/configs/hardening.config10
-rw-r--r--arch/powerpc/include/asm/local.h12
-rw-r--r--arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h3
-rw-r--r--arch/powerpc/include/asm/nohash/32/pte-8xx.h7
-rw-r--r--arch/powerpc/include/asm/nohash/64/pgtable.h2
-rw-r--r--arch/powerpc/include/asm/nohash/pgtable.h2
-rw-r--r--arch/powerpc/kernel/entry_32.S8
-rw-r--r--arch/powerpc/kernel/head_85xx.S2
-rw-r--r--arch/powerpc/kernel/hw_breakpoint.c16
-rw-r--r--arch/powerpc/kernel/hw_breakpoint_constraints.c7
-rw-r--r--arch/powerpc/kernel/setup-common.c2
-rw-r--r--arch/powerpc/kernel/smp.c6
-rw-r--r--arch/powerpc/kernel/stacktrace.c27
-rw-r--r--arch/powerpc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/powerpc/kernel/traps.c56
-rw-r--r--arch/powerpc/lib/qspinlock.c3
-rw-r--r--arch/powerpc/mm/book3s64/hugetlbpage.c5
-rw-r--r--arch/powerpc/mm/book3s64/radix_hugetlbpage.c3
-rw-r--r--arch/powerpc/mm/book3s64/radix_tlb.c9
-rw-r--r--arch/powerpc/mm/mem.c1
-rw-r--r--arch/powerpc/mm/nohash/8xx.c3
-rw-r--r--arch/powerpc/mm/pgtable.c35
-rw-r--r--arch/powerpc/perf/hv-24x7.c2
-rw-r--r--arch/powerpc/platforms/82xx/Kconfig3
-rw-r--r--arch/powerpc/platforms/cell/spufs/coredump.c11
-rw-r--r--arch/powerpc/platforms/cell/spufs/inode.c2
-rw-r--r--arch/powerpc/platforms/pseries/hvCall.S8
-rw-r--r--arch/riscv/Kconfig3
-rw-r--r--arch/riscv/Kconfig.errata1
-rw-r--r--arch/riscv/Makefile1
-rw-r--r--arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi53
-rw-r--r--arch/riscv/boot/dts/thead/th1520.dtsi1
-rw-r--r--arch/riscv/errata/andes/Makefile4
-rw-r--r--arch/riscv/include/asm/errata_list.h4
-rw-r--r--arch/riscv/include/asm/ftrace.h21
-rw-r--r--arch/riscv/include/asm/hugetlb.h3
-rw-r--r--arch/riscv/include/asm/kprobes.h11
-rw-r--r--arch/riscv/include/asm/uprobes.h13
-rw-r--r--arch/riscv/kernel/elf_kexec.c8
-rw-r--r--arch/riscv/kernel/irq.c4
-rw-r--r--arch/riscv/kernel/setup.c13
-rw-r--r--arch/riscv/kernel/signal.c7
-rw-r--r--arch/riscv/kernel/traps.c28
-rw-r--r--arch/riscv/kvm/vcpu_onereg.c7
-rw-r--r--arch/riscv/mm/fault.c2
-rw-r--r--arch/riscv/mm/hugetlbpage.c22
-rw-r--r--arch/riscv/net/bpf_jit_comp64.c18
-rw-r--r--arch/s390/boot/vmem.c7
-rw-r--r--arch/s390/configs/debug_defconfig14
-rw-r--r--arch/s390/configs/defconfig13
-rw-r--r--arch/s390/configs/zfcpdump_defconfig4
-rw-r--r--arch/s390/hypfs/inode.c4
-rw-r--r--arch/s390/include/asm/hugetlb.h6
-rw-r--r--arch/s390/kernel/cert_store.c7
-rw-r--r--arch/s390/kernel/smp.c2
-rw-r--r--arch/s390/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/s390/kernel/topology.c2
-rw-r--r--arch/s390/kvm/interrupt.c16
-rw-r--r--arch/s390/mm/hugetlbpage.c8
-rw-r--r--arch/s390/net/bpf_jit_comp.c294
-rw-r--r--arch/s390/pci/pci_dma.c15
-rw-r--r--arch/sh/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/sh/mm/ioremap.c4
-rw-r--r--arch/sparc/include/asm/hugetlb.h6
-rw-r--r--arch/sparc/kernel/cpumap.c2
-rw-r--r--arch/sparc/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/sparc/lib/checksum_32.S2
-rw-r--r--arch/sparc/mm/hugetlbpage.c8
-rw-r--r--arch/um/os-Linux/drivers/ethertap_user.c2
-rw-r--r--arch/x86/Kconfig14
-rw-r--r--arch/x86/Makefile3
-rw-r--r--arch/x86/boot/Makefile2
-rw-r--r--arch/x86/boot/compressed/acpi.c14
-rw-r--r--arch/x86/boot/compressed/cmdline.c4
-rw-r--r--arch/x86/boot/compressed/ident_map_64.c15
-rw-r--r--arch/x86/boot/compressed/kaslr.c26
-rw-r--r--arch/x86/boot/compressed/mem.c6
-rw-r--r--arch/x86/boot/compressed/misc.c24
-rw-r--r--arch/x86/boot/compressed/misc.h1
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c9
-rw-r--r--arch/x86/boot/compressed/sev.c14
-rw-r--r--arch/x86/boot/compressed/vmlinux.lds.S6
-rw-r--r--arch/x86/boot/header.S213
-rw-r--r--arch/x86/boot/setup.ld14
-rw-r--r--arch/x86/boot/tools/build.c273
-rw-r--r--arch/x86/coco/tdx/tdx.c2
-rw-r--r--arch/x86/configs/hardening.config14
-rw-r--r--arch/x86/configs/i386_defconfig1
-rw-r--r--arch/x86/configs/x86_64_defconfig1
-rw-r--r--arch/x86/entry/common.c115
-rw-r--r--arch/x86/entry/entry.S2
-rw-r--r--arch/x86/entry/entry_32.S2
-rw-r--r--arch/x86/entry/entry_64.S84
-rw-r--r--arch/x86/entry/entry_64_compat.S11
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl3
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl3
-rw-r--r--arch/x86/entry/thunk_32.S2
-rw-r--r--arch/x86/entry/thunk_64.S2
-rw-r--r--arch/x86/entry/vdso/Makefile3
-rw-r--r--arch/x86/entry/vdso/vsgx.S1
-rw-r--r--arch/x86/events/amd/core.c24
-rw-r--r--arch/x86/events/amd/uncore.c1060
-rw-r--r--arch/x86/events/core.c6
-rw-r--r--arch/x86/events/intel/core.c475
-rw-r--r--arch/x86/events/intel/cstate.c3
-rw-r--r--arch/x86/events/intel/ds.c4
-rw-r--r--arch/x86/events/intel/pt.c8
-rw-r--r--arch/x86/events/intel/uncore.c2
-rw-r--r--arch/x86/events/perf_event.h37
-rw-r--r--arch/x86/events/rapl.c22
-rw-r--r--arch/x86/events/utils.c5
-rw-r--r--arch/x86/hyperv/hv_init.c20
-rw-r--r--arch/x86/hyperv/hv_vtl.c5
-rw-r--r--arch/x86/hyperv/ivm.c2
-rw-r--r--arch/x86/include/asm/Kbuild1
-rw-r--r--arch/x86/include/asm/alternative.h4
-rw-r--r--arch/x86/include/asm/apic.h39
-rw-r--r--arch/x86/include/asm/bitops.h9
-rw-r--r--arch/x86/include/asm/boot.h47
-rw-r--r--arch/x86/include/asm/cacheinfo.h3
-rw-r--r--arch/x86/include/asm/cmpxchg.h6
-rw-r--r--arch/x86/include/asm/cpu.h2
-rw-r--r--arch/x86/include/asm/efi.h32
-rw-r--r--arch/x86/include/asm/elf.h3
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/hw_irq.h6
-rw-r--r--arch/x86/include/asm/i8259.h2
-rw-r--r--arch/x86/include/asm/ia32.h16
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/intel-family.h2
-rw-r--r--arch/x86/include/asm/kvm_host.h4
-rw-r--r--arch/x86/include/asm/linkage.h15
-rw-r--r--arch/x86/include/asm/local.h33
-rw-r--r--arch/x86/include/asm/mce.h2
-rw-r--r--arch/x86/include/asm/mem_encrypt.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h3
-rw-r--r--arch/x86/include/asm/mpspec.h2
-rw-r--r--arch/x86/include/asm/mshyperv.h6
-rw-r--r--arch/x86/include/asm/msr-index.h21
-rw-r--r--arch/x86/include/asm/nospec-branch.h71
-rw-r--r--arch/x86/include/asm/numa.h7
-rw-r--r--arch/x86/include/asm/paravirt_types.h15
-rw-r--r--arch/x86/include/asm/percpu.h110
-rw-r--r--arch/x86/include/asm/perf_event.h9
-rw-r--r--arch/x86/include/asm/pgtable.h16
-rw-r--r--arch/x86/include/asm/preempt.h4
-rw-r--r--arch/x86/include/asm/processor.h65
-rw-r--r--arch/x86/include/asm/prom.h5
-rw-r--r--arch/x86/include/asm/proto.h3
-rw-r--r--arch/x86/include/asm/smp.h5
-rw-r--r--arch/x86/include/asm/sparsemem.h2
-rw-r--r--arch/x86/include/asm/spec-ctrl.h11
-rw-r--r--arch/x86/include/asm/svm.h7
-rw-r--r--arch/x86/include/asm/syscall.h6
-rw-r--r--arch/x86/include/asm/topology.h12
-rw-r--r--arch/x86/include/asm/uaccess.h2
-rw-r--r--arch/x86/include/asm/x86_init.h2
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h37
-rw-r--r--arch/x86/kernel/acpi/boot.c7
-rw-r--r--arch/x86/kernel/alternative.c22
-rw-r--r--arch/x86/kernel/amd_nb.c12
-rw-r--r--arch/x86/kernel/apic/apic.c29
-rw-r--r--arch/x86/kernel/apic/apic_common.c4
-rw-r--r--arch/x86/kernel/apic/apic_flat_64.c8
-rw-r--r--arch/x86/kernel/apic/apic_noop.c8
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c16
-rw-r--r--arch/x86/kernel/apic/bigsmp_32.c6
-rw-r--r--arch/x86/kernel/apic/ipi.c5
-rw-r--r--arch/x86/kernel/apic/local.h7
-rw-r--r--arch/x86/kernel/apic/msi.c8
-rw-r--r--arch/x86/kernel/apic/probe_32.c12
-rw-r--r--arch/x86/kernel/apic/x2apic_phys.c6
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c19
-rw-r--r--arch/x86/kernel/callthunks.c6
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/amd.c81
-rw-r--r--arch/x86/kernel/cpu/bugs.c104
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c49
-rw-r--r--arch/x86/kernel/cpu/common.c124
-rw-r--r--arch/x86/kernel/cpu/cpu.h3
-rw-r--r--arch/x86/kernel/cpu/debugfs.c58
-rw-r--r--arch/x86/kernel/cpu/hygon.c48
-rw-r--r--arch/x86/kernel/cpu/intel.c13
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c68
-rw-r--r--arch/x86/kernel/cpu/mce/apei.c4
-rw-r--r--arch/x86/kernel/cpu/mce/core.c36
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c20
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h4
-rw-r--r--arch/x86/kernel/cpu/proc.c8
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c11
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c14
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h31
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c10
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c281
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c30
-rw-r--r--arch/x86/kernel/cpu/topology.c13
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c14
-rw-r--r--arch/x86/kernel/devicetree.c6
-rw-r--r--arch/x86/kernel/fpu/core.c5
-rw-r--r--arch/x86/kernel/fpu/xstate.c13
-rw-r--r--arch/x86/kernel/fpu/xstate.h3
-rw-r--r--arch/x86/kernel/ftrace_32.S2
-rw-r--r--arch/x86/kernel/ftrace_64.S2
-rw-r--r--arch/x86/kernel/head64.c17
-rw-r--r--arch/x86/kernel/head_32.S2
-rw-r--r--arch/x86/kernel/head_64.S7
-rw-r--r--arch/x86/kernel/hpet.c4
-rw-r--r--arch/x86/kernel/i8259.c38
-rw-r--r--arch/x86/kernel/idt.c7
-rw-r--r--arch/x86/kernel/irqflags.S2
-rw-r--r--arch/x86/kernel/kgdb.c1
-rw-r--r--arch/x86/kernel/kvm.c6
-rw-r--r--arch/x86/kernel/nmi.c13
-rw-r--r--arch/x86/kernel/paravirt.c67
-rw-r--r--arch/x86/kernel/process.c7
-rw-r--r--arch/x86/kernel/setup.c12
-rw-r--r--arch/x86/kernel/sev-shared.c122
-rw-r--r--arch/x86/kernel/sev.c35
-rw-r--r--arch/x86/kernel/shstk.c33
-rw-r--r--arch/x86/kernel/smp.c39
-rw-r--r--arch/x86/kernel/smpboot.c138
-rw-r--r--arch/x86/kernel/topology.c2
-rw-r--r--arch/x86/kernel/tsc_sync.c10
-rw-r--r--arch/x86/kernel/unwind_orc.c2
-rw-r--r--arch/x86/kernel/vmlinux.lds.S7
-rw-r--r--arch/x86/kernel/vsmp_64.c2
-rw-r--r--arch/x86/kvm/cpuid.c8
-rw-r--r--arch/x86/kvm/lapic.c8
-rw-r--r--arch/x86/kvm/mmu/mmu.c21
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h15
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c152
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.h5
-rw-r--r--arch/x86/kvm/pmu.c27
-rw-r--r--arch/x86/kvm/pmu.h6
-rw-r--r--arch/x86/kvm/svm/avic.c5
-rw-r--r--arch/x86/kvm/svm/nested.c3
-rw-r--r--arch/x86/kvm/svm/pmu.c2
-rw-r--r--arch/x86/kvm/svm/sev.c34
-rw-r--r--arch/x86/kvm/svm/svm.c54
-rw-r--r--arch/x86/kvm/svm/svm.h1
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c4
-rw-r--r--arch/x86/kvm/x86.c45
-rw-r--r--arch/x86/lib/checksum_32.S2
-rw-r--r--arch/x86/lib/clear_page_64.S2
-rw-r--r--arch/x86/lib/cmpxchg8b_emu.S2
-rw-r--r--arch/x86/lib/copy_mc.c8
-rw-r--r--arch/x86/lib/copy_page_64.S2
-rw-r--r--arch/x86/lib/copy_user_64.S2
-rw-r--r--arch/x86/lib/copy_user_uncached_64.S2
-rw-r--r--arch/x86/lib/csum-wrappers_64.c5
-rw-r--r--arch/x86/lib/getuser.S2
-rw-r--r--arch/x86/lib/hweight.S22
-rw-r--r--arch/x86/lib/memcpy_64.S4
-rw-r--r--arch/x86/lib/memmove_32.S2
-rw-r--r--arch/x86/lib/memmove_64.S4
-rw-r--r--arch/x86/lib/memset_64.S4
-rw-r--r--arch/x86/lib/putuser.S7
-rw-r--r--arch/x86/lib/retpoline.S188
-rw-r--r--arch/x86/mm/maccess.c19
-rw-r--r--arch/x86/mm/mem_encrypt.c34
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c36
-rw-r--r--arch/x86/mm/numa.c94
-rw-r--r--arch/x86/mm/pti.c58
-rw-r--r--arch/x86/net/bpf_jit_comp.c148
-rw-r--r--arch/x86/platform/efi/efi_32.c12
-rw-r--r--arch/x86/platform/efi/efi_64.c19
-rw-r--r--arch/x86/platform/uv/uv_nmi.c104
-rw-r--r--arch/x86/platform/uv/uv_time.c2
-rw-r--r--arch/x86/purgatory/Makefile4
-rw-r--r--arch/x86/xen/apic.c10
-rw-r--r--arch/x86/xen/efi.c2
-rw-r--r--arch/x86/xen/enlighten.c2
-rw-r--r--arch/x86/xen/enlighten_hvm.c2
-rw-r--r--arch/x86/xen/enlighten_pv.c40
-rw-r--r--arch/x86/xen/mmu_pv.c55
-rw-r--r--arch/x86/xen/multicalls.h4
-rw-r--r--arch/xtensa/boot/Makefile3
-rw-r--r--arch/xtensa/boot/lib/zmem.c5
-rw-r--r--arch/xtensa/include/asm/core.h4
-rw-r--r--arch/xtensa/include/asm/hw_breakpoint.h1
-rw-r--r--arch/xtensa/include/asm/processor.h5
-rw-r--r--arch/xtensa/include/asm/ptrace.h3
-rw-r--r--arch/xtensa/include/asm/smp.h1
-rw-r--r--arch/xtensa/include/asm/tlb.h2
-rw-r--r--arch/xtensa/kernel/hw_breakpoint.c1
-rw-r--r--arch/xtensa/kernel/irq.c1
-rw-r--r--arch/xtensa/kernel/ptrace.c1
-rw-r--r--arch/xtensa/kernel/signal.c2
-rw-r--r--arch/xtensa/kernel/smp.c1
-rw-r--r--arch/xtensa/kernel/stacktrace.c1
-rw-r--r--arch/xtensa/kernel/syscalls/syscall.tbl3
-rw-r--r--arch/xtensa/kernel/traps.c1
-rw-r--r--arch/xtensa/lib/umulsidi3.S4
-rw-r--r--arch/xtensa/mm/fault.c1
-rw-r--r--arch/xtensa/mm/tlb.c1
-rw-r--r--arch/xtensa/platforms/iss/network.c4
439 files changed, 5455 insertions, 3472 deletions
diff --git a/arch/alpha/include/asm/local.h b/arch/alpha/include/asm/local.h
index 0fcaad642cc3..88eb398947a5 100644
--- a/arch/alpha/include/asm/local.h
+++ b/arch/alpha/include/asm/local.h
@@ -65,28 +65,27 @@ static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (xchg_local(&((l)->a.counter), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read(l); \
- for (;;) { \
- if (unlikely(c == (u))) \
- break; \
- old = local_cmpxchg((l), c, c + (a)); \
- if (likely(old == c)) \
- break; \
- c = old; \
- } \
- c != (u); \
-})
+static __inline__ bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
#define local_add_negative(a, l) (local_add_return((a), (l)) < 0)
diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index ad37569d0507..b68f1f56b836 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -492,3 +492,7 @@
560 common set_mempolicy_home_node sys_ni_syscall
561 common cachestat sys_cachestat
562 common fchmodat2 sys_fchmodat2
+# 563 reserved for map_shadow_stack
+564 common futex_wake sys_futex_wake
+565 common futex_wait sys_futex_wait
+566 common futex_requeue sys_futex_requeue
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index d5b3ed2c58f5..c380d8c30704 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -90,10 +90,12 @@ static void show_faulting_vma(unsigned long address)
*/
if (vma) {
char buf[ARC_PATH_MAX];
- char *nm = "?";
+ char *nm = "anon";
if (vma->vm_file) {
- nm = file_path(vma->vm_file, buf, ARC_PATH_MAX-1);
+ /* XXX: can we use %pD below and get rid of buf? */
+ nm = d_path(file_user_path(vma->vm_file), buf,
+ ARC_PATH_MAX-1);
if (IS_ERR(nm))
nm = "?";
}
diff --git a/arch/arm/boot/dts/rockchip/rk3128.dtsi b/arch/arm/boot/dts/rockchip/rk3128.dtsi
index b63bd4ad3143..88a4b0d6d928 100644
--- a/arch/arm/boot/dts/rockchip/rk3128.dtsi
+++ b/arch/arm/boot/dts/rockchip/rk3128.dtsi
@@ -64,7 +64,8 @@
compatible = "arm,armv7-timer";
interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
<GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
- <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
+ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>,
+ <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) | IRQ_TYPE_LEVEL_HIGH)>;
arm,cpu-registers-not-fw-configured;
clock-frequency = <24000000>;
};
@@ -233,7 +234,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x20044000 0x20>;
interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER0>;
clock-names = "pclk", "timer";
};
@@ -241,7 +242,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x20044020 0x20>;
interrupts = <GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER1>;
clock-names = "pclk", "timer";
};
@@ -249,7 +250,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x20044040 0x20>;
interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER2>;
clock-names = "pclk", "timer";
};
@@ -257,7 +258,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x20044060 0x20>;
interrupts = <GIC_SPI 60 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER3>;
clock-names = "pclk", "timer";
};
@@ -265,7 +266,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x20044080 0x20>;
interrupts = <GIC_SPI 61 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER4>;
clock-names = "pclk", "timer";
};
@@ -273,7 +274,7 @@
compatible = "rockchip,rk3128-timer", "rockchip,rk3288-timer";
reg = <0x200440a0 0x20>;
interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>;
- clocks = <&cru PCLK_TIMER>, <&xin24m>;
+ clocks = <&cru PCLK_TIMER>, <&cru SCLK_TIMER5>;
clock-names = "pclk", "timer";
};
@@ -426,7 +427,7 @@
i2c0: i2c@20072000 {
compatible = "rockchip,rk3128-i2c", "rockchip,rk3288-i2c";
- reg = <20072000 0x1000>;
+ reg = <0x20072000 0x1000>;
interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
clock-names = "i2c";
clocks = <&cru PCLK_I2C0>;
@@ -458,6 +459,7 @@
interrupts = <GIC_SPI 0 IRQ_TYPE_LEVEL_HIGH>,
<GIC_SPI 1 IRQ_TYPE_LEVEL_HIGH>;
arm,pl330-broken-no-flushp;
+ arm,pl330-periph-burst;
clocks = <&cru ACLK_DMAC>;
clock-names = "apb_pclk";
#dma-cells = <1>;
diff --git a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
index 091ba310053e..d2d516d113ba 100644
--- a/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
+++ b/arch/arm/boot/dts/ti/omap/motorola-mapphone-common.dtsi
@@ -614,12 +614,12 @@
/* Configure pwm clock source for timers 8 & 9 */
&timer8 {
assigned-clocks = <&abe_clkctrl OMAP4_TIMER8_CLKCTRL 24>;
- assigned-clock-parents = <&sys_clkin_ck>;
+ assigned-clock-parents = <&sys_32k_ck>;
};
&timer9 {
assigned-clocks = <&l4_per_clkctrl OMAP4_TIMER9_CLKCTRL 24>;
- assigned-clock-parents = <&sys_clkin_ck>;
+ assigned-clock-parents = <&sys_32k_ck>;
};
/*
@@ -640,6 +640,7 @@
&uart3 {
interrupts-extended = <&wakeupgen GIC_SPI 74 IRQ_TYPE_LEVEL_HIGH
&omap4_pmx_core 0x17c>;
+ overrun-throttle-ms = <500>;
};
&uart4 {
diff --git a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
index 0da759f8e2c2..7dd2340bc5e4 100644
--- a/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap3-cpu-thermal.dtsi
@@ -12,8 +12,7 @@ cpu_thermal: cpu-thermal {
polling-delay = <1000>; /* milliseconds */
coefficients = <0 20000>;
- /* sensor ID */
- thermal-sensors = <&bandgap 0>;
+ thermal-sensors = <&bandgap>;
cpu_trips: trips {
cpu_alert0: cpu_alert {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
index 801b4f10350c..d484ec1e4fd8 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-cpu-thermal.dtsi
@@ -12,7 +12,10 @@ cpu_thermal: cpu_thermal {
polling-delay-passive = <250>; /* milliseconds */
polling-delay = <1000>; /* milliseconds */
- /* sensor ID */
+ /*
+ * See 44xx files for single sensor addressing, omap5 and dra7 need
+ * also sensor ID for addressing.
+ */
thermal-sensors = <&bandgap 0>;
cpu_trips: trips {
diff --git a/arch/arm/boot/dts/ti/omap/omap4-l4-abe.dtsi b/arch/arm/boot/dts/ti/omap/omap4-l4-abe.dtsi
index 7ae8b620515c..59f546a278f8 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-l4-abe.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-l4-abe.dtsi
@@ -109,6 +109,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49022000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP4_MCBSP1_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
@@ -142,6 +144,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49024000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP4_MCBSP2_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
@@ -175,6 +179,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49026000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP4_MCBSP3_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
diff --git a/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi b/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
index 46b8f9efd413..3fcef3080eae 100644
--- a/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4-l4.dtsi
@@ -2043,6 +2043,8 @@
compatible = "ti,omap4-mcbsp";
reg = <0x0 0xff>; /* L4 Interconnect */
reg-names = "mpu";
+ clocks = <&l4_per_clkctrl OMAP4_MCBSP4_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
diff --git a/arch/arm/boot/dts/ti/omap/omap443x.dtsi b/arch/arm/boot/dts/ti/omap/omap443x.dtsi
index 238aceb799f8..2104170fe2cd 100644
--- a/arch/arm/boot/dts/ti/omap/omap443x.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap443x.dtsi
@@ -69,6 +69,7 @@
};
&cpu_thermal {
+ thermal-sensors = <&bandgap>;
coefficients = <0 20000>;
};
diff --git a/arch/arm/boot/dts/ti/omap/omap4460.dtsi b/arch/arm/boot/dts/ti/omap/omap4460.dtsi
index 1b27a862ae81..a6764750d447 100644
--- a/arch/arm/boot/dts/ti/omap/omap4460.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap4460.dtsi
@@ -79,6 +79,7 @@
};
&cpu_thermal {
+ thermal-sensors = <&bandgap>;
coefficients = <348 (-9301)>;
};
diff --git a/arch/arm/boot/dts/ti/omap/omap5-l4-abe.dtsi b/arch/arm/boot/dts/ti/omap/omap5-l4-abe.dtsi
index a03bca5a3584..97b0c3b5f573 100644
--- a/arch/arm/boot/dts/ti/omap/omap5-l4-abe.dtsi
+++ b/arch/arm/boot/dts/ti/omap/omap5-l4-abe.dtsi
@@ -109,6 +109,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49022000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP5_MCBSP1_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
@@ -142,6 +144,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49024000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP5_MCBSP2_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
@@ -175,6 +179,8 @@
reg = <0x0 0xff>, /* MPU private access */
<0x49026000 0xff>; /* L3 Interconnect */
reg-names = "mpu", "dma";
+ clocks = <&abe_clkctrl OMAP5_MCBSP3_CLKCTRL 24>;
+ clock-names = "fck";
interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "common";
ti,buffer-size = <128>;
diff --git a/arch/arm/configs/hardening.config b/arch/arm/configs/hardening.config
new file mode 100644
index 000000000000..327349ce6377
--- /dev/null
+++ b/arch/arm/configs/hardening.config
@@ -0,0 +1,7 @@
+# Basic kernel hardening options (specific to arm)
+
+# Make sure PXN/PAN emulation is enabled.
+CONFIG_CPU_SW_DOMAIN_PAN=y
+
+# Dangerous; old interfaces and needless additional attack surface.
+# CONFIG_OABI_COMPAT is not set
diff --git a/arch/arm/include/asm/hardware/locomo.h b/arch/arm/include/asm/hardware/locomo.h
index 246a3de25931..aaaedafef7cc 100644
--- a/arch/arm/include/asm/hardware/locomo.h
+++ b/arch/arm/include/asm/hardware/locomo.h
@@ -195,7 +195,7 @@ struct locomo_driver {
#define LOCOMO_DRIVER_NAME(_ldev) ((_ldev)->dev.driver->name)
-void locomo_lcd_power(struct locomo_dev *, int, unsigned int);
+extern void locomolcd_power(int on);
int locomo_driver_register(struct locomo_driver *);
void locomo_driver_unregister(struct locomo_driver *);
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index a28ea6ac1eba..0daf6c5b5c1c 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -550,6 +550,7 @@ static struct platform_device *ams_delta_devices[] __initdata = {
&ams_delta_nand_device,
&ams_delta_lcd_device,
&cx20442_codec_device,
+ &modem_nreset_device,
};
static struct gpiod_lookup_table *ams_delta_gpio_tables[] __initdata = {
@@ -780,26 +781,28 @@ static struct plat_serial8250_port ams_delta_modem_ports[] = {
{ },
};
+static int ams_delta_modem_pm_activate(struct device *dev)
+{
+ modem_priv.regulator = regulator_get(dev, "RESET#");
+ if (IS_ERR(modem_priv.regulator))
+ return -EPROBE_DEFER;
+
+ return 0;
+}
+
+static struct dev_pm_domain ams_delta_modem_pm_domain = {
+ .activate = ams_delta_modem_pm_activate,
+};
+
static struct platform_device ams_delta_modem_device = {
.name = "serial8250",
.id = PLAT8250_DEV_PLATFORM1,
.dev = {
.platform_data = ams_delta_modem_ports,
+ .pm_domain = &ams_delta_modem_pm_domain,
},
};
-static int __init modem_nreset_init(void)
-{
- int err;
-
- err = platform_device_register(&modem_nreset_device);
- if (err)
- pr_err("Couldn't register the modem regulator device\n");
-
- return err;
-}
-
-
/*
* This function expects MODEM IRQ number already assigned to the port.
* The MODEM device requires its RESET# pin kept high during probe.
@@ -831,37 +834,6 @@ static int __init ams_delta_modem_init(void)
}
arch_initcall_sync(ams_delta_modem_init);
-static int __init late_init(void)
-{
- int err;
-
- err = modem_nreset_init();
- if (err)
- return err;
-
- /*
- * Once the modem device is registered, the modem_nreset
- * regulator can be requested on behalf of that device.
- */
- modem_priv.regulator = regulator_get(&ams_delta_modem_device.dev,
- "RESET#");
- if (IS_ERR(modem_priv.regulator)) {
- err = PTR_ERR(modem_priv.regulator);
- goto unregister;
- }
- return 0;
-
-unregister:
- platform_device_unregister(&ams_delta_modem_device);
- return err;
-}
-
-static void __init ams_delta_init_late(void)
-{
- omap1_init_late();
- late_init();
-}
-
static void __init ams_delta_map_io(void)
{
omap1_map_io();
@@ -875,7 +847,7 @@ MACHINE_START(AMS_DELTA, "Amstrad E3 (Delta)")
.init_early = omap1_init_early,
.init_irq = omap1_init_irq,
.init_machine = ams_delta_init,
- .init_late = ams_delta_init_late,
+ .init_late = omap1_init_late,
.init_time = omap1_timer_init,
.restart = omap1_restart,
MACHINE_END
diff --git a/arch/arm/mach-omap1/timer32k.c b/arch/arm/mach-omap1/timer32k.c
index 410d17d1d443..f618a6df2938 100644
--- a/arch/arm/mach-omap1/timer32k.c
+++ b/arch/arm/mach-omap1/timer32k.c
@@ -176,17 +176,18 @@ static u64 notrace omap_32k_read_sched_clock(void)
return sync32k_cnt_reg ? readl_relaxed(sync32k_cnt_reg) : 0;
}
+static struct timespec64 persistent_ts;
+static cycles_t cycles;
+static unsigned int persistent_mult, persistent_shift;
+
/**
* omap_read_persistent_clock64 - Return time from a persistent clock.
+ * @ts: &struct timespec64 for the returned time
*
* Reads the time from a source which isn't disabled during PM, the
* 32k sync timer. Convert the cycles elapsed since last read into
* nsecs and adds to a monotonically increasing timespec64.
*/
-static struct timespec64 persistent_ts;
-static cycles_t cycles;
-static unsigned int persistent_mult, persistent_shift;
-
static void omap_read_persistent_clock64(struct timespec64 *ts)
{
unsigned long long nsecs;
@@ -206,10 +207,9 @@ static void omap_read_persistent_clock64(struct timespec64 *ts)
/**
* omap_init_clocksource_32k - setup and register counter 32k as a
* kernel clocksource
- * @pbase: base addr of counter_32k module
- * @size: size of counter_32k to map
+ * @vbase: base addr of counter_32k module
*
- * Returns 0 upon success or negative error code upon failure.
+ * Returns: %0 upon success or negative error code upon failure.
*
*/
static int __init omap_init_clocksource_32k(void __iomem *vbase)
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 1e17b5f77588..ba71928c0fcb 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2209,7 +2209,7 @@ int omap_hwmod_parse_module_range(struct omap_hwmod *oh,
return err;
pr_debug("omap_hwmod: %s %pOFn at %pR\n",
- oh->name, np, &res);
+ oh->name, np, res);
if (oh && oh->mpu_rt_idx) {
omap_hwmod_fix_mpu_rt_idx(oh, np, res);
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index f57802f3ee3a..37b168119fe4 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -99,7 +99,7 @@ static int omap4_pm_suspend(void)
* possible causes.
* http://www.spinics.net/lists/arm-kernel/msg218641.html
*/
- pr_warn("A possible cause could be an old bootloader - try u-boot >= v2012.07\n");
+ pr_debug("A possible cause could be an old bootloader - try u-boot >= v2012.07\n");
} else {
pr_info("Successfully put all powerdomains to target state\n");
}
@@ -257,7 +257,7 @@ int __init omap4_pm_init(void)
* http://www.spinics.net/lists/arm-kernel/msg218641.html
*/
if (cpu_is_omap44xx())
- pr_warn("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
+ pr_debug("OMAP4 PM: u-boot >= v2012.07 is required for full PM support\n");
ret = pwrdm_for_each(pwrdms_setup, NULL);
if (ret) {
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index b7bc23ffd3c6..c95273c9567b 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -16,8 +16,6 @@
#include "hardware.h" /* Gives GPIO_MAX */
-extern void locomolcd_power(int on);
-
#define COLLIE_SCOOP_GPIO_BASE (GPIO_MAX + 1)
#define COLLIE_GPIO_CHARGE_ON (COLLIE_SCOOP_GPIO_BASE + 0)
#define COLLIE_SCP_DIAG_BOOT1 SCOOP_GPCR_PA12
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index ff2881458504..84a2f17ff32d 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -58,11 +58,13 @@
((op & UNIPHIER_SSCOQM_S_MASK) == UNIPHIER_SSCOQM_S_RANGE)
/**
- * uniphier_cache_data - UniPhier outer cache specific data
+ * struct uniphier_cache_data - UniPhier outer cache specific data
*
* @ctrl_base: virtual base address of control registers
* @rev_base: virtual base address of revision registers
* @op_base: virtual base address of operation registers
+ * @way_ctrl_base: virtual address of the way control registers for this
+ * SoC revision
* @way_mask: each bit specifies if the way is present
* @nsets: number of associativity sets
* @line_size: line size in bytes
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6a1c9fca5260..1d672457d02f 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -2,6 +2,7 @@
/*
* Just-In-Time compiler for eBPF filters on 32bit ARM
*
+ * Copyright (c) 2023 Puranjay Mohan <puranjay12@gmail.com>
* Copyright (c) 2017 Shubham Bansal <illusionist.neo@gmail.com>
* Copyright (c) 2011 Mircea Gherzan <mgherzan@gmail.com>
*/
@@ -15,6 +16,7 @@
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/if_vlan.h>
+#include <linux/math64.h>
#include <asm/cacheflush.h>
#include <asm/hwcap.h>
@@ -228,6 +230,44 @@ static u32 jit_mod32(u32 dividend, u32 divisor)
return dividend % divisor;
}
+static s32 jit_sdiv32(s32 dividend, s32 divisor)
+{
+ return dividend / divisor;
+}
+
+static s32 jit_smod32(s32 dividend, s32 divisor)
+{
+ return dividend % divisor;
+}
+
+/* Wrappers for 64-bit div/mod */
+static u64 jit_udiv64(u64 dividend, u64 divisor)
+{
+ return div64_u64(dividend, divisor);
+}
+
+static u64 jit_mod64(u64 dividend, u64 divisor)
+{
+ u64 rem;
+
+ div64_u64_rem(dividend, divisor, &rem);
+ return rem;
+}
+
+static s64 jit_sdiv64(s64 dividend, s64 divisor)
+{
+ return div64_s64(dividend, divisor);
+}
+
+static s64 jit_smod64(s64 dividend, s64 divisor)
+{
+ u64 q;
+
+ q = div64_s64(dividend, divisor);
+
+ return dividend - q * divisor;
+}
+
static inline void _emit(int cond, u32 inst, struct jit_ctx *ctx)
{
inst |= (cond << 28);
@@ -333,6 +373,9 @@ static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
#define ARM_LDRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
#define ARM_LDRH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
+#define ARM_LDRSH_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSH_I, rt, rn, off)
+#define ARM_LDRSB_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_LDRSB_I, rt, rn, off)
+
#define ARM_STR_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
#define ARM_STRB_I(rt, rn, off) arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
#define ARM_STRD_I(rt, rn, off) arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
@@ -474,17 +517,18 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
return to - from - 2;
}
-static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
+static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op, u8 sign)
{
const int exclude_mask = BIT(ARM_R0) | BIT(ARM_R1);
const s8 *tmp = bpf2a32[TMP_REG_1];
+ u32 dst;
#if __LINUX_ARM_ARCH__ == 7
if (elf_hwcap & HWCAP_IDIVA) {
- if (op == BPF_DIV)
- emit(ARM_UDIV(rd, rm, rn), ctx);
- else {
- emit(ARM_UDIV(ARM_IP, rm, rn), ctx);
+ if (op == BPF_DIV) {
+ emit(sign ? ARM_SDIV(rd, rm, rn) : ARM_UDIV(rd, rm, rn), ctx);
+ } else {
+ emit(sign ? ARM_SDIV(ARM_IP, rm, rn) : ARM_UDIV(ARM_IP, rm, rn), ctx);
emit(ARM_MLS(rd, rn, ARM_IP, rm), ctx);
}
return;
@@ -512,8 +556,19 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
emit(ARM_PUSH(CALLER_MASK & ~exclude_mask), ctx);
/* Call appropriate function */
- emit_mov_i(ARM_IP, op == BPF_DIV ?
- (u32)jit_udiv32 : (u32)jit_mod32, ctx);
+ if (sign) {
+ if (op == BPF_DIV)
+ dst = (u32)jit_sdiv32;
+ else
+ dst = (u32)jit_smod32;
+ } else {
+ if (op == BPF_DIV)
+ dst = (u32)jit_udiv32;
+ else
+ dst = (u32)jit_mod32;
+ }
+
+ emit_mov_i(ARM_IP, dst, ctx);
emit_blx_r(ARM_IP, ctx);
/* Restore caller-saved registers from stack */
@@ -530,6 +585,78 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
}
+static inline void emit_udivmod64(const s8 *rd, const s8 *rm, const s8 *rn, struct jit_ctx *ctx,
+ u8 op, u8 sign)
+{
+ u32 dst;
+
+ /* Push caller-saved registers on stack */
+ emit(ARM_PUSH(CALLER_MASK), ctx);
+
+ /*
+ * As we are implementing 64-bit div/mod as function calls, We need to put the dividend in
+ * R0-R1 and the divisor in R2-R3. As we have already pushed these registers on the stack,
+ * we can recover them later after returning from the function call.
+ */
+ if (rm[1] != ARM_R0 || rn[1] != ARM_R2) {
+ /*
+ * Move Rm to {R1, R0} if it is not already there.
+ */
+ if (rm[1] != ARM_R0) {
+ if (rn[1] == ARM_R0)
+ emit(ARM_PUSH(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+ emit(ARM_MOV_R(ARM_R1, rm[0]), ctx);
+ emit(ARM_MOV_R(ARM_R0, rm[1]), ctx);
+ if (rn[1] == ARM_R0) {
+ emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+ goto cont;
+ }
+ }
+ /*
+ * Move Rn to {R3, R2} if it is not already there.
+ */
+ if (rn[1] != ARM_R2) {
+ emit(ARM_MOV_R(ARM_R3, rn[0]), ctx);
+ emit(ARM_MOV_R(ARM_R2, rn[1]), ctx);
+ }
+ }
+
+cont:
+
+ /* Call appropriate function */
+ if (sign) {
+ if (op == BPF_DIV)
+ dst = (u32)jit_sdiv64;
+ else
+ dst = (u32)jit_smod64;
+ } else {
+ if (op == BPF_DIV)
+ dst = (u32)jit_udiv64;
+ else
+ dst = (u32)jit_mod64;
+ }
+
+ emit_mov_i(ARM_IP, dst, ctx);
+ emit_blx_r(ARM_IP, ctx);
+
+ /* Save return value */
+ if (rd[1] != ARM_R0) {
+ emit(ARM_MOV_R(rd[0], ARM_R1), ctx);
+ emit(ARM_MOV_R(rd[1], ARM_R0), ctx);
+ }
+
+ /* Recover {R3, R2} and {R1, R0} from stack if they are not Rd */
+ if (rd[1] != ARM_R0 && rd[1] != ARM_R2) {
+ emit(ARM_POP(CALLER_MASK), ctx);
+ } else if (rd[1] != ARM_R0) {
+ emit(ARM_POP(BIT(ARM_R0) | BIT(ARM_R1)), ctx);
+ emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+ } else {
+ emit(ARM_ADD_I(ARM_SP, ARM_SP, 8), ctx);
+ emit(ARM_POP(BIT(ARM_R2) | BIT(ARM_R3)), ctx);
+ }
+}
+
/* Is the translated BPF register on stack? */
static bool is_stacked(s8 reg)
{
@@ -744,12 +871,16 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
}
/* dst = src (4 bytes)*/
-static inline void emit_a32_mov_r(const s8 dst, const s8 src,
+static inline void emit_a32_mov_r(const s8 dst, const s8 src, const u8 off,
struct jit_ctx *ctx) {
const s8 *tmp = bpf2a32[TMP_REG_1];
s8 rt;
rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+ if (off && off != 32) {
+ emit(ARM_LSL_I(rt, rt, 32 - off), ctx);
+ emit(ARM_ASR_I(rt, rt, 32 - off), ctx);
+ }
arm_bpf_put_reg32(dst, rt, ctx);
}
@@ -758,15 +889,15 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
const s8 src[],
struct jit_ctx *ctx) {
if (!is64) {
- emit_a32_mov_r(dst_lo, src_lo, ctx);
+ emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
if (!ctx->prog->aux->verifier_zext)
/* Zero out high 4 bytes */
emit_a32_mov_i(dst_hi, 0, ctx);
} else if (__LINUX_ARM_ARCH__ < 6 &&
ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
/* complete 8 byte move */
- emit_a32_mov_r(dst_lo, src_lo, ctx);
- emit_a32_mov_r(dst_hi, src_hi, ctx);
+ emit_a32_mov_r(dst_lo, src_lo, 0, ctx);
+ emit_a32_mov_r(dst_hi, src_hi, 0, ctx);
} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
const u8 *tmp = bpf2a32[TMP_REG_1];
@@ -782,6 +913,24 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
}
}
+/* dst = (signed)src */
+static inline void emit_a32_movsx_r64(const bool is64, const u8 off, const s8 dst[], const s8 src[],
+ struct jit_ctx *ctx) {
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *rt;
+
+ rt = arm_bpf_get_reg64(dst, tmp, ctx);
+
+ emit_a32_mov_r(dst_lo, src_lo, off, ctx);
+ if (!is64) {
+ if (!ctx->prog->aux->verifier_zext)
+ /* Zero out high 4 bytes */
+ emit_a32_mov_i(dst_hi, 0, ctx);
+ } else {
+ emit(ARM_ASR_I(rt[0], rt[1], 31), ctx);
+ }
+}
+
/* Shift operations */
static inline void emit_a32_alu_i(const s8 dst, const u32 val,
struct jit_ctx *ctx, const u8 op) {
@@ -1026,6 +1175,24 @@ static bool is_ldst_imm(s16 off, const u8 size)
return -off_max <= off && off <= off_max;
}
+static bool is_ldst_imm8(s16 off, const u8 size)
+{
+ s16 off_max = 0;
+
+ switch (size) {
+ case BPF_B:
+ off_max = 0xff;
+ break;
+ case BPF_W:
+ off_max = 0xfff;
+ break;
+ case BPF_H:
+ off_max = 0xff;
+ break;
+ }
+ return -off_max <= off && off <= off_max;
+}
+
/* *(size *)(dst + off) = src */
static inline void emit_str_r(const s8 dst, const s8 src[],
s16 off, struct jit_ctx *ctx, const u8 sz){
@@ -1105,6 +1272,50 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
arm_bpf_put_reg64(dst, rd, ctx);
}
+/* dst = *(signed size*)(src + off) */
+static inline void emit_ldsx_r(const s8 dst[], const s8 src,
+ s16 off, struct jit_ctx *ctx, const u8 sz){
+ const s8 *tmp = bpf2a32[TMP_REG_1];
+ const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+ s8 rm = src;
+ int add_off;
+
+ if (!is_ldst_imm8(off, sz)) {
+ /*
+ * offset does not fit in the load/store immediate,
+ * construct an ADD instruction to apply the offset.
+ */
+ add_off = imm8m(off);
+ if (add_off > 0) {
+ emit(ARM_ADD_I(tmp[0], src, add_off), ctx);
+ rm = tmp[0];
+ } else {
+ emit_a32_mov_i(tmp[0], off, ctx);
+ emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
+ rm = tmp[0];
+ }
+ off = 0;
+ }
+
+ switch (sz) {
+ case BPF_B:
+ /* Load a Byte with sign extension*/
+ emit(ARM_LDRSB_I(rd[1], rm, off), ctx);
+ break;
+ case BPF_H:
+ /* Load a HalfWord with sign extension*/
+ emit(ARM_LDRSH_I(rd[1], rm, off), ctx);
+ break;
+ case BPF_W:
+ /* Load a Word*/
+ emit(ARM_LDR_I(rd[1], rm, off), ctx);
+ break;
+ }
+ /* Carry the sign extension to upper 32 bits */
+ emit(ARM_ASR_I(rd[0], rd[1], 31), ctx);
+ arm_bpf_put_reg64(dst, rd, ctx);
+}
+
/* Arithmatic Operation */
static inline void emit_ar_r(const u8 rd, const u8 rt, const u8 rm,
const u8 rn, struct jit_ctx *ctx, u8 op,
@@ -1385,7 +1596,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
emit_a32_mov_i(dst_hi, 0, ctx);
break;
}
- emit_a32_mov_r64(is64, dst, src, ctx);
+ if (insn->off)
+ emit_a32_movsx_r64(is64, insn->off, dst, src, ctx);
+ else
+ emit_a32_mov_r64(is64, dst, src, ctx);
break;
case BPF_K:
/* Sign-extend immediate value to destination reg */
@@ -1461,7 +1675,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
rt = src_lo;
break;
}
- emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
+ emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code), off);
arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
if (!ctx->prog->aux->verifier_zext)
emit_a32_mov_i(dst_hi, 0, ctx);
@@ -1470,7 +1684,19 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
case BPF_ALU64 | BPF_DIV | BPF_X:
case BPF_ALU64 | BPF_MOD | BPF_K:
case BPF_ALU64 | BPF_MOD | BPF_X:
- goto notyet;
+ rd = arm_bpf_get_reg64(dst, tmp2, ctx);
+ switch (BPF_SRC(code)) {
+ case BPF_X:
+ rs = arm_bpf_get_reg64(src, tmp, ctx);
+ break;
+ case BPF_K:
+ rs = tmp;
+ emit_a32_mov_se_i64(is64, rs, imm, ctx);
+ break;
+ }
+ emit_udivmod64(rd, rd, rs, ctx, BPF_OP(code), off);
+ arm_bpf_put_reg64(dst, rd, ctx);
+ break;
/* dst = dst << imm */
/* dst = dst >> imm */
/* dst = dst >> imm (signed) */
@@ -1545,10 +1771,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
break;
/* dst = htole(dst) */
/* dst = htobe(dst) */
- case BPF_ALU | BPF_END | BPF_FROM_LE:
- case BPF_ALU | BPF_END | BPF_FROM_BE:
+ case BPF_ALU | BPF_END | BPF_FROM_LE: /* also BPF_TO_LE */
+ case BPF_ALU | BPF_END | BPF_FROM_BE: /* also BPF_TO_BE */
+ /* dst = bswap(dst) */
+ case BPF_ALU64 | BPF_END | BPF_FROM_LE: /* also BPF_TO_LE */
rd = arm_bpf_get_reg64(dst, tmp, ctx);
- if (BPF_SRC(code) == BPF_FROM_LE)
+ if (BPF_SRC(code) == BPF_FROM_LE && BPF_CLASS(code) != BPF_ALU64)
goto emit_bswap_uxt;
switch (imm) {
case 16:
@@ -1603,8 +1831,15 @@ exit:
case BPF_LDX | BPF_MEM | BPF_H:
case BPF_LDX | BPF_MEM | BPF_B:
case BPF_LDX | BPF_MEM | BPF_DW:
+ /* LDSX: dst = *(signed size *)(src + off) */
+ case BPF_LDX | BPF_MEMSX | BPF_B:
+ case BPF_LDX | BPF_MEMSX | BPF_H:
+ case BPF_LDX | BPF_MEMSX | BPF_W:
rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
- emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
+ if (BPF_MODE(insn->code) == BPF_MEMSX)
+ emit_ldsx_r(dst, rn, off, ctx, BPF_SIZE(code));
+ else
+ emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
break;
/* speculation barrier */
case BPF_ST | BPF_NOSPEC:
@@ -1761,10 +1996,15 @@ go_jmp:
break;
/* JMP OFF */
case BPF_JMP | BPF_JA:
+ case BPF_JMP32 | BPF_JA:
{
- if (off == 0)
+ if (BPF_CLASS(code) == BPF_JMP32 && imm != 0)
+ jmp_offset = bpf2a32_offset(i + imm, i, ctx);
+ else if (BPF_CLASS(code) == BPF_JMP && off != 0)
+ jmp_offset = bpf2a32_offset(i + off, i, ctx);
+ else
break;
- jmp_offset = bpf2a32_offset(i+off, i, ctx);
+
check_imm24(jmp_offset);
emit(ARM_B(jmp_offset), ctx);
break;
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index e0b593a1498d..438f0e1f91a0 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -79,9 +79,11 @@
#define ARM_INST_LDST__IMM12 0x00000fff
#define ARM_INST_LDRB_I 0x05500000
#define ARM_INST_LDRB_R 0x07d00000
+#define ARM_INST_LDRSB_I 0x015000d0
#define ARM_INST_LDRD_I 0x014000d0
#define ARM_INST_LDRH_I 0x015000b0
#define ARM_INST_LDRH_R 0x019000b0
+#define ARM_INST_LDRSH_I 0x015000f0
#define ARM_INST_LDR_I 0x05100000
#define ARM_INST_LDR_R 0x07900000
@@ -137,6 +139,7 @@
#define ARM_INST_TST_I 0x03100000
#define ARM_INST_UDIV 0x0730f010
+#define ARM_INST_SDIV 0x0710f010
#define ARM_INST_UMULL 0x00800090
@@ -265,6 +268,7 @@
#define ARM_TST_I(rn, imm) _AL3_I(ARM_INST_TST, 0, rn, imm)
#define ARM_UDIV(rd, rn, rm) (ARM_INST_UDIV | (rd) << 16 | (rn) | (rm) << 8)
+#define ARM_SDIV(rd, rn, rm) (ARM_INST_SDIV | (rd) << 16 | (rn) | (rm) << 8)
#define ARM_UMULL(rd_lo, rd_hi, rn, rm) (ARM_INST_UMULL | (rd_hi) << 16 \
| (rd_lo) << 12 | (rm) << 8 | rn)
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index c572d6c3dee0..93d0d46cbb15 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -466,3 +466,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 7d59765aef22..c392e18f1e43 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -207,7 +207,7 @@ static void xen_power_off(void)
static irqreturn_t xen_arm_callback(int irq, void *arg)
{
- xen_hvm_evtchn_do_upcall();
+ xen_evtchn_do_upcall();
return IRQ_HANDLED;
}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b10515c0200b..78f20e632712 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1037,6 +1037,19 @@ config ARM64_ERRATUM_2645198
If unsure, say Y.
+config ARM64_ERRATUM_2966298
+ bool "Cortex-A520: 2966298: workaround for speculatively executed unprivileged load"
+ default y
+ help
+ This option adds the workaround for ARM Cortex-A520 erratum 2966298.
+
+ On an affected Cortex-A520 core, a speculatively executed unprivileged
+ load might leak data from a privileged level via a cache side channel.
+
+ Work around this problem by executing a TLBI before returning to EL0.
+
+ If unsure, say Y.
+
config CAVIUM_ERRATUM_22375
bool "Cavium erratum 22375, 24313"
default y
diff --git a/arch/arm64/boot/dts/freescale/Makefile b/arch/arm64/boot/dts/freescale/Makefile
index c6872b7e9471..89aee6c92576 100644
--- a/arch/arm64/boot/dts/freescale/Makefile
+++ b/arch/arm64/boot/dts/freescale/Makefile
@@ -66,6 +66,7 @@ dtb-$(CONFIG_ARCH_MXC) += imx8mm-mx8menlo.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-nitrogen-r2.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-phg.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-phyboard-polis-rdk.dtb
+dtb-$(CONFIG_ARCH_MXC) += imx8mm-prt8mm.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-tqma8mqml-mba8mx.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-var-som-symphony.dtb
dtb-$(CONFIG_ARCH_MXC) += imx8mm-venice-gw71xx-0x.dtb
diff --git a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
index e31ab8b4f54f..a882c86ec313 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-evk.dtsi
@@ -26,7 +26,7 @@
port {
hdmi_connector_in: endpoint {
- remote-endpoint = <&adv7533_out>;
+ remote-endpoint = <&adv7535_out>;
};
};
};
@@ -72,6 +72,13 @@
enable-active-high;
};
+ reg_vddext_3v3: regulator-vddext-3v3 {
+ compatible = "regulator-fixed";
+ regulator-name = "VDDEXT_3V3";
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+ };
+
backlight: backlight {
compatible = "pwm-backlight";
pwms = <&pwm1 0 5000000 0>;
@@ -317,15 +324,16 @@
hdmi@3d {
compatible = "adi,adv7535";
- reg = <0x3d>, <0x3c>, <0x3e>, <0x3f>;
- reg-names = "main", "cec", "edid", "packet";
+ reg = <0x3d>;
+ interrupt-parent = <&gpio1>;
+ interrupts = <9 IRQ_TYPE_EDGE_FALLING>;
adi,dsi-lanes = <4>;
-
- adi,input-depth = <8>;
- adi,input-colorspace = "rgb";
- adi,input-clock = "1x";
- adi,input-style = <1>;
- adi,input-justification = "evenly";
+ avdd-supply = <&buck5_reg>;
+ dvdd-supply = <&buck5_reg>;
+ pvdd-supply = <&buck5_reg>;
+ a2vdd-supply = <&buck5_reg>;
+ v3p3-supply = <&reg_vddext_3v3>;
+ v1p2-supply = <&buck5_reg>;
ports {
#address-cells = <1>;
@@ -334,7 +342,7 @@
port@0 {
reg = <0>;
- adv7533_in: endpoint {
+ adv7535_in: endpoint {
remote-endpoint = <&dsi_out>;
};
};
@@ -342,7 +350,7 @@
port@1 {
reg = <1>;
- adv7533_out: endpoint {
+ adv7535_out: endpoint {
remote-endpoint = <&hdmi_connector_in>;
};
};
@@ -448,7 +456,7 @@
reg = <1>;
dsi_out: endpoint {
- remote-endpoint = <&adv7533_in>;
+ remote-endpoint = <&adv7535_in>;
data-lanes = <1 2 3 4>;
};
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
index 06e91297fb16..acd265d8b58e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
@@ -381,9 +381,10 @@
&sai3 {
pinctrl-names = "default";
pinctrl-0 = <&pinctrl_sai3>;
- assigned-clocks = <&clk IMX8MP_CLK_SAI3>;
+ assigned-clocks = <&clk IMX8MP_CLK_SAI3>,
+ <&clk IMX8MP_AUDIO_PLL2> ;
assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
- assigned-clock-rates = <12288000>;
+ assigned-clock-rates = <12288000>, <361267200>;
fsl,sai-mclk-direction-output;
status = "okay";
};
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index 6f2f50e1639c..83d907294fbc 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -790,6 +790,12 @@
reg = <IMX8MP_POWER_DOMAIN_AUDIOMIX>;
clocks = <&clk IMX8MP_CLK_AUDIO_ROOT>,
<&clk IMX8MP_CLK_AUDIO_AXI>;
+ assigned-clocks = <&clk IMX8MP_CLK_AUDIO_AHB>,
+ <&clk IMX8MP_CLK_AUDIO_AXI_SRC>;
+ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+ <&clk IMX8MP_SYS_PLL1_800M>;
+ assigned-clock-rates = <400000000>,
+ <600000000>;
};
pgc_gpu2d: power-domain@6 {
diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
index 1c71c08becde..f6e422dc2663 100644
--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
@@ -81,7 +81,7 @@
&gpio1 {
pmic-irq-hog {
gpio-hog;
- gpios = <2 GPIO_ACTIVE_LOW>;
+ gpios = <3 GPIO_ACTIVE_LOW>;
input;
line-name = "PMIC_IRQ#";
};
diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
index 6f85a05ee7e1..dcf6e4846ac9 100644
--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
@@ -185,7 +185,7 @@
#size-cells = <1>;
ranges;
- anomix_ns_gpr: syscon@44210000 {
+ aonmix_ns_gpr: syscon@44210000 {
compatible = "fsl,imx93-aonmix-ns-syscfg", "syscon";
reg = <0x44210000 0x1000>;
};
@@ -319,6 +319,7 @@
assigned-clock-parents = <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>;
assigned-clock-rates = <40000000>;
fsl,clk-source = /bits/ 8 <0>;
+ fsl,stop-mode = <&aonmix_ns_gpr 0x14 0>;
status = "disabled";
};
@@ -591,6 +592,7 @@
assigned-clock-parents = <&clk IMX93_CLK_SYS_PLL_PFD1_DIV2>;
assigned-clock-rates = <40000000>;
fsl,clk-source = /bits/ 8 <0>;
+ fsl,stop-mode = <&wakeupmix_gpr 0x0c 2>;
status = "disabled";
};
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
index 5fc613d24151..49cbdb55b4b3 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi
@@ -13,7 +13,7 @@
/ {
aliases {
ethernet0 = &eth0;
- /* for dsa slave device */
+ /* for DSA user port device */
ethernet1 = &switch0port1;
ethernet2 = &switch0port2;
ethernet3 = &switch0port3;
diff --git a/arch/arm64/boot/dts/mediatek/mt7622.dtsi b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
index 36ef2dbe8add..3ee9266fa8e9 100644
--- a/arch/arm64/boot/dts/mediatek/mt7622.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7622.dtsi
@@ -905,7 +905,7 @@
status = "disabled";
};
- sata_phy: t-phy@1a243000 {
+ sata_phy: t-phy {
compatible = "mediatek,mt7622-tphy",
"mediatek,generic-tphy-v1";
#address-cells = <2>;
diff --git a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
index 68539ea788df..24eda00e320d 100644
--- a/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt7986a.dtsi
@@ -434,7 +434,7 @@
};
};
- pcie_phy: t-phy@11c00000 {
+ pcie_phy: t-phy {
compatible = "mediatek,mt7986-tphy",
"mediatek,generic-tphy-v2";
#address-cells = <2>;
diff --git a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
index b2485ddfd33b..5d635085fe3f 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
+++ b/arch/arm64/boot/dts/mediatek/mt8195-demo.dts
@@ -48,7 +48,7 @@
memory@40000000 {
device_type = "memory";
- reg = <0 0x40000000 0 0x80000000>;
+ reg = <0 0x40000000 0x2 0x00000000>;
};
reserved-memory {
@@ -56,13 +56,8 @@
#size-cells = <2>;
ranges;
- /* 2 MiB reserved for ARM Trusted Firmware (BL31) */
- bl31_secmon_reserved: secmon@54600000 {
- no-map;
- reg = <0 0x54600000 0x0 0x200000>;
- };
-
- /* 12 MiB reserved for OP-TEE (BL32)
+ /*
+ * 12 MiB reserved for OP-TEE (BL32)
* +-----------------------+ 0x43e0_0000
* | SHMEM 2MiB |
* +-----------------------+ 0x43c0_0000
@@ -75,6 +70,34 @@
no-map;
reg = <0 0x43200000 0 0x00c00000>;
};
+
+ scp_mem: memory@50000000 {
+ compatible = "shared-dma-pool";
+ reg = <0 0x50000000 0 0x2900000>;
+ no-map;
+ };
+
+ vpu_mem: memory@53000000 {
+ compatible = "shared-dma-pool";
+ reg = <0 0x53000000 0 0x1400000>; /* 20 MB */
+ };
+
+ /* 2 MiB reserved for ARM Trusted Firmware (BL31) */
+ bl31_secmon_mem: memory@54600000 {
+ no-map;
+ reg = <0 0x54600000 0x0 0x200000>;
+ };
+
+ snd_dma_mem: memory@60000000 {
+ compatible = "shared-dma-pool";
+ reg = <0 0x60000000 0 0x1100000>;
+ no-map;
+ };
+
+ apu_mem: memory@62000000 {
+ compatible = "shared-dma-pool";
+ reg = <0 0x62000000 0 0x1400000>; /* 20 MB */
+ };
};
};
diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
index 4dbbf8fdab75..54c674c45b49 100644
--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
@@ -313,6 +313,7 @@
interrupts = <GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH 0>;
cpus = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>,
<&cpu4>, <&cpu5>, <&cpu6>, <&cpu7>;
+ status = "fail";
};
dmic_codec: dmic-codec {
@@ -2957,7 +2958,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xc000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE0_DL_ASYNC>;
};
@@ -2970,7 +2971,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xd000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE1_DL_ASYNC>;
};
@@ -2983,7 +2984,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xe000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE2_DL_ASYNC>;
};
@@ -2996,7 +2997,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c10XXXX 0xf000 0x1000>;
- mediatek,merge-mute = <1>;
+ mediatek,merge-mute;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE3_DL_ASYNC>;
};
@@ -3009,7 +3010,7 @@
clock-names = "merge","merge_async";
power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
mediatek,gce-client-reg = <&gce0 SUBSYS_1c11XXXX 0x0000 0x1000>;
- mediatek,merge-fifo-en = <1>;
+ mediatek,merge-fifo-en;
resets = <&vdosys1 MT8195_VDOSYS1_SW0_RST_B_MERGE4_DL_ASYNC>;
};
diff --git a/arch/arm64/boot/dts/qcom/apq8096-db820c.dts b/arch/arm64/boot/dts/qcom/apq8096-db820c.dts
index 385b178314db..3067a4091a7a 100644
--- a/arch/arm64/boot/dts/qcom/apq8096-db820c.dts
+++ b/arch/arm64/boot/dts/qcom/apq8096-db820c.dts
@@ -62,25 +62,23 @@
stdout-path = "serial0:115200n8";
};
- clocks {
- divclk4: divclk4 {
- compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <32768>;
- clock-output-names = "divclk4";
+ div1_mclk: divclk1 {
+ compatible = "gpio-gate-clock";
+ pinctrl-0 = <&audio_mclk>;
+ pinctrl-names = "default";
+ clocks = <&rpmcc RPM_SMD_DIV_CLK1>;
+ #clock-cells = <0>;
+ enable-gpios = <&pm8994_gpios 15 0>;
+ };
- pinctrl-names = "default";
- pinctrl-0 = <&divclk4_pin_a>;
- };
+ divclk4: divclk4 {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "divclk4";
- div1_mclk: divclk1 {
- compatible = "gpio-gate-clock";
- pinctrl-0 = <&audio_mclk>;
- pinctrl-names = "default";
- clocks = <&rpmcc RPM_SMD_DIV_CLK1>;
- #clock-cells = <0>;
- enable-gpios = <&pm8994_gpios 15 0>;
- };
+ pinctrl-names = "default";
+ pinctrl-0 = <&divclk4_pin_a>;
};
gpio-keys {
diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
index bcd2397eb373..06f8ff624181 100644
--- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
+++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
@@ -11,26 +11,24 @@
#include <dt-bindings/pinctrl/qcom,pmic-gpio.h>
/ {
- clocks {
- divclk1_cdc: divclk1 {
- compatible = "gpio-gate-clock";
- clocks = <&rpmcc RPM_SMD_DIV_CLK1>;
- #clock-cells = <0>;
- enable-gpios = <&pm8994_gpios 15 GPIO_ACTIVE_HIGH>;
+ divclk1_cdc: divclk1 {
+ compatible = "gpio-gate-clock";
+ clocks = <&rpmcc RPM_SMD_DIV_CLK1>;
+ #clock-cells = <0>;
+ enable-gpios = <&pm8994_gpios 15 GPIO_ACTIVE_HIGH>;
- pinctrl-names = "default";
- pinctrl-0 = <&divclk1_default>;
- };
+ pinctrl-names = "default";
+ pinctrl-0 = <&divclk1_default>;
+ };
- divclk4: divclk4 {
- compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <32768>;
- clock-output-names = "divclk4";
+ divclk4: divclk4 {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "divclk4";
- pinctrl-names = "default";
- pinctrl-0 = <&divclk4_pin_a>;
- };
+ pinctrl-names = "default";
+ pinctrl-0 = <&divclk4_pin_a>;
};
gpio-keys {
diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts
index d1066edaea47..f8e9d90afab0 100644
--- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts
+++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-gemini.dts
@@ -20,16 +20,14 @@
qcom,pmic-id = <0x20009 0x2000a 0x00 0x00>;
qcom,board-id = <31 0>;
- clocks {
- divclk2_haptics: divclk2 {
- compatible = "fixed-clock";
- #clock-cells = <0>;
- clock-frequency = <32768>;
- clock-output-names = "divclk2";
-
- pinctrl-names = "default";
- pinctrl-0 = <&divclk2_pin_a>;
- };
+ divclk2_haptics: divclk2 {
+ compatible = "fixed-clock";
+ #clock-cells = <0>;
+ clock-frequency = <32768>;
+ clock-output-names = "divclk2";
+
+ pinctrl-names = "default";
+ pinctrl-0 = <&divclk2_pin_a>;
};
};
diff --git a/arch/arm64/boot/dts/qcom/sa8775p-pmics.dtsi b/arch/arm64/boot/dts/qcom/sa8775p-pmics.dtsi
index 3c3b6287cd27..eaa43f022a65 100644
--- a/arch/arm64/boot/dts/qcom/sa8775p-pmics.dtsi
+++ b/arch/arm64/boot/dts/qcom/sa8775p-pmics.dtsi
@@ -173,7 +173,7 @@
compatible = "qcom,pmm8654au-gpio", "qcom,spmi-gpio";
reg = <0x8800>;
gpio-controller;
- gpio-ranges = <&pmm8654au_2_gpios 0 0 12>;
+ gpio-ranges = <&pmm8654au_1_gpios 0 0 12>;
#gpio-cells = <2>;
interrupt-controller;
#interrupt-cells = <2>;
diff --git a/arch/arm64/boot/dts/qcom/sm8150.dtsi b/arch/arm64/boot/dts/qcom/sm8150.dtsi
index a7c3020a5de4..06c53000bb74 100644
--- a/arch/arm64/boot/dts/qcom/sm8150.dtsi
+++ b/arch/arm64/boot/dts/qcom/sm8150.dtsi
@@ -3958,7 +3958,7 @@
pdc: interrupt-controller@b220000 {
compatible = "qcom,sm8150-pdc", "qcom,pdc";
- reg = <0 0x0b220000 0 0x400>;
+ reg = <0 0x0b220000 0 0x30000>;
qcom,pdc-ranges = <0 480 94>, <94 609 31>,
<125 63 1>;
#interrupt-cells = <2>;
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index 08a3ad3e7ae9..de0a1f2af983 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -68,15 +68,17 @@
simple-audio-card,format = "i2s";
simple-audio-card,name = "Haikou,I2S-codec";
simple-audio-card,mclk-fs = <512>;
+ simple-audio-card,frame-master = <&sgtl5000_codec>;
+ simple-audio-card,bitclock-master = <&sgtl5000_codec>;
- simple-audio-card,codec {
- clocks = <&sgtl5000_clk>;
+ sgtl5000_codec: simple-audio-card,codec {
sound-dai = <&sgtl5000>;
+ // Prevent the dai subsystem from overwriting the clock
+ // frequency. We are using a fixed-frequency oscillator.
+ system-clock-fixed;
};
simple-audio-card,cpu {
- bitclock-master;
- frame-master;
sound-dai = <&i2s0_8ch>;
};
};
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
index 7dccbe8a9393..f2279aa6ca9e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rock-pi-4.dtsi
@@ -492,6 +492,7 @@
&i2s0 {
pinctrl-0 = <&i2s0_2ch_bus>;
+ pinctrl-1 = <&i2s0_2ch_bus_bclk_off>;
rockchip,capture-channels = <2>;
rockchip,playback-channels = <2>;
status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 9da0b6d77c8d..5bc2d4faeea6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -2457,6 +2457,16 @@
<4 RK_PA0 1 &pcfg_pull_none>;
};
+ i2s0_2ch_bus_bclk_off: i2s0-2ch-bus-bclk-off {
+ rockchip,pins =
+ <3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>,
+ <3 RK_PD1 1 &pcfg_pull_none>,
+ <3 RK_PD2 1 &pcfg_pull_none>,
+ <3 RK_PD3 1 &pcfg_pull_none>,
+ <3 RK_PD7 1 &pcfg_pull_none>,
+ <4 RK_PA0 1 &pcfg_pull_none>;
+ };
+
i2s0_8ch_bus: i2s0-8ch-bus {
rockchip,pins =
<3 RK_PD0 1 &pcfg_pull_none>,
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 5315789f4868..a789119e6483 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -636,6 +636,7 @@ CONFIG_POWER_RESET_MSM=y
CONFIG_POWER_RESET_QCOM_PON=m
CONFIG_POWER_RESET_XGENE=y
CONFIG_POWER_RESET_SYSCON=y
+CONFIG_POWER_RESET_SYSCON_POWEROFF=y
CONFIG_SYSCON_REBOOT_MODE=y
CONFIG_NVMEM_REBOOT_MODE=m
CONFIG_BATTERY_SBS=m
@@ -1175,7 +1176,6 @@ CONFIG_COMMON_CLK_S2MPS11=y
CONFIG_COMMON_CLK_PWM=y
CONFIG_COMMON_CLK_RS9_PCIE=y
CONFIG_COMMON_CLK_VC5=y
-CONFIG_COMMON_CLK_NPCM8XX=y
CONFIG_COMMON_CLK_BD718XX=m
CONFIG_CLK_RASPBERRYPI=m
CONFIG_CLK_IMX8MM=y
diff --git a/arch/arm64/configs/hardening.config b/arch/arm64/configs/hardening.config
new file mode 100644
index 000000000000..b0e795208998
--- /dev/null
+++ b/arch/arm64/configs/hardening.config
@@ -0,0 +1,22 @@
+# Basic kernel hardening options (specific to arm64)
+
+# Make sure PAN emulation is enabled.
+CONFIG_ARM64_SW_TTBR0_PAN=y
+
+# Software Shadow Stack or PAC
+CONFIG_SHADOW_CALL_STACK=y
+
+# Pointer authentication (ARMv8.3 and later). If hardware actually supports
+# it, one can turn off CONFIG_STACKPROTECTOR_STRONG with this enabled.
+CONFIG_ARM64_PTR_AUTH=y
+CONFIG_ARM64_PTR_AUTH_KERNEL=y
+
+# Available in ARMv8.5 and later.
+CONFIG_ARM64_BTI=y
+CONFIG_ARM64_BTI_KERNEL=y
+CONFIG_ARM64_MTE=y
+CONFIG_KASAN_HW_TAGS=y
+CONFIG_ARM64_E0PD=y
+
+# Available in ARMv8.7 and later.
+CONFIG_ARM64_EPAN=y
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 4d537d56eb84..6792a1f83f2a 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -9,6 +9,7 @@
#ifndef _ASM_ACPI_H
#define _ASM_ACPI_H
+#include <linux/cpuidle.h>
#include <linux/efi.h>
#include <linux/memblock.h>
#include <linux/psci.h>
@@ -44,6 +45,24 @@
#define ACPI_MADT_GICC_TRBE (offsetof(struct acpi_madt_generic_interrupt, \
trbe_interrupt) + sizeof(u16))
+/*
+ * Arm® Functional Fixed Hardware Specification Version 1.2.
+ * Table 2: Arm Architecture context loss flags
+ */
+#define CPUIDLE_CORE_CTXT BIT(0) /* Core context Lost */
+
+static inline unsigned int arch_get_idle_state_flags(u32 arch_flags)
+{
+ if (arch_flags & CPUIDLE_CORE_CTXT)
+ return CPUIDLE_FLAG_TIMER_STOP;
+
+ return 0;
+}
+#define arch_get_idle_state_flags arch_get_idle_state_flags
+
+#define CPUIDLE_TRACE_CTXT BIT(1) /* Trace context loss */
+#define CPUIDLE_GICR_CTXT BIT(2) /* GICR */
+#define CPUIDLE_GICD_CTXT BIT(3) /* GICD */
/* Basic configuration for ACPI */
#ifdef CONFIG_ACPI
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 96e50227f940..5bba39376055 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -663,7 +663,7 @@ static inline bool supports_clearbhb(int scope)
isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1);
return cpuid_feature_extract_unsigned_field(isar2,
- ID_AA64ISAR2_EL1_BC_SHIFT);
+ ID_AA64ISAR2_EL1_CLRBHB_SHIFT);
}
const struct cpumask *system_32bit_el0_cpumask(void);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5f6f84837a49..74d00feb62f0 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -79,6 +79,7 @@
#define ARM_CPU_PART_CORTEX_A78AE 0xD42
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
+#define ARM_CPU_PART_CORTEX_A520 0xD80
#define ARM_CPU_PART_CORTEX_A710 0xD47
#define ARM_CPU_PART_CORTEX_A715 0xD4D
#define ARM_CPU_PART_CORTEX_X2 0xD48
@@ -148,6 +149,7 @@
#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
+#define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715)
#define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index f43a38ac1779..2ddc33d93b13 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -28,7 +28,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags);
#define arch_make_huge_pte arch_make_huge_pte
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte);
+ pte_t *ptep, pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5882b2415596..1095c6647e96 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -344,14 +344,14 @@
*/
#define __HFGRTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51))
#define __HFGRTR_EL2_MASK GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK (GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
#define __HFGWTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51) | \
BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
GENMASK(26, 25) | BIT(21) | BIT(18) | \
GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
#define __HFGWTR_EL2_MASK GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK (GENMASK(55, 54) | BIT(50))
+#define __HFGWTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
#define __HFGITR_EL2_RES0 GENMASK(63, 57)
#define __HFGITR_EL2_MASK GENMASK(54, 0)
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index b7238c72a04c..66efd67ea7e8 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -118,7 +118,7 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
u64 __guest_enter(struct kvm_vcpu *vcpu);
-bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
#ifdef __KVM_NVHE_HYPERVISOR__
void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index bd77253b62e0..531effca5f1f 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -39,7 +39,7 @@
#define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5)
#define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800)
-#define __NR_compat_syscalls 453
+#define __NR_compat_syscalls 457
#endif
#define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 78b68311ec81..c453291154fd 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -911,6 +911,12 @@ __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
__SYSCALL(__NR_cachestat, sys_cachestat)
#define __NR_fchmodat2 452
__SYSCALL(__NR_fchmodat2, sys_fchmodat2)
+#define __NR_futex_wake 454
+__SYSCALL(__NR_futex_wake, sys_futex_wake)
+#define __NR_futex_wait 455
+__SYSCALL(__NR_futex_wait, sys_futex_wait)
+#define __NR_futex_requeue 456
+__SYSCALL(__NR_futex_requeue, sys_futex_requeue)
/*
* Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index be66e94a21bd..5706e74c5578 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -730,6 +730,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
.cpu_enable = cpu_clear_bf16_from_user_emulation,
},
#endif
+#ifdef CONFIG_ARM64_ERRATUM_2966298
+ {
+ .desc = "ARM erratum 2966298",
+ .capability = ARM64_WORKAROUND_2966298,
+ /* Cortex-A520 r0p0 - r0p1 */
+ ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A520, 0, 0, 1),
+ },
+#endif
#ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
{
.desc = "AmpereOne erratum AC03_CPU_38",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index b018ae12ff5f..444a73c2e638 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -222,7 +222,8 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
- ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CLRBHB_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0),
ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 6ad61de03d0a..a6030913cd58 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -428,6 +428,10 @@ alternative_else_nop_endif
ldp x28, x29, [sp, #16 * 14]
.if \el == 0
+alternative_if ARM64_WORKAROUND_2966298
+ tlbi vale1, xzr
+ dsb nsh
+alternative_else_nop_endif
alternative_if_not ARM64_UNMAP_KERNEL_AT_EL0
ldr lr, [sp, #S_LR]
add sp, sp, #PT_REGS_SIZE // restore sp
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 960b98b43506..196533c362e1 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -215,7 +215,7 @@ asmlinkage notrace void secondary_start_kernel(void)
if (system_uses_irq_prio_masking())
init_gic_priority_masking();
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
trace_hardirqs_off();
/*
@@ -401,7 +401,7 @@ void __noreturn cpu_die_early(void)
/* Mark this CPU absent */
set_cpu_present(cpu, 0);
- rcu_report_dead(cpu);
+ rcutree_report_cpu_dead();
if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) {
update_cpu_boot_status(CPU_KILL_ME);
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 6dcdae4d38cb..a1e24228aaaa 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -55,11 +55,6 @@ static struct irq_ops arch_timer_irq_ops = {
.get_input_level = kvm_arch_timer_get_input_level,
};
-static bool has_cntpoff(void)
-{
- return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));
-}
-
static int nr_timers(struct kvm_vcpu *vcpu)
{
if (!vcpu_has_nv(vcpu))
@@ -180,7 +175,7 @@ u64 kvm_phys_timer_read(void)
return timecounter->cc->read(timecounter->cc);
}
-static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
+void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
{
if (vcpu_has_nv(vcpu)) {
if (is_hyp_ctxt(vcpu)) {
@@ -548,8 +543,7 @@ static void timer_save_state(struct arch_timer_context *ctx)
timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
cval = read_sysreg_el0(SYS_CNTP_CVAL);
- if (!has_cntpoff())
- cval -= timer_get_offset(ctx);
+ cval -= timer_get_offset(ctx);
timer_set_cval(ctx, cval);
@@ -636,8 +630,7 @@ static void timer_restore_state(struct arch_timer_context *ctx)
cval = timer_get_cval(ctx);
offset = timer_get_offset(ctx);
set_cntpoff(offset);
- if (!has_cntpoff())
- cval += offset;
+ cval += offset;
write_sysreg_el0(cval, SYS_CNTP_CVAL);
isb();
write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 9ced1bf0c2b7..ee902ff2a50f 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -977,6 +977,8 @@ enum fg_filter_id {
static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
/* HFGRTR_EL2, HFGWTR_EL2 */
+ SR_FGT(SYS_PIR_EL1, HFGxTR, nPIR_EL1, 0),
+ SR_FGT(SYS_PIRE0_EL1, HFGxTR, nPIRE0_EL1, 0),
SR_FGT(SYS_TPIDR2_EL0, HFGxTR, nTPIDR2_EL0, 0),
SR_FGT(SYS_SMPRI_EL1, HFGxTR, nSMPRI_EL1, 0),
SR_FGT(SYS_ACCDATA_EL1, HFGxTR, nACCDATA_EL1, 0),
diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
index 1becb10ecd80..d9fd5e6c7d3c 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
@@ -12,6 +12,6 @@
#define FFA_MAX_FUNC_NUM 0x7F
int hyp_ffa_init(void *pages);
-bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt);
+bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
#endif /* __KVM_HYP_FFA_H */
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index ab4f5d160c58..6e4dba9eadef 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -634,9 +634,8 @@ out_handled:
return true;
}
-bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt)
+bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
{
- DECLARE_REG(u64, func_id, host_ctxt, 0);
struct arm_smccc_res res;
/*
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 90fade1b032e..1cc06e6797bd 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -57,6 +57,7 @@ __do_hyp_init:
cmp x0, #HVC_STUB_HCALL_NR
b.lo __kvm_handle_stub_hvc
+ bic x0, x0, #ARM_SMCCC_CALL_HINTS
mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
cmp x0, x3
b.eq 1f
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 857d9bc04fd4..2385fd03ed87 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -368,6 +368,7 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
if (static_branch_unlikely(&kvm_protected_mode_initialized))
hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize;
+ id &= ~ARM_SMCCC_CALL_HINTS;
id -= KVM_HOST_SMCCC_ID(0);
if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall)))
@@ -392,11 +393,14 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
{
+ DECLARE_REG(u64, func_id, host_ctxt, 0);
bool handled;
- handled = kvm_host_psci_handler(host_ctxt);
+ func_id &= ~ARM_SMCCC_CALL_HINTS;
+
+ handled = kvm_host_psci_handler(host_ctxt, func_id);
if (!handled)
- handled = kvm_host_ffa_handler(host_ctxt);
+ handled = kvm_host_ffa_handler(host_ctxt, func_id);
if (!handled)
default_host_smc_handler(host_ctxt);
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 24543d2a3490..d57bcb6ab94d 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -273,9 +273,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
}
}
-bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
{
- DECLARE_REG(u64, func_id, host_ctxt, 0);
unsigned long ret;
switch (kvm_host_psci_config.version) {
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 6537f58b1a8c..448b17080d36 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -39,6 +39,26 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
___activate_traps(vcpu);
+ if (has_cntpoff()) {
+ struct timer_map map;
+
+ get_timer_map(vcpu, &map);
+
+ /*
+ * We're entrering the guest. Reload the correct
+ * values from memory now that TGE is clear.
+ */
+ if (map.direct_ptimer == vcpu_ptimer(vcpu))
+ val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+ if (map.direct_ptimer == vcpu_hptimer(vcpu))
+ val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
+
+ if (map.direct_ptimer) {
+ write_sysreg_el0(val, SYS_CNTP_CVAL);
+ isb();
+ }
+ }
+
val = read_sysreg(cpacr_el1);
val |= CPACR_ELx_TTA;
val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
@@ -77,6 +97,30 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+ if (has_cntpoff()) {
+ struct timer_map map;
+ u64 val, offset;
+
+ get_timer_map(vcpu, &map);
+
+ /*
+ * We're exiting the guest. Save the latest CVAL value
+ * to memory and apply the offset now that TGE is set.
+ */
+ val = read_sysreg_el0(SYS_CNTP_CVAL);
+ if (map.direct_ptimer == vcpu_ptimer(vcpu))
+ __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val;
+ if (map.direct_ptimer == vcpu_hptimer(vcpu))
+ __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
+
+ offset = read_sysreg_s(SYS_CNTPOFF_EL2);
+
+ if (map.direct_ptimer && offset) {
+ write_sysreg_el0(val + offset, SYS_CNTP_CVAL);
+ isb();
+ }
+ }
+
/*
* ARM errata 1165522 and 1530923 require the actual execution of the
* above before we can switch to the EL2/EL0 translation regime used by
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 587a104f66c3..482280fe22d7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -652,6 +652,9 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
mutex_unlock(&kvm_hyp_pgd_mutex);
+ if (!ret)
+ *haddr = base;
+
return ret;
}
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 0eea225fd09a..a243934c5568 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -39,7 +39,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
- if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr))
+ if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr))
return;
if (!attr->exclude_host)
@@ -55,7 +55,7 @@ void kvm_clr_pmu_events(u32 clr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
- if (!kvm_arm_support_pmu_v3() || !pmu)
+ if (!kvm_arm_support_pmu_v3())
return;
pmu->events_host &= ~clr;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..0afd6136e275 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2122,8 +2122,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
- { SYS_DESC(SYS_PIRE0_EL1), access_vm_reg, reset_unknown, PIRE0_EL1 },
- { SYS_DESC(SYS_PIR_EL1), access_vm_reg, reset_unknown, PIR_EL1 },
+ { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 },
+ { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 },
{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
{ SYS_DESC(SYS_LORSA_EL1), trap_loregion },
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 9c52718ea750..13fd592228b1 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -241,15 +241,8 @@ static void clear_flush(struct mm_struct *mm,
flush_tlb_range(&vma, saddr, addr);
}
-static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry)
-{
- VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry));
-
- return page_folio(pfn_to_page(swp_offset_pfn(entry)));
-}
-
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
+ pte_t *ptep, pte_t pte, unsigned long sz)
{
size_t pgsize;
int i;
@@ -257,13 +250,10 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
unsigned long pfn, dpfn;
pgprot_t hugeprot;
- if (!pte_present(pte)) {
- struct folio *folio;
-
- folio = hugetlb_swap_entry_to_folio(pte_to_swp_entry(pte));
- ncontig = num_contig_ptes(folio_size(folio), &pgsize);
+ ncontig = num_contig_ptes(sz, &pgsize);
- for (i = 0; i < ncontig; i++, ptep++)
+ if (!pte_present(pte)) {
+ for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
set_pte_at(mm, addr, ptep, pte);
return;
}
@@ -273,7 +263,6 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
return;
}
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
pfn = pte_pfn(pte);
dpfn = pgsize >> PAGE_SHIFT;
hugeprot = pte_pgprot(pte);
@@ -571,5 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
{
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ unsigned long psize = huge_page_size(hstate_vma(vma));
+
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 150d1c6543f7..7d4af64e3982 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -288,7 +288,7 @@ static bool is_lsi_offset(int offset, int scale)
static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf)
{
const struct bpf_prog *prog = ctx->prog;
- const bool is_main_prog = prog->aux->func_idx == 0;
+ const bool is_main_prog = !bpf_is_subprog(prog);
const u8 r6 = bpf2a64[BPF_REG_6];
const u8 r7 = bpf2a64[BPF_REG_7];
const u8 r8 = bpf2a64[BPF_REG_8];
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index c3f06fdef609..dea3dc89234b 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -84,6 +84,7 @@ WORKAROUND_2077057
WORKAROUND_2457168
WORKAROUND_2645198
WORKAROUND_2658417
+WORKAROUND_2966298
WORKAROUND_AMPERE_AC03_CPU_38
WORKAROUND_TRBE_OVERWRITE_FILL_MODE
WORKAROUND_TSB_FLUSH_FAILURE
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg
index 2517ef7c21cf..76ce150e7347 100644
--- a/arch/arm64/tools/sysreg
+++ b/arch/arm64/tools/sysreg
@@ -1347,7 +1347,11 @@ UnsignedEnum 51:48 RPRFM
0b0000 NI
0b0001 IMP
EndEnum
-Res0 47:28
+Res0 47:32
+UnsignedEnum 31:28 CLRBHB
+ 0b0000 NI
+ 0b0001 IMP
+EndEnum
UnsignedEnum 27:24 PAC_frac
0b0000 NI
0b0001 IMP
diff --git a/arch/ia64/include/asm/cpu.h b/arch/ia64/include/asm/cpu.h
index db125df9e088..642d71675ddb 100644
--- a/arch/ia64/include/asm/cpu.h
+++ b/arch/ia64/include/asm/cpu.h
@@ -15,9 +15,4 @@ DECLARE_PER_CPU(struct ia64_cpu, cpu_devices);
DECLARE_PER_CPU(int, cpu_state);
-#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
-#endif
-
#endif /* _ASM_IA64_CPU_H_ */
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 15f6cfddcc08..41e8fe55cd98 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -907,3 +907,7 @@ EXPORT_SYMBOL(acpi_unregister_ioapic);
* TBD when IA64 starts to support suspend...
*/
int acpi_suspend_lowlevel(void) { return 0; }
+
+void acpi_proc_quirk_mwait_check(void)
+{
+}
diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl
index 83d8609aec03..81375ea78288 100644
--- a/arch/ia64/kernel/syscalls/syscall.tbl
+++ b/arch/ia64/kernel/syscalls/syscall.tbl
@@ -373,3 +373,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 94a848b06f15..741863a187a6 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -59,7 +59,7 @@ void __ref arch_unregister_cpu(int num)
}
EXPORT_SYMBOL(arch_unregister_cpu);
#else
-static int __init arch_register_cpu(int num)
+int __init arch_register_cpu(int num)
{
return register_cpu(&sysfs_cpus[num].cpu, num);
}
diff --git a/arch/loongarch/include/asm/addrspace.h b/arch/loongarch/include/asm/addrspace.h
index 5c9c03bdf915..b24437e28c6e 100644
--- a/arch/loongarch/include/asm/addrspace.h
+++ b/arch/loongarch/include/asm/addrspace.h
@@ -19,7 +19,7 @@
*/
#ifndef __ASSEMBLY__
#ifndef PHYS_OFFSET
-#define PHYS_OFFSET _AC(0, UL)
+#define PHYS_OFFSET _UL(0)
#endif
extern unsigned long vm_map_base;
#endif /* __ASSEMBLY__ */
@@ -43,7 +43,7 @@ extern unsigned long vm_map_base;
* Memory above this physical address will be considered highmem.
*/
#ifndef HIGHMEM_START
-#define HIGHMEM_START (_AC(1, UL) << _AC(DMW_PABITS, UL))
+#define HIGHMEM_START (_UL(1) << _UL(DMW_PABITS))
#endif
#define TO_PHYS(x) ( ((x) & TO_PHYS_MASK))
@@ -65,16 +65,16 @@ extern unsigned long vm_map_base;
#define _ATYPE_
#define _ATYPE32_
#define _ATYPE64_
-#define _CONST64_(x) x
#else
#define _ATYPE_ __PTRDIFF_TYPE__
#define _ATYPE32_ int
#define _ATYPE64_ __s64
+#endif
+
#ifdef CONFIG_64BIT
-#define _CONST64_(x) x ## UL
+#define _CONST64_(x) _UL(x)
#else
-#define _CONST64_(x) x ## ULL
-#endif
+#define _CONST64_(x) _ULL(x)
#endif
/*
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index 7af0cebf28d7..b9a4ab54285c 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -111,6 +111,15 @@
#define R_LARCH_TLS_GD_HI20 98
#define R_LARCH_32_PCREL 99
#define R_LARCH_RELAX 100
+#define R_LARCH_DELETE 101
+#define R_LARCH_ALIGN 102
+#define R_LARCH_PCREL20_S2 103
+#define R_LARCH_CFA 104
+#define R_LARCH_ADD6 105
+#define R_LARCH_SUB6 106
+#define R_LARCH_ADD_ULEB128 107
+#define R_LARCH_SUB_ULEB128 108
+#define R_LARCH_64_PCREL 109
#ifndef ELF_ARCH
diff --git a/arch/loongarch/include/asm/exception.h b/arch/loongarch/include/asm/exception.h
new file mode 100644
index 000000000000..af74a3fdcad1
--- /dev/null
+++ b/arch/loongarch/include/asm/exception.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __ASM_EXCEPTION_H
+#define __ASM_EXCEPTION_H
+
+#include <asm/ptrace.h>
+#include <linux/kprobes.h>
+
+void show_registers(struct pt_regs *regs);
+
+asmlinkage void cache_parity_error(void);
+asmlinkage void noinstr do_ade(struct pt_regs *regs);
+asmlinkage void noinstr do_ale(struct pt_regs *regs);
+asmlinkage void noinstr do_bce(struct pt_regs *regs);
+asmlinkage void noinstr do_bp(struct pt_regs *regs);
+asmlinkage void noinstr do_ri(struct pt_regs *regs);
+asmlinkage void noinstr do_fpu(struct pt_regs *regs);
+asmlinkage void noinstr do_fpe(struct pt_regs *regs, unsigned long fcsr);
+asmlinkage void noinstr do_lsx(struct pt_regs *regs);
+asmlinkage void noinstr do_lasx(struct pt_regs *regs);
+asmlinkage void noinstr do_lbt(struct pt_regs *regs);
+asmlinkage void noinstr do_watch(struct pt_regs *regs);
+asmlinkage void noinstr do_syscall(struct pt_regs *regs);
+asmlinkage void noinstr do_reserved(struct pt_regs *regs);
+asmlinkage void noinstr do_vint(struct pt_regs *regs, unsigned long sp);
+asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
+ unsigned long write, unsigned long address);
+
+asmlinkage void handle_ade(void);
+asmlinkage void handle_ale(void);
+asmlinkage void handle_bce(void);
+asmlinkage void handle_sys(void);
+asmlinkage void handle_bp(void);
+asmlinkage void handle_ri(void);
+asmlinkage void handle_fpu(void);
+asmlinkage void handle_fpe(void);
+asmlinkage void handle_lsx(void);
+asmlinkage void handle_lasx(void);
+asmlinkage void handle_lbt(void);
+asmlinkage void handle_watch(void);
+asmlinkage void handle_reserved(void);
+asmlinkage void handle_vint(void);
+asmlinkage void noinstr handle_loongarch_irq(struct pt_regs *regs);
+
+#endif /* __ASM_EXCEPTION_H */
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 0dcb36b32cb2..c486c2341b66 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -52,10 +52,9 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
* @offset: bus address of the memory
* @size: size of the resource to map
*/
-extern pgprot_t pgprot_wc;
-
#define ioremap_wc(offset, size) \
- ioremap_prot((offset), (size), pgprot_val(pgprot_wc))
+ ioremap_prot((offset), (size), \
+ pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC))
#define ioremap_cache(offset, size) \
ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))
diff --git a/arch/loongarch/include/asm/kasan.h b/arch/loongarch/include/asm/kasan.h
index deeff8158f45..cd6084f4e153 100644
--- a/arch/loongarch/include/asm/kasan.h
+++ b/arch/loongarch/include/asm/kasan.h
@@ -10,8 +10,6 @@
#include <asm/io.h>
#include <asm/pgtable.h>
-#define __HAVE_ARCH_SHADOW_MAP
-
#define KASAN_SHADOW_SCALE_SHIFT 3
#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL)
@@ -62,61 +60,22 @@
extern bool kasan_early_stage;
extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
+#define kasan_mem_to_shadow kasan_mem_to_shadow
+void *kasan_mem_to_shadow(const void *addr);
+
+#define kasan_shadow_to_mem kasan_shadow_to_mem
+const void *kasan_shadow_to_mem(const void *shadow_addr);
+
#define kasan_arch_is_ready kasan_arch_is_ready
static __always_inline bool kasan_arch_is_ready(void)
{
return !kasan_early_stage;
}
-static inline void *kasan_mem_to_shadow(const void *addr)
-{
- if (!kasan_arch_is_ready()) {
- return (void *)(kasan_early_shadow_page);
- } else {
- unsigned long maddr = (unsigned long)addr;
- unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
- unsigned long offset = 0;
-
- maddr &= XRANGE_SHADOW_MASK;
- switch (xrange) {
- case XKPRANGE_CC_SEG:
- offset = XKPRANGE_CC_SHADOW_OFFSET;
- break;
- case XKPRANGE_UC_SEG:
- offset = XKPRANGE_UC_SHADOW_OFFSET;
- break;
- case XKVRANGE_VC_SEG:
- offset = XKVRANGE_VC_SHADOW_OFFSET;
- break;
- default:
- WARN_ON(1);
- return NULL;
- }
-
- return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset);
- }
-}
-
-static inline const void *kasan_shadow_to_mem(const void *shadow_addr)
+#define addr_has_metadata addr_has_metadata
+static __always_inline bool addr_has_metadata(const void *addr)
{
- unsigned long addr = (unsigned long)shadow_addr;
-
- if (unlikely(addr > KASAN_SHADOW_END) ||
- unlikely(addr < KASAN_SHADOW_START)) {
- WARN_ON(1);
- return NULL;
- }
-
- if (addr >= XKVRANGE_VC_SHADOW_OFFSET)
- return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START);
- else if (addr >= XKPRANGE_UC_SHADOW_OFFSET)
- return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START);
- else if (addr >= XKPRANGE_CC_SHADOW_OFFSET)
- return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START);
- else {
- WARN_ON(1);
- return NULL;
- }
+ return (kasan_mem_to_shadow((void *)addr) != NULL);
}
void kasan_init(void);
diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h
index 81b0c4cfbf4f..e2eca1a25b4e 100644
--- a/arch/loongarch/include/asm/linkage.h
+++ b/arch/loongarch/include/asm/linkage.h
@@ -33,4 +33,12 @@
.cfi_endproc; \
SYM_END(name, SYM_T_FUNC)
+#define SYM_CODE_START(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \
+ .cfi_startproc;
+
+#define SYM_CODE_END(name) \
+ .cfi_endproc; \
+ SYM_END(name, SYM_T_NONE)
+
#endif
diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h
index c49675852bdc..f53ea653af76 100644
--- a/arch/loongarch/include/asm/local.h
+++ b/arch/loongarch/include/asm/local.h
@@ -70,22 +70,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read(l); \
- while (c != (u) && (old = local_cmpxchg((l), c, c + (a))) != c) \
- c = old; \
- c != (u); \
-})
+static inline bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
#define local_dec_return(l) local_sub_return(1, (l))
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 35348d4c4209..21319c1e045c 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -105,13 +105,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
return __pgprot(prot);
}
+extern bool wc_enabled;
+
#define pgprot_writecombine pgprot_writecombine
static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
{
unsigned long prot = pgprot_val(_prot);
- prot = (prot & ~_CACHE_MASK) | _CACHE_WUC;
+ prot = (prot & ~_CACHE_MASK) | (wc_enabled ? _CACHE_WUC : _CACHE_SUC);
return __pgprot(prot);
}
diff --git a/arch/loongarch/include/asm/smp.h b/arch/loongarch/include/asm/smp.h
index 66ecb480c894..f81e5f01d619 100644
--- a/arch/loongarch/include/asm/smp.h
+++ b/arch/loongarch/include/asm/smp.h
@@ -70,6 +70,7 @@ struct secondary_data {
extern struct secondary_data cpuboot_data;
extern asmlinkage void smpboot_entry(void);
+extern asmlinkage void start_secondary(void);
extern void calculate_cpu_foreign_map(void);
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index c56ea0b75448..4fcc168f0732 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -19,6 +19,10 @@ obj-$(CONFIG_CPU_HAS_LBT) += lbt.o
obj-$(CONFIG_ARCH_STRICT_ALIGN) += unaligned.o
+CFLAGS_module.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall.o += $(call cc-option,-Wno-override-init,)
+CFLAGS_perf_event.o += $(call cc-option,-Wno-override-init,)
+
ifdef CONFIG_FUNCTION_TRACER
ifndef CONFIG_DYNAMIC_FTRACE
obj-y += mcount.o ftrace.o
diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 9450e09073eb..8e00a754e548 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -281,7 +281,6 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
pr_info("SRAT: PXM %u -> CPU 0x%02x -> Node %u\n", pxm, pa->apic_id, node);
}
-void __init acpi_numa_arch_fixup(void) {}
#endif
void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size)
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 65518bb8f472..1ec8e4c4cc2b 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -18,7 +18,7 @@
.text
.cfi_sections .debug_frame
.align 5
-SYM_FUNC_START(handle_syscall)
+SYM_CODE_START(handle_syscall)
csrrd t0, PERCPU_BASE_KS
la.pcrel t1, kernelsp
add.d t1, t1, t0
@@ -71,7 +71,7 @@ SYM_FUNC_START(handle_syscall)
bl do_syscall
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_syscall)
+SYM_CODE_END(handle_syscall)
_ASM_NOKPROBE(handle_syscall)
SYM_CODE_START(ret_from_fork)
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 78f066384657..2bb3aa2dcfcb 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -31,7 +31,7 @@ SYM_FUNC_START(__arch_cpu_idle)
1: jr ra
SYM_FUNC_END(__arch_cpu_idle)
-SYM_FUNC_START(handle_vint)
+SYM_CODE_START(handle_vint)
BACKUP_T0T1
SAVE_ALL
la_abs t1, __arch_cpu_idle
@@ -46,11 +46,11 @@ SYM_FUNC_START(handle_vint)
la_abs t0, do_vint
jirl ra, t0, 0
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_vint)
+SYM_CODE_END(handle_vint)
-SYM_FUNC_START(except_vec_cex)
+SYM_CODE_START(except_vec_cex)
b cache_parity_error
-SYM_FUNC_END(except_vec_cex)
+SYM_CODE_END(except_vec_cex)
.macro build_prep_badv
csrrd t0, LOONGARCH_CSR_BADV
@@ -66,7 +66,7 @@ SYM_FUNC_END(except_vec_cex)
.macro BUILD_HANDLER exception handler prep
.align 5
- SYM_FUNC_START(handle_\exception)
+ SYM_CODE_START(handle_\exception)
666:
BACKUP_T0T1
SAVE_ALL
@@ -76,7 +76,7 @@ SYM_FUNC_END(except_vec_cex)
jirl ra, t0, 0
668:
RESTORE_ALL_AND_RET
- SYM_FUNC_END(handle_\exception)
+ SYM_CODE_END(handle_\exception)
SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
.endm
@@ -93,7 +93,7 @@ SYM_FUNC_END(except_vec_cex)
BUILD_HANDLER watch watch none
BUILD_HANDLER reserved reserved none /* others */
-SYM_FUNC_START(handle_sys)
+SYM_CODE_START(handle_sys)
la_abs t0, handle_syscall
jr t0
-SYM_FUNC_END(handle_sys)
+SYM_CODE_END(handle_sys)
diff --git a/arch/loongarch/kernel/mem.c b/arch/loongarch/kernel/mem.c
index 4a4107a6a965..aed901c57fb4 100644
--- a/arch/loongarch/kernel/mem.c
+++ b/arch/loongarch/kernel/mem.c
@@ -50,7 +50,6 @@ void __init memblock_init(void)
}
memblock_set_current_limit(PFN_PHYS(max_low_pfn));
- memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
/* Reserve the first 2MB */
memblock_reserve(PHYS_OFFSET, 0x200000);
@@ -58,4 +57,7 @@ void __init memblock_init(void)
/* Reserve the kernel text/data/bss */
memblock_reserve(__pa_symbol(&_text),
__pa_symbol(&_end) - __pa_symbol(&_text));
+
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
+ memblock_set_node(0, PHYS_ADDR_MAX, &memblock.reserved, 0);
}
diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c
index d4dbcda1c4b0..e2f30ff9afde 100644
--- a/arch/loongarch/kernel/module-sections.c
+++ b/arch/loongarch/kernel/module-sections.c
@@ -6,6 +6,7 @@
#include <linux/elf.h>
#include <linux/kernel.h>
#include <linux/module.h>
+#include <linux/moduleloader.h>
#include <linux/ftrace.h>
Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val)
diff --git a/arch/loongarch/kernel/module.c b/arch/loongarch/kernel/module.c
index b8b86088b2dd..b13b2858fe39 100644
--- a/arch/loongarch/kernel/module.c
+++ b/arch/loongarch/kernel/module.c
@@ -367,6 +367,24 @@ static int apply_r_larch_got_pc(struct module *mod,
return apply_r_larch_pcala(mod, location, got, rela_stack, rela_stack_top, type);
}
+static int apply_r_larch_32_pcrel(struct module *mod, u32 *location, Elf_Addr v,
+ s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+ ptrdiff_t offset = (void *)v - (void *)location;
+
+ *(u32 *)location = offset;
+ return 0;
+}
+
+static int apply_r_larch_64_pcrel(struct module *mod, u32 *location, Elf_Addr v,
+ s64 *rela_stack, size_t *rela_stack_top, unsigned int type)
+{
+ ptrdiff_t offset = (void *)v - (void *)location;
+
+ *(u64 *)location = offset;
+ return 0;
+}
+
/*
* reloc_handlers_rela() - Apply a particular relocation to a module
* @mod: the module to apply the reloc to
@@ -382,7 +400,7 @@ typedef int (*reloc_rela_handler)(struct module *mod, u32 *location, Elf_Addr v,
/* The handlers for known reloc types */
static reloc_rela_handler reloc_rela_handlers[] = {
- [R_LARCH_NONE ... R_LARCH_RELAX] = apply_r_larch_error,
+ [R_LARCH_NONE ... R_LARCH_64_PCREL] = apply_r_larch_error,
[R_LARCH_NONE] = apply_r_larch_none,
[R_LARCH_32] = apply_r_larch_32,
@@ -396,6 +414,8 @@ static reloc_rela_handler reloc_rela_handlers[] = {
[R_LARCH_SOP_POP_32_S_10_5 ... R_LARCH_SOP_POP_32_U] = apply_r_larch_sop_imm_field,
[R_LARCH_ADD32 ... R_LARCH_SUB64] = apply_r_larch_add_sub,
[R_LARCH_PCALA_HI20...R_LARCH_PCALA64_HI12] = apply_r_larch_pcala,
+ [R_LARCH_32_PCREL] = apply_r_larch_32_pcrel,
+ [R_LARCH_64_PCREL] = apply_r_larch_64_pcrel,
};
int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
diff --git a/arch/loongarch/kernel/numa.c b/arch/loongarch/kernel/numa.c
index c7d33c489e04..6e65ff12d5c7 100644
--- a/arch/loongarch/kernel/numa.c
+++ b/arch/loongarch/kernel/numa.c
@@ -436,7 +436,7 @@ void __init paging_init(void)
void __init mem_init(void)
{
- high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
+ high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
memblock_free_all();
}
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 3cb082e0c992..767d94cce0de 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -37,6 +37,7 @@
#include <asm/bootinfo.h>
#include <asm/cpu.h>
#include <asm/elf.h>
+#include <asm/exec.h>
#include <asm/fpu.h>
#include <asm/lbt.h>
#include <asm/io.h>
diff --git a/arch/loongarch/kernel/relocate_kernel.S b/arch/loongarch/kernel/relocate_kernel.S
index d13252553a7c..f49f6b053763 100644
--- a/arch/loongarch/kernel/relocate_kernel.S
+++ b/arch/loongarch/kernel/relocate_kernel.S
@@ -72,7 +72,6 @@ copy_word:
LONG_ADDI s5, s5, -1
beqz s5, process_entry
b copy_word
- b process_entry
done:
ibar 0
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 7783f0a3d742..aed65915e932 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -161,19 +161,19 @@ static void __init smbios_parse(void)
}
#ifdef CONFIG_ARCH_WRITECOMBINE
-pgprot_t pgprot_wc = PAGE_KERNEL_WUC;
+bool wc_enabled = true;
#else
-pgprot_t pgprot_wc = PAGE_KERNEL_SUC;
+bool wc_enabled = false;
#endif
-EXPORT_SYMBOL(pgprot_wc);
+EXPORT_SYMBOL(wc_enabled);
static int __init setup_writecombine(char *p)
{
if (!strcmp(p, "on"))
- pgprot_wc = PAGE_KERNEL_WUC;
+ wc_enabled = true;
else if (!strcmp(p, "off"))
- pgprot_wc = PAGE_KERNEL_SUC;
+ wc_enabled = false;
else
pr_warn("Unknown writecombine setting \"%s\".\n", p);
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 504fdfe85203..4a3686d13349 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -13,6 +13,7 @@
#include <linux/audit.h>
#include <linux/cache.h>
#include <linux/context_tracking.h>
+#include <linux/entry-common.h>
#include <linux/irqflags.h>
#include <linux/sched.h>
#include <linux/mm.h>
@@ -891,8 +892,8 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon
return new_sp;
}
-void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
- struct extctx_layout *extctx)
+static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
+ struct extctx_layout *extctx)
{
unsigned long sp;
@@ -922,7 +923,7 @@ void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs,
* Atomically swap in the new signal mask, and wait for a signal.
*/
-asmlinkage long sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
{
int sig;
sigset_t set;
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 6667b0a90f81..ef35c871244f 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -13,6 +13,7 @@
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/interrupt.h>
+#include <linux/profile.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/threads.h>
@@ -556,10 +557,12 @@ void smp_send_stop(void)
smp_call_function(stop_this_cpu, NULL, 0);
}
+#ifdef CONFIG_PROFILING
int setup_profiling_timer(unsigned int multiplier)
{
return 0;
}
+#endif
static void flush_tlb_all_ipi(void *info)
{
diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c
index 3fc4211db989..b4c5acd7aa3b 100644
--- a/arch/loongarch/kernel/syscall.c
+++ b/arch/loongarch/kernel/syscall.c
@@ -13,6 +13,7 @@
#include <linux/unistd.h>
#include <asm/asm.h>
+#include <asm/exception.h>
#include <asm/signal.h>
#include <asm/switch_to.h>
#include <asm-generic/syscalls.h>
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index c189e03cd5da..3064af94db9c 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -29,7 +29,7 @@ static void constant_event_handler(struct clock_event_device *dev)
{
}
-irqreturn_t constant_timer_interrupt(int irq, void *data)
+static irqreturn_t constant_timer_interrupt(int irq, void *data)
{
int cpu = smp_processor_id();
struct clock_event_device *cd;
diff --git a/arch/loongarch/kernel/topology.c b/arch/loongarch/kernel/topology.c
index caa7cd859078..3fd166006698 100644
--- a/arch/loongarch/kernel/topology.c
+++ b/arch/loongarch/kernel/topology.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/acpi.h>
#include <linux/cpu.h>
#include <linux/cpumask.h>
#include <linux/init.h>
@@ -7,6 +8,8 @@
#include <linux/percpu.h>
#include <asm/bootinfo.h>
+#include <acpi/processor.h>
+
static DEFINE_PER_CPU(struct cpu, cpu_devices);
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 65214774ef7c..aebfc3733a76 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -25,7 +25,6 @@
#include <linux/ptrace.h>
#include <linux/kgdb.h>
#include <linux/kdebug.h>
-#include <linux/kprobes.h>
#include <linux/notifier.h>
#include <linux/irq.h>
#include <linux/perf_event.h>
@@ -35,6 +34,7 @@
#include <asm/branch.h>
#include <asm/break.h>
#include <asm/cpu.h>
+#include <asm/exception.h>
#include <asm/fpu.h>
#include <asm/lbt.h>
#include <asm/inst.h>
@@ -53,21 +53,6 @@
#include "access-helper.h"
-extern asmlinkage void handle_ade(void);
-extern asmlinkage void handle_ale(void);
-extern asmlinkage void handle_bce(void);
-extern asmlinkage void handle_sys(void);
-extern asmlinkage void handle_bp(void);
-extern asmlinkage void handle_ri(void);
-extern asmlinkage void handle_fpu(void);
-extern asmlinkage void handle_fpe(void);
-extern asmlinkage void handle_lbt(void);
-extern asmlinkage void handle_lsx(void);
-extern asmlinkage void handle_lasx(void);
-extern asmlinkage void handle_reserved(void);
-extern asmlinkage void handle_watch(void);
-extern asmlinkage void handle_vint(void);
-
static void show_backtrace(struct task_struct *task, const struct pt_regs *regs,
const char *loglvl, bool user)
{
@@ -439,8 +424,8 @@ static inline void setup_vint_size(unsigned int size)
* happen together with Overflow or Underflow, and `ptrace' can set
* any bits.
*/
-void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr,
- struct task_struct *tsk)
+static void force_fcsr_sig(unsigned long fcsr,
+ void __user *fault_addr, struct task_struct *tsk)
{
int si_code = FPE_FLTUNK;
@@ -458,7 +443,7 @@ void force_fcsr_sig(unsigned long fcsr, void __user *fault_addr,
force_sig_fault(SIGFPE, si_code, fault_addr);
}
-int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr)
+static int process_fpemu_return(int sig, void __user *fault_addr, unsigned long fcsr)
{
int si_code;
@@ -824,7 +809,7 @@ out:
asmlinkage void noinstr do_ri(struct pt_regs *regs)
{
int status = SIGILL;
- unsigned int opcode = 0;
+ unsigned int __maybe_unused opcode;
unsigned int __user *era = (unsigned int __user *)exception_era(regs);
irqentry_state_t state = irqentry_enter(regs);
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index b1686afcf876..bb2ec86f37a8 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -53,33 +53,6 @@ SECTIONS
. = ALIGN(PECOFF_SEGMENT_ALIGN);
_etext = .;
- /*
- * struct alt_inst entries. From the header (alternative.h):
- * "Alternative instructions for different CPU types or capabilities"
- * Think locking instructions on spinlocks.
- */
- . = ALIGN(4);
- .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
- __alt_instructions = .;
- *(.altinstructions)
- __alt_instructions_end = .;
- }
-
-#ifdef CONFIG_RELOCATABLE
- . = ALIGN(8);
- .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) {
- __la_abs_begin = .;
- *(.la_abs)
- __la_abs_end = .;
- }
-#endif
-
- .got : ALIGN(16) { *(.got) }
- .plt : ALIGN(16) { *(.plt) }
- .got.plt : ALIGN(16) { *(.got.plt) }
-
- .data.rel : { *(.data.rel*) }
-
. = ALIGN(PECOFF_SEGMENT_ALIGN);
__init_begin = .;
__inittext_begin = .;
@@ -94,6 +67,18 @@ SECTIONS
__initdata_begin = .;
+ /*
+ * struct alt_inst entries. From the header (alternative.h):
+ * "Alternative instructions for different CPU types or capabilities"
+ * Think locking instructions on spinlocks.
+ */
+ . = ALIGN(4);
+ .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
+ __alt_instructions = .;
+ *(.altinstructions)
+ __alt_instructions_end = .;
+ }
+
INIT_DATA_SECTION(16)
.exit.data : {
EXIT_DATA
@@ -113,6 +98,11 @@ SECTIONS
_sdata = .;
RO_DATA(4096)
+
+ .got : ALIGN(16) { *(.got) }
+ .plt : ALIGN(16) { *(.plt) }
+ .got.plt : ALIGN(16) { *(.got.plt) }
+
RW_DATA(1 << CONFIG_L1_CACHE_SHIFT, PAGE_SIZE, THREAD_SIZE)
.rela.dyn : ALIGN(8) {
@@ -121,6 +111,17 @@ SECTIONS
__rela_dyn_end = .;
}
+ .data.rel : { *(.data.rel*) }
+
+#ifdef CONFIG_RELOCATABLE
+ . = ALIGN(8);
+ .la_abs : AT(ADDR(.la_abs) - LOAD_OFFSET) {
+ __la_abs_begin = .;
+ *(.la_abs)
+ __la_abs_end = .;
+ }
+#endif
+
.sdata : {
*(.sdata)
}
diff --git a/arch/loongarch/mm/fault.c b/arch/loongarch/mm/fault.c
index e6376e3dce86..1fc2f6813ea0 100644
--- a/arch/loongarch/mm/fault.c
+++ b/arch/loongarch/mm/fault.c
@@ -20,12 +20,12 @@
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kdebug.h>
-#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/kfence.h>
#include <asm/branch.h>
+#include <asm/exception.h>
#include <asm/mmu_context.h>
#include <asm/ptrace.h>
diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
index ba138117b124..1e76fcb83093 100644
--- a/arch/loongarch/mm/hugetlbpage.c
+++ b/arch/loongarch/mm/hugetlbpage.c
@@ -50,18 +50,6 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
return (pte_t *) pmd;
}
-/*
- * This function checks for proper alignment of input addr and len parameters.
- */
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
-{
- if (len & ~HPAGE_MASK)
- return -EINVAL;
- if (addr & ~HPAGE_MASK)
- return -EINVAL;
- return 0;
-}
-
int pmd_huge(pmd_t pmd)
{
return (pmd_val(pmd) & _PAGE_HUGE) != 0;
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index f3fe8c06ba4d..4dd53427f657 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -43,11 +43,11 @@ void copy_user_highpage(struct page *to, struct page *from,
{
void *vfrom, *vto;
- vto = kmap_atomic(to);
- vfrom = kmap_atomic(from);
+ vfrom = kmap_local_page(from);
+ vto = kmap_local_page(to);
copy_page(vto, vfrom);
- kunmap_atomic(vfrom);
- kunmap_atomic(vto);
+ kunmap_local(vfrom);
+ kunmap_local(vto);
/* Make sure this page is cleared on other CPU's too before using it */
smp_wmb();
}
@@ -240,6 +240,7 @@ pgd_t swapper_pg_dir[_PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
pgd_t invalid_pg_dir[_PTRS_PER_PGD] __page_aligned_bss;
#ifndef __PAGETABLE_PUD_FOLDED
pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss;
+EXPORT_SYMBOL(invalid_pud_table);
#endif
#ifndef __PAGETABLE_PMD_FOLDED
pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
diff --git a/arch/loongarch/mm/ioremap.c b/arch/loongarch/mm/ioremap.c
index 73b0980ab6f5..70ca73019811 100644
--- a/arch/loongarch/mm/ioremap.c
+++ b/arch/loongarch/mm/ioremap.c
@@ -4,6 +4,7 @@
*/
#include <asm/io.h>
+#include <asm-generic/early_ioremap.h>
void __init __iomem *early_ioremap(u64 phys_addr, unsigned long size)
{
diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
index da68bc1a4643..cc3e81fe0186 100644
--- a/arch/loongarch/mm/kasan_init.c
+++ b/arch/loongarch/mm/kasan_init.c
@@ -35,6 +35,57 @@ static pgd_t kasan_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
bool kasan_early_stage = true;
+void *kasan_mem_to_shadow(const void *addr)
+{
+ if (!kasan_arch_is_ready()) {
+ return (void *)(kasan_early_shadow_page);
+ } else {
+ unsigned long maddr = (unsigned long)addr;
+ unsigned long xrange = (maddr >> XRANGE_SHIFT) & 0xffff;
+ unsigned long offset = 0;
+
+ maddr &= XRANGE_SHADOW_MASK;
+ switch (xrange) {
+ case XKPRANGE_CC_SEG:
+ offset = XKPRANGE_CC_SHADOW_OFFSET;
+ break;
+ case XKPRANGE_UC_SEG:
+ offset = XKPRANGE_UC_SHADOW_OFFSET;
+ break;
+ case XKVRANGE_VC_SEG:
+ offset = XKVRANGE_VC_SHADOW_OFFSET;
+ break;
+ default:
+ WARN_ON(1);
+ return NULL;
+ }
+
+ return (void *)((maddr >> KASAN_SHADOW_SCALE_SHIFT) + offset);
+ }
+}
+
+const void *kasan_shadow_to_mem(const void *shadow_addr)
+{
+ unsigned long addr = (unsigned long)shadow_addr;
+
+ if (unlikely(addr > KASAN_SHADOW_END) ||
+ unlikely(addr < KASAN_SHADOW_START)) {
+ WARN_ON(1);
+ return NULL;
+ }
+
+ if (addr >= XKVRANGE_VC_SHADOW_OFFSET)
+ return (void *)(((addr - XKVRANGE_VC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKVRANGE_VC_START);
+ else if (addr >= XKPRANGE_UC_SHADOW_OFFSET)
+ return (void *)(((addr - XKPRANGE_UC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_UC_START);
+ else if (addr >= XKPRANGE_CC_SHADOW_OFFSET)
+ return (void *)(((addr - XKPRANGE_CC_SHADOW_OFFSET) << KASAN_SHADOW_SCALE_SHIFT) + XKPRANGE_CC_START);
+ else {
+ WARN_ON(1);
+ return NULL;
+ }
+}
+
/*
* Alloc memory for shadow memory page table.
*/
diff --git a/arch/loongarch/mm/tlb.c b/arch/loongarch/mm/tlb.c
index eb8572e201ea..2c0a411f23aa 100644
--- a/arch/loongarch/mm/tlb.c
+++ b/arch/loongarch/mm/tlb.c
@@ -261,7 +261,7 @@ unsigned long pcpu_handlers[NR_CPUS];
#endif
extern long exception_handlers[VECSIZE * 128 / sizeof(long)];
-void setup_tlb_handler(int cpu)
+static void setup_tlb_handler(int cpu)
{
setup_ptwalker();
local_flush_tlb_all();
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index ca17dd3a1915..d5d682f3d29f 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -17,7 +17,7 @@
#define PTRS_PER_PTE_BITS (PAGE_SHIFT - 3)
.macro tlb_do_page_fault, write
- SYM_FUNC_START(tlb_do_page_fault_\write)
+ SYM_CODE_START(tlb_do_page_fault_\write)
SAVE_ALL
csrrd a2, LOONGARCH_CSR_BADV
move a0, sp
@@ -25,13 +25,13 @@
li.w a1, \write
bl do_page_fault
RESTORE_ALL_AND_RET
- SYM_FUNC_END(tlb_do_page_fault_\write)
+ SYM_CODE_END(tlb_do_page_fault_\write)
.endm
tlb_do_page_fault 0
tlb_do_page_fault 1
-SYM_FUNC_START(handle_tlb_protect)
+SYM_CODE_START(handle_tlb_protect)
BACKUP_T0T1
SAVE_ALL
move a0, sp
@@ -41,9 +41,9 @@ SYM_FUNC_START(handle_tlb_protect)
la_abs t0, do_page_fault
jirl ra, t0, 0
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_tlb_protect)
+SYM_CODE_END(handle_tlb_protect)
-SYM_FUNC_START(handle_tlb_load)
+SYM_CODE_START(handle_tlb_load)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -187,16 +187,16 @@ nopage_tlb_load:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_0
jr t0
-SYM_FUNC_END(handle_tlb_load)
+SYM_CODE_END(handle_tlb_load)
-SYM_FUNC_START(handle_tlb_load_ptw)
+SYM_CODE_START(handle_tlb_load_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_0
jr t0
-SYM_FUNC_END(handle_tlb_load_ptw)
+SYM_CODE_END(handle_tlb_load_ptw)
-SYM_FUNC_START(handle_tlb_store)
+SYM_CODE_START(handle_tlb_store)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -343,16 +343,16 @@ nopage_tlb_store:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_store)
+SYM_CODE_END(handle_tlb_store)
-SYM_FUNC_START(handle_tlb_store_ptw)
+SYM_CODE_START(handle_tlb_store_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_store_ptw)
+SYM_CODE_END(handle_tlb_store_ptw)
-SYM_FUNC_START(handle_tlb_modify)
+SYM_CODE_START(handle_tlb_modify)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -497,16 +497,16 @@ nopage_tlb_modify:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_modify)
+SYM_CODE_END(handle_tlb_modify)
-SYM_FUNC_START(handle_tlb_modify_ptw)
+SYM_CODE_START(handle_tlb_modify_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_modify_ptw)
+SYM_CODE_END(handle_tlb_modify_ptw)
-SYM_FUNC_START(handle_tlb_refill)
+SYM_CODE_START(handle_tlb_refill)
csrwr t0, LOONGARCH_CSR_TLBRSAVE
csrrd t0, LOONGARCH_CSR_PGD
lddir t0, t0, 3
@@ -521,4 +521,4 @@ SYM_FUNC_START(handle_tlb_refill)
tlbfill
csrrd t0, LOONGARCH_CSR_TLBRSAVE
ertn
-SYM_FUNC_END(handle_tlb_refill)
+SYM_CODE_END(handle_tlb_refill)
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 259ceb125367..f7f997a88bab 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -452,3 +452,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index a3798c2637fd..2967ec26b978 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -458,3 +458,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/mips/alchemy/devboards/db1000.c b/arch/mips/alchemy/devboards/db1000.c
index 012da042d0a4..7b9f91db227f 100644
--- a/arch/mips/alchemy/devboards/db1000.c
+++ b/arch/mips/alchemy/devboards/db1000.c
@@ -164,6 +164,7 @@ static struct platform_device db1x00_audio_dev = {
/******************************************************************************/
+#ifdef CONFIG_MMC_AU1X
static irqreturn_t db1100_mmc_cd(int irq, void *ptr)
{
mmc_detect_change(ptr, msecs_to_jiffies(500));
@@ -369,6 +370,7 @@ static struct platform_device db1100_mmc1_dev = {
.num_resources = ARRAY_SIZE(au1100_mmc1_res),
.resource = au1100_mmc1_res,
};
+#endif /* CONFIG_MMC_AU1X */
/******************************************************************************/
@@ -440,8 +442,10 @@ static struct platform_device *db1x00_devs[] = {
static struct platform_device *db1100_devs[] = {
&au1100_lcd_device,
+#ifdef CONFIG_MMC_AU1X
&db1100_mmc0_dev,
&db1100_mmc1_dev,
+#endif
};
int __init db1000_dev_setup(void)
diff --git a/arch/mips/alchemy/devboards/db1200.c b/arch/mips/alchemy/devboards/db1200.c
index 76080c71a2a7..f521874ebb07 100644
--- a/arch/mips/alchemy/devboards/db1200.c
+++ b/arch/mips/alchemy/devboards/db1200.c
@@ -326,6 +326,7 @@ static struct platform_device db1200_ide_dev = {
/**********************************************************************/
+#ifdef CONFIG_MMC_AU1X
/* SD carddetects: they're supposed to be edge-triggered, but ack
* doesn't seem to work (CPLD Rev 2). Instead, the screaming one
* is disabled and its counterpart enabled. The 200ms timeout is
@@ -584,6 +585,7 @@ static struct platform_device pb1200_mmc1_dev = {
.num_resources = ARRAY_SIZE(au1200_mmc1_res),
.resource = au1200_mmc1_res,
};
+#endif /* CONFIG_MMC_AU1X */
/**********************************************************************/
@@ -751,7 +753,9 @@ static struct platform_device db1200_audiodma_dev = {
static struct platform_device *db1200_devs[] __initdata = {
NULL, /* PSC0, selected by S6.8 */
&db1200_ide_dev,
+#ifdef CONFIG_MMC_AU1X
&db1200_mmc0_dev,
+#endif
&au1200_lcd_dev,
&db1200_eth_dev,
&db1200_nand_dev,
@@ -762,7 +766,9 @@ static struct platform_device *db1200_devs[] __initdata = {
};
static struct platform_device *pb1200_devs[] __initdata = {
+#ifdef CONFIG_MMC_AU1X
&pb1200_mmc1_dev,
+#endif
};
/* Some peripheral base addresses differ on the PB1200 */
diff --git a/arch/mips/alchemy/devboards/db1300.c b/arch/mips/alchemy/devboards/db1300.c
index ff61901329c6..d377e043b49f 100644
--- a/arch/mips/alchemy/devboards/db1300.c
+++ b/arch/mips/alchemy/devboards/db1300.c
@@ -450,6 +450,7 @@ static struct platform_device db1300_ide_dev = {
/**********************************************************************/
+#ifdef CONFIG_MMC_AU1X
static irqreturn_t db1300_mmc_cd(int irq, void *ptr)
{
disable_irq_nosync(irq);
@@ -632,6 +633,7 @@ static struct platform_device db1300_sd0_dev = {
.resource = au1300_sd0_res,
.num_resources = ARRAY_SIZE(au1300_sd0_res),
};
+#endif /* CONFIG_MMC_AU1X */
/**********************************************************************/
@@ -767,8 +769,10 @@ static struct platform_device *db1300_dev[] __initdata = {
&db1300_5waysw_dev,
&db1300_nand_dev,
&db1300_ide_dev,
+#ifdef CONFIG_MMC_AU1X
&db1300_sd0_dev,
&db1300_sd1_dev,
+#endif
&db1300_lcd_dev,
&db1300_ac97_dev,
&db1300_i2s_dev,
diff --git a/arch/mips/include/asm/local.h b/arch/mips/include/asm/local.h
index e6ae3df0349d..86fc24022242 100644
--- a/arch/mips/include/asm/local.h
+++ b/arch/mips/include/asm/local.h
@@ -108,22 +108,27 @@ static __inline__ bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read(l); \
- while (c != (u) && (old = local_cmpxchg((l), c, c + (a))) != c) \
- c = old; \
- c != (u); \
-})
+static __inline__ bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
#define local_dec_return(l) local_sub_return(1, (l))
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index 152034b8e0a0..383abb1713f4 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -391,3 +391,6 @@
450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node
451 n32 cachestat sys_cachestat
452 n32 fchmodat2 sys_fchmodat2
+454 n32 futex_wake sys_futex_wake
+455 n32 futex_wait sys_futex_wait
+456 n32 futex_requeue sys_futex_requeue
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index cb5e757f6621..c9bd09ba905f 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -367,3 +367,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 n64 cachestat sys_cachestat
452 n64 fchmodat2 sys_fchmodat2
+454 n64 futex_wake sys_futex_wake
+455 n64 futex_wait sys_futex_wait
+456 n64 futex_requeue sys_futex_requeue
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 1a646813afdc..ba5ef6cea97a 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -440,3 +440,6 @@
450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node
451 o32 cachestat sys_cachestat
452 o32 fchmodat2 sys_fchmodat2
+454 o32 futex_wake sys_futex_wake
+455 o32 futex_wait sys_futex_wait
+456 o32 futex_requeue sys_futex_requeue
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 7b2ac1319d70..467ee6b95ae1 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -592,7 +592,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
gfn_t gfn = gpa >> PAGE_SHIFT;
int srcu_idx, err;
kvm_pfn_t pfn;
- pte_t *ptep, entry, old_pte;
+ pte_t *ptep, entry;
bool writeable;
unsigned long prot_bits;
unsigned long mmu_seq;
@@ -664,7 +664,6 @@ retry:
entry = pfn_pte(pfn, __pgprot(prot_bits));
/* Write the PTE */
- old_pte = *ptep;
set_pte(ptep, entry);
err = 0;
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
index e23d06b51a20..2a60d7a72f1f 100644
--- a/arch/parisc/include/asm/cache.h
+++ b/arch/parisc/include/asm/cache.h
@@ -37,6 +37,7 @@ extern int split_tlb;
extern int dcache_stride;
extern int icache_stride;
extern struct pdc_cache_info cache_info;
+extern struct pdc_btlb_info btlb_info;
void parisc_setup_cache_timing(void);
#define pdtlb(sr, addr) asm volatile("pdtlb 0(%%sr%0,%1)" \
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index f7f078c2872c..72daacc472a0 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -6,7 +6,7 @@
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte);
+ pte_t *ptep, pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/parisc/include/asm/ldcw.h b/arch/parisc/include/asm/ldcw.h
index 6d28b5514699..ee9e071859b2 100644
--- a/arch/parisc/include/asm/ldcw.h
+++ b/arch/parisc/include/asm/ldcw.h
@@ -2,39 +2,42 @@
#ifndef __PARISC_LDCW_H
#define __PARISC_LDCW_H
-#ifndef CONFIG_PA20
/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
and GCC only guarantees 8-byte alignment for stack locals, we can't
be assured of 16-byte alignment for atomic lock data even if we
specify "__attribute ((aligned(16)))" in the type declaration. So,
we use a struct containing an array of four ints for the atomic lock
type and dynamically select the 16-byte aligned int from the array
- for the semaphore. */
+ for the semaphore. */
+
+/* From: "Jim Hull" <jim.hull of hp.com>
+ I've attached a summary of the change, but basically, for PA 2.0, as
+ long as the ",CO" (coherent operation) completer is implemented, then the
+ 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
+ they only require "natural" alignment (4-byte for ldcw, 8-byte for
+ ldcd).
+
+ Although the cache control hint is accepted by all PA 2.0 processors,
+ it is only implemented on PA8800/PA8900 CPUs. Prior PA8X00 CPUs still
+ require 16-byte alignment. If the address is unaligned, the operation
+ of the instruction is undefined. The ldcw instruction does not generate
+ unaligned data reference traps so misaligned accesses are not detected.
+ This hid the problem for years. So, restore the 16-byte alignment dropped
+ by Kyle McMartin in "Remove __ldcw_align for PA-RISC 2.0 processors". */
#define __PA_LDCW_ALIGNMENT 16
-#define __PA_LDCW_ALIGN_ORDER 4
#define __ldcw_align(a) ({ \
unsigned long __ret = (unsigned long) &(a)->lock[0]; \
__ret = (__ret + __PA_LDCW_ALIGNMENT - 1) \
& ~(__PA_LDCW_ALIGNMENT - 1); \
(volatile unsigned int *) __ret; \
})
-#define __LDCW "ldcw"
-#else /*CONFIG_PA20*/
-/* From: "Jim Hull" <jim.hull of hp.com>
- I've attached a summary of the change, but basically, for PA 2.0, as
- long as the ",CO" (coherent operation) completer is specified, then the
- 16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
- they only require "natural" alignment (4-byte for ldcw, 8-byte for
- ldcd). */
-
-#define __PA_LDCW_ALIGNMENT 4
-#define __PA_LDCW_ALIGN_ORDER 2
-#define __ldcw_align(a) (&(a)->slock)
+#ifdef CONFIG_PA20
#define __LDCW "ldcw,co"
-
-#endif /*!CONFIG_PA20*/
+#else
+#define __LDCW "ldcw"
+#endif
/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.
We don't explicitly expose that "*a" may be written as reload
diff --git a/arch/parisc/include/asm/mckinley.h b/arch/parisc/include/asm/mckinley.h
deleted file mode 100644
index 1314390b9034..000000000000
--- a/arch/parisc/include/asm/mckinley.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef ASM_PARISC_MCKINLEY_H
-#define ASM_PARISC_MCKINLEY_H
-
-/* declared in arch/parisc/kernel/setup.c */
-extern struct proc_dir_entry * proc_mckinley_root;
-
-#endif /*ASM_PARISC_MCKINLEY_H*/
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index 269b9a159f01..5d2d9737e579 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -44,10 +44,11 @@ int pdc_model_capabilities(unsigned long *capabilities);
int pdc_model_platform_info(char *orig_prod_num, char *current_prod_num, char *serial_no);
int pdc_cache_info(struct pdc_cache_info *cache);
int pdc_spaceid_bits(unsigned long *space_bits);
-#ifndef CONFIG_PA20
int pdc_btlb_info(struct pdc_btlb_info *btlb);
+int pdc_btlb_insert(unsigned long long vpage, unsigned long physpage, unsigned long len,
+ unsigned long entry_info, unsigned long slot);
+int pdc_btlb_purge_all(void);
int pdc_mem_map_hpa(struct pdc_memory_map *r_addr, struct pdc_module_path *mod_path);
-#endif /* !CONFIG_PA20 */
int pdc_pim_toc11(struct pdc_toc_pim_11 *ret);
int pdc_pim_toc20(struct pdc_toc_pim_20 *ret);
int pdc_lan_station_id(char *lan_addr, unsigned long net_hpa);
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index d77c43d32974..ff6cbdb6903b 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -310,6 +310,7 @@ extern void do_syscall_trace_exit(struct pt_regs *);
struct seq_file;
extern void early_trap_init(void);
extern void collect_boot_cpu_data(void);
+extern void btlb_init_per_cpu(void);
extern int show_cpuinfo (struct seq_file *m, void *v);
/* driver code in driver/parisc */
diff --git a/arch/parisc/include/asm/ropes.h b/arch/parisc/include/asm/ropes.h
index fd96706c7234..e2d2d7e9bfde 100644
--- a/arch/parisc/include/asm/ropes.h
+++ b/arch/parisc/include/asm/ropes.h
@@ -29,7 +29,7 @@
struct ioc {
void __iomem *ioc_hpa; /* I/O MMU base address */
char *res_map; /* resource map, bit == pdir entry */
- u64 *pdir_base; /* physical base address */
+ __le64 *pdir_base; /* physical base address */
unsigned long ibase; /* pdir IOV Space base - shared w/lba_pci */
unsigned long imask; /* pdir IOV Space mask - shared w/lba_pci */
#ifdef ZX1_SUPPORT
@@ -86,6 +86,9 @@ struct sba_device {
struct ioc ioc[MAX_IOC];
};
+/* list of SBA's in system, see drivers/parisc/sba_iommu.c */
+extern struct sba_device *sba_list;
+
#define ASTRO_RUNWAY_PORT 0x582
#define IKE_MERCED_PORT 0x803
#define REO_MERCED_PORT 0x804
@@ -110,7 +113,7 @@ static inline int IS_PLUTO(struct parisc_device *d) {
#define SBA_PDIR_VALID_BIT 0x8000000000000000ULL
-#define SBA_AGPGART_COOKIE 0x0000badbadc0ffeeULL
+#define SBA_AGPGART_COOKIE (__force __le64) 0x0000badbadc0ffeeULL
#define SBA_FUNC_ID 0x0000 /* function id */
#define SBA_FCLASS 0x0008 /* function class, bist, header, rev... */
diff --git a/arch/parisc/include/asm/shmparam.h b/arch/parisc/include/asm/shmparam.h
index 74f74e4d35b7..5a95b0f62b87 100644
--- a/arch/parisc/include/asm/shmparam.h
+++ b/arch/parisc/include/asm/shmparam.h
@@ -2,6 +2,21 @@
#ifndef _ASMPARISC_SHMPARAM_H
#define _ASMPARISC_SHMPARAM_H
+/*
+ * PA-RISC uses virtually indexed & physically tagged (VIPT) caches
+ * which has strict requirements when two pages to the same physical
+ * address are accessed through different mappings. Read the section
+ * "Address Aliasing" in the arch docs for more detail:
+ * PA-RISC 1.1 (page 3-6):
+ * https://parisc.wiki.kernel.org/images-parisc/6/68/Pa11_acd.pdf
+ * PA-RISC 2.0 (page F-5):
+ * https://parisc.wiki.kernel.org/images-parisc/7/73/Parisc2.0.pdf
+ *
+ * For Linux we allow kernel and userspace to map pages on page size
+ * granularity (SHMLBA) but have to ensure that, if two pages are
+ * mapped to the same physical address, the virtual and physical
+ * addresses modulo SHM_COLOUR are identical.
+ */
#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */
#define SHM_COLOUR 0x00400000 /* shared mappings colouring */
diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h
index efd06a897c6a..7b986b09dba8 100644
--- a/arch/parisc/include/asm/spinlock_types.h
+++ b/arch/parisc/include/asm/spinlock_types.h
@@ -9,15 +9,10 @@
#ifndef __ASSEMBLY__
typedef struct {
-#ifdef CONFIG_PA20
- volatile unsigned int slock;
-# define __ARCH_SPIN_LOCK_UNLOCKED { __ARCH_SPIN_LOCK_UNLOCKED_VAL }
-#else
volatile unsigned int lock[4];
# define __ARCH_SPIN_LOCK_UNLOCKED \
{ { __ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL, \
__ARCH_SPIN_LOCK_UNLOCKED_VAL, __ARCH_SPIN_LOCK_UNLOCKED_VAL } }
-#endif
} arch_spinlock_t;
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 94652e13c260..757816a7bd4b 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -275,6 +275,8 @@ int main(void)
* and kernel data on physical huge pages */
#ifdef CONFIG_HUGETLB_PAGE
DEFINE(HUGEPAGE_SIZE, 1UL << REAL_HPAGE_SHIFT);
+#elif !defined(CONFIG_64BIT)
+ DEFINE(HUGEPAGE_SIZE, 4*1024*1024);
#else
DEFINE(HUGEPAGE_SIZE, PAGE_SIZE);
#endif
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index 442109a48940..268d90a9325b 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -58,7 +58,7 @@ int pa_serialize_tlb_flushes __ro_after_init;
struct pdc_cache_info cache_info __ro_after_init;
#ifndef CONFIG_PA20
-static struct pdc_btlb_info btlb_info __ro_after_init;
+struct pdc_btlb_info btlb_info __ro_after_init;
#endif
DEFINE_STATIC_KEY_TRUE(parisc_has_cache);
@@ -264,12 +264,6 @@ parisc_cache_init(void)
icache_stride = CAFL_STRIDE(cache_info.ic_conf);
#undef CAFL_STRIDE
-#ifndef CONFIG_PA20
- if (pdc_btlb_info(&btlb_info) < 0) {
- memset(&btlb_info, 0, sizeof btlb_info);
- }
-#endif
-
if ((boot_cpu_data.pdc.capabilities & PDC_MODEL_NVA_MASK) ==
PDC_MODEL_NVA_UNSUPPORTED) {
printk(KERN_WARNING "parisc_cache_init: Only equivalent aliasing supported!\n");
diff --git a/arch/parisc/kernel/drivers.c b/arch/parisc/kernel/drivers.c
index 8f4b77648491..ed8b75948061 100644
--- a/arch/parisc/kernel/drivers.c
+++ b/arch/parisc/kernel/drivers.c
@@ -925,9 +925,9 @@ static __init void qemu_header(void)
pr_info("#define PARISC_MODEL \"%s\"\n\n",
boot_cpu_data.pdc.sys_model_name);
+ #define p ((unsigned long *)&boot_cpu_data.pdc.model)
pr_info("#define PARISC_PDC_MODEL 0x%lx, 0x%lx, 0x%lx, "
"0x%lx, 0x%lx, 0x%lx, 0x%lx, 0x%lx, 0x%lx\n\n",
- #define p ((unsigned long *)&boot_cpu_data.pdc.model)
p[0], p[1], p[2], p[3], p[4], p[5], p[6], p[7], p[8]);
#undef p
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 8f37e75f2fb9..81078abec521 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -687,7 +687,6 @@ int pdc_spaceid_bits(unsigned long *space_bits)
return retval;
}
-#ifndef CONFIG_PA20
/**
* pdc_btlb_info - Return block TLB information.
* @btlb: The return buffer.
@@ -696,18 +695,51 @@ int pdc_spaceid_bits(unsigned long *space_bits)
*/
int pdc_btlb_info(struct pdc_btlb_info *btlb)
{
- int retval;
+ int retval;
unsigned long flags;
- spin_lock_irqsave(&pdc_lock, flags);
- retval = mem_pdc_call(PDC_BLOCK_TLB, PDC_BTLB_INFO, __pa(pdc_result), 0);
- memcpy(btlb, pdc_result, sizeof(*btlb));
- spin_unlock_irqrestore(&pdc_lock, flags);
+ if (IS_ENABLED(CONFIG_PA20))
+ return PDC_BAD_PROC;
- if(retval < 0) {
- btlb->max_size = 0;
- }
- return retval;
+ spin_lock_irqsave(&pdc_lock, flags);
+ retval = mem_pdc_call(PDC_BLOCK_TLB, PDC_BTLB_INFO, __pa(pdc_result), 0);
+ memcpy(btlb, pdc_result, sizeof(*btlb));
+ spin_unlock_irqrestore(&pdc_lock, flags);
+
+ if(retval < 0) {
+ btlb->max_size = 0;
+ }
+ return retval;
+}
+
+int pdc_btlb_insert(unsigned long long vpage, unsigned long physpage, unsigned long len,
+ unsigned long entry_info, unsigned long slot)
+{
+ int retval;
+ unsigned long flags;
+
+ if (IS_ENABLED(CONFIG_PA20))
+ return PDC_BAD_PROC;
+
+ spin_lock_irqsave(&pdc_lock, flags);
+ retval = mem_pdc_call(PDC_BLOCK_TLB, PDC_BTLB_INSERT, (unsigned long) (vpage >> 32),
+ (unsigned long) vpage, physpage, len, entry_info, slot);
+ spin_unlock_irqrestore(&pdc_lock, flags);
+ return retval;
+}
+
+int pdc_btlb_purge_all(void)
+{
+ int retval;
+ unsigned long flags;
+
+ if (IS_ENABLED(CONFIG_PA20))
+ return PDC_BAD_PROC;
+
+ spin_lock_irqsave(&pdc_lock, flags);
+ retval = mem_pdc_call(PDC_BLOCK_TLB, PDC_BTLB_PURGE_ALL);
+ spin_unlock_irqrestore(&pdc_lock, flags);
+ return retval;
}
/**
@@ -728,6 +760,9 @@ int pdc_mem_map_hpa(struct pdc_memory_map *address,
int retval;
unsigned long flags;
+ if (IS_ENABLED(CONFIG_PA20))
+ return PDC_BAD_PROC;
+
spin_lock_irqsave(&pdc_lock, flags);
memcpy(pdc_result2, mod_path, sizeof(*mod_path));
retval = mem_pdc_call(PDC_MEM_MAP, PDC_MEM_MAP_HPA, __pa(pdc_result),
@@ -737,7 +772,6 @@ int pdc_mem_map_hpa(struct pdc_memory_map *address,
return retval;
}
-#endif /* !CONFIG_PA20 */
/**
* pdc_lan_station_id - Get the LAN address.
diff --git a/arch/parisc/kernel/head.S b/arch/parisc/kernel/head.S
index fd15fd4bbb61..a171bf3c6b31 100644
--- a/arch/parisc/kernel/head.S
+++ b/arch/parisc/kernel/head.S
@@ -180,10 +180,10 @@ $pgt_fill_loop:
std %dp,0x18(%r10)
#endif
-#ifdef CONFIG_64BIT
- /* Get PDCE_PROC for monarch CPU. */
#define MEM_PDC_LO 0x388
#define MEM_PDC_HI 0x35C
+#ifdef CONFIG_64BIT
+ /* Get PDCE_PROC for monarch CPU. */
ldw MEM_PDC_LO(%r0),%r3
ldw MEM_PDC_HI(%r0),%r10
depd %r10, 31, 32, %r3 /* move to upper word */
@@ -269,7 +269,17 @@ stext_pdc_ret:
tovirt_r1 %r6
mtctl %r6,%cr30 /* restore task thread info */
#endif
-
+
+#ifndef CONFIG_64BIT
+ /* clear all BTLBs */
+ ldi PDC_BLOCK_TLB,%arg0
+ load32 PA(stext_pdc_btlb_ret), %rp
+ ldw MEM_PDC_LO(%r0),%r3
+ bv (%r3)
+ ldi PDC_BTLB_PURGE_ALL,%arg1
+stext_pdc_btlb_ret:
+#endif
+
/* PARANOID: clear user scratch/user space SR's */
mtsp %r0,%sr0
mtsp %r0,%sr1
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 12c4d4104ade..2f81bfd4f15e 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -365,7 +365,7 @@ union irq_stack_union {
volatile unsigned int lock[1];
};
-DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = {
+static DEFINE_PER_CPU(union irq_stack_union, irq_stack_union) = {
.slock = { 1,1,1,1 },
};
#endif
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index a0e2d37c5b3b..1fc89fa2c2d2 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -368,6 +368,8 @@ int init_per_cpu(int cpunum)
/* FUTURE: Enable Performance Monitor : ccr bit 0x20 */
init_percpu_prof(cpunum);
+ btlb_init_per_cpu();
+
return ret;
}
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 4098f9a0964b..2019c1f04bd0 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -440,7 +440,9 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
if (cpu_online(cpu))
return 0;
- if (num_online_cpus() < setup_max_cpus && smp_boot_one_cpu(cpu, tidle))
+ if (num_online_cpus() < nr_cpu_ids &&
+ num_online_cpus() < setup_max_cpus &&
+ smp_boot_one_cpu(cpu, tidle))
return -EIO;
return cpu_online(cpu) ? 0 : -EIO;
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index e97c175b56f9..9f0f6df55361 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -451,3 +451,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 1aaa2ca09800..58694d1989c2 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -154,6 +154,7 @@ SECTIONS
}
/* End of data section */
+ . = ALIGN(PAGE_SIZE);
_edata = .;
/* BSS */
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index a8a1a7c1e16e..a9f7e21f6656 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -140,7 +140,7 @@ static void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
}
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t entry)
+ pte_t *ptep, pte_t entry, unsigned long sz)
{
__set_huge_pte_at(mm, addr, ptep, entry);
}
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index a088c243edea..a2a3e89f2d9a 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -32,6 +32,7 @@
#include <asm/sections.h>
#include <asm/msgbuf.h>
#include <asm/sparsemem.h>
+#include <asm/asm-offsets.h>
extern int data_start;
extern void parisc_kernel_start(void); /* Kernel entry point in head.S */
@@ -720,6 +721,77 @@ void __init paging_init(void)
parisc_bootmem_free();
}
+static void alloc_btlb(unsigned long start, unsigned long end, int *slot,
+ unsigned long entry_info)
+{
+ const int slot_max = btlb_info.fixed_range_info.num_comb;
+ int min_num_pages = btlb_info.min_size;
+ unsigned long size;
+
+ /* map at minimum 4 pages */
+ if (min_num_pages < 4)
+ min_num_pages = 4;
+
+ size = HUGEPAGE_SIZE;
+ while (start < end && *slot < slot_max && size >= PAGE_SIZE) {
+ /* starting address must have same alignment as size! */
+ /* if correctly aligned and fits in double size, increase */
+ if (((start & (2 * size - 1)) == 0) &&
+ (end - start) >= (2 * size)) {
+ size <<= 1;
+ continue;
+ }
+ /* if current size alignment is too big, try smaller size */
+ if ((start & (size - 1)) != 0) {
+ size >>= 1;
+ continue;
+ }
+ if ((end - start) >= size) {
+ if ((size >> PAGE_SHIFT) >= min_num_pages)
+ pdc_btlb_insert(start >> PAGE_SHIFT, __pa(start) >> PAGE_SHIFT,
+ size >> PAGE_SHIFT, entry_info, *slot);
+ (*slot)++;
+ start += size;
+ continue;
+ }
+ size /= 2;
+ continue;
+ }
+}
+
+void btlb_init_per_cpu(void)
+{
+ unsigned long s, t, e;
+ int slot;
+
+ /* BTLBs are not available on 64-bit CPUs */
+ if (IS_ENABLED(CONFIG_PA20))
+ return;
+ else if (pdc_btlb_info(&btlb_info) < 0) {
+ memset(&btlb_info, 0, sizeof btlb_info);
+ }
+
+ /* insert BLTLBs for code and data segments */
+ s = (uintptr_t) dereference_function_descriptor(&_stext);
+ e = (uintptr_t) dereference_function_descriptor(&_etext);
+ t = (uintptr_t) dereference_function_descriptor(&_sdata);
+ BUG_ON(t != e);
+
+ /* code segments */
+ slot = 0;
+ alloc_btlb(s, e, &slot, 0x13800000);
+
+ /* sanity check */
+ t = (uintptr_t) dereference_function_descriptor(&_edata);
+ e = (uintptr_t) dereference_function_descriptor(&__bss_start);
+ BUG_ON(t != e);
+
+ /* data segments */
+ s = (uintptr_t) dereference_function_descriptor(&_sdata);
+ e = (uintptr_t) dereference_function_descriptor(&__bss_stop);
+ alloc_btlb(s, e, &slot, 0x11800000);
+}
+
#ifdef CONFIG_PA20
/*
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 54b9387c3691..d5d5388973ac 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -255,7 +255,7 @@ config PPC
select HAVE_KPROBES
select HAVE_KPROBES_ON_FTRACE
select HAVE_KRETPROBES
- select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT
+ select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if HAVE_OBJTOOL_MCOUNT && (!ARCH_USING_PATCHABLE_FUNCTION_ENTRY || (!CC_IS_GCC || GCC_VERSION >= 110100))
select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
select HAVE_MOD_ARCH_SPECIFIC
select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
@@ -910,7 +910,7 @@ config ARCH_FORCE_MAX_ORDER
default "6" if PPC32 && PPC_64K_PAGES
range 4 10 if PPC32 && PPC_256K_PAGES
default "4" if PPC32 && PPC_256K_PAGES
- range 10 10
+ range 10 12
default "10"
help
The kernel page allocator limits the size of maximal physically
diff --git a/arch/powerpc/configs/hardening.config b/arch/powerpc/configs/hardening.config
new file mode 100644
index 000000000000..4e9bba327e8f
--- /dev/null
+++ b/arch/powerpc/configs/hardening.config
@@ -0,0 +1,10 @@
+# PowerPC specific hardening options
+
+# Block kernel from unexpectedly reading userspace memory.
+CONFIG_PPC_KUAP=y
+
+# Attack surface reduction.
+# CONFIG_SCOM_DEBUGFS is not set
+
+# Disable internal kernel debugger.
+# CONFIG_XMON is not set
diff --git a/arch/powerpc/include/asm/local.h b/arch/powerpc/include/asm/local.h
index 45492fb5bf22..ec6ced6d7ced 100644
--- a/arch/powerpc/include/asm/local.h
+++ b/arch/powerpc/include/asm/local.h
@@ -115,23 +115,23 @@ static __inline__ long local_xchg(local_t *l, long n)
}
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to v...
* @u: ...unless v is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-static __inline__ int local_add_unless(local_t *l, long a, long u)
+static __inline__ bool local_add_unless(local_t *l, long a, long u)
{
unsigned long flags;
- int ret = 0;
+ bool ret = false;
powerpc_local_irq_pmu_save(flags);
if (l->v != u) {
l->v += a;
- ret = 1;
+ ret = true;
}
powerpc_local_irq_pmu_restore(flags);
diff --git a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
index de092b04ee1a..92df40c6cc6b 100644
--- a/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/hugetlb-8xx.h
@@ -46,7 +46,8 @@ static inline int check_and_get_huge_psize(int shift)
}
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte);
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz);
#define __HAVE_ARCH_HUGE_PTE_CLEAR
static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
index 21f681ee535a..e6fe1d5731f2 100644
--- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h
@@ -94,6 +94,13 @@ static inline pte_t pte_wrprotect(pte_t pte)
#define pte_wrprotect pte_wrprotect
+static inline int pte_read(pte_t pte)
+{
+ return (pte_val(pte) & _PAGE_RO) != _PAGE_NA;
+}
+
+#define pte_read pte_read
+
static inline int pte_write(pte_t pte)
{
return !(pte_val(pte) & _PAGE_RO);
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 5cd9acf58a7d..eb6891e34cbd 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -197,7 +197,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
{
unsigned long old;
- if (pte_young(*ptep))
+ if (!pte_young(*ptep))
return 0;
old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
return (old & _PAGE_ACCESSED) != 0;
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 56ea48276356..c721478c5934 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -25,7 +25,9 @@ static inline int pte_write(pte_t pte)
return pte_val(pte) & _PAGE_RW;
}
#endif
+#ifndef pte_read
static inline int pte_read(pte_t pte) { return 1; }
+#endif
static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; }
static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 9692acb0361f..7eda33a24bb4 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -137,8 +137,9 @@ ret_from_syscall:
lis r4,icache_44x_need_flush@ha
lwz r5,icache_44x_need_flush@l(r4)
cmplwi cr0,r5,0
- bne- 2f
+ bne- .L44x_icache_flush
#endif /* CONFIG_PPC_47x */
+.L44x_icache_flush_return:
kuep_unlock
lwz r4,_LINK(r1)
lwz r5,_CCR(r1)
@@ -172,10 +173,11 @@ syscall_exit_finish:
b 1b
#ifdef CONFIG_44x
-2: li r7,0
+.L44x_icache_flush:
+ li r7,0
iccci r0,r0
stw r7,icache_44x_need_flush@l(r4)
- b 1b
+ b .L44x_icache_flush_return
#endif /* CONFIG_44x */
.globl ret_from_fork
diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S
index 97e9ea0c7297..0f1641a31250 100644
--- a/arch/powerpc/kernel/head_85xx.S
+++ b/arch/powerpc/kernel/head_85xx.S
@@ -395,7 +395,7 @@ interrupt_base:
#ifdef CONFIG_PPC_FPU
FP_UNAVAILABLE_EXCEPTION
#else
- EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, unknown_exception)
+ EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt)
#endif
/* System Call Interrupt */
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index b8513dc3e53a..a1318ce18d0e 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -230,13 +230,15 @@ void thread_change_pc(struct task_struct *tsk, struct pt_regs *regs)
struct arch_hw_breakpoint *info;
int i;
+ preempt_disable();
+
for (i = 0; i < nr_wp_slots(); i++) {
struct perf_event *bp = __this_cpu_read(bp_per_reg[i]);
if (unlikely(bp && counter_arch_bp(bp)->perf_single_step))
goto reset;
}
- return;
+ goto out;
reset:
regs_set_return_msr(regs, regs->msr & ~MSR_SE);
@@ -245,6 +247,9 @@ reset:
__set_breakpoint(i, info);
info->perf_single_step = false;
}
+
+out:
+ preempt_enable();
}
static bool is_larx_stcx_instr(int type)
@@ -363,6 +368,11 @@ static void handle_p10dd1_spurious_exception(struct perf_event **bp,
}
}
+/*
+ * Handle a DABR or DAWR exception.
+ *
+ * Called in atomic context.
+ */
int hw_breakpoint_handler(struct die_args *args)
{
bool err = false;
@@ -490,6 +500,8 @@ NOKPROBE_SYMBOL(hw_breakpoint_handler);
/*
* Handle single-step exceptions following a DABR hit.
+ *
+ * Called in atomic context.
*/
static int single_step_dabr_instruction(struct die_args *args)
{
@@ -541,6 +553,8 @@ NOKPROBE_SYMBOL(single_step_dabr_instruction);
/*
* Handle debug exception notifications.
+ *
+ * Called in atomic context.
*/
int hw_breakpoint_exceptions_notify(
struct notifier_block *unused, unsigned long val, void *data)
diff --git a/arch/powerpc/kernel/hw_breakpoint_constraints.c b/arch/powerpc/kernel/hw_breakpoint_constraints.c
index a74623025f3a..9e51801c4915 100644
--- a/arch/powerpc/kernel/hw_breakpoint_constraints.c
+++ b/arch/powerpc/kernel/hw_breakpoint_constraints.c
@@ -131,8 +131,13 @@ void wp_get_instr_detail(struct pt_regs *regs, ppc_inst_t *instr,
int *type, int *size, unsigned long *ea)
{
struct instruction_op op;
+ int err;
- if (__get_user_instr(*instr, (void __user *)regs->nip))
+ pagefault_disable();
+ err = __get_user_instr(*instr, (void __user *)regs->nip);
+ pagefault_enable();
+
+ if (err)
return;
analyse_instr(&op, regs, *instr);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 2f1026fba00d..20f72cd1d813 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -948,6 +948,8 @@ void __init setup_arch(char **cmdline_p)
/* Parse memory topology */
mem_topology_setup();
+ /* Set max_mapnr before paging_init() */
+ set_max_mapnr(max_pfn);
/*
* Release secondary cpus out of their spinloops at 0x60 now that
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5826f5108a12..ab691c89d787 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1051,7 +1051,7 @@ static struct sched_domain_topology_level powerpc_topology[] = {
#endif
{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
{ cpu_mc_mask, SD_INIT_NAME(MC) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { cpu_cpu_mask, SD_INIT_NAME(PKG) },
{ NULL, },
};
@@ -1595,7 +1595,7 @@ static void add_cpu_to_masks(int cpu)
/* Skip all CPUs already part of current CPU core mask */
cpumask_andnot(mask, cpu_online_mask, cpu_core_mask(cpu));
- /* If chip_id is -1; limit the cpu_core_mask to within DIE*/
+ /* If chip_id is -1; limit the cpu_core_mask to within PKG */
if (chip_id == -1)
cpumask_and(mask, mask, cpu_cpu_mask(cpu));
@@ -1629,7 +1629,7 @@ void start_secondary(void *unused)
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
cpu_callin_map[cpu] = 1;
if (smp_ops->setup_cpu)
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index b15f15dcacb5..e6a958a5da27 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -73,29 +73,12 @@ int __no_sanitize_address arch_stack_walk_reliable(stack_trace_consume_fn consum
bool firstframe;
stack_end = stack_page + THREAD_SIZE;
- if (!is_idle_task(task)) {
- /*
- * For user tasks, this is the SP value loaded on
- * kernel entry, see "PACAKSAVE(r13)" in _switch() and
- * system_call_common().
- *
- * Likewise for non-swapper kernel threads,
- * this also happens to be the top of the stack
- * as setup by copy_thread().
- *
- * Note that stack backlinks are not properly setup by
- * copy_thread() and thus, a forked task() will have
- * an unreliable stack trace until it's been
- * _switch()'ed to for the first time.
- */
- stack_end -= STACK_USER_INT_FRAME_SIZE;
- } else {
- /*
- * idle tasks have a custom stack layout,
- * c.f. cpu_idle_thread_init().
- */
+
+ // See copy_thread() for details.
+ if (task->flags & PF_KTHREAD)
stack_end -= STACK_FRAME_MIN_SIZE;
- }
+ else
+ stack_end -= STACK_USER_INT_FRAME_SIZE;
if (task == current)
sp = current_stack_frame();
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 20e50586e8a2..26fc41904266 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -539,3 +539,6 @@
450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index eeff136b83d9..64ff37721fd0 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1512,23 +1512,11 @@ static void do_program_check(struct pt_regs *regs)
return;
}
- if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE) && user_mode(regs)) {
- ppc_inst_t insn;
-
- if (get_user_instr(insn, (void __user *)regs->nip)) {
- _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
- return;
- }
-
- if (ppc_inst_primary_opcode(insn) == 31 &&
- get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
- _exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
- return;
- }
+ /* User mode considers other cases after enabling IRQs */
+ if (!user_mode(regs)) {
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
}
-
- _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
- return;
}
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
if (reason & REASON_TM) {
@@ -1561,16 +1549,44 @@ static void do_program_check(struct pt_regs *regs)
/*
* If we took the program check in the kernel skip down to sending a
- * SIGILL. The subsequent cases all relate to emulating instructions
- * which we should only do for userspace. We also do not want to enable
- * interrupts for kernel faults because that might lead to further
- * faults, and loose the context of the original exception.
+ * SIGILL. The subsequent cases all relate to user space, such as
+ * emulating instructions which we should only do for user space. We
+ * also do not want to enable interrupts for kernel faults because that
+ * might lead to further faults, and loose the context of the original
+ * exception.
*/
if (!user_mode(regs))
goto sigill;
interrupt_cond_local_irq_enable(regs);
+ /*
+ * (reason & REASON_TRAP) is mostly handled before enabling IRQs,
+ * except get_user_instr() can sleep so we cannot reliably inspect the
+ * current instruction in that context. Now that we know we are
+ * handling a user space trap and can sleep, we can check if the trap
+ * was a hashchk failure.
+ */
+ if (reason & REASON_TRAP) {
+ if (cpu_has_feature(CPU_FTR_DEXCR_NPHIE)) {
+ ppc_inst_t insn;
+
+ if (get_user_instr(insn, (void __user *)regs->nip)) {
+ _exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
+ return;
+ }
+
+ if (ppc_inst_primary_opcode(insn) == 31 &&
+ get_xop(ppc_inst_val(insn)) == OP_31_XOP_HASHCHK) {
+ _exception(SIGILL, regs, ILL_ILLOPN, regs->nip);
+ return;
+ }
+ }
+
+ _exception(SIGTRAP, regs, TRAP_BRKPT, regs->nip);
+ return;
+ }
+
/* (reason & REASON_ILLEGAL) would be the obvious thing here,
* but there seems to be a hardware bug on the 405GP (RevD)
* that means ESR is sometimes set incorrectly - either to
diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 253620979d0c..6dd2f46bd3ef 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -406,6 +406,9 @@ static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode *
if ((yield_count & 1) == 0)
goto yield_prev; /* owner vcpu is running */
+ if (get_owner_cpu(READ_ONCE(lock->val)) != yield_cpu)
+ goto yield_prev; /* re-sample lock owner */
+
spin_end();
preempted = true;
diff --git a/arch/powerpc/mm/book3s64/hugetlbpage.c b/arch/powerpc/mm/book3s64/hugetlbpage.c
index 3bc0eb21b2a0..5a2e512e96db 100644
--- a/arch/powerpc/mm/book3s64/hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/hugetlbpage.c
@@ -143,11 +143,14 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep, pte_t old_pte, pte_t pte)
{
+ unsigned long psize;
if (radix_enabled())
return radix__huge_ptep_modify_prot_commit(vma, addr, ptep,
old_pte, pte);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+
+ psize = huge_page_size(hstate_vma(vma));
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
void __init hugetlbpage_init_defaultsize(void)
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 17075c78d4bc..35fd2a95be24 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -47,6 +47,7 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
pte_t old_pte, pte_t pte)
{
struct mm_struct *mm = vma->vm_mm;
+ unsigned long psize = huge_page_size(hstate_vma(vma));
/*
* POWER9 NMMU must flush the TLB after clearing the PTE before
@@ -58,5 +59,5 @@ void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
atomic_read(&mm->context.copros) > 0)
radix__flush_hugetlb_page(vma, addr);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
}
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 39acc2cbab4c..9e1f6558d026 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -1212,14 +1212,7 @@ void radix__tlb_flush(struct mmu_gather *tlb)
smp_mb(); /* see radix__flush_tlb_mm */
exit_flush_lazy_tlbs(mm);
- _tlbiel_pid(mm->context.id, RIC_FLUSH_ALL);
-
- /*
- * It should not be possible to have coprocessors still
- * attached here.
- */
- if (WARN_ON_ONCE(atomic_read(&mm->context.copros) > 0))
- __flush_all_mm(mm, true);
+ __flush_all_mm(mm, true);
preempt_enable();
} else {
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 8b121df7b08f..07e8f4f1e07f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -288,7 +288,6 @@ void __init mem_init(void)
#endif
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
- set_max_mapnr(max_pfn);
kasan_late_init();
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index dbbfe897455d..a642a7929892 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -91,7 +91,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
if (new && WARN_ON(pte_present(*ptep) && pgprot_val(prot)))
return -EINVAL;
- set_huge_pte_at(&init_mm, va, ptep, pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)));
+ set_huge_pte_at(&init_mm, va, ptep,
+ pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
return 0;
}
diff --git a/arch/powerpc/mm/pgtable.c b/arch/powerpc/mm/pgtable.c
index 3f86fd217690..4d69bfb9bc11 100644
--- a/arch/powerpc/mm/pgtable.c
+++ b/arch/powerpc/mm/pgtable.c
@@ -104,6 +104,8 @@ static pte_t set_pte_filter_hash(pte_t pte) { return pte; }
/* Embedded type MMU with HW exec support. This is a bit more complicated
* as we don't have two bits to spare for _PAGE_EXEC and _PAGE_HWEXEC so
* instead we "filter out" the exec permission for non clean pages.
+ *
+ * This is also called once for the folio. So only work with folio->flags here.
*/
static inline pte_t set_pte_filter(pte_t pte)
{
@@ -190,29 +192,39 @@ static pte_t set_access_flags_filter(pte_t pte, struct vm_area_struct *vma,
void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
pte_t pte, unsigned int nr)
{
- /*
- * Make sure hardware valid bit is not set. We don't do
- * tlb flush for this update.
- */
- VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
/* Note: mm->context.id might not yet have been assigned as
* this context might not have been activated yet when this
- * is called.
+ * is called. Filter the pte value and use the filtered value
+ * to setup all the ptes in the range.
*/
pte = set_pte_filter(pte);
- /* Perform the setting of the PTE */
- arch_enter_lazy_mmu_mode();
+ /*
+ * We don't need to call arch_enter/leave_lazy_mmu_mode()
+ * because we expect set_ptes to be only be used on not present
+ * and not hw_valid ptes. Hence there is no translation cache flush
+ * involved that need to be batched.
+ */
for (;;) {
+
+ /*
+ * Make sure hardware valid bit is not set. We don't do
+ * tlb flush for this update.
+ */
+ VM_WARN_ON(pte_hw_valid(*ptep) && !pte_protnone(*ptep));
+
+ /* Perform the setting of the PTE */
__set_pte_at(mm, addr, ptep, pte, 0);
if (--nr == 0)
break;
ptep++;
- pte = __pte(pte_val(pte) + (1UL << PTE_RPN_SHIFT));
addr += PAGE_SIZE;
+ /*
+ * increment the pfn.
+ */
+ pte = pfn_pte(pte_pfn(pte) + 1, pte_pgprot((pte)));
}
- arch_leave_lazy_mmu_mode();
}
void unmap_kernel_page(unsigned long va)
@@ -288,7 +300,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
}
#if defined(CONFIG_PPC_8xx)
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
+ pte_t pte, unsigned long sz)
{
pmd_t *pmd = pmd_off(mm, addr);
pte_basic_t val;
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 317175791d23..3449be7c0d51 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -1418,7 +1418,7 @@ static int h_24x7_event_init(struct perf_event *event)
}
domain = event_get_domain(event);
- if (domain >= HV_PERF_DOMAIN_MAX) {
+ if (domain == 0 || domain >= HV_PERF_DOMAIN_MAX) {
pr_devel("invalid domain %d\n", domain);
return -EINVAL;
}
diff --git a/arch/powerpc/platforms/82xx/Kconfig b/arch/powerpc/platforms/82xx/Kconfig
index d9f1a2a83158..1824536cf6f2 100644
--- a/arch/powerpc/platforms/82xx/Kconfig
+++ b/arch/powerpc/platforms/82xx/Kconfig
@@ -2,6 +2,7 @@
menuconfig PPC_82xx
bool "82xx-based boards (PQ II)"
depends on PPC_BOOK3S_32
+ select FSL_SOC
if PPC_82xx
@@ -9,7 +10,6 @@ config EP8248E
bool "Embedded Planet EP8248E (a.k.a. CWH-PPC-8248N-VE)"
select CPM2
select PPC_INDIRECT_PCI if PCI
- select FSL_SOC
select PHYLIB if NETDEVICES
select MDIO_BITBANG if PHYLIB
help
@@ -22,7 +22,6 @@ config MGCOGE
bool "Keymile MGCOGE"
select CPM2
select PPC_INDIRECT_PCI if PCI
- select FSL_SOC
help
This enables support for the Keymile MGCOGE board.
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index 1a587618015c..18daafbe2e65 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -66,7 +66,7 @@ static int match_context(const void *v, struct file *file, unsigned fd)
*/
static struct spu_context *coredump_next_context(int *fd)
{
- struct spu_context *ctx;
+ struct spu_context *ctx = NULL;
struct file *file;
int n = iterate_fd(current->files, *fd, match_context, NULL);
if (!n)
@@ -74,10 +74,13 @@ static struct spu_context *coredump_next_context(int *fd)
*fd = n - 1;
rcu_read_lock();
- file = lookup_fd_rcu(*fd);
- ctx = SPUFS_I(file_inode(file))->i_ctx;
- get_spu_context(ctx);
+ file = lookup_fdget_rcu(*fd);
rcu_read_unlock();
+ if (file) {
+ ctx = SPUFS_I(file_inode(file))->i_ctx;
+ get_spu_context(ctx);
+ fput(file);
+ }
return ctx;
}
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 38c5be34c895..10c1320adfd0 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -86,7 +86,7 @@ spufs_new_inode(struct super_block *sb, umode_t mode)
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = current_fsgid();
- inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
out:
return inode;
}
diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S
index bae45b358a09..2b0cac6fb61f 100644
--- a/arch/powerpc/platforms/pseries/hvCall.S
+++ b/arch/powerpc/platforms/pseries/hvCall.S
@@ -184,9 +184,6 @@ _GLOBAL_TOC(plpar_hcall)
plpar_hcall_trace:
HCALL_INST_PRECALL(R5)
- std r4,STK_PARAM(R4)(r1)
- mr r0,r4
-
mr r4,r5
mr r5,r6
mr r6,r7
@@ -196,7 +193,7 @@ plpar_hcall_trace:
HVSC
- ld r12,STK_PARAM(R4)(r1)
+ ld r12,STACK_FRAME_MIN_SIZE+STK_PARAM(R4)(r1)
std r4,0(r12)
std r5,8(r12)
std r6,16(r12)
@@ -296,9 +293,6 @@ _GLOBAL_TOC(plpar_hcall9)
plpar_hcall9_trace:
HCALL_INST_PRECALL(R5)
- std r4,STK_PARAM(R4)(r1)
- mr r0,r4
-
mr r4,r5
mr r5,r6
mr r6,r7
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d607ab0f7c6d..9c48fecc6719 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -273,11 +273,9 @@ config RISCV_DMA_NONCOHERENT
select ARCH_HAS_SYNC_DMA_FOR_CPU
select ARCH_HAS_SYNC_DMA_FOR_DEVICE
select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB
- select DMA_DIRECT_REMAP if MMU
config RISCV_NONSTANDARD_CACHE_OPS
bool
- depends on RISCV_DMA_NONCOHERENT
help
This enables function pointer support for non-standard noncoherent
systems to handle cache management.
@@ -550,6 +548,7 @@ config RISCV_ISA_ZICBOM
depends on RISCV_ALTERNATIVE
default y
select RISCV_DMA_NONCOHERENT
+ select DMA_DIRECT_REMAP
help
Adds support to dynamically detect the presence of the ZICBOM
extension (Cache Block Management Operations) and enable its
diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata
index 566bcefeab50..e2c731cfed8c 100644
--- a/arch/riscv/Kconfig.errata
+++ b/arch/riscv/Kconfig.errata
@@ -77,6 +77,7 @@ config ERRATA_THEAD_PBMT
config ERRATA_THEAD_CMO
bool "Apply T-Head cache management errata"
depends on ERRATA_THEAD && MMU
+ select DMA_DIRECT_REMAP
select RISCV_DMA_NONCOHERENT
default y
help
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 1329e060c548..b43a6bb7e4dc 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -6,7 +6,6 @@
# for more details.
#
-OBJCOPYFLAGS := -O binary
LDFLAGS_vmlinux := -z norelro
ifeq ($(CONFIG_RELOCATABLE),y)
LDFLAGS_vmlinux += -shared -Bsymbolic -z notext --emit-relocs
diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
index d79f94432b27..2c02358abd71 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi
@@ -262,7 +262,7 @@
reg = <0x100000 0x400000>;
};
reserved-data@600000 {
- reg = <0x600000 0x1000000>;
+ reg = <0x600000 0xa00000>;
};
};
};
@@ -431,7 +431,7 @@
};
ss-pins {
- pinmux = <GPIOMUX(48, GPOUT_SYS_SPI0_FSS,
+ pinmux = <GPIOMUX(49, GPOUT_SYS_SPI0_FSS,
GPOEN_ENABLE,
GPI_SYS_SPI0_FSS)>;
bias-disable;
@@ -440,30 +440,6 @@
};
};
- uart0_pins: uart0-0 {
- tx-pins {
- pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX,
- GPOEN_ENABLE,
- GPI_NONE)>;
- bias-disable;
- drive-strength = <12>;
- input-disable;
- input-schmitt-disable;
- slew-rate = <0>;
- };
-
- rx-pins {
- pinmux = <GPIOMUX(6, GPOUT_LOW,
- GPOEN_DISABLE,
- GPI_SYS_UART0_RX)>;
- bias-disable; /* external pull-up */
- drive-strength = <2>;
- input-enable;
- input-schmitt-enable;
- slew-rate = <0>;
- };
- };
-
tdm_pins: tdm-0 {
tx-pins {
pinmux = <GPIOMUX(44, GPOUT_SYS_TDM_TXD,
@@ -497,6 +473,30 @@
input-enable;
};
};
+
+ uart0_pins: uart0-0 {
+ tx-pins {
+ pinmux = <GPIOMUX(5, GPOUT_SYS_UART0_TX,
+ GPOEN_ENABLE,
+ GPI_NONE)>;
+ bias-disable;
+ drive-strength = <12>;
+ input-disable;
+ input-schmitt-disable;
+ slew-rate = <0>;
+ };
+
+ rx-pins {
+ pinmux = <GPIOMUX(6, GPOUT_LOW,
+ GPOEN_DISABLE,
+ GPI_SYS_UART0_RX)>;
+ bias-disable; /* external pull-up */
+ drive-strength = <2>;
+ input-enable;
+ input-schmitt-enable;
+ slew-rate = <0>;
+ };
+ };
};
&tdm {
@@ -513,6 +513,7 @@
&usb0 {
dr_mode = "peripheral";
+ status = "okay";
};
&U74_1 {
diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi
index ce708183b6f6..ff364709a6df 100644
--- a/arch/riscv/boot/dts/thead/th1520.dtsi
+++ b/arch/riscv/boot/dts/thead/th1520.dtsi
@@ -139,6 +139,7 @@
interrupt-parent = <&plic>;
#address-cells = <2>;
#size-cells = <2>;
+ dma-noncoherent;
ranges;
plic: interrupt-controller@ffd8000000 {
diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile
index 2d644e19caef..6278c389b801 100644
--- a/arch/riscv/errata/andes/Makefile
+++ b/arch/riscv/errata/andes/Makefile
@@ -1 +1,5 @@
+ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+CFLAGS_errata.o := -mcmodel=medany
+endif
+
obj-y += errata.o
diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h
index e2ecd01bfac7..b55b434f0059 100644
--- a/arch/riscv/include/asm/errata_list.h
+++ b/arch/riscv/include/asm/errata_list.h
@@ -105,7 +105,7 @@ asm volatile(ALTERNATIVE( \
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
* 0000001 01001 rs1 000 00000 0001011
* dcache.cva rs1 (clean, virtual address)
- * 0000001 00100 rs1 000 00000 0001011
+ * 0000001 00101 rs1 000 00000 0001011
*
* dcache.cipa rs1 (clean then invalidate, physical address)
* | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 |
@@ -118,7 +118,7 @@ asm volatile(ALTERNATIVE( \
* 0000000 11001 00000 000 00000 0001011
*/
#define THEAD_inval_A0 ".long 0x0265000b"
-#define THEAD_clean_A0 ".long 0x0245000b"
+#define THEAD_clean_A0 ".long 0x0255000b"
#define THEAD_flush_A0 ".long 0x0275000b"
#define THEAD_SYNC_S ".long 0x0190000b"
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 740a979171e5..2b2f5df7ef2c 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -31,6 +31,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
return addr;
}
+/*
+ * Let's do like x86/arm64 and ignore the compat syscalls.
+ */
+#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS
+static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
+{
+ return is_compat_task();
+}
+
+#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME
+static inline bool arch_syscall_match_sym_name(const char *sym,
+ const char *name)
+{
+ /*
+ * Since all syscall functions have __riscv_ prefix, we must skip it.
+ * However, as we described above, we decided to ignore compat
+ * syscalls, so we don't care about __riscv_compat_ prefix here.
+ */
+ return !strcmp(sym + 8, name);
+}
+
struct dyn_arch_ftrace {
};
#endif
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index 34e24f078cc1..4c5b0e929890 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -18,7 +18,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm,
- unsigned long addr, pte_t *ptep, pte_t pte);
+ unsigned long addr, pte_t *ptep, pte_t pte,
+ unsigned long sz);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h
index e7882ccb0fd4..78ea44f76718 100644
--- a/arch/riscv/include/asm/kprobes.h
+++ b/arch/riscv/include/asm/kprobes.h
@@ -40,6 +40,15 @@ void arch_remove_kprobe(struct kprobe *p);
int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr);
bool kprobe_breakpoint_handler(struct pt_regs *regs);
bool kprobe_single_step_handler(struct pt_regs *regs);
-
+#else
+static inline bool kprobe_breakpoint_handler(struct pt_regs *regs)
+{
+ return false;
+}
+
+static inline bool kprobe_single_step_handler(struct pt_regs *regs)
+{
+ return false;
+}
#endif /* CONFIG_KPROBES */
#endif /* _ASM_RISCV_KPROBES_H */
diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h
index f2183e00fdd2..3fc7deda9190 100644
--- a/arch/riscv/include/asm/uprobes.h
+++ b/arch/riscv/include/asm/uprobes.h
@@ -34,7 +34,18 @@ struct arch_uprobe {
bool simulate;
};
+#ifdef CONFIG_UPROBES
bool uprobe_breakpoint_handler(struct pt_regs *regs);
bool uprobe_single_step_handler(struct pt_regs *regs);
-
+#else
+static inline bool uprobe_breakpoint_handler(struct pt_regs *regs)
+{
+ return false;
+}
+
+static inline bool uprobe_single_step_handler(struct pt_regs *regs)
+{
+ return false;
+}
+#endif /* CONFIG_UPROBES */
#endif /* _ASM_RISCV_UPROBES_H */
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index f4099059ed8f..e60fbd8660c4 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -98,7 +98,13 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
kbuf.image = image;
kbuf.buf_min = lowest_paddr;
kbuf.buf_max = ULONG_MAX;
- kbuf.buf_align = PAGE_SIZE;
+
+ /*
+ * Current riscv boot protocol requires 2MB alignment for
+ * RV64 and 4MB alignment for RV32
+ *
+ */
+ kbuf.buf_align = PMD_SIZE;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
kbuf.top_down = false;
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index a8efa053c4a5..9cc0a7669271 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -60,7 +60,7 @@ static void init_irq_stacks(void)
}
#endif /* CONFIG_VMAP_STACK */
-#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK
+#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK
void do_softirq_own_stack(void)
{
#ifdef CONFIG_IRQ_STACKS
@@ -92,7 +92,7 @@ void do_softirq_own_stack(void)
#endif
__do_softirq();
}
-#endif /* CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK */
+#endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */
#else
static void init_irq_stacks(void) {}
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index e600aab116a4..aac853ae4eb7 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -173,19 +173,6 @@ static void __init init_resources(void)
if (ret < 0)
goto error;
-#ifdef CONFIG_KEXEC_CORE
- if (crashk_res.start != crashk_res.end) {
- ret = add_resource(&iomem_resource, &crashk_res);
- if (ret < 0)
- goto error;
- }
- if (crashk_low_res.start != crashk_low_res.end) {
- ret = add_resource(&iomem_resource, &crashk_low_res);
- if (ret < 0)
- goto error;
- }
-#endif
-
#ifdef CONFIG_CRASH_DUMP
if (elfcorehdr_size > 0) {
elfcorehdr_res.start = elfcorehdr_addr;
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 180d951d3624..21a4d0e111bc 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -311,13 +311,6 @@ static inline void __user *get_sigframe(struct ksignal *ksig,
/* Align the stack frame. */
sp &= ~0xfUL;
- /*
- * Fail if the size of the altstack is not large enough for the
- * sigframe construction.
- */
- if (current->sas_ss_size && sp < current->sas_ss_sp)
- return (void __user __force *)-1UL;
-
return (void __user *)sp;
}
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 19807c4d3805..fae8f610d867 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -13,6 +13,8 @@
#include <linux/kdebug.h>
#include <linux/uaccess.h>
#include <linux/kprobes.h>
+#include <linux/uprobes.h>
+#include <asm/uprobes.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/irq.h>
@@ -247,22 +249,28 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
return GET_INSN_LENGTH(insn);
}
+static bool probe_single_step_handler(struct pt_regs *regs)
+{
+ bool user = user_mode(regs);
+
+ return user ? uprobe_single_step_handler(regs) : kprobe_single_step_handler(regs);
+}
+
+static bool probe_breakpoint_handler(struct pt_regs *regs)
+{
+ bool user = user_mode(regs);
+
+ return user ? uprobe_breakpoint_handler(regs) : kprobe_breakpoint_handler(regs);
+}
+
void handle_break(struct pt_regs *regs)
{
-#ifdef CONFIG_KPROBES
- if (kprobe_single_step_handler(regs))
+ if (probe_single_step_handler(regs))
return;
- if (kprobe_breakpoint_handler(regs))
- return;
-#endif
-#ifdef CONFIG_UPROBES
- if (uprobe_single_step_handler(regs))
+ if (probe_breakpoint_handler(regs))
return;
- if (uprobe_breakpoint_handler(regs))
- return;
-#endif
current->thread.bad_cause = regs->cause;
if (user_mode(regs))
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 1b7e9fa265cb..b7e0e03c69b1 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -460,8 +460,11 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu,
reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
return -ENOENT;
- *reg_val = 0;
host_isa_ext = kvm_isa_ext_arr[reg_num];
+ if (!__riscv_isa_extension_available(NULL, host_isa_ext))
+ return -ENOENT;
+
+ *reg_val = 0;
if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
*reg_val = 1; /* Mark the given extension as available */
@@ -842,7 +845,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu,
u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i;
isa_ext = kvm_isa_ext_arr[i];
- if (!__riscv_isa_extension_available(vcpu->arch.isa, isa_ext))
+ if (!__riscv_isa_extension_available(NULL, isa_ext))
continue;
if (uindices) {
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 6115d7514972..90d4ba36d1d0 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -72,7 +72,7 @@ static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_f
}
pagefault_out_of_memory();
return;
- } else if (fault & VM_FAULT_SIGBUS) {
+ } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs)) {
no_context(regs, addr);
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 96225a8533ad..b52f0210481f 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -180,17 +180,25 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
void set_huge_pte_at(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep,
- pte_t pte)
+ pte_t pte,
+ unsigned long sz)
{
+ unsigned long hugepage_shift;
int i, pte_num;
- if (!pte_napot(pte)) {
- set_pte_at(mm, addr, ptep, pte);
- return;
- }
+ if (sz >= PGDIR_SIZE)
+ hugepage_shift = PGDIR_SHIFT;
+ else if (sz >= P4D_SIZE)
+ hugepage_shift = P4D_SHIFT;
+ else if (sz >= PUD_SIZE)
+ hugepage_shift = PUD_SHIFT;
+ else if (sz >= PMD_SIZE)
+ hugepage_shift = PMD_SHIFT;
+ else
+ hugepage_shift = PAGE_SHIFT;
- pte_num = napot_pte_num(napot_cont_order(pte));
- for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE)
+ pte_num = sz >> hugepage_shift;
+ for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift))
set_pte_at(mm, addr, ptep, pte);
}
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index ecd3ae6f4116..8581693e62d3 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -245,7 +245,7 @@ static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx)
emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx);
/* Set return value. */
if (!is_tail_call)
- emit_mv(RV_REG_A0, RV_REG_A5, ctx);
+ emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx);
emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA,
is_tail_call ? (RV_FENTRY_NINSNS + 1) * 4 : 0, /* skip reserved nops and TCC init */
ctx);
@@ -759,8 +759,10 @@ static int invoke_bpf_prog(struct bpf_tramp_link *l, int args_off, int retval_of
if (ret)
return ret;
- if (save_ret)
- emit_sd(RV_REG_FP, -retval_off, regmap[BPF_REG_0], ctx);
+ if (save_ret) {
+ emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx);
+ emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx);
+ }
/* update branch with beqz */
if (ctx->insns) {
@@ -853,7 +855,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET);
if (save_ret) {
- stack_size += 8;
+ stack_size += 16; /* Save both A5 (BPF R0) and A0 */
retval_off = stack_size;
}
@@ -957,6 +959,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
if (ret)
goto out;
emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx);
+ emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx);
im->ip_after_call = ctx->insns + ctx->ninsns;
/* 2 nops reserved for auipc+jalr pair */
emit(rv_nop(), ctx);
@@ -988,8 +991,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
if (flags & BPF_TRAMP_F_RESTORE_REGS)
restore_args(nregs, args_off, ctx);
- if (save_ret)
+ if (save_ret) {
emit_ld(RV_REG_A0, -retval_off, RV_REG_FP, ctx);
+ emit_ld(regmap[BPF_REG_0], -(retval_off - 8), RV_REG_FP, ctx);
+ }
emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx);
@@ -1515,7 +1520,8 @@ out_be:
if (ret)
return ret;
- emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx);
+ if (insn->src_reg != BPF_PSEUDO_CALL)
+ emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx);
break;
}
/* tail call */
diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
index 01257ce3b89c..442a74f113cb 100644
--- a/arch/s390/boot/vmem.c
+++ b/arch/s390/boot/vmem.c
@@ -57,6 +57,7 @@ static void kasan_populate_shadow(void)
pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY);
pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY);
p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY);
+ unsigned long memgap_start = 0;
unsigned long untracked_end;
unsigned long start, end;
int i;
@@ -101,8 +102,12 @@ static void kasan_populate_shadow(void)
* +- shadow end ----+---------+- shadow end ---+
*/
- for_each_physmem_usable_range(i, &start, &end)
+ for_each_physmem_usable_range(i, &start, &end) {
kasan_populate(start, end, POPULATE_KASAN_MAP_SHADOW);
+ if (memgap_start && physmem_info.info_source == MEM_DETECT_DIAG260)
+ kasan_populate(memgap_start, start, POPULATE_KASAN_ZERO_SHADOW);
+ memgap_start = end;
+ }
if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
untracked_end = VMALLOC_START;
/* shallowly populate kasan shadow for vmalloc and modules */
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index af2fbe48e16c..438cd92e6080 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -40,23 +40,25 @@ CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
CONFIG_PROFILING=y
+CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
+CONFIG_CRASH_DUMP=y
CONFIG_LIVEPATCH=y
CONFIG_MARCH_ZEC12=y
CONFIG_TUNE_ZEC12=y
CONFIG_NR_CPUS=512
CONFIG_NUMA=y
CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
-CONFIG_KEXEC_SIG=y
+CONFIG_CERT_STORE=y
CONFIG_EXPOLINE=y
CONFIG_EXPOLINE_AUTO=y
CONFIG_CHSC_SCH=y
CONFIG_VFIO_CCW=m
CONFIG_VFIO_AP=m
-CONFIG_CRASH_DUMP=y
CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
CONFIG_CMM=m
CONFIG_APPLDATA_BASE=y
+CONFIG_S390_HYPFS_FS=y
CONFIG_KVM=m
CONFIG_S390_UNWIND_SELFTEST=m
CONFIG_S390_KPROBES_SANITY_TEST=m
@@ -434,6 +436,7 @@ CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
+# CONFIG_MD_BITMAP_FILE is not set
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
@@ -577,6 +580,7 @@ CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
# CONFIG_DRM_DEBUG_MODESET_LOCK is not set
CONFIG_FB=y
+# CONFIG_FB_DEVICE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID_SUPPORT is not set
@@ -647,6 +651,7 @@ CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_TMPFS_INODE64=y
+CONFIG_TMPFS_QUOTA=y
CONFIG_HUGETLBFS=y
CONFIG_ECRYPT_FS=m
CONFIG_CRAMFS=m
@@ -703,6 +708,7 @@ CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_INIT_STACK_NONE=y
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
CONFIG_CRYPTO_PCRYPT=m
@@ -825,9 +831,9 @@ CONFIG_LOCK_STAT=y
CONFIG_DEBUG_ATOMIC_SLEEP=y
CONFIG_DEBUG_LOCKING_API_SELFTESTS=y
CONFIG_DEBUG_IRQFLAGS=y
+CONFIG_DEBUG_LIST=y
CONFIG_DEBUG_SG=y
CONFIG_DEBUG_NOTIFIERS=y
-CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_DEBUG_CREDENTIALS=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_REF_SCALE_TEST=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 3f263b767a4c..1b8150e50f6a 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -38,23 +38,25 @@ CONFIG_SCHED_AUTOGROUP=y
CONFIG_EXPERT=y
# CONFIG_SYSFS_SYSCALL is not set
CONFIG_PROFILING=y
+CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
+CONFIG_CRASH_DUMP=y
CONFIG_LIVEPATCH=y
CONFIG_MARCH_ZEC12=y
CONFIG_TUNE_ZEC12=y
CONFIG_NR_CPUS=512
CONFIG_NUMA=y
CONFIG_HZ_100=y
-CONFIG_KEXEC_FILE=y
-CONFIG_KEXEC_SIG=y
+CONFIG_CERT_STORE=y
CONFIG_EXPOLINE=y
CONFIG_EXPOLINE_AUTO=y
CONFIG_CHSC_SCH=y
CONFIG_VFIO_CCW=m
CONFIG_VFIO_AP=m
-CONFIG_CRASH_DUMP=y
CONFIG_PROTECTED_VIRTUALIZATION_GUEST=y
CONFIG_CMM=m
CONFIG_APPLDATA_BASE=y
+CONFIG_S390_HYPFS_FS=y
CONFIG_KVM=m
CONFIG_S390_UNWIND_SELFTEST=m
CONFIG_S390_KPROBES_SANITY_TEST=m
@@ -424,6 +426,7 @@ CONFIG_SCSI_DH_EMC=m
CONFIG_SCSI_DH_ALUA=m
CONFIG_MD=y
CONFIG_BLK_DEV_MD=y
+# CONFIG_MD_BITMAP_FILE is not set
CONFIG_MD_LINEAR=m
CONFIG_MD_MULTIPATH=m
CONFIG_MD_FAULTY=m
@@ -566,6 +569,7 @@ CONFIG_WATCHDOG_NOWAYOUT=y
CONFIG_SOFT_WATCHDOG=m
CONFIG_DIAG288_WATCHDOG=m
CONFIG_FB=y
+# CONFIG_FB_DEVICE is not set
CONFIG_FRAMEBUFFER_CONSOLE=y
CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
# CONFIG_HID_SUPPORT is not set
@@ -632,6 +636,7 @@ CONFIG_PROC_KCORE=y
CONFIG_TMPFS=y
CONFIG_TMPFS_POSIX_ACL=y
CONFIG_TMPFS_INODE64=y
+CONFIG_TMPFS_QUOTA=y
CONFIG_HUGETLBFS=y
CONFIG_CONFIGFS_FS=m
CONFIG_ECRYPT_FS=m
@@ -687,6 +692,7 @@ CONFIG_IMA_WRITE_POLICY=y
CONFIG_IMA_APPRAISE=y
CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
CONFIG_INIT_STACK_NONE=y
+CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_CRYPTO_FIPS=y
CONFIG_CRYPTO_USER=m
# CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -781,7 +787,6 @@ CONFIG_PTDUMP_DEBUGFS=y
CONFIG_DEBUG_MEMORY_INIT=y
CONFIG_PANIC_ON_OOPS=y
CONFIG_TEST_LOCKUP=m
-CONFIG_BUG_ON_DATA_CORRUPTION=y
CONFIG_RCU_TORTURE_TEST=m
CONFIG_RCU_REF_SCALE_TEST=m
CONFIG_RCU_CPU_STALL_TIMEOUT=60
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index e62fb2015102..b831083b4edd 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -8,6 +8,7 @@ CONFIG_BPF_SYSCALL=y
# CONFIG_NET_NS is not set
CONFIG_BLK_DEV_INITRD=y
CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_CRASH_DUMP=y
CONFIG_MARCH_ZEC12=y
CONFIG_TUNE_ZEC12=y
# CONFIG_COMPAT is not set
@@ -15,9 +16,8 @@ CONFIG_NR_CPUS=2
CONFIG_HZ_100=y
# CONFIG_CHSC_SCH is not set
# CONFIG_SCM_BUS is not set
-CONFIG_CRASH_DUMP=y
# CONFIG_PFAULT is not set
-# CONFIG_S390_HYPFS_FS is not set
+# CONFIG_S390_HYPFS is not set
# CONFIG_VIRTUALIZATION is not set
# CONFIG_S390_GUEST is not set
# CONFIG_SECCOMP is not set
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index ada83149932f..858beaf4a8cb 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -53,7 +53,7 @@ static void hypfs_update_update(struct super_block *sb)
struct inode *inode = d_inode(sb_info->update_file);
sb_info->last_update = ktime_get_seconds();
- inode->i_atime = inode->i_mtime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
}
/* directory tree removal functions */
@@ -101,7 +101,7 @@ static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode)
ret->i_mode = mode;
ret->i_uid = hypfs_info->uid;
ret->i_gid = hypfs_info->gid;
- ret->i_atime = ret->i_mtime = inode_set_ctime_current(ret);
+ simple_inode_init_ts(ret);
if (S_ISDIR(mode))
set_nlink(ret, 2);
}
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index f07267875a19..deb198a61039 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -16,6 +16,8 @@
#define hugepages_supported() (MACHINE_HAS_EDAT1)
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
pte_t huge_ptep_get(pte_t *ptep);
pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
@@ -65,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
int changed = !pte_same(huge_ptep_get(ptep), pte);
if (changed) {
huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ __set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
}
return changed;
}
@@ -74,7 +76,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
- set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
+ __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
}
static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot)
diff --git a/arch/s390/kernel/cert_store.c b/arch/s390/kernel/cert_store.c
index 3986a044eb36..554447768bdd 100644
--- a/arch/s390/kernel/cert_store.c
+++ b/arch/s390/kernel/cert_store.c
@@ -432,15 +432,16 @@ static char *get_key_description(struct vcssb *vcssb, const struct vce *vce)
char *desc;
cs_token = vcssb->cs_token;
- /* Description string contains "%64s:%04u:%08u\0". */
+ /* Description string contains "%64s:%05u:%010u\0". */
name_len = sizeof(vce->vce_hdr.vc_name);
- len = name_len + 1 + 4 + 1 + 8 + 1;
+ len = name_len + 1 + 5 + 1 + 10 + 1;
desc = kmalloc(len, GFP_KERNEL);
if (!desc)
return NULL;
memcpy(desc, vce->vce_hdr.vc_name, name_len);
- sprintf(desc + name_len, ":%04u:%08u", vce->vce_hdr.vc_index, cs_token);
+ snprintf(desc + name_len, len - name_len, ":%05u:%010u",
+ vce->vce_hdr.vc_index, cs_token);
return desc;
}
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a4edb7ea66ea..214a1b67f80a 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -898,7 +898,7 @@ static void smp_start_secondary(void *cpuvoid)
S390_lowcore.restart_flags = 0;
restore_access_regs(S390_lowcore.access_regs_save_area);
cpu_init();
- rcu_cpu_starting(cpu);
+ rcutree_report_cpu_starting(cpu);
init_cpu_timer();
vtime_init();
vdso_getcpu_init();
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 0122cc156952..31be90b241f7 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -455,3 +455,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue sys_futex_requeue
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 68adf1de8888..66bda6a8f918 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -522,7 +522,7 @@ static struct sched_domain_topology_level s390_topology[] = {
{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
{ cpu_book_mask, SD_INIT_NAME(BOOK) },
{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
- { cpu_cpu_mask, SD_INIT_NAME(DIE) },
+ { cpu_cpu_mask, SD_INIT_NAME(PKG) },
{ NULL, },
};
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c1b47d608a2b..efaebba5ee19 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -303,11 +303,6 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
return 0;
}
-static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa)
-{
- return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa);
-}
-
static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
{
set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
@@ -3216,11 +3211,12 @@ void kvm_s390_gisa_destroy(struct kvm *kvm)
if (!gi->origin)
return;
- if (gi->alert.mask)
- KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x",
- kvm, gi->alert.mask);
- while (gisa_in_alert_list(gi->origin))
- cpu_relax();
+ WARN(gi->alert.mask != 0x00,
+ "unexpected non zero alert.mask 0x%02x",
+ gi->alert.mask);
+ gi->alert.mask = 0x00;
+ if (gisa_set_iam(gi->origin, gi->alert.mask))
+ process_gib_alert_list();
hrtimer_cancel(&gi->timer);
gi->origin = NULL;
VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa);
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index c718f2a0de94..297a6d897d5a 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -142,7 +142,7 @@ static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
__storage_key_init_range(paddr, paddr + size - 1);
}
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte)
{
unsigned long rste;
@@ -163,6 +163,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
set_pte(ptep, __pte(rste));
}
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz)
+{
+ __set_huge_pte_at(mm, addr, ptep, pte);
+}
+
pte_t huge_ptep_get(pte_t *ptep)
{
return __rste_to_pte(pte_val(*ptep));
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index de2fb12120d2..bf06b7283f0c 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -556,7 +556,7 @@ static void bpf_jit_prologue(struct bpf_jit *jit, struct bpf_prog *fp,
EMIT6_PCREL_RILC(0xc0040000, 0, jit->prologue_plt);
jit->prologue_plt_ret = jit->prg;
- if (fp->aux->func_idx == 0) {
+ if (!bpf_is_subprog(fp)) {
/* Initialize the tail call counter in the main program. */
/* xc STK_OFF_TCCNT(4,%r15),STK_OFF_TCCNT(%r15) */
_EMIT6(0xd703f000 | STK_OFF_TCCNT, 0xf000 | STK_OFF_TCCNT);
@@ -670,15 +670,18 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
static int get_probe_mem_regno(const u8 *insn)
{
/*
- * insn must point to llgc, llgh, llgf or lg, which have destination
- * register at the same position.
+ * insn must point to llgc, llgh, llgf, lg, lgb, lgh or lgf, which have
+ * destination register at the same position.
*/
- if (insn[0] != 0xe3) /* common llgc, llgh, llgf and lg prefix */
+ if (insn[0] != 0xe3) /* common prefix */
return -1;
if (insn[5] != 0x90 && /* llgc */
insn[5] != 0x91 && /* llgh */
insn[5] != 0x16 && /* llgf */
- insn[5] != 0x04) /* lg */
+ insn[5] != 0x04 && /* lg */
+ insn[5] != 0x77 && /* lgb */
+ insn[5] != 0x15 && /* lgh */
+ insn[5] != 0x14) /* lgf */
return -1;
return insn[1] >> 4;
}
@@ -776,6 +779,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
int i, bool extra_pass, u32 stack_depth)
{
struct bpf_insn *insn = &fp->insnsi[i];
+ s16 branch_oc_off = insn->off;
u32 dst_reg = insn->dst_reg;
u32 src_reg = insn->src_reg;
int last, insn_count = 1;
@@ -788,22 +792,55 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
int err;
if (BPF_CLASS(insn->code) == BPF_LDX &&
- BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
probe_prg = jit->prg;
switch (insn->code) {
/*
* BPF_MOV
*/
- case BPF_ALU | BPF_MOV | BPF_X: /* dst = (u32) src */
- /* llgfr %dst,%src */
- EMIT4(0xb9160000, dst_reg, src_reg);
- if (insn_is_zext(&insn[1]))
- insn_count = 2;
+ case BPF_ALU | BPF_MOV | BPF_X:
+ switch (insn->off) {
+ case 0: /* DST = (u32) SRC */
+ /* llgfr %dst,%src */
+ EMIT4(0xb9160000, dst_reg, src_reg);
+ if (insn_is_zext(&insn[1]))
+ insn_count = 2;
+ break;
+ case 8: /* DST = (u32)(s8) SRC */
+ /* lbr %dst,%src */
+ EMIT4(0xb9260000, dst_reg, src_reg);
+ /* llgfr %dst,%dst */
+ EMIT4(0xb9160000, dst_reg, dst_reg);
+ break;
+ case 16: /* DST = (u32)(s16) SRC */
+ /* lhr %dst,%src */
+ EMIT4(0xb9270000, dst_reg, src_reg);
+ /* llgfr %dst,%dst */
+ EMIT4(0xb9160000, dst_reg, dst_reg);
+ break;
+ }
break;
- case BPF_ALU64 | BPF_MOV | BPF_X: /* dst = src */
- /* lgr %dst,%src */
- EMIT4(0xb9040000, dst_reg, src_reg);
+ case BPF_ALU64 | BPF_MOV | BPF_X:
+ switch (insn->off) {
+ case 0: /* DST = SRC */
+ /* lgr %dst,%src */
+ EMIT4(0xb9040000, dst_reg, src_reg);
+ break;
+ case 8: /* DST = (s8) SRC */
+ /* lgbr %dst,%src */
+ EMIT4(0xb9060000, dst_reg, src_reg);
+ break;
+ case 16: /* DST = (s16) SRC */
+ /* lghr %dst,%src */
+ EMIT4(0xb9070000, dst_reg, src_reg);
+ break;
+ case 32: /* DST = (s32) SRC */
+ /* lgfr %dst,%src */
+ EMIT4(0xb9140000, dst_reg, src_reg);
+ break;
+ }
break;
case BPF_ALU | BPF_MOV | BPF_K: /* dst = (u32) imm */
/* llilf %dst,imm */
@@ -912,66 +949,115 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
/*
* BPF_DIV / BPF_MOD
*/
- case BPF_ALU | BPF_DIV | BPF_X: /* dst = (u32) dst / (u32) src */
- case BPF_ALU | BPF_MOD | BPF_X: /* dst = (u32) dst % (u32) src */
+ case BPF_ALU | BPF_DIV | BPF_X:
+ case BPF_ALU | BPF_MOD | BPF_X:
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
- /* lhi %w0,0 */
- EMIT4_IMM(0xa7080000, REG_W0, 0);
- /* lr %w1,%dst */
- EMIT2(0x1800, REG_W1, dst_reg);
- /* dlr %w0,%src */
- EMIT4(0xb9970000, REG_W0, src_reg);
+ switch (off) {
+ case 0: /* dst = (u32) dst {/,%} (u32) src */
+ /* xr %w0,%w0 */
+ EMIT2(0x1700, REG_W0, REG_W0);
+ /* lr %w1,%dst */
+ EMIT2(0x1800, REG_W1, dst_reg);
+ /* dlr %w0,%src */
+ EMIT4(0xb9970000, REG_W0, src_reg);
+ break;
+ case 1: /* dst = (u32) ((s32) dst {/,%} (s32) src) */
+ /* lgfr %r1,%dst */
+ EMIT4(0xb9140000, REG_W1, dst_reg);
+ /* dsgfr %r0,%src */
+ EMIT4(0xb91d0000, REG_W0, src_reg);
+ break;
+ }
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
if (insn_is_zext(&insn[1]))
insn_count = 2;
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_X: /* dst = dst / src */
- case BPF_ALU64 | BPF_MOD | BPF_X: /* dst = dst % src */
+ case BPF_ALU64 | BPF_DIV | BPF_X:
+ case BPF_ALU64 | BPF_MOD | BPF_X:
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
- /* lghi %w0,0 */
- EMIT4_IMM(0xa7090000, REG_W0, 0);
- /* lgr %w1,%dst */
- EMIT4(0xb9040000, REG_W1, dst_reg);
- /* dlgr %w0,%dst */
- EMIT4(0xb9870000, REG_W0, src_reg);
+ switch (off) {
+ case 0: /* dst = dst {/,%} src */
+ /* lghi %w0,0 */
+ EMIT4_IMM(0xa7090000, REG_W0, 0);
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* dlgr %w0,%src */
+ EMIT4(0xb9870000, REG_W0, src_reg);
+ break;
+ case 1: /* dst = (s64) dst {/,%} (s64) src */
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* dsgr %w0,%src */
+ EMIT4(0xb90d0000, REG_W0, src_reg);
+ break;
+ }
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
break;
}
- case BPF_ALU | BPF_DIV | BPF_K: /* dst = (u32) dst / (u32) imm */
- case BPF_ALU | BPF_MOD | BPF_K: /* dst = (u32) dst % (u32) imm */
+ case BPF_ALU | BPF_DIV | BPF_K:
+ case BPF_ALU | BPF_MOD | BPF_K:
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
if (imm == 1) {
if (BPF_OP(insn->code) == BPF_MOD)
- /* lhgi %dst,0 */
+ /* lghi %dst,0 */
EMIT4_IMM(0xa7090000, dst_reg, 0);
else
EMIT_ZERO(dst_reg);
break;
}
- /* lhi %w0,0 */
- EMIT4_IMM(0xa7080000, REG_W0, 0);
- /* lr %w1,%dst */
- EMIT2(0x1800, REG_W1, dst_reg);
if (!is_first_pass(jit) && can_use_ldisp_for_lit32(jit)) {
- /* dl %w0,<d(imm)>(%l) */
- EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0, REG_L,
- EMIT_CONST_U32(imm));
+ switch (off) {
+ case 0: /* dst = (u32) dst {/,%} (u32) imm */
+ /* xr %w0,%w0 */
+ EMIT2(0x1700, REG_W0, REG_W0);
+ /* lr %w1,%dst */
+ EMIT2(0x1800, REG_W1, dst_reg);
+ /* dl %w0,<d(imm)>(%l) */
+ EMIT6_DISP_LH(0xe3000000, 0x0097, REG_W0, REG_0,
+ REG_L, EMIT_CONST_U32(imm));
+ break;
+ case 1: /* dst = (s32) dst {/,%} (s32) imm */
+ /* lgfr %r1,%dst */
+ EMIT4(0xb9140000, REG_W1, dst_reg);
+ /* dsgf %r0,<d(imm)>(%l) */
+ EMIT6_DISP_LH(0xe3000000, 0x001d, REG_W0, REG_0,
+ REG_L, EMIT_CONST_U32(imm));
+ break;
+ }
} else {
- /* lgfrl %dst,imm */
- EMIT6_PCREL_RILB(0xc40c0000, dst_reg,
- _EMIT_CONST_U32(imm));
- jit->seen |= SEEN_LITERAL;
- /* dlr %w0,%dst */
- EMIT4(0xb9970000, REG_W0, dst_reg);
+ switch (off) {
+ case 0: /* dst = (u32) dst {/,%} (u32) imm */
+ /* xr %w0,%w0 */
+ EMIT2(0x1700, REG_W0, REG_W0);
+ /* lr %w1,%dst */
+ EMIT2(0x1800, REG_W1, dst_reg);
+ /* lrl %dst,imm */
+ EMIT6_PCREL_RILB(0xc40d0000, dst_reg,
+ _EMIT_CONST_U32(imm));
+ jit->seen |= SEEN_LITERAL;
+ /* dlr %w0,%dst */
+ EMIT4(0xb9970000, REG_W0, dst_reg);
+ break;
+ case 1: /* dst = (s32) dst {/,%} (s32) imm */
+ /* lgfr %w1,%dst */
+ EMIT4(0xb9140000, REG_W1, dst_reg);
+ /* lgfrl %dst,imm */
+ EMIT6_PCREL_RILB(0xc40c0000, dst_reg,
+ _EMIT_CONST_U32(imm));
+ jit->seen |= SEEN_LITERAL;
+ /* dsgr %w0,%dst */
+ EMIT4(0xb90d0000, REG_W0, dst_reg);
+ break;
+ }
}
/* llgfr %dst,%rc */
EMIT4(0xb9160000, dst_reg, rc_reg);
@@ -979,8 +1065,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
insn_count = 2;
break;
}
- case BPF_ALU64 | BPF_DIV | BPF_K: /* dst = dst / imm */
- case BPF_ALU64 | BPF_MOD | BPF_K: /* dst = dst % imm */
+ case BPF_ALU64 | BPF_DIV | BPF_K:
+ case BPF_ALU64 | BPF_MOD | BPF_K:
{
int rc_reg = BPF_OP(insn->code) == BPF_DIV ? REG_W1 : REG_W0;
@@ -990,21 +1076,50 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
EMIT4_IMM(0xa7090000, dst_reg, 0);
break;
}
- /* lghi %w0,0 */
- EMIT4_IMM(0xa7090000, REG_W0, 0);
- /* lgr %w1,%dst */
- EMIT4(0xb9040000, REG_W1, dst_reg);
if (!is_first_pass(jit) && can_use_ldisp_for_lit64(jit)) {
- /* dlg %w0,<d(imm)>(%l) */
- EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0, REG_L,
- EMIT_CONST_U64(imm));
+ switch (off) {
+ case 0: /* dst = dst {/,%} imm */
+ /* lghi %w0,0 */
+ EMIT4_IMM(0xa7090000, REG_W0, 0);
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* dlg %w0,<d(imm)>(%l) */
+ EMIT6_DISP_LH(0xe3000000, 0x0087, REG_W0, REG_0,
+ REG_L, EMIT_CONST_U64(imm));
+ break;
+ case 1: /* dst = (s64) dst {/,%} (s64) imm */
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* dsg %w0,<d(imm)>(%l) */
+ EMIT6_DISP_LH(0xe3000000, 0x000d, REG_W0, REG_0,
+ REG_L, EMIT_CONST_U64(imm));
+ break;
+ }
} else {
- /* lgrl %dst,imm */
- EMIT6_PCREL_RILB(0xc4080000, dst_reg,
- _EMIT_CONST_U64(imm));
- jit->seen |= SEEN_LITERAL;
- /* dlgr %w0,%dst */
- EMIT4(0xb9870000, REG_W0, dst_reg);
+ switch (off) {
+ case 0: /* dst = dst {/,%} imm */
+ /* lghi %w0,0 */
+ EMIT4_IMM(0xa7090000, REG_W0, 0);
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* lgrl %dst,imm */
+ EMIT6_PCREL_RILB(0xc4080000, dst_reg,
+ _EMIT_CONST_U64(imm));
+ jit->seen |= SEEN_LITERAL;
+ /* dlgr %w0,%dst */
+ EMIT4(0xb9870000, REG_W0, dst_reg);
+ break;
+ case 1: /* dst = (s64) dst {/,%} (s64) imm */
+ /* lgr %w1,%dst */
+ EMIT4(0xb9040000, REG_W1, dst_reg);
+ /* lgrl %dst,imm */
+ EMIT6_PCREL_RILB(0xc4080000, dst_reg,
+ _EMIT_CONST_U64(imm));
+ jit->seen |= SEEN_LITERAL;
+ /* dsgr %w0,%dst */
+ EMIT4(0xb90d0000, REG_W0, dst_reg);
+ break;
+ }
}
/* lgr %dst,%rc */
EMIT4(0xb9040000, dst_reg, rc_reg);
@@ -1217,6 +1332,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
}
break;
case BPF_ALU | BPF_END | BPF_FROM_LE:
+ case BPF_ALU64 | BPF_END | BPF_FROM_LE:
switch (imm) {
case 16: /* dst = (u16) cpu_to_le16(dst) */
/* lrvr %dst,%dst */
@@ -1374,6 +1490,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
if (insn_is_zext(&insn[1]))
insn_count = 2;
break;
+ case BPF_LDX | BPF_MEMSX | BPF_B: /* dst = *(s8 *)(ul) (src + off) */
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_B:
+ /* lgb %dst,0(off,%src) */
+ EMIT6_DISP_LH(0xe3000000, 0x0077, dst_reg, src_reg, REG_0, off);
+ jit->seen |= SEEN_MEM;
+ break;
case BPF_LDX | BPF_MEM | BPF_H: /* dst = *(u16 *)(ul) (src + off) */
case BPF_LDX | BPF_PROBE_MEM | BPF_H:
/* llgh %dst,0(off,%src) */
@@ -1382,6 +1504,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
if (insn_is_zext(&insn[1]))
insn_count = 2;
break;
+ case BPF_LDX | BPF_MEMSX | BPF_H: /* dst = *(s16 *)(ul) (src + off) */
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_H:
+ /* lgh %dst,0(off,%src) */
+ EMIT6_DISP_LH(0xe3000000, 0x0015, dst_reg, src_reg, REG_0, off);
+ jit->seen |= SEEN_MEM;
+ break;
case BPF_LDX | BPF_MEM | BPF_W: /* dst = *(u32 *)(ul) (src + off) */
case BPF_LDX | BPF_PROBE_MEM | BPF_W:
/* llgf %dst,off(%src) */
@@ -1390,6 +1518,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
if (insn_is_zext(&insn[1]))
insn_count = 2;
break;
+ case BPF_LDX | BPF_MEMSX | BPF_W: /* dst = *(s32 *)(ul) (src + off) */
+ case BPF_LDX | BPF_PROBE_MEMSX | BPF_W:
+ /* lgf %dst,off(%src) */
+ jit->seen |= SEEN_MEM;
+ EMIT6_DISP_LH(0xe3000000, 0x0014, dst_reg, src_reg, REG_0, off);
+ break;
case BPF_LDX | BPF_MEM | BPF_DW: /* dst = *(u64 *)(ul) (src + off) */
case BPF_LDX | BPF_PROBE_MEM | BPF_DW:
/* lg %dst,0(off,%src) */
@@ -1570,6 +1704,9 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp,
* instruction itself (loop) and for BPF with offset 0 we
* branch to the instruction behind the branch.
*/
+ case BPF_JMP32 | BPF_JA: /* if (true) */
+ branch_oc_off = imm;
+ fallthrough;
case BPF_JMP | BPF_JA: /* if (true) */
mask = 0xf000; /* j */
goto branch_oc;
@@ -1738,14 +1875,16 @@ branch_xu:
break;
branch_oc:
if (!is_first_pass(jit) &&
- can_use_rel(jit, addrs[i + off + 1])) {
+ can_use_rel(jit, addrs[i + branch_oc_off + 1])) {
/* brc mask,off */
EMIT4_PCREL_RIC(0xa7040000,
- mask >> 12, addrs[i + off + 1]);
+ mask >> 12,
+ addrs[i + branch_oc_off + 1]);
} else {
/* brcl mask,off */
EMIT6_PCREL_RILC(0xc0040000,
- mask >> 12, addrs[i + off + 1]);
+ mask >> 12,
+ addrs[i + branch_oc_off + 1]);
}
break;
}
@@ -2066,6 +2205,7 @@ struct bpf_tramp_jit {
* func_addr's original caller
*/
int stack_size; /* Trampoline stack size */
+ int backchain_off; /* Offset of backchain */
int stack_args_off; /* Offset of stack arguments for calling
* func_addr, has to be at the top
*/
@@ -2086,9 +2226,10 @@ struct bpf_tramp_jit {
* for __bpf_prog_enter() return value and
* func_addr respectively
*/
- int r14_off; /* Offset of saved %r14 */
int run_ctx_off; /* Offset of struct bpf_tramp_run_ctx */
int tccnt_off; /* Offset of saved tailcall counter */
+ int r14_off; /* Offset of saved %r14, has to be at the
+ * bottom */
int do_fexit; /* do_fexit: label */
};
@@ -2247,8 +2388,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
* Calculate the stack layout.
*/
- /* Reserve STACK_FRAME_OVERHEAD bytes for the callees. */
+ /*
+ * Allocate STACK_FRAME_OVERHEAD bytes for the callees. As the s390x
+ * ABI requires, put our backchain at the end of the allocated memory.
+ */
tjit->stack_size = STACK_FRAME_OVERHEAD;
+ tjit->backchain_off = tjit->stack_size - sizeof(u64);
tjit->stack_args_off = alloc_stack(tjit, nr_stack_args * sizeof(u64));
tjit->reg_args_off = alloc_stack(tjit, nr_reg_args * sizeof(u64));
tjit->ip_off = alloc_stack(tjit, sizeof(u64));
@@ -2256,16 +2401,25 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
tjit->bpf_args_off = alloc_stack(tjit, nr_bpf_args * sizeof(u64));
tjit->retval_off = alloc_stack(tjit, sizeof(u64));
tjit->r7_r8_off = alloc_stack(tjit, 2 * sizeof(u64));
- tjit->r14_off = alloc_stack(tjit, sizeof(u64));
tjit->run_ctx_off = alloc_stack(tjit,
sizeof(struct bpf_tramp_run_ctx));
tjit->tccnt_off = alloc_stack(tjit, sizeof(u64));
- /* The caller has already reserved STACK_FRAME_OVERHEAD bytes. */
- tjit->stack_size -= STACK_FRAME_OVERHEAD;
+ tjit->r14_off = alloc_stack(tjit, sizeof(u64) * 2);
+ /*
+ * In accordance with the s390x ABI, the caller has allocated
+ * STACK_FRAME_OVERHEAD bytes for us. 8 of them contain the caller's
+ * backchain, and the rest we can use.
+ */
+ tjit->stack_size -= STACK_FRAME_OVERHEAD - sizeof(u64);
tjit->orig_stack_args_off = tjit->stack_size + STACK_FRAME_OVERHEAD;
+ /* lgr %r1,%r15 */
+ EMIT4(0xb9040000, REG_1, REG_15);
/* aghi %r15,-stack_size */
EMIT4_IMM(0xa70b0000, REG_15, -tjit->stack_size);
+ /* stg %r1,backchain_off(%r15) */
+ EMIT6_DISP_LH(0xe3000000, 0x0024, REG_1, REG_0, REG_15,
+ tjit->backchain_off);
/* mvc tccnt_off(4,%r15),stack_size+STK_OFF_TCCNT(%r15) */
_EMIT6(0xd203f000 | tjit->tccnt_off,
0xf000 | (tjit->stack_size + STK_OFF_TCCNT));
@@ -2513,7 +2667,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
return -E2BIG;
}
- return ret;
+ return tjit.common.prg;
}
bool bpf_jit_supports_subprog_tailcalls(void)
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 2d9b01d7ca4c..99209085c75b 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -564,6 +564,17 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
s->dma_length = 0;
}
}
+
+static unsigned long *bitmap_vzalloc(size_t bits, gfp_t flags)
+{
+ size_t n = BITS_TO_LONGS(bits);
+ size_t bytes;
+
+ if (unlikely(check_mul_overflow(n, sizeof(unsigned long), &bytes)))
+ return NULL;
+
+ return vzalloc(bytes);
+}
int zpci_dma_init_device(struct zpci_dev *zdev)
{
@@ -604,13 +615,13 @@ int zpci_dma_init_device(struct zpci_dev *zdev)
zdev->end_dma - zdev->start_dma + 1);
zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1;
zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT;
- zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8);
+ zdev->iommu_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL);
if (!zdev->iommu_bitmap) {
rc = -ENOMEM;
goto free_dma_table;
}
if (!s390_iommu_strict) {
- zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8);
+ zdev->lazy_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL);
if (!zdev->lazy_bitmap) {
rc = -ENOMEM;
goto free_bitmap;
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index e90d585c4d3e..4bc5d488ab17 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -455,3 +455,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/sh/mm/ioremap.c b/arch/sh/mm/ioremap.c
index c33b3daa4ad1..33d20f34560f 100644
--- a/arch/sh/mm/ioremap.c
+++ b/arch/sh/mm/ioremap.c
@@ -72,8 +72,8 @@ __ioremap_29bit(phys_addr_t offset, unsigned long size, pgprot_t prot)
#define __ioremap_29bit(offset, size, prot) NULL
#endif /* CONFIG_29BIT */
-void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size,
- unsigned long prot)
+void __iomem __ref *ioremap_prot(phys_addr_t phys_addr, size_t size,
+ unsigned long prot)
{
void __iomem *mapped;
pgprot_t pgprot = __pgprot(prot);
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 0a26cca24232..c714ca6a05aa 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -14,6 +14,8 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t pte, unsigned long sz);
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pte);
#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
@@ -32,7 +34,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
pte_t old_pte = *ptep;
- set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+ __set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
}
#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -42,7 +44,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
{
int changed = !pte_same(*ptep, pte);
if (changed) {
- set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+ __set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
flush_tlb_page(vma, addr);
}
return changed;
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index f07ea88a83af..8fcf2d8c6bd2 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -50,7 +50,7 @@ struct cpuinfo_tree {
/* Offsets into nodes[] for each level of the tree */
struct cpuinfo_level level[CPUINFO_LVL_MAX];
- struct cpuinfo_node nodes[];
+ struct cpuinfo_node nodes[] __counted_by(total_nodes);
};
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 4ed06c71c43f..8404c8e50394 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -498,3 +498,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 84ad709cbecb..66eda40fce36 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -453,5 +453,5 @@ ccslow: cmp %g1, 0
* we only bother with faults on loads... */
cc_fault:
- ret
+ retl
clr %o0
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d7018823206c..b432500c13a5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -328,7 +328,7 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
return pte_offset_huge(pmd, addr);
}
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t entry)
{
unsigned int nptes, orig_shift, shift;
@@ -364,6 +364,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
orig_shift);
}
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t entry, unsigned long sz)
+{
+ __set_huge_pte_at(mm, addr, ptep, entry);
+}
+
pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
diff --git a/arch/um/os-Linux/drivers/ethertap_user.c b/arch/um/os-Linux/drivers/ethertap_user.c
index 9483021d86dd..3363851a4ae8 100644
--- a/arch/um/os-Linux/drivers/ethertap_user.c
+++ b/arch/um/os-Linux/drivers/ethertap_user.c
@@ -105,7 +105,7 @@ static int etap_tramp(char *dev, char *gate, int control_me,
sprintf(data_fd_buf, "%d", data_remote);
sprintf(version_buf, "%d", UML_NET_VERSION);
if (gate != NULL) {
- strncpy(gate_buf, gate, 15);
+ strscpy(gate_buf, gate, sizeof(gate_buf));
args = setup_args;
}
else args = nosetup_args;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 982b777eadc7..ad478a2b49e2 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,7 +28,6 @@ config X86_64
select ARCH_HAS_GIGANTIC_PAGE
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_PER_VMA_LOCK
- select ARCH_USE_CMPXCHG_LOCKREF
select HAVE_ARCH_SOFT_DIRTY
select MODULES_USE_ELF_RELA
select NEED_DMA_MAP_STATE
@@ -118,6 +117,7 @@ config X86
select ARCH_SUPPORTS_LTO_CLANG
select ARCH_SUPPORTS_LTO_CLANG_THIN
select ARCH_USE_BUILTIN_BSWAP
+ select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS
select ARCH_USE_QUEUED_SPINLOCKS
@@ -1534,6 +1534,7 @@ config NUMA
depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
default y if X86_BIGSMP
select USE_PERCPU_NUMA_NODE_ID
+ select OF_NUMA if OF
help
Enable NUMA (Non-Uniform Memory Access) support.
@@ -1945,6 +1946,7 @@ config EFI
select UCS2_STRING
select EFI_RUNTIME_WRAPPERS
select ARCH_USE_MEMREMAP_PROT
+ select EFI_RUNTIME_MAP if KEXEC_CORE
help
This enables the kernel to use EFI runtime services that are
available (such as the EFI variable services).
@@ -2020,7 +2022,6 @@ config EFI_MAX_FAKE_MEM
config EFI_RUNTIME_MAP
bool "Export EFI runtime maps to sysfs" if EXPERT
depends on EFI
- default KEXEC_CORE
help
Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
That memory map is required by the 2nd kernel to set up EFI virtual
@@ -2954,6 +2955,15 @@ config IA32_EMULATION
64-bit kernel. You should likely turn this on, unless you're
100% sure that you don't have any 32-bit programs left.
+config IA32_EMULATION_DEFAULT_DISABLED
+ bool "IA32 emulation disabled by default"
+ default n
+ depends on IA32_EMULATION
+ help
+ Make IA32 emulation disabled by default. This prevents loading 32-bit
+ processes and access to 32-bit syscalls. If unsure, leave it to its
+ default value.
+
config X86_X32_ABI
bool "x32 ABI for 64-bit mode"
depends on X86_64
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 5bfe5caaa444..76da1e8b3eb0 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -43,7 +43,7 @@ endif
# How to compile the 16-bit code. Note we always compile for -march=i386;
# that way we can complain to the user if the CPU is insufficient.
-REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
+REALMODE_CFLAGS := -std=gnu11 -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \
-Wall -Wstrict-prototypes -march=i386 -mregparm=3 \
-fno-strict-aliasing -fomit-frame-pointer -fno-pic \
-mno-mmx -mno-sse $(call cc-option,-fcf-protection=none)
@@ -81,6 +81,7 @@ ifeq ($(CONFIG_X86_KERNEL_IBT),y)
# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816
#
KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables)
+KBUILD_RUSTFLAGS += -Zcf-protection=branch -Zno-jump-tables
else
KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none)
endif
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index f33e45ed1437..3cece19b7473 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c
index 9caf89063e77..55c98fdd67d2 100644
--- a/arch/x86/boot/compressed/acpi.c
+++ b/arch/x86/boot/compressed/acpi.c
@@ -30,13 +30,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len)
* Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to
* ACPI_TABLE_GUID because it has more features.
*/
- rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len,
+ rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len,
ACPI_20_TABLE_GUID);
if (rsdp_addr)
return (acpi_physical_address)rsdp_addr;
/* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */
- rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len,
+ rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len,
ACPI_TABLE_GUID);
if (rsdp_addr)
return (acpi_physical_address)rsdp_addr;
@@ -56,15 +56,15 @@ static acpi_physical_address efi_get_rsdp_addr(void)
enum efi_type et;
int ret;
- et = efi_get_type(boot_params);
+ et = efi_get_type(boot_params_ptr);
if (et == EFI_TYPE_NONE)
return 0;
- systab_pa = efi_get_system_table(boot_params);
+ systab_pa = efi_get_system_table(boot_params_ptr);
if (!systab_pa)
error("EFI support advertised, but unable to locate system table.");
- ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len);
+ ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len);
if (ret || !cfg_tbl_pa)
error("EFI config table not found.");
@@ -156,7 +156,7 @@ acpi_physical_address get_rsdp_addr(void)
{
acpi_physical_address pa;
- pa = boot_params->acpi_rsdp_addr;
+ pa = boot_params_ptr->acpi_rsdp_addr;
if (!pa)
pa = efi_get_rsdp_addr();
@@ -210,7 +210,7 @@ static unsigned long get_acpi_srat_table(void)
rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp();
if (!rsdp)
rsdp = (struct acpi_table_rsdp *)(long)
- boot_params->acpi_rsdp_addr;
+ boot_params_ptr->acpi_rsdp_addr;
if (!rsdp)
return 0;
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index f1add5d85da9..c1bb180973ea 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -14,9 +14,9 @@ static inline char rdfs8(addr_t addr)
#include "../cmdline.c"
unsigned long get_cmd_line_ptr(void)
{
- unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr;
+ unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr;
- cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32;
+ cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32;
return cmd_line_ptr;
}
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index bcc956c17872..473ba59b82a8 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context)
return NULL;
}
+ /* Consumed more tables than expected? */
+ if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) {
+ debug_putstr("pgt_buf running low in " __FILE__ "\n");
+ debug_putstr("Need to raise BOOT_PGT_SIZE?\n");
+ debug_putaddr(pages->pgt_buf_offset);
+ debug_putaddr(pages->pgt_buf_size);
+ }
+
entry = pages->pgt_buf + pages->pgt_buf_offset;
pages->pgt_buf_offset += PAGE_SIZE;
@@ -151,8 +159,9 @@ void initialize_identity_maps(void *rmode)
* or does not touch all the pages covering them.
*/
kernel_add_identity_map((unsigned long)_head, (unsigned long)_end);
- boot_params = rmode;
- kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1));
+ boot_params_ptr = rmode;
+ kernel_add_identity_map((unsigned long)boot_params_ptr,
+ (unsigned long)(boot_params_ptr + 1));
cmdline = get_cmd_line_ptr();
kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE);
@@ -160,7 +169,7 @@ void initialize_identity_maps(void *rmode)
* Also map the setup_data entries passed via boot_params in case they
* need to be accessed by uncompressed kernel via the identity mapping.
*/
- sd = (struct setup_data *)boot_params->hdr.setup_data;
+ sd = (struct setup_data *)boot_params_ptr->hdr.setup_data;
while (sd) {
unsigned long sd_addr = (unsigned long)sd;
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 9193acf0e9cd..dec961c6d16a 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -63,7 +63,7 @@ static unsigned long get_boot_seed(void)
unsigned long hash = 0;
hash = rotate_xor(hash, build_str, sizeof(build_str));
- hash = rotate_xor(hash, boot_params, sizeof(*boot_params));
+ hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr));
return hash;
}
@@ -383,7 +383,7 @@ static void handle_mem_options(void)
static void mem_avoid_init(unsigned long input, unsigned long input_size,
unsigned long output)
{
- unsigned long init_size = boot_params->hdr.init_size;
+ unsigned long init_size = boot_params_ptr->hdr.init_size;
u64 initrd_start, initrd_size;
unsigned long cmd_line, cmd_line_size;
@@ -395,10 +395,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input;
/* Avoid initrd. */
- initrd_start = (u64)boot_params->ext_ramdisk_image << 32;
- initrd_start |= boot_params->hdr.ramdisk_image;
- initrd_size = (u64)boot_params->ext_ramdisk_size << 32;
- initrd_size |= boot_params->hdr.ramdisk_size;
+ initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32;
+ initrd_start |= boot_params_ptr->hdr.ramdisk_image;
+ initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32;
+ initrd_size |= boot_params_ptr->hdr.ramdisk_size;
mem_avoid[MEM_AVOID_INITRD].start = initrd_start;
mem_avoid[MEM_AVOID_INITRD].size = initrd_size;
/* No need to set mapping for initrd, it will be handled in VO. */
@@ -413,8 +413,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
}
/* Avoid boot parameters. */
- mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params;
- mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params);
+ mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr;
+ mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr);
/* We don't need to set a mapping for setup_data. */
@@ -447,7 +447,7 @@ static bool mem_avoid_overlap(struct mem_vector *img,
}
/* Avoid all entries in the setup_data linked list. */
- ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
+ ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
while (ptr) {
struct mem_vector avoid;
@@ -706,7 +706,7 @@ static inline bool memory_type_is_free(efi_memory_desc_t *md)
static bool
process_efi_entries(unsigned long minimum, unsigned long image_size)
{
- struct efi_info *e = &boot_params->efi_info;
+ struct efi_info *e = &boot_params_ptr->efi_info;
bool efi_mirror_found = false;
struct mem_vector region;
efi_memory_desc_t *md;
@@ -777,8 +777,8 @@ static void process_e820_entries(unsigned long minimum,
struct boot_e820_entry *entry;
/* Verify potential e820 positions, appending to slots list. */
- for (i = 0; i < boot_params->e820_entries; i++) {
- entry = &boot_params->e820_table[i];
+ for (i = 0; i < boot_params_ptr->e820_entries; i++) {
+ entry = &boot_params_ptr->e820_table[i];
/* Skip non-RAM entries. */
if (entry->type != E820_TYPE_RAM)
continue;
@@ -852,7 +852,7 @@ void choose_random_location(unsigned long input,
return;
}
- boot_params->hdr.loadflags |= KASLR_FLAG;
+ boot_params_ptr->hdr.loadflags |= KASLR_FLAG;
if (IS_ENABLED(CONFIG_X86_32))
mem_limit = KERNEL_IMAGE_SIZE;
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c
index 3c1609245f2a..b3c3a4be7471 100644
--- a/arch/x86/boot/compressed/mem.c
+++ b/arch/x86/boot/compressed/mem.c
@@ -54,17 +54,17 @@ bool init_unaccepted_memory(void)
enum efi_type et;
int ret;
- et = efi_get_type(boot_params);
+ et = efi_get_type(boot_params_ptr);
if (et == EFI_TYPE_NONE)
return false;
- ret = efi_get_conf_table(boot_params, &cfg_table_pa, &cfg_table_len);
+ ret = efi_get_conf_table(boot_params_ptr, &cfg_table_pa, &cfg_table_len);
if (ret) {
warn("EFI config table not found.");
return false;
}
- table = (void *)efi_find_vendor_table(boot_params, cfg_table_pa,
+ table = (void *)efi_find_vendor_table(boot_params_ptr, cfg_table_pa,
cfg_table_len, guid);
if (!table)
return false;
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index f711f2a85862..b99e08e6815b 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -46,7 +46,7 @@ void *memmove(void *dest, const void *src, size_t n);
/*
* This is set up by the setup-routine at boot-time
*/
-struct boot_params *boot_params;
+struct boot_params *boot_params_ptr;
struct port_io_ops pio_ops;
@@ -132,8 +132,8 @@ void __putstr(const char *s)
if (lines == 0 || cols == 0)
return;
- x = boot_params->screen_info.orig_x;
- y = boot_params->screen_info.orig_y;
+ x = boot_params_ptr->screen_info.orig_x;
+ y = boot_params_ptr->screen_info.orig_y;
while ((c = *s++) != '\0') {
if (c == '\n') {
@@ -154,8 +154,8 @@ void __putstr(const char *s)
}
}
- boot_params->screen_info.orig_x = x;
- boot_params->screen_info.orig_y = y;
+ boot_params_ptr->screen_info.orig_x = x;
+ boot_params_ptr->screen_info.orig_y = y;
pos = (x + cols * y) * 2; /* Update cursor position */
outb(14, vidport);
@@ -382,14 +382,14 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
size_t entry_offset;
/* Retain x86 boot parameters pointer passed from startup_32/64. */
- boot_params = rmode;
+ boot_params_ptr = rmode;
/* Clear flags intended for solely in-kernel use. */
- boot_params->hdr.loadflags &= ~KASLR_FLAG;
+ boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG;
- sanitize_boot_params(boot_params);
+ sanitize_boot_params(boot_params_ptr);
- if (boot_params->screen_info.orig_video_mode == 7) {
+ if (boot_params_ptr->screen_info.orig_video_mode == 7) {
vidmem = (char *) 0xb0000;
vidport = 0x3b4;
} else {
@@ -397,8 +397,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
vidport = 0x3d4;
}
- lines = boot_params->screen_info.orig_video_lines;
- cols = boot_params->screen_info.orig_video_cols;
+ lines = boot_params_ptr->screen_info.orig_video_lines;
+ cols = boot_params_ptr->screen_info.orig_video_cols;
init_default_io_ops();
@@ -417,7 +417,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output)
* so that early debugging output from the RSDP parsing code can be
* collected.
*/
- boot_params->acpi_rsdp_addr = get_rsdp_addr();
+ boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr();
debug_putstr("early console in extract_kernel\n");
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index cc70d3fb9049..c0d502bd8716 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -61,7 +61,6 @@ extern memptr free_mem_ptr;
extern memptr free_mem_end_ptr;
void *malloc(int size);
void free(void *where);
-extern struct boot_params *boot_params;
void __putstr(const char *s);
void __puthex(unsigned long value);
#define error_putstr(__x) __putstr(__x)
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index 7939eb6e6ce9..51f957b24ba7 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -28,7 +28,6 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
*/
unsigned long *trampoline_32bit __section(".data");
-extern struct boot_params *boot_params;
int cmdline_find_option_bool(const char *option);
static unsigned long find_trampoline_placement(void)
@@ -49,7 +48,7 @@ static unsigned long find_trampoline_placement(void)
*
* Only look for values in the legacy ROM for non-EFI system.
*/
- signature = (char *)&boot_params->efi_info.efi_loader_signature;
+ signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature;
if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) &&
strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) {
ebda_start = *(unsigned short *)0x40e << 4;
@@ -65,10 +64,10 @@ static unsigned long find_trampoline_placement(void)
bios_start = round_down(bios_start, PAGE_SIZE);
/* Find the first usable memory region under bios_start. */
- for (i = boot_params->e820_entries - 1; i >= 0; i--) {
+ for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) {
unsigned long new = bios_start;
- entry = &boot_params->e820_table[i];
+ entry = &boot_params_ptr->e820_table[i];
/* Skip all entries above bios_start. */
if (bios_start <= entry->addr)
@@ -107,7 +106,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
bool l5_required = false;
/* Initialize boot_params. Required for cmdline_find_option_bool(). */
- boot_params = bp;
+ boot_params_ptr = bp;
/*
* Check if LA57 is desired and supported.
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index dc8c876fbd8f..454acd7a2daf 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -25,7 +25,7 @@
#include "error.h"
#include "../msr.h"
-struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
+static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
struct ghcb *boot_ghcb;
/*
@@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
return ES_OK;
}
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+ return false;
+}
+
#undef __init
#define __init
@@ -605,7 +615,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt)
* accessed after switchover.
*/
if (sev_snp_enabled()) {
- unsigned long cc_info_pa = boot_params->cc_blob_address;
+ unsigned long cc_info_pa = boot_params_ptr->cc_blob_address;
struct cc_blob_sev_info *cc_info;
kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info));
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index b22f34b8684a..083ec6d7722a 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -43,11 +43,13 @@ SECTIONS
*(.rodata.*)
_erodata = . ;
}
- .data : {
+ .data : ALIGN(0x1000) {
_data = . ;
*(.data)
*(.data.*)
- *(.bss.efistub)
+
+ /* Add 4 bytes of extra space for a CRC-32 checksum */
+ . = ALIGN(. + 4, 0x200);
_edata = . ;
}
. = ALIGN(L1_CACHE_BYTES);
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b04ca8e2b213..b2771710ed98 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -36,66 +36,20 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
#define ROOT_RDONLY 1
#endif
+ .set salign, 0x1000
+ .set falign, 0x200
+
.code16
.section ".bstext", "ax"
-
- .global bootsect_start
-bootsect_start:
#ifdef CONFIG_EFI_STUB
# "MZ", MS-DOS header
.word MZ_MAGIC
-#endif
-
- # Normalize the start address
- ljmp $BOOTSEG, $start2
-
-start2:
- movw %cs, %ax
- movw %ax, %ds
- movw %ax, %es
- movw %ax, %ss
- xorw %sp, %sp
- sti
- cld
-
- movw $bugger_off_msg, %si
-
-msg_loop:
- lodsb
- andb %al, %al
- jz bs_die
- movb $0xe, %ah
- movw $7, %bx
- int $0x10
- jmp msg_loop
-
-bs_die:
- # Allow the user to press a key, then reboot
- xorw %ax, %ax
- int $0x16
- int $0x19
-
- # int 0x19 should never return. In case it does anyway,
- # invoke the BIOS reset code...
- ljmp $0xf000,$0xfff0
-
-#ifdef CONFIG_EFI_STUB
.org 0x38
#
# Offset to the PE header.
#
.long LINUX_PE_MAGIC
.long pe_header
-#endif /* CONFIG_EFI_STUB */
-
- .section ".bsdata", "a"
-bugger_off_msg:
- .ascii "Use a boot loader.\r\n"
- .ascii "\n"
- .ascii "Remove disk and press any key to reboot...\r\n"
- .byte 0
-
-#ifdef CONFIG_EFI_STUB
pe_header:
.long PE_MAGIC
@@ -124,30 +78,26 @@ optional_header:
.byte 0x02 # MajorLinkerVersion
.byte 0x14 # MinorLinkerVersion
- # Filled in by build.c
- .long 0 # SizeOfCode
+ .long ZO__data # SizeOfCode
- .long 0 # SizeOfInitializedData
+ .long ZO__end - ZO__data # SizeOfInitializedData
.long 0 # SizeOfUninitializedData
- # Filled in by build.c
- .long 0x0000 # AddressOfEntryPoint
+ .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint
- .long 0x0200 # BaseOfCode
+ .long setup_size # BaseOfCode
#ifdef CONFIG_X86_32
.long 0 # data
#endif
extra_header_fields:
- # PE specification requires ImageBase to be 64k aligned
- .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff
#ifdef CONFIG_X86_32
- .long image_base # ImageBase
+ .long 0 # ImageBase
#else
- .quad image_base # ImageBase
+ .quad 0 # ImageBase
#endif
- .long 0x20 # SectionAlignment
- .long 0x20 # FileAlignment
+ .long salign # SectionAlignment
+ .long falign # FileAlignment
.word 0 # MajorOperatingSystemVersion
.word 0 # MinorOperatingSystemVersion
.word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion
@@ -156,12 +106,10 @@ extra_header_fields:
.word 0 # MinorSubsystemVersion
.long 0 # Win32VersionValue
- #
- # The size of the bzImage is written in tools/build.c
- #
- .long 0 # SizeOfImage
+ .long setup_size + ZO__end + pecompat_vsize
+ # SizeOfImage
- .long 0x200 # SizeOfHeaders
+ .long salign # SizeOfHeaders
.long 0 # CheckSum
.word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application)
#ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES
@@ -192,87 +140,78 @@ extra_header_fields:
# Section table
section_table:
- #
- # The offset & size fields are filled in by build.c.
- #
.ascii ".setup"
.byte 0
.byte 0
- .long 0
- .long 0x0 # startup_{32,64}
- .long 0 # Size of initialized data
- # on disk
- .long 0x0 # startup_{32,64}
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
- .long IMAGE_SCN_CNT_CODE | \
- IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_EXECUTE | \
- IMAGE_SCN_ALIGN_16BYTES # Characteristics
+ .long setup_size - salign # VirtualSize
+ .long salign # VirtualAddress
+ .long pecompat_fstart - salign # SizeOfRawData
+ .long salign # PointerToRawData
- #
- # The EFI application loader requires a relocation section
- # because EFI applications must be relocatable. The .reloc
- # offset & size fields are filled in by build.c.
- #
- .ascii ".reloc"
- .byte 0
- .byte 0
- .long 0
- .long 0
- .long 0 # SizeOfRawData
- .long 0 # PointerToRawData
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
+ .long 0, 0, 0
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_DISCARDABLE | \
- IMAGE_SCN_ALIGN_1BYTES # Characteristics
+ IMAGE_SCN_MEM_DISCARDABLE # Characteristics
#ifdef CONFIG_EFI_MIXED
- #
- # The offset & size fields are filled in by build.c.
- #
.asciz ".compat"
- .long 0
- .long 0x0
- .long 0 # Size of initialized data
- # on disk
- .long 0x0
- .long 0 # PointerToRelocations
- .long 0 # PointerToLineNumbers
- .word 0 # NumberOfRelocations
- .word 0 # NumberOfLineNumbers
+
+ .long 8 # VirtualSize
+ .long setup_size + ZO__end # VirtualAddress
+ .long pecompat_fsize # SizeOfRawData
+ .long pecompat_fstart # PointerToRawData
+
+ .long 0, 0, 0
.long IMAGE_SCN_CNT_INITIALIZED_DATA | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_DISCARDABLE | \
- IMAGE_SCN_ALIGN_1BYTES # Characteristics
+ IMAGE_SCN_MEM_DISCARDABLE # Characteristics
+
+ /*
+ * Put the IA-32 machine type and the associated entry point address in
+ * the .compat section, so loaders can figure out which other execution
+ * modes this image supports.
+ */
+ .pushsection ".pecompat", "a", @progbits
+ .balign falign
+ .set pecompat_vsize, salign
+ .globl pecompat_fstart
+pecompat_fstart:
+ .byte 0x1 # Version
+ .byte 8 # Size
+ .word IMAGE_FILE_MACHINE_I386 # PE machine type
+ .long setup_size + ZO_efi32_pe_entry # Entrypoint
+ .popsection
+#else
+ .set pecompat_vsize, 0
+ .set pecompat_fstart, setup_size
#endif
-
- #
- # The offset & size fields are filled in by build.c.
- #
.ascii ".text"
.byte 0
.byte 0
.byte 0
- .long 0
- .long 0x0 # startup_{32,64}
- .long 0 # Size of initialized data
+ .long ZO__data
+ .long setup_size
+ .long ZO__data # Size of initialized data
# on disk
- .long 0x0 # startup_{32,64}
+ .long setup_size
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
.word 0 # NumberOfLineNumbers
.long IMAGE_SCN_CNT_CODE | \
IMAGE_SCN_MEM_READ | \
- IMAGE_SCN_MEM_EXECUTE | \
- IMAGE_SCN_ALIGN_16BYTES # Characteristics
+ IMAGE_SCN_MEM_EXECUTE # Characteristics
+
+ .ascii ".data\0\0\0"
+ .long ZO__end - ZO__data # VirtualSize
+ .long setup_size + ZO__data # VirtualAddress
+ .long ZO__edata - ZO__data # SizeOfRawData
+ .long setup_size + ZO__data # PointerToRawData
+
+ .long 0, 0, 0
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_WRITE # Characteristics
.set section_count, (. - section_table) / 40
#endif /* CONFIG_EFI_STUB */
@@ -286,12 +225,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */
.globl hdr
hdr:
-setup_sects: .byte 0 /* Filled in by build.c */
+ .byte setup_sects - 1
root_flags: .word ROOT_RDONLY
-syssize: .long 0 /* Filled in by build.c */
+syssize: .long ZO__edata / 16
ram_size: .word 0 /* Obsolete */
vid_mode: .word SVGA_MODE
-root_dev: .word 0 /* Filled in by build.c */
+root_dev: .word 0 /* Default to major/minor 0/0 */
boot_flag: .word 0xAA55
# offset 512, entry point
@@ -579,9 +518,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr
# define INIT_SIZE VO_INIT_SIZE
#endif
+ .macro __handover_offset
+#ifndef CONFIG_EFI_HANDOVER_PROTOCOL
+ .long 0
+#elif !defined(CONFIG_X86_64)
+ .long ZO_efi32_stub_entry
+#else
+ /* Yes, this is really how we defined it :( */
+ .long ZO_efi64_stub_entry - 0x200
+#ifdef CONFIG_EFI_MIXED
+ .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200
+ .error "32-bit and 64-bit EFI entry points do not match"
+ .endif
+#endif
+#endif
+ .endm
+
init_size: .long INIT_SIZE # kernel initialization size
-handover_offset: .long 0 # Filled in by build.c
-kernel_info_offset: .long 0 # Filled in by build.c
+handover_offset: __handover_offset
+kernel_info_offset: .long ZO_kernel_info
# End of setup header #####################################################
diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld
index 49546c247ae2..83bb7efad8ae 100644
--- a/arch/x86/boot/setup.ld
+++ b/arch/x86/boot/setup.ld
@@ -10,10 +10,11 @@ ENTRY(_start)
SECTIONS
{
. = 0;
- .bstext : { *(.bstext) }
- .bsdata : { *(.bsdata) }
+ .bstext : {
+ *(.bstext)
+ . = 495;
+ } =0xffffffff
- . = 495;
.header : { *(.header) }
.entrytext : { *(.entrytext) }
.inittext : { *(.inittext) }
@@ -35,11 +36,16 @@ SECTIONS
. = ALIGN(16);
.data : { *(.data*) }
+ .pecompat : { *(.pecompat) }
+ PROVIDE(pecompat_fsize = setup_size - pecompat_fstart);
+
.signature : {
setup_sig = .;
LONG(0x5a5aaa55)
- }
+ setup_size = ALIGN(ABSOLUTE(.), 4096);
+ setup_sects = ABSOLUTE(setup_size / 512);
+ }
. = ALIGN(16);
.bss :
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index bd247692b701..10311d77c67f 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -40,10 +40,6 @@ typedef unsigned char u8;
typedef unsigned short u16;
typedef unsigned int u32;
-#define DEFAULT_MAJOR_ROOT 0
-#define DEFAULT_MINOR_ROOT 0
-#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT)
-
/* Minimal number of setup sectors */
#define SETUP_SECT_MIN 5
#define SETUP_SECT_MAX 64
@@ -51,22 +47,7 @@ typedef unsigned int u32;
/* This must be large enough to hold the entire setup */
u8 buf[SETUP_SECT_MAX*512];
-#define PECOFF_RELOC_RESERVE 0x20
-
-#ifdef CONFIG_EFI_MIXED
-#define PECOFF_COMPAT_RESERVE 0x20
-#else
-#define PECOFF_COMPAT_RESERVE 0x0
-#endif
-
-static unsigned long efi32_stub_entry;
-static unsigned long efi64_stub_entry;
-static unsigned long efi_pe_entry;
-static unsigned long efi32_pe_entry;
-static unsigned long kernel_info;
-static unsigned long startup_64;
-static unsigned long _ehead;
-static unsigned long _end;
+static unsigned long _edata;
/*----------------------------------------------------------------------*/
@@ -152,180 +133,6 @@ static void usage(void)
die("Usage: build setup system zoffset.h image");
}
-#ifdef CONFIG_EFI_STUB
-
-static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset)
-{
- unsigned int pe_header;
- unsigned short num_sections;
- u8 *section;
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
- num_sections = get_unaligned_le16(&buf[pe_header + 6]);
-
-#ifdef CONFIG_X86_32
- section = &buf[pe_header + 0xa8];
-#else
- section = &buf[pe_header + 0xb8];
-#endif
-
- while (num_sections > 0) {
- if (strncmp((char*)section, section_name, 8) == 0) {
- /* section header size field */
- put_unaligned_le32(size, section + 0x8);
-
- /* section header vma field */
- put_unaligned_le32(vma, section + 0xc);
-
- /* section header 'size of initialised data' field */
- put_unaligned_le32(datasz, section + 0x10);
-
- /* section header 'file offset' field */
- put_unaligned_le32(offset, section + 0x14);
-
- break;
- }
- section += 0x28;
- num_sections--;
- }
-}
-
-static void update_pecoff_section_header(char *section_name, u32 offset, u32 size)
-{
- update_pecoff_section_header_fields(section_name, offset, size, size, offset);
-}
-
-static void update_pecoff_setup_and_reloc(unsigned int size)
-{
- u32 setup_offset = 0x200;
- u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE;
-#ifdef CONFIG_EFI_MIXED
- u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE;
-#endif
- u32 setup_size = reloc_offset - setup_offset;
-
- update_pecoff_section_header(".setup", setup_offset, setup_size);
- update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE);
-
- /*
- * Modify .reloc section contents with a single entry. The
- * relocation is applied to offset 10 of the relocation section.
- */
- put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]);
- put_unaligned_le32(10, &buf[reloc_offset + 4]);
-
-#ifdef CONFIG_EFI_MIXED
- update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE);
-
- /*
- * Put the IA-32 machine type (0x14c) and the associated entry point
- * address in the .compat section, so loaders can figure out which other
- * execution modes this image supports.
- */
- buf[compat_offset] = 0x1;
- buf[compat_offset + 1] = 0x8;
- put_unaligned_le16(0x14c, &buf[compat_offset + 2]);
- put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]);
-#endif
-}
-
-static void update_pecoff_text(unsigned int text_start, unsigned int file_sz,
- unsigned int init_sz)
-{
- unsigned int pe_header;
- unsigned int text_sz = file_sz - text_start;
- unsigned int bss_sz = init_sz - file_sz;
-
- pe_header = get_unaligned_le32(&buf[0x3c]);
-
- /*
- * The PE/COFF loader may load the image at an address which is
- * misaligned with respect to the kernel_alignment field in the setup
- * header.
- *
- * In order to avoid relocating the kernel to correct the misalignment,
- * add slack to allow the buffer to be aligned within the declared size
- * of the image.
- */
- bss_sz += CONFIG_PHYSICAL_ALIGN;
- init_sz += CONFIG_PHYSICAL_ALIGN;
-
- /*
- * Size of code: Subtract the size of the first sector (512 bytes)
- * which includes the header.
- */
- put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]);
-
- /* Size of image */
- put_unaligned_le32(init_sz, &buf[pe_header + 0x50]);
-
- /*
- * Address of entry point for PE/COFF executable
- */
- put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]);
-
- update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz,
- text_sz, text_start);
-}
-
-static int reserve_pecoff_reloc_section(int c)
-{
- /* Reserve 0x20 bytes for .reloc section */
- memset(buf+c, 0, PECOFF_RELOC_RESERVE);
- return PECOFF_RELOC_RESERVE;
-}
-
-static void efi_stub_defaults(void)
-{
- /* Defaults for old kernel */
-#ifdef CONFIG_X86_32
- efi_pe_entry = 0x10;
-#else
- efi_pe_entry = 0x210;
- startup_64 = 0x200;
-#endif
-}
-
-static void efi_stub_entry_update(void)
-{
- unsigned long addr = efi32_stub_entry;
-
-#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
-#ifdef CONFIG_X86_64
- /* Yes, this is really how we defined it :( */
- addr = efi64_stub_entry - 0x200;
-#endif
-
-#ifdef CONFIG_EFI_MIXED
- if (efi32_stub_entry != addr)
- die("32-bit and 64-bit EFI entry points do not match\n");
-#endif
-#endif
- put_unaligned_le32(addr, &buf[0x264]);
-}
-
-#else
-
-static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
-static inline void update_pecoff_text(unsigned int text_start,
- unsigned int file_sz,
- unsigned int init_sz) {}
-static inline void efi_stub_defaults(void) {}
-static inline void efi_stub_entry_update(void) {}
-
-static inline int reserve_pecoff_reloc_section(int c)
-{
- return 0;
-}
-#endif /* CONFIG_EFI_STUB */
-
-static int reserve_pecoff_compat_section(int c)
-{
- /* Reserve 0x20 bytes for .compat section */
- memset(buf+c, 0, PECOFF_COMPAT_RESERVE);
- return PECOFF_COMPAT_RESERVE;
-}
-
/*
* Parse zoffset.h and find the entry points. We could just #include zoffset.h
* but that would mean tools/build would have to be rebuilt every time. It's
@@ -354,14 +161,7 @@ static void parse_zoffset(char *fname)
p = (char *)buf;
while (p && *p) {
- PARSE_ZOFS(p, efi32_stub_entry);
- PARSE_ZOFS(p, efi64_stub_entry);
- PARSE_ZOFS(p, efi_pe_entry);
- PARSE_ZOFS(p, efi32_pe_entry);
- PARSE_ZOFS(p, kernel_info);
- PARSE_ZOFS(p, startup_64);
- PARSE_ZOFS(p, _ehead);
- PARSE_ZOFS(p, _end);
+ PARSE_ZOFS(p, _edata);
p = strchr(p, '\n');
while (p && (*p == '\r' || *p == '\n'))
@@ -371,17 +171,14 @@ static void parse_zoffset(char *fname)
int main(int argc, char ** argv)
{
- unsigned int i, sz, setup_sectors, init_sz;
+ unsigned int i, sz, setup_sectors;
int c;
- u32 sys_size;
struct stat sb;
FILE *file, *dest;
int fd;
void *kernel;
u32 crc = 0xffffffffUL;
- efi_stub_defaults();
-
if (argc != 5)
usage();
parse_zoffset(argv[3]);
@@ -403,72 +200,27 @@ int main(int argc, char ** argv)
die("Boot block hasn't got boot flag (0xAA55)");
fclose(file);
- c += reserve_pecoff_compat_section(c);
- c += reserve_pecoff_reloc_section(c);
-
/* Pad unused space with zeros */
- setup_sectors = (c + 511) / 512;
+ setup_sectors = (c + 4095) / 4096;
+ setup_sectors *= 8;
if (setup_sectors < SETUP_SECT_MIN)
setup_sectors = SETUP_SECT_MIN;
i = setup_sectors*512;
memset(buf+c, 0, i-c);
- update_pecoff_setup_and_reloc(i);
-
- /* Set the default root device */
- put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
-
/* Open and stat the kernel file */
fd = open(argv[2], O_RDONLY);
if (fd < 0)
die("Unable to open `%s': %m", argv[2]);
if (fstat(fd, &sb))
die("Unable to stat `%s': %m", argv[2]);
- sz = sb.st_size;
+ if (_edata != sb.st_size)
+ die("Unexpected file size `%s': %u != %u", argv[2], _edata,
+ sb.st_size);
+ sz = _edata - 4;
kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0);
if (kernel == MAP_FAILED)
die("Unable to mmap '%s': %m", argv[2]);
- /* Number of 16-byte paragraphs, including space for a 4-byte CRC */
- sys_size = (sz + 15 + 4) / 16;
-#ifdef CONFIG_EFI_STUB
- /*
- * COFF requires minimum 32-byte alignment of sections, and
- * adding a signature is problematic without that alignment.
- */
- sys_size = (sys_size + 1) & ~1;
-#endif
-
- /* Patch the setup code with the appropriate size parameters */
- buf[0x1f1] = setup_sectors-1;
- put_unaligned_le32(sys_size, &buf[0x1f4]);
-
- init_sz = get_unaligned_le32(&buf[0x260]);
-#ifdef CONFIG_EFI_STUB
- /*
- * The decompression buffer will start at ImageBase. When relocating
- * the compressed kernel to its end, we must ensure that the head
- * section does not get overwritten. The head section occupies
- * [i, i + _ehead), and the destination is [init_sz - _end, init_sz).
- *
- * At present these should never overlap, because 'i' is at most 32k
- * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the
- * calculation of INIT_SIZE in boot/header.S ensures that
- * 'init_sz - _end' is at least 64k.
- *
- * For future-proofing, increase init_sz if necessary.
- */
-
- if (init_sz - _end < i + _ehead) {
- init_sz = (i + _ehead + _end + 4095) & ~4095;
- put_unaligned_le32(init_sz, &buf[0x260]);
- }
-#endif
- update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz);
-
- efi_stub_entry_update();
-
- /* Update kernel_info offset. */
- put_unaligned_le32(kernel_info, &buf[0x268]);
crc = partial_crc32(buf, i, crc);
if (fwrite(buf, 1, i, dest) != i)
@@ -479,13 +231,6 @@ int main(int argc, char ** argv)
if (fwrite(kernel, 1, sz, dest) != sz)
die("Writing kernel failed");
- /* Add padding leaving 4 bytes for the checksum */
- while (sz++ < (sys_size*16) - 4) {
- crc = partial_crc32_one('\0', crc);
- if (fwrite("\0", 1, 1, dest) != 1)
- die("Writing padding failed");
- }
-
/* Write the CRC */
put_unaligned_le32(crc, buf);
if (fwrite(buf, 1, 4, dest) != 4)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 1d6b863c42b0..2e1be592c220 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -119,7 +119,7 @@ static void __noreturn tdx_panic(const char *msg)
} message;
/* VMM assumes '\0' in byte 65, if the message took all 64 bytes */
- strncpy(message.str, msg, 64);
+ strtomem_pad(message.str, msg, '\0');
args.r8 = message.r8;
args.r9 = message.r9;
diff --git a/arch/x86/configs/hardening.config b/arch/x86/configs/hardening.config
new file mode 100644
index 000000000000..7b497f3b7bc3
--- /dev/null
+++ b/arch/x86/configs/hardening.config
@@ -0,0 +1,14 @@
+# Basic kernel hardening options (specific to x86)
+
+# Modern libc no longer needs a fixed-position mapping in userspace, remove
+# it as a possible target.
+CONFIG_LEGACY_VSYSCALL_NONE=y
+
+# Enable chip-specific IOMMU support.
+CONFIG_INTEL_IOMMU=y
+CONFIG_INTEL_IOMMU_DEFAULT_ON=y
+CONFIG_INTEL_IOMMU_SVM=y
+CONFIG_AMD_IOMMU=y
+
+# Enable CET Shadow Stack for userspace.
+CONFIG_X86_USER_SHADOW_STACK=y
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 1b411bbf3cb0..73abbbdd26f8 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -281,4 +281,5 @@ CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_BOOT_PARAMS=y
CONFIG_UNWINDER_FRAME_POINTER=y
+CONFIG_DEBUG_ENTRY=y
# CONFIG_64BIT is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 409e9182bd29..61e25f6209ed 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -276,3 +276,4 @@ CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_BOOT_PARAMS=y
+CONFIG_DEBUG_ENTRY=y
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6c2826417b33..d813160b14d8 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -19,6 +19,7 @@
#include <linux/nospec.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
+#include <linux/init.h>
#ifdef CONFIG_XEN_PV
#include <xen/xen-ops.h>
@@ -70,7 +71,8 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
return false;
}
-__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
+/* Returns true to return using SYSRET, or false to use IRET */
+__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr)
{
add_random_kstack_offset();
nr = syscall_enter_from_user_mode(regs, nr);
@@ -84,6 +86,46 @@ __visible noinstr void do_syscall_64(struct pt_regs *regs, int nr)
instrumentation_end();
syscall_exit_to_user_mode(regs);
+
+ /*
+ * Check that the register state is valid for using SYSRET to exit
+ * to userspace. Otherwise use the slower but fully capable IRET
+ * exit path.
+ */
+
+ /* XEN PV guests always use the IRET path */
+ if (cpu_feature_enabled(X86_FEATURE_XENPV))
+ return false;
+
+ /* SYSRET requires RCX == RIP and R11 == EFLAGS */
+ if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags))
+ return false;
+
+ /* CS and SS must match the values set in MSR_STAR */
+ if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS))
+ return false;
+
+ /*
+ * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
+ * in kernel space. This essentially lets the user take over
+ * the kernel, since userspace controls RSP.
+ *
+ * TASK_SIZE_MAX covers all user-accessible addresses other than
+ * the deprecated vsyscall page.
+ */
+ if (unlikely(regs->ip >= TASK_SIZE_MAX))
+ return false;
+
+ /*
+ * SYSRET cannot restore RF. It can restore TF, but unlike IRET,
+ * restoring TF results in a trap from userspace immediately after
+ * SYSRET.
+ */
+ if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)))
+ return false;
+
+ /* Use SYSRET to exit to userspace */
+ return true;
}
#endif
@@ -96,6 +138,16 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs)
return (int)regs->orig_ax;
}
+#ifdef CONFIG_IA32_EMULATION
+bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED);
+
+static int ia32_emulation_override_cmdline(char *arg)
+{
+ return kstrtobool(arg, &__ia32_enabled);
+}
+early_param("ia32_emulation", ia32_emulation_override_cmdline);
+#endif
+
/*
* Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL.
*/
@@ -182,8 +234,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs)
return true;
}
-/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs)
{
/*
* Called using the internal vDSO SYSENTER/SYSCALL32 calling
@@ -201,41 +253,36 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs)
/* Invoke the syscall. If it failed, keep it simple: use IRET. */
if (!__do_fast_syscall_32(regs))
- return 0;
+ return false;
-#ifdef CONFIG_X86_64
/*
- * Opportunistic SYSRETL: if possible, try to return using SYSRETL.
- * SYSRETL is available on all 64-bit CPUs, so we don't need to
- * bother with SYSEXIT.
- *
- * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
- * because the ECX fixup above will ensure that this is essentially
- * never the case.
- */
- return regs->cs == __USER32_CS && regs->ss == __USER_DS &&
- regs->ip == landing_pad &&
- (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0;
-#else
- /*
- * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT.
- *
- * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP,
- * because the ECX fixup above will ensure that this is essentially
- * never the case.
- *
- * We don't allow syscalls at all from VM86 mode, but we still
- * need to check VM, because we might be returning from sys_vm86.
+ * Check that the register state is valid for using SYSRETL/SYSEXIT
+ * to exit to userspace. Otherwise use the slower but fully capable
+ * IRET exit path.
*/
- return static_cpu_has(X86_FEATURE_SEP) &&
- regs->cs == __USER_CS && regs->ss == __USER_DS &&
- regs->ip == landing_pad &&
- (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0;
-#endif
+
+ /* XEN PV guests always use the IRET path */
+ if (cpu_feature_enabled(X86_FEATURE_XENPV))
+ return false;
+
+ /* EIP must point to the VDSO landing pad */
+ if (unlikely(regs->ip != landing_pad))
+ return false;
+
+ /* CS and SS must match the values set in MSR_STAR */
+ if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS))
+ return false;
+
+ /* If the TF, RF, or VM flags are set, use IRET */
+ if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)))
+ return false;
+
+ /* Use SYSRETL/SYSEXIT to exit to userspace */
+ return true;
}
-/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */
-__visible noinstr long do_SYSENTER_32(struct pt_regs *regs)
+/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */
+__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs)
{
/* SYSENTER loses RSP, but the vDSO saved it in RBP. */
regs->sp = regs->bp;
@@ -294,7 +341,7 @@ static void __xen_pv_evtchn_do_upcall(struct pt_regs *regs)
inc_irq_stat(irq_hv_callback_count);
- xen_hvm_evtchn_do_upcall();
+ xen_evtchn_do_upcall();
set_irq_regs(old_regs);
}
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index bfb7bcb362bc..8c8d38f0cb1d 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -3,8 +3,8 @@
* Common place for both 32- and 64-bit entry routines.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
-#include <asm/export.h>
#include <asm/msr-index.h>
.pushsection .noinstr.text, "ax"
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 6e6af42e044a..c73047bf9f4b 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -837,7 +837,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
movl %esp, %eax
call do_SYSENTER_32
- testl %eax, %eax
+ testb %al, %al
jz .Lsyscall_32_done
STACKLEAK_ERASE
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 43606de22511..de6469dffe3a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -18,6 +18,7 @@
* - SYM_FUNC_START/END:Define functions in the symbol table.
* - idtentry: Define exception entry points.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
@@ -34,7 +35,6 @@
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/pgtable_types.h>
-#include <asm/export.h>
#include <asm/frame.h>
#include <asm/trapnr.h>
#include <asm/nospec-branch.h>
@@ -126,70 +126,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
* In the Xen PV case we must use iret anyway.
*/
- ALTERNATIVE "", "jmp swapgs_restore_regs_and_return_to_usermode", \
- X86_FEATURE_XENPV
-
- movq RCX(%rsp), %rcx
- movq RIP(%rsp), %r11
-
- cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */
- jne swapgs_restore_regs_and_return_to_usermode
-
- /*
- * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
- * in kernel space. This essentially lets the user take over
- * the kernel, since userspace controls RSP.
- *
- * If width of "canonical tail" ever becomes variable, this will need
- * to be updated to remain correct on both old and new CPUs.
- *
- * Change top bits to match most significant bit (47th or 56th bit
- * depending on paging mode) in the address.
- */
-#ifdef CONFIG_X86_5LEVEL
- ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
- "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
-#else
- shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
- sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
-#endif
-
- /* If this changed %rcx, it was not canonical */
- cmpq %rcx, %r11
- jne swapgs_restore_regs_and_return_to_usermode
-
- cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */
- jne swapgs_restore_regs_and_return_to_usermode
-
- movq R11(%rsp), %r11
- cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */
- jne swapgs_restore_regs_and_return_to_usermode
-
- /*
- * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
- * restore RF properly. If the slowpath sets it for whatever reason, we
- * need to restore it correctly.
- *
- * SYSRET can restore TF, but unlike IRET, restoring TF results in a
- * trap from userspace immediately after SYSRET. This would cause an
- * infinite loop whenever #DB happens with register state that satisfies
- * the opportunistic SYSRET conditions. For example, single-stepping
- * this user code:
- *
- * movq $stuck_here, %rcx
- * pushfq
- * popq %r11
- * stuck_here:
- *
- * would never get past 'stuck_here'.
- */
- testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
- jnz swapgs_restore_regs_and_return_to_usermode
-
- /* nothing to check for RSP */
-
- cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */
- jne swapgs_restore_regs_and_return_to_usermode
+ ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
+ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
/*
* We win! This label is here just for ease of understanding
@@ -1163,8 +1101,8 @@ SYM_CODE_START(asm_exc_nmi)
* anyway.
*
* To handle this case we do the following:
- * Check the a special location on the stack that contains
- * a variable that is set when NMIs are executing.
+ * Check a special location on the stack that contains a
+ * variable that is set when NMIs are executing.
* The interrupted task's stack is also checked to see if it
* is an NMI stack.
* If the variable is not set and the stack is not the NMI
@@ -1237,7 +1175,6 @@ SYM_CODE_START(asm_exc_nmi)
*/
movq %rsp, %rdi
- movq $-1, %rsi
call exc_nmi
/*
@@ -1295,8 +1232,8 @@ SYM_CODE_START(asm_exc_nmi)
* end_repeat_nmi, then we are a nested NMI. We must not
* modify the "iret" frame because it's being written by
* the outer NMI. That's okay; the outer NMI handler is
- * about to about to call exc_nmi() anyway, so we can just
- * resume the outer NMI.
+ * about to call exc_nmi() anyway, so we can just resume
+ * the outer NMI.
*/
movq $repeat_nmi, %rdx
@@ -1451,7 +1388,6 @@ end_repeat_nmi:
UNWIND_HINT_REGS
movq %rsp, %rdi
- movq $-1, %rsi
call exc_nmi
/* Always restore stashed SPEC_CTRL value (see paranoid_entry) */
@@ -1511,18 +1447,16 @@ nmi_restore:
iretq
SYM_CODE_END(asm_exc_nmi)
-#ifndef CONFIG_IA32_EMULATION
/*
* This handles SYSCALL from 32-bit code. There is no way to program
* MSRs to fully disable 32-bit SYSCALL.
*/
-SYM_CODE_START(ignore_sysret)
+SYM_CODE_START(entry_SYSCALL32_ignore)
UNWIND_HINT_END_OF_STACK
ENDBR
mov $-ENOSYS, %eax
sysretl
-SYM_CODE_END(ignore_sysret)
-#endif
+SYM_CODE_END(entry_SYSCALL32_ignore)
.pushsection .text, "ax"
__FUNC_ALIGN
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 70150298f8bd..27c05d08558a 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -118,9 +118,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
movq %rsp, %rdi
call do_SYSENTER_32
- /* XEN PV guests always use IRET path */
- ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
- "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
jmp sysret32_from_system_call
.Lsysenter_fix_flags:
@@ -212,13 +209,15 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
movq %rsp, %rdi
call do_fast_syscall_32
+
+sysret32_from_system_call:
/* XEN PV guests always use IRET path */
- ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \
+ ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \
"jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
- /* Opportunistic SYSRET */
-sysret32_from_system_call:
/*
+ * Opportunistic SYSRET
+ *
* We are not going to return to userspace from the trampoline
* stack. So let's erase the thread stack right now.
*/
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 2d0b1bd866ea..31c48bc2c3d8 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -457,3 +457,6 @@
450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node
451 i386 cachestat sys_cachestat
452 i386 fchmodat2 sys_fchmodat2
+454 i386 futex_wake sys_futex_wake
+455 i386 futex_wait sys_futex_wait
+456 i386 futex_requeue sys_futex_requeue
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 1d6eee30eceb..a577bb27c16d 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -375,6 +375,9 @@
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
453 64 map_shadow_stack sys_map_shadow_stack
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index ff6e7003da97..0103e103a657 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -4,9 +4,9 @@
* Copyright 2008 by Steven Rostedt, Red Hat, Inc
* (inspired by Andi Kleen's thunk_64.S)
*/
+ #include <linux/export.h>
#include <linux/linkage.h>
#include <asm/asm.h>
- #include <asm/export.h>
/* put return address in eax (arg1) */
.macro THUNK name, func, put_ret_addr_in_eax=0
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 27b5da2111ac..416b400f39db 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -4,10 +4,10 @@
* disturbance of register allocation in some inline assembly constructs.
* Copyright 2001,2002 by Andi Kleen, SuSE Labs.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include "calling.h"
#include <asm/asm.h>
-#include <asm/export.h>
/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
.macro THUNK name, func
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 6a1821bd7d5e..83c0afb7c741 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -42,7 +42,8 @@ vdso_img-$(VDSO64-y) += 64
vdso_img-$(VDSOX32-y) += x32
vdso_img-$(VDSO32-y) += 32
-obj-$(VDSO32-y) += vdso32-setup.o
+obj-$(VDSO32-y) += vdso32-setup.o
+OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F)
diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S
index d77d278ee9dd..37a3d4c02366 100644
--- a/arch/x86/entry/vdso/vsgx.S
+++ b/arch/x86/entry/vdso/vsgx.S
@@ -1,7 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/linkage.h>
-#include <asm/export.h>
#include <asm/errno.h>
#include <asm/enclu.h>
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index abadd5f23425..e24976593a29 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu)
/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
- /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask);
+ /*
+ * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
+ * and PerfCntrGLobalStatus.PerfCntrOvfl
+ */
+ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+ GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
}
static int amd_pmu_cpu_prepare(int cpu)
@@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu)
int i, nb_id;
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
+ amd_pmu_cpu_reset(cpu);
if (!x86_pmu.amd_nb_constraints)
return;
@@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu)
cpuc->amd_nb->nb_id = nb_id;
cpuc->amd_nb->refcnt++;
-
- amd_pmu_cpu_reset(cpu);
}
static void amd_pmu_cpu_dead(int cpu)
@@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu)
kfree(cpuhw->lbr_sel);
cpuhw->lbr_sel = NULL;
+ amd_pmu_cpu_reset(cpu);
if (!x86_pmu.amd_nb_constraints)
return;
@@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu)
cpuhw->amd_nb = NULL;
}
-
- amd_pmu_cpu_reset(cpu);
}
static inline void amd_pmu_set_global_ctl(u64 ctl)
@@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
struct hw_perf_event *hwc;
struct perf_event *event;
int handled = 0, idx;
- u64 status, mask;
+ u64 reserved, status, mask;
bool pmu_enabled;
/*
@@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
status &= ~GLOBAL_STATUS_LBRS_FROZEN;
}
+ reserved = status & ~amd_pmu_global_cntr_mask;
+ if (reserved)
+ pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n",
+ reserved);
+
+ /* Clear any reserved bits set by buggy microcode */
+ status &= amd_pmu_global_cntr_mask;
+
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
if (!test_bit(idx, cpuc->active_mask))
continue;
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 83f15fe411b3..5bf03c575812 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -26,57 +26,66 @@
#define RDPMC_BASE_LLC 10
#define COUNTER_SHIFT 16
+#define UNCORE_NAME_LEN 16
+#define UNCORE_GROUP_MAX 256
#undef pr_fmt
#define pr_fmt(fmt) "amd_uncore: " fmt
static int pmu_version;
-static int num_counters_llc;
-static int num_counters_nb;
-static bool l3_mask;
-static HLIST_HEAD(uncore_unused_list);
-
-struct amd_uncore {
- int id;
+struct amd_uncore_ctx {
int refcnt;
int cpu;
+ struct perf_event **events;
+ struct hlist_node node;
+};
+
+struct amd_uncore_pmu {
+ char name[UNCORE_NAME_LEN];
int num_counters;
int rdpmc_base;
u32 msr_base;
- cpumask_t *active_mask;
- struct pmu *pmu;
- struct perf_event **events;
- struct hlist_node node;
+ int group;
+ cpumask_t active_mask;
+ struct pmu pmu;
+ struct amd_uncore_ctx * __percpu *ctx;
};
-static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_llc;
+enum {
+ UNCORE_TYPE_DF,
+ UNCORE_TYPE_L3,
+ UNCORE_TYPE_UMC,
-static struct pmu amd_nb_pmu;
-static struct pmu amd_llc_pmu;
+ UNCORE_TYPE_MAX
+};
-static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_llc_active_mask;
+union amd_uncore_info {
+ struct {
+ u64 aux_data:32; /* auxiliary data */
+ u64 num_pmcs:8; /* number of counters */
+ u64 gid:8; /* group id */
+ u64 cid:8; /* context id */
+ } split;
+ u64 full;
+};
-static bool is_nb_event(struct perf_event *event)
-{
- return event->pmu->type == amd_nb_pmu.type;
-}
+struct amd_uncore {
+ union amd_uncore_info * __percpu info;
+ struct amd_uncore_pmu *pmus;
+ unsigned int num_pmus;
+ bool init_done;
+ void (*scan)(struct amd_uncore *uncore, unsigned int cpu);
+ int (*init)(struct amd_uncore *uncore, unsigned int cpu);
+ void (*move)(struct amd_uncore *uncore, unsigned int cpu);
+ void (*free)(struct amd_uncore *uncore, unsigned int cpu);
+};
-static bool is_llc_event(struct perf_event *event)
-{
- return event->pmu->type == amd_llc_pmu.type;
-}
+static struct amd_uncore uncores[UNCORE_TYPE_MAX];
-static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
+static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
{
- if (is_nb_event(event) && amd_uncore_nb)
- return *per_cpu_ptr(amd_uncore_nb, event->cpu);
- else if (is_llc_event(event) && amd_uncore_llc)
- return *per_cpu_ptr(amd_uncore_llc, event->cpu);
-
- return NULL;
+ return container_of(event->pmu, struct amd_uncore_pmu, pmu);
}
static void amd_uncore_read(struct perf_event *event)
@@ -91,7 +100,16 @@ static void amd_uncore_read(struct perf_event *event)
*/
prev = local64_read(&hwc->prev_count);
- rdpmcl(hwc->event_base_rdpmc, new);
+
+ /*
+ * Some uncore PMUs do not have RDPMC assignments. In such cases,
+ * read counts directly from the corresponding PERF_CTR.
+ */
+ if (hwc->event_base_rdpmc < 0)
+ rdmsrl(hwc->event_base, new);
+ else
+ rdpmcl(hwc->event_base_rdpmc, new);
+
local64_set(&hwc->prev_count, new);
delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
delta >>= COUNTER_SHIFT;
@@ -118,7 +136,7 @@ static void amd_uncore_stop(struct perf_event *event, int flags)
hwc->state |= PERF_HES_STOPPED;
if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
- amd_uncore_read(event);
+ event->pmu->read(event);
hwc->state |= PERF_HES_UPTODATE;
}
}
@@ -126,15 +144,16 @@ static void amd_uncore_stop(struct perf_event *event, int flags)
static int amd_uncore_add(struct perf_event *event, int flags)
{
int i;
- struct amd_uncore *uncore = event_to_amd_uncore(event);
+ struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+ struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
struct hw_perf_event *hwc = &event->hw;
/* are we already assigned? */
- if (hwc->idx != -1 && uncore->events[hwc->idx] == event)
+ if (hwc->idx != -1 && ctx->events[hwc->idx] == event)
goto out;
- for (i = 0; i < uncore->num_counters; i++) {
- if (uncore->events[i] == event) {
+ for (i = 0; i < pmu->num_counters; i++) {
+ if (ctx->events[i] == event) {
hwc->idx = i;
goto out;
}
@@ -142,8 +161,8 @@ static int amd_uncore_add(struct perf_event *event, int flags)
/* if not, take the first available counter */
hwc->idx = -1;
- for (i = 0; i < uncore->num_counters; i++) {
- if (cmpxchg(&uncore->events[i], NULL, event) == NULL) {
+ for (i = 0; i < pmu->num_counters; i++) {
+ if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
hwc->idx = i;
break;
}
@@ -153,23 +172,16 @@ out:
if (hwc->idx == -1)
return -EBUSY;
- hwc->config_base = uncore->msr_base + (2 * hwc->idx);
- hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx);
- hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx;
+ hwc->config_base = pmu->msr_base + (2 * hwc->idx);
+ hwc->event_base = pmu->msr_base + 1 + (2 * hwc->idx);
+ hwc->event_base_rdpmc = pmu->rdpmc_base + hwc->idx;
hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
- /*
- * The first four DF counters are accessible via RDPMC index 6 to 9
- * followed by the L3 counters from index 10 to 15. For processors
- * with more than four DF counters, the DF RDPMC assignments become
- * discontiguous as the additional counters are accessible starting
- * from index 16.
- */
- if (is_nb_event(event) && hwc->idx >= NUM_COUNTERS_NB)
- hwc->event_base_rdpmc += NUM_COUNTERS_L3;
+ if (pmu->rdpmc_base < 0)
+ hwc->event_base_rdpmc = -1;
if (flags & PERF_EF_START)
- amd_uncore_start(event, PERF_EF_RELOAD);
+ event->pmu->start(event, PERF_EF_RELOAD);
return 0;
}
@@ -177,55 +189,36 @@ out:
static void amd_uncore_del(struct perf_event *event, int flags)
{
int i;
- struct amd_uncore *uncore = event_to_amd_uncore(event);
+ struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+ struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
struct hw_perf_event *hwc = &event->hw;
- amd_uncore_stop(event, PERF_EF_UPDATE);
+ event->pmu->stop(event, PERF_EF_UPDATE);
- for (i = 0; i < uncore->num_counters; i++) {
- if (cmpxchg(&uncore->events[i], event, NULL) == event)
+ for (i = 0; i < pmu->num_counters; i++) {
+ if (cmpxchg(&ctx->events[i], event, NULL) == event)
break;
}
hwc->idx = -1;
}
-/*
- * Return a full thread and slice mask unless user
- * has provided them
- */
-static u64 l3_thread_slice_mask(u64 config)
-{
- if (boot_cpu_data.x86 <= 0x18)
- return ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) |
- ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK);
-
- /*
- * If the user doesn't specify a threadmask, they're not trying to
- * count core 0, so we enable all cores & threads.
- * We'll also assume that they want to count slice 0 if they specify
- * a threadmask and leave sliceid and enallslices unpopulated.
- */
- if (!(config & AMD64_L3_F19H_THREAD_MASK))
- return AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES |
- AMD64_L3_EN_ALL_CORES;
-
- return config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK |
- AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES |
- AMD64_L3_COREID_MASK);
-}
-
static int amd_uncore_event_init(struct perf_event *event)
{
- struct amd_uncore *uncore;
+ struct amd_uncore_pmu *pmu;
+ struct amd_uncore_ctx *ctx;
struct hw_perf_event *hwc = &event->hw;
- u64 event_mask = AMD64_RAW_EVENT_MASK_NB;
if (event->attr.type != event->pmu->type)
return -ENOENT;
- if (pmu_version >= 2 && is_nb_event(event))
- event_mask = AMD64_PERFMON_V2_RAW_EVENT_MASK_NB;
+ if (event->cpu < 0)
+ return -EINVAL;
+
+ pmu = event_to_amd_uncore_pmu(event);
+ ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
+ if (!ctx)
+ return -ENODEV;
/*
* NB and Last level cache counters (MSRs) are shared across all cores
@@ -235,28 +228,14 @@ static int amd_uncore_event_init(struct perf_event *event)
* out. So we do not support sampling and per-thread events via
* CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
*/
- hwc->config = event->attr.config & event_mask;
+ hwc->config = event->attr.config;
hwc->idx = -1;
- if (event->cpu < 0)
- return -EINVAL;
-
- /*
- * SliceMask and ThreadMask need to be set for certain L3 events.
- * For other events, the two fields do not affect the count.
- */
- if (l3_mask && is_llc_event(event))
- hwc->config |= l3_thread_slice_mask(event->attr.config);
-
- uncore = event_to_amd_uncore(event);
- if (!uncore)
- return -ENODEV;
-
/*
* since request can come in to any of the shared cores, we will remap
* to a single common cpu.
*/
- event->cpu = uncore->cpu;
+ event->cpu = ctx->cpu;
return 0;
}
@@ -278,17 +257,10 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
struct device_attribute *attr,
char *buf)
{
- cpumask_t *active_mask;
- struct pmu *pmu = dev_get_drvdata(dev);
+ struct pmu *ptr = dev_get_drvdata(dev);
+ struct amd_uncore_pmu *pmu = container_of(ptr, struct amd_uncore_pmu, pmu);
- if (pmu->type == amd_nb_pmu.type)
- active_mask = &amd_nb_active_mask;
- else if (pmu->type == amd_llc_pmu.type)
- active_mask = &amd_llc_active_mask;
- else
- return 0;
-
- return cpumap_print_to_pagebuf(true, buf, active_mask);
+ return cpumap_print_to_pagebuf(true, buf, &pmu->active_mask);
}
static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
@@ -315,7 +287,7 @@ static struct device_attribute format_attr_##_var = \
DEFINE_UNCORE_FORMAT_ATTR(event12, event, "config:0-7,32-35");
DEFINE_UNCORE_FORMAT_ATTR(event14, event, "config:0-7,32-35,59-60"); /* F17h+ DF */
DEFINE_UNCORE_FORMAT_ATTR(event14v2, event, "config:0-7,32-37"); /* PerfMonV2 DF */
-DEFINE_UNCORE_FORMAT_ATTR(event8, event, "config:0-7"); /* F17h+ L3 */
+DEFINE_UNCORE_FORMAT_ATTR(event8, event, "config:0-7"); /* F17h+ L3, PerfMonV2 UMC */
DEFINE_UNCORE_FORMAT_ATTR(umask8, umask, "config:8-15");
DEFINE_UNCORE_FORMAT_ATTR(umask12, umask, "config:8-15,24-27"); /* PerfMonV2 DF */
DEFINE_UNCORE_FORMAT_ATTR(coreid, coreid, "config:42-44"); /* F19h L3 */
@@ -325,6 +297,7 @@ DEFINE_UNCORE_FORMAT_ATTR(threadmask2, threadmask, "config:56-57"); /* F19h L
DEFINE_UNCORE_FORMAT_ATTR(enallslices, enallslices, "config:46"); /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(enallcores, enallcores, "config:47"); /* F19h L3 */
DEFINE_UNCORE_FORMAT_ATTR(sliceid, sliceid, "config:48-50"); /* F19h L3 */
+DEFINE_UNCORE_FORMAT_ATTR(rdwrmask, rdwrmask, "config:8-9"); /* PerfMonV2 UMC */
/* Common DF and NB attributes */
static struct attribute *amd_uncore_df_format_attr[] = {
@@ -341,6 +314,13 @@ static struct attribute *amd_uncore_l3_format_attr[] = {
NULL,
};
+/* Common UMC attributes */
+static struct attribute *amd_uncore_umc_format_attr[] = {
+ &format_attr_event8.attr, /* event */
+ &format_attr_rdwrmask.attr, /* rdwrmask */
+ NULL,
+};
+
/* F17h unique L3 attributes */
static struct attribute *amd_f17h_uncore_l3_format_attr[] = {
&format_attr_slicemask.attr, /* slicemask */
@@ -378,6 +358,11 @@ static struct attribute_group amd_f19h_uncore_l3_format_group = {
.is_visible = amd_f19h_uncore_is_visible,
};
+static struct attribute_group amd_uncore_umc_format_group = {
+ .name = "format",
+ .attrs = amd_uncore_umc_format_attr,
+};
+
static const struct attribute_group *amd_uncore_df_attr_groups[] = {
&amd_uncore_attr_group,
&amd_uncore_df_format_group,
@@ -396,259 +381,636 @@ static const struct attribute_group *amd_uncore_l3_attr_update[] = {
NULL,
};
-static struct pmu amd_nb_pmu = {
- .task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_df_attr_groups,
- .name = "amd_nb",
- .event_init = amd_uncore_event_init,
- .add = amd_uncore_add,
- .del = amd_uncore_del,
- .start = amd_uncore_start,
- .stop = amd_uncore_stop,
- .read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
- .module = THIS_MODULE,
+static const struct attribute_group *amd_uncore_umc_attr_groups[] = {
+ &amd_uncore_attr_group,
+ &amd_uncore_umc_format_group,
+ NULL,
};
-static struct pmu amd_llc_pmu = {
- .task_ctx_nr = perf_invalid_context,
- .attr_groups = amd_uncore_l3_attr_groups,
- .attr_update = amd_uncore_l3_attr_update,
- .name = "amd_l2",
- .event_init = amd_uncore_event_init,
- .add = amd_uncore_add,
- .del = amd_uncore_del,
- .start = amd_uncore_start,
- .stop = amd_uncore_stop,
- .read = amd_uncore_read,
- .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
- .module = THIS_MODULE,
-};
+static __always_inline
+int amd_uncore_ctx_cid(struct amd_uncore *uncore, unsigned int cpu)
+{
+ union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+ return info->split.cid;
+}
-static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
+static __always_inline
+int amd_uncore_ctx_gid(struct amd_uncore *uncore, unsigned int cpu)
{
- return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL,
- cpu_to_node(cpu));
+ union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+ return info->split.gid;
}
-static inline struct perf_event **
-amd_uncore_events_alloc(unsigned int num, unsigned int cpu)
+static __always_inline
+int amd_uncore_ctx_num_pmcs(struct amd_uncore *uncore, unsigned int cpu)
{
- return kzalloc_node(sizeof(struct perf_event *) * num, GFP_KERNEL,
- cpu_to_node(cpu));
+ union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+ return info->split.num_pmcs;
}
-static int amd_uncore_cpu_up_prepare(unsigned int cpu)
+static void amd_uncore_ctx_free(struct amd_uncore *uncore, unsigned int cpu)
{
- struct amd_uncore *uncore_nb = NULL, *uncore_llc = NULL;
+ struct amd_uncore_pmu *pmu;
+ struct amd_uncore_ctx *ctx;
+ int i;
- if (amd_uncore_nb) {
- *per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
- uncore_nb = amd_uncore_alloc(cpu);
- if (!uncore_nb)
- goto fail;
- uncore_nb->cpu = cpu;
- uncore_nb->num_counters = num_counters_nb;
- uncore_nb->rdpmc_base = RDPMC_BASE_NB;
- uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
- uncore_nb->active_mask = &amd_nb_active_mask;
- uncore_nb->pmu = &amd_nb_pmu;
- uncore_nb->events = amd_uncore_events_alloc(num_counters_nb, cpu);
- if (!uncore_nb->events)
- goto fail;
- uncore_nb->id = -1;
- *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
+ if (!uncore->init_done)
+ return;
+
+ for (i = 0; i < uncore->num_pmus; i++) {
+ pmu = &uncore->pmus[i];
+ ctx = *per_cpu_ptr(pmu->ctx, cpu);
+ if (!ctx)
+ continue;
+
+ if (cpu == ctx->cpu)
+ cpumask_clear_cpu(cpu, &pmu->active_mask);
+
+ if (!--ctx->refcnt) {
+ kfree(ctx->events);
+ kfree(ctx);
+ }
+
+ *per_cpu_ptr(pmu->ctx, cpu) = NULL;
}
+}
- if (amd_uncore_llc) {
- *per_cpu_ptr(amd_uncore_llc, cpu) = NULL;
- uncore_llc = amd_uncore_alloc(cpu);
- if (!uncore_llc)
- goto fail;
- uncore_llc->cpu = cpu;
- uncore_llc->num_counters = num_counters_llc;
- uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
- uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
- uncore_llc->active_mask = &amd_llc_active_mask;
- uncore_llc->pmu = &amd_llc_pmu;
- uncore_llc->events = amd_uncore_events_alloc(num_counters_llc, cpu);
- if (!uncore_llc->events)
- goto fail;
- uncore_llc->id = -1;
- *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
+static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+ struct amd_uncore_ctx *curr, *prev;
+ struct amd_uncore_pmu *pmu;
+ int node, cid, gid, i, j;
+
+ if (!uncore->init_done || !uncore->num_pmus)
+ return 0;
+
+ cid = amd_uncore_ctx_cid(uncore, cpu);
+ gid = amd_uncore_ctx_gid(uncore, cpu);
+
+ for (i = 0; i < uncore->num_pmus; i++) {
+ pmu = &uncore->pmus[i];
+ *per_cpu_ptr(pmu->ctx, cpu) = NULL;
+ curr = NULL;
+
+ /* Check for group exclusivity */
+ if (gid != pmu->group)
+ continue;
+
+ /* Find a sibling context */
+ for_each_online_cpu(j) {
+ if (cpu == j)
+ continue;
+
+ prev = *per_cpu_ptr(pmu->ctx, j);
+ if (!prev)
+ continue;
+
+ if (cid == amd_uncore_ctx_cid(uncore, j)) {
+ curr = prev;
+ break;
+ }
+ }
+
+ /* Allocate context if sibling does not exist */
+ if (!curr) {
+ node = cpu_to_node(cpu);
+ curr = kzalloc_node(sizeof(*curr), GFP_KERNEL, node);
+ if (!curr)
+ goto fail;
+
+ curr->cpu = cpu;
+ curr->events = kzalloc_node(sizeof(*curr->events) *
+ pmu->num_counters,
+ GFP_KERNEL, node);
+ if (!curr->events) {
+ kfree(curr);
+ goto fail;
+ }
+
+ cpumask_set_cpu(cpu, &pmu->active_mask);
+ }
+
+ curr->refcnt++;
+ *per_cpu_ptr(pmu->ctx, cpu) = curr;
}
return 0;
fail:
- if (uncore_nb) {
- kfree(uncore_nb->events);
- kfree(uncore_nb);
- }
-
- if (uncore_llc) {
- kfree(uncore_llc->events);
- kfree(uncore_llc);
- }
+ amd_uncore_ctx_free(uncore, cpu);
return -ENOMEM;
}
-static struct amd_uncore *
-amd_uncore_find_online_sibling(struct amd_uncore *this,
- struct amd_uncore * __percpu *uncores)
+static void amd_uncore_ctx_move(struct amd_uncore *uncore, unsigned int cpu)
{
- unsigned int cpu;
- struct amd_uncore *that;
-
- for_each_online_cpu(cpu) {
- that = *per_cpu_ptr(uncores, cpu);
+ struct amd_uncore_ctx *curr, *next;
+ struct amd_uncore_pmu *pmu;
+ int i, j;
- if (!that)
- continue;
+ if (!uncore->init_done)
+ return;
- if (this == that)
+ for (i = 0; i < uncore->num_pmus; i++) {
+ pmu = &uncore->pmus[i];
+ curr = *per_cpu_ptr(pmu->ctx, cpu);
+ if (!curr)
continue;
- if (this->id == that->id) {
- hlist_add_head(&this->node, &uncore_unused_list);
- this = that;
- break;
+ /* Migrate to a shared sibling if possible */
+ for_each_online_cpu(j) {
+ next = *per_cpu_ptr(pmu->ctx, j);
+ if (!next || cpu == j)
+ continue;
+
+ if (curr == next) {
+ perf_pmu_migrate_context(&pmu->pmu, cpu, j);
+ cpumask_clear_cpu(cpu, &pmu->active_mask);
+ cpumask_set_cpu(j, &pmu->active_mask);
+ next->cpu = j;
+ break;
+ }
}
}
-
- this->refcnt++;
- return this;
}
static int amd_uncore_cpu_starting(unsigned int cpu)
{
- unsigned int eax, ebx, ecx, edx;
struct amd_uncore *uncore;
+ int i;
+
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ uncore->scan(uncore, cpu);
+ }
+
+ return 0;
+}
- if (amd_uncore_nb) {
- uncore = *per_cpu_ptr(amd_uncore_nb, cpu);
- cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- uncore->id = ecx & 0xff;
+static int amd_uncore_cpu_online(unsigned int cpu)
+{
+ struct amd_uncore *uncore;
+ int i;
- uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb);
- *per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ if (uncore->init(uncore, cpu))
+ break;
}
- if (amd_uncore_llc) {
- uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
- uncore->id = get_llc_id(cpu);
+ return 0;
+}
- uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
- *per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
+static int amd_uncore_cpu_down_prepare(unsigned int cpu)
+{
+ struct amd_uncore *uncore;
+ int i;
+
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ uncore->move(uncore, cpu);
}
return 0;
}
-static void uncore_clean_online(void)
+static int amd_uncore_cpu_dead(unsigned int cpu)
{
struct amd_uncore *uncore;
- struct hlist_node *n;
+ int i;
- hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
- hlist_del(&uncore->node);
- kfree(uncore->events);
- kfree(uncore);
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ uncore->free(uncore, cpu);
}
+
+ return 0;
}
-static void uncore_online(unsigned int cpu,
- struct amd_uncore * __percpu *uncores)
+static int amd_uncore_df_event_init(struct perf_event *event)
{
- struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+ struct hw_perf_event *hwc = &event->hw;
+ int ret = amd_uncore_event_init(event);
- uncore_clean_online();
+ if (ret || pmu_version < 2)
+ return ret;
- if (cpu == uncore->cpu)
- cpumask_set_cpu(cpu, uncore->active_mask);
+ hwc->config = event->attr.config &
+ (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB :
+ AMD64_RAW_EVENT_MASK_NB);
+
+ return 0;
}
-static int amd_uncore_cpu_online(unsigned int cpu)
+static int amd_uncore_df_add(struct perf_event *event, int flags)
{
- if (amd_uncore_nb)
- uncore_online(cpu, amd_uncore_nb);
+ int ret = amd_uncore_add(event, flags & ~PERF_EF_START);
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (ret)
+ return ret;
+
+ /*
+ * The first four DF counters are accessible via RDPMC index 6 to 9
+ * followed by the L3 counters from index 10 to 15. For processors
+ * with more than four DF counters, the DF RDPMC assignments become
+ * discontiguous as the additional counters are accessible starting
+ * from index 16.
+ */
+ if (hwc->idx >= NUM_COUNTERS_NB)
+ hwc->event_base_rdpmc += NUM_COUNTERS_L3;
- if (amd_uncore_llc)
- uncore_online(cpu, amd_uncore_llc);
+ /* Delayed start after rdpmc base update */
+ if (flags & PERF_EF_START)
+ amd_uncore_start(event, PERF_EF_RELOAD);
return 0;
}
-static void uncore_down_prepare(unsigned int cpu,
- struct amd_uncore * __percpu *uncores)
+static
+void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
- unsigned int i;
- struct amd_uncore *this = *per_cpu_ptr(uncores, cpu);
+ union cpuid_0x80000022_ebx ebx;
+ union amd_uncore_info info;
- if (this->cpu != cpu)
+ if (!boot_cpu_has(X86_FEATURE_PERFCTR_NB))
return;
- /* this cpu is going down, migrate to a shared sibling if possible */
- for_each_online_cpu(i) {
- struct amd_uncore *that = *per_cpu_ptr(uncores, i);
+ info.split.aux_data = 0;
+ info.split.num_pmcs = NUM_COUNTERS_NB;
+ info.split.gid = 0;
+ info.split.cid = topology_die_id(cpu);
- if (cpu == i)
- continue;
+ if (pmu_version >= 2) {
+ ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
+ info.split.num_pmcs = ebx.split.num_df_pmc;
+ }
- if (this == that) {
- perf_pmu_migrate_context(this->pmu, cpu, i);
- cpumask_clear_cpu(cpu, that->active_mask);
- cpumask_set_cpu(i, that->active_mask);
- that->cpu = i;
- break;
- }
+ *per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+ struct attribute **df_attr = amd_uncore_df_format_attr;
+ struct amd_uncore_pmu *pmu;
+
+ /* Run just once */
+ if (uncore->init_done)
+ return amd_uncore_ctx_init(uncore, cpu);
+
+ /* No grouping, single instance for a system */
+ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+ if (!uncore->pmus) {
+ uncore->num_pmus = 0;
+ goto done;
}
+
+ /*
+ * For Family 17h and above, the Northbridge counters are repurposed
+ * as Data Fabric counters. The PMUs are exported based on family as
+ * either NB or DF.
+ */
+ pmu = &uncore->pmus[0];
+ strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
+ sizeof(pmu->name));
+ pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->msr_base = MSR_F15H_NB_PERF_CTL;
+ pmu->rdpmc_base = RDPMC_BASE_NB;
+ pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+
+ if (pmu_version >= 2) {
+ *df_attr++ = &format_attr_event14v2.attr;
+ *df_attr++ = &format_attr_umask12.attr;
+ } else if (boot_cpu_data.x86 >= 0x17) {
+ *df_attr = &format_attr_event14.attr;
+ }
+
+ pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+ if (!pmu->ctx)
+ goto done;
+
+ pmu->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .attr_groups = amd_uncore_df_attr_groups,
+ .name = pmu->name,
+ .event_init = amd_uncore_df_event_init,
+ .add = amd_uncore_df_add,
+ .del = amd_uncore_del,
+ .start = amd_uncore_start,
+ .stop = amd_uncore_stop,
+ .read = amd_uncore_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
+ };
+
+ if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+ free_percpu(pmu->ctx);
+ pmu->ctx = NULL;
+ goto done;
+ }
+
+ pr_info("%d %s%s counters detected\n", pmu->num_counters,
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON " : "",
+ pmu->pmu.name);
+
+ uncore->num_pmus = 1;
+
+done:
+ uncore->init_done = true;
+
+ return amd_uncore_ctx_init(uncore, cpu);
}
-static int amd_uncore_cpu_down_prepare(unsigned int cpu)
+static int amd_uncore_l3_event_init(struct perf_event *event)
{
- if (amd_uncore_nb)
- uncore_down_prepare(cpu, amd_uncore_nb);
+ int ret = amd_uncore_event_init(event);
+ struct hw_perf_event *hwc = &event->hw;
+ u64 config = event->attr.config;
+ u64 mask;
- if (amd_uncore_llc)
- uncore_down_prepare(cpu, amd_uncore_llc);
+ hwc->config = config & AMD64_RAW_EVENT_MASK_NB;
+
+ /*
+ * SliceMask and ThreadMask need to be set for certain L3 events.
+ * For other events, the two fields do not affect the count.
+ */
+ if (ret || boot_cpu_data.x86 < 0x17)
+ return ret;
+
+ mask = config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK |
+ AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES |
+ AMD64_L3_COREID_MASK);
+
+ if (boot_cpu_data.x86 <= 0x18)
+ mask = ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) |
+ ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK);
+
+ /*
+ * If the user doesn't specify a ThreadMask, they're not trying to
+ * count core 0, so we enable all cores & threads.
+ * We'll also assume that they want to count slice 0 if they specify
+ * a ThreadMask and leave SliceId and EnAllSlices unpopulated.
+ */
+ else if (!(config & AMD64_L3_F19H_THREAD_MASK))
+ mask = AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES |
+ AMD64_L3_EN_ALL_CORES;
+
+ hwc->config |= mask;
return 0;
}
-static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
+static
+void amd_uncore_l3_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
- struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+ union amd_uncore_info info;
- if (cpu == uncore->cpu)
- cpumask_clear_cpu(cpu, uncore->active_mask);
+ if (!boot_cpu_has(X86_FEATURE_PERFCTR_LLC))
+ return;
+
+ info.split.aux_data = 0;
+ info.split.num_pmcs = NUM_COUNTERS_L2;
+ info.split.gid = 0;
+ info.split.cid = per_cpu_llc_id(cpu);
- if (!--uncore->refcnt) {
- kfree(uncore->events);
- kfree(uncore);
+ if (boot_cpu_data.x86 >= 0x17)
+ info.split.num_pmcs = NUM_COUNTERS_L3;
+
+ *per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+ struct attribute **l3_attr = amd_uncore_l3_format_attr;
+ struct amd_uncore_pmu *pmu;
+
+ /* Run just once */
+ if (uncore->init_done)
+ return amd_uncore_ctx_init(uncore, cpu);
+
+ /* No grouping, single instance for a system */
+ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+ if (!uncore->pmus) {
+ uncore->num_pmus = 0;
+ goto done;
}
- *per_cpu_ptr(uncores, cpu) = NULL;
+ /*
+ * For Family 17h and above, L3 cache counters are available instead
+ * of L2 cache counters. The PMUs are exported based on family as
+ * either L2 or L3.
+ */
+ pmu = &uncore->pmus[0];
+ strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
+ sizeof(pmu->name));
+ pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+ pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
+ pmu->rdpmc_base = RDPMC_BASE_LLC;
+ pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+
+ if (boot_cpu_data.x86 >= 0x17) {
+ *l3_attr++ = &format_attr_event8.attr;
+ *l3_attr++ = &format_attr_umask8.attr;
+ *l3_attr++ = boot_cpu_data.x86 >= 0x19 ?
+ &format_attr_threadmask2.attr :
+ &format_attr_threadmask8.attr;
+ }
+
+ pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+ if (!pmu->ctx)
+ goto done;
+
+ pmu->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .attr_groups = amd_uncore_l3_attr_groups,
+ .attr_update = amd_uncore_l3_attr_update,
+ .name = pmu->name,
+ .event_init = amd_uncore_l3_event_init,
+ .add = amd_uncore_add,
+ .del = amd_uncore_del,
+ .start = amd_uncore_start,
+ .stop = amd_uncore_stop,
+ .read = amd_uncore_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
+ };
+
+ if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+ free_percpu(pmu->ctx);
+ pmu->ctx = NULL;
+ goto done;
+ }
+
+ pr_info("%d %s%s counters detected\n", pmu->num_counters,
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON " : "",
+ pmu->pmu.name);
+
+ uncore->num_pmus = 1;
+
+done:
+ uncore->init_done = true;
+
+ return amd_uncore_ctx_init(uncore, cpu);
}
-static int amd_uncore_cpu_dead(unsigned int cpu)
+static int amd_uncore_umc_event_init(struct perf_event *event)
{
- if (amd_uncore_nb)
- uncore_dead(cpu, amd_uncore_nb);
+ struct hw_perf_event *hwc = &event->hw;
+ int ret = amd_uncore_event_init(event);
+
+ if (ret)
+ return ret;
- if (amd_uncore_llc)
- uncore_dead(cpu, amd_uncore_llc);
+ hwc->config = event->attr.config & AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC;
return 0;
}
-static int __init amd_uncore_init(void)
+static void amd_uncore_umc_start(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (flags & PERF_EF_RELOAD)
+ wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+
+ hwc->state = 0;
+ wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
+ perf_event_update_userpage(event);
+}
+
+static
+void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
- struct attribute **df_attr = amd_uncore_df_format_attr;
- struct attribute **l3_attr = amd_uncore_l3_format_attr;
union cpuid_0x80000022_ebx ebx;
+ union amd_uncore_info info;
+ unsigned int eax, ecx, edx;
+
+ if (pmu_version < 2)
+ return;
+
+ cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
+ info.split.aux_data = ecx; /* stash active mask */
+ info.split.num_pmcs = ebx.split.num_umc_pmc;
+ info.split.gid = topology_die_id(cpu);
+ info.split.cid = topology_die_id(cpu);
+ *per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+ DECLARE_BITMAP(gmask, UNCORE_GROUP_MAX) = { 0 };
+ u8 group_num_pmus[UNCORE_GROUP_MAX] = { 0 };
+ u8 group_num_pmcs[UNCORE_GROUP_MAX] = { 0 };
+ union amd_uncore_info info;
+ struct amd_uncore_pmu *pmu;
+ int index = 0, gid, i;
+
+ if (pmu_version < 2)
+ return 0;
+
+ /* Run just once */
+ if (uncore->init_done)
+ return amd_uncore_ctx_init(uncore, cpu);
+
+ /* Find unique groups */
+ for_each_online_cpu(i) {
+ info = *per_cpu_ptr(uncore->info, i);
+ gid = info.split.gid;
+ if (test_bit(gid, gmask))
+ continue;
+
+ __set_bit(gid, gmask);
+ group_num_pmus[gid] = hweight32(info.split.aux_data);
+ group_num_pmcs[gid] = info.split.num_pmcs;
+ uncore->num_pmus += group_num_pmus[gid];
+ }
+
+ uncore->pmus = kzalloc(sizeof(*uncore->pmus) * uncore->num_pmus,
+ GFP_KERNEL);
+ if (!uncore->pmus) {
+ uncore->num_pmus = 0;
+ goto done;
+ }
+
+ for_each_set_bit(gid, gmask, UNCORE_GROUP_MAX) {
+ for (i = 0; i < group_num_pmus[gid]; i++) {
+ pmu = &uncore->pmus[index];
+ snprintf(pmu->name, sizeof(pmu->name), "amd_umc_%d", index);
+ pmu->num_counters = group_num_pmcs[gid] / group_num_pmus[gid];
+ pmu->msr_base = MSR_F19H_UMC_PERF_CTL + i * pmu->num_counters * 2;
+ pmu->rdpmc_base = -1;
+ pmu->group = gid;
+
+ pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+ if (!pmu->ctx)
+ goto done;
+
+ pmu->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .attr_groups = amd_uncore_umc_attr_groups,
+ .name = pmu->name,
+ .event_init = amd_uncore_umc_event_init,
+ .add = amd_uncore_add,
+ .del = amd_uncore_del,
+ .start = amd_uncore_umc_start,
+ .stop = amd_uncore_stop,
+ .read = amd_uncore_read,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+ .module = THIS_MODULE,
+ };
+
+ if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+ free_percpu(pmu->ctx);
+ pmu->ctx = NULL;
+ goto done;
+ }
+
+ pr_info("%d %s counters detected\n", pmu->num_counters,
+ pmu->pmu.name);
+
+ index++;
+ }
+ }
+
+done:
+ uncore->num_pmus = index;
+ uncore->init_done = true;
+
+ return amd_uncore_ctx_init(uncore, cpu);
+}
+
+static struct amd_uncore uncores[UNCORE_TYPE_MAX] = {
+ /* UNCORE_TYPE_DF */
+ {
+ .scan = amd_uncore_df_ctx_scan,
+ .init = amd_uncore_df_ctx_init,
+ .move = amd_uncore_ctx_move,
+ .free = amd_uncore_ctx_free,
+ },
+ /* UNCORE_TYPE_L3 */
+ {
+ .scan = amd_uncore_l3_ctx_scan,
+ .init = amd_uncore_l3_ctx_init,
+ .move = amd_uncore_ctx_move,
+ .free = amd_uncore_ctx_free,
+ },
+ /* UNCORE_TYPE_UMC */
+ {
+ .scan = amd_uncore_umc_ctx_scan,
+ .init = amd_uncore_umc_ctx_init,
+ .move = amd_uncore_ctx_move,
+ .free = amd_uncore_ctx_free,
+ },
+};
+
+static int __init amd_uncore_init(void)
+{
+ struct amd_uncore *uncore;
int ret = -ENODEV;
+ int i;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -660,125 +1022,91 @@ static int __init amd_uncore_init(void)
if (boot_cpu_has(X86_FEATURE_PERFMON_V2))
pmu_version = 2;
- num_counters_nb = NUM_COUNTERS_NB;
- num_counters_llc = NUM_COUNTERS_L2;
- if (boot_cpu_data.x86 >= 0x17) {
- /*
- * For F17h and above, the Northbridge counters are
- * repurposed as Data Fabric counters. Also, L3
- * counters are supported too. The PMUs are exported
- * based on family as either L2 or L3 and NB or DF.
- */
- num_counters_llc = NUM_COUNTERS_L3;
- amd_nb_pmu.name = "amd_df";
- amd_llc_pmu.name = "amd_l3";
- l3_mask = true;
- }
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
- if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
- if (pmu_version >= 2) {
- *df_attr++ = &format_attr_event14v2.attr;
- *df_attr++ = &format_attr_umask12.attr;
- } else if (boot_cpu_data.x86 >= 0x17) {
- *df_attr = &format_attr_event14.attr;
- }
+ BUG_ON(!uncore->scan);
+ BUG_ON(!uncore->init);
+ BUG_ON(!uncore->move);
+ BUG_ON(!uncore->free);
- amd_uncore_nb = alloc_percpu(struct amd_uncore *);
- if (!amd_uncore_nb) {
+ uncore->info = alloc_percpu(union amd_uncore_info);
+ if (!uncore->info) {
ret = -ENOMEM;
- goto fail_nb;
- }
- ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
- if (ret)
- goto fail_nb;
-
- if (pmu_version >= 2) {
- ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
- num_counters_nb = ebx.split.num_df_pmc;
- }
-
- pr_info("%d %s %s counters detected\n", num_counters_nb,
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "",
- amd_nb_pmu.name);
-
- ret = 0;
- }
-
- if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
- if (boot_cpu_data.x86 >= 0x19) {
- *l3_attr++ = &format_attr_event8.attr;
- *l3_attr++ = &format_attr_umask8.attr;
- *l3_attr++ = &format_attr_threadmask2.attr;
- } else if (boot_cpu_data.x86 >= 0x17) {
- *l3_attr++ = &format_attr_event8.attr;
- *l3_attr++ = &format_attr_umask8.attr;
- *l3_attr++ = &format_attr_threadmask8.attr;
- }
-
- amd_uncore_llc = alloc_percpu(struct amd_uncore *);
- if (!amd_uncore_llc) {
- ret = -ENOMEM;
- goto fail_llc;
+ goto fail;
}
- ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
- if (ret)
- goto fail_llc;
-
- pr_info("%d %s %s counters detected\n", num_counters_llc,
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "",
- amd_llc_pmu.name);
- ret = 0;
- }
+ };
/*
* Install callbacks. Core will call them for each online cpu.
*/
- if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
- "perf/x86/amd/uncore:prepare",
- amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
- goto fail_llc;
-
- if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
- "perf/x86/amd/uncore:starting",
- amd_uncore_cpu_starting, NULL))
+ ret = cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
+ "perf/x86/amd/uncore:prepare",
+ NULL, amd_uncore_cpu_dead);
+ if (ret)
+ goto fail;
+
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
+ "perf/x86/amd/uncore:starting",
+ amd_uncore_cpu_starting, NULL);
+ if (ret)
goto fail_prep;
- if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
- "perf/x86/amd/uncore:online",
- amd_uncore_cpu_online,
- amd_uncore_cpu_down_prepare))
+
+ ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
+ "perf/x86/amd/uncore:online",
+ amd_uncore_cpu_online,
+ amd_uncore_cpu_down_prepare);
+ if (ret)
goto fail_start;
+
return 0;
fail_start:
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
fail_prep:
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_llc:
- if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
- perf_pmu_unregister(&amd_nb_pmu);
- free_percpu(amd_uncore_llc);
-fail_nb:
- free_percpu(amd_uncore_nb);
+fail:
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ if (uncore->info) {
+ free_percpu(uncore->info);
+ uncore->info = NULL;
+ }
+ }
return ret;
}
static void __exit amd_uncore_exit(void)
{
+ struct amd_uncore *uncore;
+ struct amd_uncore_pmu *pmu;
+ int i, j;
+
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE);
cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
- if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
- perf_pmu_unregister(&amd_llc_pmu);
- free_percpu(amd_uncore_llc);
- amd_uncore_llc = NULL;
- }
+ for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+ uncore = &uncores[i];
+ if (!uncore->info)
+ continue;
+
+ free_percpu(uncore->info);
+ uncore->info = NULL;
+
+ for (j = 0; j < uncore->num_pmus; j++) {
+ pmu = &uncore->pmus[j];
+ if (!pmu->ctx)
+ continue;
+
+ perf_pmu_unregister(&pmu->pmu);
+ free_percpu(pmu->ctx);
+ pmu->ctx = NULL;
+ }
- if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
- perf_pmu_unregister(&amd_nb_pmu);
- free_percpu(amd_uncore_nb);
- amd_uncore_nb = NULL;
+ kfree(uncore->pmus);
+ uncore->pmus = NULL;
}
}
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 185f902e5f28..40ad1425ffa2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1887,9 +1887,9 @@ ssize_t events_hybrid_sysfs_show(struct device *dev,
str = pmu_attr->event_str;
for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
- if (!(x86_pmu.hybrid_pmu[i].cpu_type & pmu_attr->pmu_type))
+ if (!(x86_pmu.hybrid_pmu[i].pmu_type & pmu_attr->pmu_type))
continue;
- if (x86_pmu.hybrid_pmu[i].cpu_type & pmu->cpu_type) {
+ if (x86_pmu.hybrid_pmu[i].pmu_type & pmu->pmu_type) {
next_str = strchr(str, ';');
if (next_str)
return snprintf(page, next_str - str + 1, "%s", str);
@@ -2169,7 +2169,7 @@ static int __init init_hw_perf_events(void)
hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE;
err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name,
- (hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1);
+ (hybrid_pmu->pmu_type == hybrid_big) ? PERF_TYPE_RAW : -1);
if (err)
break;
}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fa355d3658a6..a08f794a0e79 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -211,6 +211,14 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
EVENT_CONSTRAINT_END
};
+static struct event_constraint intel_grt_event_constraints[] __read_mostly = {
+ FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+ EVENT_CONSTRAINT_END
+};
+
static struct event_constraint intel_skl_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
@@ -299,7 +307,7 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
-static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
+static struct extra_reg intel_glc_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
@@ -309,11 +317,12 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
-static struct event_constraint intel_spr_event_constraints[] = {
+static struct event_constraint intel_glc_event_constraints[] = {
FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */
FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
+ FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */
METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
@@ -349,7 +358,7 @@ static struct event_constraint intel_spr_event_constraints[] = {
EVENT_CONSTRAINT_END
};
-static struct extra_reg intel_gnr_extra_regs[] __read_mostly = {
+static struct extra_reg intel_rwc_extra_regs[] __read_mostly = {
INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
@@ -473,7 +482,7 @@ static u64 intel_pmu_event_map(int hw_event)
return intel_perfmon_event_map[hw_event];
}
-static __initconst const u64 spr_hw_cache_event_ids
+static __initconst const u64 glc_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -552,7 +561,7 @@ static __initconst const u64 spr_hw_cache_event_ids
},
};
-static __initconst const u64 spr_hw_cache_extra_regs
+static __initconst const u64 glc_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -2556,16 +2565,6 @@ static int icl_set_topdown_event_period(struct perf_event *event)
return 0;
}
-static int adl_set_topdown_event_period(struct perf_event *event)
-{
- struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
-
- if (pmu->cpu_type != hybrid_big)
- return 0;
-
- return icl_set_topdown_event_period(event);
-}
-
DEFINE_STATIC_CALL(intel_pmu_set_topdown_event_period, x86_perf_event_set_period);
static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx)
@@ -2708,16 +2707,6 @@ static u64 icl_update_topdown_event(struct perf_event *event)
x86_pmu.num_topdown_events - 1);
}
-static u64 adl_update_topdown_event(struct perf_event *event)
-{
- struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
-
- if (pmu->cpu_type != hybrid_big)
- return 0;
-
- return icl_update_topdown_event(event);
-}
-
DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
static void intel_pmu_read_topdown_event(struct perf_event *event)
@@ -3869,7 +3858,7 @@ static inline bool require_mem_loads_aux_event(struct perf_event *event)
return false;
if (is_hybrid())
- return hybrid_pmu(event->pmu)->cpu_type == hybrid_big;
+ return hybrid_pmu(event->pmu)->pmu_type == hybrid_big;
return true;
}
@@ -4273,7 +4262,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
}
static struct event_constraint *
-spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+glc_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
{
struct event_constraint *c;
@@ -4361,9 +4350,9 @@ adl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
{
struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
- if (pmu->cpu_type == hybrid_big)
- return spr_get_event_constraints(cpuc, idx, event);
- else if (pmu->cpu_type == hybrid_small)
+ if (pmu->pmu_type == hybrid_big)
+ return glc_get_event_constraints(cpuc, idx, event);
+ else if (pmu->pmu_type == hybrid_small)
return tnt_get_event_constraints(cpuc, idx, event);
WARN_ON(1);
@@ -4409,7 +4398,7 @@ rwc_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
{
struct event_constraint *c;
- c = spr_get_event_constraints(cpuc, idx, event);
+ c = glc_get_event_constraints(cpuc, idx, event);
/* The Retire Latency is not supported by the fixed counter 0. */
if (event->attr.precise_ip &&
@@ -4433,9 +4422,9 @@ mtl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
{
struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
- if (pmu->cpu_type == hybrid_big)
+ if (pmu->pmu_type == hybrid_big)
return rwc_get_event_constraints(cpuc, idx, event);
- if (pmu->cpu_type == hybrid_small)
+ if (pmu->pmu_type == hybrid_small)
return cmt_get_event_constraints(cpuc, idx, event);
WARN_ON(1);
@@ -4446,18 +4435,18 @@ static int adl_hw_config(struct perf_event *event)
{
struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
- if (pmu->cpu_type == hybrid_big)
+ if (pmu->pmu_type == hybrid_big)
return hsw_hw_config(event);
- else if (pmu->cpu_type == hybrid_small)
+ else if (pmu->pmu_type == hybrid_small)
return intel_pmu_hw_config(event);
WARN_ON(1);
return -EOPNOTSUPP;
}
-static u8 adl_get_hybrid_cpu_type(void)
+static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
{
- return hybrid_big;
+ return HYBRID_INTEL_CORE;
}
/*
@@ -4490,7 +4479,7 @@ static void nhm_limit_period(struct perf_event *event, s64 *left)
*left = max(*left, 32LL);
}
-static void spr_limit_period(struct perf_event *event, s64 *left)
+static void glc_limit_period(struct perf_event *event, s64 *left)
{
if (event->attr.precise_ip == 3)
*left = max(*left, 128LL);
@@ -4618,6 +4607,23 @@ static void intel_pmu_check_num_counters(int *num_counters,
int *num_counters_fixed,
u64 *intel_ctrl, u64 fixed_mask);
+static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
+ int num_counters,
+ int num_counters_fixed,
+ u64 intel_ctrl);
+
+static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
+
+static inline bool intel_pmu_broken_perf_cap(void)
+{
+ /* The Perf Metric (Bit 15) is always cleared */
+ if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
+ (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
+ return true;
+
+ return false;
+}
+
static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
{
unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF);
@@ -4628,27 +4634,83 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
&eax, &ebx, &ecx, &edx);
pmu->num_counters = fls(eax);
pmu->num_counters_fixed = fls(ebx);
- intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
- &pmu->intel_ctrl, ebx);
+ }
+
+
+ if (!intel_pmu_broken_perf_cap()) {
+ /* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
}
}
-static bool init_hybrid_pmu(int cpu)
+static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
+{
+ intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
+ &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
+ pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->unconstrained = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+ 0, pmu->num_counters, 0, 0);
+
+ if (pmu->intel_cap.perf_metrics)
+ pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+ else
+ pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+
+ if (pmu->intel_cap.pebs_output_pt_available)
+ pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+ else
+ pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+
+ intel_pmu_check_event_constraints(pmu->event_constraints,
+ pmu->num_counters,
+ pmu->num_counters_fixed,
+ pmu->intel_ctrl);
+
+ intel_pmu_check_extra_regs(pmu->extra_regs);
+}
+
+static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
{
- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
u8 cpu_type = get_this_hybrid_cpu_type();
- struct x86_hybrid_pmu *pmu = NULL;
int i;
- if (!cpu_type && x86_pmu.get_hybrid_cpu_type)
- cpu_type = x86_pmu.get_hybrid_cpu_type();
+ /*
+ * This is running on a CPU model that is known to have hybrid
+ * configurations. But the CPU told us it is not hybrid, shame
+ * on it. There should be a fixup function provided for these
+ * troublesome CPUs (->get_hybrid_cpu_type).
+ */
+ if (cpu_type == HYBRID_INTEL_NONE) {
+ if (x86_pmu.get_hybrid_cpu_type)
+ cpu_type = x86_pmu.get_hybrid_cpu_type();
+ else
+ return NULL;
+ }
+ /*
+ * This essentially just maps between the 'hybrid_cpu_type'
+ * and 'hybrid_pmu_type' enums:
+ */
for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
- if (x86_pmu.hybrid_pmu[i].cpu_type == cpu_type) {
- pmu = &x86_pmu.hybrid_pmu[i];
- break;
- }
+ enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
+
+ if (cpu_type == HYBRID_INTEL_CORE &&
+ pmu_type == hybrid_big)
+ return &x86_pmu.hybrid_pmu[i];
+ if (cpu_type == HYBRID_INTEL_ATOM &&
+ pmu_type == hybrid_small)
+ return &x86_pmu.hybrid_pmu[i];
}
+
+ return NULL;
+}
+
+static bool init_hybrid_pmu(int cpu)
+{
+ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+ struct x86_hybrid_pmu *pmu = find_hybrid_pmu_for_cpu();
+
if (WARN_ON_ONCE(!pmu || (pmu->pmu.type == -1))) {
cpuc->pmu = NULL;
return false;
@@ -4661,6 +4723,8 @@ static bool init_hybrid_pmu(int cpu)
if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
update_pmu_cap(pmu);
+ intel_pmu_check_hybrid_pmus(pmu);
+
if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
return false;
@@ -5337,14 +5401,14 @@ static struct attribute *icl_tsx_events_attrs[] = {
EVENT_ATTR_STR(mem-stores, mem_st_spr, "event=0xcd,umask=0x2");
EVENT_ATTR_STR(mem-loads-aux, mem_ld_aux, "event=0x03,umask=0x82");
-static struct attribute *spr_events_attrs[] = {
+static struct attribute *glc_events_attrs[] = {
EVENT_PTR(mem_ld_hsw),
EVENT_PTR(mem_st_spr),
EVENT_PTR(mem_ld_aux),
NULL,
};
-static struct attribute *spr_td_events_attrs[] = {
+static struct attribute *glc_td_events_attrs[] = {
EVENT_PTR(slots),
EVENT_PTR(td_retiring),
EVENT_PTR(td_bad_spec),
@@ -5357,7 +5421,7 @@ static struct attribute *spr_td_events_attrs[] = {
NULL,
};
-static struct attribute *spr_tsx_events_attrs[] = {
+static struct attribute *glc_tsx_events_attrs[] = {
EVENT_PTR(tx_start),
EVENT_PTR(tx_abort),
EVENT_PTR(tx_commit),
@@ -5699,7 +5763,7 @@ static bool is_attr_for_this_pmu(struct kobject *kobj, struct attribute *attr)
struct perf_pmu_events_hybrid_attr *pmu_attr =
container_of(attr, struct perf_pmu_events_hybrid_attr, attr.attr);
- return pmu->cpu_type & pmu_attr->pmu_type;
+ return pmu->pmu_type & pmu_attr->pmu_type;
}
static umode_t hybrid_events_is_visible(struct kobject *kobj,
@@ -5736,7 +5800,7 @@ static umode_t hybrid_format_is_visible(struct kobject *kobj,
container_of(attr, struct perf_pmu_format_hybrid_attr, attr.attr);
int cpu = hybrid_find_supported_cpu(pmu);
- return (cpu >= 0) && (pmu->cpu_type & pmu_attr->pmu_type) ? attr->mode : 0;
+ return (cpu >= 0) && (pmu->pmu_type & pmu_attr->pmu_type) ? attr->mode : 0;
}
static struct attribute_group hybrid_group_events_td = {
@@ -5880,40 +5944,105 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs)
}
}
-static void intel_pmu_check_hybrid_pmus(u64 fixed_mask)
+static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
+ { hybrid_small, "cpu_atom" },
+ { hybrid_big, "cpu_core" },
+};
+
+static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
{
+ unsigned long pmus_mask = pmus;
struct x86_hybrid_pmu *pmu;
- int i;
+ int idx = 0, bit;
- for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
- pmu = &x86_pmu.hybrid_pmu[i];
+ x86_pmu.num_hybrid_pmus = hweight_long(pmus_mask);
+ x86_pmu.hybrid_pmu = kcalloc(x86_pmu.num_hybrid_pmus,
+ sizeof(struct x86_hybrid_pmu),
+ GFP_KERNEL);
+ if (!x86_pmu.hybrid_pmu)
+ return -ENOMEM;
- intel_pmu_check_num_counters(&pmu->num_counters,
- &pmu->num_counters_fixed,
- &pmu->intel_ctrl,
- fixed_mask);
+ static_branch_enable(&perf_is_hybrid);
+ x86_pmu.filter = intel_pmu_filter;
- if (pmu->intel_cap.perf_metrics) {
- pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
- pmu->intel_ctrl |= INTEL_PMC_MSK_FIXED_SLOTS;
+ for_each_set_bit(bit, &pmus_mask, ARRAY_SIZE(intel_hybrid_pmu_type_map)) {
+ pmu = &x86_pmu.hybrid_pmu[idx++];
+ pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
+ pmu->name = intel_hybrid_pmu_type_map[bit].name;
+
+ pmu->num_counters = x86_pmu.num_counters;
+ pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+ pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+ pmu->unconstrained = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+ 0, pmu->num_counters, 0, 0);
+
+ pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
+ if (pmu->pmu_type & hybrid_small) {
+ pmu->intel_cap.perf_metrics = 0;
+ pmu->intel_cap.pebs_output_pt_available = 1;
+ pmu->mid_ack = true;
+ } else if (pmu->pmu_type & hybrid_big) {
+ pmu->intel_cap.perf_metrics = 1;
+ pmu->intel_cap.pebs_output_pt_available = 0;
+ pmu->late_ack = true;
}
+ }
- if (pmu->intel_cap.pebs_output_pt_available)
- pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+ return 0;
+}
- intel_pmu_check_event_constraints(pmu->event_constraints,
- pmu->num_counters,
- pmu->num_counters_fixed,
- pmu->intel_ctrl);
+static __always_inline void intel_pmu_ref_cycles_ext(void)
+{
+ if (!(x86_pmu.events_maskl & (INTEL_PMC_MSK_FIXED_REF_CYCLES >> INTEL_PMC_IDX_FIXED)))
+ intel_perfmon_event_map[PERF_COUNT_HW_REF_CPU_CYCLES] = 0x013c;
+}
- intel_pmu_check_extra_regs(pmu->extra_regs);
- }
+static __always_inline void intel_pmu_init_glc(struct pmu *pmu)
+{
+ x86_pmu.late_ack = true;
+ x86_pmu.limit_period = glc_limit_period;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.pebs_block = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+ x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+ x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.num_topdown_events = 8;
+ static_call_update(intel_pmu_update_topdown_event,
+ &icl_update_topdown_event);
+ static_call_update(intel_pmu_set_topdown_event_period,
+ &icl_set_topdown_event_period);
+
+ memcpy(hybrid_var(pmu, hw_cache_event_ids), glc_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hybrid_var(pmu, hw_cache_extra_regs), glc_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hybrid(pmu, event_constraints) = intel_glc_event_constraints;
+ hybrid(pmu, pebs_constraints) = intel_glc_pebs_event_constraints;
+
+ intel_pmu_ref_cycles_ext();
}
-static __always_inline bool is_mtl(u8 x86_model)
+static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
{
- return (x86_model == INTEL_FAM6_METEORLAKE) ||
- (x86_model == INTEL_FAM6_METEORLAKE_L);
+ x86_pmu.mid_ack = true;
+ x86_pmu.limit_period = glc_limit_period;
+ x86_pmu.pebs_aliases = NULL;
+ x86_pmu.pebs_prec_dist = true;
+ x86_pmu.pebs_block = true;
+ x86_pmu.lbr_pt_coexist = true;
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+ memcpy(hybrid_var(pmu, hw_cache_event_ids), glp_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hybrid_var(pmu, hw_cache_extra_regs), tnt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ hybrid_var(pmu, hw_cache_event_ids)[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+ hybrid(pmu, event_constraints) = intel_grt_event_constraints;
+ hybrid(pmu, pebs_constraints) = intel_grt_pebs_event_constraints;
+ hybrid(pmu, extra_regs) = intel_grt_extra_regs;
+
+ intel_pmu_ref_cycles_ext();
}
__init int intel_pmu_init(void)
@@ -6194,28 +6323,10 @@ __init int intel_pmu_init(void)
break;
case INTEL_FAM6_ATOM_GRACEMONT:
- x86_pmu.mid_ack = true;
- memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
- memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
- sizeof(hw_cache_extra_regs));
- hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
-
- x86_pmu.event_constraints = intel_slm_event_constraints;
- x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
- x86_pmu.extra_regs = intel_grt_extra_regs;
-
- x86_pmu.pebs_aliases = NULL;
- x86_pmu.pebs_prec_dist = true;
- x86_pmu.pebs_block = true;
- x86_pmu.lbr_pt_coexist = true;
- x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
+ intel_pmu_init_grt(NULL);
intel_pmu_pebs_data_source_grt();
x86_pmu.pebs_latency_data = adl_latency_data_small;
x86_pmu.get_event_constraints = tnt_get_event_constraints;
- x86_pmu.limit_period = spr_limit_period;
td_attr = tnt_events_attrs;
mem_attr = grt_mem_attrs;
extra_attr = nhm_format_attr;
@@ -6225,28 +6336,11 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_ATOM_CRESTMONT:
case INTEL_FAM6_ATOM_CRESTMONT_X:
- x86_pmu.mid_ack = true;
- memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
- sizeof(hw_cache_event_ids));
- memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
- sizeof(hw_cache_extra_regs));
- hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
-
- x86_pmu.event_constraints = intel_slm_event_constraints;
- x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+ intel_pmu_init_grt(NULL);
x86_pmu.extra_regs = intel_cmt_extra_regs;
-
- x86_pmu.pebs_aliases = NULL;
- x86_pmu.pebs_prec_dist = true;
- x86_pmu.lbr_pt_coexist = true;
- x86_pmu.pebs_block = true;
- x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
intel_pmu_pebs_data_source_cmt();
x86_pmu.pebs_latency_data = mtl_latency_data_small;
x86_pmu.get_event_constraints = cmt_get_event_constraints;
- x86_pmu.limit_period = spr_limit_period;
td_attr = cmt_events_attrs;
mem_attr = grt_mem_attrs;
extra_attr = cmt_format_attr;
@@ -6563,44 +6657,23 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_SAPPHIRERAPIDS_X:
case INTEL_FAM6_EMERALDRAPIDS_X:
x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
- x86_pmu.extra_regs = intel_spr_extra_regs;
+ x86_pmu.extra_regs = intel_glc_extra_regs;
fallthrough;
case INTEL_FAM6_GRANITERAPIDS_X:
case INTEL_FAM6_GRANITERAPIDS_D:
- pmem = true;
- x86_pmu.late_ack = true;
- memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
- memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-
- x86_pmu.event_constraints = intel_spr_event_constraints;
- x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints;
+ intel_pmu_init_glc(NULL);
if (!x86_pmu.extra_regs)
- x86_pmu.extra_regs = intel_gnr_extra_regs;
- x86_pmu.limit_period = spr_limit_period;
+ x86_pmu.extra_regs = intel_rwc_extra_regs;
x86_pmu.pebs_ept = 1;
- x86_pmu.pebs_aliases = NULL;
- x86_pmu.pebs_prec_dist = true;
- x86_pmu.pebs_block = true;
- x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
x86_pmu.hw_config = hsw_hw_config;
- x86_pmu.get_event_constraints = spr_get_event_constraints;
+ x86_pmu.get_event_constraints = glc_get_event_constraints;
extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
hsw_format_attr : nhm_format_attr;
extra_skl_attr = skl_format_attr;
- mem_attr = spr_events_attrs;
- td_attr = spr_td_events_attrs;
- tsx_attr = spr_tsx_events_attrs;
- x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
- x86_pmu.lbr_pt_coexist = true;
- intel_pmu_pebs_data_source_skl(pmem);
- x86_pmu.num_topdown_events = 8;
- static_call_update(intel_pmu_update_topdown_event,
- &icl_update_topdown_event);
- static_call_update(intel_pmu_set_topdown_event_period,
- &icl_set_topdown_event_period);
+ mem_attr = glc_events_attrs;
+ td_attr = glc_td_events_attrs;
+ tsx_attr = glc_tsx_events_attrs;
+ intel_pmu_pebs_data_source_skl(true);
pr_cont("Sapphire Rapids events, ");
name = "sapphire_rapids";
break;
@@ -6610,47 +6683,17 @@ __init int intel_pmu_init(void)
case INTEL_FAM6_RAPTORLAKE:
case INTEL_FAM6_RAPTORLAKE_P:
case INTEL_FAM6_RAPTORLAKE_S:
- case INTEL_FAM6_METEORLAKE:
- case INTEL_FAM6_METEORLAKE_L:
/*
* Alder Lake has 2 types of CPU, core and atom.
*
* Initialize the common PerfMon capabilities here.
*/
- x86_pmu.hybrid_pmu = kcalloc(X86_HYBRID_NUM_PMUS,
- sizeof(struct x86_hybrid_pmu),
- GFP_KERNEL);
- if (!x86_pmu.hybrid_pmu)
- return -ENOMEM;
- static_branch_enable(&perf_is_hybrid);
- x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
+ intel_pmu_init_hybrid(hybrid_big_small);
- x86_pmu.pebs_aliases = NULL;
- x86_pmu.pebs_prec_dist = true;
- x86_pmu.pebs_block = true;
- x86_pmu.flags |= PMU_FL_HAS_RSP_1;
- x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
- x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
- x86_pmu.lbr_pt_coexist = true;
x86_pmu.pebs_latency_data = adl_latency_data_small;
- x86_pmu.num_topdown_events = 8;
- static_call_update(intel_pmu_update_topdown_event,
- &adl_update_topdown_event);
- static_call_update(intel_pmu_set_topdown_event_period,
- &adl_set_topdown_event_period);
-
- x86_pmu.filter = intel_pmu_filter;
x86_pmu.get_event_constraints = adl_get_event_constraints;
x86_pmu.hw_config = adl_hw_config;
- x86_pmu.limit_period = spr_limit_period;
x86_pmu.get_hybrid_cpu_type = adl_get_hybrid_cpu_type;
- /*
- * The rtm_abort_event is used to check whether to enable GPRs
- * for the RTM abort event. Atom doesn't have the RTM abort
- * event. There is no harmful to set it in the common
- * x86_pmu.rtm_abort_event.
- */
- x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
td_attr = adl_hybrid_events_attrs;
mem_attr = adl_hybrid_mem_attrs;
@@ -6660,9 +6703,7 @@ __init int intel_pmu_init(void)
/* Initialize big core specific PerfMon capabilities.*/
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
- pmu->name = "cpu_core";
- pmu->cpu_type = hybrid_big;
- pmu->late_ack = true;
+ intel_pmu_init_glc(&pmu->pmu);
if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
pmu->num_counters = x86_pmu.num_counters + 2;
pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
@@ -6687,54 +6728,45 @@ __init int intel_pmu_init(void)
pmu->unconstrained = (struct event_constraint)
__EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
0, pmu->num_counters, 0, 0);
- pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
- pmu->intel_cap.perf_metrics = 1;
- pmu->intel_cap.pebs_output_pt_available = 0;
+ pmu->extra_regs = intel_glc_extra_regs;
+
+ /* Initialize Atom core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+ intel_pmu_init_grt(&pmu->pmu);
+
+ x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+ intel_pmu_pebs_data_source_adl();
+ pr_cont("Alderlake Hybrid events, ");
+ name = "alderlake_hybrid";
+ break;
+
+ case INTEL_FAM6_METEORLAKE:
+ case INTEL_FAM6_METEORLAKE_L:
+ intel_pmu_init_hybrid(hybrid_big_small);
- memcpy(pmu->hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids));
- memcpy(pmu->hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs));
- pmu->event_constraints = intel_spr_event_constraints;
- pmu->pebs_constraints = intel_spr_pebs_event_constraints;
- pmu->extra_regs = intel_spr_extra_regs;
+ x86_pmu.pebs_latency_data = mtl_latency_data_small;
+ x86_pmu.get_event_constraints = mtl_get_event_constraints;
+ x86_pmu.hw_config = adl_hw_config;
+
+ td_attr = adl_hybrid_events_attrs;
+ mem_attr = mtl_hybrid_mem_attrs;
+ tsx_attr = adl_hybrid_tsx_attrs;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+ /* Initialize big core specific PerfMon capabilities.*/
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+ intel_pmu_init_glc(&pmu->pmu);
+ pmu->extra_regs = intel_rwc_extra_regs;
/* Initialize Atom core specific PerfMon capabilities.*/
pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
- pmu->name = "cpu_atom";
- pmu->cpu_type = hybrid_small;
- pmu->mid_ack = true;
- pmu->num_counters = x86_pmu.num_counters;
- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
- pmu->max_pebs_events = x86_pmu.max_pebs_events;
- pmu->unconstrained = (struct event_constraint)
- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
- 0, pmu->num_counters, 0, 0);
- pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
- pmu->intel_cap.perf_metrics = 0;
- pmu->intel_cap.pebs_output_pt_available = 1;
-
- memcpy(pmu->hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids));
- memcpy(pmu->hw_cache_extra_regs, tnt_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs));
- pmu->hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
- pmu->event_constraints = intel_slm_event_constraints;
- pmu->pebs_constraints = intel_grt_pebs_event_constraints;
- pmu->extra_regs = intel_grt_extra_regs;
- if (is_mtl(boot_cpu_data.x86_model)) {
- x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs;
- x86_pmu.pebs_latency_data = mtl_latency_data_small;
- extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
- mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
- mem_attr = mtl_hybrid_mem_attrs;
- intel_pmu_pebs_data_source_mtl();
- x86_pmu.get_event_constraints = mtl_get_event_constraints;
- pmu->extra_regs = intel_cmt_extra_regs;
- pr_cont("Meteorlake Hybrid events, ");
- name = "meteorlake_hybrid";
- } else {
- x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
- intel_pmu_pebs_data_source_adl();
- pr_cont("Alderlake Hybrid events, ");
- name = "alderlake_hybrid";
- }
+ intel_pmu_init_grt(&pmu->pmu);
+ pmu->extra_regs = intel_cmt_extra_regs;
+
+ intel_pmu_pebs_data_source_mtl();
+ pr_cont("Meteorlake Hybrid events, ");
+ name = "meteorlake_hybrid";
break;
default:
@@ -6846,9 +6878,6 @@ __init int intel_pmu_init(void)
if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
- if (is_hybrid())
- intel_pmu_check_hybrid_pmus((u64)fixed_mask);
-
if (x86_pmu.intel_cap.pebs_timing_info)
x86_pmu.flags |= PMU_FL_RETIRE_LATENCY;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 96fffb2d521d..cbeb6d2bf5b4 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -336,6 +336,9 @@ static int cstate_pmu_event_init(struct perf_event *event)
cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
if (!(pkg_msr_mask & (1 << cfg)))
return -EINVAL;
+
+ event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
event->hw.event_base = pkg_msr[cfg].msr;
cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
topology_die_cpumask(event->cpu));
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index eb8dd8b8a1e8..bf97ab904d40 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -261,7 +261,7 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
{
u64 val;
- WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big);
+ WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
dse &= PERF_PEBS_DATA_SOURCE_MASK;
val = hybrid_var(event->pmu, pebs_data_source)[dse];
@@ -1058,7 +1058,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
EVENT_CONSTRAINT_END
};
-struct event_constraint intel_spr_pebs_event_constraints[] = {
+struct event_constraint intel_glc_pebs_event_constraints[] = {
INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */
INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 42a55794004a..8e2a12235e62 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -736,6 +736,7 @@ static bool topa_table_full(struct topa *topa)
/**
* topa_insert_pages() - create a list of ToPA tables
* @buf: PT buffer being initialized.
+ * @cpu: CPU on which to allocate.
* @gfp: Allocation flags.
*
* This initializes a list of ToPA tables with entries from
@@ -1207,8 +1208,11 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf)
/**
* pt_buffer_init_topa() - initialize ToPA table for pt buffer
* @buf: PT buffer.
- * @size: Total size of all regions within this ToPA.
+ * @cpu: CPU on which to allocate.
+ * @nr_pages: No. of pages to allocate.
* @gfp: Allocation flags.
+ *
+ * Return: 0 on success or error code.
*/
static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu,
unsigned long nr_pages, gfp_t gfp)
@@ -1281,7 +1285,7 @@ out:
/**
* pt_buffer_setup_aux() - set up topa tables for a PT buffer
- * @cpu: Cpu on which to allocate, -1 means current.
+ * @event: Performance event
* @pages: Array of pointers to buffer pages passed from perf core.
* @nr_pages: Number of pages in the buffer.
* @snapshot: If this is a snapshot/overwrite counter.
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 69043e02e8a7..01023aa5125b 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -74,7 +74,7 @@ int uncore_device_to_die(struct pci_dev *dev)
struct cpuinfo_x86 *c = &cpu_data(cpu);
if (c->initialized && cpu_to_node(cpu) == node)
- return c->logical_die_id;
+ return c->topo.logical_die_id;
}
return -1;
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c8ba2be7585d..53dd5d495ba6 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -652,10 +652,29 @@ enum {
#define PERF_PEBS_DATA_SOURCE_MAX 0x10
#define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1)
+enum hybrid_cpu_type {
+ HYBRID_INTEL_NONE,
+ HYBRID_INTEL_ATOM = 0x20,
+ HYBRID_INTEL_CORE = 0x40,
+};
+
+enum hybrid_pmu_type {
+ not_hybrid,
+ hybrid_small = BIT(0),
+ hybrid_big = BIT(1),
+
+ hybrid_big_small = hybrid_big | hybrid_small, /* only used for matching */
+};
+
+#define X86_HYBRID_PMU_ATOM_IDX 0
+#define X86_HYBRID_PMU_CORE_IDX 1
+
+#define X86_HYBRID_NUM_PMUS 2
+
struct x86_hybrid_pmu {
struct pmu pmu;
const char *name;
- u8 cpu_type;
+ enum hybrid_pmu_type pmu_type;
cpumask_t supported_cpus;
union perf_capabilities intel_cap;
u64 intel_ctrl;
@@ -721,18 +740,6 @@ extern struct static_key_false perf_is_hybrid;
__Fp; \
})
-enum hybrid_pmu_type {
- hybrid_big = 0x40,
- hybrid_small = 0x20,
-
- hybrid_big_small = hybrid_big | hybrid_small,
-};
-
-#define X86_HYBRID_PMU_ATOM_IDX 0
-#define X86_HYBRID_PMU_CORE_IDX 1
-
-#define X86_HYBRID_NUM_PMUS 2
-
/*
* struct x86_pmu - generic x86 pmu
*/
@@ -940,7 +947,7 @@ struct x86_pmu {
*/
int num_hybrid_pmus;
struct x86_hybrid_pmu *hybrid_pmu;
- u8 (*get_hybrid_cpu_type) (void);
+ enum hybrid_cpu_type (*get_hybrid_cpu_type) (void);
};
struct x86_perf_task_context_opt {
@@ -1521,7 +1528,7 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
extern struct event_constraint intel_icl_pebs_event_constraints[];
-extern struct event_constraint intel_spr_pebs_event_constraints[];
+extern struct event_constraint intel_glc_pebs_event_constraints[];
struct event_constraint *intel_pebs_constraints(struct perf_event *event);
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 1579429846cc..8d98d468b976 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -115,7 +115,7 @@ struct rapl_pmu {
struct rapl_pmus {
struct pmu pmu;
unsigned int maxdie;
- struct rapl_pmu *pmus[];
+ struct rapl_pmu *pmus[] __counted_by(maxdie);
};
enum rapl_unit_quirk {
@@ -179,15 +179,11 @@ static u64 rapl_event_update(struct perf_event *event)
s64 delta, sdelta;
int shift = RAPL_CNTR_WIDTH;
-again:
prev_raw_count = local64_read(&hwc->prev_count);
- rdmsrl(event->hw.event_base, new_raw_count);
-
- if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
- new_raw_count) != prev_raw_count) {
- cpu_relax();
- goto again;
- }
+ do {
+ rdmsrl(event->hw.event_base, new_raw_count);
+ } while (!local64_try_cmpxchg(&hwc->prev_count,
+ &prev_raw_count, new_raw_count));
/*
* Now we have the new raw value and have updated the prev
@@ -537,11 +533,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = {
* - want to use same event codes across both architectures
*/
static struct perf_msr amd_rapl_msrs[] = {
- [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 },
+ [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, NULL, false, 0 },
[PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK },
- [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 },
- [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 },
- [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 },
+ [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, NULL, false, 0 },
+ [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, NULL, false, 0 },
+ [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, NULL, false, 0 },
};
static int rapl_cpu_offline(unsigned int cpu)
diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c
index 76b1f8bb0fd5..dab4ed199227 100644
--- a/arch/x86/events/utils.c
+++ b/arch/x86/events/utils.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <asm/insn.h>
+#include <linux/mm.h>
#include "perf_event.h"
@@ -132,9 +133,9 @@ static int get_branch_type(unsigned long from, unsigned long to, int abort,
* The LBR logs any address in the IP, even if the IP just
* faulted. This means userspace can control the from address.
* Ensure we don't blindly read any address by validating it is
- * a known text address.
+ * a known text address and not a vsyscall address.
*/
- if (kernel_text_address(from)) {
+ if (kernel_text_address(from) && !in_gate_area_no_mm(from)) {
addr = (void *)from;
/*
* Assume we can get the maximum possible size
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 783ed339f341..21556ad87f4b 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -7,6 +7,8 @@
* Author : K. Y. Srinivasan <kys@microsoft.com>
*/
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
#include <linux/efi.h>
#include <linux/types.h>
#include <linux/bitfield.h>
@@ -191,7 +193,7 @@ void set_hv_tscchange_cb(void (*cb)(void))
struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
if (!hv_reenlightenment_available()) {
- pr_warn("Hyper-V: reenlightenment support is unavailable\n");
+ pr_warn("reenlightenment support is unavailable\n");
return;
}
@@ -394,6 +396,7 @@ static void __init hv_get_partition_id(void)
local_irq_restore(flags);
}
+#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
static u8 __init get_vtl(void)
{
u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
@@ -416,13 +419,16 @@ static u8 __init get_vtl(void)
if (hv_result_success(ret)) {
ret = output->as64.low & HV_X64_VTL_MASK;
} else {
- pr_err("Failed to get VTL(%lld) and set VTL to zero by default.\n", ret);
- ret = 0;
+ pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
+ BUG();
}
local_irq_restore(flags);
return ret;
}
+#else
+static inline u8 get_vtl(void) { return 0; }
+#endif
/*
* This function is to be invoked early in the boot sequence after the
@@ -564,7 +570,7 @@ skip_hypercall_pg_init:
if (cpu_feature_enabled(X86_FEATURE_IBT) &&
*(u32 *)hv_hypercall_pg != gen_endbr()) {
setup_clear_cpu_cap(X86_FEATURE_IBT);
- pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n");
+ pr_warn("Disabling IBT because of Hyper-V bug\n");
}
#endif
@@ -604,8 +610,10 @@ skip_hypercall_pg_init:
hv_query_ext_cap(0);
/* Find the VTL */
- if (!ms_hyperv.paravisor_present && hv_isolation_type_snp())
- ms_hyperv.vtl = get_vtl();
+ ms_hyperv.vtl = get_vtl();
+
+ if (ms_hyperv.vtl > 0) /* non default VTL */
+ hv_vtl_early_init();
return;
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 36a562218010..96e6c51515f5 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -196,7 +196,7 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id)
return ret;
}
-static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
{
int vp_id;
@@ -215,7 +215,7 @@ static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip)
return hv_vtl_bringup_vcpu(vp_id, start_eip);
}
-static int __init hv_vtl_early_init(void)
+int __init hv_vtl_early_init(void)
{
/*
* `boot_cpu_has` returns the runtime feature support,
@@ -230,4 +230,3 @@ static int __init hv_vtl_early_init(void)
return 0;
}
-early_initcall(hv_vtl_early_init);
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 8c6bf07f7d2b..c6edde1a1dec 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -288,7 +288,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
free_page((unsigned long)vmsa);
}
-int hv_snp_boot_ap(int cpu, unsigned long start_ip)
+int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
{
struct sev_es_save_area *vmsa = (struct sev_es_save_area *)
__get_free_page(GFP_KERNEL | __GFP_ZERO);
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4f1ce5fc4e19..a192bdea69e2 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -10,5 +10,4 @@ generated-y += unistd_64_x32.h
generated-y += xen-hypercalls.h
generic-y += early_ioremap.h
-generic-y += export.h
generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 9c4da699e11a..65f79092c9d9 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -58,7 +58,7 @@
#define ANNOTATE_IGNORE_ALTERNATIVE \
"999:\n\t" \
".pushsection .discard.ignore_alts\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
/*
@@ -352,7 +352,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
.macro ANNOTATE_IGNORE_ALTERNATIVE
.Lannotate_\@:
.pushsection .discard.ignore_alts
- .long .Lannotate_\@ - .
+ .long .Lannotate_\@
.popsection
.endm
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 5af4ec1a0f71..b0d192f613b7 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -54,7 +54,7 @@ extern int local_apic_timer_c2_ok;
extern bool apic_is_disabled;
extern unsigned int lapic_timer_period;
-extern int cpuid_to_apicid[];
+extern u32 cpuid_to_apicid[];
extern enum apic_intr_mode_id apic_intr_mode;
enum apic_intr_mode_id {
@@ -292,19 +292,19 @@ struct apic {
int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
bool (*apic_id_registered)(void);
- bool (*check_apicid_used)(physid_mask_t *map, int apicid);
+ bool (*check_apicid_used)(physid_mask_t *map, u32 apicid);
void (*init_apic_ldr)(void);
void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
- int (*cpu_present_to_apicid)(int mps_cpu);
- int (*phys_pkg_id)(int cpuid_apic, int index_msb);
+ u32 (*cpu_present_to_apicid)(int mps_cpu);
+ u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
- u32 (*get_apic_id)(unsigned long x);
- u32 (*set_apic_id)(unsigned int id);
+ u32 (*get_apic_id)(u32 id);
+ u32 (*set_apic_id)(u32 apicid);
/* wakeup_secondary_cpu */
- int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
/* wakeup secondary CPU using 64-bit wakeup point */
- int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
char *name;
};
@@ -322,8 +322,8 @@ struct apic_override {
void (*send_IPI_self)(int vector);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
- int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip);
- int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
};
/*
@@ -493,16 +493,6 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector)
return !!(irr & (1U << (vector % 32)));
}
-static inline unsigned default_get_apic_id(unsigned long x)
-{
- unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-
- if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
- return (x >> 24) & 0xFF;
- else
- return (x >> 24) & 0x0F;
-}
-
/*
* Warm reset vector position:
*/
@@ -517,9 +507,9 @@ extern void generic_bigsmp_probe(void);
extern struct apic apic_noop;
-static inline unsigned int read_apic_id(void)
+static inline u32 read_apic_id(void)
{
- unsigned int reg = apic_read(APIC_ID);
+ u32 reg = apic_read(APIC_ID);
return apic->get_apic_id(reg);
}
@@ -538,13 +528,12 @@ extern int default_apic_id_valid(u32 apicid);
extern u32 apic_default_calc_apicid(unsigned int cpu);
extern u32 apic_flat_calc_apicid(unsigned int cpu);
-extern bool default_check_apicid_used(physid_mask_t *map, int apicid);
extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap);
-extern int default_cpu_present_to_apicid(int mps_cpu);
+extern u32 default_cpu_present_to_apicid(int mps_cpu);
#else /* CONFIG_X86_LOCAL_APIC */
-static inline unsigned int read_apic_id(void) { return 0; }
+static inline u32 read_apic_id(void) { return 0; }
#endif /* !CONFIG_X86_LOCAL_APIC */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 2edf68475fec..50e5ebf9d0a0 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -293,6 +293,9 @@ static __always_inline unsigned long variable_ffz(unsigned long word)
*/
static __always_inline unsigned long __fls(unsigned long word)
{
+ if (__builtin_constant_p(word))
+ return BITS_PER_LONG - 1 - __builtin_clzl(word);
+
asm("bsr %1,%0"
: "=r" (word)
: "rm" (word));
@@ -360,6 +363,9 @@ static __always_inline int fls(unsigned int x)
{
int r;
+ if (__builtin_constant_p(x))
+ return x ? 32 - __builtin_clz(x) : 0;
+
#ifdef CONFIG_X86_64
/*
* AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
@@ -401,6 +407,9 @@ static __always_inline int fls(unsigned int x)
static __always_inline int fls64(__u64 x)
{
int bitpos = -1;
+
+ if (__builtin_constant_p(x))
+ return x ? 64 - __builtin_clzll(x) : 0;
/*
* AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
* dest reg is undefined if x==0, but their CPU architect says its
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 4ae14339cb8c..a38cc0afc90a 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -40,23 +40,40 @@
#ifdef CONFIG_X86_64
# define BOOT_STACK_SIZE 0x4000
+/*
+ * Used by decompressor's startup_32() to allocate page tables for identity
+ * mapping of the 4G of RAM in 4-level paging mode:
+ * - 1 level4 table;
+ * - 1 level3 table;
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
+ */
# define BOOT_INIT_PGT_SIZE (6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
+
/*
- * Assuming all cross the 512GB boundary:
- * 1 page for level4
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
- * Total is 19 pages.
+ * Total number of page tables kernel_add_identity_map() can allocate,
+ * including page tables consumed by startup_32().
+ *
+ * Worst-case scenario:
+ * - 5-level paging needs 1 level5 table;
+ * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ * assuming all of them cross 256T boundary:
+ * + 4*2 level4 table;
+ * + 4*2 level3 table;
+ * + 4*2 level2 table;
+ * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ * + 1 level4 table;
+ * + 1 level3 table;
+ * + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
*/
-# ifdef CONFIG_X86_VERBOSE_BOOTUP
-# define BOOT_PGT_SIZE (19*4096)
-# else /* !CONFIG_X86_VERBOSE_BOOTUP */
-# define BOOT_PGT_SIZE (17*4096)
-# endif
-# else /* !CONFIG_RANDOMIZE_BASE */
-# define BOOT_PGT_SIZE BOOT_INIT_PGT_SIZE
-# endif
+# define BOOT_PGT_SIZE_WARN (28*4096)
+# define BOOT_PGT_SIZE (32*4096)
#else /* !CONFIG_X86_64 */
# define BOOT_STACK_SIZE 0x1000
@@ -68,6 +85,8 @@ extern const unsigned long kernel_total_size;
unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
void (*error)(char *x));
+
+extern struct boot_params *boot_params_ptr;
#endif
#endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h
index ce9685fc78d8..5aa061199866 100644
--- a/arch/x86/include/asm/cacheinfo.h
+++ b/arch/x86/include/asm/cacheinfo.h
@@ -7,9 +7,6 @@ extern unsigned int memory_caching_control;
#define CACHE_MTRR 0x01
#define CACHE_PAT 0x02
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu);
-
void cache_disable(void);
void cache_enable(void);
void set_cache_aps_delayed_init(bool val);
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index d53636506134..5612648b0202 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -221,12 +221,18 @@ extern void __add_wrong_size(void)
#define __try_cmpxchg(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX)
+#define __sync_try_cmpxchg(ptr, pold, new, size) \
+ __raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ")
+
#define __try_cmpxchg_local(ptr, pold, new, size) \
__raw_try_cmpxchg((ptr), (pold), (new), (size), "")
#define arch_try_cmpxchg(ptr, pold, new) \
__try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+#define arch_sync_try_cmpxchg(ptr, pold, new) \
+ __sync_try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr)))
+
#define arch_try_cmpxchg_local(ptr, pold, new) \
__try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr)))
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 3a233ebff712..25050d953eee 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -28,8 +28,6 @@ struct x86_cpu {
};
#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
extern void soft_restart_cpu(void);
#endif
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b0994ae3bc23..c4555b269a1b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
#ifdef CONFIG_X86_32
#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1)
-
-#define arch_efi_call_virt_setup() \
-({ \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
-})
-
-#define arch_efi_call_virt_teardown() \
-({ \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#else /* !CONFIG_X86_32 */
#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
__efi_call(__VA_ARGS__); \
})
-#define arch_efi_call_virt_setup() \
-({ \
- efi_sync_low_kernel_mappings(); \
- efi_fpu_begin(); \
- firmware_restrict_branch_speculation_start(); \
- efi_enter_mm(); \
-})
-
#undef arch_efi_call_virt
#define arch_efi_call_virt(p, f, args...) ({ \
u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime); \
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
ret; \
})
-#define arch_efi_call_virt_teardown() \
-({ \
- efi_leave_mm(); \
- firmware_restrict_branch_speculation_end(); \
- efi_fpu_end(); \
-})
-
#ifdef CONFIG_KASAN
/*
* CONFIG_KASAN may redefine memset to __memset. __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
extern void efi_free_boot_services(void);
-void efi_enter_mm(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
/* kexec external ABI */
struct efi_setup_data {
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 18fd06f7936a..a0234dfd1031 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -7,6 +7,7 @@
*/
#include <linux/thread_info.h>
+#include <asm/ia32.h>
#include <asm/ptrace.h>
#include <asm/user.h>
#include <asm/auxvec.h>
@@ -149,7 +150,7 @@ do { \
((x)->e_machine == EM_X86_64)
#define compat_elf_check_arch(x) \
- (elf_check_arch_ia32(x) || \
+ ((elf_check_arch_ia32(x) && ia32_enabled()) || \
(IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64))
static inline void elf_common_init(struct thread_struct *t,
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 31089b851c4f..a2be3aefff9f 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) {
static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
#endif
-extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru);
extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 551829884734..b02c3cd3c0f6 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -28,7 +28,7 @@
#include <asm/irq.h>
#include <asm/sections.h>
-#ifdef CONFIG_X86_LOCAL_APIC
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
struct irq_data;
struct pci_dev;
struct msi_desc;
@@ -105,10 +105,10 @@ static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
extern void apic_ack_edge(struct irq_data *data);
-#else /* CONFIG_X86_LOCAL_APIC */
+#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
-#endif /* CONFIG_X86_LOCAL_APIC */
+#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
/* Statistics */
extern atomic_t irq_err_count;
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 637fa1df3512..c715097e92fd 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -69,6 +69,8 @@ struct legacy_pic {
void (*make_irq)(unsigned int irq);
};
+void legacy_pic_pcat_compat(void);
+
extern struct legacy_pic *legacy_pic;
extern struct legacy_pic null_legacy_pic;
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index fada857f0a1e..5a2ae24b1204 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -68,6 +68,20 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm);
#endif
-#endif /* CONFIG_IA32_EMULATION */
+extern bool __ia32_enabled;
+
+static inline bool ia32_enabled(void)
+{
+ return __ia32_enabled;
+}
+
+#else /* !CONFIG_IA32_EMULATION */
+
+static inline bool ia32_enabled(void)
+{
+ return IS_ENABLED(CONFIG_X86_32);
+}
+
+#endif
#endif /* _ASM_X86_IA32_H */
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 5f1d3c421f68..cc9ccf61b6bd 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_INIT_H
#define _ASM_X86_INIT_H
+#define __head __section(".head.text")
+
struct x86_mapping_info {
void *(*alloc_pgt_page)(void *); /* allocate buf for page table */
void *context; /* context for alloc_pgt_page */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 5fcd85fd64fd..197316121f04 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -27,6 +27,7 @@
* _X - regular server parts
* _D - micro server parts
* _N,_P - other mobile parts
+ * _H - premium mobile parts
* _S - other client parts
*
* Historical OPTDIFFs:
@@ -124,6 +125,7 @@
#define INTEL_FAM6_METEORLAKE 0xAC
#define INTEL_FAM6_METEORLAKE_L 0xAA
+#define INTEL_FAM6_ARROWLAKE_H 0xC5
#define INTEL_FAM6_ARROWLAKE 0xC6
#define INTEL_FAM6_LUNARLAKE_M 0xBD
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1a4def36d5bb..70d139406bc8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -528,7 +528,6 @@ struct kvm_pmu {
u64 raw_event_mask;
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
- struct irq_work irq_work;
/*
* Overlay the bitmap with a 64-bit atomic so that all bits can be
@@ -1419,7 +1418,6 @@ struct kvm_arch {
* the thread holds the MMU lock in write mode.
*/
spinlock_t tdp_mmu_pages_lock;
- struct workqueue_struct *tdp_mmu_zap_wq;
#endif /* CONFIG_X86_64 */
/*
@@ -1835,7 +1833,7 @@ void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 97a3de7892d3..571fe4d2d232 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,6 +8,14 @@
#undef notrace
#define notrace __attribute__((no_instrument_function))
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
#ifdef CONFIG_X86_32
#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
#endif /* CONFIG_X86_32 */
@@ -97,6 +105,13 @@
CFI_POST_PADDING \
SYM_FUNC_END(__cfi_##name)
+/* UML needs to be able to override memcpy() and friends for KASAN. */
+#ifdef CONFIG_UML
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK
+#else
+# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS
+#endif
+
/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */
#define SYM_TYPED_FUNC_START(name) \
SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 635132a12778..73dba8b94443 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -135,28 +135,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
/**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
* @l: pointer of type local_t
* @a: the amount to add to l...
* @u: ...unless l is equal to u.
*
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
*/
-#define local_add_unless(l, a, u) \
-({ \
- long c, old; \
- c = local_read((l)); \
- for (;;) { \
- if (unlikely(c == (u))) \
- break; \
- old = local_cmpxchg((l), c, c + (a)); \
- if (likely(old == c)) \
- break; \
- c = old; \
- } \
- c != (u); \
-})
+static __always_inline bool
+local_add_unless(local_t *l, long a, long u)
+{
+ long c = local_read(l);
+
+ do {
+ if (unlikely(c == u))
+ return false;
+ } while (!local_try_cmpxchg(l, &c, c + a));
+
+ return true;
+}
+
#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
/* On x86_32, these are no better than the atomic variants.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 180b1cbfcc4e..6de6e1d95952 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -245,7 +245,7 @@ static inline void cmci_recheck(void) {}
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
bool mce_is_correctable(struct mce *m);
-int mce_usable_address(struct mce *m);
+bool mce_usable_address(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 473b16d73b47..359ada486fa9 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -19,8 +19,10 @@
#ifdef CONFIG_X86_MEM_ENCRYPT
void __init mem_encrypt_init(void);
+void __init mem_encrypt_setup_arch(void);
#else
static inline void mem_encrypt_init(void) { }
+static inline void __init mem_encrypt_setup_arch(void) { }
#endif
#ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -43,7 +45,6 @@ void __init sme_map_bootdata(char *real_mode_data);
void __init sme_unmap_bootdata(char *real_mode_data);
void __init sme_early_init(void);
-void __init sev_setup_arch(void);
void __init sme_encrypt_kernel(struct boot_params *bp);
void __init sme_enable(struct boot_params *bp);
@@ -73,7 +74,6 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { }
static inline void __init sme_unmap_bootdata(char *real_mode_data) { }
static inline void __init sme_early_init(void) { }
-static inline void __init sev_setup_arch(void) { }
static inline void __init sme_encrypt_kernel(struct boot_params *bp) { }
static inline void __init sme_enable(struct boot_params *bp) { }
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 416901d406f8..8dac45a2c7fc 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -186,8 +186,7 @@ do { \
#else
#define deactivate_mm(tsk, mm) \
do { \
- if (!tsk->vfork_done) \
- shstk_free(tsk); \
+ shstk_free(tsk); \
load_gs_index(0); \
loadsegment(fs, 0); \
} while (0)
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index f46df8349e86..4b0f98a8d338 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -37,7 +37,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES];
extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
-extern unsigned int boot_cpu_physical_apicid;
+extern u32 boot_cpu_physical_apicid;
extern u8 boot_cpu_apic_version;
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 033b53f993c6..ce4ce8720d55 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -276,11 +276,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
#ifdef CONFIG_AMD_MEM_ENCRYPT
bool hv_ghcb_negotiate_protocol(void);
void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(int cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
#else
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(int cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
#endif
#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
@@ -340,8 +340,10 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; }
#ifdef CONFIG_HYPERV_VTL_MODE
void __init hv_vtl_init_platform(void);
+int __init hv_vtl_early_init(void);
#else
static inline void __init hv_vtl_init_platform(void) {}
+static inline int __init hv_vtl_early_init(void) { return 0; }
#endif
#include <asm-generic/mshyperv.h>
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1d111350197f..e3fa9cecd599 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -637,12 +637,21 @@
/* AMD Last Branch Record MSRs */
#define MSR_AMD64_LBR_SELECT 0xc000010e
+/* Zen4 */
+#define MSR_ZEN4_BP_CFG 0xc001102e
+#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL 0xc0010800
+#define MSR_F19H_UMC_PERF_CTR 0xc0010801
+
+/* Zen 2 */
+#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
+
/* Fam 17h MSRs */
#define MSR_F17H_IRPERF 0xc00000e9
-#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1)
-
/* Fam 16h MSRs */
#define MSR_F16H_L2I_PERF_CTL 0xc0010230
#define MSR_F16H_L2I_PERF_CTR 0xc0010231
@@ -1112,12 +1121,16 @@
#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14)
#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-/* AMD-V MSRs */
+/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
#define MSR_VM_IGNNE 0xc0010115
#define MSR_VM_HSAVE_PA 0xc0010117
+#define SVM_VM_CR_VALID_MASK 0x001fULL
+#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
+#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
+
/* Hardware Feedback Interface */
#define MSR_IA32_HW_FEEDBACK_PTR 0x17d0
#define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index c55cc243592e..f93e9b96927a 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -196,7 +196,7 @@
.macro ANNOTATE_RETPOLINE_SAFE
.Lhere_\@:
.pushsection .discard.retpoline_safe
- .long .Lhere_\@ - .
+ .long .Lhere_\@
.popsection
.endm
@@ -271,7 +271,7 @@
.Lskip_rsb_\@:
.endm
-#ifdef CONFIG_CPU_UNRET_ENTRY
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
#define CALL_UNTRAIN_RET "call entry_untrain_ret"
#else
#define CALL_UNTRAIN_RET ""
@@ -288,38 +288,24 @@
* As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
* where we have a stack but before any RET instruction.
*/
-.macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
+.macro __UNTRAIN_RET ibpb_feature, call_depth_insns
+#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY)
VALIDATE_UNRET_END
ALTERNATIVE_3 "", \
CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+ "call entry_ibpb", \ibpb_feature, \
+ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH
#endif
.endm
-.macro UNTRAIN_RET_VM
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \
- __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH)
-.macro UNTRAIN_RET_FROM_CALL
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
- defined(CONFIG_CALL_DEPTH_TRACKING)
- VALIDATE_UNRET_END
- ALTERNATIVE_3 "", \
- CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \
- "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \
- __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH
-#endif
-.endm
+#define UNTRAIN_RET_VM \
+ __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH)
+
+#define UNTRAIN_RET_FROM_CALL \
+ __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL)
.macro CALL_DEPTH_ACCOUNT
@@ -334,7 +320,7 @@
#define ANNOTATE_RETPOLINE_SAFE \
"999:\n\t" \
".pushsection .discard.retpoline_safe\n\t" \
- ".long 999b - .\n\t" \
+ ".long 999b\n\t" \
".popsection\n\t"
typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
@@ -348,13 +334,23 @@ extern void __x86_return_thunk(void);
static inline void __x86_return_thunk(void) {}
#endif
+#ifdef CONFIG_CPU_UNRET_ENTRY
extern void retbleed_return_thunk(void);
+#else
+static inline void retbleed_return_thunk(void) {}
+#endif
+
+#ifdef CONFIG_CPU_SRSO
extern void srso_return_thunk(void);
extern void srso_alias_return_thunk(void);
+#else
+static inline void srso_return_thunk(void) {}
+static inline void srso_alias_return_thunk(void) {}
+#endif
-extern void retbleed_untrain_ret(void);
-extern void srso_untrain_ret(void);
-extern void srso_alias_untrain_ret(void);
+extern void retbleed_return_thunk(void);
+extern void srso_return_thunk(void);
+extern void srso_alias_return_thunk(void);
extern void entry_untrain_ret(void);
extern void entry_ibpb(void);
@@ -362,12 +358,7 @@ extern void entry_ibpb(void);
extern void (*x86_return_thunk)(void);
#ifdef CONFIG_CALL_DEPTH_TRACKING
-extern void __x86_return_skl(void);
-
-static inline void x86_set_skl_return_thunk(void)
-{
- x86_return_thunk = &__x86_return_skl;
-}
+extern void call_depth_return_thunk(void);
#define CALL_DEPTH_ACCOUNT \
ALTERNATIVE("", \
@@ -380,12 +371,12 @@ DECLARE_PER_CPU(u64, __x86_ret_count);
DECLARE_PER_CPU(u64, __x86_stuffs_count);
DECLARE_PER_CPU(u64, __x86_ctxsw_count);
#endif
-#else
-static inline void x86_set_skl_return_thunk(void) {}
+#else /* !CONFIG_CALL_DEPTH_TRACKING */
+static inline void call_depth_return_thunk(void) {}
#define CALL_DEPTH_ACCOUNT ""
-#endif
+#endif /* CONFIG_CALL_DEPTH_TRACKING */
#ifdef CONFIG_RETPOLINE
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index e3bae2b60a0d..ef2844d69173 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -12,13 +12,6 @@
#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-/*
- * Too small node sizes may confuse the VM badly. Usually they
- * result from BIOS bugs. So dont recognize nodes as standalone
- * NUMA entities that have less than this amount of RAM listed:
- */
-#define NODE_MIN_SIZE (4*1024*1024)
-
extern int numa_off;
/*
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 4acbcddddc29..772d03487520 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -9,13 +9,6 @@ struct paravirt_patch_site {
u8 type; /* type of this instruction */
u8 len; /* length of original instruction */
};
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
- PARAVIRT_LAZY_NONE,
- PARAVIRT_LAZY_MMU,
- PARAVIRT_LAZY_CPU,
-};
#endif
#ifdef CONFIG_PARAVIRT
@@ -549,14 +542,6 @@ int paravirt_disable_iospace(void);
__PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \
PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4))
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_start_context_switch(struct task_struct *prev);
-void paravirt_end_context_switch(struct task_struct *next);
-
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_flush_lazy_mmu(void);
-
void _paravirt_nop(void);
void paravirt_BUG(void);
unsigned long paravirt_ret0(void);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 34734d730463..20624b80f890 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -210,6 +210,25 @@ do { \
(typeof(_var))(unsigned long) pco_old__; \
})
+#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval) \
+({ \
+ bool success; \
+ __pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
+ __pcpu_type_##size pco_old__ = *pco_oval__; \
+ __pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
+ asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
+ __percpu_arg([var])) \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [oval] "+a" (pco_old__), \
+ [var] "+m" (_var) \
+ : [nval] __pcpu_reg_##size(, pco_new__) \
+ : "memory"); \
+ if (unlikely(!success)) \
+ *pco_oval__ = pco_old__; \
+ likely(success); \
+})
+
#if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval) \
({ \
@@ -223,26 +242,63 @@ do { \
old__.var = _oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("leal %P[var], %%esi; call this_cpu_cmpxchg8b_emu", \
+ asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
"cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
: [var] "+m" (_var), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
- "c" (new__.high) \
- : "memory", "esi"); \
+ "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
\
old__.var; \
})
#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval)
#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval) \
+({ \
+ bool success; \
+ u64 *_oval = (u64 *)(_ovalp); \
+ union { \
+ u64 var; \
+ struct { \
+ u32 low, high; \
+ }; \
+ } old__, new__; \
+ \
+ old__.var = *_oval; \
+ new__.var = _nval; \
+ \
+ asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \
+ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [var] "+m" (_var), \
+ "+a" (old__.low), \
+ "+d" (old__.high) \
+ : "b" (new__.low), \
+ "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
+ if (unlikely(!success)) \
+ *_oval = old__.var; \
+ likely(success); \
+})
+
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval)
#endif
#ifdef CONFIG_X86_64
#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval);
#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval);
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval);
+
#define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval) \
({ \
union { \
@@ -255,20 +311,54 @@ do { \
old__.var = _oval; \
new__.var = _nval; \
\
- asm qual (ALTERNATIVE("leaq %P[var], %%rsi; call this_cpu_cmpxchg16b_emu", \
+ asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
"cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
: [var] "+m" (_var), \
"+a" (old__.low), \
"+d" (old__.high) \
: "b" (new__.low), \
- "c" (new__.high) \
- : "memory", "rsi"); \
+ "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
\
old__.var; \
})
#define raw_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, , pcp, oval, nval)
#define this_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval) \
+({ \
+ bool success; \
+ u128 *_oval = (u128 *)(_ovalp); \
+ union { \
+ u128 var; \
+ struct { \
+ u64 low, high; \
+ }; \
+ } old__, new__; \
+ \
+ old__.var = *_oval; \
+ new__.var = _nval; \
+ \
+ asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \
+ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+ CC_SET(z) \
+ : CC_OUT(z) (success), \
+ [var] "+m" (_var), \
+ "+a" (old__.low), \
+ "+d" (old__.high) \
+ : "b" (new__.low), \
+ "c" (new__.high), \
+ "S" (&(_var)) \
+ : "memory"); \
+ if (unlikely(!success)) \
+ *_oval = old__.var; \
+ likely(success); \
+})
+
+#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval)
#endif
/*
@@ -343,6 +433,9 @@ do { \
#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval)
#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval)
#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val)
#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val)
@@ -350,6 +443,9 @@ do { \
#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
/*
* Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -364,6 +460,7 @@ do { \
#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val)
#define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval)
#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp)
#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val)
@@ -373,6 +470,7 @@ do { \
#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val)
#define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval)
#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
#endif
static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 85a9fd5a3ec3..2618ec7c3d1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -112,6 +112,13 @@
(AMD64_PERFMON_V2_EVENTSEL_EVENT_NB | \
AMD64_PERFMON_V2_EVENTSEL_UMASK_NB)
+#define AMD64_PERFMON_V2_ENABLE_UMC BIT_ULL(31)
+#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC GENMASK_ULL(7, 0)
+#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC GENMASK_ULL(9, 8)
+#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC \
+ (AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC | \
+ AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC)
+
#define AMD64_NUM_COUNTERS 4
#define AMD64_NUM_COUNTERS_CORE 6
#define AMD64_NUM_COUNTERS_NB 4
@@ -232,6 +239,8 @@ union cpuid_0x80000022_ebx {
unsigned int lbr_v2_stack_sz:6;
/* Number of Data Fabric Counters */
unsigned int num_df_pmc:6;
+ /* Number of Unified Memory Controller Counters */
+ unsigned int num_umc_pmc:6;
} split;
unsigned int full;
};
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index d6ad98ca1288..57bab91bbf50 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -955,6 +955,14 @@ static inline int pte_same(pte_t a, pte_t b)
return a.pte == b.pte;
}
+static inline pte_t pte_next_pfn(pte_t pte)
+{
+ if (__pte_needs_invert(pte_val(pte)))
+ return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT));
+ return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT));
+}
+#define pte_next_pfn pte_next_pfn
+
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
@@ -1708,6 +1716,14 @@ static inline bool pud_user_accessible_page(pud_t pud)
}
#endif
+#ifdef CONFIG_X86_SGX
+int arch_memory_failure(unsigned long pfn, int flags);
+#define arch_memory_failure arch_memory_failure
+
+bool arch_is_platform_page(u64 paddr);
+#define arch_is_platform_page arch_is_platform_page
+#endif
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 2d13f25b1bd8..4527e1430c6d 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -31,11 +31,11 @@ static __always_inline void preempt_count_set(int pc)
{
int old, new;
+ old = raw_cpu_read_4(pcpu_hot.preempt_count);
do {
- old = raw_cpu_read_4(pcpu_hot.preempt_count);
new = (old & PREEMPT_NEED_RESCHED) |
(pc & ~PREEMPT_NEED_RESCHED);
- } while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old);
+ } while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new));
}
/*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 0086920cda06..ae81a7191c1c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -75,11 +75,36 @@ extern u16 __read_mostly tlb_lld_4m[NR_INFO];
extern u16 __read_mostly tlb_lld_1g[NR_INFO];
/*
- * CPU type and hardware bug flags. Kept separately for each CPU.
- * Members of this structure are referenced in head_32.S, so think twice
- * before touching them. [mj]
+ * CPU type and hardware bug flags. Kept separately for each CPU.
*/
+struct cpuinfo_topology {
+ // Real APIC ID read from the local APIC
+ u32 apicid;
+ // The initial APIC ID provided by CPUID
+ u32 initial_apicid;
+
+ // Physical package ID
+ u32 pkg_id;
+
+ // Physical die ID on AMD, Relative on Intel
+ u32 die_id;
+
+ // Compute unit ID - AMD specific
+ u32 cu_id;
+
+ // Core ID relative to the package
+ u32 core_id;
+
+ // Logical ID mappings
+ u32 logical_pkg_id;
+ u32 logical_die_id;
+
+ // Cache level topology IDs
+ u32 llc_id;
+ u32 l2c_id;
+};
+
struct cpuinfo_x86 {
__u8 x86; /* CPU family */
__u8 x86_vendor; /* CPU vendor */
@@ -96,7 +121,6 @@ struct cpuinfo_x86 {
__u8 x86_phys_bits;
/* CPUID returned core id bits: */
__u8 x86_coreid_bits;
- __u8 cu_id;
/* Max extended CPUID function supported: */
__u32 extended_cpuid_level;
/* Maximum supported CPUID level, -1=no CPUID: */
@@ -112,6 +136,7 @@ struct cpuinfo_x86 {
};
char x86_vendor_id[16];
char x86_model_id[64];
+ struct cpuinfo_topology topo;
/* in KB - valid for CPUS which support this call: */
unsigned int x86_cache_size;
int x86_cache_alignment; /* In bytes */
@@ -125,19 +150,9 @@ struct cpuinfo_x86 {
u64 ppin;
/* cpuid returned max cores value: */
u16 x86_max_cores;
- u16 apicid;
- u16 initial_apicid;
u16 x86_clflush_size;
/* number of cores as seen by the OS: */
u16 booted_cores;
- /* Physical processor id: */
- u16 phys_proc_id;
- /* Logical processor id: */
- u16 logical_proc_id;
- /* Core id: */
- u16 cpu_core_id;
- u16 cpu_die_id;
- u16 logical_die_id;
/* Index into per_cpu list: */
u16 cpu_index;
/* Is SMT active on this core? */
@@ -399,7 +414,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)
return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
}
-extern asmlinkage void ignore_sysret(void);
+extern asmlinkage void entry_SYSCALL32_ignore(void);
/* Save actual FS/GS selectors and bases to current->thread */
void current_save_fsgs(void);
@@ -678,18 +693,24 @@ extern int set_tsc_mode(unsigned int val);
DECLARE_PER_CPU(u64, msr_misc_features_shadow);
-extern u16 get_llc_id(unsigned int cpu);
+static inline u32 per_cpu_llc_id(unsigned int cpu)
+{
+ return per_cpu(cpu_info.topo.llc_id, cpu);
+}
+
+static inline u32 per_cpu_l2c_id(unsigned int cpu)
+{
+ return per_cpu(cpu_info.topo.l2c_id, cpu);
+}
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
-extern bool cpu_has_ibpb_brtype_microcode(void);
extern void amd_clear_divider(void);
extern void amd_check_microcode(void);
#else
static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
-static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; }
static inline void amd_clear_divider(void) { }
static inline void amd_check_microcode(void) { }
#endif
@@ -726,14 +747,6 @@ enum mds_mitigations {
MDS_MITIGATION_VMWERV,
};
-#ifdef CONFIG_X86_SGX
-int arch_memory_failure(unsigned long pfn, int flags);
-#define arch_memory_failure arch_memory_failure
-
-bool arch_is_platform_page(u64 paddr);
-#define arch_is_platform_page arch_is_platform_page
-#endif
-
extern bool gds_ucode_mitigated(void);
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index b716d291d0d4..65dee2420624 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -31,6 +31,11 @@ static inline void x86_dtb_init(void) { }
#define of_ioapic 0
#endif
+#ifdef CONFIG_OF_EARLY_FLATTREE
+void x86_flattree_get_config(void);
+#else
+static inline void x86_flattree_get_config(void) { }
+#endif
extern char cmd_line[COMMAND_LINE_SIZE];
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 12ef86b19910..4d84122bd643 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -36,6 +36,9 @@ void entry_INT80_compat(void);
#ifdef CONFIG_XEN_PV
void xen_entry_INT80_compat(void);
#endif
+#else /* !CONFIG_IA32_EMULATION */
+#define entry_SYSCALL_compat NULL
+#define entry_SYSENTER_compat NULL
#endif
void x86_configure_nx(void);
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ad98dd1d9cfb..4fab2ed454f3 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -17,10 +17,8 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map);
/* cpus sharing the last level cache: */
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
-DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
-DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid);
DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
struct task_struct;
@@ -129,7 +127,6 @@ void native_smp_send_reschedule(int cpu);
void native_send_call_func_ipi(const struct cpumask *mask);
void native_send_call_func_single_ipi(int cpu);
-bool smp_park_other_cpus_in_init(void);
void smp_store_cpu_info(int id);
asmlinkage __visible void smp_reboot_interrupt(void);
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 64df897c0ee3..1be13b2dfe8b 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,6 +37,8 @@ extern int phys_to_target_node(phys_addr_t start);
#define phys_to_target_node phys_to_target_node
extern int memory_add_physaddr_to_nid(u64 start);
#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+extern int numa_fill_memblks(u64 start, u64 end);
+#define numa_fill_memblks numa_fill_memblks
#endif
#endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index cb0386fc4dc3..c648502e4535 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -4,6 +4,7 @@
#include <linux/thread_info.h>
#include <asm/nospec-branch.h>
+#include <asm/msr.h>
/*
* On VMENTER we must preserve whatever view of the SPEC_CTRL MSR
@@ -76,6 +77,16 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL;
}
+/*
+ * This can be used in noinstr functions & should only be called in bare
+ * metal context.
+ */
+static __always_inline void __update_spec_ctrl(u64 val)
+{
+ __this_cpu_write(x86_spec_ctrl_current, val);
+ native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+}
+
#ifdef CONFIG_SMP
extern void speculative_store_bypass_ht_init(void);
#else
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 19bf955b67e0..87a7b917d30e 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -229,10 +229,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT)
#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT)
-#define SVM_VM_CR_VALID_MASK 0x001fULL
-#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL
-#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL
-
#define SVM_NESTED_CTL_NP_ENABLE BIT(0)
#define SVM_NESTED_CTL_SEV_ENABLE BIT(1)
#define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2)
@@ -268,6 +264,7 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
AVIC_IPI_FAILURE_INVALID_TARGET,
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
+ AVIC_IPI_FAILURE_INVALID_IPI_VECTOR,
};
#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0)
@@ -571,8 +568,6 @@ struct vmcb {
#define SVM_CPUID_FUNC 0x8000000a
-#define SVM_VM_CR_SVM_DISABLE 4
-
#define SVM_SELECTOR_S_SHIFT 4
#define SVM_SELECTOR_DPL_SHIFT 5
#define SVM_SELECTOR_P_SHIFT 7
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 4fb36fba4b5a..f44e2f9ab65d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -126,12 +126,12 @@ static inline int syscall_get_arch(struct task_struct *task)
? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
}
-void do_syscall_64(struct pt_regs *regs, int nr);
+bool do_syscall_64(struct pt_regs *regs, int nr);
#endif /* CONFIG_X86_32 */
void do_int80_syscall_32(struct pt_regs *regs);
-long do_fast_syscall_32(struct pt_regs *regs);
-long do_SYSENTER_32(struct pt_regs *regs);
+bool do_fast_syscall_32(struct pt_regs *regs);
+bool do_SYSENTER_32(struct pt_regs *regs);
#endif /* _ASM_X86_SYSCALL_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 3235ba1e5b06..5f87f6b9b09e 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -105,17 +105,17 @@ static inline void setup_node_to_cpumask_map(void) { }
extern const struct cpumask *cpu_coregroup_mask(int cpu);
extern const struct cpumask *cpu_clustergroup_mask(int cpu);
-#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id)
-#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
-#define topology_logical_die_id(cpu) (cpu_data(cpu).logical_die_id)
-#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id)
-#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
+#define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id)
+#define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id)
+#define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id)
+#define topology_die_id(cpu) (cpu_data(cpu).topo.die_id)
+#define topology_core_id(cpu) (cpu_data(cpu).topo.core_id)
#define topology_ppin(cpu) (cpu_data(cpu).ppin)
extern unsigned int __max_die_per_package;
#ifdef CONFIG_SMP
-#define topology_cluster_id(cpu) (per_cpu(cpu_l2c_id, cpu))
+#define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id)
#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu))
#define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu))
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8bae40a66282..5c367c1290c3 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -496,7 +496,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned len);
#define copy_mc_to_kernel copy_mc_to_kernel
unsigned long __must_check
-copy_mc_to_user(void *to, const void *from, unsigned len);
+copy_mc_to_user(void __user *to, const void *from, unsigned len);
#endif
/*
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 5240d88db52a..c878616a18b8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -177,7 +177,7 @@ struct x86_init_ops {
* struct x86_cpuinit_ops - platform specific cpu hotplug setups
* @setup_percpu_clockev: set up the per cpu clock event device
* @early_percpu_clock_init: early init of the per cpu clock event device
- * @fixup_cpu_id: fixup function for cpuinfo_x86::phys_proc_id
+ * @fixup_cpu_id: fixup function for cpuinfo_x86::topo.pkg_id
* @parallel_bringup: Parallel bringup control
*/
struct x86_cpuinit_ops {
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index 5fc35f889cd1..7048dfacc04b 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -36,6 +36,7 @@
extern struct shared_info *HYPERVISOR_shared_info;
extern struct start_info *xen_start_info;
+#include <asm/bug.h>
#include <asm/processor.h>
#define XEN_SIGNATURE "XenVMMXenVMM"
@@ -63,4 +64,40 @@ void __init xen_pvh_init(struct boot_params *boot_params);
void __init mem_map_via_hcall(struct boot_params *boot_params_p);
#endif
+/* Lazy mode for batching updates / context switch */
+enum xen_lazy_mode {
+ XEN_LAZY_NONE,
+ XEN_LAZY_MMU,
+ XEN_LAZY_CPU,
+};
+
+DECLARE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode);
+DECLARE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+static inline void enter_lazy(enum xen_lazy_mode mode)
+{
+ enum xen_lazy_mode old_mode = this_cpu_read(xen_lazy_mode);
+
+ if (mode == old_mode) {
+ this_cpu_inc(xen_lazy_nesting);
+ return;
+ }
+
+ BUG_ON(old_mode != XEN_LAZY_NONE);
+
+ this_cpu_write(xen_lazy_mode, mode);
+}
+
+static inline void leave_lazy(enum xen_lazy_mode mode)
+{
+ BUG_ON(this_cpu_read(xen_lazy_mode) != mode);
+
+ if (this_cpu_read(xen_lazy_nesting) == 0)
+ this_cpu_write(xen_lazy_mode, XEN_LAZY_NONE);
+ else
+ this_cpu_dec(xen_lazy_nesting);
+}
+
+enum xen_lazy_mode xen_get_lazy_mode(void);
+
#endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 2a0ea38955df..d0918a75cb00 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -148,6 +148,9 @@ static int __init acpi_parse_madt(struct acpi_table_header *table)
pr_debug("Local APIC address 0x%08x\n", madt->address);
}
+ if (madt->flags & ACPI_MADT_PCAT_COMPAT)
+ legacy_pic_pcat_compat();
+
/* ACPI 6.3 and newer support the online capable bit. */
if (acpi_gbl_FADT.header.revision > 6 ||
(acpi_gbl_FADT.header.revision == 6 &&
@@ -359,7 +362,7 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e
}
#ifdef CONFIG_X86_64
-static int acpi_wakeup_cpu(int apicid, unsigned long start_ip)
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
{
/*
* Remap mailbox memory only for the first call to acpi_wakeup_cpu().
@@ -856,7 +859,7 @@ int acpi_unmap_cpu(int cpu)
set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
#endif
- per_cpu(x86_cpu_to_apicid, cpu) = -1;
+ per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
set_cpu_present(cpu, false);
num_processors--;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a5ead6a6d233..73be3931e4f0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -403,6 +403,17 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
u8 insn_buff[MAX_PATCH_LEN];
DPRINTK(ALT, "alt table %px, -> %px", start, end);
+
+ /*
+ * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+ * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
+ * During the process, KASAN becomes confused seeing partial LA57
+ * conversion and triggers a false-positive out-of-bound report.
+ *
+ * Disable KASAN until the patching is complete.
+ */
+ kasan_disable_current();
+
/*
* The scan order should be from start to end. A later scanned
* alternative code can overwrite previously scanned alternative code.
@@ -452,6 +463,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
text_poke_early(instr, insn_buff, insn_buff_sz);
}
+
+ kasan_enable_current();
}
static inline bool is_jcc32(struct insn *insn)
@@ -720,13 +733,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
{
s32 *s;
- /*
- * Do not patch out the default return thunks if those needed are the
- * ones generated by the compiler.
- */
- if (cpu_feature_enabled(X86_FEATURE_RETHUNK) &&
- (x86_return_thunk == __x86_return_thunk))
- return;
+ if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+ static_call_force_reinit();
for (s = start; s < end; s++) {
void *dest = NULL, *addr = (void *)s + *s;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 356de955e78d..053f6dcc6b2c 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -27,6 +27,7 @@
#define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a
#define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
#define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb
+#define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8
#define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464
#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec
@@ -43,6 +44,7 @@
#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc
#define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4
#define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4
+#define PCI_DEVICE_ID_AMD_MI300_DF_F4 0x152c
/* Protect the PCI config register pairs used for SMN. */
static DEFINE_MUTEX(smn_mutex);
@@ -62,6 +64,7 @@ static const struct pci_device_id amd_root_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) },
{}
};
@@ -93,6 +96,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) },
{}
};
@@ -112,9 +116,13 @@ static const struct pci_device_id amd_nb_link_ids[] = {
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) },
{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F4) },
{}
};
@@ -386,7 +394,7 @@ int amd_get_subcaches(int cpu)
pci_read_config_dword(link, 0x1d4, &mask);
- return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf;
+ return (mask >> (4 * cpu_data(cpu).topo.core_id)) & 0xf;
}
int amd_set_subcaches(int cpu, unsigned long mask)
@@ -412,7 +420,7 @@ int amd_set_subcaches(int cpu, unsigned long mask)
pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
}
- cuid = cpu_data(cpu).cpu_core_id;
+ cuid = cpu_data(cpu).topo.core_id;
mask <<= 4 * cuid;
mask |= (0xf ^ (1 << cuid)) << 26;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 760adac3d1a8..41093cf20acd 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -36,6 +36,8 @@
#include <linux/smp.h>
#include <linux/mm.h>
+#include <xen/xen.h>
+
#include <asm/trace/irq_vectors.h>
#include <asm/irq_remapping.h>
#include <asm/pc-conf-reg.h>
@@ -70,7 +72,7 @@ unsigned int num_processors;
unsigned disabled_cpus;
/* Processor that is doing the boot up */
-unsigned int boot_cpu_physical_apicid __ro_after_init = -1U;
+u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID;
EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid);
u8 boot_cpu_apic_version __ro_after_init;
@@ -85,7 +87,7 @@ physid_mask_t phys_cpu_present_map;
* disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to
* avoid undefined behaviour caused by sending INIT from AP to BSP.
*/
-static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID;
+static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID;
/*
* This variable controls which CPUs receive external NMIs. By default,
@@ -109,7 +111,7 @@ static inline bool apic_accessible(void)
/*
* Map cpu index to physical APIC ID
*/
-DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID);
DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid);
@@ -1763,7 +1765,7 @@ static void __x2apic_enable(void)
static int __init setup_nox2apic(char *str)
{
if (x2apic_enabled()) {
- int apicid = native_apic_msr_read(APIC_ID);
+ u32 apicid = native_apic_msr_read(APIC_ID);
if (apicid >= 255) {
pr_warn("Apicid: %08x, cannot enforce nox2apic\n",
@@ -2316,13 +2318,11 @@ static int nr_logical_cpuids = 1;
/*
* Used to store mapping between logical CPU IDs and APIC IDs.
*/
-int cpuid_to_apicid[] = {
- [0 ... NR_CPUS - 1] = -1,
-};
+u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, };
bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
{
- return phys_id == cpuid_to_apicid[cpu];
+ return phys_id == (u64)cpuid_to_apicid[cpu];
}
#ifdef CONFIG_SMP
@@ -2344,6 +2344,15 @@ static int __init smp_init_primary_thread_mask(void)
{
unsigned int cpu;
+ /*
+ * XEN/PV provides either none or useless topology information.
+ * Pretend that all vCPUs are primary threads.
+ */
+ if (xen_pv_domain()) {
+ cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask);
+ return 0;
+ }
+
for (cpu = 0; cpu < nr_logical_cpuids; cpu++)
cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]);
return 0;
@@ -2382,7 +2391,7 @@ static int allocate_logical_cpuid(int apicid)
return nr_logical_cpuids++;
}
-static void cpu_update_apic(int cpu, int apicid)
+static void cpu_update_apic(int cpu, u32 apicid)
{
#if defined(CONFIG_SMP) || defined(CONFIG_X86_64)
early_per_cpu(x86_cpu_to_apicid, cpu) = apicid;
@@ -2535,7 +2544,7 @@ static struct {
*/
int active;
/* r/w apic fields */
- unsigned int apic_id;
+ u32 apic_id;
unsigned int apic_taskpri;
unsigned int apic_ldr;
unsigned int apic_dfr;
diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c
index 7bc5d9bf59cd..8a00141073ea 100644
--- a/arch/x86/kernel/apic/apic_common.c
+++ b/arch/x86/kernel/apic/apic_common.c
@@ -18,7 +18,7 @@ u32 apic_flat_calc_apicid(unsigned int cpu)
return 1U << cpu;
}
-bool default_check_apicid_used(physid_mask_t *map, int apicid)
+bool default_check_apicid_used(physid_mask_t *map, u32 apicid)
{
return physid_isset(apicid, *map);
}
@@ -28,7 +28,7 @@ void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap)
*retmap = *phys_map;
}
-int default_cpu_present_to_apicid(int mps_cpu)
+u32 default_cpu_present_to_apicid(int mps_cpu)
{
if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu))
return (int)per_cpu(x86_cpu_to_apicid, mps_cpu);
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 032a84e2c3cc..37daa3fd6819 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -56,17 +56,17 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
_flat_send_IPI_mask(mask, vector);
}
-static unsigned int flat_get_apic_id(unsigned long x)
+static u32 flat_get_apic_id(u32 x)
{
return (x >> 24) & 0xFF;
}
-static u32 set_apic_id(unsigned int id)
+static u32 set_apic_id(u32 id)
{
return (id & 0xFF) << 24;
}
-static int flat_phys_pkg_id(int initial_apic_id, int index_msb)
+static u32 flat_phys_pkg_id(u32 initial_apic_id, int index_msb)
{
return initial_apic_id >> index_msb;
}
@@ -158,8 +158,6 @@ static struct apic apic_physflat __ro_after_init = {
.disable_esr = 0,
- .check_apicid_used = NULL,
- .ioapic_phys_id_map = NULL,
.cpu_present_to_apicid = default_cpu_present_to_apicid,
.phys_pkg_id = flat_phys_pkg_id,
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 966d7cf10b95..b00d52ae84fa 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -18,6 +18,8 @@
#include <asm/apic.h>
+#include "local.h"
+
static void noop_send_IPI(int cpu, int vector) { }
static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { }
static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { }
@@ -25,10 +27,10 @@ static void noop_send_IPI_allbutself(int vector) { }
static void noop_send_IPI_all(int vector) { }
static void noop_send_IPI_self(int vector) { }
static void noop_apic_icr_write(u32 low, u32 id) { }
-static int noop_wakeup_secondary_cpu(int apicid, unsigned long start_eip) { return -1; }
+static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; }
static u64 noop_apic_icr_read(void) { return 0; }
-static int noop_phys_pkg_id(int cpuid_apic, int index_msb) { return 0; }
-static unsigned int noop_get_apic_id(unsigned long x) { return 0; }
+static u32 noop_phys_pkg_id(u32 cpuid_apic, int index_msb) { return 0; }
+static u32 noop_get_apic_id(u32 apicid) { return 0; }
static void noop_apic_eoi(void) { }
static u32 noop_apic_read(u32 reg)
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 63f3d7be9dc7..456a14c44f67 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -25,7 +25,7 @@ static const struct apic apic_numachip1;
static const struct apic apic_numachip2;
static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly;
-static unsigned int numachip1_get_apic_id(unsigned long x)
+static u32 numachip1_get_apic_id(u32 x)
{
unsigned long value;
unsigned int id = (x >> 24) & 0xff;
@@ -38,12 +38,12 @@ static unsigned int numachip1_get_apic_id(unsigned long x)
return id;
}
-static u32 numachip1_set_apic_id(unsigned int id)
+static u32 numachip1_set_apic_id(u32 id)
{
return (id & 0xff) << 24;
}
-static unsigned int numachip2_get_apic_id(unsigned long x)
+static u32 numachip2_get_apic_id(u32 x)
{
u64 mcfg;
@@ -51,12 +51,12 @@ static unsigned int numachip2_get_apic_id(unsigned long x)
return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24);
}
-static u32 numachip2_set_apic_id(unsigned int id)
+static u32 numachip2_set_apic_id(u32 id)
{
return id << 24;
}
-static int numachip_phys_pkg_id(int initial_apic_id, int index_msb)
+static u32 numachip_phys_pkg_id(u32 initial_apic_id, int index_msb)
{
return initial_apic_id >> index_msb;
}
@@ -71,7 +71,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val)
numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val);
}
-static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
{
numachip_apic_icr_write(phys_apicid, APIC_DM_INIT);
numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP |
@@ -161,7 +161,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
u64 val;
u32 nodes = 1;
- this_cpu_write(cpu_llc_id, node);
+ c->topo.llc_id = node;
/* Account for nodes per socket in multi-core-module processors */
if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
@@ -169,7 +169,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
nodes = ((val >> 3) & 7) + 1;
}
- c->phys_proc_id = node / nodes;
+ c->topo.pkg_id = node / nodes;
}
static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index 0e5535add4b5..7ee3c486cb33 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -13,12 +13,12 @@
#include "local.h"
-static unsigned bigsmp_get_apic_id(unsigned long x)
+static u32 bigsmp_get_apic_id(u32 x)
{
return (x >> 24) & 0xFF;
}
-static bool bigsmp_check_apicid_used(physid_mask_t *map, int apicid)
+static bool bigsmp_check_apicid_used(physid_mask_t *map, u32 apicid)
{
return false;
}
@@ -29,7 +29,7 @@ static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *re
physids_promote(0xFFL, retmap);
}
-static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb)
+static u32 bigsmp_phys_pkg_id(u32 cpuid_apic, int index_msb)
{
return cpuid_apic >> index_msb;
}
diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c
index a44ba7209ef3..0078730a512e 100644
--- a/arch/x86/kernel/apic/ipi.c
+++ b/arch/x86/kernel/apic/ipi.c
@@ -281,7 +281,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector)
}
#ifdef CONFIG_SMP
-static int convert_apicid_to_cpu(int apic_id)
+static int convert_apicid_to_cpu(u32 apic_id)
{
int i;
@@ -294,7 +294,8 @@ static int convert_apicid_to_cpu(int apic_id)
int safe_smp_processor_id(void)
{
- int apicid, cpuid;
+ u32 apicid;
+ int cpuid;
if (!boot_cpu_has(X86_FEATURE_APIC))
return 0;
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index ec219c659c7d..9ea6186ea88c 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -15,9 +15,9 @@
/* X2APIC */
void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest);
-unsigned int x2apic_get_apic_id(unsigned long id);
-u32 x2apic_set_apic_id(unsigned int id);
-int x2apic_phys_pkg_id(int initial_apicid, int index_msb);
+u32 x2apic_get_apic_id(u32 id);
+u32 x2apic_set_apic_id(u32 id);
+u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb);
void x2apic_send_IPI_all(int vector);
void x2apic_send_IPI_allbutself(int vector);
@@ -64,6 +64,7 @@ void default_send_IPI_all(int vector);
void default_send_IPI_self(int vector);
bool default_apic_id_registered(void);
+bool default_check_apicid_used(physid_mask_t *map, u32 apicid);
#ifdef CONFIG_X86_32
void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 6b6b711678fe..d9651f15ae4f 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -55,14 +55,14 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force)
* caused by the non-atomic update of the address/data pair.
*
* Direct update is possible when:
- * - The MSI is maskable (remapped MSI does not use this code path)).
- * The quirk bit is not set in this case.
+ * - The MSI is maskable (remapped MSI does not use this code path).
+ * The reservation mode bit is set in this case.
* - The new vector is the same as the old vector
* - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up)
* - The interrupt is not yet started up
* - The new destination CPU is the same as the old destination CPU
*/
- if (!irqd_msi_nomask_quirk(irqd) ||
+ if (!irqd_can_reserve(irqd) ||
cfg->vector == old_cfg.vector ||
old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR ||
!irqd_is_started(irqd) ||
@@ -215,8 +215,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
if (WARN_ON_ONCE(domain != real_parent))
return false;
info->chip->irq_set_affinity = msi_set_affinity;
- /* See msi_set_affinity() for the gory details */
- info->flags |= MSI_FLAG_NOMASK_QUIRK;
break;
case DOMAIN_BUS_DMAR:
case DOMAIN_BUS_AMDVI:
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 9a06df6cdd68..5eb3fbe472da 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -18,11 +18,21 @@
#include "local.h"
-static int default_phys_pkg_id(int cpuid_apic, int index_msb)
+static u32 default_phys_pkg_id(u32 cpuid_apic, int index_msb)
{
return cpuid_apic >> index_msb;
}
+static u32 default_get_apic_id(u32 x)
+{
+ unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+
+ if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID))
+ return (x >> 24) & 0xFF;
+ else
+ return (x >> 24) & 0x0F;
+}
+
/* should be called last. */
static int probe_default(void)
{
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 788cdb4ee394..7c9fe28f742f 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -124,17 +124,17 @@ static int x2apic_phys_probe(void)
return apic == &apic_x2apic_phys;
}
-unsigned int x2apic_get_apic_id(unsigned long id)
+u32 x2apic_get_apic_id(u32 id)
{
return id;
}
-u32 x2apic_set_apic_id(unsigned int id)
+u32 x2apic_set_apic_id(u32 id)
{
return id;
}
-int x2apic_phys_pkg_id(int initial_apicid, int index_msb)
+u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb)
{
return initial_apicid >> index_msb;
}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d9f5d7492f83..1b0d7336a28f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -110,7 +110,7 @@ static void __init early_get_pnodeid(void)
} else if (UVH_RH_GAM_ADDR_MAP_CONFIG) {
union uvh_rh_gam_addr_map_config_u m_n_config;
- m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_ADDR_MAP_CONFIG);
+ m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_ADDR_MAP_CONFIG);
uv_cpuid.n_skt = m_n_config.s.n_skt;
if (is_uv(UV3))
uv_cpuid.m_skt = m_n_config.s3.m_skt;
@@ -701,7 +701,7 @@ static __init void build_uv_gr_table(void)
}
}
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
{
unsigned long val;
int pnode;
@@ -779,7 +779,7 @@ static void uv_send_IPI_all(int vector)
uv_send_IPI_mask(cpu_online_mask, vector);
}
-static u32 set_apic_id(unsigned int id)
+static u32 set_apic_id(u32 id)
{
return id;
}
@@ -789,7 +789,7 @@ static unsigned int uv_read_apic_id(void)
return x2apic_get_apic_id(apic_read(APIC_ID));
}
-static int uv_phys_pkg_id(int initial_apicid, int index_msb)
+static u32 uv_phys_pkg_id(u32 initial_apicid, int index_msb)
{
return uv_read_apic_id() >> index_msb;
}
@@ -1533,7 +1533,7 @@ static void __init build_socket_tables(void)
{
struct uv_gam_range_entry *gre = uv_gre_table;
int nums, numn, nump;
- int cpu, i, lnid;
+ int i, lnid, apicid;
int minsock = _min_socket;
int maxsock = _max_socket;
int minpnode = _min_pnode;
@@ -1584,15 +1584,14 @@ static void __init build_socket_tables(void)
/* Set socket -> node values: */
lnid = NUMA_NO_NODE;
- for_each_possible_cpu(cpu) {
- int nid = cpu_to_node(cpu);
- int apicid, sockid;
+ for (apicid = 0; apicid < ARRAY_SIZE(__apicid_to_node); apicid++) {
+ int nid = __apicid_to_node[apicid];
+ int sockid;
- if (lnid == nid)
+ if ((nid == NUMA_NO_NODE) || (lnid == nid))
continue;
lnid = nid;
- apicid = per_cpu(x86_cpu_to_apicid, cpu);
sockid = apicid >> uv_cpuid.socketid_shift;
if (_socket_to_node[sockid - minsock] == SOCK_EMPTY)
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index c06bfc086565..e9ad518a5003 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -48,11 +48,6 @@ EXPORT_SYMBOL_GPL(__x86_call_count);
extern s32 __call_sites[], __call_sites_end[];
-struct thunk_desc {
- void *template;
- unsigned int template_size;
-};
-
struct core_text {
unsigned long base;
unsigned long end;
@@ -272,7 +267,6 @@ void __init callthunks_patch_builtin_calls(void)
pr_info("Setting up call depth tracking\n");
mutex_lock(&text_mutex);
callthunks_setup(&cs, &builtin_coretext);
- static_call_force_reinit();
thunks_initialized = true;
mutex_unlock(&text_mutex);
}
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4350f6bfc064..93eabf544031 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -54,6 +54,8 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o
obj-$(CONFIG_ACRN_GUEST) += acrn.o
+obj-$(CONFIG_DEBUG_FS) += debugfs.o
+
quiet_cmd_mkcapflags = MKCAP $@
cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index dd8379d84445..a7eab05e5f29 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -80,6 +80,10 @@ static const int amd_div0[] =
AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf),
AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf));
+static const int amd_erratum_1485[] =
+ AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
+ AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf));
+
static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
{
int osvw_id = *erratum++;
@@ -378,7 +382,7 @@ static int nearby_node(int apicid)
#endif
/*
- * Fix up cpu_core_id for pre-F17h systems to be in the
+ * Fix up topo::core_id for pre-F17h systems to be in the
* [0 .. cores_per_node - 1] range. Not really needed but
* kept so as not to break existing setups.
*/
@@ -390,7 +394,7 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
return;
cus_per_node = c->x86_max_cores / nodes_per_socket;
- c->cpu_core_id %= cus_per_node;
+ c->topo.core_id %= cus_per_node;
}
/*
@@ -401,8 +405,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
*/
static void amd_get_topology(struct cpuinfo_x86 *c)
{
- int cpu = smp_processor_id();
-
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
int err;
@@ -410,13 +412,13 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- c->cpu_die_id = ecx & 0xff;
+ c->topo.die_id = ecx & 0xff;
if (c->x86 == 0x15)
- c->cu_id = ebx & 0xff;
+ c->topo.cu_id = ebx & 0xff;
if (c->x86 >= 0x17) {
- c->cpu_core_id = ebx & 0xff;
+ c->topo.core_id = ebx & 0xff;
if (smp_num_siblings > 1)
c->x86_max_cores /= smp_num_siblings;
@@ -430,15 +432,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
- cacheinfo_amd_init_llc_id(c, cpu);
+ cacheinfo_amd_init_llc_id(c);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
rdmsrl(MSR_FAM10H_NODE_ID, value);
- c->cpu_die_id = value & 7;
-
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
+ c->topo.die_id = value & 7;
+ c->topo.llc_id = c->topo.die_id;
} else
return;
@@ -455,15 +456,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
static void amd_detect_cmp(struct cpuinfo_x86 *c)
{
unsigned bits;
- int cpu = smp_processor_id();
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
- c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+ c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
/* Convert the initial APIC ID into the socket ID */
- c->phys_proc_id = c->initial_apicid >> bits;
+ c->topo.pkg_id = c->topo.initial_apicid >> bits;
/* use socket ID also for last level cache */
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
+ c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
}
u32 amd_get_nodes_per_socket(void)
@@ -477,11 +477,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
- unsigned apicid = c->apicid;
+ unsigned apicid = c->topo.apicid;
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
- node = get_llc_id(cpu);
+ node = per_cpu_llc_id(cpu);
/*
* On multi-fabric platform (e.g. Numascale NumaChip) a
@@ -511,7 +511,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
* through CPU mapping may alter the outcome, directly
* access __apicid_to_node[].
*/
- int ht_nodeid = c->initial_apicid;
+ int ht_nodeid = c->topo.initial_apicid;
if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
node = __apicid_to_node[ht_nodeid];
@@ -766,6 +766,15 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_TOPOEXT))
smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
+
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
+ if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
+ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+ else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+ setup_force_cpu_cap(X86_FEATURE_SBPB);
+ }
+ }
}
static void init_amd_k8(struct cpuinfo_x86 *c)
@@ -1001,7 +1010,6 @@ static bool cpu_has_zenbleed_microcode(void)
default:
return false;
- break;
}
if (boot_cpu_data.microcode < good_rev)
@@ -1031,6 +1039,8 @@ static void zenbleed_check(struct cpuinfo_x86 *c)
static void init_amd(struct cpuinfo_x86 *c)
{
+ u64 vm_cr;
+
early_init_amd(c);
/*
@@ -1047,7 +1057,7 @@ static void init_amd(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_FSRS);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = read_apic_id();
+ c->topo.apicid = read_apic_id();
/* K6s reports MCEs but don't actually have all the MSRs */
if (c->x86 < 6)
@@ -1082,6 +1092,14 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
+ if (cpu_has(c, X86_FEATURE_SVM)) {
+ rdmsrl(MSR_VM_CR, vm_cr);
+ if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
+ pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
+ clear_cpu_cap(c, X86_FEATURE_SVM);
+ }
+ }
+
if (!cpu_has(c, X86_FEATURE_LFENCE_RDTSC) && cpu_has(c, X86_FEATURE_XMM2)) {
/*
* Use LFENCE for execution serialization. On families which
@@ -1140,6 +1158,10 @@ static void init_amd(struct cpuinfo_x86 *c)
pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
setup_force_cpu_bug(X86_BUG_DIV0);
}
+
+ if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
+ cpu_has_amd_erratum(c, amd_erratum_1485))
+ msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
}
#ifdef CONFIG_X86_32
@@ -1301,25 +1323,6 @@ void amd_check_microcode(void)
on_each_cpu(zenbleed_check_cpu, NULL, 1);
}
-bool cpu_has_ibpb_brtype_microcode(void)
-{
- switch (boot_cpu_data.x86) {
- /* Zen1/2 IBPB flushes branch type predictions too. */
- case 0x17:
- return boot_cpu_has(X86_FEATURE_AMD_IBPB);
- case 0x19:
- /* Poke the MSR bit on Zen3/4 to check its presence. */
- if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
- setup_force_cpu_cap(X86_FEATURE_SBPB);
- return true;
- } else {
- return false;
- }
- default:
- return false;
- }
-}
-
/*
* Issue a DIV 0/1 insn to clear any division data from previous DIV
* operations.
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index f081d26616ac..bb0ab8466b91 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -63,7 +63,7 @@ EXPORT_SYMBOL_GPL(x86_pred_cmd);
static DEFINE_MUTEX(spec_ctrl_mutex);
-void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk;
+void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
static void update_spec_ctrl(u64 val)
@@ -717,7 +717,7 @@ void update_gds_msr(void)
case GDS_MITIGATION_UCODE_NEEDED:
case GDS_MITIGATION_HYPERVISOR:
return;
- };
+ }
wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
@@ -1019,7 +1019,6 @@ static void __init retbleed_select_mitigation(void)
do_cmd_auto:
case RETBLEED_CMD_AUTO:
- default:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY))
@@ -1042,8 +1041,7 @@ do_cmd_auto:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_UNRET);
- if (IS_ENABLED(CONFIG_RETHUNK))
- x86_return_thunk = retbleed_return_thunk;
+ x86_return_thunk = retbleed_return_thunk;
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -1061,7 +1059,8 @@ do_cmd_auto:
case RETBLEED_MITIGATION_STUFF:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
- x86_set_skl_return_thunk();
+
+ x86_return_thunk = call_depth_return_thunk;
break;
default:
@@ -1290,6 +1289,8 @@ spectre_v2_user_select_mitigation(void)
spectre_v2_user_ibpb = mode;
switch (cmd) {
+ case SPECTRE_V2_USER_CMD_NONE:
+ break;
case SPECTRE_V2_USER_CMD_FORCE:
case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
@@ -1301,8 +1302,6 @@ spectre_v2_user_select_mitigation(void)
case SPECTRE_V2_USER_CMD_SECCOMP:
static_branch_enable(&switch_mm_cond_ibpb);
break;
- default:
- break;
}
pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
@@ -2160,6 +2159,10 @@ static int l1d_flush_prctl_get(struct task_struct *task)
static int ssb_prctl_get(struct task_struct *task)
{
switch (ssb_mode) {
+ case SPEC_STORE_BYPASS_NONE:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ return PR_SPEC_ENABLE;
+ return PR_SPEC_NOT_AFFECTED;
case SPEC_STORE_BYPASS_DISABLE:
return PR_SPEC_DISABLE;
case SPEC_STORE_BYPASS_SECCOMP:
@@ -2171,11 +2174,8 @@ static int ssb_prctl_get(struct task_struct *task)
if (task_spec_ssb_disable(task))
return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
- default:
- if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
- return PR_SPEC_ENABLE;
- return PR_SPEC_NOT_AFFECTED;
}
+ BUG();
}
static int ib_prctl_get(struct task_struct *task)
@@ -2353,6 +2353,8 @@ early_param("l1tf", l1tf_cmdline);
enum srso_mitigation {
SRSO_MITIGATION_NONE,
+ SRSO_MITIGATION_UCODE_NEEDED,
+ SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED,
SRSO_MITIGATION_MICROCODE,
SRSO_MITIGATION_SAFE_RET,
SRSO_MITIGATION_IBPB,
@@ -2368,11 +2370,13 @@ enum srso_mitigation_cmd {
};
static const char * const srso_strings[] = {
- [SRSO_MITIGATION_NONE] = "Vulnerable",
- [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode",
- [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET",
- [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB",
- [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only"
+ [SRSO_MITIGATION_NONE] = "Vulnerable",
+ [SRSO_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
+ [SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED] = "Vulnerable: Safe RET, no microcode",
+ [SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET",
+ [SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET",
+ [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB",
+ [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only"
};
static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
@@ -2404,46 +2408,45 @@ early_param("spec_rstack_overflow", srso_parse_cmdline);
static void __init srso_select_mitigation(void)
{
- bool has_microcode;
+ bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
- if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off())
- goto pred_cmd;
+ if (cpu_mitigations_off())
+ return;
- /*
- * The first check is for the kernel running as a guest in order
- * for guests to verify whether IBPB is a viable mitigation.
- */
- has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode();
- if (!has_microcode) {
- pr_warn("IBPB-extending microcode not applied!\n");
- pr_warn(SRSO_NOTICE);
- } else {
- /*
- * Enable the synthetic (even if in a real CPUID leaf)
- * flags for guests.
- */
- setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+ if (!boot_cpu_has_bug(X86_BUG_SRSO)) {
+ if (boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
+ return;
+ }
+ if (has_microcode) {
/*
* Zen1/2 with SMT off aren't vulnerable after the right
* IBPB microcode has been applied.
+ *
+ * Zen1/2 don't have SBPB, no need to try to enable it here.
*/
if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
return;
}
- }
- if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
- if (has_microcode) {
- pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n");
+ if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
srso_mitigation = SRSO_MITIGATION_IBPB;
- goto pred_cmd;
+ goto out;
}
+ } else {
+ pr_warn("IBPB-extending microcode not applied!\n");
+ pr_warn(SRSO_NOTICE);
+
+ /* may be overwritten by SRSO_CMD_SAFE_RET below */
+ srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED;
}
switch (srso_cmd) {
case SRSO_CMD_OFF:
+ if (boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
return;
case SRSO_CMD_MICROCODE:
@@ -2469,10 +2472,12 @@ static void __init srso_select_mitigation(void)
setup_force_cpu_cap(X86_FEATURE_SRSO);
x86_return_thunk = srso_return_thunk;
}
- srso_mitigation = SRSO_MITIGATION_SAFE_RET;
+ if (has_microcode)
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET;
+ else
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
} else {
pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
- goto pred_cmd;
}
break;
@@ -2484,7 +2489,6 @@ static void __init srso_select_mitigation(void)
}
} else {
pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
- goto pred_cmd;
}
break;
@@ -2496,20 +2500,12 @@ static void __init srso_select_mitigation(void)
}
} else {
pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
- goto pred_cmd;
}
break;
-
- default:
- break;
}
- pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode"));
-
-pred_cmd:
- if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) &&
- boot_cpu_has(X86_FEATURE_SBPB))
- x86_pred_cmd = PRED_CMD_SBPB;
+out:
+ pr_info("%s\n", srso_strings[srso_mitigation]);
}
#undef pr_fmt
@@ -2715,9 +2711,7 @@ static ssize_t srso_show_state(char *buf)
if (boot_cpu_has(X86_FEATURE_SRSO_NO))
return sysfs_emit(buf, "Mitigation: SMT disabled\n");
- return sysfs_emit(buf, "%s%s\n",
- srso_strings[srso_mitigation],
- (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));
+ return sysfs_emit(buf, "%s\n", srso_strings[srso_mitigation]);
}
static ssize_t gds_show_state(char *buf)
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 8f86eacf69f7..c131c412db89 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -661,7 +661,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c)
return i;
}
-void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c)
{
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -672,13 +672,13 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
if (c->x86 < 0x17) {
/* LLC is at the node level. */
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
+ c->topo.llc_id = c->topo.die_id;
} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
*/
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ c->topo.llc_id = c->topo.apicid >> 3;
} else {
/*
* LLC ID is calculated from the number of threads sharing the
@@ -694,12 +694,12 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu)
if (num_sharing_cache) {
int bits = get_count_order(num_sharing_cache);
- per_cpu(cpu_llc_id, cpu) = c->apicid >> bits;
+ c->topo.llc_id = c->topo.apicid >> bits;
}
}
}
-void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu)
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
{
/*
* We may have multiple LLCs if L3 caches exist, so check if we
@@ -712,7 +712,7 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu)
* LLC is at the core complex level.
* Core complex ID is ApicId[3] for these processors.
*/
- per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
+ c->topo.llc_id = c->topo.apicid >> 3;
}
void init_amd_cacheinfo(struct cpuinfo_x86 *c)
@@ -740,9 +740,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
-#ifdef CONFIG_SMP
- unsigned int cpu = c->cpu_index;
-#endif
if (c->cpuid_level > 3) {
static int is_initialized;
@@ -776,13 +773,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
new_l2 = this_leaf.size/1024;
num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- l2_id = c->apicid & ~((1 << index_msb) - 1);
+ l2_id = c->topo.apicid & ~((1 << index_msb) - 1);
break;
case 3:
new_l3 = this_leaf.size/1024;
num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- l3_id = c->apicid & ~((1 << index_msb) - 1);
+ l3_id = c->topo.apicid & ~((1 << index_msb) - 1);
break;
default:
break;
@@ -856,30 +853,24 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
if (new_l2) {
l2 = new_l2;
-#ifdef CONFIG_SMP
- per_cpu(cpu_llc_id, cpu) = l2_id;
- per_cpu(cpu_l2c_id, cpu) = l2_id;
-#endif
+ c->topo.llc_id = l2_id;
+ c->topo.l2c_id = l2_id;
}
if (new_l3) {
l3 = new_l3;
-#ifdef CONFIG_SMP
- per_cpu(cpu_llc_id, cpu) = l3_id;
-#endif
+ c->topo.llc_id = l3_id;
}
-#ifdef CONFIG_SMP
/*
- * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+ * If llc_id is not yet set, this means cpuid_level < 4 which in
* turns means that the only possibility is SMT (as indicated in
* cpuid1). Since cpuid2 doesn't specify shared caches, and we know
* that SMT shares all caches, we can unconditionally set cpu_llc_id to
- * c->phys_proc_id.
+ * c->topo.pkg_id.
*/
- if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
- per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
-#endif
+ if (c->topo.llc_id == BAD_APICID)
+ c->topo.llc_id = c->topo.pkg_id;
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
@@ -915,7 +906,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
unsigned int apicid, nshared, first, last;
nshared = base->eax.split.num_threads_sharing + 1;
- apicid = cpu_data(cpu).apicid;
+ apicid = cpu_data(cpu).topo.apicid;
first = apicid - (apicid % nshared);
last = first + nshared - 1;
@@ -924,14 +915,14 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
if (!this_cpu_ci->info_list)
continue;
- apicid = cpu_data(i).apicid;
+ apicid = cpu_data(i).topo.apicid;
if ((apicid < first) || (apicid > last))
continue;
this_leaf = this_cpu_ci->info_list + index;
for_each_online_cpu(sibling) {
- apicid = cpu_data(sibling).apicid;
+ apicid = cpu_data(sibling).topo.apicid;
if ((apicid < first) || (apicid > last))
continue;
cpumask_set_cpu(sibling,
@@ -969,7 +960,7 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i)
- if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) {
+ if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) {
struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
if (i == cpu || !sib_cpu_ci->info_list)
@@ -1024,7 +1015,7 @@ static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- id4_regs->id = c->apicid >> index_msb;
+ id4_regs->id = c->topo.apicid >> index_msb;
}
int populate_cache_leaves(unsigned int cpu)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 382d4e6b848d..5d9591146244 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -62,6 +62,7 @@
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/uv/uv.h>
+#include <asm/ia32.h>
#include <asm/set_memory.h>
#include <asm/traps.h>
#include <asm/sev.h>
@@ -74,18 +75,6 @@ u32 elf_hwcap2 __read_mostly;
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);
-/* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
-
-u16 get_llc_id(unsigned int cpu)
-{
- return per_cpu(cpu_llc_id, cpu);
-}
-EXPORT_SYMBOL_GPL(get_llc_id);
-
-/* L2 cache ID of each logical CPU */
-DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID;
-
static struct ppin_info {
int feature;
int msr_ppin_ctl;
@@ -914,7 +903,7 @@ void detect_ht(struct cpuinfo_x86 *c)
return;
index_msb = get_count_order(smp_num_siblings);
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
+ c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb);
smp_num_siblings = smp_num_siblings / c->x86_max_cores;
@@ -922,8 +911,8 @@ void detect_ht(struct cpuinfo_x86 *c)
core_bits = get_count_order(c->x86_max_cores);
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
- ((1 << core_bits) - 1);
+ c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) &
+ ((1 << core_bits) - 1);
#endif
}
@@ -1114,18 +1103,34 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
void get_cpu_address_sizes(struct cpuinfo_x86 *c)
{
u32 eax, ebx, ecx, edx;
+ bool vp_bits_from_cpuid = true;
- if (c->extended_cpuid_level >= 0x80000008) {
+ if (!cpu_has(c, X86_FEATURE_CPUID) ||
+ (c->extended_cpuid_level < 0x80000008))
+ vp_bits_from_cpuid = false;
+
+ if (vp_bits_from_cpuid) {
cpuid(0x80000008, &eax, &ebx, &ecx, &edx);
c->x86_virt_bits = (eax >> 8) & 0xff;
c->x86_phys_bits = eax & 0xff;
+ } else {
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ c->x86_clflush_size = 64;
+ c->x86_phys_bits = 36;
+ c->x86_virt_bits = 48;
+ } else {
+ c->x86_clflush_size = 32;
+ c->x86_virt_bits = 32;
+ c->x86_phys_bits = 32;
+
+ if (cpu_has(c, X86_FEATURE_PAE) ||
+ cpu_has(c, X86_FEATURE_PSE36))
+ c->x86_phys_bits = 36;
+ }
}
-#ifdef CONFIG_X86_32
- else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36))
- c->x86_phys_bits = 36;
-#endif
c->x86_cache_bits = c->x86_phys_bits;
+ c->x86_cache_alignment = c->x86_clflush_size;
}
static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
@@ -1303,7 +1308,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
- VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
+ VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
VULNBL_AMD(0x19, SRSO),
{}
};
@@ -1579,17 +1584,6 @@ static void __init cpu_parse_early_param(void)
*/
static void __init early_identify_cpu(struct cpuinfo_x86 *c)
{
-#ifdef CONFIG_X86_64
- c->x86_clflush_size = 64;
- c->x86_phys_bits = 36;
- c->x86_virt_bits = 48;
-#else
- c->x86_clflush_size = 32;
- c->x86_phys_bits = 32;
- c->x86_virt_bits = 32;
-#endif
- c->x86_cache_alignment = c->x86_clflush_size;
-
memset(&c->x86_capability, 0, sizeof(c->x86_capability));
c->extended_cpuid_level = 0;
@@ -1601,7 +1595,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
cpu_detect(c);
get_cpu_vendor(c);
get_cpu_cap(c);
- get_cpu_address_sizes(c);
setup_force_cpu_cap(X86_FEATURE_CPUID);
cpu_parse_early_param();
@@ -1617,6 +1610,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_CPUID);
}
+ get_cpu_address_sizes(c);
+
setup_force_cpu_cap(X86_FEATURE_ALWAYS);
cpu_set_bug_bits(c);
@@ -1761,15 +1756,15 @@ static void generic_identify(struct cpuinfo_x86 *c)
get_cpu_address_sizes(c);
if (c->cpuid_level >= 0x00000001) {
- c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
+ c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF;
#ifdef CONFIG_X86_32
# ifdef CONFIG_SMP
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
# else
- c->apicid = c->initial_apicid;
+ c->topo.apicid = c->topo.initial_apicid;
# endif
#endif
- c->phys_proc_id = c->initial_apicid;
+ c->topo.pkg_id = c->topo.initial_apicid;
}
get_model_name(c); /* Default name */
@@ -1799,18 +1794,19 @@ static void generic_identify(struct cpuinfo_x86 *c)
static void validate_apic_and_package_id(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
- unsigned int apicid, cpu = smp_processor_id();
+ unsigned int cpu = smp_processor_id();
+ u32 apicid;
apicid = apic->cpu_present_to_apicid(cpu);
- if (apicid != c->apicid) {
+ if (apicid != c->topo.apicid) {
pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n",
- cpu, apicid, c->initial_apicid);
+ cpu, apicid, c->topo.initial_apicid);
}
- BUG_ON(topology_update_package_map(c->phys_proc_id, cpu));
- BUG_ON(topology_update_die_map(c->cpu_die_id, cpu));
+ BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu));
+ BUG_ON(topology_update_die_map(c->topo.die_id, cpu));
#else
- c->logical_proc_id = 0;
+ c->topo.logical_pkg_id = 0;
#endif
}
@@ -1829,7 +1825,9 @@ static void identify_cpu(struct cpuinfo_x86 *c)
c->x86_model_id[0] = '\0'; /* Unset */
c->x86_max_cores = 1;
c->x86_coreid_bits = 0;
- c->cu_id = 0xff;
+ c->topo.cu_id = 0xff;
+ c->topo.llc_id = BAD_APICID;
+ c->topo.l2c_id = BAD_APICID;
#ifdef CONFIG_X86_64
c->x86_clflush_size = 64;
c->x86_phys_bits = 36;
@@ -1855,7 +1853,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
apply_forced_caps(c);
#ifdef CONFIG_X86_64
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
#endif
/*
@@ -2074,24 +2072,24 @@ void syscall_init(void)
wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
-#ifdef CONFIG_IA32_EMULATION
- wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
- /*
- * This only works on Intel CPUs.
- * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
- * This does not cause SYSENTER to jump to the wrong location, because
- * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
- */
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
- (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
-#else
- wrmsrl_cstar((unsigned long)ignore_sysret);
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
-#endif
+ if (ia32_enabled()) {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+ /*
+ * This only works on Intel CPUs.
+ * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
+ * This does not cause SYSENTER to jump to the wrong location, because
+ * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
+ */
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+ (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+ } else {
+ wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
+ wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+ wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+ }
/*
* Flags to clear on syscall; clear as much as possible
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1dcd7d4e38ef..885281ae79a5 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -78,6 +78,9 @@ extern int detect_ht_early(struct cpuinfo_x86 *c);
extern void detect_ht(struct cpuinfo_x86 *c);
extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
+void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c);
+void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);
+
unsigned int aperfmperf_get_khz(int cpu);
void cpu_select_mitigations(void);
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
new file mode 100644
index 000000000000..0c179d684b3b
--- /dev/null
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/debugfs.h>
+
+#include <asm/apic.h>
+#include <asm/processor.h>
+
+static int cpu_debug_show(struct seq_file *m, void *p)
+{
+ unsigned long cpu = (unsigned long)m->private;
+ struct cpuinfo_x86 *c = per_cpu_ptr(&cpu_info, cpu);
+
+ seq_printf(m, "online: %d\n", cpu_online(cpu));
+ if (!c->initialized)
+ return 0;
+
+ seq_printf(m, "initial_apicid: %x\n", c->topo.initial_apicid);
+ seq_printf(m, "apicid: %x\n", c->topo.apicid);
+ seq_printf(m, "pkg_id: %u\n", c->topo.pkg_id);
+ seq_printf(m, "die_id: %u\n", c->topo.die_id);
+ seq_printf(m, "cu_id: %u\n", c->topo.cu_id);
+ seq_printf(m, "core_id: %u\n", c->topo.core_id);
+ seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id);
+ seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id);
+ seq_printf(m, "llc_id: %u\n", c->topo.llc_id);
+ seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id);
+ seq_printf(m, "max_cores: %u\n", c->x86_max_cores);
+ seq_printf(m, "max_die_per_pkg: %u\n", __max_die_per_package);
+ seq_printf(m, "smp_num_siblings: %u\n", smp_num_siblings);
+ return 0;
+}
+
+static int cpu_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, cpu_debug_show, inode->i_private);
+}
+
+static const struct file_operations dfs_cpu_ops = {
+ .open = cpu_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static __init int cpu_init_debugfs(void)
+{
+ struct dentry *dir, *base = debugfs_create_dir("topo", arch_debugfs_dir);
+ unsigned long id;
+ char name[24];
+
+ dir = debugfs_create_dir("cpus", base);
+ for_each_possible_cpu(id) {
+ sprintf(name, "%lu", id);
+ debugfs_create_file(name, 0444, dir, (void *)id, &dfs_cpu_ops);
+ }
+ return 0;
+}
+late_initcall(cpu_init_debugfs);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index defdc594be14..6f247d66758d 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -63,8 +63,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c)
*/
static void hygon_get_topology(struct cpuinfo_x86 *c)
{
- int cpu = smp_processor_id();
-
/* get information required for multi-node processors */
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
int err;
@@ -72,9 +70,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
- c->cpu_die_id = ecx & 0xff;
+ c->topo.die_id = ecx & 0xff;
- c->cpu_core_id = ebx & 0xff;
+ c->topo.core_id = ebx & 0xff;
if (smp_num_siblings > 1)
c->x86_max_cores /= smp_num_siblings;
@@ -87,17 +85,20 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
if (!err)
c->x86_coreid_bits = get_count_order(c->x86_max_cores);
- /* Socket ID is ApicId[6] for these processors. */
- c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT;
+ /*
+ * Socket ID is ApicId[6] for the processors with model <= 0x3
+ * when running on host.
+ */
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3)
+ c->topo.pkg_id = c->topo.apicid >> APICID_SOCKET_ID_BIT;
- cacheinfo_hygon_init_llc_id(c, cpu);
+ cacheinfo_hygon_init_llc_id(c);
} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
u64 value;
rdmsrl(MSR_FAM10H_NODE_ID, value);
- c->cpu_die_id = value & 7;
-
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id;
+ c->topo.die_id = value & 7;
+ c->topo.llc_id = c->topo.die_id;
} else
return;
@@ -112,15 +113,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c)
static void hygon_detect_cmp(struct cpuinfo_x86 *c)
{
unsigned int bits;
- int cpu = smp_processor_id();
bits = c->x86_coreid_bits;
/* Low order bits define the core id (index of core in socket) */
- c->cpu_core_id = c->initial_apicid & ((1 << bits)-1);
+ c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1);
/* Convert the initial APIC ID into the socket ID */
- c->phys_proc_id = c->initial_apicid >> bits;
- /* use socket ID also for last level cache */
- per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id;
+ c->topo.pkg_id = c->topo.initial_apicid >> bits;
+ /* Use package ID also for last level cache */
+ c->topo.llc_id = c->topo.die_id = c->topo.pkg_id;
}
static void srat_detect_node(struct cpuinfo_x86 *c)
@@ -128,11 +128,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
#ifdef CONFIG_NUMA
int cpu = smp_processor_id();
int node;
- unsigned int apicid = c->apicid;
+ unsigned int apicid = c->topo.apicid;
node = numa_cpu_node(cpu);
if (node == NUMA_NO_NODE)
- node = per_cpu(cpu_llc_id, cpu);
+ node = c->topo.llc_id;
/*
* On multi-fabric platform (e.g. Numascale NumaChip) a
@@ -161,7 +161,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c)
* through CPU mapping may alter the outcome, directly
* access __apicid_to_node[].
*/
- int ht_nodeid = c->initial_apicid;
+ int ht_nodeid = c->topo.initial_apicid;
if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE)
node = __apicid_to_node[ht_nodeid];
@@ -290,6 +290,8 @@ static void early_init_hygon(struct cpuinfo_x86 *c)
static void init_hygon(struct cpuinfo_x86 *c)
{
+ u64 vm_cr;
+
early_init_hygon(c);
/*
@@ -301,7 +303,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
/* get apicid instead of initial apic id from cpuid */
- c->apicid = read_apic_id();
+ c->topo.apicid = read_apic_id();
/*
* XXX someone from Hygon needs to confirm this DTRT
@@ -320,6 +322,14 @@ static void init_hygon(struct cpuinfo_x86 *c)
init_hygon_cacheinfo(c);
+ if (cpu_has(c, X86_FEATURE_SVM)) {
+ rdmsrl(MSR_VM_CR, vm_cr);
+ if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
+ pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
+ clear_cpu_cap(c, X86_FEATURE_SVM);
+ }
+ }
+
if (cpu_has(c, X86_FEATURE_XMM2)) {
/*
* Use LFENCE for execution serialization. On families which
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index be4045628fd3..55efadb0e998 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -314,19 +314,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
setup_clear_cpu_cap(X86_FEATURE_PGE);
}
- if (c->cpuid_level >= 0x00000001) {
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
- /*
- * If HTT (EDX[28]) is set EBX[16:23] contain the number of
- * apicids which are reserved per package. Store the resulting
- * shift value for the package management code.
- */
- if (edx & (1U << 28))
- c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
- }
-
check_memory_type_self_snoop_errata(c);
/*
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index c267f43de39e..f3517b8a8e91 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -713,17 +713,75 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
deferred_error_interrupt_enable(c);
}
-bool amd_mce_is_memory_error(struct mce *m)
+/*
+ * DRAM ECC errors are reported in the Northbridge (bank 4) with
+ * Extended Error Code 8.
+ */
+static bool legacy_mce_is_memory_error(struct mce *m)
+{
+ return m->bank == 4 && XEC(m->status, 0x1f) == 8;
+}
+
+/*
+ * DRAM ECC errors are reported in Unified Memory Controllers with
+ * Extended Error Code 0.
+ */
+static bool smca_mce_is_memory_error(struct mce *m)
{
enum smca_bank_types bank_type;
- /* ErrCodeExt[20:16] */
- u8 xec = (m->status >> 16) & 0x1f;
+
+ if (XEC(m->status, 0x3f))
+ return false;
bank_type = smca_get_bank_type(m->extcpu, m->bank);
+
+ return bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2;
+}
+
+bool amd_mce_is_memory_error(struct mce *m)
+{
if (mce_flags.smca)
- return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0;
+ return smca_mce_is_memory_error(m);
+ else
+ return legacy_mce_is_memory_error(m);
+}
+
+/*
+ * AMD systems do not have an explicit indicator that the value in MCA_ADDR is
+ * a system physical address. Therefore, individual cases need to be detected.
+ * Future cases and checks will be added as needed.
+ *
+ * 1) General case
+ * a) Assume address is not usable.
+ * 2) Poison errors
+ * a) Indicated by MCA_STATUS[43]: poison. Defined for all banks except legacy
+ * northbridge (bank 4).
+ * b) Refers to poison consumption in the core. Does not include "no action",
+ * "action optional", or "deferred" error severities.
+ * c) Will include a usable address so that immediate action can be taken.
+ * 3) Northbridge DRAM ECC errors
+ * a) Reported in legacy bank 4 with extended error code (XEC) 8.
+ * b) MCA_STATUS[43] is *not* defined as poison in legacy bank 4. Therefore,
+ * this bit should not be checked.
+ *
+ * NOTE: SMCA UMC memory errors fall into case #1.
+ */
+bool amd_mce_usable_address(struct mce *m)
+{
+ /* Check special northbridge case 3) first. */
+ if (!mce_flags.smca) {
+ if (legacy_mce_is_memory_error(m))
+ return true;
+ else if (m->bank == 4)
+ return false;
+ }
- return m->bank == 4 && xec == 0x8;
+ /* Check poison bit for all other bank types. */
+ if (m->status & MCI_STATUS_POISON)
+ return true;
+
+ /* Assume address is not usable for all others. */
+ return false;
}
static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c
index 8ed341714686..7f7309ff67d0 100644
--- a/arch/x86/kernel/cpu/mce/apei.c
+++ b/arch/x86/kernel/cpu/mce/apei.c
@@ -103,9 +103,9 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id)
m.socketid = -1;
for_each_possible_cpu(cpu) {
- if (cpu_data(cpu).initial_apicid == lapic_id) {
+ if (cpu_data(cpu).topo.initial_apicid == lapic_id) {
m.extcpu = cpu;
- m.socketid = cpu_data(m.extcpu).phys_proc_id;
+ m.socketid = cpu_data(m.extcpu).topo.pkg_id;
break;
}
}
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 6f35f724cc14..7b397370b4d6 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -123,8 +123,8 @@ void mce_setup(struct mce *m)
m->time = __ktime_get_real_seconds();
m->cpuvendor = boot_cpu_data.x86_vendor;
m->cpuid = cpuid_eax(1);
- m->socketid = cpu_data(m->extcpu).phys_proc_id;
- m->apicid = cpu_data(m->extcpu).initial_apicid;
+ m->socketid = cpu_data(m->extcpu).topo.pkg_id;
+ m->apicid = cpu_data(m->extcpu).topo.initial_apicid;
m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
m->ppin = cpu_data(m->extcpu).ppin;
m->microcode = boot_cpu_data.microcode;
@@ -453,32 +453,22 @@ static void mce_irq_work_cb(struct irq_work *entry)
mce_schedule_work();
}
-/*
- * Check if the address reported by the CPU is in a format we can parse.
- * It would be possible to add code for most other cases, but all would
- * be somewhat complicated (e.g. segment offset would require an instruction
- * parser). So only support physical addresses up to page granularity for now.
- */
-int mce_usable_address(struct mce *m)
+bool mce_usable_address(struct mce *m)
{
if (!(m->status & MCI_STATUS_ADDRV))
- return 0;
-
- /* Checks after this one are Intel/Zhaoxin-specific: */
- if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL &&
- boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN)
- return 1;
-
- if (!(m->status & MCI_STATUS_MISCV))
- return 0;
+ return false;
- if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
- return 0;
+ switch (m->cpuvendor) {
+ case X86_VENDOR_AMD:
+ return amd_mce_usable_address(m);
- if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
- return 0;
+ case X86_VENDOR_INTEL:
+ case X86_VENDOR_ZHAOXIN:
+ return intel_mce_usable_address(m);
- return 1;
+ default:
+ return true;
+ }
}
EXPORT_SYMBOL_GPL(mce_usable_address);
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f5323551c1a9..52bce533ddcc 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -536,3 +536,23 @@ bool intel_filter_mce(struct mce *m)
return false;
}
+
+/*
+ * Check if the address reported by the CPU is in a format we can parse.
+ * It would be possible to add code for most other cases, but all would
+ * be somewhat complicated (e.g. segment offset would require an instruction
+ * parser). So only support physical addresses up to page granularity for now.
+ */
+bool intel_mce_usable_address(struct mce *m)
+{
+ if (!(m->status & MCI_STATUS_MISCV))
+ return false;
+
+ if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT)
+ return false;
+
+ if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS)
+ return false;
+
+ return true;
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index bcf1b3c66c9c..e13a26c9c0ac 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -49,6 +49,7 @@ void intel_init_cmci(void);
void intel_init_lmce(void);
void intel_clear_lmce(void);
bool intel_filter_mce(struct mce *m);
+bool intel_mce_usable_address(struct mce *m);
#else
# define cmci_intel_adjust_timer mce_adjust_timer_default
static inline bool mce_intel_cmci_poll(void) { return false; }
@@ -58,6 +59,7 @@ static inline void intel_init_cmci(void) { }
static inline void intel_init_lmce(void) { }
static inline void intel_clear_lmce(void) { }
static inline bool intel_filter_mce(struct mce *m) { return false; }
+static inline bool intel_mce_usable_address(struct mce *m) { return false; }
#endif
void mce_timer_kick(unsigned long interval);
@@ -210,6 +212,7 @@ extern bool filter_mce(struct mce *m);
#ifdef CONFIG_X86_MCE_AMD
extern bool amd_filter_mce(struct mce *m);
+bool amd_mce_usable_address(struct mce *m);
/*
* If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits
@@ -237,6 +240,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m)
#else
static inline bool amd_filter_mce(struct mce *m) { return false; }
+static inline bool amd_mce_usable_address(struct mce *m) { return false; }
static inline void smca_extract_err_addr(struct mce *m) { }
#endif
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 31c0e68f6227..e65fae63660e 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -20,13 +20,13 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
unsigned int cpu)
{
#ifdef CONFIG_SMP
- seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
+ seq_printf(m, "physical id\t: %d\n", c->topo.pkg_id);
seq_printf(m, "siblings\t: %d\n",
cpumask_weight(topology_core_cpumask(cpu)));
- seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
+ seq_printf(m, "core id\t\t: %d\n", c->topo.core_id);
seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
- seq_printf(m, "apicid\t\t: %d\n", c->apicid);
- seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid);
+ seq_printf(m, "apicid\t\t: %d\n", c->topo.apicid);
+ seq_printf(m, "initial apicid\t: %d\n", c->topo.initial_apicid);
#endif
}
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 030d3b409768..19e0681f0435 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -152,6 +152,7 @@ static inline void cache_alloc_hsw_probe(void)
r->cache.cbm_len = 20;
r->cache.shareable_bits = 0xc0000;
r->cache.min_cbm_bits = 2;
+ r->cache.arch_has_sparse_bitmasks = false;
r->alloc_capable = true;
rdt_alloc_capable = true;
@@ -267,15 +268,18 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r)
{
struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
union cpuid_0x10_1_eax eax;
+ union cpuid_0x10_x_ecx ecx;
union cpuid_0x10_x_edx edx;
- u32 ebx, ecx;
+ u32 ebx;
- cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full);
+ cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full);
hw_res->num_closid = edx.split.cos_max + 1;
r->cache.cbm_len = eax.split.cbm_len + 1;
r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1;
r->cache.shareable_bits = ebx & r->default_ctrl;
r->data_width = (r->cache.cbm_len + 3) / 4;
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ r->cache.arch_has_sparse_bitmasks = ecx.split.noncont;
r->alloc_capable = true;
}
@@ -872,7 +876,6 @@ static __init void rdt_init_res_defs_intel(void)
if (r->rid == RDT_RESOURCE_L3 ||
r->rid == RDT_RESOURCE_L2) {
- r->cache.arch_has_sparse_bitmaps = false;
r->cache.arch_has_per_cpu_cfg = false;
r->cache.min_cbm_bits = 1;
} else if (r->rid == RDT_RESOURCE_MBA) {
@@ -892,7 +895,7 @@ static __init void rdt_init_res_defs_amd(void)
if (r->rid == RDT_RESOURCE_L3 ||
r->rid == RDT_RESOURCE_L2) {
- r->cache.arch_has_sparse_bitmaps = true;
+ r->cache.arch_has_sparse_bitmasks = true;
r->cache.arch_has_per_cpu_cfg = true;
r->cache.min_cbm_bits = 0;
} else if (r->rid == RDT_RESOURCE_MBA) {
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index b44c487727d4..beccb0e87ba7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -87,10 +87,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
/*
* Check whether a cache bit mask is valid.
- * For Intel the SDM says:
- * Please note that all (and only) contiguous '1' combinations
- * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
- * Additionally Haswell requires at least two bits set.
+ * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
+ * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
+ * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
+ *
+ * Haswell does not support a non-contiguous 1s value and additionally
+ * requires at least two bits set.
* AMD allows non-contiguous bitmasks.
*/
static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
@@ -113,8 +115,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
first_bit = find_first_bit(&val, cbm_len);
zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
- /* Are non-contiguous bitmaps allowed? */
- if (!r->cache.arch_has_sparse_bitmaps &&
+ /* Are non-contiguous bitmasks allowed? */
+ if (!r->cache.arch_has_sparse_bitmasks &&
(find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
return false;
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 85ceaf9a31ac..a4f1aa15f0a2 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -59,6 +59,7 @@ struct rdt_fs_context {
bool enable_cdpl2;
bool enable_cdpl3;
bool enable_mba_mbps;
+ bool enable_debug;
};
static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
@@ -243,18 +244,17 @@ struct rdtgroup {
*/
#define RFTYPE_INFO BIT(0)
#define RFTYPE_BASE BIT(1)
-#define RF_CTRLSHIFT 4
-#define RF_MONSHIFT 5
-#define RF_TOPSHIFT 6
-#define RFTYPE_CTRL BIT(RF_CTRLSHIFT)
-#define RFTYPE_MON BIT(RF_MONSHIFT)
-#define RFTYPE_TOP BIT(RF_TOPSHIFT)
+#define RFTYPE_CTRL BIT(4)
+#define RFTYPE_MON BIT(5)
+#define RFTYPE_TOP BIT(6)
#define RFTYPE_RES_CACHE BIT(8)
#define RFTYPE_RES_MB BIT(9)
-#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
-#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
-#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
-#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
+#define RFTYPE_DEBUG BIT(10)
+#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
+#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
+#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
+#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
+#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON)
/* List of all resource groups */
extern struct list_head rdt_all_groups;
@@ -270,7 +270,7 @@ void __exit rdtgroup_exit(void);
* @mode: Access mode
* @kf_ops: File operations
* @flags: File specific RFTYPE_FLAGS_* flags
- * @fflags: File specific RF_* or RFTYPE_* flags
+ * @fflags: File specific RFTYPE_* flags
* @seq_show: Show content of the file
* @write: Write to the file
*/
@@ -492,6 +492,15 @@ union cpuid_0x10_3_eax {
unsigned int full;
};
+/* CPUID.(EAX=10H, ECX=ResID).ECX */
+union cpuid_0x10_x_ecx {
+ struct {
+ unsigned int reserved:3;
+ unsigned int noncont:1;
+ } split;
+ unsigned int full;
+};
+
/* CPUID.(EAX=10H, ECX=ResID).EDX */
union cpuid_0x10_x_edx {
struct {
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index ded1fc7cb7cb..f136ac046851 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -30,15 +30,15 @@ struct rmid_entry {
struct list_head list;
};
-/**
- * @rmid_free_lru A least recently used list of free RMIDs
+/*
+ * @rmid_free_lru - A least recently used list of free RMIDs
* These RMIDs are guaranteed to have an occupancy less than the
* threshold occupancy
*/
static LIST_HEAD(rmid_free_lru);
-/**
- * @rmid_limbo_count count of currently unused but (potentially)
+/*
+ * @rmid_limbo_count - count of currently unused but (potentially)
* dirty RMIDs.
* This counts RMIDs that no one is currently using but that
* may have a occupancy value > resctrl_rmid_realloc_threshold. User can
@@ -46,7 +46,7 @@ static LIST_HEAD(rmid_free_lru);
*/
static unsigned int rmid_limbo_count;
-/**
+/*
* @rmid_entry - The entry in the limbo and free lists.
*/
static struct rmid_entry *rmid_ptrs;
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 725344048f85..69a1de92384a 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -54,8 +54,13 @@ static struct kernfs_node *kn_mondata;
static struct seq_buf last_cmd_status;
static char last_cmd_status_buf[512];
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
+static void rdtgroup_destroy_root(void);
+
struct dentry *debugfs_resctrl;
+static bool resctrl_debug;
+
void rdt_last_cmd_clear(void)
{
lockdep_assert_held(&rdtgroup_mutex);
@@ -696,11 +701,10 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
{
struct rdtgroup *rdtgrp;
+ char *pid_str;
int ret = 0;
pid_t pid;
- if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
- return -EINVAL;
rdtgrp = rdtgroup_kn_lock_live(of->kn);
if (!rdtgrp) {
rdtgroup_kn_unlock(of->kn);
@@ -715,7 +719,27 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
goto unlock;
}
- ret = rdtgroup_move_task(pid, rdtgrp, of);
+ while (buf && buf[0] != '\0' && buf[0] != '\n') {
+ pid_str = strim(strsep(&buf, ","));
+
+ if (kstrtoint(pid_str, 0, &pid)) {
+ rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
+ ret = -EINVAL;
+ break;
+ }
+
+ if (pid < 0) {
+ rdt_last_cmd_printf("Invalid pid %d\n", pid);
+ ret = -EINVAL;
+ break;
+ }
+
+ ret = rdtgroup_move_task(pid, rdtgrp, of);
+ if (ret) {
+ rdt_last_cmd_printf("Error while processing task %d\n", pid);
+ break;
+ }
+ }
unlock:
rdtgroup_kn_unlock(of->kn);
@@ -755,6 +779,38 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of,
return ret;
}
+static int rdtgroup_closid_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (rdtgrp)
+ seq_printf(s, "%u\n", rdtgrp->closid);
+ else
+ ret = -ENOENT;
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret;
+}
+
+static int rdtgroup_rmid_show(struct kernfs_open_file *of,
+ struct seq_file *s, void *v)
+{
+ struct rdtgroup *rdtgrp;
+ int ret = 0;
+
+ rdtgrp = rdtgroup_kn_lock_live(of->kn);
+ if (rdtgrp)
+ seq_printf(s, "%u\n", rdtgrp->mon.rmid);
+ else
+ ret = -ENOENT;
+ rdtgroup_kn_unlock(of->kn);
+
+ return ret;
+}
+
#ifdef CONFIG_PROC_CPU_RESCTRL
/*
@@ -895,7 +951,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
return 0;
}
-/**
+/*
* rdt_bit_usage_show - Display current usage of resources
*
* A domain is a shared resource that can now be allocated differently. Here
@@ -1117,12 +1173,24 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
}
}
+static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
+ struct seq_file *seq, void *v)
+{
+ struct resctrl_schema *s = of->kn->parent->priv;
+ struct rdt_resource *r = s->res;
+
+ seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
+
+ return 0;
+}
+
/**
* __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
* @r: Resource to which domain instance @d belongs.
* @d: The domain instance for which @closid is being tested.
* @cbm: Capacity bitmask being tested.
* @closid: Intended closid for @cbm.
+ * @type: CDP type of @r.
* @exclusive: Only check if overlaps with exclusive resource groups
*
* Checks if provided @cbm intended to be used for @closid on domain
@@ -1209,6 +1277,7 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
/**
* rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ * @rdtgrp: Resource group identified through its closid.
*
* An exclusive resource group implies that there should be no sharing of
* its allocated resources. At the time this group is considered to be
@@ -1251,9 +1320,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
return true;
}
-/**
+/*
* rdtgroup_mode_write - Modify the resource group's mode
- *
*/
static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
char *buf, size_t nbytes, loff_t off)
@@ -1357,12 +1425,11 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
return size;
}
-/**
+/*
* rdtgroup_size_show - Display size in bytes of allocated regions
*
* The "size" file mirrors the layout of the "schemata" file, printing the
* size in bytes of each region instead of the capacity bitmask.
- *
*/
static int rdtgroup_size_show(struct kernfs_open_file *of,
struct seq_file *s, void *v)
@@ -1686,77 +1753,77 @@ static struct rftype res_common_files[] = {
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_last_cmd_status_show,
- .fflags = RF_TOP_INFO,
+ .fflags = RFTYPE_TOP_INFO,
},
{
.name = "num_closids",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_num_closids_show,
- .fflags = RF_CTRL_INFO,
+ .fflags = RFTYPE_CTRL_INFO,
},
{
.name = "mon_features",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_mon_features_show,
- .fflags = RF_MON_INFO,
+ .fflags = RFTYPE_MON_INFO,
},
{
.name = "num_rmids",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_num_rmids_show,
- .fflags = RF_MON_INFO,
+ .fflags = RFTYPE_MON_INFO,
},
{
.name = "cbm_mask",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_default_ctrl_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "min_cbm_bits",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_min_cbm_bits_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "shareable_bits",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_shareable_bits_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "bit_usage",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_bit_usage_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
},
{
.name = "min_bandwidth",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_min_bw_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
{
.name = "bandwidth_gran",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_bw_gran_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
{
.name = "delay_linear",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdt_delay_linear_show,
- .fflags = RF_CTRL_INFO | RFTYPE_RES_MB,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
},
/*
* Platform specific which (if any) capabilities are provided by
@@ -1775,7 +1842,7 @@ static struct rftype res_common_files[] = {
.kf_ops = &rdtgroup_kf_single_ops,
.write = max_threshold_occ_write,
.seq_show = max_threshold_occ_show,
- .fflags = RF_MON_INFO | RFTYPE_RES_CACHE,
+ .fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
},
{
.name = "mbm_total_bytes_config",
@@ -1817,12 +1884,19 @@ static struct rftype res_common_files[] = {
.fflags = RFTYPE_BASE,
},
{
+ .name = "mon_hw_id",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdtgroup_rmid_show,
+ .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG,
+ },
+ {
.name = "schemata",
.mode = 0644,
.kf_ops = &rdtgroup_kf_single_ops,
.write = rdtgroup_schemata_write,
.seq_show = rdtgroup_schemata_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
},
{
.name = "mode",
@@ -1830,14 +1904,28 @@ static struct rftype res_common_files[] = {
.kf_ops = &rdtgroup_kf_single_ops,
.write = rdtgroup_mode_write,
.seq_show = rdtgroup_mode_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
},
{
.name = "size",
.mode = 0444,
.kf_ops = &rdtgroup_kf_single_ops,
.seq_show = rdtgroup_size_show,
- .fflags = RF_CTRL_BASE,
+ .fflags = RFTYPE_CTRL_BASE,
+ },
+ {
+ .name = "sparse_masks",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdt_has_sparse_bitmasks_show,
+ .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
+ },
+ {
+ .name = "ctrl_hw_id",
+ .mode = 0444,
+ .kf_ops = &rdtgroup_kf_single_ops,
+ .seq_show = rdtgroup_closid_show,
+ .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
},
};
@@ -1852,6 +1940,9 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
lockdep_assert_held(&rdtgroup_mutex);
+ if (resctrl_debug)
+ fflags |= RFTYPE_DEBUG;
+
for (rft = rfts; rft < rfts + len; rft++) {
if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
ret = rdtgroup_add_file(kn, rft);
@@ -1894,7 +1985,7 @@ void __init thread_throttle_mode_init(void)
if (!rft)
return;
- rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB;
+ rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB;
}
void __init mbm_config_rftype_init(const char *config)
@@ -1903,7 +1994,7 @@ void __init mbm_config_rftype_init(const char *config)
rft = rdtgroup_get_rftype_by_name(config);
if (rft)
- rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE;
+ rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE;
}
/**
@@ -2038,21 +2129,21 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
if (IS_ERR(kn_info))
return PTR_ERR(kn_info);
- ret = rdtgroup_add_files(kn_info, RF_TOP_INFO);
+ ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
if (ret)
goto out_destroy;
/* loop over enabled controls, these are all alloc_capable */
list_for_each_entry(s, &resctrl_schema_all, list) {
r = s->res;
- fflags = r->fflags | RF_CTRL_INFO;
+ fflags = r->fflags | RFTYPE_CTRL_INFO;
ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
if (ret)
goto out_destroy;
}
for_each_mon_capable_rdt_resource(r) {
- fflags = r->fflags | RF_MON_INFO;
+ fflags = r->fflags | RFTYPE_MON_INFO;
sprintf(name, "%s_MON", r->name);
ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
if (ret)
@@ -2271,14 +2362,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
return 0;
}
-static void cdp_disable_all(void)
-{
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-}
-
/*
* We don't allow rdtgroup directories to be created anywhere
* except the root directory. Thus when looking for the rdtgroup
@@ -2358,19 +2441,47 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn,
struct rdtgroup *prgrp,
struct kernfs_node **mon_data_kn);
+static void rdt_disable_ctx(void)
+{
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+ set_mba_sc(false);
+
+ resctrl_debug = false;
+}
+
static int rdt_enable_ctx(struct rdt_fs_context *ctx)
{
int ret = 0;
- if (ctx->enable_cdpl2)
+ if (ctx->enable_cdpl2) {
ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
+ if (ret)
+ goto out_done;
+ }
- if (!ret && ctx->enable_cdpl3)
+ if (ctx->enable_cdpl3) {
ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
+ if (ret)
+ goto out_cdpl2;
+ }
- if (!ret && ctx->enable_mba_mbps)
+ if (ctx->enable_mba_mbps) {
ret = set_mba_sc(true);
+ if (ret)
+ goto out_cdpl3;
+ }
+
+ if (ctx->enable_debug)
+ resctrl_debug = true;
+ return 0;
+
+out_cdpl3:
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
+out_cdpl2:
+ resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
+out_done:
return ret;
}
@@ -2463,6 +2574,7 @@ static void schemata_list_destroy(void)
static int rdt_get_tree(struct fs_context *fc)
{
struct rdt_fs_context *ctx = rdt_fc2context(fc);
+ unsigned long flags = RFTYPE_CTRL_BASE;
struct rdt_domain *dom;
struct rdt_resource *r;
int ret;
@@ -2477,18 +2589,31 @@ static int rdt_get_tree(struct fs_context *fc)
goto out;
}
+ ret = rdtgroup_setup_root(ctx);
+ if (ret)
+ goto out;
+
ret = rdt_enable_ctx(ctx);
- if (ret < 0)
- goto out_cdp;
+ if (ret)
+ goto out_root;
ret = schemata_list_create();
if (ret) {
schemata_list_destroy();
- goto out_mba;
+ goto out_ctx;
}
closid_init();
+ if (rdt_mon_capable)
+ flags |= RFTYPE_MON;
+
+ ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
+ if (ret)
+ goto out_schemata_free;
+
+ kernfs_activate(rdtgroup_default.kn);
+
ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
if (ret < 0)
goto out_schemata_free;
@@ -2543,11 +2668,10 @@ out_info:
kernfs_remove(kn_info);
out_schemata_free:
schemata_list_destroy();
-out_mba:
- if (ctx->enable_mba_mbps)
- set_mba_sc(false);
-out_cdp:
- cdp_disable_all();
+out_ctx:
+ rdt_disable_ctx();
+out_root:
+ rdtgroup_destroy_root();
out:
rdt_last_cmd_clear();
mutex_unlock(&rdtgroup_mutex);
@@ -2559,6 +2683,7 @@ enum rdt_param {
Opt_cdp,
Opt_cdpl2,
Opt_mba_mbps,
+ Opt_debug,
nr__rdt_params
};
@@ -2566,6 +2691,7 @@ static const struct fs_parameter_spec rdt_fs_parameters[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
fsparam_flag("mba_MBps", Opt_mba_mbps),
+ fsparam_flag("debug", Opt_debug),
{}
};
@@ -2591,6 +2717,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
return -EINVAL;
ctx->enable_mba_mbps = true;
return 0;
+ case Opt_debug:
+ ctx->enable_debug = true;
+ return 0;
}
return -EINVAL;
@@ -2618,7 +2747,6 @@ static int rdt_init_fs_context(struct fs_context *fc)
if (!ctx)
return -ENOMEM;
- ctx->kfc.root = rdt_root;
ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
fc->fs_private = &ctx->kfc;
fc->ops = &rdt_fs_context_ops;
@@ -2779,16 +2907,16 @@ static void rdt_kill_sb(struct super_block *sb)
cpus_read_lock();
mutex_lock(&rdtgroup_mutex);
- set_mba_sc(false);
+ rdt_disable_ctx();
/*Put everything back to default values. */
for_each_alloc_capable_rdt_resource(r)
reset_all_ctrls(r);
- cdp_disable_all();
rmdir_all_sub();
rdt_pseudo_lock_release();
rdtgroup_default.mode = RDT_MODE_SHAREABLE;
schemata_list_destroy();
+ rdtgroup_destroy_root();
static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
static_branch_disable_cpuslocked(&rdt_mon_enable_key);
static_branch_disable_cpuslocked(&rdt_enable_key);
@@ -3170,8 +3298,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
enum rdt_group_type rtype, struct rdtgroup **r)
{
struct rdtgroup *prdtgrp, *rdtgrp;
+ unsigned long files = 0;
struct kernfs_node *kn;
- uint files = 0;
int ret;
prdtgrp = rdtgroup_kn_lock_live(parent_kn);
@@ -3223,7 +3351,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
goto out_destroy;
}
- files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype);
+ if (rtype == RDTCTRL_GROUP) {
+ files = RFTYPE_BASE | RFTYPE_CTRL;
+ if (rdt_mon_capable)
+ files |= RFTYPE_MON;
+ } else {
+ files = RFTYPE_BASE | RFTYPE_MON;
+ }
+
ret = rdtgroup_add_files(kn, files);
if (ret) {
rdt_last_cmd_puts("kernfs fill error\n");
@@ -3656,6 +3791,9 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl))
seq_puts(seq, ",mba_MBps");
+ if (resctrl_debug)
+ seq_puts(seq, ",debug");
+
return 0;
}
@@ -3666,10 +3804,8 @@ static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
.show_options = rdtgroup_show_options,
};
-static int __init rdtgroup_setup_root(void)
+static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
{
- int ret;
-
rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
KERNFS_ROOT_CREATE_DEACTIVATED |
KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
@@ -3677,6 +3813,20 @@ static int __init rdtgroup_setup_root(void)
if (IS_ERR(rdt_root))
return PTR_ERR(rdt_root);
+ ctx->kfc.root = rdt_root;
+ rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
+
+ return 0;
+}
+
+static void rdtgroup_destroy_root(void)
+{
+ kernfs_destroy_root(rdt_root);
+ rdtgroup_default.kn = NULL;
+}
+
+static void __init rdtgroup_setup_default(void)
+{
mutex_lock(&rdtgroup_mutex);
rdtgroup_default.closid = 0;
@@ -3686,19 +3836,7 @@ static int __init rdtgroup_setup_root(void)
list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
- ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RF_CTRL_BASE);
- if (ret) {
- kernfs_destroy_root(rdt_root);
- goto out;
- }
-
- rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
- kernfs_activate(rdtgroup_default.kn);
-
-out:
mutex_unlock(&rdtgroup_mutex);
-
- return ret;
}
static void domain_destroy_mon_state(struct rdt_domain *d)
@@ -3820,13 +3958,11 @@ int __init rdtgroup_init(void)
seq_buf_init(&last_cmd_status, last_cmd_status_buf,
sizeof(last_cmd_status_buf));
- ret = rdtgroup_setup_root();
- if (ret)
- return ret;
+ rdtgroup_setup_default();
ret = sysfs_create_mount_point(fs_kobj, "resctrl");
if (ret)
- goto cleanup_root;
+ return ret;
ret = register_filesystem(&rdt_fs_type);
if (ret)
@@ -3859,8 +3995,6 @@ int __init rdtgroup_init(void)
cleanup_mountpoint:
sysfs_remove_mount_point(fs_kobj, "resctrl");
-cleanup_root:
- kernfs_destroy_root(rdt_root);
return ret;
}
@@ -3870,5 +4004,4 @@ void __exit rdtgroup_exit(void)
debugfs_remove_recursive(debugfs_resctrl);
unregister_filesystem(&rdt_fs_type);
sysfs_remove_mount_point(fs_kobj, "resctrl");
- kernfs_destroy_root(rdt_root);
}
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 91fa70e51004..279148e72459 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page,
return epc_page;
}
+/*
+ * Ensure the SECS page is not swapped out. Must be called with encl->lock
+ * to protect the enclave states including SECS and ensure the SECS page is
+ * not swapped out again while being used.
+ */
+static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl)
+{
+ struct sgx_epc_page *epc_page = encl->secs.epc_page;
+
+ if (!epc_page)
+ epc_page = sgx_encl_eldu(&encl->secs, NULL);
+
+ return epc_page;
+}
+
static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
struct sgx_encl_page *entry)
{
@@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
return entry;
}
- if (!(encl->secs.epc_page)) {
- epc_page = sgx_encl_eldu(&encl->secs, NULL);
- if (IS_ERR(epc_page))
- return ERR_CAST(epc_page);
- }
+ epc_page = sgx_encl_load_secs(encl);
+ if (IS_ERR(epc_page))
+ return ERR_CAST(epc_page);
epc_page = sgx_encl_eldu(entry, encl->secs.epc_page);
if (IS_ERR(epc_page))
@@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
mutex_lock(&encl->lock);
+ epc_page = sgx_encl_load_secs(encl);
+ if (IS_ERR(epc_page)) {
+ if (PTR_ERR(epc_page) == -EBUSY)
+ vmret = VM_FAULT_NOPAGE;
+ goto err_out_unlock;
+ }
+
epc_page = sgx_alloc_epc_page(encl_page, false);
if (IS_ERR(epc_page)) {
if (PTR_ERR(epc_page) == -EBUSY)
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 0270925fe013..dc136703566f 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -78,7 +78,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
/*
* initial apic id, which also represents 32-bit extended x2apic id.
*/
- c->initial_apicid = edx;
+ c->topo.initial_apicid = edx;
smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
#endif
return 0;
@@ -108,7 +108,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
* Populate HT related information from sub-leaf level 0.
*/
cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
- c->initial_apicid = edx;
+ c->topo.initial_apicid = edx;
core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx));
core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
@@ -146,20 +146,19 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
die_select_mask = (~(-1 << die_plus_mask_width)) >>
core_plus_mask_width;
- c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+ c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid,
ht_mask_width) & core_select_mask;
if (die_level_present) {
- c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+ c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid,
core_plus_mask_width) & die_select_mask;
}
- c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
- pkg_mask_width);
+ c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, pkg_mask_width);
/*
* Reinit the apicid, now that we have extended initial_apicid.
*/
- c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
+ c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0);
c->x86_max_cores = (core_level_siblings / smp_num_siblings);
__max_die_per_package = (die_level_siblings / core_level_siblings);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 05fa4ef63490..415564a6523b 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -65,20 +65,6 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
}
-
- if (c->cpuid_level >= 0x00000001) {
- u32 eax, ebx, ecx, edx;
-
- cpuid(0x00000001, &eax, &ebx, &ecx, &edx);
- /*
- * If HTT (EDX[28]) is set EBX[16:23] contain the number of
- * apicids which are reserved per package. Store the resulting
- * shift value for the package management code.
- */
- if (edx & (1U << 28))
- c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff);
- }
-
}
static void init_zhaoxin(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 87d38f17ff5c..afd09924094e 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -278,7 +278,7 @@ static void __init dtb_apic_setup(void)
}
#ifdef CONFIG_OF_EARLY_FLATTREE
-static void __init x86_flattree_get_config(void)
+void __init x86_flattree_get_config(void)
{
u32 size, map_len;
void *dt;
@@ -300,14 +300,10 @@ static void __init x86_flattree_get_config(void)
unflatten_and_copy_device_tree();
early_memunmap(dt, map_len);
}
-#else
-static inline void x86_flattree_get_config(void) { }
#endif
void __init x86_dtb_init(void)
{
- x86_flattree_get_config();
-
if (!of_have_populated_dt())
return;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index a86d37052a64..a21a4d0ecc34 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
- unsigned int size, u32 pkru)
+ unsigned int size, u64 xfeatures, u32 pkru)
{
struct fpstate *kstate = gfpu->fpstate;
union fpregs_state *ustate = buf;
struct membuf mb = { .p = buf, .left = size };
if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
- __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
+ __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru,
+ XSTATE_COPY_XSAVE);
} else {
memcpy(&ustate->fxsave, &kstate->regs.fxsave,
sizeof(ustate->fxsave));
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index cadf68737e6b..117e74c44e75 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
* __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
* @to: membuf descriptor
* @fpstate: The fpstate buffer from which to copy
+ * @xfeatures: The mask of xfeatures to save (XSAVE mode only)
* @pkru_val: The PKRU value to store in the PKRU component
* @copy_mode: The requested copy mode
*
@@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
* It supports partial copy but @to.pos always starts from zero.
*/
void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
- u32 pkru_val, enum xstate_copy_mode copy_mode)
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode)
{
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
struct xregs_state *xinit = &init_fpstate.regs.xsave;
@@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
break;
case XSTATE_COPY_XSAVE:
- header.xfeatures &= fpstate->user_xfeatures;
+ header.xfeatures &= fpstate->user_xfeatures & xfeatures;
break;
}
@@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode copy_mode)
{
__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+ tsk->thread.fpu.fpstate->user_xfeatures,
tsk->thread.pkru, copy_mode);
}
@@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
fpregs_restore_userregs();
newfps->xfeatures = curfps->xfeatures | xfeatures;
-
- if (!guest_fpu)
- newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
-
+ newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
newfps->xfd = curfps->xfd & ~xfeatures;
/* Do the final updates within the locked region */
@@ -1736,7 +1736,6 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm);
/**
* fpu_xstate_prctl - xstate permission operations
- * @tsk: Redundant pointer to current
* @option: A subfunction of arch_prctl()
* @arg2: option argument
* Return: 0 if successful; otherwise, an error code
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index a4ecb04d8d64..3518fb26d06b 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -43,7 +43,8 @@ enum xstate_copy_mode {
struct membuf;
extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
- u32 pkru_val, enum xstate_copy_mode copy_mode);
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode);
extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode mode);
extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 24c1175a47e2..58d9ed50fe61 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -3,10 +3,10 @@
* Copyright (C) 2017 Steven Rostedt, VMware Inc.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/page_types.h>
#include <asm/segment.h>
-#include <asm/export.h>
#include <asm/ftrace.h>
#include <asm/nospec-branch.h>
#include <asm/frame.h>
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 945cfa5f7239..214f30e9f0c0 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -3,12 +3,12 @@
* Copyright (C) 2014 Steven Rostedt, Red Hat Inc
*/
+#include <linux/export.h>
#include <linux/cfi_types.h>
#include <linux/linkage.h>
#include <asm/asm-offsets.h>
#include <asm/ptrace.h>
#include <asm/ftrace.h>
-#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
#include <asm/frame.h>
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 49f7629b17f7..05a110c97111 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -41,6 +41,7 @@
#include <asm/trapnr.h>
#include <asm/sev.h>
#include <asm/tdx.h>
+#include <asm/init.h>
/*
* Manage page tables very early on.
@@ -69,7 +70,7 @@ EXPORT_SYMBOL(vmemmap_base);
/*
* GDT used on the boot CPU before switching to virtual addresses.
*/
-static struct desc_struct startup_gdt[GDT_ENTRIES] = {
+static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = {
[GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff),
[GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff),
[GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff),
@@ -79,13 +80,11 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] = {
* Address needs to be set at runtime because it references the startup_gdt
* while the kernel still uses a direct mapping.
*/
-static struct desc_ptr startup_gdt_descr = {
- .size = sizeof(startup_gdt),
+static struct desc_ptr startup_gdt_descr __initdata = {
+ .size = sizeof(startup_gdt)-1,
.address = 0,
};
-#define __head __section(".head.text")
-
static void __head *fixup_pointer(void *ptr, unsigned long physaddr)
{
return ptr - (void *)_text + (void *)physaddr;
@@ -211,7 +210,7 @@ unsigned long __head __startup_64(unsigned long physaddr,
/* Fixup the physical addresses in the page table */
- pgd = fixup_pointer(&early_top_pgt, physaddr);
+ pgd = fixup_pointer(early_top_pgt, physaddr);
p = pgd + pgd_index(__START_KERNEL_map);
if (la57)
*p = (unsigned long)level4_kernel_pgt;
@@ -220,11 +219,11 @@ unsigned long __head __startup_64(unsigned long physaddr,
*p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta;
if (la57) {
- p4d = fixup_pointer(&level4_kernel_pgt, physaddr);
+ p4d = fixup_pointer(level4_kernel_pgt, physaddr);
p4d[511] += load_delta;
}
- pud = fixup_pointer(&level3_kernel_pgt, physaddr);
+ pud = fixup_pointer(level3_kernel_pgt, physaddr);
pud[510] += load_delta;
pud[511] += load_delta;
@@ -588,7 +587,7 @@ static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler)
}
/* This runs while still in the direct mapping */
-static void startup_64_load_idt(unsigned long physbase)
+static void __head startup_64_load_idt(unsigned long physbase)
{
struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase);
gate_desc *idt = fixup_pointer(bringup_idt_table, physbase);
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index c9318993f959..b6554212b7c7 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -8,6 +8,7 @@
*/
.text
+#include <linux/export.h>
#include <linux/threads.h>
#include <linux/init.h>
#include <linux/linkage.h>
@@ -25,7 +26,6 @@
#include <asm/nops.h>
#include <asm/nospec-branch.h>
#include <asm/bootparam.h>
-#include <asm/export.h>
#include <asm/pgtable_32.h>
/* Physical address */
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index ea6995920b7a..086a2c3aaaa0 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -9,7 +9,7 @@
* Copyright (C) 2005 Eric Biederman <ebiederm@xmission.com>
*/
-
+#include <linux/export.h>
#include <linux/linkage.h>
#include <linux/threads.h>
#include <linux/init.h>
@@ -22,7 +22,6 @@
#include <asm/percpu.h>
#include <asm/nops.h>
#include "../entry/calling.h"
-#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/apicdef.h>
#include <asm/fixmap.h>
@@ -180,8 +179,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
movl $0, %ecx
#endif
- /* Enable PAE mode, PGE and LA57 */
- orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
+ /* Enable PAE mode, PSE, PGE and LA57 */
+ orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
#ifdef CONFIG_X86_5LEVEL
testl $1, __pgtable_l5_enabled(%rip)
jz 1f
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 1648aa0204d9..41eecf180b7f 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -52,7 +52,7 @@ unsigned long hpet_address;
u8 hpet_blockid; /* OS timer block num */
bool hpet_msi_disable;
-#ifdef CONFIG_GENERIC_MSI_IRQ
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_GENERIC_MSI_IRQ)
static DEFINE_PER_CPU(struct hpet_channel *, cpu_hpet_channel);
static struct irq_domain *hpet_domain;
#endif
@@ -469,7 +469,7 @@ static void __init hpet_legacy_clockevent_register(struct hpet_channel *hc)
/*
* HPET MSI Support
*/
-#ifdef CONFIG_GENERIC_MSI_IRQ
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_GENERIC_MSI_IRQ)
static void hpet_msi_unmask(struct irq_data *data)
{
struct hpet_channel *hc = irq_data_get_irq_handler_data(data);
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 30a55207c000..c20d1832c481 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -32,6 +32,7 @@
*/
static void init_8259A(int auto_eoi);
+static bool pcat_compat __ro_after_init;
static int i8259A_auto_eoi;
DEFINE_RAW_SPINLOCK(i8259A_lock);
@@ -299,15 +300,32 @@ static void unmask_8259A(void)
static int probe_8259A(void)
{
+ unsigned char new_val, probe_val = ~(1 << PIC_CASCADE_IR);
unsigned long flags;
- unsigned char probe_val = ~(1 << PIC_CASCADE_IR);
- unsigned char new_val;
+
+ /*
+ * If MADT has the PCAT_COMPAT flag set, then do not bother probing
+ * for the PIC. Some BIOSes leave the PIC uninitialized and probing
+ * fails.
+ *
+ * Right now this causes problems as quite some code depends on
+ * nr_legacy_irqs() > 0 or has_legacy_pic() == true. This is silly
+ * when the system has an IO/APIC because then PIC is not required
+ * at all, except for really old machines where the timer interrupt
+ * must be routed through the PIC. So just pretend that the PIC is
+ * there and let legacy_pic->init() initialize it for nothing.
+ *
+ * Alternatively this could just try to initialize the PIC and
+ * repeat the probe, but for cases where there is no PIC that's
+ * just pointless.
+ */
+ if (pcat_compat)
+ return nr_legacy_irqs();
+
/*
- * Check to see if we have a PIC.
- * Mask all except the cascade and read
- * back the value we just wrote. If we don't
- * have a PIC, we will read 0xff as opposed to the
- * value we wrote.
+ * Check to see if we have a PIC. Mask all except the cascade and
+ * read back the value we just wrote. If we don't have a PIC, we
+ * will read 0xff as opposed to the value we wrote.
*/
raw_spin_lock_irqsave(&i8259A_lock, flags);
@@ -429,5 +447,9 @@ static int __init i8259A_init_ops(void)
return 0;
}
-
device_initcall(i8259A_init_ops);
+
+void __init legacy_pic_pcat_compat(void)
+{
+ pcat_compat = true;
+}
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index b786d48f5a0f..8857abc706e4 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -10,6 +10,7 @@
#include <asm/proto.h>
#include <asm/desc.h>
#include <asm/hw_irq.h>
+#include <asm/ia32.h>
#include <asm/idtentry.h>
#define DPL0 0x0
@@ -116,6 +117,9 @@ static const __initconst struct idt_data def_idts[] = {
#endif
SYSG(X86_TRAP_OF, asm_exc_overflow),
+};
+
+static const struct idt_data ia32_idt[] __initconst = {
#if defined(CONFIG_IA32_EMULATION)
SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat),
#elif defined(CONFIG_X86_32)
@@ -225,6 +229,9 @@ void __init idt_setup_early_traps(void)
void __init idt_setup_traps(void)
{
idt_setup_from_table(idt_table, def_idts, ARRAY_SIZE(def_idts), true);
+
+ if (ia32_enabled())
+ idt_setup_from_table(idt_table, ia32_idt, ARRAY_SIZE(ia32_idt), true);
}
#ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
index aaf9e776f323..7f542a7799cb 100644
--- a/arch/x86/kernel/irqflags.S
+++ b/arch/x86/kernel/irqflags.S
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <asm/asm.h>
-#include <asm/export.h>
+#include <linux/export.h>
#include <linux/linkage.h>
/*
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 3a43a2dee658..9c9faa1634fb 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -695,7 +695,6 @@ void kgdb_arch_exit(void)
}
/**
- *
* kgdb_skipexception - Bail out of KGDB when we've been triggered.
* @exception: Exception vector number
* @regs: Current &struct pt_regs.
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index b8ab9ee5896c..0ddb3bd0f1aa 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -500,13 +500,13 @@ static bool pv_sched_yield_supported(void)
static void __send_ipi_mask(const struct cpumask *mask, int vector)
{
unsigned long flags;
- int cpu, apic_id, icr;
- int min = 0, max = 0;
+ int cpu, min = 0, max = 0;
#ifdef CONFIG_X86_64
__uint128_t ipi_bitmap = 0;
#else
u64 ipi_bitmap = 0;
#endif
+ u32 apic_id, icr;
long ret;
if (cpumask_empty(mask))
@@ -1028,8 +1028,8 @@ arch_initcall(activate_jump_labels);
/* Kick a cpu by its apicid. Used to wake up a halted vcpu */
static void kvm_kick_cpu(int cpu)
{
- int apicid;
unsigned long flags = 0;
+ u32 apicid;
apicid = per_cpu(x86_cpu_to_apicid, cpu);
kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index a0c551846b35..4766b6bed443 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -507,12 +507,13 @@ DEFINE_IDTENTRY_RAW(exc_nmi)
}
this_cpu_write(nmi_state, NMI_EXECUTING);
this_cpu_write(nmi_cr2, read_cr2());
+
+nmi_restart:
if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) {
WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1);
WARN_ON_ONCE(!(nsp->idt_seq & 0x1));
WRITE_ONCE(nsp->recv_jiffies, jiffies);
}
-nmi_restart:
/*
* Needs to happen before DR7 is accessed, because the hypervisor can
@@ -548,16 +549,16 @@ nmi_restart:
if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
write_cr2(this_cpu_read(nmi_cr2));
- if (this_cpu_dec_return(nmi_state))
- goto nmi_restart;
-
- if (user_mode(regs))
- mds_user_clear_cpu_buffers();
if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) {
WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1);
WARN_ON_ONCE(nsp->idt_seq & 0x1);
WRITE_ONCE(nsp->recv_jiffies, jiffies);
}
+ if (this_cpu_dec_return(nmi_state))
+ goto nmi_restart;
+
+ if (user_mode(regs))
+ mds_user_clear_cpu_buffers();
}
#if IS_ENABLED(CONFIG_KVM_INTEL)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 975f98d5eee5..97f1436c1a20 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -143,66 +143,7 @@ int paravirt_disable_iospace(void)
return request_resource(&ioport_resource, &reserve_ioports);
}
-static DEFINE_PER_CPU(enum paravirt_lazy_mode, paravirt_lazy_mode) = PARAVIRT_LAZY_NONE;
-
-static inline void enter_lazy(enum paravirt_lazy_mode mode)
-{
- BUG_ON(this_cpu_read(paravirt_lazy_mode) != PARAVIRT_LAZY_NONE);
-
- this_cpu_write(paravirt_lazy_mode, mode);
-}
-
-static void leave_lazy(enum paravirt_lazy_mode mode)
-{
- BUG_ON(this_cpu_read(paravirt_lazy_mode) != mode);
-
- this_cpu_write(paravirt_lazy_mode, PARAVIRT_LAZY_NONE);
-}
-
-void paravirt_enter_lazy_mmu(void)
-{
- enter_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_leave_lazy_mmu(void)
-{
- leave_lazy(PARAVIRT_LAZY_MMU);
-}
-
-void paravirt_flush_lazy_mmu(void)
-{
- preempt_disable();
-
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
- arch_leave_lazy_mmu_mode();
- arch_enter_lazy_mmu_mode();
- }
-
- preempt_enable();
-}
-
#ifdef CONFIG_PARAVIRT_XXL
-void paravirt_start_context_switch(struct task_struct *prev)
-{
- BUG_ON(preemptible());
-
- if (this_cpu_read(paravirt_lazy_mode) == PARAVIRT_LAZY_MMU) {
- arch_leave_lazy_mmu_mode();
- set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
- }
- enter_lazy(PARAVIRT_LAZY_CPU);
-}
-
-void paravirt_end_context_switch(struct task_struct *next)
-{
- BUG_ON(preemptible());
-
- leave_lazy(PARAVIRT_LAZY_CPU);
-
- if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
- arch_enter_lazy_mmu_mode();
-}
-
static noinstr void pv_native_write_cr2(unsigned long val)
{
native_write_cr2(val);
@@ -229,14 +170,6 @@ static noinstr void pv_native_safe_halt(void)
}
#endif
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
-{
- if (in_interrupt())
- return PARAVIRT_LAZY_NONE;
-
- return this_cpu_read(paravirt_lazy_mode);
-}
-
struct pv_info pv_info = {
.name = "bare hardware",
#ifdef CONFIG_PARAVIRT_XXL
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9f0909142a0a..b6f4e8399fca 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -257,13 +257,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
if (!ret && unlikely(test_tsk_thread_flag(current, TIF_IO_BITMAP)))
io_bitmap_share(p);
- /*
- * If copy_thread() if failing, don't leak the shadow stack possibly
- * allocated in shstk_alloc_thread_stack() above.
- */
- if (ret)
- shstk_free(p);
-
return ret;
}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b9145a63da77..ccd3ad29a1dc 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -358,15 +358,11 @@ static void __init add_early_ima_buffer(u64 phys_addr)
#if defined(CONFIG_HAVE_IMA_KEXEC) && !defined(CONFIG_OF_FLATTREE)
int __init ima_free_kexec_buffer(void)
{
- int rc;
-
if (!ima_kexec_buffer_size)
return -ENOENT;
- rc = memblock_phys_free(ima_kexec_buffer_phys,
- ima_kexec_buffer_size);
- if (rc)
- return rc;
+ memblock_free_late(ima_kexec_buffer_phys,
+ ima_kexec_buffer_size);
ima_kexec_buffer_phys = 0;
ima_kexec_buffer_size = 0;
@@ -1124,7 +1120,7 @@ void __init setup_arch(char **cmdline_p)
* Needs to run after memblock setup because it needs the physical
* memory size.
*/
- sev_setup_arch();
+ mem_encrypt_setup_arch();
efi_fake_memmap();
efi_find_mirror();
@@ -1221,6 +1217,8 @@ void __init setup_arch(char **cmdline_p)
early_acpi_boot_init();
+ x86_flattree_get_config();
+
initmem_init();
dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT);
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index 2eabccde94fb..ccb0915e84e1 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -256,7 +256,7 @@ static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg)
return 0;
}
-static int sev_cpuid_hv(struct cpuid_leaf *leaf)
+static int __sev_cpuid_hv_msr(struct cpuid_leaf *leaf)
{
int ret;
@@ -279,6 +279,45 @@ static int sev_cpuid_hv(struct cpuid_leaf *leaf)
return ret;
}
+static int __sev_cpuid_hv_ghcb(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+{
+ u32 cr4 = native_read_cr4();
+ int ret;
+
+ ghcb_set_rax(ghcb, leaf->fn);
+ ghcb_set_rcx(ghcb, leaf->subfn);
+
+ if (cr4 & X86_CR4_OSXSAVE)
+ /* Safe to read xcr0 */
+ ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
+ else
+ /* xgetbv will cause #UD - use reset value for xcr0 */
+ ghcb_set_xcr0(ghcb, 1);
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (!(ghcb_rax_is_valid(ghcb) &&
+ ghcb_rbx_is_valid(ghcb) &&
+ ghcb_rcx_is_valid(ghcb) &&
+ ghcb_rdx_is_valid(ghcb)))
+ return ES_VMM_ERROR;
+
+ leaf->eax = ghcb->save.rax;
+ leaf->ebx = ghcb->save.rbx;
+ leaf->ecx = ghcb->save.rcx;
+ leaf->edx = ghcb->save.rdx;
+
+ return ES_OK;
+}
+
+static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
+{
+ return ghcb ? __sev_cpuid_hv_ghcb(ghcb, ctxt, leaf)
+ : __sev_cpuid_hv_msr(leaf);
+}
+
/*
* This may be called early while still running on the initial identity
* mapping. Use RIP-relative addressing to obtain the correct address
@@ -388,19 +427,20 @@ snp_cpuid_get_validated_func(struct cpuid_leaf *leaf)
return false;
}
-static void snp_cpuid_hv(struct cpuid_leaf *leaf)
+static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
{
- if (sev_cpuid_hv(leaf))
+ if (sev_cpuid_hv(ghcb, ctxt, leaf))
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV);
}
-static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
+static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ struct cpuid_leaf *leaf)
{
struct cpuid_leaf leaf_hv = *leaf;
switch (leaf->fn) {
case 0x1:
- snp_cpuid_hv(&leaf_hv);
+ snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
/* initial APIC ID */
leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0));
@@ -419,7 +459,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
break;
case 0xB:
leaf_hv.subfn = 0;
- snp_cpuid_hv(&leaf_hv);
+ snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
/* extended APIC ID */
leaf->edx = leaf_hv.edx;
@@ -467,7 +507,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
}
break;
case 0x8000001E:
- snp_cpuid_hv(&leaf_hv);
+ snp_cpuid_hv(ghcb, ctxt, &leaf_hv);
/* extended APIC ID */
leaf->eax = leaf_hv.eax;
@@ -488,7 +528,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf)
* Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
* should be treated as fatal by caller.
*/
-static int snp_cpuid(struct cpuid_leaf *leaf)
+static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -522,7 +562,7 @@ static int snp_cpuid(struct cpuid_leaf *leaf)
return 0;
}
- return snp_cpuid_postprocess(leaf);
+ return snp_cpuid_postprocess(ghcb, ctxt, leaf);
}
/*
@@ -544,14 +584,14 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code)
leaf.fn = fn;
leaf.subfn = subfn;
- ret = snp_cpuid(&leaf);
+ ret = snp_cpuid(NULL, NULL, &leaf);
if (!ret)
goto cpuid_done;
if (ret != -EOPNOTSUPP)
goto fail;
- if (sev_cpuid_hv(&leaf))
+ if (__sev_cpuid_hv_msr(&leaf))
goto fail;
cpuid_done:
@@ -592,6 +632,23 @@ fail:
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+ unsigned long address,
+ bool write)
+{
+ if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_USER;
+ ctxt->fi.cr2 = address;
+ if (write)
+ ctxt->fi.error_code |= X86_PF_WRITE;
+
+ return ES_EXCEPTION;
+ }
+
+ return ES_OK;
+}
+
static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
void *src, char *buf,
unsigned int data_size,
@@ -599,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
bool backwards)
{
int i, b = backwards ? -1 : 1;
- enum es_result ret = ES_OK;
+ unsigned long address = (unsigned long)src;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, false);
+ if (ret != ES_OK)
+ return ret;
for (i = 0; i < count; i++) {
void *s = src + (i * data_size * b);
@@ -620,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
bool backwards)
{
int i, s = backwards ? -1 : 1;
- enum es_result ret = ES_OK;
+ unsigned long address = (unsigned long)dst;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, true);
+ if (ret != ES_OK)
+ return ret;
for (i = 0; i < count; i++) {
void *d = dst + (i * data_size * s);
@@ -656,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
{
struct insn *insn = &ctxt->insn;
+ size_t size;
+ u64 port;
+
*exitinfo = 0;
switch (insn->opcode.bytes[0]) {
@@ -664,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0x6d:
*exitinfo |= IOIO_TYPE_INS;
*exitinfo |= IOIO_SEG_ES;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* OUTS opcodes */
@@ -672,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0x6f:
*exitinfo |= IOIO_TYPE_OUTS;
*exitinfo |= IOIO_SEG_DS;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* IN immediate opcodes */
case 0xe4:
case 0xe5:
*exitinfo |= IOIO_TYPE_IN;
- *exitinfo |= (u8)insn->immediate.value << 16;
+ port = (u8)insn->immediate.value & 0xffff;
break;
/* OUT immediate opcodes */
case 0xe6:
case 0xe7:
*exitinfo |= IOIO_TYPE_OUT;
- *exitinfo |= (u8)insn->immediate.value << 16;
+ port = (u8)insn->immediate.value & 0xffff;
break;
/* IN register opcodes */
case 0xec:
case 0xed:
*exitinfo |= IOIO_TYPE_IN;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* OUT register opcodes */
case 0xee:
case 0xef:
*exitinfo |= IOIO_TYPE_OUT;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
default:
return ES_DECODE_FAILED;
}
+ *exitinfo |= port << 16;
+
switch (insn->opcode.bytes[0]) {
case 0x6c:
case 0x6e:
@@ -716,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0xee:
/* Single byte opcodes */
*exitinfo |= IOIO_DATA_8;
+ size = 1;
break;
default:
/* Length determined by instruction parsing */
*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
: IOIO_DATA_32;
+ size = (insn->opnd_bytes == 2) ? 2 : 4;
}
+
switch (insn->addr_bytes) {
case 2:
*exitinfo |= IOIO_ADDR_16;
@@ -737,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
if (insn_has_rep_prefix(insn))
*exitinfo |= IOIO_REP;
- return ES_OK;
+ return vc_ioio_check(ctxt, (u16)port, size);
}
static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
@@ -848,14 +923,15 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
return ret;
}
-static int vc_handle_cpuid_snp(struct pt_regs *regs)
+static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
+ struct pt_regs *regs = ctxt->regs;
struct cpuid_leaf leaf;
int ret;
leaf.fn = regs->ax;
leaf.subfn = regs->cx;
- ret = snp_cpuid(&leaf);
+ ret = snp_cpuid(ghcb, ctxt, &leaf);
if (!ret) {
regs->ax = leaf.eax;
regs->bx = leaf.ebx;
@@ -874,7 +950,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
enum es_result ret;
int snp_cpuid_ret;
- snp_cpuid_ret = vc_handle_cpuid_snp(regs);
+ snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
if (!snp_cpuid_ret)
return ES_OK;
if (snp_cpuid_ret != -EOPNOTSUPP)
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index 2787826d9f60..70472eebe719 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
return ES_OK;
}
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ BUG_ON(size > 4);
+
+ if (user_mode(ctxt->regs)) {
+ struct thread_struct *t = &current->thread;
+ struct io_bitmap *iobm = t->io_bitmap;
+ size_t idx;
+
+ if (!iobm)
+ goto fault;
+
+ for (idx = port; idx < port + size; ++idx) {
+ if (test_bit(idx, iobm->bitmap))
+ goto fault;
+ }
+ }
+
+ return ES_OK;
+
+fault:
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+
+ return ES_EXCEPTION;
+}
+
/* Include code shared with pre-decompression boot stage */
#include "sev-shared.c"
@@ -868,8 +895,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned long npages)
void snp_accept_memory(phys_addr_t start, phys_addr_t end)
{
- unsigned long vaddr;
- unsigned int npages;
+ unsigned long vaddr, npages;
if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
return;
@@ -940,7 +966,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
free_page((unsigned long)vmsa);
}
-static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip)
+static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
{
struct sev_es_save_area *cur_vmsa, *vmsa;
struct ghcb_state state;
@@ -1509,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
return ES_DECODE_FAILED;
}
+ if (user_mode(ctxt->regs))
+ return ES_UNSUPPORTED;
+
switch (mmio) {
case INSN_MMIO_WRITE:
memcpy(ghcb->shared_buffer, reg_data, bytes);
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index fd689921a1db..59e15dd8d0f8 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -205,10 +205,21 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, unsigned long cl
return 0;
/*
- * For CLONE_VM, except vfork, the child needs a separate shadow
+ * For CLONE_VFORK the child will share the parents shadow stack.
+ * Make sure to clear the internal tracking of the thread shadow
+ * stack so the freeing logic run for child knows to leave it alone.
+ */
+ if (clone_flags & CLONE_VFORK) {
+ shstk->base = 0;
+ shstk->size = 0;
+ return 0;
+ }
+
+ /*
+ * For !CLONE_VM the child will use a copy of the parents shadow
* stack.
*/
- if ((clone_flags & (CLONE_VFORK | CLONE_VM)) != CLONE_VM)
+ if (!(clone_flags & CLONE_VM))
return 0;
size = adjust_shstk_size(stack_size);
@@ -408,7 +419,25 @@ void shstk_free(struct task_struct *tsk)
if (!tsk->mm || tsk->mm != current->mm)
return;
+ /*
+ * If shstk->base is NULL, then this task is not managing its
+ * own shadow stack (CLONE_VFORK). So skip freeing it.
+ */
+ if (!shstk->base)
+ return;
+
+ /*
+ * shstk->base is NULL for CLONE_VFORK child tasks, and so is
+ * normal. But size = 0 on a shstk->base is not normal and
+ * indicated an attempt to free the thread shadow stack twice.
+ * Warn about it.
+ */
+ if (WARN_ON(!shstk->size))
+ return;
+
unmap_shadow_stack(shstk->base, shstk->size);
+
+ shstk->size = 0;
}
static int wrss_control(bool enable)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 6eb06d001bcc..96a771f9f930 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -131,7 +131,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs)
}
/*
- * Disable virtualization, APIC etc. and park the CPU in a HLT loop
+ * this function calls the 'stop' function on all other CPUs in the system.
*/
DEFINE_IDTENTRY_SYSVEC(sysvec_reboot)
{
@@ -172,17 +172,13 @@ static void native_stop_other_cpus(int wait)
* 2) Wait for all other CPUs to report that they reached the
* HLT loop in stop_this_cpu()
*
- * 3) If the system uses INIT/STARTUP for CPU bringup, then
- * send all present CPUs an INIT vector, which brings them
- * completely out of the way.
+ * 3) If #2 timed out send an NMI to the CPUs which did not
+ * yet report
*
- * 4) If #3 is not possible and #2 timed out send an NMI to the
- * CPUs which did not yet report
- *
- * 5) Wait for all other CPUs to report that they reached the
+ * 4) Wait for all other CPUs to report that they reached the
* HLT loop in stop_this_cpu()
*
- * #4 can obviously race against a CPU reaching the HLT loop late.
+ * #3 can obviously race against a CPU reaching the HLT loop late.
* That CPU will have reported already and the "have all CPUs
* reached HLT" condition will be true despite the fact that the
* other CPU is still handling the NMI. Again, there is no
@@ -198,7 +194,7 @@ static void native_stop_other_cpus(int wait)
/*
* Don't wait longer than a second for IPI completion. The
* wait request is not checked here because that would
- * prevent an NMI/INIT shutdown in case that not all
+ * prevent an NMI shutdown attempt in case that not all
* CPUs reach shutdown state.
*/
timeout = USEC_PER_SEC;
@@ -206,27 +202,7 @@ static void native_stop_other_cpus(int wait)
udelay(1);
}
- /*
- * Park all other CPUs in INIT including "offline" CPUs, if
- * possible. That's a safe place where they can't resume execution
- * of HLT and then execute the HLT loop from overwritten text or
- * page tables.
- *
- * The only downside is a broadcast MCE, but up to the point where
- * the kexec() kernel brought all APs online again an MCE will just
- * make HLT resume and handle the MCE. The machine crashes and burns
- * due to overwritten text, page tables and data. So there is a
- * choice between fire and frying pan. The result is pretty much
- * the same. Chose frying pan until x86 provides a sane mechanism
- * to park a CPU.
- */
- if (smp_park_other_cpus_in_init())
- goto done;
-
- /*
- * If park with INIT was not possible and the REBOOT_VECTOR didn't
- * take all secondary CPUs offline, try with the NMI.
- */
+ /* if the REBOOT_VECTOR didn't work, try with the NMI */
if (!cpumask_empty(&cpus_stop_mask)) {
/*
* If NMI IPI is enabled, try to register the stop handler
@@ -249,7 +225,6 @@ static void native_stop_other_cpus(int wait)
udelay(1);
}
-done:
local_irq_save(flags);
disable_local_APIC();
mcheck_cpu_clear(this_cpu_ptr(&cpu_info));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4e45ff44aa07..c4aca66f0902 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -87,6 +87,7 @@
#include <asm/hw_irq.h>
#include <asm/stackprotector.h>
#include <asm/sev.h>
+#include <asm/spec-ctrl.h>
/* representing HT siblings of each logical CPU */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
@@ -124,7 +125,20 @@ struct mwait_cpu_dead {
*/
static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead);
-/* Logical package management. We might want to allocate that dynamically */
+/* Logical package management. */
+struct logical_maps {
+ u32 phys_pkg_id;
+ u32 phys_die_id;
+ u32 logical_pkg_id;
+ u32 logical_die_id;
+};
+
+/* Temporary workaround until the full topology mechanics is in place */
+static DEFINE_PER_CPU_READ_MOSTLY(struct logical_maps, logical_maps) = {
+ .phys_pkg_id = U32_MAX,
+ .phys_die_id = U32_MAX,
+};
+
unsigned int __max_logical_packages __read_mostly;
EXPORT_SYMBOL(__max_logical_packages);
static unsigned int logical_packages __read_mostly;
@@ -288,7 +302,7 @@ static void notrace start_secondary(void *unused)
cpu_init();
fpu__init_cpu();
- rcu_cpu_starting(raw_smp_processor_id());
+ rcutree_report_cpu_starting(raw_smp_processor_id());
x86_cpuinit.early_percpu_clock_init();
ap_starting();
@@ -337,10 +351,8 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg)
int cpu;
for_each_possible_cpu(cpu) {
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- if (c->initialized && c->phys_proc_id == phys_pkg)
- return c->logical_proc_id;
+ if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg)
+ return per_cpu(logical_maps.logical_pkg_id, cpu);
}
return -1;
}
@@ -355,14 +367,12 @@ EXPORT_SYMBOL(topology_phys_to_logical_pkg);
*/
static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu)
{
- int cpu, proc_id = cpu_data(cur_cpu).phys_proc_id;
+ int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id;
for_each_possible_cpu(cpu) {
- struct cpuinfo_x86 *c = &cpu_data(cpu);
-
- if (c->initialized && c->cpu_die_id == die_id &&
- c->phys_proc_id == proc_id)
- return c->logical_die_id;
+ if (per_cpu(logical_maps.phys_pkg_id, cpu) == proc_id &&
+ per_cpu(logical_maps.phys_die_id, cpu) == die_id)
+ return per_cpu(logical_maps.logical_die_id, cpu);
}
return -1;
}
@@ -387,7 +397,9 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
cpu, pkg, new);
}
found:
- cpu_data(cpu).logical_proc_id = new;
+ per_cpu(logical_maps.phys_pkg_id, cpu) = pkg;
+ per_cpu(logical_maps.logical_pkg_id, cpu) = new;
+ cpu_data(cpu).topo.logical_pkg_id = new;
return 0;
}
/**
@@ -410,7 +422,9 @@ int topology_update_die_map(unsigned int die, unsigned int cpu)
cpu, die, new);
}
found:
- cpu_data(cpu).logical_die_id = new;
+ per_cpu(logical_maps.phys_die_id, cpu) = die;
+ per_cpu(logical_maps.logical_die_id, cpu) = new;
+ cpu_data(cpu).topo.logical_die_id = new;
return 0;
}
@@ -421,8 +435,8 @@ static void __init smp_store_boot_cpu_info(void)
*c = boot_cpu_data;
c->cpu_index = id;
- topology_update_package_map(c->phys_proc_id, id);
- topology_update_die_map(c->cpu_die_id, id);
+ topology_update_package_map(c->topo.pkg_id, id);
+ topology_update_die_map(c->topo.die_id, id);
c->initialized = true;
}
@@ -476,21 +490,21 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
- if (c->phys_proc_id == o->phys_proc_id &&
- c->cpu_die_id == o->cpu_die_id &&
- per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
- if (c->cpu_core_id == o->cpu_core_id)
+ if (c->topo.pkg_id == o->topo.pkg_id &&
+ c->topo.die_id == o->topo.die_id &&
+ per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) {
+ if (c->topo.core_id == o->topo.core_id)
return topology_sane(c, o, "smt");
- if ((c->cu_id != 0xff) &&
- (o->cu_id != 0xff) &&
- (c->cu_id == o->cu_id))
+ if ((c->topo.cu_id != 0xff) &&
+ (o->topo.cu_id != 0xff) &&
+ (c->topo.cu_id == o->topo.cu_id))
return topology_sane(c, o, "smt");
}
- } else if (c->phys_proc_id == o->phys_proc_id &&
- c->cpu_die_id == o->cpu_die_id &&
- c->cpu_core_id == o->cpu_core_id) {
+ } else if (c->topo.pkg_id == o->topo.pkg_id &&
+ c->topo.die_id == o->topo.die_id &&
+ c->topo.core_id == o->topo.core_id) {
return topology_sane(c, o, "smt");
}
@@ -499,8 +513,8 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (c->phys_proc_id == o->phys_proc_id &&
- c->cpu_die_id == o->cpu_die_id)
+ if (c->topo.pkg_id == o->topo.pkg_id &&
+ c->topo.die_id == o->topo.die_id)
return true;
return false;
}
@@ -510,11 +524,11 @@ static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
/* If the arch didn't set up l2c_id, fall back to SMT */
- if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID)
+ if (per_cpu_l2c_id(cpu1) == BAD_APICID)
return match_smt(c, o);
/* Do not match if L2 cache id does not match: */
- if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2))
+ if (per_cpu_l2c_id(cpu1) != per_cpu_l2c_id(cpu2))
return false;
return topology_sane(c, o, "l2c");
@@ -527,7 +541,7 @@ static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
*/
static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
{
- if (c->phys_proc_id == o->phys_proc_id)
+ if (c->topo.pkg_id == o->topo.pkg_id)
return true;
return false;
}
@@ -560,11 +574,11 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
bool intel_snc = id && id->driver_data;
/* Do not match if we do not have a valid APICID for cpu: */
- if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID)
+ if (per_cpu_llc_id(cpu1) == BAD_APICID)
return false;
/* Do not match if LLC id does not match: */
- if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2))
+ if (per_cpu_llc_id(cpu1) != per_cpu_llc_id(cpu2))
return false;
/*
@@ -579,7 +593,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
}
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
static inline int x86_sched_itmt_flags(void)
{
return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -603,7 +616,14 @@ static int x86_cluster_flags(void)
return cpu_cluster_flags() | x86_sched_itmt_flags();
}
#endif
-#endif
+
+static int x86_die_flags(void)
+{
+ if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+ return x86_sched_itmt_flags();
+
+ return 0;
+}
/*
* Set if a package/die has multiple NUMA nodes inside.
@@ -634,13 +654,13 @@ static void __init build_sched_topology(void)
};
#endif
/*
- * When there is NUMA topology inside the package skip the DIE domain
+ * When there is NUMA topology inside the package skip the PKG domain
* since the NUMA domains will auto-magically create the right spanning
* domains based on the SLIT.
*/
if (!x86_has_numa_in_package) {
x86_topology[i++] = (struct sched_domain_topology_level){
- cpu_cpu_mask, SD_INIT_NAME(DIE)
+ cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG)
};
}
@@ -803,7 +823,7 @@ static void __init smp_quirk_init_udelay(void)
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
-static void send_init_sequence(int phys_apicid)
+static void send_init_sequence(u32 phys_apicid)
{
int maxlvt = lapic_get_maxlvt();
@@ -829,7 +849,7 @@ static void send_init_sequence(int phys_apicid)
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
-static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip)
{
unsigned long send_status = 0, accept_status = 0;
int num_starts, j, maxlvt;
@@ -976,7 +996,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
* Returns zero if startup was successfully sent, else error code from
* ->wakeup_secondary_cpu.
*/
-static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
{
unsigned long start_ip = real_mode_header->trampoline_start;
int ret;
@@ -1044,7 +1064,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
int native_kick_ap(unsigned int cpu, struct task_struct *tidle)
{
- int apicid = apic->cpu_present_to_apicid(cpu);
+ u32 apicid = apic->cpu_present_to_apicid(cpu);
int err;
lockdep_assert_irqs_enabled();
@@ -1234,33 +1254,6 @@ void arch_thaw_secondary_cpus_end(void)
cache_aps_init();
}
-bool smp_park_other_cpus_in_init(void)
-{
- unsigned int cpu, this_cpu = smp_processor_id();
- unsigned int apicid;
-
- if (apic->wakeup_secondary_cpu_64 || apic->wakeup_secondary_cpu)
- return false;
-
- /*
- * If this is a crash stop which does not execute on the boot CPU,
- * then this cannot use the INIT mechanism because INIT to the boot
- * CPU will reset the machine.
- */
- if (this_cpu)
- return false;
-
- for_each_cpu_and(cpu, &cpus_booted_once_mask, cpu_present_mask) {
- if (cpu == this_cpu)
- continue;
- apicid = apic->cpu_present_to_apicid(cpu);
- if (apicid == BAD_APICID)
- continue;
- send_init_sequence(apicid);
- }
- return true;
-}
-
/*
* Early setup to make printk work.
*/
@@ -1426,7 +1419,7 @@ static void remove_siblinginfo(int cpu)
cpumask_clear(topology_sibling_cpumask(cpu));
cpumask_clear(topology_core_cpumask(cpu));
cpumask_clear(topology_die_cpumask(cpu));
- c->cpu_core_id = 0;
+ c->topo.core_id = 0;
c->booted_cores = 0;
cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
recompute_smt_state();
@@ -1617,8 +1610,15 @@ void __noreturn hlt_play_dead(void)
native_halt();
}
+/*
+ * native_play_dead() is essentially a __noreturn function, but it can't
+ * be marked as such as the compiler may complain about it.
+ */
void native_play_dead(void)
{
+ if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
+ __update_spec_ctrl(0);
+
play_dead_common();
tboot_shutdown(TB_SHUTDOWN_WFS);
diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c
index ca004e2e4469..0bab03130033 100644
--- a/arch/x86/kernel/topology.c
+++ b/arch/x86/kernel/topology.c
@@ -54,7 +54,7 @@ void arch_unregister_cpu(int num)
EXPORT_SYMBOL(arch_unregister_cpu);
#else /* CONFIG_HOTPLUG_CPU */
-static int __init arch_register_cpu(int num)
+int __init arch_register_cpu(int num)
{
return register_cpu(&per_cpu(cpu_devices, num).cpu, num);
}
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index bbc440c93e08..1123ef3ccf90 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -15,6 +15,7 @@
* ( The serial nature of the boot logic and the CPU hotplug lock
* protects against more than 2 CPUs entering this code. )
*/
+#include <linux/workqueue.h>
#include <linux/topology.h>
#include <linux/spinlock.h>
#include <linux/kernel.h>
@@ -342,6 +343,13 @@ static inline unsigned int loop_timeout(int cpu)
return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20;
}
+static void tsc_sync_mark_tsc_unstable(struct work_struct *work)
+{
+ mark_tsc_unstable("check_tsc_sync_source failed");
+}
+
+static DECLARE_WORK(tsc_sync_work, tsc_sync_mark_tsc_unstable);
+
/*
* The freshly booted CPU initiates this via an async SMP function call.
*/
@@ -395,7 +403,7 @@ retry:
"turning off TSC clock.\n", max_warp);
if (random_warps)
pr_warn("TSC warped randomly between CPUs\n");
- mark_tsc_unstable("check_tsc_sync_source failed");
+ schedule_work(&tsc_sync_work);
}
/*
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7e574cf3bf8a..d00c28aaa5be 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -85,7 +85,7 @@ static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
{
int *first = ip_table;
int *last = ip_table + num_entries - 1;
- int *mid = first, *found = first;
+ int *mid, *found = first;
if (!num_entries)
return NULL;
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index f15fb71f280e..54a5596adaa6 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -139,10 +139,7 @@ SECTIONS
STATIC_CALL_TEXT
ALIGN_ENTRY_TEXT_BEGIN
-#ifdef CONFIG_CPU_SRSO
*(.text..__x86.rethunk_untrain)
-#endif
-
ENTRY_TEXT
#ifdef CONFIG_CPU_SRSO
@@ -520,12 +517,12 @@ INIT_PER_CPU(irq_stack_backing_store);
"fixed_percpu_data is not at start of per-cpu area");
#endif
-#ifdef CONFIG_RETHUNK
+#ifdef CONFIG_CPU_UNRET_ENTRY
. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
-. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
#endif
#ifdef CONFIG_CPU_SRSO
+. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
/*
* GNU ld cannot do XOR until 2.41.
* https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index 65e96b76c423..d3fc01770558 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -127,7 +127,7 @@ static void __init vsmp_cap_cpus(void)
#endif
}
-static int apicid_phys_pkg_id(int initial_apic_id, int index_msb)
+static u32 apicid_phys_pkg_id(u32 initial_apic_id, int index_msb)
{
return read_apic_id() >> index_msb;
}
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0544e30b4946..773132c3bf5a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vcpu->arch.guest_supported_xcr0 =
cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
- /*
- * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
- * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
- * supported by the host.
- */
- vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
- XFEATURE_MASK_FPSSE;
-
kvm_update_pv_runtime(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dcd60b39e794..3e977dbbf993 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
{
u32 reg = kvm_lapic_get_reg(apic, lvt_type);
int vector, mode, trig_mode;
+ int r;
if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
vector = reg & APIC_VECTOR_MASK;
mode = reg & APIC_MODE_MASK;
trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
- return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
- NULL);
+
+ r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
+ if (r && lvt_type == APIC_LVTPC)
+ kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
+ return r;
}
return 0;
}
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e1d011c67cc6..f7901cb4d2fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
}
-int kvm_mmu_init_vm(struct kvm *kvm)
+void kvm_mmu_init_vm(struct kvm *kvm)
{
- int r;
-
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
- if (tdp_mmu_enabled) {
- r = kvm_mmu_init_tdp_mmu(kvm);
- if (r < 0)
- return r;
- }
+ if (tdp_mmu_enabled)
+ kvm_mmu_init_tdp_mmu(kvm);
kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
-
- return 0;
}
static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
{
bool flush;
- int i;
if (WARN_ON_ONCE(gfn_end <= gfn_start))
return;
@@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
- if (tdp_mmu_enabled) {
- for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
- flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
- gfn_end, true, flush);
- }
+ if (tdp_mmu_enabled)
+ flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush);
if (flush)
kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b102014e2c60..decc1f153669 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -58,7 +58,12 @@ struct kvm_mmu_page {
bool tdp_mmu_page;
bool unsync;
- u8 mmu_valid_gen;
+ union {
+ u8 mmu_valid_gen;
+
+ /* Only accessed under slots_lock. */
+ bool tdp_mmu_scheduled_root_to_zap;
+ };
/*
* The shadow page can't be replaced by an equivalent huge page
@@ -100,13 +105,7 @@ struct kvm_mmu_page {
struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
tdp_ptep_t ptep;
};
- union {
- DECLARE_BITMAP(unsync_child_bitmap, 512);
- struct {
- struct work_struct tdp_mmu_async_work;
- void *tdp_mmu_async_data;
- };
- };
+ DECLARE_BITMAP(unsync_child_bitmap, 512);
/*
* Tracks shadow pages that, if zapped, would allow KVM to create an NX
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6c63f2d1675f..6cd4dd631a2f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -12,18 +12,10 @@
#include <trace/events/kvm.h>
/* Initializes the TDP MMU for the VM, if enabled. */
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
{
- struct workqueue_struct *wq;
-
- wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
- if (!wq)
- return -ENOMEM;
-
INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
- kvm->arch.tdp_mmu_zap_wq = wq;
- return 1;
}
/* Arbitrarily returns true so that this may be used in if statements. */
@@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
* ultimately frees all roots.
*/
kvm_tdp_mmu_invalidate_all_roots(kvm);
-
- /*
- * Destroying a workqueue also first flushes the workqueue, i.e. no
- * need to invoke kvm_tdp_mmu_zap_invalidated_roots().
- */
- destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
+ kvm_tdp_mmu_zap_invalidated_roots(kvm);
WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
/*
* Ensure that all the outstanding RCU callbacks to free shadow pages
- * can run before the VM is torn down. Work items on tdp_mmu_zap_wq
- * can call kvm_tdp_mmu_put_root and create new callbacks.
+ * can run before the VM is torn down. Putting the last reference to
+ * zapped roots will create new callbacks.
*/
rcu_barrier();
}
@@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
tdp_mmu_free_sp(sp);
}
-static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
- bool shared);
-
-static void tdp_mmu_zap_root_work(struct work_struct *work)
-{
- struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page,
- tdp_mmu_async_work);
- struct kvm *kvm = root->tdp_mmu_async_data;
-
- read_lock(&kvm->mmu_lock);
-
- /*
- * A TLB flush is not necessary as KVM performs a local TLB flush when
- * allocating a new root (see kvm_mmu_load()), and when migrating vCPU
- * to a different pCPU. Note, the local TLB flush on reuse also
- * invalidates any paging-structure-cache entries, i.e. TLB entries for
- * intermediate paging structures, that may be zapped, as such entries
- * are associated with the ASID on both VMX and SVM.
- */
- tdp_mmu_zap_root(kvm, root, true);
-
- /*
- * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for
- * avoiding an infinite loop. By design, the root is reachable while
- * it's being asynchronously zapped, thus a different task can put its
- * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an
- * asynchronously zapped root is unavoidable.
- */
- kvm_tdp_mmu_put_root(kvm, root, true);
-
- read_unlock(&kvm->mmu_lock);
-}
-
-static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root)
-{
- root->tdp_mmu_async_data = kvm;
- INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work);
- queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work);
-}
-
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared)
{
@@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \
__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \
- __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false)
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \
+ for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \
+ _root; \
+ _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \
+ if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \
+ } else
/*
* Iterate over all TDP MMU roots. Requires that mmu_lock be held for write,
@@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
* by a memslot update or by the destruction of the VM. Initialize the
* refcount to two; one reference for the vCPU, and one reference for
* the TDP MMU itself, which is held until the root is invalidated and
- * is ultimately put by tdp_mmu_zap_root_work().
+ * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots().
*/
refcount_set(&root->tdp_mmu_root_count, 2);
@@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
* true if a TLB flush is needed before releasing the MMU lock, i.e. if one or
* more SPTEs were zapped since the MMU lock was last acquired.
*/
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
- bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
{
struct kvm_mmu_page *root;
- for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
- flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
+ for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+ flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
return flush;
}
@@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
void kvm_tdp_mmu_zap_all(struct kvm *kvm)
{
struct kvm_mmu_page *root;
- int i;
/*
* Zap all roots, including invalid roots, as all SPTEs must be dropped
@@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
* is being destroyed or the userspace VMM has exited. In both cases,
* KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
*/
- for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
- for_each_tdp_mmu_root_yield_safe(kvm, root, i)
- tdp_mmu_zap_root(kvm, root, false);
- }
+ for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+ tdp_mmu_zap_root(kvm, root, false);
}
/*
@@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
*/
void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
{
- flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
+ struct kvm_mmu_page *root;
+
+ read_lock(&kvm->mmu_lock);
+
+ for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+ if (!root->tdp_mmu_scheduled_root_to_zap)
+ continue;
+
+ root->tdp_mmu_scheduled_root_to_zap = false;
+ KVM_BUG_ON(!root->role.invalid, kvm);
+
+ /*
+ * A TLB flush is not necessary as KVM performs a local TLB
+ * flush when allocating a new root (see kvm_mmu_load()), and
+ * when migrating a vCPU to a different pCPU. Note, the local
+ * TLB flush on reuse also invalidates paging-structure-cache
+ * entries, i.e. TLB entries for intermediate paging structures,
+ * that may be zapped, as such entries are associated with the
+ * ASID on both VMX and SVM.
+ */
+ tdp_mmu_zap_root(kvm, root, true);
+
+ /*
+ * The referenced needs to be put *after* zapping the root, as
+ * the root must be reachable by mmu_notifiers while it's being
+ * zapped
+ */
+ kvm_tdp_mmu_put_root(kvm, root, true);
+ }
+
+ read_unlock(&kvm->mmu_lock);
}
/*
* Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
* is about to be zapped, e.g. in response to a memslots update. The actual
- * zapping is performed asynchronously. Using a separate workqueue makes it
- * easy to ensure that the destruction is performed before the "fast zap"
- * completes, without keeping a separate list of invalidated roots; the list is
- * effectively the list of work items in the workqueue.
+ * zapping is done separately so that it happens with mmu_lock with read,
+ * whereas invalidating roots must be done with mmu_lock held for write (unless
+ * the VM is being destroyed).
*
- * Note, the asynchronous worker is gifted the TDP MMU's reference.
+ * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
* See kvm_tdp_mmu_get_vcpu_root_hpa().
*/
void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
@@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
/*
* As above, mmu_lock isn't held when destroying the VM! There can't
* be other references to @kvm, i.e. nothing else can invalidate roots
- * or be consuming roots, but walking the list of roots does need to be
- * guarded against roots being deleted by the asynchronous zap worker.
+ * or get/put references to roots.
*/
- rcu_read_lock();
-
- list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) {
+ list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+ /*
+ * Note, invalid roots can outlive a memslot update! Invalid
+ * roots must be *zapped* before the memslot update completes,
+ * but a different task can acquire a reference and keep the
+ * root alive after its been zapped.
+ */
if (!root->role.invalid) {
+ root->tdp_mmu_scheduled_root_to_zap = true;
root->role.invalid = true;
- tdp_mmu_schedule_zap_root(kvm, root);
}
}
-
- rcu_read_unlock();
}
/*
@@ -1146,8 +1123,13 @@ retry:
bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
bool flush)
{
- return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
- range->end, range->may_block, flush);
+ struct kvm_mmu_page *root;
+
+ __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+ flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
+ range->may_block, flush);
+
+ return flush;
}
typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 0a63b1afabd3..733a3aef3a96 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -7,7 +7,7 @@
#include "spte.h"
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
@@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
bool shared);
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
- gfn_t end, bool can_yield, bool flush);
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
void kvm_tdp_mmu_zap_all(struct kvm *kvm);
void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index edb89b51b383..9ae07db6f0f6 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops)
#undef __KVM_X86_PMU_OP
}
-static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
-{
- struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
- struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
- kvm_pmu_deliver_pmi(vcpu);
-}
-
static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
}
- if (!pmc->intr || skip_pmi)
- return;
-
- /*
- * Inject PMI. If vcpu was in a guest mode during NMI PMI
- * can be ejected on a guest mode re-entry. Otherwise we can't
- * be sure that vcpu wasn't executing hlt instruction at the
- * time of vmexit and is not going to re-enter guest mode until
- * woken up. So we should wake it, but this is impossible from
- * NMI context. Do it from irq work instead.
- */
- if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu))
- irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
- else
+ if (pmc->intr && !skip_pmi)
kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
}
@@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
void kvm_pmu_reset(struct kvm_vcpu *vcpu)
{
- struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
- irq_work_sync(&pmu->irq_work);
static_call(kvm_x86_pmu_reset)(vcpu);
}
@@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
memset(pmu, 0, sizeof(*pmu));
static_call(kvm_x86_pmu_init)(vcpu);
- init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
pmu->event_count = 0;
pmu->need_cleanup = false;
kvm_pmu_refresh(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7d9ba301c090..1d64113de488 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
return counter & pmc_bitmask(pmc);
}
+static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+ pmc->counter += val - pmc_read_counter(pmc);
+ pmc->counter &= pmc_bitmask(pmc);
+}
+
static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
{
if (pmc->perf_event) {
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 2092db892d7d..4b74ea91f4e6 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
WARN_ONCE(1, "Invalid backing page\n");
break;
+ case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR:
+ /* Invalid IPI with vector < 16 */
+ break;
default:
- pr_err("Unknown IPI interception\n");
+ vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n");
}
return 1;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index dd496c9e5f91..3fea8c47679e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
nested_svm_uninit_mmu_context(vcpu);
vmcb_mark_all_dirty(svm->vmcb);
+
+ if (kvm_apicv_activated(vcpu->kvm))
+ kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
}
kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index cef5a3d0abd0..373ff6a6687b 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* MSR_PERFCTRn */
pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
if (pmc) {
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
return 0;
}
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b9a0a939d59f..4900c078045a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
count, in);
}
+static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+
+ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+ bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+ guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+ set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
+ }
+}
+
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+ struct kvm_vcpu *vcpu = &svm->vcpu;
+ struct kvm_cpuid_entry2 *best;
+
+ /* For sev guests, the memory encryption bit is not reserved in CR3. */
+ best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
+ if (best)
+ vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
+
+ if (sev_es_guest(svm->vcpu.kvm))
+ sev_es_vcpu_after_set_cpuid(svm);
+}
+
static void sev_es_init_vmcb(struct vcpu_svm *svm)
{
struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
- if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) &&
- (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) ||
- guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) {
- set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1);
- if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP))
- svm_clr_intercept(svm, INTERCEPT_RDTSCP);
- }
}
void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f283eb47f6ac..ded1d80d72cb 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -531,8 +531,6 @@ static bool __kvm_is_svm_supported(void)
int cpu = smp_processor_id();
struct cpuinfo_x86 *c = &cpu_data(cpu);
- u64 vm_cr;
-
if (c->x86_vendor != X86_VENDOR_AMD &&
c->x86_vendor != X86_VENDOR_HYGON) {
pr_err("CPU %d isn't AMD or Hygon\n", cpu);
@@ -549,12 +547,6 @@ static bool __kvm_is_svm_supported(void)
return false;
}
- rdmsrl(MSR_VM_CR, vm_cr);
- if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) {
- pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu);
- return false;
- }
-
return true;
}
@@ -683,6 +675,21 @@ static int svm_hardware_enable(void)
amd_pmu_enable_virt();
+ /*
+ * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
+ * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
+ * Since Linux does not change the value of TSC_AUX once set, prime the
+ * TSC_AUX field now to avoid a RDMSR on every vCPU run.
+ */
+ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+ struct sev_es_save_area *hostsa;
+ u32 __maybe_unused msr_hi;
+
+ hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
+
+ rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi);
+ }
+
return 0;
}
@@ -898,8 +905,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
if (intercept == svm->x2avic_msrs_intercepted)
return;
- if (!x2avic_enabled ||
- !apic_x2apic_mode(svm->vcpu.arch.apic))
+ if (!x2avic_enabled)
return;
for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) {
@@ -1532,7 +1538,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
if (tsc_scaling)
__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
- if (likely(tsc_aux_uret_slot >= 0))
+ /*
+ * TSC_AUX is always virtualized for SEV-ES guests when the feature is
+ * available. The user return MSR support is not required in this case
+ * because TSC_AUX is restored on #VMEXIT from the host save area
+ * (which has been initialized in svm_hardware_enable()).
+ */
+ if (likely(tsc_aux_uret_slot >= 0) &&
+ (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
svm->guest_state_loaded = true;
@@ -3087,6 +3100,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
case MSR_TSC_AUX:
/*
+ * TSC_AUX is always virtualized for SEV-ES guests when the
+ * feature is available. The user return MSR support is not
+ * required in this case because TSC_AUX is restored on #VMEXIT
+ * from the host save area (which has been initialized in
+ * svm_hardware_enable()).
+ */
+ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
+ break;
+
+ /*
* TSC_AUX is usually changed only during boot and never read
* directly. Intercept TSC_AUX instead of exposing it to the
* guest via direct_access_msrs, and switch it via user return.
@@ -4284,7 +4307,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct kvm_cpuid_entry2 *best;
/*
* SVM doesn't provide a way to disable just XSAVES in the guest, KVM
@@ -4328,12 +4350,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
!!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
- /* For sev guests, the memory encryption bit is not reserved in CR3. */
- if (sev_guest(vcpu->kvm)) {
- best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
- if (best)
- vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
- }
+ if (sev_guest(vcpu->kvm))
+ sev_vcpu_after_set_cpuid(svm);
init_vmcb_after_set_cpuid(vcpu);
}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f41253958357..be67ab7fdd10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -684,6 +684,7 @@ void __init sev_hardware_setup(void);
void sev_hardware_unsetup(void);
int sev_cpu_init(struct svm_cpu_data *sd);
void sev_init_vmcb(struct vcpu_svm *svm);
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
void sev_free_vcpu(struct kvm_vcpu *vcpu);
int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f2efa0bf7ae8..820d3e1f6b4f 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!msr_info->host_initiated &&
!(msr & MSR_PMC_FULL_WIDTH_BIT))
data = (s64)(s32)data;
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
break;
} else if ((pmc = get_fixed_pmc(pmu, msr))) {
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
break;
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c9c81e82e65..41cce5031126 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5382,26 +5382,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
return 0;
}
-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
- struct kvm_xsave *guest_xsave)
-{
- if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return;
-
- fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
- guest_xsave->region,
- sizeof(guest_xsave->region),
- vcpu->arch.pkru);
-}
static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
u8 *state, unsigned int size)
{
+ /*
+ * Only copy state for features that are enabled for the guest. The
+ * state itself isn't problematic, but setting bits in the header for
+ * features that are supported in *this* host but not exposed to the
+ * guest can result in KVM_SET_XSAVE failing when live migrating to a
+ * compatible host without the features that are NOT exposed to the
+ * guest.
+ *
+ * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+ * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+ * supported by the host.
+ */
+ u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 |
+ XFEATURE_MASK_FPSSE;
+
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return;
- fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
- state, size, vcpu->arch.pkru);
+ fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
+ supported_xcr0, vcpu->arch.pkru);
+}
+
+static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *guest_xsave)
+{
+ return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+ sizeof(guest_xsave->region));
}
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -12308,9 +12319,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (ret)
goto out;
- ret = kvm_mmu_init_vm(kvm);
- if (ret)
- goto out_page_track;
+ kvm_mmu_init_vm(kvm);
ret = static_call(kvm_x86_vm_init)(kvm);
if (ret)
@@ -12355,7 +12364,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
out_uninit_mmu:
kvm_mmu_uninit_vm(kvm);
-out_page_track:
kvm_page_track_cleanup(kvm);
out:
return ret;
@@ -12846,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return true;
#endif
+ if (kvm_test_request(KVM_REQ_PMI, vcpu))
+ return true;
+
if (kvm_arch_interrupt_allowed(vcpu) &&
(kvm_cpu_has_interrupt(vcpu) ||
kvm_guest_apic_has_interrupt(vcpu)))
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 23318c338db0..68f7fa3e1322 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -21,10 +21,10 @@
* converted to pure assembler
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/errno.h>
#include <asm/asm.h>
-#include <asm/export.h>
#include <asm/nospec-branch.h>
/*
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index f74a3e704a1c..2760a15fbc00 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/asm.h>
-#include <asm/export.h>
/*
* Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 49805257b125..873e4ef23e49 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/export.h>
#include <linux/linkage.h>
-#include <asm/export.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
index 80efd45a7761..6e8b7e600def 100644
--- a/arch/x86/lib/copy_mc.c
+++ b/arch/x86/lib/copy_mc.c
@@ -70,23 +70,23 @@ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigne
}
EXPORT_SYMBOL_GPL(copy_mc_to_kernel);
-unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len)
+unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len)
{
unsigned long ret;
if (copy_mc_fragile_enabled) {
__uaccess_begin();
- ret = copy_mc_fragile(dst, src, len);
+ ret = copy_mc_fragile((__force void *)dst, src, len);
__uaccess_end();
return ret;
}
if (static_cpu_has(X86_FEATURE_ERMS)) {
__uaccess_begin();
- ret = copy_mc_enhanced_fast_string(dst, src, len);
+ ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len);
__uaccess_end();
return ret;
}
- return copy_user_generic(dst, src, len);
+ return copy_user_generic((__force void *)dst, src, len);
}
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 30ea644bf446..d6ae793d08fa 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,10 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
-#include <asm/export.h>
/*
* Some CPUs run faster using the string copy instructions (sane microcode).
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 0a81aafed7f8..fc9fb5d06174 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -6,11 +6,11 @@
* Functions to copy from and to user space.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <asm/asm.h>
-#include <asm/export.h>
/*
* rep_movs_alternative - memory copy with exception handling.
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 5c5f38d32672..2918e36eece2 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -3,9 +3,9 @@
* Copyright 2023 Linus Torvalds <torvalds@linux-foundation.org>
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/asm.h>
-#include <asm/export.h>
/*
* copy_user_nocache - Uncached memory copy with exception handling
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 145f9a0bde29..f4df4d241526 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -14,8 +14,6 @@
* @src: source address (user space)
* @dst: destination address
* @len: number of bytes to be copied.
- * @isum: initial sum that is added into the result (32bit unfolded)
- * @errp: set to -EFAULT for an bad source address.
*
* Returns an 32bit unfolded checksum of the buffer.
* src and dst are best aligned to 64bits.
@@ -38,8 +36,6 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len)
* @src: source address
* @dst: destination address (user space)
* @len: number of bytes to be copied.
- * @isum: initial sum that is added into the result (32bit unfolded)
- * @errp: set to -EFAULT for an bad destination address.
*
* Returns an 32bit unfolded checksum of the buffer.
* src and dst are best aligned to 64bits.
@@ -62,7 +58,6 @@ csum_and_copy_to_user(const void *src, void __user *dst, int len)
* @src: source address
* @dst: destination address
* @len: number of bytes to be copied.
- * @sum: initial sum that is added into the result (32bit unfolded)
*
* Returns an 32bit unfolded checksum of the buffer.
*/
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 9c63713477bb..20ef350a60fb 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,6 +26,7 @@
* as they get called from within inline assembly.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/page_types.h>
#include <asm/errno.h>
@@ -33,7 +34,6 @@
#include <asm/thread_info.h>
#include <asm/asm.h>
#include <asm/smap.h>
-#include <asm/export.h>
#define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 12c16c6aa44a..774bdf3e6f0a 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
#include <linux/linkage.h>
-#include <asm/export.h>
#include <asm/asm.h>
@@ -36,8 +36,12 @@ SYM_FUNC_START(__sw_hweight32)
SYM_FUNC_END(__sw_hweight32)
EXPORT_SYMBOL(__sw_hweight32)
-SYM_FUNC_START(__sw_hweight64)
+/*
+ * No 32-bit variant, because it's implemented as an inline wrapper
+ * on top of __arch_hweight32():
+ */
#ifdef CONFIG_X86_64
+SYM_FUNC_START(__sw_hweight64)
pushq %rdi
pushq %rdx
@@ -66,18 +70,6 @@ SYM_FUNC_START(__sw_hweight64)
popq %rdx
popq %rdi
RET
-#else /* CONFIG_X86_32 */
- /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
- pushl %ecx
-
- call __sw_hweight32
- movl %eax, %ecx # stash away result
- movl %edx, %eax # second part of input
- call __sw_hweight32
- addl %ecx, %eax # result
-
- popl %ecx
- RET
-#endif
SYM_FUNC_END(__sw_hweight64)
EXPORT_SYMBOL(__sw_hweight64)
+#endif
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 8f95fb267caa..0ae2e1712e2e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -1,12 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright 2002 Andi Kleen */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <linux/cfi_types.h>
#include <asm/errno.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
-#include <asm/export.h>
.section .noinstr.text, "ax"
@@ -40,7 +40,7 @@ SYM_TYPED_FUNC_START(__memcpy)
SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
EXPORT_SYMBOL(memcpy)
SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S
index 0588b2c0fc95..35010ba3dd6f 100644
--- a/arch/x86/lib/memmove_32.S
+++ b/arch/x86/lib/memmove_32.S
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
#include <linux/linkage.h>
-#include <asm/export.h>
SYM_FUNC_START(memmove)
/*
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0559b206fb11..1b60ae81ecd8 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,10 +6,10 @@
* This assembly file is re-written from memmove_64.c file.
* - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
-#include <asm/export.h>
#undef memmove
@@ -212,5 +212,5 @@ SYM_FUNC_START(__memmove)
SYM_FUNC_END(__memmove)
EXPORT_SYMBOL(__memmove)
-SYM_FUNC_ALIAS(memmove, __memmove)
+SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove)
EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 7c59a704c458..0199d56cb479 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,10 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0 */
/* Copyright 2002 Andi Kleen, SuSE Labs */
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
-#include <asm/export.h>
.section .noinstr.text, "ax"
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
SYM_FUNC_END(__memset)
EXPORT_SYMBOL(__memset)
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
EXPORT_SYMBOL(memset)
SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 1451e0c4ae22..2877f5934177 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,13 +11,12 @@
* return an error value in addition to the "real"
* return value.
*/
+#include <linux/export.h>
#include <linux/linkage.h>
#include <asm/thread_info.h>
#include <asm/errno.h>
#include <asm/asm.h>
#include <asm/smap.h>
-#include <asm/export.h>
-
/*
* __put_user_X
@@ -56,7 +55,6 @@ SYM_FUNC_END(__put_user_1)
EXPORT_SYMBOL(__put_user_1)
SYM_FUNC_START(__put_user_nocheck_1)
- ENDBR
ASM_STAC
2: movb %al,(%_ASM_CX)
xor %ecx,%ecx
@@ -76,7 +74,6 @@ SYM_FUNC_END(__put_user_2)
EXPORT_SYMBOL(__put_user_2)
SYM_FUNC_START(__put_user_nocheck_2)
- ENDBR
ASM_STAC
4: movw %ax,(%_ASM_CX)
xor %ecx,%ecx
@@ -96,7 +93,6 @@ SYM_FUNC_END(__put_user_4)
EXPORT_SYMBOL(__put_user_4)
SYM_FUNC_START(__put_user_nocheck_4)
- ENDBR
ASM_STAC
6: movl %eax,(%_ASM_CX)
xor %ecx,%ecx
@@ -119,7 +115,6 @@ SYM_FUNC_END(__put_user_8)
EXPORT_SYMBOL(__put_user_8)
SYM_FUNC_START(__put_user_nocheck_8)
- ENDBR
ASM_STAC
9: mov %_ASM_AX,(%_ASM_CX)
#ifdef CONFIG_X86_32
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index cd86aeb5fdd3..7b2589877d06 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -1,12 +1,12 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
#include <linux/stringify.h>
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#include <asm/cpufeatures.h>
#include <asm/alternative.h>
#include <asm/asm-offsets.h>
-#include <asm/export.h>
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
#include <asm/percpu.h>
@@ -126,11 +126,19 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
#include <asm/GEN-for-each-reg.h>
#undef GEN
#endif
+
+#ifdef CONFIG_RETHUNK
+
/*
- * This function name is magical and is used by -mfunction-return=thunk-extern
- * for the compiler to generate JMPs to it.
+ * Be careful here: that label cannot really be removed because in
+ * some configurations and toolchains, the JMP __x86_return_thunk the
+ * compiler issues is either a short one or the compiler doesn't use
+ * relocations for same-section JMPs and that breaks the returns
+ * detection logic in apply_returns() and in objtool.
*/
-#ifdef CONFIG_RETHUNK
+ .section .text..__x86.return_thunk
+
+#ifdef CONFIG_CPU_SRSO
/*
* srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
@@ -147,29 +155,18 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
*
* As a result, srso_alias_safe_ret() becomes a safe return.
*/
-#ifdef CONFIG_CPU_SRSO
- .section .text..__x86.rethunk_untrain
-
-SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ .pushsection .text..__x86.rethunk_untrain
+SYM_CODE_START_NOALIGN(srso_alias_untrain_ret)
UNWIND_HINT_FUNC
ANNOTATE_NOENDBR
ASM_NOP2
lfence
jmp srso_alias_return_thunk
SYM_FUNC_END(srso_alias_untrain_ret)
-__EXPORT_THUNK(srso_alias_untrain_ret)
-
- .section .text..__x86.rethunk_safe
-#else
-/* dummy definition for alternatives */
-SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
- ANNOTATE_UNRET_SAFE
- ret
- int3
-SYM_FUNC_END(srso_alias_untrain_ret)
-#endif
+ .popsection
-SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ .pushsection .text..__x86.rethunk_safe
+SYM_CODE_START_NOALIGN(srso_alias_safe_ret)
lea 8(%_ASM_SP), %_ASM_SP
UNWIND_HINT_FUNC
ANNOTATE_UNRET_SAFE
@@ -177,14 +174,63 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
int3
SYM_FUNC_END(srso_alias_safe_ret)
- .section .text..__x86.return_thunk
-
-SYM_CODE_START(srso_alias_return_thunk)
+SYM_CODE_START_NOALIGN(srso_alias_return_thunk)
UNWIND_HINT_FUNC
ANNOTATE_NOENDBR
call srso_alias_safe_ret
ud2
SYM_CODE_END(srso_alias_return_thunk)
+ .popsection
+
+/*
+ * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
+ * above. On kernel entry, srso_untrain_ret() is executed which is a
+ *
+ * movabs $0xccccc30824648d48,%rax
+ *
+ * and when the return thunk executes the inner label srso_safe_ret()
+ * later, it is a stack manipulation and a RET which is mispredicted and
+ * thus a "safe" one to use.
+ */
+ .align 64
+ .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
+SYM_CODE_START_LOCAL_NOALIGN(srso_untrain_ret)
+ ANNOTATE_NOENDBR
+ .byte 0x48, 0xb8
+
+/*
+ * This forces the function return instruction to speculate into a trap
+ * (UD2 in srso_return_thunk() below). This RET will then mispredict
+ * and execution will continue at the return site read from the top of
+ * the stack.
+ */
+SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
+ lea 8(%_ASM_SP), %_ASM_SP
+ ret
+ int3
+ int3
+ /* end of movabs */
+ lfence
+ call srso_safe_ret
+ ud2
+SYM_CODE_END(srso_safe_ret)
+SYM_FUNC_END(srso_untrain_ret)
+
+SYM_CODE_START(srso_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ call srso_safe_ret
+ ud2
+SYM_CODE_END(srso_return_thunk)
+
+#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
+#else /* !CONFIG_CPU_SRSO */
+#define JMP_SRSO_UNTRAIN_RET "ud2"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_SRSO */
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
/*
* Some generic notes on the untraining sequences:
@@ -216,7 +262,7 @@ SYM_CODE_END(srso_alias_return_thunk)
*/
.align 64
.skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc
-SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+SYM_CODE_START_LOCAL_NOALIGN(retbleed_untrain_ret)
ANNOTATE_NOENDBR
/*
* As executed from retbleed_untrain_ret, this is:
@@ -264,72 +310,27 @@ SYM_CODE_END(retbleed_return_thunk)
jmp retbleed_return_thunk
int3
SYM_FUNC_END(retbleed_untrain_ret)
-__EXPORT_THUNK(retbleed_untrain_ret)
-/*
- * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
- * above. On kernel entry, srso_untrain_ret() is executed which is a
- *
- * movabs $0xccccc30824648d48,%rax
- *
- * and when the return thunk executes the inner label srso_safe_ret()
- * later, it is a stack manipulation and a RET which is mispredicted and
- * thus a "safe" one to use.
- */
- .align 64
- .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
-SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
- ANNOTATE_NOENDBR
- .byte 0x48, 0xb8
+#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret"
+#else /* !CONFIG_CPU_UNRET_ENTRY */
+#define JMP_RETBLEED_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_UNRET_ENTRY */
-/*
- * This forces the function return instruction to speculate into a trap
- * (UD2 in srso_return_thunk() below). This RET will then mispredict
- * and execution will continue at the return site read from the top of
- * the stack.
- */
-SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
- lea 8(%_ASM_SP), %_ASM_SP
- ret
- int3
- int3
- /* end of movabs */
- lfence
- call srso_safe_ret
- ud2
-SYM_CODE_END(srso_safe_ret)
-SYM_FUNC_END(srso_untrain_ret)
-__EXPORT_THUNK(srso_untrain_ret)
-
-SYM_CODE_START(srso_return_thunk)
- UNWIND_HINT_FUNC
- ANNOTATE_NOENDBR
- call srso_safe_ret
- ud2
-SYM_CODE_END(srso_return_thunk)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
SYM_FUNC_START(entry_untrain_ret)
- ALTERNATIVE_2 "jmp retbleed_untrain_ret", \
- "jmp srso_untrain_ret", X86_FEATURE_SRSO, \
- "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
+ ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \
+ JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \
+ JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
SYM_FUNC_END(entry_untrain_ret)
__EXPORT_THUNK(entry_untrain_ret)
-SYM_CODE_START(__x86_return_thunk)
- UNWIND_HINT_FUNC
- ANNOTATE_NOENDBR
- ANNOTATE_UNRET_SAFE
- ret
- int3
-SYM_CODE_END(__x86_return_thunk)
-EXPORT_SYMBOL(__x86_return_thunk)
-
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
#ifdef CONFIG_CALL_DEPTH_TRACKING
.align 64
-SYM_FUNC_START(__x86_return_skl)
+SYM_FUNC_START(call_depth_return_thunk)
ANNOTATE_NOENDBR
/*
* Keep the hotpath in a 16byte I-fetch for the non-debug
@@ -356,6 +357,33 @@ SYM_FUNC_START(__x86_return_skl)
ANNOTATE_UNRET_SAFE
ret
int3
-SYM_FUNC_END(__x86_return_skl)
+SYM_FUNC_END(call_depth_return_thunk)
#endif /* CONFIG_CALL_DEPTH_TRACKING */
+
+/*
+ * This function name is magical and is used by -mfunction-return=thunk-extern
+ * for the compiler to generate JMPs to it.
+ *
+ * This code is only used during kernel boot or module init. All
+ * 'JMP __x86_return_thunk' sites are changed to something else by
+ * apply_returns().
+ *
+ * This should be converted eventually to call a warning function which
+ * should scream loudly when the default return thunk is called after
+ * alternatives have been applied.
+ *
+ * That warning function cannot BUG() because the bug splat cannot be
+ * displayed in all possible configurations, leading to users not really
+ * knowing why the machine froze.
+ */
+SYM_CODE_START(__x86_return_thunk)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_CODE_END(__x86_return_thunk)
+EXPORT_SYMBOL(__x86_return_thunk)
+
+#endif /* CONFIG_RETHUNK */
diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c
index 5a53c2cc169c..6993f026adec 100644
--- a/arch/x86/mm/maccess.c
+++ b/arch/x86/mm/maccess.c
@@ -9,12 +9,21 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
unsigned long vaddr = (unsigned long)unsafe_src;
/*
- * Range covering the highest possible canonical userspace address
- * as well as non-canonical address range. For the canonical range
- * we also need to include the userspace guard page.
+ * Do not allow userspace addresses. This disallows
+ * normal userspace and the userspace guard page:
*/
- return vaddr >= TASK_SIZE_MAX + PAGE_SIZE &&
- __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
+ if (vaddr < TASK_SIZE_MAX + PAGE_SIZE)
+ return false;
+
+ /*
+ * Allow everything during early boot before 'x86_virt_bits'
+ * is initialized. Needed for instruction decoding in early
+ * exception handlers.
+ */
+ if (!boot_cpu_data.x86_virt_bits)
+ return true;
+
+ return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits);
}
#else
bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index 9f27e14e185f..c290c55b632b 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -12,6 +12,7 @@
#include <linux/swiotlb.h>
#include <linux/cc_platform.h>
#include <linux/mem_encrypt.h>
+#include <linux/virtio_anchor.h>
/* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
bool force_dma_unencrypted(struct device *dev)
@@ -86,3 +87,36 @@ void __init mem_encrypt_init(void)
print_mem_encrypt_feature_info();
}
+
+void __init mem_encrypt_setup_arch(void)
+{
+ phys_addr_t total_mem = memblock_phys_mem_size();
+ unsigned long size;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+ return;
+
+ /*
+ * For SEV and TDX, all DMA has to occur via shared/unencrypted pages.
+ * Kernel uses SWIOTLB to make this happen without changing device
+ * drivers. However, depending on the workload being run, the
+ * default 64MB of SWIOTLB may not be enough and SWIOTLB may
+ * run out of buffers for DMA, resulting in I/O errors and/or
+ * performance degradation especially with high I/O workloads.
+ *
+ * Adjust the default size of SWIOTLB using a percentage of guest
+ * memory for SWIOTLB buffers. Also, as the SWIOTLB bounce buffer
+ * memory is allocated from low memory, ensure that the adjusted size
+ * is within the limits of low available memory.
+ *
+ * The percentage of guest memory used here for SWIOTLB buffers
+ * is more of an approximation of the static adjustment which
+ * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
+ */
+ size = total_mem * 6 / 100;
+ size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
+ swiotlb_adjust_size(size);
+
+ /* Set restricted memory access for virtio. */
+ virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
+}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 6faea41e99b6..a68f2dda0948 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -19,8 +19,6 @@
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/dma-mapping.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_anchor.h>
#include <linux/cc_platform.h>
#include <asm/tlbflush.h>
@@ -215,40 +213,6 @@ void __init sme_map_bootdata(char *real_mode_data)
__sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true);
}
-void __init sev_setup_arch(void)
-{
- phys_addr_t total_mem = memblock_phys_mem_size();
- unsigned long size;
-
- if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
- return;
-
- /*
- * For SEV, all DMA has to occur via shared/unencrypted pages.
- * SEV uses SWIOTLB to make this happen without changing device
- * drivers. However, depending on the workload being run, the
- * default 64MB of SWIOTLB may not be enough and SWIOTLB may
- * run out of buffers for DMA, resulting in I/O errors and/or
- * performance degradation especially with high I/O workloads.
- *
- * Adjust the default size of SWIOTLB for SEV guests using
- * a percentage of guest memory for SWIOTLB buffers.
- * Also, as the SWIOTLB bounce buffer memory is allocated
- * from low memory, ensure that the adjusted size is within
- * the limits of low available memory.
- *
- * The percentage of guest memory used here for SWIOTLB buffers
- * is more of an approximation of the static adjustment which
- * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6%
- */
- size = total_mem * 6 / 100;
- size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G);
- swiotlb_adjust_size(size);
-
- /* Set restricted memory access for virtio. */
- virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc);
-}
-
static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot)
{
unsigned long pfn = 0;
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 2aadb2019b4f..b29ceb19e46e 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -3,6 +3,7 @@
#include <linux/acpi.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/of.h>
#include <linux/string.h>
#include <linux/init.h>
#include <linux/memblock.h>
@@ -11,6 +12,7 @@
#include <linux/nodemask.h>
#include <linux/sched.h>
#include <linux/topology.h>
+#include <linux/sort.h>
#include <asm/e820/api.h>
#include <asm/proto.h>
@@ -56,7 +58,7 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = {
int numa_cpu_node(int cpu)
{
- int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+ u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
if (apicid != BAD_APICID)
return __apicid_to_node[apicid];
@@ -601,13 +603,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
if (start >= end)
continue;
- /*
- * Don't confuse VM with a node that doesn't have the
- * minimum amount of memory:
- */
- if (end && (end - start) < NODE_MIN_SIZE)
- continue;
-
alloc_node_data(nid);
}
@@ -733,6 +728,8 @@ void __init x86_numa_init(void)
if (!numa_init(amd_numa_init))
return;
#endif
+ if (acpi_disabled && !numa_init(of_numa_init))
+ return;
}
numa_init(dummy_numa_init);
@@ -786,7 +783,7 @@ void __init init_gi_nodes(void)
void __init init_cpu_to_node(void)
{
int cpu;
- u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
+ u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid);
BUG_ON(cpu_to_apicid == NULL);
@@ -961,4 +958,83 @@ int memory_add_physaddr_to_nid(u64 start)
return nid;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
+
+static int __init cmp_memblk(const void *a, const void *b)
+{
+ const struct numa_memblk *ma = *(const struct numa_memblk **)a;
+ const struct numa_memblk *mb = *(const struct numa_memblk **)b;
+
+ return ma->start - mb->start;
+}
+
+static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata;
+
+/**
+ * numa_fill_memblks - Fill gaps in numa_meminfo memblks
+ * @start: address to begin fill
+ * @end: address to end fill
+ *
+ * Find and extend numa_meminfo memblks to cover the @start-@end
+ * physical address range, such that the first memblk includes
+ * @start, the last memblk includes @end, and any gaps in between
+ * are filled.
+ *
+ * RETURNS:
+ * 0 : Success
+ * NUMA_NO_MEMBLK : No memblk exists in @start-@end range
+ */
+
+int __init numa_fill_memblks(u64 start, u64 end)
+{
+ struct numa_memblk **blk = &numa_memblk_list[0];
+ struct numa_meminfo *mi = &numa_meminfo;
+ int count = 0;
+ u64 prev_end;
+
+ /*
+ * Create a list of pointers to numa_meminfo memblks that
+ * overlap start, end. Exclude (start == bi->end) since
+ * end addresses in both a CFMWS range and a memblk range
+ * are exclusive.
+ *
+ * This list of pointers is used to make in-place changes
+ * that fill out the numa_meminfo memblks.
+ */
+ for (int i = 0; i < mi->nr_blks; i++) {
+ struct numa_memblk *bi = &mi->blk[i];
+
+ if (start < bi->end && end >= bi->start) {
+ blk[count] = &mi->blk[i];
+ count++;
+ }
+ }
+ if (!count)
+ return NUMA_NO_MEMBLK;
+
+ /* Sort the list of pointers in memblk->start order */
+ sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL);
+
+ /* Make sure the first/last memblks include start/end */
+ blk[0]->start = min(blk[0]->start, start);
+ blk[count - 1]->end = max(blk[count - 1]->end, end);
+
+ /*
+ * Fill any gaps by tracking the previous memblks
+ * end address and backfilling to it if needed.
+ */
+ prev_end = blk[0]->end;
+ for (int i = 1; i < count; i++) {
+ struct numa_memblk *curr = blk[i];
+
+ if (prev_end >= curr->start) {
+ if (prev_end < curr->end)
+ prev_end = curr->end;
+ } else {
+ curr->start = prev_end;
+ prev_end = curr->end;
+ }
+ }
+ return 0;
+}
+
#endif
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 78414c6d1b5e..5dd733944629 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -69,6 +69,7 @@ static void __init pti_print_if_secure(const char *reason)
pr_info("%s\n", reason);
}
+/* Assume mode is auto unless overridden via cmdline below. */
static enum pti_mode {
PTI_AUTO = 0,
PTI_FORCE_OFF,
@@ -77,50 +78,49 @@ static enum pti_mode {
void __init pti_check_boottime_disable(void)
{
- char arg[5];
- int ret;
-
- /* Assume mode is auto unless overridden. */
- pti_mode = PTI_AUTO;
-
if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
pti_mode = PTI_FORCE_OFF;
pti_print_if_insecure("disabled on XEN PV.");
return;
}
- ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
- if (ret > 0) {
- if (ret == 3 && !strncmp(arg, "off", 3)) {
- pti_mode = PTI_FORCE_OFF;
- pti_print_if_insecure("disabled on command line.");
- return;
- }
- if (ret == 2 && !strncmp(arg, "on", 2)) {
- pti_mode = PTI_FORCE_ON;
- pti_print_if_secure("force enabled on command line.");
- goto enable;
- }
- if (ret == 4 && !strncmp(arg, "auto", 4)) {
- pti_mode = PTI_AUTO;
- goto autosel;
- }
- }
-
- if (cmdline_find_option_bool(boot_command_line, "nopti") ||
- cpu_mitigations_off()) {
+ if (cpu_mitigations_off())
pti_mode = PTI_FORCE_OFF;
+ if (pti_mode == PTI_FORCE_OFF) {
pti_print_if_insecure("disabled on command line.");
return;
}
-autosel:
- if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ if (pti_mode == PTI_FORCE_ON)
+ pti_print_if_secure("force enabled on command line.");
+
+ if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
return;
-enable:
+
setup_force_cpu_cap(X86_FEATURE_PTI);
}
+static int __init pti_parse_cmdline(char *arg)
+{
+ if (!strcmp(arg, "off"))
+ pti_mode = PTI_FORCE_OFF;
+ else if (!strcmp(arg, "on"))
+ pti_mode = PTI_FORCE_ON;
+ else if (!strcmp(arg, "auto"))
+ pti_mode = PTI_AUTO;
+ else
+ return -EINVAL;
+ return 0;
+}
+early_param("pti", pti_parse_cmdline);
+
+static int __init pti_parse_cmdline_nopti(char *arg)
+{
+ pti_mode = PTI_FORCE_OFF;
+ return 0;
+}
+early_param("nopti", pti_parse_cmdline_nopti);
+
pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
{
/*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a5930042139d..8c10d9abc239 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -16,6 +16,9 @@
#include <asm/set_memory.h>
#include <asm/nospec-branch.h>
#include <asm/text-patching.h>
+#include <asm/unwind.h>
+
+static bool all_callee_regs_used[4] = {true, true, true, true};
static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
{
@@ -255,6 +258,14 @@ struct jit_context {
/* Number of bytes that will be skipped on tailcall */
#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE)
+static void push_r12(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x54); /* push r12 */
+ *pprog = prog;
+}
+
static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
@@ -270,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used)
*pprog = prog;
}
+static void pop_r12(u8 **pprog)
+{
+ u8 *prog = *pprog;
+
+ EMIT2(0x41, 0x5C); /* pop r12 */
+ *pprog = prog;
+}
+
static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
{
u8 *prog = *pprog;
@@ -291,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used)
* while jumping to another program
*/
static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
- bool tail_call_reachable, bool is_subprog)
+ bool tail_call_reachable, bool is_subprog,
+ bool is_exception_cb)
{
u8 *prog = *pprog;
@@ -303,12 +323,30 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
prog += X86_PATCH_SIZE;
if (!ebpf_from_cbpf) {
if (tail_call_reachable && !is_subprog)
+ /* When it's the entry of the whole tailcall context,
+ * zeroing rax means initialising tail_call_cnt.
+ */
EMIT2(0x31, 0xC0); /* xor eax, eax */
else
+ /* Keep the same instruction layout. */
EMIT2(0x66, 0x90); /* nop2 */
}
- EMIT1(0x55); /* push rbp */
- EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+ /* Exception callback receives FP as third parameter */
+ if (is_exception_cb) {
+ EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */
+ EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */
+ /* The main frame must have exception_boundary as true, so we
+ * first restore those callee-saved regs from stack, before
+ * reusing the stack frame.
+ */
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ /* Reset the stack frame. */
+ EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */
+ } else {
+ EMIT1(0x55); /* push rbp */
+ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */
+ }
/* X86_TAIL_CALL_OFFSET is here */
EMIT_ENDBR();
@@ -467,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip)
* goto *(prog->bpf_func + prologue_size);
* out:
*/
-static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
+static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ u8 **pprog, bool *callee_regs_used,
u32 stack_depth, u8 *ip,
struct jit_context *ctx)
{
@@ -517,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
offset = ctx->tail_call_indirect_label - (prog + 2 - start);
EMIT2(X86_JE, offset); /* je out */
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
EMIT1(0x58); /* pop rax */
if (stack_depth)
@@ -541,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used,
*pprog = prog;
}
-static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
+static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+ struct bpf_jit_poke_descriptor *poke,
u8 **pprog, u8 *ip,
bool *callee_regs_used, u32 stack_depth,
struct jit_context *ctx)
@@ -570,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke,
emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
poke->tailcall_bypass);
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
+
EMIT1(0x58); /* pop rax */
if (stack_depth)
EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
@@ -1018,6 +1069,10 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
#define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
+/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
+#define RESTORE_TAIL_CALL_CNT(stack) \
+ EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8)
+
static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
int oldproglen, struct jit_context *ctx, bool jmp_padding)
{
@@ -1041,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image
emit_prologue(&prog, bpf_prog->aux->stack_depth,
bpf_prog_was_classic(bpf_prog), tail_call_reachable,
- bpf_prog->aux->func_idx != 0);
- push_callee_regs(&prog, callee_regs_used);
+ bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb);
+ /* Exception callback will clobber callee regs for its own use, and
+ * restore the original callee regs from main prog's stack frame.
+ */
+ if (bpf_prog->aux->exception_boundary) {
+ /* We also need to save r12, which is not mapped to any BPF
+ * register, as we throw after entry into the kernel, which may
+ * overwrite r12.
+ */
+ push_r12(&prog);
+ push_callee_regs(&prog, all_callee_regs_used);
+ } else {
+ push_callee_regs(&prog, callee_regs_used);
+ }
ilen = prog - temp;
if (rw_image)
@@ -1623,9 +1690,7 @@ st: if (is_imm8(insn->off))
func = (u8 *) __bpf_call_base + imm32;
if (tail_call_reachable) {
- /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
- EMIT3_off32(0x48, 0x8B, 0x85,
- -round_up(bpf_prog->aux->stack_depth, 8) - 8);
+ RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
if (!imm32)
return -EINVAL;
offs = 7 + x86_call_depth_emit_accounting(&prog, func);
@@ -1641,13 +1706,15 @@ st: if (is_imm8(insn->off))
case BPF_JMP | BPF_TAIL_CALL:
if (imm32)
- emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1],
+ emit_bpf_tail_call_direct(bpf_prog,
+ &bpf_prog->aux->poke_tab[imm32 - 1],
&prog, image + addrs[i - 1],
callee_regs_used,
bpf_prog->aux->stack_depth,
ctx);
else
- emit_bpf_tail_call_indirect(&prog,
+ emit_bpf_tail_call_indirect(bpf_prog,
+ &prog,
callee_regs_used,
bpf_prog->aux->stack_depth,
image + addrs[i - 1],
@@ -1900,7 +1967,12 @@ emit_jmp:
seen_exit = true;
/* Update cleanup_addr */
ctx->cleanup_addr = proglen;
- pop_callee_regs(&prog, callee_regs_used);
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+ } else {
+ pop_callee_regs(&prog, callee_regs_used);
+ }
EMIT1(0xC9); /* leave */
emit_return(&prog, image + addrs[i - 1] + (prog - temp));
break;
@@ -2400,6 +2472,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
* [ ... ]
* [ stack_arg2 ]
* RBP - arg_stack_off [ stack_arg1 ]
+ * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX
*/
/* room for return value of orig_call or fentry prog */
@@ -2464,6 +2537,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
else
/* sub rsp, stack_size */
EMIT4(0x48, 0x83, 0xEC, stack_size);
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ EMIT1(0x50); /* push rax */
/* mov QWORD PTR [rbp - rbx_off], rbx */
emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off);
@@ -2516,9 +2591,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
restore_regs(m, &prog, regs_off);
save_args(m, &prog, arg_stack_off, true);
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ /* Before calling the original function, restore the
+ * tail_call_cnt from stack to rax.
+ */
+ RESTORE_TAIL_CALL_CNT(stack_size);
+
if (flags & BPF_TRAMP_F_ORIG_STACK) {
- emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
- EMIT2(0xff, 0xd0); /* call *rax */
+ emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8);
+ EMIT2(0xff, 0xd3); /* call *rbx */
} else {
/* call original function */
if (emit_rsb_call(&prog, orig_call, prog)) {
@@ -2569,7 +2650,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
ret = -EINVAL;
goto cleanup;
}
- }
+ } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX)
+ /* Before running the original function, restore the
+ * tail_call_cnt from stack to rax.
+ */
+ RESTORE_TAIL_CALL_CNT(stack_size);
+
/* restore return value of orig_call or fentry prog back into RAX */
if (save_ret)
emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
@@ -2913,3 +2999,29 @@ void bpf_jit_free(struct bpf_prog *prog)
bpf_prog_unlock_free(prog);
}
+
+bool bpf_jit_supports_exceptions(void)
+{
+ /* We unwind through both kernel frames (starting from within bpf_throw
+ * call) and BPF frames. Therefore we require ORC unwinder to be enabled
+ * to walk kernel frames and reach BPF frames in the stack trace.
+ */
+ return IS_ENABLED(CONFIG_UNWINDER_ORC);
+}
+
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie)
+{
+#if defined(CONFIG_UNWINDER_ORC)
+ struct unwind_state state;
+ unsigned long addr;
+
+ for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state);
+ unwind_next_frame(&state)) {
+ addr = unwind_get_return_address(&state);
+ if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp))
+ break;
+ }
+ return;
+#endif
+ WARN(1, "verification of programs using bpf_throw should have failed\n");
+}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e06a199423c0..b2cc7b4552a1 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -140,3 +140,15 @@ void __init efi_runtime_update_mappings(void)
}
}
}
+
+void arch_efi_call_virt_setup(void)
+{
+ efi_fpu_begin();
+ firmware_restrict_branch_speculation_start();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+ firmware_restrict_branch_speculation_end();
+ efi_fpu_end();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77f7ac3668cb..91d31ac422d6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -474,19 +474,34 @@ void __init efi_dump_pagetable(void)
* can not change under us.
* It should be ensured that there are no concurrent calls to this function.
*/
-void efi_enter_mm(void)
+static void efi_enter_mm(void)
{
efi_prev_mm = current->active_mm;
current->active_mm = &efi_mm;
switch_mm(efi_prev_mm, &efi_mm, NULL);
}
-void efi_leave_mm(void)
+static void efi_leave_mm(void)
{
current->active_mm = efi_prev_mm;
switch_mm(&efi_mm, efi_prev_mm, NULL);
}
+void arch_efi_call_virt_setup(void)
+{
+ efi_sync_low_kernel_mappings();
+ efi_fpu_begin();
+ firmware_restrict_branch_speculation_start();
+ efi_enter_mm();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+ efi_leave_mm();
+ firmware_restrict_branch_speculation_end();
+ efi_fpu_end();
+}
+
static DEFINE_SPINLOCK(efi_runtime_lock);
/*
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index 45d0c17ce77c..e03207de2880 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -17,6 +17,7 @@
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/slab.h>
+#include <linux/string.h>
#include <linux/clocksource.h>
#include <asm/apic.h>
@@ -178,49 +179,56 @@ module_param_named(debug, uv_nmi_debug, int, 0644);
} while (0)
/* Valid NMI Actions */
-#define ACTION_LEN 16
-static struct nmi_action {
- char *action;
- char *desc;
-} valid_acts[] = {
- { "kdump", "do kernel crash dump" },
- { "dump", "dump process stack for each cpu" },
- { "ips", "dump Inst Ptr info for each cpu" },
- { "kdb", "enter KDB (needs kgdboc= assignment)" },
- { "kgdb", "enter KGDB (needs gdb target remote)" },
- { "health", "check if CPUs respond to NMI" },
+enum action_t {
+ nmi_act_kdump,
+ nmi_act_dump,
+ nmi_act_ips,
+ nmi_act_kdb,
+ nmi_act_kgdb,
+ nmi_act_health,
+ nmi_act_max
};
-typedef char action_t[ACTION_LEN];
-static action_t uv_nmi_action = { "dump" };
+
+static const char * const actions[nmi_act_max] = {
+ [nmi_act_kdump] = "kdump",
+ [nmi_act_dump] = "dump",
+ [nmi_act_ips] = "ips",
+ [nmi_act_kdb] = "kdb",
+ [nmi_act_kgdb] = "kgdb",
+ [nmi_act_health] = "health",
+};
+
+static const char * const actions_desc[nmi_act_max] = {
+ [nmi_act_kdump] = "do kernel crash dump",
+ [nmi_act_dump] = "dump process stack for each cpu",
+ [nmi_act_ips] = "dump Inst Ptr info for each cpu",
+ [nmi_act_kdb] = "enter KDB (needs kgdboc= assignment)",
+ [nmi_act_kgdb] = "enter KGDB (needs gdb target remote)",
+ [nmi_act_health] = "check if CPUs respond to NMI",
+};
+
+static enum action_t uv_nmi_action = nmi_act_dump;
static int param_get_action(char *buffer, const struct kernel_param *kp)
{
- return sprintf(buffer, "%s\n", uv_nmi_action);
+ return sprintf(buffer, "%s\n", actions[uv_nmi_action]);
}
static int param_set_action(const char *val, const struct kernel_param *kp)
{
- int i;
- int n = ARRAY_SIZE(valid_acts);
- char arg[ACTION_LEN];
-
- /* (remove possible '\n') */
- strscpy(arg, val, strnchrnul(val, sizeof(arg)-1, '\n') - val + 1);
-
- for (i = 0; i < n; i++)
- if (!strcmp(arg, valid_acts[i].action))
- break;
+ int i, n = ARRAY_SIZE(actions);
- if (i < n) {
- strscpy(uv_nmi_action, arg, sizeof(uv_nmi_action));
- pr_info("UV: New NMI action:%s\n", uv_nmi_action);
+ i = sysfs_match_string(actions, val);
+ if (i >= 0) {
+ uv_nmi_action = i;
+ pr_info("UV: New NMI action:%s\n", actions[i]);
return 0;
}
- pr_err("UV: Invalid NMI action:%s, valid actions are:\n", arg);
+ pr_err("UV: Invalid NMI action. Valid actions are:\n");
for (i = 0; i < n; i++)
- pr_err("UV: %-8s - %s\n",
- valid_acts[i].action, valid_acts[i].desc);
+ pr_err("UV: %-8s - %s\n", actions[i], actions_desc[i]);
+
return -EINVAL;
}
@@ -228,15 +236,10 @@ static const struct kernel_param_ops param_ops_action = {
.get = param_get_action,
.set = param_set_action,
};
-#define param_check_action(name, p) __param_check(name, p, action_t)
+#define param_check_action(name, p) __param_check(name, p, enum action_t)
module_param_named(action, uv_nmi_action, action, 0644);
-static inline bool uv_nmi_action_is(const char *action)
-{
- return (strncmp(uv_nmi_action, action, strlen(action)) == 0);
-}
-
/* Setup which NMI support is present in system */
static void uv_nmi_setup_mmrs(void)
{
@@ -727,10 +730,10 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs)
if (cpu == 0)
uv_nmi_dump_cpu_ip_hdr();
- if (current->pid != 0 || !uv_nmi_action_is("ips"))
+ if (current->pid != 0 || uv_nmi_action != nmi_act_ips)
uv_nmi_dump_cpu_ip(cpu, regs);
- if (uv_nmi_action_is("dump")) {
+ if (uv_nmi_action == nmi_act_dump) {
pr_info("UV:%sNMI process trace for CPU %d\n", dots, cpu);
show_regs(regs);
}
@@ -798,7 +801,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master)
int saved_console_loglevel = console_loglevel;
pr_alert("UV: tracing %s for %d CPUs from CPU %d\n",
- uv_nmi_action_is("ips") ? "IPs" : "processes",
+ uv_nmi_action == nmi_act_ips ? "IPs" : "processes",
atomic_read(&uv_nmi_cpus_in_nmi), cpu);
console_loglevel = uv_nmi_loglevel;
@@ -874,7 +877,7 @@ static inline int uv_nmi_kdb_reason(void)
static inline int uv_nmi_kdb_reason(void)
{
/* Ensure user is expecting to attach gdb remote */
- if (uv_nmi_action_is("kgdb"))
+ if (uv_nmi_action == nmi_act_kgdb)
return 0;
pr_err("UV: NMI error: KDB is not enabled in this kernel\n");
@@ -950,28 +953,35 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
master = (atomic_read(&uv_nmi_cpu) == cpu);
/* If NMI action is "kdump", then attempt to do it */
- if (uv_nmi_action_is("kdump")) {
+ if (uv_nmi_action == nmi_act_kdump) {
uv_nmi_kdump(cpu, master, regs);
/* Unexpected return, revert action to "dump" */
if (master)
- strscpy(uv_nmi_action, "dump", sizeof(uv_nmi_action));
+ uv_nmi_action = nmi_act_dump;
}
/* Pause as all CPU's enter the NMI handler */
uv_nmi_wait(master);
/* Process actions other than "kdump": */
- if (uv_nmi_action_is("health")) {
+ switch (uv_nmi_action) {
+ case nmi_act_health:
uv_nmi_action_health(cpu, regs, master);
- } else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) {
+ break;
+ case nmi_act_ips:
+ case nmi_act_dump:
uv_nmi_dump_state(cpu, regs, master);
- } else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) {
+ break;
+ case nmi_act_kdb:
+ case nmi_act_kgdb:
uv_call_kgdb_kdb(cpu, regs, master);
- } else {
+ break;
+ default:
if (master)
- pr_alert("UV: unknown NMI action: %s\n", uv_nmi_action);
+ pr_alert("UV: unknown NMI action: %d\n", uv_nmi_action);
uv_nmi_sync_exit(master);
+ break;
}
/* Clear per_cpu "in_nmi" flag */
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 54663f3e00cb..ff5afc8a5a41 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -53,7 +53,7 @@ struct uv_rtc_timer_head {
struct {
int lcpu; /* systemwide logical cpu number */
u64 expires; /* next timer expiration for this cpu */
- } cpu[];
+ } cpu[] __counted_by(ncpus);
};
/*
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index c2a29be35c01..08aa0f25f12a 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
# optimization flags.
KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
+# When LTO is enabled, llvm emits many text sections, which is not supported
+# by kexec. Remove -flto=* flags.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+
# When linking purgatory.ro with -r unresolved symbols are not checked,
# also link a purgatory.chk binary without -r to check for unresolved symbols.
PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index 7ad91225fdf4..9dd5490b3318 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -33,13 +33,13 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
return 0xfd;
}
-static u32 xen_set_apic_id(unsigned int x)
+static u32 xen_set_apic_id(u32 x)
{
WARN_ON(1);
return x;
}
-static unsigned int xen_get_apic_id(unsigned long x)
+static u32 xen_get_apic_id(u32 x)
{
return ((x)>>24) & 0xFFu;
}
@@ -110,15 +110,15 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
return xen_pv_domain();
}
-static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
+static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb)
{
return initial_apic_id >> index_msb;
}
-static int xen_cpu_present_to_apicid(int cpu)
+static u32 xen_cpu_present_to_apicid(int cpu)
{
if (cpu_present(cpu))
- return cpu_data(cpu).apicid;
+ return cpu_data(cpu).topo.apicid;
else
return BAD_APICID;
}
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 863d0d6b3edc..7250d0e0e1a9 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -138,7 +138,7 @@ void __init xen_efi_init(struct boot_params *boot_params)
if (efi_systab_xen == NULL)
return;
- strncpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
+ strscpy((char *)&boot_params->efi_info.efi_loader_signature, "Xen",
sizeof(boot_params->efi_info.efi_loader_signature));
boot_params->efi_info.efi_systab = (__u32)__pa(efi_systab_xen);
boot_params->efi_info.efi_systab_hi = (__u32)(__pa(efi_systab_xen) >> 32);
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b8db2148c07d..0337392a3121 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -32,7 +32,7 @@ EXPORT_SYMBOL_GPL(hypercall_page);
* &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
* and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
* but during boot it is switched to point to xen_vcpu_info.
- * The pointer is used in __xen_evtchn_do_upcall to acknowledge pending events.
+ * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events.
*/
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9a192f51f1b0..3f8c34707c50 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -136,7 +136,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_xen_hvm_callback)
inc_irq_stat(irq_hv_callback_count);
- xen_hvm_evtchn_do_upcall();
+ xen_evtchn_do_upcall();
set_irq_regs(old_regs);
}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 49352fad7d1d..bbbfdd495ebd 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -101,6 +101,17 @@ struct tls_descs {
struct desc_struct desc[3];
};
+DEFINE_PER_CPU(enum xen_lazy_mode, xen_lazy_mode) = XEN_LAZY_NONE;
+DEFINE_PER_CPU(unsigned int, xen_lazy_nesting);
+
+enum xen_lazy_mode xen_get_lazy_mode(void)
+{
+ if (in_interrupt())
+ return XEN_LAZY_NONE;
+
+ return this_cpu_read(xen_lazy_mode);
+}
+
/*
* Updating the 3 TLS descriptors in the GDT on every task switch is
* surprisingly expensive so we avoid updating them if they haven't
@@ -362,10 +373,25 @@ static noinstr unsigned long xen_get_debugreg(int reg)
return HYPERVISOR_get_debugreg(reg);
}
+static void xen_start_context_switch(struct task_struct *prev)
+{
+ BUG_ON(preemptible());
+
+ if (this_cpu_read(xen_lazy_mode) == XEN_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ set_ti_thread_flag(task_thread_info(prev), TIF_LAZY_MMU_UPDATES);
+ }
+ enter_lazy(XEN_LAZY_CPU);
+}
+
static void xen_end_context_switch(struct task_struct *next)
{
+ BUG_ON(preemptible());
+
xen_mc_flush();
- paravirt_end_context_switch(next);
+ leave_lazy(XEN_LAZY_CPU);
+ if (test_and_clear_ti_thread_flag(task_thread_info(next), TIF_LAZY_MMU_UPDATES))
+ arch_enter_lazy_mmu_mode();
}
static unsigned long xen_store_tr(void)
@@ -472,7 +498,7 @@ static void xen_set_ldt(const void *addr, unsigned entries)
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ xen_mc_issue(XEN_LAZY_CPU);
}
static void xen_load_gdt(const struct desc_ptr *dtr)
@@ -568,7 +594,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
* exception between the new %fs descriptor being loaded and
* %fs being effectively cleared at __switch_to().
*/
- if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)
+ if (xen_get_lazy_mode() == XEN_LAZY_CPU)
loadsegment(fs, 0);
xen_mc_batch();
@@ -577,7 +603,7 @@ static void xen_load_tls(struct thread_struct *t, unsigned int cpu)
load_TLS_descriptor(t, cpu, 1);
load_TLS_descriptor(t, cpu, 2);
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ xen_mc_issue(XEN_LAZY_CPU);
}
static void xen_load_gs_index(unsigned int idx)
@@ -909,7 +935,7 @@ static void xen_load_sp0(unsigned long sp0)
mcs = xen_mc_entry(0);
MULTI_stack_switch(mcs.mc, __KERNEL_DS, sp0);
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ xen_mc_issue(XEN_LAZY_CPU);
this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
}
@@ -973,7 +999,7 @@ static void xen_write_cr0(unsigned long cr0)
MULTI_fpu_taskswitch(mcs.mc, (cr0 & X86_CR0_TS) != 0);
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ xen_mc_issue(XEN_LAZY_CPU);
}
static void xen_write_cr4(unsigned long cr4)
@@ -1156,7 +1182,7 @@ static const typeof(pv_ops) xen_cpu_ops __initconst = {
#endif
.io_delay = xen_io_delay,
- .start_context_switch = paravirt_start_context_switch,
+ .start_context_switch = xen_start_context_switch,
.end_context_switch = xen_end_context_switch,
},
};
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 1652c39e3dfb..b6830554ff69 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -236,7 +236,7 @@ static void xen_set_pmd_hyper(pmd_t *ptr, pmd_t val)
u.val = pmd_val_ma(val);
xen_extend_mmu_update(&u);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
@@ -270,7 +270,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
{
struct mmu_update u;
- if (paravirt_get_lazy_mode() != PARAVIRT_LAZY_MMU)
+ if (xen_get_lazy_mode() != XEN_LAZY_MMU)
return false;
xen_mc_batch();
@@ -279,7 +279,7 @@ static bool xen_batched_set_pte(pte_t *ptep, pte_t pteval)
u.val = pte_val_ma(pteval);
xen_extend_mmu_update(&u);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
return true;
}
@@ -325,7 +325,7 @@ void xen_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr,
u.val = pte_val_ma(pte);
xen_extend_mmu_update(&u);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
}
/* Assume pteval_t is equivalent to all the other *val_t types. */
@@ -419,7 +419,7 @@ static void xen_set_pud_hyper(pud_t *ptr, pud_t val)
u.val = pud_val_ma(val);
xen_extend_mmu_update(&u);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
@@ -499,7 +499,7 @@ static void __init xen_set_p4d_hyper(p4d_t *ptr, p4d_t val)
__xen_set_p4d_hyper(ptr, val);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
@@ -531,7 +531,7 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
if (user_ptr)
__xen_set_p4d_hyper((p4d_t *)user_ptr, val);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
}
#if CONFIG_PGTABLE_LEVELS >= 5
@@ -1245,7 +1245,7 @@ static noinline void xen_flush_tlb(void)
op->cmd = MMUEXT_TLB_FLUSH_LOCAL;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
@@ -1265,7 +1265,7 @@ static void xen_flush_tlb_one_user(unsigned long addr)
op->arg1.linear_addr = addr & PAGE_MASK;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
@@ -1302,7 +1302,7 @@ static void xen_flush_tlb_multi(const struct cpumask *cpus,
MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
}
static unsigned long xen_read_cr3(void)
@@ -1361,7 +1361,7 @@ static void xen_write_cr3(unsigned long cr3)
else
__xen_write_cr3(false, 0);
- xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
+ xen_mc_issue(XEN_LAZY_CPU); /* interrupts restored */
}
/*
@@ -1396,7 +1396,7 @@ static void __init xen_write_cr3_init(unsigned long cr3)
__xen_write_cr3(true, cr3);
- xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
+ xen_mc_issue(XEN_LAZY_CPU); /* interrupts restored */
}
static int xen_pgd_alloc(struct mm_struct *mm)
@@ -1557,7 +1557,7 @@ static inline void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn,
if (level == PT_PTE && USE_SPLIT_PTE_PTLOCKS && !pinned)
__pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
}
}
@@ -1587,7 +1587,7 @@ static inline void xen_release_ptpage(unsigned long pfn, unsigned level)
__set_pfn_prot(pfn, PAGE_KERNEL);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
ClearPagePinned(page);
}
@@ -1804,7 +1804,7 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
*/
xen_mc_batch();
__xen_write_cr3(true, __pa(init_top_pgt));
- xen_mc_issue(PARAVIRT_LAZY_CPU);
+ xen_mc_issue(XEN_LAZY_CPU);
/* We can't that easily rip out L3 and L2, as the Xen pagetables are
* set out this way: [L4], [L1], [L2], [L3], [L1], [L1] ... for
@@ -2083,6 +2083,23 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
#endif
}
+static void xen_enter_lazy_mmu(void)
+{
+ enter_lazy(XEN_LAZY_MMU);
+}
+
+static void xen_flush_lazy_mmu(void)
+{
+ preempt_disable();
+
+ if (xen_get_lazy_mode() == XEN_LAZY_MMU) {
+ arch_leave_lazy_mmu_mode();
+ arch_enter_lazy_mmu_mode();
+ }
+
+ preempt_enable();
+}
+
static void __init xen_post_allocator_init(void)
{
pv_ops.mmu.set_pte = xen_set_pte;
@@ -2107,7 +2124,7 @@ static void xen_leave_lazy_mmu(void)
{
preempt_disable();
xen_mc_flush();
- paravirt_leave_lazy_mmu();
+ leave_lazy(XEN_LAZY_MMU);
preempt_enable();
}
@@ -2166,9 +2183,9 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
.exit_mmap = xen_exit_mmap,
.lazy_mode = {
- .enter = paravirt_enter_lazy_mmu,
+ .enter = xen_enter_lazy_mmu,
.leave = xen_leave_lazy_mmu,
- .flush = paravirt_flush_lazy_mmu,
+ .flush = xen_flush_lazy_mmu,
},
.set_fixmap = xen_set_fixmap,
@@ -2385,7 +2402,7 @@ static noinline void xen_flush_tlb_all(void)
op->cmd = MMUEXT_TLB_FLUSH_ALL;
MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- xen_mc_issue(PARAVIRT_LAZY_MMU);
+ xen_mc_issue(XEN_LAZY_MMU);
preempt_enable();
}
diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 1c51b2c87f30..c3867b585e0d 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -26,7 +26,7 @@ static inline void xen_mc_batch(void)
/* need to disable interrupts until this entry is complete */
local_irq_save(flags);
- trace_xen_mc_batch(paravirt_get_lazy_mode());
+ trace_xen_mc_batch(xen_get_lazy_mode());
__this_cpu_write(xen_mc_irq_flags, flags);
}
@@ -44,7 +44,7 @@ static inline void xen_mc_issue(unsigned mode)
{
trace_xen_mc_issue(mode);
- if ((paravirt_get_lazy_mode() & mode) == 0)
+ if ((xen_get_lazy_mode() & mode) == 0)
xen_mc_flush();
/* restore flags saved in xen_mc_batch */
diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index a65b7a9ebff2..d8b0fadf429a 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -9,8 +9,7 @@
# KBUILD_CFLAGS used when building rest of boot (takes effect recursively)
-KBUILD_CFLAGS += -fno-builtin -Iarch/$(ARCH)/boot/include
-HOSTFLAGS += -Iarch/$(ARCH)/boot/include
+KBUILD_CFLAGS += -fno-builtin
subdir-y := lib
targets += vmlinux.bin vmlinux.bin.gz
diff --git a/arch/xtensa/boot/lib/zmem.c b/arch/xtensa/boot/lib/zmem.c
index e3ecd743c515..b89189355122 100644
--- a/arch/xtensa/boot/lib/zmem.c
+++ b/arch/xtensa/boot/lib/zmem.c
@@ -4,13 +4,14 @@
/* bits taken from ppc */
extern void *avail_ram, *end_avail;
+void gunzip(void *dst, int dstlen, unsigned char *src, int *lenp);
-void exit (void)
+static void exit(void)
{
for (;;);
}
-void *zalloc(unsigned size)
+static void *zalloc(unsigned int size)
{
void *p = avail_ram;
diff --git a/arch/xtensa/include/asm/core.h b/arch/xtensa/include/asm/core.h
index 3f5ffae89b58..6f02f6f21890 100644
--- a/arch/xtensa/include/asm/core.h
+++ b/arch/xtensa/include/asm/core.h
@@ -6,6 +6,10 @@
#include <variant/core.h>
+#ifndef XCHAL_HAVE_DIV32
+#define XCHAL_HAVE_DIV32 0
+#endif
+
#ifndef XCHAL_HAVE_EXCLUSIVE
#define XCHAL_HAVE_EXCLUSIVE 0
#endif
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index 9f119c1ca0b5..9ec86f440a48 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -48,6 +48,7 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp);
void hw_breakpoint_pmu_read(struct perf_event *bp);
int check_hw_breakpoint(struct pt_regs *regs);
void clear_ptrace_hw_breakpoint(struct task_struct *tsk);
+void restore_dbreak(void);
#else
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index a6d09fe04831..d008a153a2b9 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -14,6 +14,8 @@
#include <linux/compiler.h>
#include <linux/stringify.h>
+
+#include <asm/bootparam.h>
#include <asm/ptrace.h>
#include <asm/types.h>
#include <asm/regs.h>
@@ -217,6 +219,9 @@ struct mm_struct;
extern unsigned long __get_wchan(struct task_struct *p);
+void init_arch(bp_tag_t *bp_start);
+void do_notify_resume(struct pt_regs *regs);
+
#define KSTK_EIP(tsk) (task_pt_regs(tsk)->pc)
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1])
diff --git a/arch/xtensa/include/asm/ptrace.h b/arch/xtensa/include/asm/ptrace.h
index 308f209a4740..a270467556dc 100644
--- a/arch/xtensa/include/asm/ptrace.h
+++ b/arch/xtensa/include/asm/ptrace.h
@@ -106,6 +106,9 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
return regs->areg[2];
}
+int do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
#else /* __ASSEMBLY__ */
# include <asm/asm-offsets.h>
diff --git a/arch/xtensa/include/asm/smp.h b/arch/xtensa/include/asm/smp.h
index 5dc5bf8cdd77..e446e6fc4557 100644
--- a/arch/xtensa/include/asm/smp.h
+++ b/arch/xtensa/include/asm/smp.h
@@ -23,6 +23,7 @@ struct cpumask;
void arch_send_call_function_ipi_mask(const struct cpumask *mask);
void arch_send_call_function_single_ipi(int cpu);
+void secondary_start_kernel(void);
void smp_init_cpus(void);
void secondary_init_irq(void);
void ipi_init(void);
diff --git a/arch/xtensa/include/asm/tlb.h b/arch/xtensa/include/asm/tlb.h
index 50889935138a..8c3ceb427018 100644
--- a/arch/xtensa/include/asm/tlb.h
+++ b/arch/xtensa/include/asm/tlb.h
@@ -18,4 +18,6 @@
#define __pte_free_tlb(tlb, pte, address) pte_free((tlb)->mm, pte)
+void check_tlb_sanity(void);
+
#endif /* _XTENSA_TLB_H */
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index 285fb2942b06..1eeecd58eb0c 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -13,6 +13,7 @@
#include <linux/percpu.h>
#include <linux/perf_event.h>
#include <asm/core.h>
+#include <asm/hw_breakpoint.h>
/* Breakpoint currently in use for each IBREAKA. */
static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[XCHAL_NUM_IBREAK]);
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 42f106004400..b1e410f6b5ab 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -28,6 +28,7 @@
#include <asm/mxregs.h>
#include <linux/uaccess.h>
#include <asm/platform.h>
+#include <asm/traps.h>
DECLARE_PER_CPU(unsigned long, nmi_count);
diff --git a/arch/xtensa/kernel/ptrace.c b/arch/xtensa/kernel/ptrace.c
index f29477162ede..9056cd1a8302 100644
--- a/arch/xtensa/kernel/ptrace.c
+++ b/arch/xtensa/kernel/ptrace.c
@@ -541,7 +541,6 @@ long arch_ptrace(struct task_struct *child, long request,
return ret;
}
-void do_syscall_trace_leave(struct pt_regs *regs);
int do_syscall_trace_enter(struct pt_regs *regs)
{
if (regs->syscall == NO_SYSCALL)
diff --git a/arch/xtensa/kernel/signal.c b/arch/xtensa/kernel/signal.c
index 5c01d7e70d90..81f0b106cfc1 100644
--- a/arch/xtensa/kernel/signal.c
+++ b/arch/xtensa/kernel/signal.c
@@ -26,6 +26,8 @@
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/coprocessor.h>
+#include <asm/processor.h>
+#include <asm/syscall.h>
#include <asm/unistd.h>
extern struct task_struct *coproc_owners[];
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 07dd6baf18cf..94a23f100726 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -21,6 +21,7 @@
#include <linux/irq.h>
#include <linux/kdebug.h>
#include <linux/module.h>
+#include <linux/profile.h>
#include <linux/sched/mm.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task_stack.h>
diff --git a/arch/xtensa/kernel/stacktrace.c b/arch/xtensa/kernel/stacktrace.c
index f643ea5e36da..831ffb648bda 100644
--- a/arch/xtensa/kernel/stacktrace.c
+++ b/arch/xtensa/kernel/stacktrace.c
@@ -12,6 +12,7 @@
#include <linux/sched.h>
#include <linux/stacktrace.h>
+#include <asm/ftrace.h>
#include <asm/stacktrace.h>
#include <asm/traps.h>
#include <linux/uaccess.h>
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index fc1a4f3c81d9..dd71ecce8b86 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -423,3 +423,6 @@
450 common set_mempolicy_home_node sys_set_mempolicy_home_node
451 common cachestat sys_cachestat
452 common fchmodat2 sys_fchmodat2
+454 common futex_wake sys_futex_wake
+455 common futex_wait sys_futex_wait
+456 common futex_requeue sys_futex_requeue
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 427c125a137a..38092d21acf8 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -23,6 +23,7 @@
* for more details.
*/
+#include <linux/cpu.h>
#include <linux/kernel.h>
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
diff --git a/arch/xtensa/lib/umulsidi3.S b/arch/xtensa/lib/umulsidi3.S
index 8c7a94a0c5d0..5da501b57813 100644
--- a/arch/xtensa/lib/umulsidi3.S
+++ b/arch/xtensa/lib/umulsidi3.S
@@ -3,7 +3,9 @@
#include <asm/asmmacro.h>
#include <asm/core.h>
-#if !XCHAL_HAVE_MUL16 && !XCHAL_HAVE_MUL32 && !XCHAL_HAVE_MAC16
+#if XCHAL_HAVE_MUL16 || XCHAL_HAVE_MUL32 || XCHAL_HAVE_MAC16
+#define XCHAL_NO_MUL 0
+#else
#define XCHAL_NO_MUL 1
#endif
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index d1eb8d6c5b82..16e11b6f6f78 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -20,6 +20,7 @@
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/hardirq.h>
+#include <asm/traps.h>
void bad_page_fault(struct pt_regs*, unsigned long, int);
diff --git a/arch/xtensa/mm/tlb.c b/arch/xtensa/mm/tlb.c
index 0a11fc5f185b..4f974b74883c 100644
--- a/arch/xtensa/mm/tlb.c
+++ b/arch/xtensa/mm/tlb.c
@@ -17,6 +17,7 @@
#include <linux/mm.h>
#include <asm/processor.h>
#include <asm/mmu_context.h>
+#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c
index 85c82cd42188..e89f27f2bb18 100644
--- a/arch/xtensa/platforms/iss/network.c
+++ b/arch/xtensa/platforms/iss/network.c
@@ -201,7 +201,7 @@ static int tuntap_write(struct iss_net_private *lp, struct sk_buff **skb)
return simc_write(lp->tp.info.tuntap.fd, (*skb)->data, (*skb)->len);
}
-unsigned short tuntap_protocol(struct sk_buff *skb)
+static unsigned short tuntap_protocol(struct sk_buff *skb)
{
return eth_type_trans(skb, skb->dev);
}
@@ -441,7 +441,7 @@ static int iss_net_change_mtu(struct net_device *dev, int new_mtu)
return -EINVAL;
}
-void iss_net_user_timer_expire(struct timer_list *unused)
+static void iss_net_user_timer_expire(struct timer_list *unused)
{
}